Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Improve double buffering batched gemm perf for matrix sizes >64x64 #1239

Merged
merged 17 commits into from
Jan 7, 2022
Merged

Improve double buffering batched gemm perf for matrix sizes >64x64 #1239

merged 17 commits into from
Jan 7, 2022

Conversation

vqd8a
Copy link
Contributor

@vqd8a vqd8a commented Dec 19, 2021 •
edited
Loading

Not multiplying with alpha in matrix multiplication, but when storing results back to global memory instead.
Some perf numbers with batch_size=32768 on V100 GPU

Matrix Size 32x32 40x40 60x60 64x64 70x70 80x80 96x96 110x110 120x120 128x128 135x135
GFLOPS (before) 1552 1057 2055 2696 1580 2033 2943 2197 2621 3084 2196
GFLOPS (after) 1567 1244 2199 2857 1908 2463 3630 2686 3210 3830 2745

@vqd8a vqd8a requested a review from e10harvey December 19, 2021 21:42
@kokkos-devops-admin
Copy link

Status Flag 'Pre-Test Inspection' - Auto Inspected - Inspection Is Not Necessary for this Pull Request.

@vqd8a vqd8a changed the title Improve double buffering batched gemm for matrix sizes >64 Improve double buffering batched gemm for matrix sizes >64x64 Dec 19, 2021
@vqd8a vqd8a changed the title Improve double buffering batched gemm for matrix sizes >64x64 Improve double buffering batched gemm perf for matrix sizes >64x64 Dec 19, 2021
@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Failure: Timed out waiting for job KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740 to start: Total Wait = 3603

  • Other jobs have been previously started - We must stop them...

e10harvey
e10harvey requested changes Dec 22, 2021
View reviewed changes
Copy link
Contributor

@e10harvey e10harvey left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you, @vqd8a !

I am seeing an improvement with these changes after 16384x64x64 but a performance regression before 16384x66x66. Can you please add some overload wrappers and tags to select this alpha change for matrices > 64x64?

@e10harvey e10harvey mentioned this pull request Dec 23, 2021
Merged
@e10harvey
Copy link
Contributor

@vqd8a, using https://github.com/e10harvey/kokkos-kernels/tree/6a28191eeb729cea1c8320851bb5acc88b5c2098, I am seeing:

access_view_bounds_check (using KOKKOSKERNELS_MACRO_MIN)

$ export OMP_PROC_BIND=true; ./KokkosBlas3_perf_test --gemm_scalars=0.43,0.34 --test=batched_heuristic --routines=gemm --loop_type=parallel --batch_size_last_dim=0 --matrix_size_start=2x2,2x2,2x2 --matrix_size_stop=128x128,128x128,128x128 --matrix_size_step=2 --batch_size=$((2048*4)) --warm_up_loop=5 --iter=10 --verify=0

Kokkos::Cuda::initialize WARNING: Cuda is allocating into UVMSpace by default
                                  without setting CUDA_MANAGED_FORCE_DEVICE_ALLOC=1 or
                                  setting CUDA_VISIBLE_DEVICES.
                                  This could on multi GPU systems lead to severe performance"
                                  penalties.
Testing gemm...
SCALAR:d, LAYOUT:N6Kokkos11LayoutRightE, DEVICE:N6Kokkos4CudaE, SPACE:N6Kokkos12CudaUVMSpaceE
algorithm vector_type transAtransB alpha beta team_size vector_len loop_type A_dims B_dims C_dims warm_up_n iter total_time(s) average_time(s) FLOPS GFLOP/average_time(s)
batched_heuristic - NN 0.43 0.34 - - parallel 8192x2x2 8192x2x2 8192x2x2 5 10 5.8656e-05 5.8656e-06 131072 22.3459
batched_heuristic - NN 0.43 0.34 - - parallel 8192x4x4 8192x4x4 8192x4x4 5 10 6.6028e-05 6.6028e-06 1.04858e+06 158.808
batched_heuristic - NN 0.43 0.34 - - parallel 8192x6x6 8192x6x6 8192x6x6 5 10 0.000151316 1.51316e-05 3.53894e+06 233.878
batched_heuristic - NN 0.43 0.34 - - parallel 8192x8x8 8192x8x8 8192x8x8 5 10 0.000287888 2.87888e-05 8.38861e+06 291.384
batched_heuristic - NN 0.43 0.34 - - parallel 8192x10x10 8192x10x10 8192x10x10 5 10 0.000466388 4.66388e-05 1.6384e+07 351.295
batched_heuristic - NN 0.43 0.34 - - parallel 8192x12x12 8192x12x12 8192x12x12 5 10 0.000609122 6.09122e-05 2.83116e+07 464.793
batched_heuristic - NN 0.43 0.34 - - parallel 8192x14x14 8192x14x14 8192x14x14 5 10 0.000903219 9.03219e-05 4.49577e+07 497.75
batched_heuristic - NN 0.43 0.34 - - parallel 8192x16x16 8192x16x16 8192x16x16 5 10 0.00117125 0.000117125 6.71089e+07 572.967
batched_heuristic - NN 0.43 0.34 - - parallel 8192x18x18 8192x18x18 8192x18x18 5 10 0.00177529 0.000177529 9.55515e+07 538.23
batched_heuristic - NN 0.43 0.34 - - parallel 8192x20x20 8192x20x20 8192x20x20 5 10 0.00190465 0.000190465 1.31072e+08 688.168
batched_heuristic - NN 0.43 0.34 - - parallel 8192x22x22 8192x22x22 8192x22x22 5 10 0.00265484 0.000265484 1.74457e+08 657.127
batched_heuristic - NN 0.43 0.34 - - parallel 8192x24x24 8192x24x24 8192x24x24 5 10 0.00247352 0.000247353 2.26492e+08 915.667
batched_heuristic - NN 0.43 0.34 - - parallel 8192x26x26 8192x26x26 8192x26x26 5 10 0.00321013 0.000321013 2.87965e+08 897.052
batched_heuristic - NN 0.43 0.34 - - parallel 8192x28x28 8192x28x28 8192x28x28 5 10 0.00333583 0.000333583 3.59662e+08 1078.18
batched_heuristic - NN 0.43 0.34 - - parallel 8192x30x30 8192x30x30 8192x30x30 5 10 0.00377465 0.000377465 4.42368e+08 1171.94
batched_heuristic - NN 0.43 0.34 - - parallel 8192x32x32 8192x32x32 8192x32x32 5 10 0.00360396 0.000360396 5.36871e+08 1489.67
batched_heuristic - NN 0.43 0.34 - - parallel 8192x34x34 8192x34x34 8192x34x34 5 10 0.00952859 0.000952859 6.43957e+08 675.815
batched_heuristic - NN 0.43 0.34 - - parallel 8192x36x36 8192x36x36 8192x36x36 5 10 0.00991886 0.000991886 7.64412e+08 770.665
batched_heuristic - NN 0.43 0.34 - - parallel 8192x38x38 8192x38x38 8192x38x38 5 10 0.0105148 0.00105148 8.99023e+08 855.003
batched_heuristic - NN 0.43 0.34 - - parallel 8192x40x40 8192x40x40 8192x40x40 5 10 0.0108574 0.00108574 1.04858e+09 965.771
batched_heuristic - NN 0.43 0.34 - - parallel 8192x42x42 8192x42x42 8192x42x42 5 10 0.0120492 0.00120492 1.21386e+09 1007.42
batched_heuristic - NN 0.43 0.34 - - parallel 8192x44x44 8192x44x44 8192x44x44 5 10 0.0125638 0.00125638 1.39565e+09 1110.86
batched_heuristic - NN 0.43 0.34 - - parallel 8192x46x46 8192x46x46 8192x46x46 5 10 0.0131731 0.00131731 1.59475e+09 1210.62
batched_heuristic - NN 0.43 0.34 - - parallel 8192x48x48 8192x48x48 8192x48x48 5 10 0.0133301 0.00133301 1.81194e+09 1359.28
batched_heuristic - NN 0.43 0.34 - - parallel 8192x50x50 8192x50x50 8192x50x50 5 10 0.0149486 0.00149486 2.048e+09 1370.03
batched_heuristic - NN 0.43 0.34 - - parallel 8192x52x52 8192x52x52 8192x52x52 5 10 0.0153718 0.00153718 2.30372e+09 1498.67
batched_heuristic - NN 0.43 0.34 - - parallel 8192x54x54 8192x54x54 8192x54x54 5 10 0.0160803 0.00160803 2.57989e+09 1604.38
batched_heuristic - NN 0.43 0.34 - - parallel 8192x56x56 8192x56x56 8192x56x56 5 10 0.0162022 0.00162022 2.87729e+09 1775.86
batched_heuristic - NN 0.43 0.34 - - parallel 8192x58x58 8192x58x58 8192x58x58 5 10 0.0182032 0.00182032 3.19672e+09 1756.13
batched_heuristic - NN 0.43 0.34 - - parallel 8192x60x60 8192x60x60 8192x60x60 5 10 0.0185315 0.00185315 3.53894e+09 1909.69
batched_heuristic - NN 0.43 0.34 - - parallel 8192x62x62 8192x62x62 8192x62x62 5 10 0.019442 0.0019442 3.90477e+09 2008.42
batched_heuristic - NN 0.43 0.34 - - parallel 8192x64x64 8192x64x64 8192x64x64 5 10 0.0164667 0.00164667 4.29497e+09 2608.27
batched_heuristic - NN 0.43 0.34 - - parallel 8192x66x66 8192x66x66 8192x66x66 5 10 0.0365635 0.00365635 4.71033e+09 1288.26
batched_heuristic - NN 0.43 0.34 - - parallel 8192x68x68 8192x68x68 8192x68x68 5 10 0.0375077 0.00375077 5.15165e+09 1373.49
batched_heuristic - NN 0.43 0.34 - - parallel 8192x70x70 8192x70x70 8192x70x70 5 10 0.0385151 0.00385151 5.61971e+09 1459.1
batched_heuristic - NN 0.43 0.34 - - parallel 8192x72x72 8192x72x72 8192x72x72 5 10 0.0389493 0.00389493 6.1153e+09 1570.07
batched_heuristic - NN 0.43 0.34 - - parallel 8192x74x74 8192x74x74 8192x74x74 5 10 0.0426042 0.00426042 6.63919e+09 1558.34
batched_heuristic - NN 0.43 0.34 - - parallel 8192x76x76 8192x76x76 8192x76x76 5 10 0.0433035 0.00433035 7.19218e+09 1660.88
batched_heuristic - NN 0.43 0.34 - - parallel 8192x78x78 8192x78x78 8192x78x78 5 10 0.0448108 0.00448108 7.77506e+09 1735.09
batched_heuristic - NN 0.43 0.34 - - parallel 8192x80x80 8192x80x80 8192x80x80 5 10 0.0448678 0.00448678 8.38861e+09 1869.63
batched_heuristic - NN 0.43 0.34 - - parallel 8192x82x82 8192x82x82 8192x82x82 5 10 0.0489406 0.00489406 9.03361e+09 1845.83
batched_heuristic - NN 0.43 0.34 - - parallel 8192x84x84 8192x84x84 8192x84x84 5 10 0.0501939 0.00501939 9.71086e+09 1934.67
batched_heuristic - NN 0.43 0.34 - - parallel 8192x86x86 8192x86x86 8192x86x86 5 10 0.0516644 0.00516644 1.04211e+10 2017.08
batched_heuristic - NN 0.43 0.34 - - parallel 8192x88x88 8192x88x88 8192x88x88 5 10 0.0520358 0.00520358 1.11652e+10 2145.68
batched_heuristic - NN 0.43 0.34 - - parallel 8192x90x90 8192x90x90 8192x90x90 5 10 0.0571556 0.00571556 1.19439e+10 2089.72
batched_heuristic - NN 0.43 0.34 - - parallel 8192x92x92 8192x92x92 8192x92x92 5 10 0.0580547 0.00580547 1.2758e+10 2197.59
batched_heuristic - NN 0.43 0.34 - - parallel 8192x94x94 8192x94x94 8192x94x94 5 10 0.0590537 0.00590537 1.36083e+10 2304.39
batched_heuristic - NN 0.43 0.34 - - parallel 8192x96x96 8192x96x96 8192x96x96 5 10 0.0483284 0.00483284 1.44955e+10 2999.38
batched_heuristic - NN 0.43 0.34 - - parallel 8192x98x98 8192x98x98 8192x98x98 5 10 0.0876406 0.00876406 1.54205e+10 1759.52
batched_heuristic - NN 0.43 0.34 - - parallel 8192x100x100 8192x100x100 8192x100x100 5 10 0.0891323 0.00891323 1.6384e+10 1838.17
batched_heuristic - NN 0.43 0.34 - - parallel 8192x102x102 8192x102x102 8192x102x102 5 10 0.0912092 0.00912092 1.73868e+10 1906.26
batched_heuristic - NN 0.43 0.34 - - parallel 8192x104x104 8192x104x104 8192x104x104 5 10 0.0917832 0.00917832 1.84298e+10 2007.97
batched_heuristic - NN 0.43 0.34 - - parallel 8192x106x106 8192x106x106 8192x106x106 5 10 0.0976798 0.00976798 1.95136e+10 1997.71
batched_heuristic - NN 0.43 0.34 - - parallel 8192x108x108 8192x108x108 8192x108x108 5 10 0.0975676 0.00975676 2.06391e+10 2115.37
batched_heuristic - NN 0.43 0.34 - - parallel 8192x110x110 8192x110x110 8192x110x110 5 10 0.101327 0.0101327 2.18071e+10 2152.15
batched_heuristic - NN 0.43 0.34 - - parallel 8192x112x112 8192x112x112 8192x112x112 5 10 0.10082 0.010082 2.30183e+10 2283.11
batched_heuristic - NN 0.43 0.34 - - parallel 8192x114x114 8192x114x114 8192x114x114 5 10 0.107338 0.0107338 2.42736e+10 2261.43
batched_heuristic - NN 0.43 0.34 - - parallel 8192x116x116 8192x116x116 8192x116x116 5 10 0.108847 0.0108847 2.55737e+10 2349.51
batched_heuristic - NN 0.43 0.34 - - parallel 8192x118x118 8192x118x118 8192x118x118 5 10 0.110601 0.0110601 2.69194e+10 2433.93
batched_heuristic - NN 0.43 0.34 - - parallel 8192x120x120 8192x120x120 8192x120x120 5 10 0.109326 0.0109326 2.83116e+10 2589.65
batched_heuristic - NN 0.43 0.34 - - parallel 8192x122x122 8192x122x122 8192x122x122 5 10 0.117467 0.0117467 2.97509e+10 2532.7
batched_heuristic - NN 0.43 0.34 - - parallel 8192x124x124 8192x124x124 8192x124x124 5 10 0.118182 0.0118182 3.12381e+10 2643.22
batched_heuristic - NN 0.43 0.34 - - parallel 8192x126x126 8192x126x126 8192x126x126 5 10 0.122016 0.0122016 3.27742e+10 2686.06
batched_heuristic - NN 0.43 0.34 - - parallel 8192x128x128 8192x128x128 8192x128x128 5 10 0.103816 0.0103816 3.43597e+10 3309.69

Using https://github.com/e10harvey/kokkos-kernels/tree/61eda67251b66dc6c10b96cbf107aee9569388e1 I am seeing:

access_view_bounds_check (if-else)

$ export OMP_PROC_BIND=true; ./KokkosBlas3_perf_test.ifel --gemm_scalars=0.43,0.34 --test=batched_heuristic --routines=gemm --loop_type=parallel --batch_size_last_dim=0 --matrix_size_start=2x2,2x2,2x2 --matrix_size_stop=128x128,128x128,128x128 --matrix_size_step=2 --batch_size=$((2048*4)) --warm_up_loop=5 --iter=10 --verify=0

Kokkos::Cuda::initialize WARNING: Cuda is allocating into UVMSpace by default
                                  without setting CUDA_MANAGED_FORCE_DEVICE_ALLOC=1 or
                                  setting CUDA_VISIBLE_DEVICES.
                                  This could on multi GPU systems lead to severe performance"
                                  penalties.
Testing gemm...
SCALAR:d, LAYOUT:N6Kokkos11LayoutRightE, DEVICE:N6Kokkos4CudaE, SPACE:N6Kokkos12CudaUVMSpaceE
algorithm vector_type transAtransB alpha beta team_size vector_len loop_type A_dims B_dims C_dims warm_up_n iter total_time(s) average_time(s) FLOPS GFLOP/average_time(s)
batched_heuristic - NN 0.43 0.34 - - parallel 8192x2x2 8192x2x2 8192x2x2 5 10 5.9132e-05 5.9132e-06 131072 22.166
batched_heuristic - NN 0.43 0.34 - - parallel 8192x4x4 8192x4x4 8192x4x4 5 10 6.7049e-05 6.7049e-06 1.04858e+06 156.39
batched_heuristic - NN 0.43 0.34 - - parallel 8192x6x6 8192x6x6 8192x6x6 5 10 0.000152284 1.52284e-05 3.53894e+06 232.391
batched_heuristic - NN 0.43 0.34 - - parallel 8192x8x8 8192x8x8 8192x8x8 5 10 0.000284414 2.84414e-05 8.38861e+06 294.944
batched_heuristic - NN 0.43 0.34 - - parallel 8192x10x10 8192x10x10 8192x10x10 5 10 0.000466371 4.66371e-05 1.6384e+07 351.308
batched_heuristic - NN 0.43 0.34 - - parallel 8192x12x12 8192x12x12 8192x12x12 5 10 0.000609396 6.09396e-05 2.83116e+07 464.584
batched_heuristic - NN 0.43 0.34 - - parallel 8192x14x14 8192x14x14 8192x14x14 5 10 0.000908037 9.08037e-05 4.49577e+07 495.109
batched_heuristic - NN 0.43 0.34 - - parallel 8192x16x16 8192x16x16 8192x16x16 5 10 0.0011742 0.000117421 6.71089e+07 571.526
batched_heuristic - NN 0.43 0.34 - - parallel 8192x18x18 8192x18x18 8192x18x18 5 10 0.00176963 0.000176963 9.55515e+07 539.951
batched_heuristic - NN 0.43 0.34 - - parallel 8192x20x20 8192x20x20 8192x20x20 5 10 0.0019887 0.00019887 1.31072e+08 659.082
batched_heuristic - NN 0.43 0.34 - - parallel 8192x22x22 8192x22x22 8192x22x22 5 10 0.00264238 0.000264238 1.74457e+08 660.227
batched_heuristic - NN 0.43 0.34 - - parallel 8192x24x24 8192x24x24 8192x24x24 5 10 0.00248065 0.000248065 2.26492e+08 913.036
batched_heuristic - NN 0.43 0.34 - - parallel 8192x26x26 8192x26x26 8192x26x26 5 10 0.0032487 0.00032487 2.87965e+08 886.4
batched_heuristic - NN 0.43 0.34 - - parallel 8192x28x28 8192x28x28 8192x28x28 5 10 0.00335772 0.000335772 3.59662e+08 1071.15
batched_heuristic - NN 0.43 0.34 - - parallel 8192x30x30 8192x30x30 8192x30x30 5 10 0.00380541 0.000380541 4.42368e+08 1162.47
batched_heuristic - NN 0.43 0.34 - - parallel 8192x32x32 8192x32x32 8192x32x32 5 10 0.00361115 0.000361115 5.36871e+08 1486.7
batched_heuristic - NN 0.43 0.34 - - parallel 8192x34x34 8192x34x34 8192x34x34 5 10 0.00956439 0.000956439 6.43957e+08 673.286
batched_heuristic - NN 0.43 0.34 - - parallel 8192x36x36 8192x36x36 8192x36x36 5 10 0.00996848 0.000996848 7.64412e+08 766.829
batched_heuristic - NN 0.43 0.34 - - parallel 8192x38x38 8192x38x38 8192x38x38 5 10 0.0105164 0.00105164 8.99023e+08 854.88
batched_heuristic - NN 0.43 0.34 - - parallel 8192x40x40 8192x40x40 8192x40x40 5 10 0.010997 0.0010997 1.04858e+09 953.513
batched_heuristic - NN 0.43 0.34 - - parallel 8192x42x42 8192x42x42 8192x42x42 5 10 0.01213 0.001213 1.21386e+09 1000.71
batched_heuristic - NN 0.43 0.34 - - parallel 8192x44x44 8192x44x44 8192x44x44 5 10 0.0127 0.00127 1.39565e+09 1098.94
batched_heuristic - NN 0.43 0.34 - - parallel 8192x46x46 8192x46x46 8192x46x46 5 10 0.0132937 0.00132937 1.59475e+09 1199.63
batched_heuristic - NN 0.43 0.34 - - parallel 8192x48x48 8192x48x48 8192x48x48 5 10 0.0135291 0.00135291 1.81194e+09 1339.29
batched_heuristic - NN 0.43 0.34 - - parallel 8192x50x50 8192x50x50 8192x50x50 5 10 0.0151308 0.00151308 2.048e+09 1353.53
batched_heuristic - NN 0.43 0.34 - - parallel 8192x52x52 8192x52x52 8192x52x52 5 10 0.0157025 0.00157025 2.30372e+09 1467.1
batched_heuristic - NN 0.43 0.34 - - parallel 8192x54x54 8192x54x54 8192x54x54 5 10 0.0163476 0.00163476 2.57989e+09 1578.14
batched_heuristic - NN 0.43 0.34 - - parallel 8192x56x56 8192x56x56 8192x56x56 5 10 0.0165237 0.00165237 2.87729e+09 1741.31
batched_heuristic - NN 0.43 0.34 - - parallel 8192x58x58 8192x58x58 8192x58x58 5 10 0.0185613 0.00185613 3.19672e+09 1722.24
batched_heuristic - NN 0.43 0.34 - - parallel 8192x60x60 8192x60x60 8192x60x60 5 10 0.0188836 0.00188836 3.53894e+09 1874.08
batched_heuristic - NN 0.43 0.34 - - parallel 8192x62x62 8192x62x62 8192x62x62 5 10 0.0197419 0.00197419 3.90477e+09 1977.91
batched_heuristic - NN 0.43 0.34 - - parallel 8192x64x64 8192x64x64 8192x64x64 5 10 0.0164996 0.00164996 4.29497e+09 2603.08
batched_heuristic - NN 0.43 0.34 - - parallel 8192x66x66 8192x66x66 8192x66x66 5 10 0.0365242 0.00365242 4.71033e+09 1289.65
batched_heuristic - NN 0.43 0.34 - - parallel 8192x68x68 8192x68x68 8192x68x68 5 10 0.0374438 0.00374438 5.15165e+09 1375.84
batched_heuristic - NN 0.43 0.34 - - parallel 8192x70x70 8192x70x70 8192x70x70 5 10 0.0383418 0.00383418 5.61971e+09 1465.69
batched_heuristic - NN 0.43 0.34 - - parallel 8192x72x72 8192x72x72 8192x72x72 5 10 0.0392436 0.00392436 6.1153e+09 1558.29
batched_heuristic - NN 0.43 0.34 - - parallel 8192x74x74 8192x74x74 8192x74x74 5 10 0.0422136 0.00422136 6.63919e+09 1572.76
batched_heuristic - NN 0.43 0.34 - - parallel 8192x76x76 8192x76x76 8192x76x76 5 10 0.0440583 0.00440583 7.19218e+09 1632.43
batched_heuristic - NN 0.43 0.34 - - parallel 8192x78x78 8192x78x78 8192x78x78 5 10 0.04484 0.004484 7.77506e+09 1733.96
batched_heuristic - NN 0.43 0.34 - - parallel 8192x80x80 8192x80x80 8192x80x80 5 10 0.0449478 0.00449478 8.38861e+09 1866.3
batched_heuristic - NN 0.43 0.34 - - parallel 8192x82x82 8192x82x82 8192x82x82 5 10 0.0491196 0.00491196 9.03361e+09 1839.11
batched_heuristic - NN 0.43 0.34 - - parallel 8192x84x84 8192x84x84 8192x84x84 5 10 0.0511506 0.00511506 9.71086e+09 1898.49
batched_heuristic - NN 0.43 0.34 - - parallel 8192x86x86 8192x86x86 8192x86x86 5 10 0.0522619 0.00522619 1.04211e+10 1994.02
batched_heuristic - NN 0.43 0.34 - - parallel 8192x88x88 8192x88x88 8192x88x88 5 10 0.0525548 0.00525548 1.11652e+10 2124.5
batched_heuristic - NN 0.43 0.34 - - parallel 8192x90x90 8192x90x90 8192x90x90 5 10 0.056651 0.0056651 1.19439e+10 2108.34
batched_heuristic - NN 0.43 0.34 - - parallel 8192x92x92 8192x92x92 8192x92x92 5 10 0.0579655 0.00579655 1.2758e+10 2200.97
batched_heuristic - NN 0.43 0.34 - - parallel 8192x94x94 8192x94x94 8192x94x94 5 10 0.0591426 0.00591426 1.36083e+10 2300.93
batched_heuristic - NN 0.43 0.34 - - parallel 8192x96x96 8192x96x96 8192x96x96 5 10 0.0483157 0.00483157 1.44955e+10 3000.17
batched_heuristic - NN 0.43 0.34 - - parallel 8192x98x98 8192x98x98 8192x98x98 5 10 0.0880541 0.00880541 1.54205e+10 1751.25
batched_heuristic - NN 0.43 0.34 - - parallel 8192x100x100 8192x100x100 8192x100x100 5 10 0.0886525 0.00886525 1.6384e+10 1848.12
batched_heuristic - NN 0.43 0.34 - - parallel 8192x102x102 8192x102x102 8192x102x102 5 10 0.0917698 0.00917698 1.73868e+10 1894.61
batched_heuristic - NN 0.43 0.34 - - parallel 8192x104x104 8192x104x104 8192x104x104 5 10 0.0915989 0.00915989 1.84298e+10 2012.01
batched_heuristic - NN 0.43 0.34 - - parallel 8192x106x106 8192x106x106 8192x106x106 5 10 0.097199 0.0097199 1.95136e+10 2007.59
batched_heuristic - NN 0.43 0.34 - - parallel 8192x108x108 8192x108x108 8192x108x108 5 10 0.0979803 0.00979803 2.06391e+10 2106.46
batched_heuristic - NN 0.43 0.34 - - parallel 8192x110x110 8192x110x110 8192x110x110 5 10 0.10128 0.010128 2.18071e+10 2153.16
batched_heuristic - NN 0.43 0.34 - - parallel 8192x112x112 8192x112x112 8192x112x112 5 10 0.10221 0.010221 2.30183e+10 2252.05
batched_heuristic - NN 0.43 0.34 - - parallel 8192x114x114 8192x114x114 8192x114x114 5 10 0.108273 0.0108273 2.42736e+10 2241.9
batched_heuristic - NN 0.43 0.34 - - parallel 8192x116x116 8192x116x116 8192x116x116 5 10 0.108957 0.0108957 2.55737e+10 2347.14
batched_heuristic - NN 0.43 0.34 - - parallel 8192x118x118 8192x118x118 8192x118x118 5 10 0.112457 0.0112457 2.69194e+10 2393.75
batched_heuristic - NN 0.43 0.34 - - parallel 8192x120x120 8192x120x120 8192x120x120 5 10 0.111701 0.0111701 2.83116e+10 2534.59
batched_heuristic - NN 0.43 0.34 - - parallel 8192x122x122 8192x122x122 8192x122x122 5 10 0.11896 0.011896 2.97509e+10 2500.91
batched_heuristic - NN 0.43 0.34 - - parallel 8192x124x124 8192x124x124 8192x124x124 5 10 0.121238 0.0121238 3.12381e+10 2576.58
batched_heuristic - NN 0.43 0.34 - - parallel 8192x126x126 8192x126x126 8192x126x126 5 10 0.122508 0.0122508 3.27742e+10 2675.27
batched_heuristic - NN 0.43 0.34 - - parallel 8192x128x128 8192x128x128 8192x128x128 5 10 0.103371 0.0103371 3.43597e+10 3323.93

I am also seeing a small speedup (of ~30 GFLOP/s for 60x60 in this case) with the KOKKOSKERNELS_MACRO_MIN.

Note that both of the above tables are using gcc/8.3.0 + cuda/11 on V100 with the alpha tag selection such that alpha is applied in the fma for matrices > 64x64, otherwise alpha is applied in __mul.

@vqd8a vqd8a added the AT: RETEST Have this PR retested. label Dec 31, 2021
@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - User Requested Retest - Label AT: RETEST will be reset after testing.

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Testing Jenkins Projects:

Pull Request Auto Testing STARTING (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740

  • Build Num: 46
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight

  • Build Num: 46
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 704
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 351
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 695
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 682
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_CLANG1001

  • Build Num: 88
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Using Repos:

Repo: KOKKOSKERNELS (vqd8a/kokkos-kernels)
  • Branch: batched_gemm_fix_alpha
  • SHA: 64e92e3
  • Mode: TEST_REPO

Pull Request Author: vqd8a

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Jenkins Testing: 1 or more Jobs FAILED

Note: Testing will normally be attempted again in approx. 2 Hrs 30 Mins. If a change to the PR source branch occurs, the testing will be attempted again on next available autotester run.

Pull Request Auto Testing has FAILED (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740

  • Build Num: 46
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight

  • Build Num: 46
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 704
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 351
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 695
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 682
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_CLANG1001

  • Build Num: 88
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS AT: RETEST
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740 # 46 (click to expand) 

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp(744): error: no instance of overloaded function "KokkosBatched::fma_bounds_check" matches the argument list

argument types are: (Kokkos::View<Kokkos::complex **, Kokkos::Cuda::array_layout, Kokkos::Device<Kokkos::CudaUVMSpace::execution_space, Kokkos::CudaUVMSpace::memory_space>, Kokkos::MemoryManaged>, int, int, Kokkos::complex, const double, KokkosBatched::BoundsCheck::Yes)

detected during:

instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::Functor<MemberType, REG_M, REG_N, STRIDE_M, STRIDE_N>::operator()(const MemberType &) const [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=32, TILE_N=32, TILE_K=8, MemberType=Kokkos::Impl::CudaTeamMember, REG_M=4, REG_N=4, STRIDE_M=8, STRIDE_N=8]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.46/TestAll_2021-12-31_12.39.39/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(704): here

instantiation of "std::enable_if<std::is_same<TagType, void>::value, void>::type Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::exec_team(const Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::Member &) const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Properties=Kokkos::Cuda::execution_space, TagType=Kokkos::Impl::WorkTagTrait::base_traits::work_tag]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.46/TestAll_2021-12-31_12.39.39/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(755): here

instantiation of "void Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::operator()() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Properties=Kokkos::Cuda::execution_space]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.46/TestAll_2021-12-31_12.39.39/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(121): here

instantiation of "void Kokkos::Impl::cuda_parallel_launch_local_memory(DriverType) [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::HostSpace::execution_space, Kokkos::HostSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.46/TestAll_2021-12-31_12.39.39/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(322): here

instantiation of "std::decay_t<decltype(())> Kokkos::Impl::CudaParallelLaunchKernelFunc<DriverType, Kokkos::LaunchBounds<0U, 0U>, Kokkos::Impl::Experimental::CudaLaunchMechanism::LocalMemory>::get_kernel_func() [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::HostSpace::execution_space, Kokkos::HostSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.46/TestAll_2021-12-31_12.39.39/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(659): here

[ 3 instantiation contexts not shown ]

instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=32, TILE_N=32, TILE_K=8]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp(487): here

instantiation of "int KokkosBatched::BatchedGemm<ArgTransA,ArgTransB,ArgBatchSzDim,BatchedGemmHandleType,ScalarType,AViewType,BViewType,CViewType>(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(231): here

instantiation of "void Test::impl_test_batched_gemm<DeviceType,ViewType,ScalarType,ParamTagType>(int, int, int, int, int, int, int) [with DeviceType=Kokkos::Cuda, ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here

instantiation of "void test_batched_gemm_with_layout<ViewType,DeviceType,ValueType,ScalarType,ParamTagType>() [with ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here

instantiation of "int test_batched_gemm<DeviceType,ValueType,ScalarType,ParamTagType>() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here


/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp(744): error: no instance of overloaded function "KokkosBatched::fma_bounds_check" matches the argument list

argument types are: (Kokkos::View<Kokkos::complex **, Kokkos::Cuda::array_layout, Kokkos::Device<Kokkos::CudaUVMSpace::execution_space, Kokkos::CudaUVMSpace::memory_space>, Kokkos::MemoryManaged>, int, int, Kokkos::complex, const double, KokkosBatched::BoundsCheck::Yes)

detected during:

instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::Functor<MemberType, REG_M, REG_N, STRIDE_M, STRIDE_N>::operator()(const MemberType &) const [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1, MemberType=Kokkos::Impl::CudaTeamMember, REG_M=1, REG_N=1, STRIDE_M=1, STRIDE_N=1]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.46/TestAll_2021-12-31_12.39.39/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(704): here

instantiation of "std::enable_if<std::is_same<TagType, void>::value, void>::type Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::exec_team(const Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::Member &) const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Properties=Kokkos::Cuda::execution_space, TagType=Kokkos::Impl::WorkTagTrait::base_traits::work_tag]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.46/TestAll_2021-12-31_12.39.39/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(755): here

instantiation of "void Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::operator()() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Properties=Kokkos::Cuda::execution_space]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.46/TestAll_2021-12-31_12.39.39/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(121): here

instantiation of "void Kokkos::Impl::cuda_parallel_launch_local_memory(DriverType) [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::HostSpace::execution_space, Kokkos::HostSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.46/TestAll_2021-12-31_12.39.39/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(322): here

instantiation of "std::decay_t<decltype(())> Kokkos::Impl::CudaParallelLaunchKernelFunc<DriverType, Kokkos::LaunchBounds<0U, 0U>, Kokkos::Impl::Experimental::CudaLaunchMechanism::LocalMemory>::get_kernel_func() [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::HostSpace::execution_space, Kokkos::HostSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.46/TestAll_2021-12-31_12.39.39/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(659): here

[ 3 instantiation contexts not shown ]

instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp(510): here

instantiation of "int KokkosBatched::BatchedGemm<ArgTransA,ArgTransB,ArgBatchSzDim,BatchedGemmHandleType,ScalarType,AViewType,BViewType,CViewType>(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(231): here

instantiation of "void Test::impl_test_batched_gemm<DeviceType,ViewType,ScalarType,ParamTagType>(int, int, int, int, int, int, int) [with DeviceType=Kokkos::Cuda, ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here

instantiation of "void test_batched_gemm_with_layout<ViewType,DeviceType,ValueType,ScalarType,ParamTagType>() [with ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here

instantiation of "int test_batched_gemm<DeviceType,ValueType,ScalarType,ParamTagType>() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here


48 errors detected in the compilation of "/tmp/tmpxft_00022078_00000000-6_Test_Cuda_Batched_Dense.cpp1.ii".

make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_cuda.dir/cuda/Test_Cuda_Batched_Dense.cpp.o] Error 1

make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_cuda.dir/all] Error 2

[ 91%] Linking CXX executable KokkosKernels_batched_sla_cuda

[ 91%] Built target KokkosKernels_batched_sla_cuda

[ 91%] Linking CXX executable KokkosBlas3_gemm_perf_test

[ 91%] Built target KokkosBlas3_gemm_perf_test

[ 91%] Linking CXX executable sparse_kk_spmv

[ 91%] Built target sparse_kk_spmv

[ 91%] Linking CXX executable KokkosKernels_graph_openmp

[ 91%] Built target KokkosKernels_graph_openmp

[ 91%] Linking CXX executable KokkosKernels_blas_cuda

[ 91%] Built target KokkosKernels_blas_cuda

[ 91%] Linking CXX executable KokkosKernels_sparse_openmp

[ 91%] Built target KokkosKernels_sparse_openmp

[ 91%] Linking CXX executable KokkosKernels_sparse_cuda

[ 91%] Built target KokkosKernels_sparse_cuda

make: *** [all] Error 2

#######################################################

PASSED TESTS

#######################################################

#######################################################

FAILED TESTS

#######################################################

cuda-9.2.88-Cuda_OpenMP-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 cuda/9.2.88 gcc/7.2.0 netlib/3.8.0/gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Cuda,OpenMP --arch=Power9,Volta70 --compiler=/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos/bin/nvcc_wrapper --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --with-cuda=/home/projects/ppc64le-pwr9-nvidia/cuda/9.2.88  --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas,cublas,cusparse --user-blas-path=/home/projects/ppc64le-pwr9/netlib/3.8.0/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/netlib/3.8.0/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=force_uvm,enable_lambda   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.46/TestAll_2021-12-31_12.39.39/cuda/9.2.88/Cuda_OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight # 46 (click to expand) 

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here
            instantiation of "int test_batched_gemm() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp(744): error: no instance of overloaded function "KokkosBatched::fma_bounds_check" matches the argument list

argument types are: (Kokkos::View<Kokkos::complex **, Kokkos::Cuda::array_layout, Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, Kokkos::MemoryManaged>, int, int, Kokkos::complex, const double, KokkosBatched::BoundsCheck::Yes)

detected during:

instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::Functor<MemberType, REG_M, REG_N, STRIDE_M, STRIDE_N>::operator()(const MemberType &) const [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=32, TILE_N=32, TILE_K=8, MemberType=Kokkos::Impl::CudaTeamMember, REG_M=4, REG_N=4, STRIDE_M=8, STRIDE_N=8]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.46/TestAll_2021-12-31_12.39.48/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(704): here

instantiation of "std::enable_if<std::is_same<TagType, void>::value, void>::type Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::exec_team(const Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::Member &) const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Properties=Kokkos::Cuda::execution_space, TagType=Kokkos::Impl::WorkTagTrait::base_traits::work_tag]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.46/TestAll_2021-12-31_12.39.48/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(755): here

instantiation of "void Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::operator()() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Properties=Kokkos::Cuda::execution_space]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.46/TestAll_2021-12-31_12.39.48/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(121): here

instantiation of "void Kokkos::Impl::cuda_parallel_launch_local_memory(DriverType) [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.46/TestAll_2021-12-31_12.39.48/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(322): here

instantiation of "std::decay_t<decltype(())> Kokkos::Impl::CudaParallelLaunchKernelFunc<DriverType, Kokkos::LaunchBounds<0U, 0U>, Kokkos::Impl::Experimental::CudaLaunchMechanism::LocalMemory>::get_kernel_func() [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.46/TestAll_2021-12-31_12.39.48/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(659): here

[ 3 instantiation contexts not shown ]

instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=32, TILE_N=32, TILE_K=8]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp(487): here

instantiation of "int KokkosBatched::BatchedGemm<ArgTransA,ArgTransB,ArgBatchSzDim,BatchedGemmHandleType,ScalarType,AViewType,BViewType,CViewType>(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(231): here

instantiation of "void Test::impl_test_batched_gemm<DeviceType,ViewType,ScalarType,ParamTagType>(int, int, int, int, int, int, int) [with DeviceType=Kokkos::Cuda, ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here

instantiation of "void test_batched_gemm_with_layout<ViewType,DeviceType,ValueType,ScalarType,ParamTagType>() [with ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here

instantiation of "int test_batched_gemm<DeviceType,ValueType,ScalarType,ParamTagType>() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here


/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp(744): error: no instance of overloaded function "KokkosBatched::fma_bounds_check" matches the argument list

argument types are: (Kokkos::View<Kokkos::complex **, Kokkos::Cuda::array_layout, Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, Kokkos::MemoryManaged>, int, int, Kokkos::complex, const double, KokkosBatched::BoundsCheck::Yes)

detected during:

instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::Functor<MemberType, REG_M, REG_N, STRIDE_M, STRIDE_N>::operator()(const MemberType &) const [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1, MemberType=Kokkos::Impl::CudaTeamMember, REG_M=1, REG_N=1, STRIDE_M=1, STRIDE_N=1]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.46/TestAll_2021-12-31_12.39.48/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(704): here

instantiation of "std::enable_if<std::is_same<TagType, void>::value, void>::type Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::exec_team(const Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::Member &) const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Properties=Kokkos::Cuda::execution_space, TagType=Kokkos::Impl::WorkTagTrait::base_traits::work_tag]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.46/TestAll_2021-12-31_12.39.48/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(755): here

instantiation of "void Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::operator()() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Properties=Kokkos::Cuda::execution_space]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.46/TestAll_2021-12-31_12.39.48/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(121): here

instantiation of "void Kokkos::Impl::cuda_parallel_launch_local_memory(DriverType) [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.46/TestAll_2021-12-31_12.39.48/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(322): here

instantiation of "std::decay_t<decltype(())> Kokkos::Impl::CudaParallelLaunchKernelFunc<DriverType, Kokkos::LaunchBounds<0U, 0U>, Kokkos::Impl::Experimental::CudaLaunchMechanism::LocalMemory>::get_kernel_func() [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.46/TestAll_2021-12-31_12.39.48/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(659): here

[ 3 instantiation contexts not shown ]

instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp(510): here

instantiation of "int KokkosBatched::BatchedGemm<ArgTransA,ArgTransB,ArgBatchSzDim,BatchedGemmHandleType,ScalarType,AViewType,BViewType,CViewType>(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(231): here

instantiation of "void Test::impl_test_batched_gemm<DeviceType,ViewType,ScalarType,ParamTagType>(int, int, int, int, int, int, int) [with DeviceType=Kokkos::Cuda, ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here

instantiation of "void test_batched_gemm_with_layout<ViewType,DeviceType,ValueType,ScalarType,ParamTagType>() [with ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here

instantiation of "int test_batched_gemm<DeviceType,ValueType,ScalarType,ParamTagType>() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here


[ 91%] Linking CXX executable sparse_sptrsv_supernode

[ 91%] Built target sparse_sptrsv_supernode

48 errors detected in the compilation of "/tmp/tmpxft_000178c2_00000000-6_Test_Cuda_Batched_Dense.cpp1.ii".

make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_cuda.dir/cuda/Test_Cuda_Batched_Dense.cpp.o] Error 1

make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_cuda.dir/all] Error 2

[ 91%] Linking CXX executable KokkosKernels_batched_sla_cuda

[ 91%] Built target KokkosKernels_batched_sla_cuda

[ 91%] Linking CXX executable KokkosKernels_common_serial

[ 91%] Built target KokkosKernels_common_serial

[ 91%] Linking CXX executable KokkosBlas3_gemm_perf_test

[ 91%] Built target KokkosBlas3_gemm_perf_test

[ 91%] Linking CXX executable sparse_kk_spmv

[ 91%] Built target sparse_kk_spmv

[ 91%] Linking CXX executable KokkosKernels_sparse_serial

[ 91%] Built target KokkosKernels_sparse_serial

make: *** [all] Error 2

#######################################################

PASSED TESTS

#######################################################

#######################################################

FAILED TESTS

#######################################################

cuda-10.1.243-Cuda_Serial-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 cuda/10.1.243 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Cuda,Serial --arch=Power9,Volta70 --compiler=/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos/bin/nvcc_wrapper --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --with-cuda=/home/projects/ppc64le-pwr9-nvidia/cuda/10.1.243  --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas,cublas,cusparse --user-blas-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=,enable_lambda   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.46/TestAll_2021-12-31_12.39.48/cuda/10.1.243/Cuda_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC720 # 704 (click to expand) 

/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
[ 88%] Linking CXX executable sparse_kk_spmv
[ 88%] Built target sparse_kk_spmv
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched_Dense.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
[ 88%] Linking CXX executable KokkosKernels_common_openmp
[ 88%] Built target KokkosKernels_common_openmp
[ 89%] Linking CXX executable KokkosKernels_blas_openmp
[ 89%] Built target KokkosKernels_blas_openmp
[ 89%] Linking CXX executable KokkosKernels_graph_openmp
[ 89%] Built target KokkosKernels_graph_openmp
[ 89%] Linking CXX executable KokkosKernels_sparse_openmp
[ 89%] Built target KokkosKernels_sparse_openmp
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

gcc-7.2.0-Pthread_Serial-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.704/TestAll_2021-12-31_12.40.54/gcc/7.2.0/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013886

salloc: Job allocation 1013886 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC720_Light_LayoutRight # 351 (click to expand) 

/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched_Dense.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
[ 87%] Linking CXX executable sparse_kk_spmv
[ 87%] Built target sparse_kk_spmv
[ 87%] Linking CXX executable KokkosKernels_common_openmp
[ 87%] Built target KokkosKernels_common_openmp
[ 88%] Linking CXX executable KokkosKernels_blas_openmp
[ 88%] Built target KokkosKernels_blas_openmp
[ 88%] Linking CXX executable KokkosKernels_graph_openmp
[ 88%] Built target KokkosKernels_graph_openmp
[ 88%] Linking CXX executable KokkosKernels_sparse_openmp
[ 88%] Built target KokkosKernels_sparse_openmp
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutRight --with-tpls=    --with-options= --with-cuda-options=  --with-spaces=hostspace --no-examples  --no-default-eti


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

gcc-7.2.0-Pthread_Serial-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutRight --with-tpls=    --with-options= --with-cuda-options=  --with-spaces=hostspace --no-examples  --no-default-eti


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.351/TestAll_2021-12-31_12.41.01/gcc/7.2.0/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013887

salloc: Job allocation 1013887 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_GCC720 # 695 (click to expand) 

/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::NoTranspose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::NoTranspose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
Scanning dependencies of target KokkosKernels_common_openmp
[ 86%] Building CXX object unit_test/CMakeFiles/KokkosKernels_common_openmp.dir/Test_Main.cpp.o
make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 1
make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[ 86%] Building CXX object unit_test/CMakeFiles/KokkosKernels_common_openmp.dir/openmp/Test_OpenMP_Common.cpp.o
[ 86%] Linking CXX executable KokkosBlas2_gemv_perf_test
[ 86%] Built target KokkosBlas2_gemv_perf_test
[ 87%] Linking CXX executable KokkosKernels_batched_sla_openmp
[ 87%] Built target KokkosKernels_batched_sla_openmp
[ 87%] Linking CXX executable sparse_kk_spmv
[ 87%] Built target sparse_kk_spmv
[ 88%] Linking CXX executable KokkosBlas3_gemm_perf_test
[ 88%] Built target KokkosBlas3_gemm_perf_test
[ 88%] Linking CXX executable KokkosKernels_common_serial
[ 88%] Built target KokkosKernels_common_serial
[ 89%] Linking CXX executable KokkosKernels_common_openmp
[ 89%] Built target KokkosKernels_common_openmp
[ 89%] Linking CXX executable KokkosKernels_blas_openmp
[ 89%] Linking CXX executable KokkosKernels_graph_openmp
[ 89%] Built target KokkosKernels_graph_openmp
[ 89%] Built target KokkosKernels_blas_openmp
[ 89%] Linking CXX executable KokkosKernels_blas_serial
[ 89%] Built target KokkosKernels_blas_serial
[ 90%] Linking CXX executable KokkosKernels_sparse_serial
[ 90%] Built target KokkosKernels_sparse_serial
[ 90%] Linking CXX executable KokkosKernels_sparse_openmp
[ 90%] Built target KokkosKernels_sparse_openmp
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP_Serial-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas --user-blas-path=/home/projects/x86-64-skylake/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/x86-64-skylake/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.695/TestAll_2021-12-31_12.41.11/gcc/7.2.0/OpenMP_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013888

salloc: Job allocation 1013888 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_INTEL18 # 682 (click to expand) 

            instantiation of "void Kokkos::Impl::ParallelFor, Kokkos::Threads>::exec(Kokkos::Impl::ThreadsExec &, const void *) [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm::Functor, Properties=]" at line 352 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.682/TestAll_2021-12-31_12.41.21/intel/18.1.163/Pthread-release/kokkos-install/include/Threads/Kokkos_Threads_Parallel.hpp"
            instantiation of "void Kokkos::Impl::ParallelFor, Kokkos::Threads>::execute() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm::Functor, Properties=]" at line 144 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.682/TestAll_2021-12-31_12.41.21/intel/18.1.163/Pthread-release/kokkos-install/include/Kokkos_Parallel.hpp"
            instantiation of "void Kokkos::parallel_for(const ExecPolicy &, const FunctorType &, const std::__cxx11::string &, std::enable_if::value, void>::type *) [with ExecPolicy=Kokkos::TeamPolicy, FunctorType=KokkosBatched::Impl::BatchedDblBufGemm::Functor]" at line 175 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.682/TestAll_2021-12-31_12.41.21/intel/18.1.163/Pthread-release/kokkos-install/include/Kokkos_Parallel.hpp"
            instantiation of "void Kokkos::parallel_for(const std::__cxx11::string &, const ExecPolicy &, const FunctorType &) [with ExecPolicy=Kokkos::TeamPolicy, FunctorType=KokkosBatched::Impl::BatchedDblBufGemm::Functor]" at line 191
            instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm::__run() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Left, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double}, AViewType=vector_view_type_3d, BViewType=vector_view_type_3d,
                      CViewType=vector_view_type_3d, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1]" at line 108
            instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Left, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double}, AViewType=vector_view_type_3d, BViewType=vector_view_type_3d,
                      CViewType=vector_view_type_3d, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1]" at line 510 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp"
            instantiation of "int KokkosBatched::BatchedGemm(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Left, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double},
                      AViewType=vector_view_type_3d, BViewType=vector_view_type_3d, CViewType=vector_view_type_3d]" at line 562 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"
            instantiation of "void __do_gemm_parallel_batched_heuristic_template(options_t, gemm_args_t) [with algo_tag=void, blocking_type=void, device_type=default_device, algo_mode=void]" at line 589 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"
            instantiation of "void __do_gemm_parallel_batched_heuristic(options_t, gemm_args_t) [with algo_tag=void, blocking_type=void, device_type=default_device, algo_mode=void]" at line 2265 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"

Scanning dependencies of target KokkosKernels_wiki_rcm

[ 75%] Building CXX object example/wiki/graph/CMakeFiles/KokkosKernels_wiki_rcm.dir/KokkosGraph_wiki_rcm.cpp.o

[ 76%] Linking CXX executable KokkosKernels_wiki_mis2

compilation aborted for /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_perf_test.cpp (code 2)

make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 2

make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2

make[1]: *** Waiting for unfinished jobs....

[ 76%] Built target KokkosKernels_wiki_mis2

[ 78%] Linking CXX executable KokkosKernels_wiki_rcm

[ 78%] Built target KokkosKernels_wiki_rcm

[ 79%] Linking CXX executable KokkosKernels_wiki_coarsening

[ 79%] Built target KokkosKernels_wiki_coarsening

[ 80%] Linking CXX executable KokkosKernels_wiki_coloring

[ 80%] Built target KokkosKernels_wiki_coloring

[ 81%] Linking CXX executable sparse_kk_spmv

[ 81%] Built target sparse_kk_spmv

[ 82%] Linking CXX executable KokkosKernels_wiki_spgemm

[ 82%] Built target KokkosKernels_wiki_spgemm

[ 83%] Linking CXX executable sparse_pcg

[ 83%] Built target sparse_pcg

[ 84%] Linking CXX executable sparse_block_pcg

[ 84%] Built target sparse_block_pcg

[ 85%] Linking CXX executable KokkosKernels_wiki_gauss_seidel

[ 85%] Built target KokkosKernels_wiki_gauss_seidel

[ 86%] Linking CXX executable sparse_spmv_struct

[ 86%] Built target sparse_spmv_struct

[ 87%] Linking CXX executable sparse_spmv_struct_tuning

[ 87%] Built target sparse_spmv_struct_tuning

make: *** [all] Error 2

#######################################################

PASSED TESTS

#######################################################

#######################################################

FAILED TESTS

#######################################################

intel-18.1.163-OpenMP-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 intel/compilers/18.1.163



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/intel/compilers/2018/compilers_and_libraries_2018.1.163/linux/bin/intel64/icpc --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=mkl    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.682/TestAll_2021-12-31_12.41.21/intel/18.1.163/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

intel-18.1.163-Pthread-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 intel/compilers/18.1.163



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread --arch=SKX --compiler=/home/projects/x86-64/intel/compilers/2018/compilers_and_libraries_2018.1.163/linux/bin/intel64/icpc --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=mkl    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.682/TestAll_2021-12-31_12.41.21/intel/18.1.163/Pthread-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013889

salloc: Job allocation 1013889 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG1001 # 88 (click to expand) 

    ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:479:20: note: in instantiation of member function 'KokkosBatched::Impl::BatchedDblBufGemm, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, Kokkos::View, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, Kokkos::View, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, KokkosBatched::BoundsCheck::No, 32, 32, 8>::invoke' requested here
                  .invoke();
                   ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp:552:24: note: in instantiation of function template specialization 'KokkosBatched::BatchedGemm, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, Kokkos::View, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, Kokkos::View, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads> >' requested here
        KokkosBatched::BatchedGemm(
                       ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp:587:5: note: in instantiation of function template specialization '__do_gemm_parallel_batched_heuristic_template' requested here
    __do_gemm_parallel_batched_heuristic_template' requested here
      __do_gemm_parallel_batched_heuristic);
      ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/KokkosBatched_Util.hpp:858:29: note: candidate template ignored: deduced conflicting types for parameter 'ScalarType' ('KokkosBatched::Vector, 8>' vs. 'double')
KOKKOS_INLINE_FUNCTION void fma_bounds_check(ViewType v, SizeType m, SizeType n,
                            ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/KokkosBatched_Util.hpp:865:29: note: candidate template ignored: deduced conflicting types for parameter 'ScalarType' ('KokkosBatched::Vector, 8>' vs. 'double')
KOKKOS_INLINE_FUNCTION void fma_bounds_check(ViewType v, SizeType m, SizeType n,
                            ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/KokkosBatched_Util.hpp:841:29: note: candidate function template not viable: requires 7 arguments, but 6 were provided
KOKKOS_INLINE_FUNCTION void fma_bounds_check(ViewType v, SizeType m, SizeType n,
                            ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/KokkosBatched_Util.hpp:850:29: note: candidate function template not viable: requires 7 arguments, but 6 were provided
KOKKOS_INLINE_FUNCTION void fma_bounds_check(ViewType v, SizeType m, SizeType n,
                            ^
fatal error: too many errors emitted, stopping now [-ferror-limit=]
20 errors generated.
make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 1
make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[ 78%] Building CXX object unit_test/CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o
[ 78%] Linking CXX executable KokkosBlas2_gemv_perf_test
[ 78%] Built target KokkosBlas2_gemv_perf_test
[ 79%] Linking CXX executable sparse_sptrsv_supernode
[ 79%] Built target sparse_sptrsv_supernode
[ 79%] Linking CXX executable sparse_spmv_struct
[ 79%] Built target sparse_spmv_struct
[ 80%] Linking CXX executable KokkosBlas3_gemm_perf_test
[ 80%] Built target KokkosBlas3_gemm_perf_test
[ 81%] Linking CXX executable KokkosKernels_batched_sla_serial
[ 81%] Built target KokkosKernels_batched_sla_serial
[ 81%] Linking CXX executable sparse_kk_spmv
[ 81%] Built target sparse_kk_spmv
[ 81%] Linking CXX executable sparse_pcg
[ 81%] Built target sparse_pcg
[ 82%] Linking CXX executable KokkosKernels_blas_serial
[ 83%] Linking CXX executable sparse_block_pcg
[ 83%] Built target KokkosKernels_blas_serial
[ 83%] Built target sparse_block_pcg
[ 84%] Linking CXX executable sparse_gs
[ 84%] Built target sparse_gs
[ 84%] Linking CXX executable KokkosKernels_sparse_serial
CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o: In function `int KokkosBlas::trtri, Kokkos::MemoryTraits<1u> > >(char const*, char const*, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)':
Test_Serial_Sparse.cpp:(.text._ZN10KokkosBlas5trtriIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEEEEiPKcSE_RKT_[_ZN10KokkosBlas5trtriIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEEEEiPKcSE_RKT_]+0x463): undefined reference to `KokkosBlas::Impl::TRTRI >, Kokkos::View, Kokkos::MemoryTraits<1u> >, false, false>::trtri(Kokkos::View > const&, char const*, char const*, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)'
CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o: In function `void KokkosBlas::trmm, Kokkos::MemoryTraits<1u> >, Kokkos::View, Kokkos::MemoryTraits<1u> > >(char const*, char const*, char const*, char const*, Kokkos::View, Kokkos::MemoryTraits<1u> >::const_value_type&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)':
Test_Serial_Sparse.cpp:(.text._ZN10KokkosBlas4trmmIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEESC_EEvPKcSE_SE_SE_RNT0_16const_value_typeERKT_RKSF_[_ZN10KokkosBlas4trmmIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEESC_EEvPKcSE_SE_SE_RNT0_16const_value_typeERKT_RKSF_]+0x8de): undefined reference to `KokkosBlas::Impl::TRMM, Kokkos::MemoryTraits<1u> >, Kokkos::View, Kokkos::MemoryTraits<1u> >, false, false>::trmm(char const*, char const*, char const*, char const*, double const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)'
CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o: In function `int KokkosBlas::trtri**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > >(char const*, char const*, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)':
Test_Serial_Sparse.cpp:(.text._ZN10KokkosBlas5trtriIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEEEEiPKcSG_RKT_[_ZN10KokkosBlas5trtriIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEEEEiPKcSG_RKT_]+0x463): undefined reference to `KokkosBlas::Impl::TRTRI >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, false, false>::trtri(Kokkos::View > const&, char const*, char const*, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)'
CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o: In function `void KokkosBlas::trmm**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > >(char const*, char const*, char const*, char const*, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >::const_value_type&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)':
Test_Serial_Sparse.cpp:(.text._ZN10KokkosBlas4trmmIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEESE_EEvPKcSG_SG_SG_RNT0_16const_value_typeERKT_RKSH_[_ZN10KokkosBlas4trmmIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEESE_EEvPKcSG_SG_SG_RNT0_16const_value_typeERKT_RKSH_]+0x8de): undefined reference to `KokkosBlas::Impl::TRMM const**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, false, false>::trmm(char const*, char const*, char const*, char const*, Kokkos::complex const&, Kokkos::View const**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)'
../src/libkokkoskernels.a(Sparse_sptrsv_solve_eti_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE.cpp.o): In function `void KokkosBlas::trsm, Kokkos::MemoryTraits<1u> >, Kokkos::View > >(char const*, char const*, char const*, char const*, Kokkos::View >::const_value_type&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&, Kokkos::View > const&)':
Sparse_sptrsv_solve_eti_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE.cpp:(.text._ZN10KokkosBlas4trsmIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEENS2_IS4_JS5_S8_SB_EEEEEvPKcSF_SF_SF_RNT0_16const_value_typeERKT_RKSG_[_ZN10KokkosBlas4trsmIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEENS2_IS4_JS5_S8_SB_EEEEEvPKcSF_SF_SF_RNT0_16const_value_typeERKT_RKSG_]+0x8fe): undefined reference to `KokkosBlas::Impl::TRSM, Kokkos::MemoryTraits<1u> >, Kokkos::View, Kokkos::MemoryTraits<1u> >, false, false>::trsm(char const*, char const*, char const*, char const*, double const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)'
../src/libkokkoskernels.a(Sparse_sptrsv_solve_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE.cpp.o): In function `void KokkosBlas::trsm**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::HostSpace, Kokkos::MemoryTraits<1u> > >(char const*, char const*, char const*, char const*, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::HostSpace, Kokkos::MemoryTraits<1u> >::const_value_type&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::HostSpace, Kokkos::MemoryTraits<1u> > const&)':
Sparse_sptrsv_solve_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE.cpp:(.text._ZN10KokkosBlas4trsmIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEENS2_IS6_JS7_SA_SD_EEEEEvPKcSH_SH_SH_RNT0_16const_value_typeERKT_RKSI_[_ZN10KokkosBlas4trsmIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEENS2_IS6_JS7_SA_SD_EEEEEvPKcSH_SH_SH_RNT0_16const_value_typeERKT_RKSI_]+0x8fe): undefined reference to `KokkosBlas::Impl::TRSM const**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, false, false>::trsm(char const*, char const*, char const*, char const*, Kokkos::complex const&, Kokkos::View const**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)'
clang-10: error: linker command failed with exit code 1 (use -v to see invocation)
make[2]: *** [unit_test/KokkosKernels_sparse_serial] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_sparse_serial.dir/all] Error 2
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
clang-10.0.1-Pthread_Serial-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 clang/10.0.1

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/spack/opt/spack/linux-rhel7-x86_64/gcc-10.2.0/llvm-10.0.1-nldepabrxk2zcykcq7rlky5sr53hnm63/bin/clang++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/KokkosKernels_PullRequest_CLANG1001.88/TestAll_2021-12-31_12.41.30/clang/10.0.1/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013890

salloc: Job allocation 1013890 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE

@kokkos-devops-admin kokkos-devops-admin removed the AT: RETEST Have this PR retested. label Dec 31, 2021
@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Testing Jenkins Projects:

Pull Request Auto Testing STARTING (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740

  • Build Num: 47
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight

  • Build Num: 47
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 705
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 352
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 696
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 683
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_CLANG1001

  • Build Num: 89
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Using Repos:

Repo: KOKKOSKERNELS (vqd8a/kokkos-kernels)
  • Branch: batched_gemm_fix_alpha
  • SHA: 64e92e3
  • Mode: TEST_REPO

Pull Request Author: vqd8a

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Jenkins Testing: 1 or more Jobs FAILED

Note: Testing will normally be attempted again in approx. 2 Hrs 30 Mins. If a change to the PR source branch occurs, the testing will be attempted again on next available autotester run.

Pull Request Auto Testing has FAILED (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740

  • Build Num: 47
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight

  • Build Num: 47
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 705
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 352
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 696
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 683
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_CLANG1001

  • Build Num: 89
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740 # 47 (click to expand) 

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp(744): error: no instance of overloaded function "KokkosBatched::fma_bounds_check" matches the argument list
            argument types are: (Kokkos::View **, Kokkos::Cuda::array_layout, Kokkos::Device, Kokkos::MemoryManaged>, int, int, Kokkos::complex, const double, KokkosBatched::BoundsCheck::Yes)
          detected during:
            instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType &) const [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=32, TILE_N=32, TILE_K=8, MemberType=Kokkos::Impl::CudaTeamMember, REG_M=4, REG_N=4, STRIDE_M=8, STRIDE_N=8]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.47/TestAll_2021-12-31_15.37.30/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(704): here
            instantiation of "std::enable_if::value, void>::type Kokkos::Impl::ParallelFor, Kokkos::Cuda>::exec_team(const Kokkos::Impl::ParallelFor, Kokkos::Cuda>::Member &) const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor, Properties=, TagType=Kokkos::Impl::WorkTagTrait::base_traits::work_tag]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.47/TestAll_2021-12-31_15.37.30/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(755): here
            instantiation of "void Kokkos::Impl::ParallelFor, Kokkos::Cuda>::operator()() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor, Properties=]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.47/TestAll_2021-12-31_15.37.30/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(121): here
            instantiation of "void Kokkos::Impl::cuda_parallel_launch_local_memory(DriverType) [with DriverType=Kokkos::Impl::ParallelFor ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor, Kokkos::TeamPolicy, Kokkos::detected_or_t, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM, Kokkos::View, Kokkos::View, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicy>>]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.47/TestAll_2021-12-31_15.37.30/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(322): here
            instantiation of "std::decay_t))> Kokkos::Impl::CudaParallelLaunchKernelFunc, Kokkos::Impl::Experimental::CudaLaunchMechanism::LocalMemory>::get_kernel_func() [with DriverType=Kokkos::Impl::ParallelFor ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor, Kokkos::TeamPolicy, Kokkos::detected_or_t, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM, Kokkos::View, Kokkos::View, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicy>>]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.47/TestAll_2021-12-31_15.37.30/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(659): here
            [ 3 instantiation contexts not shown ]
            instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=32, TILE_N=32, TILE_K=8]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp(487): here
            instantiation of "int KokkosBatched::BatchedGemm(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(231): here
            instantiation of "void Test::impl_test_batched_gemm(int, int, int, int, int, int, int) [with DeviceType=Kokkos::Cuda, ViewType=Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here
            instantiation of "void test_batched_gemm_with_layout() [with ViewType=Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here
            instantiation of "int test_batched_gemm() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp(744): error: no instance of overloaded function "KokkosBatched::fma_bounds_check" matches the argument list

argument types are: (Kokkos::View<Kokkos::complex **, Kokkos::Cuda::array_layout, Kokkos::Device<Kokkos::CudaUVMSpace::execution_space, Kokkos::CudaUVMSpace::memory_space>, Kokkos::MemoryManaged>, int, int, Kokkos::complex, const double, KokkosBatched::BoundsCheck::Yes)

detected during:

instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::Functor<MemberType, REG_M, REG_N, STRIDE_M, STRIDE_N>::operator()(const MemberType &) const [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1, MemberType=Kokkos::Impl::CudaTeamMember, REG_M=1, REG_N=1, STRIDE_M=1, STRIDE_N=1]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.47/TestAll_2021-12-31_15.37.30/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(704): here

instantiation of "std::enable_if<std::is_same<TagType, void>::value, void>::type Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::exec_team(const Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::Member &) const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Properties=Kokkos::Cuda::execution_space, TagType=Kokkos::Impl::WorkTagTrait::base_traits::work_tag]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.47/TestAll_2021-12-31_15.37.30/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(755): here

instantiation of "void Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::operator()() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Properties=Kokkos::Cuda::execution_space]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.47/TestAll_2021-12-31_15.37.30/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(121): here

instantiation of "void Kokkos::Impl::cuda_parallel_launch_local_memory(DriverType) [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::HostSpace::execution_space, Kokkos::HostSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.47/TestAll_2021-12-31_15.37.30/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(322): here

instantiation of "std::decay_t<decltype(())> Kokkos::Impl::CudaParallelLaunchKernelFunc<DriverType, Kokkos::LaunchBounds<0U, 0U>, Kokkos::Impl::Experimental::CudaLaunchMechanism::LocalMemory>::get_kernel_func() [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::HostSpace::execution_space, Kokkos::HostSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.47/TestAll_2021-12-31_15.37.30/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(659): here

[ 3 instantiation contexts not shown ]

instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp(510): here

instantiation of "int KokkosBatched::BatchedGemm<ArgTransA,ArgTransB,ArgBatchSzDim,BatchedGemmHandleType,ScalarType,AViewType,BViewType,CViewType>(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(231): here

instantiation of "void Test::impl_test_batched_gemm<DeviceType,ViewType,ScalarType,ParamTagType>(int, int, int, int, int, int, int) [with DeviceType=Kokkos::Cuda, ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here

instantiation of "void test_batched_gemm_with_layout<ViewType,DeviceType,ValueType,ScalarType,ParamTagType>() [with ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here

instantiation of "int test_batched_gemm<DeviceType,ValueType,ScalarType,ParamTagType>() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here


48 errors detected in the compilation of "/tmp/tmpxft_00026ea5_00000000-6_Test_Cuda_Batched_Dense.cpp1.ii".

make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_cuda.dir/cuda/Test_Cuda_Batched_Dense.cpp.o] Error 1

make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_cuda.dir/all] Error 2

[ 91%] Linking CXX executable KokkosKernels_batched_sla_cuda

[ 91%] Built target KokkosKernels_batched_sla_cuda

[ 91%] Linking CXX executable KokkosBlas3_gemm_perf_test

[ 91%] Built target KokkosBlas3_gemm_perf_test

[ 91%] Linking CXX executable sparse_kk_spmv

[ 91%] Built target sparse_kk_spmv

[ 91%] Linking CXX executable KokkosKernels_graph_openmp

[ 91%] Built target KokkosKernels_graph_openmp

[ 91%] Linking CXX executable KokkosKernels_common_cuda

[ 91%] Built target KokkosKernels_common_cuda

[ 91%] Linking CXX executable KokkosKernels_blas_cuda

[ 91%] Built target KokkosKernels_blas_cuda

[ 91%] Linking CXX executable KokkosKernels_sparse_openmp

[ 91%] Built target KokkosKernels_sparse_openmp

[ 91%] Linking CXX executable KokkosKernels_sparse_cuda

[ 91%] Built target KokkosKernels_sparse_cuda

make: *** [all] Error 2

#######################################################

PASSED TESTS

#######################################################

#######################################################

FAILED TESTS

#######################################################

cuda-9.2.88-Cuda_OpenMP-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 cuda/9.2.88 gcc/7.2.0 netlib/3.8.0/gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Cuda,OpenMP --arch=Power9,Volta70 --compiler=/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos/bin/nvcc_wrapper --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --with-cuda=/home/projects/ppc64le-pwr9-nvidia/cuda/9.2.88  --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas,cublas,cusparse --user-blas-path=/home/projects/ppc64le-pwr9/netlib/3.8.0/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/netlib/3.8.0/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=force_uvm,enable_lambda   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.47/TestAll_2021-12-31_15.37.30/cuda/9.2.88/Cuda_OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight # 47 (click to expand) 

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here
            instantiation of "void test_batched_gemm_with_layout() [with ViewType=Kokkos::View ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here
            instantiation of "int test_batched_gemm() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp(744): error: no instance of overloaded function "KokkosBatched::fma_bounds_check" matches the argument list

argument types are: (Kokkos::View<Kokkos::complex **, Kokkos::Cuda::array_layout, Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, Kokkos::MemoryManaged>, int, int, Kokkos::complex, const double, KokkosBatched::BoundsCheck::Yes)

detected during:

instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::Functor<MemberType, REG_M, REG_N, STRIDE_M, STRIDE_N>::operator()(const MemberType &) const [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=32, TILE_N=32, TILE_K=8, MemberType=Kokkos::Impl::CudaTeamMember, REG_M=4, REG_N=4, STRIDE_M=8, STRIDE_N=8]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.47/TestAll_2021-12-31_15.37.38/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(704): here

instantiation of "std::enable_if<std::is_same<TagType, void>::value, void>::type Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::exec_team(const Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::Member &) const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Properties=Kokkos::Cuda::execution_space, TagType=Kokkos::Impl::WorkTagTrait::base_traits::work_tag]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.47/TestAll_2021-12-31_15.37.38/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(755): here

instantiation of "void Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::operator()() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Properties=Kokkos::Cuda::execution_space]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.47/TestAll_2021-12-31_15.37.38/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(121): here

instantiation of "void Kokkos::Impl::cuda_parallel_launch_local_memory(DriverType) [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.47/TestAll_2021-12-31_15.37.38/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(322): here

instantiation of "std::decay_t<decltype(())> Kokkos::Impl::CudaParallelLaunchKernelFunc<DriverType, Kokkos::LaunchBounds<0U, 0U>, Kokkos::Impl::Experimental::CudaLaunchMechanism::LocalMemory>::get_kernel_func() [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.47/TestAll_2021-12-31_15.37.38/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(659): here

[ 3 instantiation contexts not shown ]

instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=32, TILE_N=32, TILE_K=8]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp(487): here

instantiation of "int KokkosBatched::BatchedGemm<ArgTransA,ArgTransB,ArgBatchSzDim,BatchedGemmHandleType,ScalarType,AViewType,BViewType,CViewType>(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(231): here

instantiation of "void Test::impl_test_batched_gemm<DeviceType,ViewType,ScalarType,ParamTagType>(int, int, int, int, int, int, int) [with DeviceType=Kokkos::Cuda, ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here

instantiation of "void test_batched_gemm_with_layout<ViewType,DeviceType,ValueType,ScalarType,ParamTagType>() [with ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here

instantiation of "int test_batched_gemm<DeviceType,ValueType,ScalarType,ParamTagType>() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here


/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp(744): error: no instance of overloaded function "KokkosBatched::fma_bounds_check" matches the argument list

argument types are: (Kokkos::View<Kokkos::complex **, Kokkos::Cuda::array_layout, Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, Kokkos::MemoryManaged>, int, int, Kokkos::complex, const double, KokkosBatched::BoundsCheck::Yes)

detected during:

instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::Functor<MemberType, REG_M, REG_N, STRIDE_M, STRIDE_N>::operator()(const MemberType &) const [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1, MemberType=Kokkos::Impl::CudaTeamMember, REG_M=1, REG_N=1, STRIDE_M=1, STRIDE_N=1]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.47/TestAll_2021-12-31_15.37.38/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(704): here

instantiation of "std::enable_if<std::is_same<TagType, void>::value, void>::type Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::exec_team(const Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::Member &) const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Properties=Kokkos::Cuda::execution_space, TagType=Kokkos::Impl::WorkTagTrait::base_traits::work_tag]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.47/TestAll_2021-12-31_15.37.38/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(755): here

instantiation of "void Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::operator()() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Properties=Kokkos::Cuda::execution_space]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.47/TestAll_2021-12-31_15.37.38/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(121): here

instantiation of "void Kokkos::Impl::cuda_parallel_launch_local_memory(DriverType) [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.47/TestAll_2021-12-31_15.37.38/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(322): here

instantiation of "std::decay_t<decltype(())> Kokkos::Impl::CudaParallelLaunchKernelFunc<DriverType, Kokkos::LaunchBounds<0U, 0U>, Kokkos::Impl::Experimental::CudaLaunchMechanism::LocalMemory>::get_kernel_func() [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.47/TestAll_2021-12-31_15.37.38/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(659): here

[ 3 instantiation contexts not shown ]

instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp(510): here

instantiation of "int KokkosBatched::BatchedGemm<ArgTransA,ArgTransB,ArgBatchSzDim,BatchedGemmHandleType,ScalarType,AViewType,BViewType,CViewType>(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(231): here

instantiation of "void Test::impl_test_batched_gemm<DeviceType,ViewType,ScalarType,ParamTagType>(int, int, int, int, int, int, int) [with DeviceType=Kokkos::Cuda, ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here

instantiation of "void test_batched_gemm_with_layout<ViewType,DeviceType,ValueType,ScalarType,ParamTagType>() [with ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here

instantiation of "int test_batched_gemm<DeviceType,ValueType,ScalarType,ParamTagType>() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here


48 errors detected in the compilation of "/tmp/tmpxft_0001c509_00000000-6_Test_Cuda_Batched_Dense.cpp1.ii".

make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_cuda.dir/cuda/Test_Cuda_Batched_Dense.cpp.o] Error 1

make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_cuda.dir/all] Error 2

[ 91%] Linking CXX executable KokkosKernels_batched_sla_cuda

[ 91%] Built target KokkosKernels_batched_sla_cuda

[ 91%] Linking CXX executable KokkosKernels_common_serial

[ 91%] Built target KokkosKernels_common_serial

[ 91%] Linking CXX executable KokkosBlas3_gemm_perf_test

[ 91%] Built target KokkosBlas3_gemm_perf_test

[ 91%] Linking CXX executable sparse_kk_spmv

[ 91%] Built target sparse_kk_spmv

[ 91%] Linking CXX executable KokkosKernels_sparse_serial

[ 91%] Built target KokkosKernels_sparse_serial

make: *** [all] Error 2

#######################################################

PASSED TESTS

#######################################################

#######################################################

FAILED TESTS

#######################################################

cuda-10.1.243-Cuda_Serial-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 cuda/10.1.243 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Cuda,Serial --arch=Power9,Volta70 --compiler=/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos/bin/nvcc_wrapper --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --with-cuda=/home/projects/ppc64le-pwr9-nvidia/cuda/10.1.243  --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas,cublas,cusparse --user-blas-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=,enable_lambda   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.47/TestAll_2021-12-31_15.37.38/cuda/10.1.243/Cuda_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC720 # 705 (click to expand) 

 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched_Dense.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
[ 88%] Linking CXX executable KokkosKernels_common_openmp
[ 88%] Built target KokkosKernels_common_openmp
[ 89%] Linking CXX executable KokkosKernels_blas_openmp
[ 89%] Built target KokkosKernels_blas_openmp
[ 89%] Linking CXX executable KokkosKernels_graph_openmp
[ 89%] Built target KokkosKernels_graph_openmp
[ 89%] Linking CXX executable KokkosKernels_sparse_openmp
[ 89%] Built target KokkosKernels_sparse_openmp
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

gcc-7.2.0-Pthread_Serial-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.705/TestAll_2021-12-31_15.38.53/gcc/7.2.0/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013891

salloc: Job allocation 1013891 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC720_Light_LayoutRight # 352 (click to expand) 

/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
[ 87%] Linking CXX executable sparse_kk_spmv
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched_Dense.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
[ 87%] Built target sparse_kk_spmv
[ 87%] Linking CXX executable KokkosKernels_common_openmp
[ 87%] Built target KokkosKernels_common_openmp
[ 88%] Linking CXX executable KokkosKernels_blas_openmp
[ 88%] Built target KokkosKernels_blas_openmp
[ 88%] Linking CXX executable KokkosKernels_graph_openmp
[ 88%] Built target KokkosKernels_graph_openmp
[ 88%] Linking CXX executable KokkosKernels_sparse_openmp
[ 88%] Built target KokkosKernels_sparse_openmp
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutRight --with-tpls=    --with-options= --with-cuda-options=  --with-spaces=hostspace --no-examples  --no-default-eti


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

gcc-7.2.0-Pthread_Serial-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutRight --with-tpls=    --with-options= --with-cuda-options=  --with-spaces=hostspace --no-examples  --no-default-eti


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.352/TestAll_2021-12-31_15.39.00/gcc/7.2.0/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013892

salloc: Job allocation 1013892 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_GCC720 # 696 (click to expand) 

                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::NoTranspose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::NoTranspose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
[ 86%] Building CXX object unit_test/CMakeFiles/KokkosKernels_blas_serial.dir/serial/Test_Serial_Blas.cpp.o
[ 86%] Building CXX object unit_test/CMakeFiles/KokkosKernels_common_openmp.dir/openmp/Test_OpenMP_Common.cpp.o
make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 1
make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[ 86%] Linking CXX executable KokkosBlas2_gemv_perf_test
[ 86%] Built target KokkosBlas2_gemv_perf_test
[ 87%] Linking CXX executable KokkosKernels_batched_sla_openmp
[ 87%] Built target KokkosKernels_batched_sla_openmp
[ 87%] Linking CXX executable sparse_kk_spmv
[ 87%] Built target sparse_kk_spmv
[ 88%] Linking CXX executable KokkosBlas3_gemm_perf_test
[ 88%] Built target KokkosBlas3_gemm_perf_test
[ 88%] Linking CXX executable KokkosKernels_common_serial
[ 88%] Built target KokkosKernels_common_serial
[ 89%] Linking CXX executable KokkosKernels_common_openmp
[ 89%] Built target KokkosKernels_common_openmp
[ 89%] Linking CXX executable KokkosKernels_blas_openmp
[ 89%] Built target KokkosKernels_blas_openmp
[ 89%] Linking CXX executable KokkosKernels_graph_openmp
[ 89%] Built target KokkosKernels_graph_openmp
[ 89%] Linking CXX executable KokkosKernels_blas_serial
[ 89%] Built target KokkosKernels_blas_serial
[ 89%] Linking CXX executable KokkosKernels_sparse_openmp
[ 89%] Built target KokkosKernels_sparse_openmp
[ 90%] Linking CXX executable KokkosKernels_sparse_serial
[ 90%] Built target KokkosKernels_sparse_serial
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP_Serial-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas --user-blas-path=/home/projects/x86-64-skylake/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/x86-64-skylake/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.696/TestAll_2021-12-31_15.39.10/gcc/7.2.0/OpenMP_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013893

salloc: Job allocation 1013893 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_INTEL18 # 683 (click to expand) 

            instantiation of "void Kokkos::Impl::ParallelFor, Kokkos::Threads>::execute() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm::Functor, Properties=]" at line 144 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.683/TestAll_2021-12-31_15.39.21/intel/18.1.163/Pthread-release/kokkos-install/include/Kokkos_Parallel.hpp"
            instantiation of "void Kokkos::parallel_for(const ExecPolicy &, const FunctorType &, const std::__cxx11::string &, std::enable_if::value, void>::type *) [with ExecPolicy=Kokkos::TeamPolicy, FunctorType=KokkosBatched::Impl::BatchedDblBufGemm::Functor]" at line 175 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.683/TestAll_2021-12-31_15.39.21/intel/18.1.163/Pthread-release/kokkos-install/include/Kokkos_Parallel.hpp"
            instantiation of "void Kokkos::parallel_for(const std::__cxx11::string &, const ExecPolicy &, const FunctorType &) [with ExecPolicy=Kokkos::TeamPolicy, FunctorType=KokkosBatched::Impl::BatchedDblBufGemm::Functor]" at line 191
            instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm::__run() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Left, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double}, AViewType=vector_view_type_3d, BViewType=vector_view_type_3d,
                      CViewType=vector_view_type_3d, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1]" at line 108
            instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Left, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double}, AViewType=vector_view_type_3d, BViewType=vector_view_type_3d,
                      CViewType=vector_view_type_3d, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1]" at line 510 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp"
            instantiation of "int KokkosBatched::BatchedGemm(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Left, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double},
                      AViewType=vector_view_type_3d, BViewType=vector_view_type_3d, CViewType=vector_view_type_3d]" at line 562 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"
            instantiation of "void __do_gemm_parallel_batched_heuristic_template(options_t, gemm_args_t) [with algo_tag=void, blocking_type=void, device_type=default_device, algo_mode=void]" at line 589 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"
            instantiation of "void __do_gemm_parallel_batched_heuristic(options_t, gemm_args_t) [with algo_tag=void, blocking_type=void, device_type=default_device, algo_mode=void]" at line 2265 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"

[ 76%] Linking CXX executable KokkosKernels_wiki_mis2

[ 76%] Built target KokkosKernels_wiki_mis2

Scanning dependencies of target KokkosKernels_gmres_test_real_A

[ 78%] Building CXX object example/gmres/CMakeFiles/KokkosKernels_gmres_test_real_A.dir/test_real_A.cpp.o

[ 79%] Linking CXX executable KokkosKernels_wiki_rcm

compilation aborted for /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_perf_test.cpp (code 2)

make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 2

make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2

make[1]: *** Waiting for unfinished jobs....

[ 79%] Built target KokkosKernels_wiki_rcm

[ 80%] Linking CXX executable KokkosKernels_wiki_coarsening

[ 80%] Built target KokkosKernels_wiki_coarsening

[ 81%] Linking CXX executable KokkosKernels_wiki_coloring

[ 81%] Built target KokkosKernels_wiki_coloring

[ 82%] Linking CXX executable KokkosKernels_gmres_test_real_A

[ 82%] Built target KokkosKernels_gmres_test_real_A

[ 83%] Linking CXX executable sparse_kk_spmv

[ 83%] Built target sparse_kk_spmv

[ 84%] Linking CXX executable KokkosKernels_wiki_spgemm

[ 84%] Built target KokkosKernels_wiki_spgemm

[ 85%] Linking CXX executable sparse_pcg

[ 85%] Built target sparse_pcg

[ 86%] Linking CXX executable sparse_block_pcg

[ 86%] Built target sparse_block_pcg

[ 87%] Linking CXX executable KokkosKernels_wiki_gauss_seidel

[ 87%] Built target KokkosKernels_wiki_gauss_seidel

[ 89%] Linking CXX executable sparse_spmv_struct

[ 89%] Built target sparse_spmv_struct

[ 90%] Linking CXX executable sparse_spmv_struct_tuning

[ 90%] Built target sparse_spmv_struct_tuning

make: *** [all] Error 2

#######################################################

PASSED TESTS

#######################################################

#######################################################

FAILED TESTS

#######################################################

intel-18.1.163-OpenMP-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 intel/compilers/18.1.163



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/intel/compilers/2018/compilers_and_libraries_2018.1.163/linux/bin/intel64/icpc --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=mkl    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.683/TestAll_2021-12-31_15.39.21/intel/18.1.163/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

intel-18.1.163-Pthread-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 intel/compilers/18.1.163



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread --arch=SKX --compiler=/home/projects/x86-64/intel/compilers/2018/compilers_and_libraries_2018.1.163/linux/bin/intel64/icpc --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=mkl    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.683/TestAll_2021-12-31_15.39.21/intel/18.1.163/Pthread-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013894

salloc: Job allocation 1013894 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG1001 # 89 (click to expand) 

    ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:479:20: note: in instantiation of member function 'KokkosBatched::Impl::BatchedDblBufGemm, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, Kokkos::View, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, Kokkos::View, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, KokkosBatched::BoundsCheck::No, 32, 32, 8>::invoke' requested here
                  .invoke();
                   ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp:552:24: note: in instantiation of function template specialization 'KokkosBatched::BatchedGemm, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, Kokkos::View, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, Kokkos::View, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads> >' requested here
        KokkosBatched::BatchedGemm(
                       ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp:587:5: note: in instantiation of function template specialization '__do_gemm_parallel_batched_heuristic_template' requested here
    __do_gemm_parallel_batched_heuristic_template' requested here
      __do_gemm_parallel_batched_heuristic);
      ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/KokkosBatched_Util.hpp:858:29: note: candidate template ignored: deduced conflicting types for parameter 'ScalarType' ('KokkosBatched::Vector, 8>' vs. 'double')
KOKKOS_INLINE_FUNCTION void fma_bounds_check(ViewType v, SizeType m, SizeType n,
                            ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/KokkosBatched_Util.hpp:865:29: note: candidate template ignored: deduced conflicting types for parameter 'ScalarType' ('KokkosBatched::Vector, 8>' vs. 'double')
KOKKOS_INLINE_FUNCTION void fma_bounds_check(ViewType v, SizeType m, SizeType n,
                            ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/KokkosBatched_Util.hpp:841:29: note: candidate function template not viable: requires 7 arguments, but 6 were provided
KOKKOS_INLINE_FUNCTION void fma_bounds_check(ViewType v, SizeType m, SizeType n,
                            ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/KokkosBatched_Util.hpp:850:29: note: candidate function template not viable: requires 7 arguments, but 6 were provided
KOKKOS_INLINE_FUNCTION void fma_bounds_check(ViewType v, SizeType m, SizeType n,
                            ^
fatal error: too many errors emitted, stopping now [-ferror-limit=]
20 errors generated.
make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 1
make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[ 78%] Building CXX object unit_test/CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o
[ 78%] Linking CXX executable KokkosBlas2_gemv_perf_test
[ 78%] Built target KokkosBlas2_gemv_perf_test
[ 79%] Linking CXX executable sparse_sptrsv_supernode
[ 79%] Built target sparse_sptrsv_supernode
[ 80%] Linking CXX executable KokkosBlas3_gemm_perf_test
[ 80%] Built target KokkosBlas3_gemm_perf_test
[ 80%] Linking CXX executable sparse_spmv_struct
[ 80%] Built target sparse_spmv_struct
[ 81%] Linking CXX executable KokkosKernels_batched_sla_serial
[ 81%] Built target KokkosKernels_batched_sla_serial
[ 81%] Linking CXX executable sparse_kk_spmv
[ 81%] Built target sparse_kk_spmv
[ 81%] Linking CXX executable sparse_pcg
[ 81%] Built target sparse_pcg
[ 82%] Linking CXX executable sparse_block_pcg
[ 82%] Built target sparse_block_pcg
[ 83%] Linking CXX executable KokkosKernels_blas_serial
[ 83%] Built target KokkosKernels_blas_serial
[ 84%] Linking CXX executable sparse_gs
[ 84%] Built target sparse_gs
[ 84%] Linking CXX executable KokkosKernels_sparse_serial
CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o: In function `int KokkosBlas::trtri, Kokkos::MemoryTraits<1u> > >(char const*, char const*, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)':
Test_Serial_Sparse.cpp:(.text._ZN10KokkosBlas5trtriIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEEEEiPKcSE_RKT_[_ZN10KokkosBlas5trtriIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEEEEiPKcSE_RKT_]+0x463): undefined reference to `KokkosBlas::Impl::TRTRI >, Kokkos::View, Kokkos::MemoryTraits<1u> >, false, false>::trtri(Kokkos::View > const&, char const*, char const*, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)'
CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o: In function `void KokkosBlas::trmm, Kokkos::MemoryTraits<1u> >, Kokkos::View, Kokkos::MemoryTraits<1u> > >(char const*, char const*, char const*, char const*, Kokkos::View, Kokkos::MemoryTraits<1u> >::const_value_type&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)':
Test_Serial_Sparse.cpp:(.text._ZN10KokkosBlas4trmmIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEESC_EEvPKcSE_SE_SE_RNT0_16const_value_typeERKT_RKSF_[_ZN10KokkosBlas4trmmIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEESC_EEvPKcSE_SE_SE_RNT0_16const_value_typeERKT_RKSF_]+0x8de): undefined reference to `KokkosBlas::Impl::TRMM, Kokkos::MemoryTraits<1u> >, Kokkos::View, Kokkos::MemoryTraits<1u> >, false, false>::trmm(char const*, char const*, char const*, char const*, double const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)'
CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o: In function `int KokkosBlas::trtri**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > >(char const*, char const*, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)':
Test_Serial_Sparse.cpp:(.text._ZN10KokkosBlas5trtriIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEEEEiPKcSG_RKT_[_ZN10KokkosBlas5trtriIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEEEEiPKcSG_RKT_]+0x463): undefined reference to `KokkosBlas::Impl::TRTRI >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, false, false>::trtri(Kokkos::View > const&, char const*, char const*, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)'
CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o: In function `void KokkosBlas::trmm**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > >(char const*, char const*, char const*, char const*, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >::const_value_type&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)':
Test_Serial_Sparse.cpp:(.text._ZN10KokkosBlas4trmmIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEESE_EEvPKcSG_SG_SG_RNT0_16const_value_typeERKT_RKSH_[_ZN10KokkosBlas4trmmIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEESE_EEvPKcSG_SG_SG_RNT0_16const_value_typeERKT_RKSH_]+0x8de): undefined reference to `KokkosBlas::Impl::TRMM const**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, false, false>::trmm(char const*, char const*, char const*, char const*, Kokkos::complex const&, Kokkos::View const**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)'
../src/libkokkoskernels.a(Sparse_sptrsv_solve_eti_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE.cpp.o): In function `void KokkosBlas::trsm, Kokkos::MemoryTraits<1u> >, Kokkos::View > >(char const*, char const*, char const*, char const*, Kokkos::View >::const_value_type&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&, Kokkos::View > const&)':
Sparse_sptrsv_solve_eti_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE.cpp:(.text._ZN10KokkosBlas4trsmIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEENS2_IS4_JS5_S8_SB_EEEEEvPKcSF_SF_SF_RNT0_16const_value_typeERKT_RKSG_[_ZN10KokkosBlas4trsmIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEENS2_IS4_JS5_S8_SB_EEEEEvPKcSF_SF_SF_RNT0_16const_value_typeERKT_RKSG_]+0x8fe): undefined reference to `KokkosBlas::Impl::TRSM, Kokkos::MemoryTraits<1u> >, Kokkos::View, Kokkos::MemoryTraits<1u> >, false, false>::trsm(char const*, char const*, char const*, char const*, double const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)'
../src/libkokkoskernels.a(Sparse_sptrsv_solve_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE.cpp.o): In function `void KokkosBlas::trsm**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::HostSpace, Kokkos::MemoryTraits<1u> > >(char const*, char const*, char const*, char const*, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::HostSpace, Kokkos::MemoryTraits<1u> >::const_value_type&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::HostSpace, Kokkos::MemoryTraits<1u> > const&)':
Sparse_sptrsv_solve_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE.cpp:(.text._ZN10KokkosBlas4trsmIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEENS2_IS6_JS7_SA_SD_EEEEEvPKcSH_SH_SH_RNT0_16const_value_typeERKT_RKSI_[_ZN10KokkosBlas4trsmIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEENS2_IS6_JS7_SA_SD_EEEEEvPKcSH_SH_SH_RNT0_16const_value_typeERKT_RKSI_]+0x8fe): undefined reference to `KokkosBlas::Impl::TRSM const**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, false, false>::trsm(char const*, char const*, char const*, char const*, Kokkos::complex const&, Kokkos::View const**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)'
clang-10: error: linker command failed with exit code 1 (use -v to see invocation)
make[2]: *** [unit_test/KokkosKernels_sparse_serial] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_sparse_serial.dir/all] Error 2
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
clang-10.0.1-Pthread_Serial-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 clang/10.0.1

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/spack/opt/spack/linux-rhel7-x86_64/gcc-10.2.0/llvm-10.0.1-nldepabrxk2zcykcq7rlky5sr53hnm63/bin/clang++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/KokkosKernels_PullRequest_CLANG1001.89/TestAll_2021-12-31_15.39.30/clang/10.0.1/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013895

salloc: Job allocation 1013895 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Testing Jenkins Projects:

Pull Request Auto Testing STARTING (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740

  • Build Num: 48
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight

  • Build Num: 48
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 706
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 353
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 697
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 684
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_CLANG1001

  • Build Num: 90
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Using Repos:

Repo: KOKKOSKERNELS (vqd8a/kokkos-kernels)
  • Branch: batched_gemm_fix_alpha
  • SHA: 64e92e3
  • Mode: TEST_REPO

Pull Request Author: vqd8a

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Jenkins Testing: 1 or more Jobs FAILED

Note: Testing will normally be attempted again in approx. 2 Hrs 30 Mins. If a change to the PR source branch occurs, the testing will be attempted again on next available autotester run.

Pull Request Auto Testing has FAILED (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740

  • Build Num: 48
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight

  • Build Num: 48
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 706
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 353
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 697
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 684
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_CLANG1001

  • Build Num: 90
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 64e92e3
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740 # 48 (click to expand) 

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp(744): error: no instance of overloaded function "KokkosBatched::fma_bounds_check" matches the argument list

argument types are: (Kokkos::View<Kokkos::complex **, Kokkos::Cuda::array_layout, Kokkos::Device<Kokkos::CudaUVMSpace::execution_space, Kokkos::CudaUVMSpace::memory_space>, Kokkos::MemoryManaged>, int, int, Kokkos::complex, const double, KokkosBatched::BoundsCheck::Yes)

detected during:

instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::Functor<MemberType, REG_M, REG_N, STRIDE_M, STRIDE_N>::operator()(const MemberType &) const [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=32, TILE_N=32, TILE_K=8, MemberType=Kokkos::Impl::CudaTeamMember, REG_M=4, REG_N=4, STRIDE_M=8, STRIDE_N=8]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.48/TestAll_2021-12-31_18.35.35/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(704): here

instantiation of "std::enable_if<std::is_same<TagType, void>::value, void>::type Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::exec_team(const Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::Member &) const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Properties=Kokkos::Cuda::execution_space, TagType=Kokkos::Impl::WorkTagTrait::base_traits::work_tag]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.48/TestAll_2021-12-31_18.35.35/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(755): here

instantiation of "void Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::operator()() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Properties=Kokkos::Cuda::execution_space]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.48/TestAll_2021-12-31_18.35.35/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(121): here

instantiation of "void Kokkos::Impl::cuda_parallel_launch_local_memory(DriverType) [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::HostSpace::execution_space, Kokkos::HostSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.48/TestAll_2021-12-31_18.35.35/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(322): here

instantiation of "std::decay_t<decltype(())> Kokkos::Impl::CudaParallelLaunchKernelFunc<DriverType, Kokkos::LaunchBounds<0U, 0U>, Kokkos::Impl::Experimental::CudaLaunchMechanism::LocalMemory>::get_kernel_func() [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::HostSpace::execution_space, Kokkos::HostSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.48/TestAll_2021-12-31_18.35.35/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(659): here

[ 3 instantiation contexts not shown ]

instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=32, TILE_N=32, TILE_K=8]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp(487): here

instantiation of "int KokkosBatched::BatchedGemm<ArgTransA,ArgTransB,ArgBatchSzDim,BatchedGemmHandleType,ScalarType,AViewType,BViewType,CViewType>(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(231): here

instantiation of "void Test::impl_test_batched_gemm<DeviceType,ViewType,ScalarType,ParamTagType>(int, int, int, int, int, int, int) [with DeviceType=Kokkos::Cuda, ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here

instantiation of "void test_batched_gemm_with_layout<ViewType,DeviceType,ValueType,ScalarType,ParamTagType>() [with ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here

instantiation of "int test_batched_gemm<DeviceType,ValueType,ScalarType,ParamTagType>() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here


/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp(744): error: no instance of overloaded function "KokkosBatched::fma_bounds_check" matches the argument list

argument types are: (Kokkos::View<Kokkos::complex **, Kokkos::Cuda::array_layout, Kokkos::Device<Kokkos::CudaUVMSpace::execution_space, Kokkos::CudaUVMSpace::memory_space>, Kokkos::MemoryManaged>, int, int, Kokkos::complex, const double, KokkosBatched::BoundsCheck::Yes)

detected during:

instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::Functor<MemberType, REG_M, REG_N, STRIDE_M, STRIDE_N>::operator()(const MemberType &) const [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1, MemberType=Kokkos::Impl::CudaTeamMember, REG_M=1, REG_N=1, STRIDE_M=1, STRIDE_N=1]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.48/TestAll_2021-12-31_18.35.35/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(704): here

instantiation of "std::enable_if<std::is_same<TagType, void>::value, void>::type Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::exec_team(const Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::Member &) const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Properties=Kokkos::Cuda::execution_space, TagType=Kokkos::Impl::WorkTagTrait::base_traits::work_tag]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.48/TestAll_2021-12-31_18.35.35/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(755): here

instantiation of "void Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::operator()() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Properties=Kokkos::Cuda::execution_space]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.48/TestAll_2021-12-31_18.35.35/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(121): here

instantiation of "void Kokkos::Impl::cuda_parallel_launch_local_memory(DriverType) [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::HostSpace::execution_space, Kokkos::HostSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.48/TestAll_2021-12-31_18.35.35/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(322): here

instantiation of "std::decay_t<decltype(())> Kokkos::Impl::CudaParallelLaunchKernelFunc<DriverType, Kokkos::LaunchBounds<0U, 0U>, Kokkos::Impl::Experimental::CudaLaunchMechanism::LocalMemory>::get_kernel_func() [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::HostSpace::execution_space, Kokkos::HostSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.48/TestAll_2021-12-31_18.35.35/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(659): here

[ 3 instantiation contexts not shown ]

instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp(510): here

instantiation of "int KokkosBatched::BatchedGemm<ArgTransA,ArgTransB,ArgBatchSzDim,BatchedGemmHandleType,ScalarType,AViewType,BViewType,CViewType>(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(231): here

instantiation of "void Test::impl_test_batched_gemm<DeviceType,ViewType,ScalarType,ParamTagType>(int, int, int, int, int, int, int) [with DeviceType=Kokkos::Cuda, ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here

instantiation of "void test_batched_gemm_with_layout<ViewType,DeviceType,ValueType,ScalarType,ParamTagType>() [with ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here

instantiation of "int test_batched_gemm<DeviceType,ValueType,ScalarType,ParamTagType>() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here


48 errors detected in the compilation of "/tmp/tmpxft_00008574_00000000-6_Test_Cuda_Batched_Dense.cpp1.ii".

make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_cuda.dir/cuda/Test_Cuda_Batched_Dense.cpp.o] Error 1

make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_cuda.dir/all] Error 2

[ 91%] Linking CXX executable KokkosKernels_batched_sla_cuda

[ 91%] Linking CXX executable KokkosBlas3_gemm_perf_test

[ 91%] Built target KokkosKernels_batched_sla_cuda

[ 91%] Built target KokkosBlas3_gemm_perf_test

[ 91%] Linking CXX executable sparse_kk_spmv

[ 91%] Built target sparse_kk_spmv

[ 91%] Linking CXX executable KokkosKernels_graph_openmp

[ 91%] Built target KokkosKernels_graph_openmp

[ 91%] Linking CXX executable KokkosKernels_blas_cuda

[ 91%] Built target KokkosKernels_blas_cuda

[ 91%] Linking CXX executable KokkosKernels_sparse_openmp

[ 91%] Built target KokkosKernels_sparse_openmp

[ 91%] Linking CXX executable KokkosKernels_sparse_cuda

[ 91%] Built target KokkosKernels_sparse_cuda

make: *** [all] Error 2

#######################################################

PASSED TESTS

#######################################################

#######################################################

FAILED TESTS

#######################################################

cuda-9.2.88-Cuda_OpenMP-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 cuda/9.2.88 gcc/7.2.0 netlib/3.8.0/gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Cuda,OpenMP --arch=Power9,Volta70 --compiler=/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos/bin/nvcc_wrapper --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --with-cuda=/home/projects/ppc64le-pwr9-nvidia/cuda/9.2.88  --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas,cublas,cusparse --user-blas-path=/home/projects/ppc64le-pwr9/netlib/3.8.0/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/netlib/3.8.0/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=force_uvm,enable_lambda   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.48/TestAll_2021-12-31_18.35.35/cuda/9.2.88/Cuda_OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight # 48 (click to expand) 

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here
            instantiation of "int test_batched_gemm() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag]" 
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp(744): error: no instance of overloaded function "KokkosBatched::fma_bounds_check" matches the argument list

argument types are: (Kokkos::View<Kokkos::complex **, Kokkos::Cuda::array_layout, Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, Kokkos::MemoryManaged>, int, int, Kokkos::complex, const double, KokkosBatched::BoundsCheck::Yes)

detected during:

instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::Functor<MemberType, REG_M, REG_N, STRIDE_M, STRIDE_N>::operator()(const MemberType &) const [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=32, TILE_N=32, TILE_K=8, MemberType=Kokkos::Impl::CudaTeamMember, REG_M=4, REG_N=4, STRIDE_M=8, STRIDE_N=8]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.48/TestAll_2021-12-31_18.35.44/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(704): here

instantiation of "std::enable_if<std::is_same<TagType, void>::value, void>::type Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::exec_team(const Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::Member &) const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Properties=Kokkos::Cuda::execution_space, TagType=Kokkos::Impl::WorkTagTrait::base_traits::work_tag]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.48/TestAll_2021-12-31_18.35.44/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(755): here

instantiation of "void Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::operator()() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Properties=Kokkos::Cuda::execution_space]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.48/TestAll_2021-12-31_18.35.44/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(121): here

instantiation of "void Kokkos::Impl::cuda_parallel_launch_local_memory(DriverType) [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.48/TestAll_2021-12-31_18.35.44/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(322): here

instantiation of "std::decay_t<decltype(())> Kokkos::Impl::CudaParallelLaunchKernelFunc<DriverType, Kokkos::LaunchBounds<0U, 0U>, Kokkos::Impl::Experimental::CudaLaunchMechanism::LocalMemory>::get_kernel_func() [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 32, 32, 8>::Functor<Kokkos::Impl::CudaTeamMember, 4, 4, 8, 8>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.48/TestAll_2021-12-31_18.35.44/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(659): here

[ 3 instantiation contexts not shown ]

instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=32, TILE_N=32, TILE_K=8]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp(487): here

instantiation of "int KokkosBatched::BatchedGemm<ArgTransA,ArgTransB,ArgBatchSzDim,BatchedGemmHandleType,ScalarType,AViewType,BViewType,CViewType>(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(231): here

instantiation of "void Test::impl_test_batched_gemm<DeviceType,ViewType,ScalarType,ParamTagType>(int, int, int, int, int, int, int) [with DeviceType=Kokkos::Cuda, ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here

instantiation of "void test_batched_gemm_with_layout<ViewType,DeviceType,ValueType,ScalarType,ParamTagType>() [with ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here

instantiation of "int test_batched_gemm<DeviceType,ValueType,ScalarType,ParamTagType>() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here


/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp(744): error: no instance of overloaded function "KokkosBatched::fma_bounds_check" matches the argument list

argument types are: (Kokkos::View<Kokkos::complex **, Kokkos::Cuda::array_layout, Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, Kokkos::MemoryManaged>, int, int, Kokkos::complex, const double, KokkosBatched::BoundsCheck::Yes)

detected during:

instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::Functor<MemberType, REG_M, REG_N, STRIDE_M, STRIDE_N>::operator()(const MemberType &) const [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1, MemberType=Kokkos::Impl::CudaTeamMember, REG_M=1, REG_N=1, STRIDE_M=1, STRIDE_N=1]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.48/TestAll_2021-12-31_18.35.44/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(704): here

instantiation of "std::enable_if<std::is_same<TagType, void>::value, void>::type Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::exec_team(const Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::Member &) const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Properties=Kokkos::Cuda::execution_space, TagType=Kokkos::Impl::WorkTagTrait::base_traits::work_tag]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.48/TestAll_2021-12-31_18.35.44/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_Parallel.hpp(755): here

instantiation of "void Kokkos::Impl::ParallelFor<FunctorType, Kokkos::TeamPolicy<Properties...>, Kokkos::Cuda>::operator()() const [with FunctorType=KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Properties=Kokkos::Cuda::execution_space]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.48/TestAll_2021-12-31_18.35.44/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(121): here

instantiation of "void Kokkos::Impl::cuda_parallel_launch_local_memory(DriverType) [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.48/TestAll_2021-12-31_18.35.44/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(322): here

instantiation of "std::decay_t<decltype(())> Kokkos::Impl::CudaParallelLaunchKernelFunc<DriverType, Kokkos::LaunchBounds<0U, 0U>, Kokkos::Impl::Experimental::CudaLaunchMechanism::LocalMemory>::get_kernel_func() [with DriverType=Kokkos::Impl::ParallelFor<KokkosBatched::Impl::BatchedDblBufGemm<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right, KokkosBatched::BatchedGemmHandle, double, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor<Kokkos::Impl::CudaTeamMember, 1, 1, 1, 1>, Kokkos::TeamPolicyKokkos::Cuda::execution_space, Kokkos::detected_or_t<Kokkos::detected_or_t<std::conditional_t<false, Kokkos::detected_t<Kokkos::Impl::execution_space_t, Kokkos::detected_t<Kokkos::Impl::device_type_t, Kokkos::Impl::ViewValueFunctor<Kokkos::Device<Kokkos::CudaSpace::execution_space, Kokkos::CudaSpace::memory_space>, uint32_t, true>>>, Kokkos::DefaultExecutionSpace>, Kokkos::Impl::execution_space_t, Test::Functor_BatchedVanillaGEMM<Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::View<Test::halfScalarType ***, Kokkos::LayoutLeft, Kokkos::Cuda>, Kokkos::Cuda::execution_space>>, Kokkos::Impl::execution_space_t, Kokkos::TeamPolicyKokkos::Cuda::execution_space>>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.48/TestAll_2021-12-31_18.35.44/cuda/10.1.243/Cuda_Serial-release/kokkos-install/include/Cuda/Kokkos_Cuda_KernelLaunch.hpp(659): here

[ 3 instantiation contexts not shown ]

instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm<ArgTransA, ArgTransB, ArgBatchSzDim, HandleType, ScalarType, AViewType, BViewType, CViewType, ArgBoundsCheck, TILE_M, TILE_N, TILE_K>::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp(510): here

instantiation of "int KokkosBatched::BatchedGemm<ArgTransA,ArgTransB,ArgBatchSzDim,BatchedGemmHandleType,ScalarType,AViewType,BViewType,CViewType>(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=double, AViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, BViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, CViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(231): here

instantiation of "void Test::impl_test_batched_gemm<DeviceType,ViewType,ScalarType,ParamTagType>(int, int, int, int, int, int, int) [with DeviceType=Kokkos::Cuda, ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(248): here

instantiation of "void test_batched_gemm_with_layout<ViewType,DeviceType,ValueType,ScalarType,ParamTagType>() [with ViewType=Kokkos::View<Kokkos::complex ***, Kokkos::LayoutLeft, Kokkos::Cuda>, DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp(311): here

instantiation of "int test_batched_gemm<DeviceType,ValueType,ScalarType,ParamTagType>() [with DeviceType=Kokkos::Cuda, ValueType=Kokkos::complex, ScalarType=Kokkos::complex, ParamTagType=Test::SharedParamTag<KokkosBatched::Trans::Transpose, KokkosBatched::Trans::Transpose, KokkosBatched::BatchLayout::Right>]"

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp(166): here


[ 91%] Linking CXX executable sparse_sptrsv_supernode

[ 91%] Built target sparse_sptrsv_supernode

48 errors detected in the compilation of "/tmp/tmpxft_0000cb40_00000000-6_Test_Cuda_Batched_Dense.cpp1.ii".

make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_cuda.dir/cuda/Test_Cuda_Batched_Dense.cpp.o] Error 1

make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_cuda.dir/all] Error 2

[ 91%] Linking CXX executable KokkosKernels_batched_sla_cuda

[ 91%] Built target KokkosKernels_batched_sla_cuda

[ 91%] Linking CXX executable KokkosKernels_common_serial

[ 91%] Built target KokkosKernels_common_serial

[ 91%] Linking CXX executable KokkosBlas3_gemm_perf_test

[ 91%] Built target KokkosBlas3_gemm_perf_test

[ 91%] Linking CXX executable sparse_kk_spmv

[ 91%] Built target sparse_kk_spmv

[ 91%] Linking CXX executable KokkosKernels_sparse_serial

[ 91%] Built target KokkosKernels_sparse_serial

make: *** [all] Error 2

#######################################################

PASSED TESTS

#######################################################

#######################################################

FAILED TESTS

#######################################################

cuda-10.1.243-Cuda_Serial-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 cuda/10.1.243 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Cuda,Serial --arch=Power9,Volta70 --compiler=/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos/bin/nvcc_wrapper --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --with-cuda=/home/projects/ppc64le-pwr9-nvidia/cuda/10.1.243  --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas,cublas,cusparse --user-blas-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=,enable_lambda   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.48/TestAll_2021-12-31_18.35.44/cuda/10.1.243/Cuda_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC720 # 706 (click to expand) 

                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
[ 88%] Linking CXX executable sparse_kk_spmv
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched_Dense.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
[ 88%] Built target sparse_kk_spmv
[ 88%] Linking CXX executable KokkosKernels_common_openmp
[ 88%] Built target KokkosKernels_common_openmp
[ 89%] Linking CXX executable KokkosKernels_blas_openmp
[ 89%] Built target KokkosKernels_blas_openmp
[ 89%] Linking CXX executable KokkosKernels_graph_openmp
[ 89%] Built target KokkosKernels_graph_openmp
[ 89%] Linking CXX executable KokkosKernels_sparse_openmp
[ 89%] Built target KokkosKernels_sparse_openmp
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

gcc-7.2.0-Pthread_Serial-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.706/TestAll_2021-12-31_18.35.56/gcc/7.2.0/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013898

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC720_Light_LayoutRight # 353 (click to expand) 

/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::NoTranspose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/OpenMP-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutRight, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched_Dense.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
[ 87%] Linking CXX executable sparse_kk_spmv
[ 87%] Built target sparse_kk_spmv
[ 87%] Linking CXX executable KokkosKernels_common_openmp
[ 87%] Built target KokkosKernels_common_openmp
[ 88%] Linking CXX executable KokkosKernels_blas_openmp
[ 88%] Built target KokkosKernels_blas_openmp
[ 88%] Linking CXX executable KokkosKernels_graph_openmp
[ 88%] Built target KokkosKernels_graph_openmp
[ 88%] Linking CXX executable KokkosKernels_sparse_openmp
[ 88%] Built target KokkosKernels_sparse_openmp
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutRight --with-tpls=    --with-options= --with-cuda-options=  --with-spaces=hostspace --no-examples  --no-default-eti


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

gcc-7.2.0-Pthread_Serial-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutRight --with-tpls=    --with-options= --with-cuda-options=  --with-spaces=hostspace --no-examples  --no-default-eti


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.353/TestAll_2021-12-31_18.36.06/gcc/7.2.0/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013899

salloc: Job allocation 1013899 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_GCC720 # 697 (click to expand) 

 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:847:29: error: void Kokkos::parallel_for(const Kokkos::Impl::ThreadVectorRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/impl/Kokkos_HostThreadTeam.hpp:835:29: error: void Kokkos::parallel_for(const Kokkos::Impl::TeamThreadRangeBoundariesStruct&, const Closure&, const typename std::enable_if::value>::type**) [with iType = int; Closure = KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::; Member = Kokkos::Impl::HostThreadTeamMember; typename std::enable_if::value>::type = void], declared using local type const KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Left; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = double; AViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View, 8>***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::, is used but never defined [-fpermissive]
 KOKKOS_INLINE_FUNCTION void parallel_for(
                             ^~~~~~~~~~~~
[ 86%] Building CXX object unit_test/CMakeFiles/KokkosKernels_blas_serial.dir/serial/Test_Serial_Blas.cpp.o
Scanning dependencies of target KokkosKernels_common_openmp
[ 86%] Building CXX object unit_test/CMakeFiles/KokkosKernels_common_openmp.dir/Test_Main.cpp.o
make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 1
make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[ 86%] Building CXX object unit_test/CMakeFiles/KokkosKernels_common_openmp.dir/openmp/Test_OpenMP_Common.cpp.o
[ 86%] Linking CXX executable KokkosBlas2_gemv_perf_test
[ 86%] Built target KokkosBlas2_gemv_perf_test
[ 87%] Linking CXX executable KokkosKernels_batched_sla_openmp
[ 87%] Built target KokkosKernels_batched_sla_openmp
[ 87%] Linking CXX executable sparse_kk_spmv
[ 87%] Built target sparse_kk_spmv
[ 88%] Linking CXX executable KokkosBlas3_gemm_perf_test
[ 88%] Built target KokkosBlas3_gemm_perf_test
[ 88%] Linking CXX executable KokkosKernels_common_serial
[ 88%] Built target KokkosKernels_common_serial
[ 89%] Linking CXX executable KokkosKernels_common_openmp
[ 89%] Built target KokkosKernels_common_openmp
[ 89%] Linking CXX executable KokkosKernels_blas_openmp
[ 89%] Built target KokkosKernels_blas_openmp
[ 89%] Linking CXX executable KokkosKernels_graph_openmp
[ 89%] Built target KokkosKernels_graph_openmp
[ 89%] Linking CXX executable KokkosKernels_blas_serial
[ 89%] Built target KokkosKernels_blas_serial
[ 89%] Linking CXX executable KokkosKernels_sparse_openmp
[ 89%] Built target KokkosKernels_sparse_openmp
[ 90%] Linking CXX executable KokkosKernels_sparse_serial
[ 90%] Built target KokkosKernels_sparse_serial
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP_Serial-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas --user-blas-path=/home/projects/x86-64-skylake/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/x86-64-skylake/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.697/TestAll_2021-12-31_18.36.16/gcc/7.2.0/OpenMP_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013900

salloc: Job allocation 1013900 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_INTEL18 # 684 (click to expand) 

                      vector_view_type_3d, vector_view_type_3d, vector_view_type_3d, KokkosBatched::BoundsCheck::Yes, 1, 1, 1>::Functor]" at line 175 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.684/TestAll_2021-12-31_18.36.26/intel/18.1.163/Pthread-release/kokkos-install/include/Kokkos_Parallel.hpp"
            instantiation of "void Kokkos::parallel_for(const std::__cxx11::string &, const ExecPolicy &, const FunctorType &) [with ExecPolicy=Kokkos::TeamPolicy, FunctorType=KokkosBatched::Impl::BatchedDblBufGemm::Functor]" at line 191
            instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm::__run() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Left, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double}, AViewType=vector_view_type_3d, BViewType=vector_view_type_3d,
                      CViewType=vector_view_type_3d, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1]" at line 108
            instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm::invoke() [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Left, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double}, AViewType=vector_view_type_3d, BViewType=vector_view_type_3d,
                      CViewType=vector_view_type_3d, ArgBoundsCheck=KokkosBatched::BoundsCheck::Yes, TILE_M=1, TILE_N=1, TILE_K=1]" at line 510 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp"
            instantiation of "int KokkosBatched::BatchedGemm(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::Transpose, ArgTransB=KokkosBatched::Trans::Transpose, ArgBatchSzDim=KokkosBatched::BatchLayout::Left, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double},
                      AViewType=vector_view_type_3d, BViewType=vector_view_type_3d, CViewType=vector_view_type_3d]" at line 562 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"
            instantiation of "void __do_gemm_parallel_batched_heuristic_template(options_t, gemm_args_t) [with algo_tag=void, blocking_type=void, device_type=default_device, algo_mode=void]" at line 589 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"
            instantiation of "void __do_gemm_parallel_batched_heuristic(options_t, gemm_args_t) [with algo_tag=void, blocking_type=void, device_type=default_device, algo_mode=void]" at line 2265 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"

[ 76%] Linking CXX executable KokkosKernels_wiki_rcm

[ 78%] Linking CXX executable KokkosKernels_wiki_mis2

[ 78%] Built target KokkosKernels_wiki_rcm

[ 78%] Built target KokkosKernels_wiki_mis2

Scanning dependencies of target KokkosKernels_gmres_test_real_A

Scanning dependencies of target gmres_ex_real_A

[ 80%] Building CXX object example/gmres/CMakeFiles/KokkosKernels_gmres_test_real_A.dir/test_real_A.cpp.o

[ 80%] Building CXX object example/gmres/CMakeFiles/gmres_ex_real_A.dir/ex_real_A.cpp.o

compilation aborted for /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_perf_test.cpp (code 2)

make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 2

make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2

make[1]: *** Waiting for unfinished jobs....

[ 81%] Linking CXX executable KokkosKernels_wiki_coarsening

[ 81%] Built target KokkosKernels_wiki_coarsening

[ 82%] Linking CXX executable KokkosKernels_wiki_coloring

[ 82%] Built target KokkosKernels_wiki_coloring

[ 83%] Linking CXX executable KokkosKernels_gmres_test_real_A

[ 83%] Built target KokkosKernels_gmres_test_real_A

[ 84%] Linking CXX executable gmres_ex_real_A

[ 84%] Built target gmres_ex_real_A

[ 85%] Linking CXX executable sparse_kk_spmv

[ 85%] Built target sparse_kk_spmv

[ 86%] Linking CXX executable KokkosKernels_wiki_spgemm

[ 86%] Built target KokkosKernels_wiki_spgemm

[ 87%] Linking CXX executable sparse_pcg

[ 87%] Built target sparse_pcg

[ 89%] Linking CXX executable sparse_block_pcg

[ 89%] Built target sparse_block_pcg

[ 90%] Linking CXX executable KokkosKernels_wiki_gauss_seidel

[ 90%] Built target KokkosKernels_wiki_gauss_seidel

[ 91%] Linking CXX executable sparse_spmv_struct

[ 91%] Built target sparse_spmv_struct

[ 92%] Linking CXX executable sparse_spmv_struct_tuning

[ 92%] Built target sparse_spmv_struct_tuning

make: *** [all] Error 2

#######################################################

PASSED TESTS

#######################################################

#######################################################

FAILED TESTS

#######################################################

intel-18.1.163-OpenMP-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 intel/compilers/18.1.163



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/intel/compilers/2018/compilers_and_libraries_2018.1.163/linux/bin/intel64/icpc --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=mkl    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.684/TestAll_2021-12-31_18.36.26/intel/18.1.163/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

intel-18.1.163-Pthread-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 intel/compilers/18.1.163



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread --arch=SKX --compiler=/home/projects/x86-64/intel/compilers/2018/compilers_and_libraries_2018.1.163/linux/bin/intel64/icpc --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=mkl    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.684/TestAll_2021-12-31_18.36.26/intel/18.1.163/Pthread-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013901

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG1001 # 90 (click to expand) 

    __run();
    ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:479:20: note: in instantiation of member function 'KokkosBatched::Impl::BatchedDblBufGemm, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, Kokkos::View, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, Kokkos::View, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, KokkosBatched::BoundsCheck::No, 32, 32, 8>::invoke' requested here
                  .invoke();
                   ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp:552:24: note: in instantiation of function template specialization 'KokkosBatched::BatchedGemm, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, Kokkos::View, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads>, Kokkos::View, 8> ***, Kokkos::LayoutLeft, Kokkos::Threads> >' requested here
        KokkosBatched::BatchedGemm(
                       ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp:587:5: note: in instantiation of function template specialization '__do_gemm_parallel_batched_heuristic_template' requested here
    __do_gemm_parallel_batched_heuristic_template' requested here
      __do_gemm_parallel_batched_heuristic);
      ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/KokkosBatched_Util.hpp:858:29: note: candidate template ignored: deduced conflicting types for parameter 'ScalarType' ('KokkosBatched::Vector, 8>' vs. 'double')
KOKKOS_INLINE_FUNCTION void fma_bounds_check(ViewType v, SizeType m, SizeType n,
                            ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/KokkosBatched_Util.hpp:865:29: note: candidate template ignored: deduced conflicting types for parameter 'ScalarType' ('KokkosBatched::Vector, 8>' vs. 'double')
KOKKOS_INLINE_FUNCTION void fma_bounds_check(ViewType v, SizeType m, SizeType n,
                            ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/KokkosBatched_Util.hpp:841:29: note: candidate function template not viable: requires 7 arguments, but 6 were provided
KOKKOS_INLINE_FUNCTION void fma_bounds_check(ViewType v, SizeType m, SizeType n,
                            ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/KokkosBatched_Util.hpp:850:29: note: candidate function template not viable: requires 7 arguments, but 6 were provided
KOKKOS_INLINE_FUNCTION void fma_bounds_check(ViewType v, SizeType m, SizeType n,
                            ^
fatal error: too many errors emitted, stopping now [-ferror-limit=]
20 errors generated.
make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 1
make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[ 78%] Linking CXX executable KokkosBlas2_gemv_perf_test
[ 78%] Built target KokkosBlas2_gemv_perf_test
[ 79%] Linking CXX executable sparse_sptrsv_supernode
[ 79%] Built target sparse_sptrsv_supernode
[ 80%] Linking CXX executable KokkosBlas3_gemm_perf_test
[ 80%] Built target KokkosBlas3_gemm_perf_test
[ 80%] Linking CXX executable sparse_spmv_struct
[ 80%] Built target sparse_spmv_struct
[ 81%] Linking CXX executable KokkosKernels_batched_sla_serial
[ 81%] Built target KokkosKernels_batched_sla_serial
[ 81%] Linking CXX executable sparse_kk_spmv
[ 81%] Built target sparse_kk_spmv
[ 81%] Linking CXX executable sparse_pcg
[ 81%] Built target sparse_pcg
[ 82%] Linking CXX executable sparse_block_pcg
[ 82%] Built target sparse_block_pcg
[ 83%] Linking CXX executable KokkosKernels_blas_serial
[ 83%] Built target KokkosKernels_blas_serial
[ 84%] Linking CXX executable sparse_gs
[ 84%] Built target sparse_gs
[ 84%] Linking CXX executable KokkosKernels_sparse_serial
CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o: In function `int KokkosBlas::trtri, Kokkos::MemoryTraits<1u> > >(char const*, char const*, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)':
Test_Serial_Sparse.cpp:(.text._ZN10KokkosBlas5trtriIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEEEEiPKcSE_RKT_[_ZN10KokkosBlas5trtriIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEEEEiPKcSE_RKT_]+0x463): undefined reference to `KokkosBlas::Impl::TRTRI >, Kokkos::View, Kokkos::MemoryTraits<1u> >, false, false>::trtri(Kokkos::View > const&, char const*, char const*, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)'
CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o: In function `void KokkosBlas::trmm, Kokkos::MemoryTraits<1u> >, Kokkos::View, Kokkos::MemoryTraits<1u> > >(char const*, char const*, char const*, char const*, Kokkos::View, Kokkos::MemoryTraits<1u> >::const_value_type&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)':
Test_Serial_Sparse.cpp:(.text._ZN10KokkosBlas4trmmIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEESC_EEvPKcSE_SE_SE_RNT0_16const_value_typeERKT_RKSF_[_ZN10KokkosBlas4trmmIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEESC_EEvPKcSE_SE_SE_RNT0_16const_value_typeERKT_RKSF_]+0x8de): undefined reference to `KokkosBlas::Impl::TRMM, Kokkos::MemoryTraits<1u> >, Kokkos::View, Kokkos::MemoryTraits<1u> >, false, false>::trmm(char const*, char const*, char const*, char const*, double const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)'
CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o: In function `int KokkosBlas::trtri**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > >(char const*, char const*, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)':
Test_Serial_Sparse.cpp:(.text._ZN10KokkosBlas5trtriIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEEEEiPKcSG_RKT_[_ZN10KokkosBlas5trtriIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEEEEiPKcSG_RKT_]+0x463): undefined reference to `KokkosBlas::Impl::TRTRI >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, false, false>::trtri(Kokkos::View > const&, char const*, char const*, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)'
CMakeFiles/KokkosKernels_sparse_serial.dir/serial/Test_Serial_Sparse.cpp.o: In function `void KokkosBlas::trmm**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > >(char const*, char const*, char const*, char const*, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >::const_value_type&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)':
Test_Serial_Sparse.cpp:(.text._ZN10KokkosBlas4trmmIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEESE_EEvPKcSG_SG_SG_RNT0_16const_value_typeERKT_RKSH_[_ZN10KokkosBlas4trmmIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEESE_EEvPKcSG_SG_SG_RNT0_16const_value_typeERKT_RKSH_]+0x8de): undefined reference to `KokkosBlas::Impl::TRMM const**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, false, false>::trmm(char const*, char const*, char const*, char const*, Kokkos::complex const&, Kokkos::View const**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)'
../src/libkokkoskernels.a(Sparse_sptrsv_solve_eti_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE.cpp.o): In function `void KokkosBlas::trsm, Kokkos::MemoryTraits<1u> >, Kokkos::View > >(char const*, char const*, char const*, char const*, Kokkos::View >::const_value_type&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&, Kokkos::View > const&)':
Sparse_sptrsv_solve_eti_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE.cpp:(.text._ZN10KokkosBlas4trsmIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEENS2_IS4_JS5_S8_SB_EEEEEvPKcSF_SF_SF_RNT0_16const_value_typeERKT_RKSG_[_ZN10KokkosBlas4trsmIN6Kokkos4ViewIPPdJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEENS2_IS4_JS5_S8_SB_EEEEEvPKcSF_SF_SF_RNT0_16const_value_typeERKT_RKSG_]+0x8fe): undefined reference to `KokkosBlas::Impl::TRSM, Kokkos::MemoryTraits<1u> >, Kokkos::View, Kokkos::MemoryTraits<1u> >, false, false>::trsm(char const*, char const*, char const*, char const*, double const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&, Kokkos::View, Kokkos::MemoryTraits<1u> > const&)'
../src/libkokkoskernels.a(Sparse_sptrsv_solve_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE.cpp.o): In function `void KokkosBlas::trsm**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::HostSpace, Kokkos::MemoryTraits<1u> > >(char const*, char const*, char const*, char const*, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::HostSpace, Kokkos::MemoryTraits<1u> >::const_value_type&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::HostSpace, Kokkos::MemoryTraits<1u> > const&)':
Sparse_sptrsv_solve_eti_COMPLEX_DOUBLE_ORDINAL_INT_OFFSET_INT_LAYOUTLEFT_EXECSPACE_SERIAL_MEMSPACE_HOSTSPACE.cpp:(.text._ZN10KokkosBlas4trsmIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEENS2_IS6_JS7_SA_SD_EEEEEvPKcSH_SH_SH_RNT0_16const_value_typeERKT_RKSI_[_ZN10KokkosBlas4trsmIN6Kokkos4ViewIPPNS1_7complexIdEEJNS1_10LayoutLeftENS1_6DeviceINS1_7ThreadsENS1_9HostSpaceEEENS1_12MemoryTraitsILj1EEEEEENS2_IS6_JS7_SA_SD_EEEEEvPKcSH_SH_SH_RNT0_16const_value_typeERKT_RKSI_]+0x8fe): undefined reference to `KokkosBlas::Impl::TRSM const**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> >, false, false>::trsm(char const*, char const*, char const*, char const*, Kokkos::complex const&, Kokkos::View const**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&, Kokkos::View**, Kokkos::LayoutLeft, Kokkos::Device, Kokkos::MemoryTraits<1u> > const&)'
clang-10: error: linker command failed with exit code 1 (use -v to see invocation)
make[2]: *** [unit_test/KokkosKernels_sparse_serial] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_sparse_serial.dir/all] Error 2
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
clang-10.0.1-Pthread_Serial-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 clang/10.0.1

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/spack/opt/spack/linux-rhel7-x86_64/gcc-10.2.0/llvm-10.0.1-nldepabrxk2zcykcq7rlky5sr53hnm63/bin/clang++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/KokkosKernels_PullRequest_CLANG1001.90/TestAll_2021-12-31_18.36.35/clang/10.0.1/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1013902

salloc: Job allocation 1013902 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE

@kokkos-devops-admin
Copy link

Status Flag 'Pre-Test Inspection' - Auto Inspected - Inspection Is Not Necessary for this Pull Request.

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Testing Jenkins Projects:

Pull Request Auto Testing STARTING (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740

  • Build Num: 72
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 0b9220d
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight

  • Build Num: 71
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 0b9220d
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 729
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 0b9220d
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 376
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 0b9220d
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 720
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 0b9220d
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 707
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 0b9220d
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_CLANG1001

  • Build Num: 113
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 0b9220d
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 598ac78
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Using Repos:

Repo: KOKKOSKERNELS (vqd8a/kokkos-kernels)
  • Branch: batched_gemm_fix_alpha
  • SHA: 0b9220d
  • Mode: TEST_REPO

Pull Request Author: vqd8a

@kokkos-devops-admin
Copy link

Status Flag 'Pre-Test Inspection' - Auto Inspected - Inspection Is Not Necessary for this Pull Request.

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Testing Jenkins Projects:

Pull Request Auto Testing STARTING (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740

  • Build Num: 78
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight

  • Build Num: 77
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 735
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 382
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 726
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 714
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_CLANG1001

  • Build Num: 119
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Using Repos:

Repo: KOKKOSKERNELS (vqd8a/kokkos-kernels)
  • Branch: batched_gemm_fix_alpha
  • SHA: 12201db
  • Mode: TEST_REPO

Pull Request Author: vqd8a

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Jenkins Testing: 1 or more Jobs FAILED

Note: Testing will normally be attempted again in approx. 2 Hrs 30 Mins. If a change to the PR source branch occurs, the testing will be attempted again on next available autotester run.

Pull Request Auto Testing has FAILED (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740

  • Build Num: 78
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight

  • Build Num: 77
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 735
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 382
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 726
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 714
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_CLANG1001

  • Build Num: 119
  • Status: FAILED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 12201db
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740 # 78 (click to expand) 

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:18:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:335:21:   required from void KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.78/TestAll_2022-01-06_20.20.04/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/OpenMP/Kokkos_OpenMP_Parallel.hpp:867:8:   required from static typename std::enable_if::value>::type Kokkos::Impl::ParallelFor, Kokkos::OpenMP>::exec_team(const FunctorType&, Kokkos::Impl::HostThreadTeamData&, int, int, int) [with TagType = void; FunctorType = KokkosBatched::Impl::BatchedDblBufGemm, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::Yes, 32, 32, 8>::Functor, 4, 4, 8, 8>; Properties = {Kokkos::OpenMP}; typename std::enable_if::value>::type = void]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.78/TestAll_2022-01-06_20.20.04/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/OpenMP/Kokkos_OpenMP_Parallel.hpp:940:101:   [ skipping 5 instantiation contexts, use -ftemplate-backtrace-limit=0 to disable ]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:501:5:   required from int KokkosBatched::BatchedGemm(BatchedGemmHandleType*, ScalarType, const AViewType&, const BViewType&, ScalarType, const CViewType&) [with ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; BatchedGemmHandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:90:118:   required from void Test::impl_test_batched_gemm_with_handle(KokkosBatched::BatchedGemmHandle*, int, int, int, int, int, int, int, ScalarType, ScalarType) [with DeviceType = Kokkos::OpenMP; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:204:85:   required from void Test::impl_test_batched_gemm(int, int, int, int, int, int, int) [with DeviceType = Kokkos::OpenMP; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:247:79:   required from void test_batched_gemm_with_layout() [with ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; DeviceType = Kokkos::OpenMP; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:310:144:   required from int test_batched_gemm() [with DeviceType = Kokkos::OpenMP; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp:166:218:   required from here
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:23: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp: In instantiation of KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:::: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]:
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:18:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:340:21:   required from KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:18:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:335:21:   required from void KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.78/TestAll_2022-01-06_20.20.04/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/OpenMP/Kokkos_OpenMP_Parallel.hpp:867:8:   required from static typename std::enable_if::value>::type Kokkos::Impl::ParallelFor, Kokkos::OpenMP>::exec_team(const FunctorType&, Kokkos::Impl::HostThreadTeamData&, int, int, int) [with TagType = void; FunctorType = KokkosBatched::Impl::BatchedDblBufGemm, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::No, 32, 32, 8>::Functor, 4, 4, 8, 8>; Properties = {Kokkos::OpenMP}; typename std::enable_if::value>::type = void]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.78/TestAll_2022-01-06_20.20.04/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/OpenMP/Kokkos_OpenMP_Parallel.hpp:940:101:   [ skipping 5 instantiation contexts, use -ftemplate-backtrace-limit=0 to disable ]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:509:5:   required from int KokkosBatched::BatchedGemm(BatchedGemmHandleType*, ScalarType, const AViewType&, const BViewType&, ScalarType, const CViewType&) [with ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; BatchedGemmHandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:90:118:   required from void Test::impl_test_batched_gemm_with_handle(KokkosBatched::BatchedGemmHandle*, int, int, int, int, int, int, int, ScalarType, ScalarType) [with DeviceType = Kokkos::OpenMP; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:204:85:   required from void Test::impl_test_batched_gemm(int, int, int, int, int, int, int) [with DeviceType = Kokkos::OpenMP; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:247:79:   required from void test_batched_gemm_with_layout() [with ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; DeviceType = Kokkos::OpenMP; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:310:144:   required from int test_batched_gemm() [with DeviceType = Kokkos::OpenMP; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp:166:218:   required from here
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:23: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp: In instantiation of KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:::: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]:
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:18:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:340:21:   required from KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:18:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:335:21:   required from void KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.78/TestAll_2022-01-06_20.20.04/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/OpenMP/Kokkos_OpenMP_Parallel.hpp:867:8:   required from static typename std::enable_if::value>::type Kokkos::Impl::ParallelFor, Kokkos::OpenMP>::exec_team(const FunctorType&, Kokkos::Impl::HostThreadTeamData&, int, int, int) [with TagType = void; FunctorType = KokkosBatched::Impl::BatchedDblBufGemm, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::No, 1, 1, 1>::Functor, 1, 1, 1, 1>; Properties = {Kokkos::OpenMP}; typename std::enable_if::value>::type = void]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.78/TestAll_2022-01-06_20.20.04/cuda/9.2.88/Cuda_OpenMP-release/kokkos-install/include/OpenMP/Kokkos_OpenMP_Parallel.hpp:940:101:   [ skipping 5 instantiation contexts, use -ftemplate-backtrace-limit=0 to disable ]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:534:5:   required from int KokkosBatched::BatchedGemm(BatchedGemmHandleType*, ScalarType, const AViewType&, const BViewType&, ScalarType, const CViewType&) [with ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; BatchedGemmHandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:90:118:   required from void Test::impl_test_batched_gemm_with_handle(KokkosBatched::BatchedGemmHandle*, int, int, int, int, int, int, int, ScalarType, ScalarType) [with DeviceType = Kokkos::OpenMP; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:204:85:   required from void Test::impl_test_batched_gemm(int, int, int, int, int, int, int) [with DeviceType = Kokkos::OpenMP; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:247:79:   required from void test_batched_gemm_with_layout() [with ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; DeviceType = Kokkos::OpenMP; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:310:144:   required from int test_batched_gemm() [with DeviceType = Kokkos::OpenMP; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp:166:218:   required from here
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:23: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Util.hpp(869): warning: statement is unreachable

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Util.hpp(869): warning: statement is unreachable


[100%] Linking CXX executable KokkosBlas3_perf_test

[100%] Built target KokkosBlas3_perf_test

[100%] Linking CXX executable KokkosKernels_blas_openmp

[100%] Built target KokkosKernels_blas_openmp

[100%] Linking CXX executable gmres_ex_real_A

[100%] Linking CXX executable KokkosKernels_graph_cuda

[100%] Built target gmres_ex_real_A

[100%] Linking CXX executable KokkosKernels_gmres_test_real_A

[100%] Built target KokkosKernels_graph_cuda

[100%] Built target KokkosKernels_gmres_test_real_A

[100%] Linking CXX executable gmres_test_cmplx_A

[100%] Built target gmres_test_cmplx_A

[100%] Linking CXX executable KokkosKernels_gmres_test_prec

[100%] Built target KokkosKernels_gmres_test_prec

[100%] Linking CXX executable KokkosKernels_sparse_openmp

[100%] Built target KokkosKernels_sparse_openmp

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos-kernels/src/batched/KokkosBatched_Util.hpp(869): warning: statement is unreachable


[100%] Linking CXX executable KokkosKernels_sparse_cuda

[100%] Built target KokkosKernels_sparse_cuda

cc1plus: all warnings being treated as errors

make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched_Dense.cpp.o] Error 1

make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2

make[1]: *** Waiting for unfinished jobs....

[100%] Linking CXX executable KokkosKernels_batched_dla_cuda

[100%] Built target KokkosKernels_batched_dla_cuda

make: *** [all] Error 2

#######################################################

PASSED TESTS

#######################################################

#######################################################

FAILED TESTS

#######################################################

cuda-9.2.88-Cuda_OpenMP-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 cuda/9.2.88 gcc/7.2.0 netlib/3.8.0/gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Cuda,OpenMP --arch=Power9,Volta70 --compiler=/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/kokkos/bin/nvcc_wrapper --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --with-cuda=/home/projects/ppc64le-pwr9-nvidia/cuda/9.2.88  --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas,cublas,cusparse --user-blas-path=/home/projects/ppc64le-pwr9/netlib/3.8.0/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/netlib/3.8.0/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=force_uvm,enable_lambda   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740/KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740.78/TestAll_2022-01-06_20.20.04/cuda/9.2.88/Cuda_OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight # 77 (click to expand) 

/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:310:144:   required from int test_batched_gemm() [with DeviceType = Kokkos::Serial; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp:166:218:   required from here
/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:23: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
[ 96%] Linking CXX executable KokkosKernels_common_cuda
[ 96%] Built target KokkosKernels_common_cuda
Scanning dependencies of target KokkosKernels_wiki_gauss_seidel
[ 96%] Building CXX object example/wiki/sparse/CMakeFiles/KokkosKernels_wiki_gauss_seidel.dir/KokkosSparse_wiki_gauss_seidel.cpp.o
[ 96%] Linking CXX executable KokkosKernels_wiki_spmv
[ 96%] Built target KokkosKernels_wiki_spmv
[ 96%] Linking CXX executable KokkosKernels_graph_serial
Scanning dependencies of target KokkosKernels_wiki_spadd
[ 96%] Building CXX object example/wiki/sparse/CMakeFiles/KokkosKernels_wiki_spadd.dir/KokkosSparse_wiki_spadd.cpp.o
[ 96%] Built target KokkosKernels_graph_serial
Scanning dependencies of target KokkosKernels_wiki_coarsening
[ 96%] Building CXX object example/wiki/graph/CMakeFiles/KokkosKernels_wiki_coarsening.dir/KokkosGraph_wiki_coarsening.cpp.o
[ 96%] Linking CXX executable KokkosKernels_wiki_spgemm
[ 96%] Built target KokkosKernels_wiki_spgemm
Scanning dependencies of target KokkosKernels_wiki_coloring
[ 96%] Building CXX object example/wiki/graph/CMakeFiles/KokkosKernels_wiki_coloring.dir/KokkosGraph_wiki_coloring.cpp.o
[ 96%] Linking CXX executable KokkosKernels_wiki_gauss_seidel
[ 96%] Built target KokkosKernels_wiki_gauss_seidel
Scanning dependencies of target KokkosKernels_wiki_rcm
[ 96%] Building CXX object example/wiki/graph/CMakeFiles/KokkosKernels_wiki_rcm.dir/KokkosGraph_wiki_rcm.cpp.o
[ 96%] Linking CXX executable KokkosKernels_wiki_spadd
[ 96%] Built target KokkosKernels_wiki_spadd
Scanning dependencies of target KokkosKernels_wiki_mis2
[ 96%] Building CXX object example/wiki/graph/CMakeFiles/KokkosKernels_wiki_mis2.dir/KokkosGraph_wiki_mis2.cpp.o
[ 96%] Linking CXX executable KokkosKernels_wiki_coarsening
[ 96%] Built target KokkosKernels_wiki_coarsening
Scanning dependencies of target gmres_ex_real_A
[ 96%] Building CXX object example/gmres/CMakeFiles/gmres_ex_real_A.dir/ex_real_A.cpp.o
[ 96%] Linking CXX executable KokkosKernels_wiki_rcm
[ 96%] Built target KokkosKernels_wiki_rcm
Scanning dependencies of target KokkosKernels_gmres_test_real_A
[ 97%] Building CXX object example/gmres/CMakeFiles/KokkosKernels_gmres_test_real_A.dir/test_real_A.cpp.o
[ 97%] Linking CXX executable KokkosKernels_blas_serial
[ 97%] Built target KokkosKernels_blas_serial
Scanning dependencies of target gmres_test_cmplx_A
[ 99%] Building CXX object example/gmres/CMakeFiles/gmres_test_cmplx_A.dir/test_cmplx_A.cpp.o
[ 99%] Linking CXX executable KokkosKernels_wiki_mis2
[ 99%] Built target KokkosKernels_wiki_mis2
Scanning dependencies of target KokkosKernels_gmres_test_prec
[ 99%] Building CXX object example/gmres/CMakeFiles/KokkosKernels_gmres_test_prec.dir/test_prec.cpp.o
[100%] Linking CXX executable KokkosKernels_wiki_coloring
[100%] Built target KokkosKernels_wiki_coloring
[100%] Linking CXX executable KokkosKernels_graph_cuda
[100%] Built target KokkosKernels_graph_cuda
[100%] Linking CXX executable gmres_ex_real_A
[100%] Linking CXX executable KokkosKernels_blas_cuda
[100%] Built target gmres_ex_real_A
[100%] Linking CXX executable KokkosBlas3_perf_test
[100%] Built target KokkosKernels_blas_cuda
[100%] Built target KokkosBlas3_perf_test
[100%] Linking CXX executable KokkosKernels_gmres_test_real_A
[100%] Built target KokkosKernels_gmres_test_real_A
[100%] Linking CXX executable gmres_test_cmplx_A
[100%] Built target gmres_test_cmplx_A
[100%] Linking CXX executable KokkosKernels_gmres_test_prec
[100%] Built target KokkosKernels_gmres_test_prec
[100%] Linking CXX executable KokkosKernels_sparse_serial
[100%] Built target KokkosKernels_sparse_serial
cc1plus: all warnings being treated as errors
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_serial.dir/serial/Test_Serial_Batched_Dense.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_serial.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[100%] Linking CXX executable KokkosKernels_sparse_cuda
[100%] Built target KokkosKernels_sparse_cuda
[100%] Linking CXX executable KokkosKernels_batched_dla_cuda
[100%] Built target KokkosKernels_batched_dla_cuda
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
cuda-10.1.243-Cuda_Serial-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 cuda/10.1.243 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Cuda,Serial --arch=Power9,Volta70 --compiler=/home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/kokkos/bin/nvcc_wrapper --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags="" --with-cuda=/home/projects/ppc64le-pwr9-nvidia/cuda/10.1.243  --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas,cublas,cusparse --user-blas-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/ppc64le-pwr9/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=,enable_lambda   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/weaver-new/workspace/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight/KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight.77/TestAll_2022-01-06_20.20.14/cuda/10.1.243/Cuda_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC720 # 735 (click to expand) 

/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:248:47:   required from void test_batched_gemm_with_layout() [with ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; DeviceType = Kokkos::OpenMP; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:311:46:   required from int test_batched_gemm() [with DeviceType = Kokkos::OpenMP; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp:167:62:   required from here
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:35: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp: In instantiation of KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:::: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:42:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:340:33:   required from KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:42:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:335:27:   required from void KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.735/TestAll_2022-01-06_20.20.26/gcc/7.2.0/OpenMP-release/kokkos-install/include/OpenMP/Kokkos_OpenMP_Parallel.hpp:867:14:   required from static typename std::enable_if::value>::type Kokkos::Impl::ParallelFor, Kokkos::OpenMP>::exec_team(const FunctorType&, Kokkos::Impl::HostThreadTeamData&, int, int, int) [with TagType = void; FunctorType = KokkosBatched::Impl::BatchedDblBufGemm, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::No, 1, 1, 1>::Functor, 1, 1, 1, 1>; Properties = {Kokkos::OpenMP}; typename std::enable_if::value>::type = void]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.735/TestAll_2022-01-06_20.20.26/gcc/7.2.0/OpenMP-release/kokkos-install/include/OpenMP/Kokkos_OpenMP_Parallel.hpp:940:51:   [ skipping 5 instantiation contexts, use -ftemplate-backtrace-limit=0 to disable ]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:534:11:   required from int KokkosBatched::BatchedGemm(BatchedGemmHandleType*, ScalarType, const AViewType&, const BViewType&, ScalarType, const CViewType&) [with ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; BatchedGemmHandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:90:51:   required from void Test::impl_test_batched_gemm_with_handle(KokkosBatched::BatchedGemmHandle*, int, int, int, int, int, int, int, ScalarType, ScalarType) [with DeviceType = Kokkos::OpenMP; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:205:57:   required from void Test::impl_test_batched_gemm(int, int, int, int, int, int, int) [with DeviceType = Kokkos::OpenMP; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:248:47:   required from void test_batched_gemm_with_layout() [with ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::OpenMP>; DeviceType = Kokkos::OpenMP; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:311:46:   required from int test_batched_gemm() [with DeviceType = Kokkos::OpenMP; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp:167:62:   required from here
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:35: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
[ 95%] Linking CXX executable sparse_kk_spmv
[ 95%] Built target sparse_kk_spmv
[ 95%] Linking CXX executable KokkosKernels_wiki_coloring
[ 95%] Built target KokkosKernels_wiki_coloring
[ 95%] Linking CXX executable KokkosKernels_common_openmp
[ 95%] Built target KokkosKernels_common_openmp
[ 96%] Linking CXX executable KokkosKernels_gmres_test_real_A
[ 96%] Built target KokkosKernels_gmres_test_real_A
[ 97%] Linking CXX executable gmres_ex_real_A
[ 97%] Built target gmres_ex_real_A
[ 97%] Linking CXX executable KokkosKernels_gmres_test_prec
[ 97%] Built target KokkosKernels_gmres_test_prec
cc1plus: all warnings being treated as errors
make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 1
make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[ 98%] Linking CXX executable gmres_test_cmplx_A
[ 98%] Built target gmres_test_cmplx_A
[ 99%] Linking CXX executable KokkosKernels_blas_openmp
[ 99%] Built target KokkosKernels_blas_openmp
[ 99%] Linking CXX executable KokkosKernels_graph_openmp
[ 99%] Built target KokkosKernels_graph_openmp
[ 99%] Linking CXX executable KokkosKernels_sparse_openmp
[ 99%] Built target KokkosKernels_sparse_openmp
cc1plus: all warnings being treated as errors
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched_Dense.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.735/TestAll_2022-01-06_20.20.26/gcc/7.2.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

gcc-7.2.0-Pthread_Serial-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720/KokkosKernels_PullRequest_GCC720.735/TestAll_2022-01-06_20.20.26/gcc/7.2.0/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1014768

salloc: Job allocation 1014768 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_GCC720_Light_LayoutRight # 382 (click to expand) 

/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp:167:62:   required from here
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:35: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
[ 93%] Linking CXX executable KokkosKernels_wiki_gauss_seidel
[ 93%] Built target KokkosKernels_wiki_gauss_seidel
Scanning dependencies of target KokkosKernels_gmres_test_real_A
[ 93%] Building CXX object example/gmres/CMakeFiles/KokkosKernels_gmres_test_real_A.dir/test_real_A.cpp.o
[ 93%] Linking CXX executable KokkosKernels_wiki_rcm
[ 93%] Built target KokkosKernels_wiki_rcm
[ 94%] Linking CXX executable KokkosKernels_wiki_mis2
[ 94%] Built target KokkosKernels_wiki_mis2
Scanning dependencies of target gmres_ex_real_A
[ 94%] Building CXX object example/gmres/CMakeFiles/gmres_ex_real_A.dir/ex_real_A.cpp.o
Scanning dependencies of target KokkosKernels_gmres_test_prec
[ 95%] Building CXX object example/gmres/CMakeFiles/KokkosKernels_gmres_test_prec.dir/test_prec.cpp.o
[ 95%] Linking CXX executable KokkosKernels_wiki_coarsening
[ 95%] Built target KokkosKernels_wiki_coarsening
[ 95%] Linking CXX executable sparse_kk_spmv
[ 95%] Built target sparse_kk_spmv
Scanning dependencies of target gmres_test_cmplx_A
[ 95%] Building CXX object example/gmres/CMakeFiles/gmres_test_cmplx_A.dir/test_cmplx_A.cpp.o
[ 95%] Linking CXX executable KokkosKernels_wiki_coloring
[ 95%] Linking CXX executable KokkosKernels_common_openmp
[ 95%] Built target KokkosKernels_wiki_coloring
[ 95%] Built target KokkosKernels_common_openmp
[ 96%] Linking CXX executable KokkosKernels_gmres_test_real_A
[ 96%] Built target KokkosKernels_gmres_test_real_A
[ 97%] Linking CXX executable gmres_ex_real_A
cc1plus: all warnings being treated as errors
make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 1
make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
[ 97%] Built target gmres_ex_real_A
[ 98%] Linking CXX executable gmres_test_cmplx_A
[ 98%] Linking CXX executable KokkosKernels_gmres_test_prec
[ 98%] Built target gmres_test_cmplx_A
[ 98%] Built target KokkosKernels_gmres_test_prec
[ 99%] Linking CXX executable KokkosKernels_blas_openmp
[ 99%] Built target KokkosKernels_blas_openmp
[ 99%] Linking CXX executable KokkosKernels_graph_openmp
[ 99%] Built target KokkosKernels_graph_openmp
[ 99%] Linking CXX executable KokkosKernels_sparse_openmp
[ 99%] Built target KokkosKernels_sparse_openmp
cc1plus: all warnings being treated as errors
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched_Dense.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutRight --with-tpls=    --with-options= --with-cuda-options=  --with-spaces=hostspace --no-examples  --no-default-eti


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.382/TestAll_2022-01-06_20.20.35/gcc/7.2.0/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

gcc-7.2.0-Pthread_Serial-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 gcc/7.2.0



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutRight --with-tpls=    --with-options= --with-cuda-options=  --with-spaces=hostspace --no-examples  --no-default-eti


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_GCC720_Light_LayoutRight/KokkosKernels_PullRequest_GCC720_Light_LayoutRight.382/TestAll_2022-01-06_20.20.35/gcc/7.2.0/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1014769

salloc: Job allocation 1014769 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_GCC720 # 726 (click to expand) 

/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.726/TestAll_2022-01-06_20.20.45/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/Kokkos_Serial.hpp:979:5:   [ skipping 5 instantiation contexts, use -ftemplate-backtrace-limit=0 to disable ]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:491:17:   required from int KokkosBatched::BatchedGemm(BatchedGemmHandleType*, ScalarType, const AViewType&, const BViewType&, ScalarType, const CViewType&) [with ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; BatchedGemmHandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:90:51:   required from void Test::impl_test_batched_gemm_with_handle(KokkosBatched::BatchedGemmHandle*, int, int, int, int, int, int, int, ScalarType, ScalarType) [with DeviceType = Kokkos::Serial; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:205:57:   required from void Test::impl_test_batched_gemm(int, int, int, int, int, int, int) [with DeviceType = Kokkos::Serial; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:248:47:   required from void test_batched_gemm_with_layout() [with ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; DeviceType = Kokkos::Serial; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:311:46:   required from int test_batched_gemm() [with DeviceType = Kokkos::Serial; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp:167:62:   required from here
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:35: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp: In instantiation of KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:::: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:42:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:340:33:   required from KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:42:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:335:27:   required from void KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::Yes; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.726/TestAll_2022-01-06_20.20.45/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/Kokkos_Serial.hpp:951:7:   required from typename std::enable_if::value>::type Kokkos::Impl::ParallelFor, Kokkos::Serial>::exec(Kokkos::Impl::HostThreadTeamData&) const [with TagType = void; FunctorType = KokkosBatched::Impl::BatchedDblBufGemm, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::Yes, 32, 32, 8>::Functor, 4, 4, 8, 8>; Properties = {Kokkos::Serial}; typename std::enable_if::value>::type = void]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.726/TestAll_2022-01-06_20.20.45/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/Kokkos_Serial.hpp:979:5:   [ skipping 5 instantiation contexts, use -ftemplate-backtrace-limit=0 to disable ]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:501:17:   required from int KokkosBatched::BatchedGemm(BatchedGemmHandleType*, ScalarType, const AViewType&, const BViewType&, ScalarType, const CViewType&) [with ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; BatchedGemmHandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:90:51:   required from void Test::impl_test_batched_gemm_with_handle(KokkosBatched::BatchedGemmHandle*, int, int, int, int, int, int, int, ScalarType, ScalarType) [with DeviceType = Kokkos::Serial; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:205:57:   required from void Test::impl_test_batched_gemm(int, int, int, int, int, int, int) [with DeviceType = Kokkos::Serial; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:248:47:   required from void test_batched_gemm_with_layout() [with ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; DeviceType = Kokkos::Serial; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:311:46:   required from int test_batched_gemm() [with DeviceType = Kokkos::Serial; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp:167:62:   required from here
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:35: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp: In instantiation of KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:::: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:42:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:340:33:   required from KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:42:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]::
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:335:27:   required from void KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 4; int REG_N = 4; int STRIDE_M = 8; int STRIDE_N = 8; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 32; int TILE_N = 32; int TILE_K = 8]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.726/TestAll_2022-01-06_20.20.45/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/Kokkos_Serial.hpp:951:7:   required from typename std::enable_if::value>::type Kokkos::Impl::ParallelFor, Kokkos::Serial>::exec(Kokkos::Impl::HostThreadTeamData&) const [with TagType = void; FunctorType = KokkosBatched::Impl::BatchedDblBufGemm, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::No, 32, 32, 8>::Functor, 4, 4, 8, 8>; Properties = {Kokkos::Serial}; typename std::enable_if::value>::type = void]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.726/TestAll_2022-01-06_20.20.45/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/Kokkos_Serial.hpp:979:5:   [ skipping 5 instantiation contexts, use -ftemplate-backtrace-limit=0 to disable ]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:509:17:   required from int KokkosBatched::BatchedGemm(BatchedGemmHandleType*, ScalarType, const AViewType&, const BViewType&, ScalarType, const CViewType&) [with ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; BatchedGemmHandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:90:51:   required from void Test::impl_test_batched_gemm_with_handle(KokkosBatched::BatchedGemmHandle*, int, int, int, int, int, int, int, ScalarType, ScalarType) [with DeviceType = Kokkos::Serial; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:205:57:   required from void Test::impl_test_batched_gemm(int, int, int, int, int, int, int) [with DeviceType = Kokkos::Serial; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:248:47:   required from void test_batched_gemm_with_layout() [with ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; DeviceType = Kokkos::Serial; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:311:46:   required from int test_batched_gemm() [with DeviceType = Kokkos::Serial; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp:167:62:   required from here
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:35: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp: In instantiation of KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:::: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:42:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:340:33:   required from KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const:: [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:442:42:   required from struct KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]::
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:335:27:   required from void KokkosBatched::Impl::BatchedDblBufGemm::Functor::operator()(const MemberType&) const [with MemberType = Kokkos::Impl::HostThreadTeamMember; int REG_M = 1; int REG_N = 1; int STRIDE_M = 1; int STRIDE_N = 1; ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; HandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ArgBoundsCheck = KokkosBatched::BoundsCheck::Yes; ArgAlphaFmaTag = KokkosBatched::AlphaTag::No; int TILE_M = 1; int TILE_N = 1; int TILE_K = 1]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.726/TestAll_2022-01-06_20.20.45/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/Kokkos_Serial.hpp:951:7:   required from typename std::enable_if::value>::type Kokkos::Impl::ParallelFor, Kokkos::Serial>::exec(Kokkos::Impl::HostThreadTeamData&) const [with TagType = void; FunctorType = KokkosBatched::Impl::BatchedDblBufGemm, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>, Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::No, 1, 1, 1>::Functor, 1, 1, 1, 1>; Properties = {Kokkos::Serial}; typename std::enable_if::value>::type = void]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.726/TestAll_2022-01-06_20.20.45/gcc/7.2.0/OpenMP_Serial-release/kokkos-install/include/Kokkos_Serial.hpp:979:5:   [ skipping 5 instantiation contexts, use -ftemplate-backtrace-limit=0 to disable ]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:534:11:   required from int KokkosBatched::BatchedGemm(BatchedGemmHandleType*, ScalarType, const AViewType&, const BViewType&, ScalarType, const CViewType&) [with ArgTransA = KokkosBatched::Trans::Transpose; ArgTransB = KokkosBatched::Trans::Transpose; ArgBatchSzDim = KokkosBatched::BatchLayout::Right; BatchedGemmHandleType = KokkosBatched::BatchedGemmHandle; ScalarType = Kokkos::complex; AViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; BViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; CViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:90:51:   required from void Test::impl_test_batched_gemm_with_handle(KokkosBatched::BatchedGemmHandle*, int, int, int, int, int, int, int, ScalarType, ScalarType) [with DeviceType = Kokkos::Serial; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:205:57:   required from void Test::impl_test_batched_gemm(int, int, int, int, int, int, int) [with DeviceType = Kokkos::Serial; ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:248:47:   required from void test_batched_gemm_with_layout() [with ViewType = Kokkos::View***, Kokkos::LayoutLeft, Kokkos::Serial>; DeviceType = Kokkos::Serial; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm.hpp:311:46:   required from int test_batched_gemm() [with DeviceType = Kokkos::Serial; ValueType = Kokkos::complex; ScalarType = Kokkos::complex; ParamTagType = Test::SharedParamTag]
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/unit_test/batched/dense/Test_Batched_BatchedGemm_Complex.hpp:167:62:   required from here
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:35: error: comparison between signed and unsigned integer expressions [-Werror=sign-compare]
[ 93%] Built target KokkosKernels_blas_openmp
[ 93%] Linking CXX executable KokkosKernels_graph_openmp
[ 93%] Built target KokkosKernels_graph_openmp
[ 93%] Linking CXX executable KokkosKernels_blas_serial
[ 93%] Built target KokkosKernels_blas_serial
[ 93%] Linking CXX executable KokkosKernels_graph_serial
[ 93%] Built target KokkosKernels_graph_serial
[ 93%] Linking CXX executable KokkosKernels_sparse_openmp
[ 93%] Built target KokkosKernels_sparse_openmp
[ 94%] Linking CXX executable KokkosKernels_sparse_serial
[ 94%] Built target KokkosKernels_sparse_serial
cc1plus: all warnings being treated as errors
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_serial.dir/serial/Test_Serial_Batched_Dense.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_serial.dir/all] Error 2
cc1plus: all warnings being treated as errors
make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/openmp/Test_OpenMP_Batched_Dense.cpp.o] Error 1
make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_openmp.dir/all] Error 2
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
gcc-7.2.0-OpenMP_Serial-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 gcc/7.2.0 openblas/0.2.20/gcc/7.2.0

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP,Serial --arch=SKX --compiler=/home/projects/x86-64/gcc/7.2.0/bin/g++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wignored-qualifiers -Wempty-body -Wclobbered -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=blas --user-blas-path=/home/projects/x86-64-skylake/openblas/0.2.20/gcc/7.2.0/lib --user-lapack-path=/home/projects/x86-64-skylake/openblas/0.2.20/gcc/7.2.0/lib --user-blas-lib=blas --user-lapack-lib=lapack --extra-linker-flags=-lgfortran,-lm --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_GCC720/KokkosKernels_PullRequest_Tpls_GCC720.726/TestAll_2022-01-06_20.20.45/gcc/7.2.0/OpenMP_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1014770

salloc: Job allocation 1014770 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_Tpls_INTEL18 # 714 (click to expand) 

                      KokkosBatched::BoundsCheck::No, KokkosBatched::AlphaTag::Yes, 32, 32, 8>::Functor]" at line 196
            instantiation of "void KokkosBatched::Impl::BatchedDblBufGemm::__run() [with ArgTransA=KokkosBatched::Trans::NoTranspose, ArgTransB=KokkosBatched::Trans::NoTranspose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double}, AViewType=vector_view_type_3d,
                      BViewType=vector_view_type_3d, CViewType=vector_view_type_3d, ArgBoundsCheck=KokkosBatched::BoundsCheck::No, ArgAlphaFmaTag=KokkosBatched::AlphaTag::Yes, TILE_M=32, TILE_N=32, TILE_K=8]" at line 113
            instantiation of "int KokkosBatched::Impl::BatchedDblBufGemm::invoke() [with ArgTransA=KokkosBatched::Trans::NoTranspose, ArgTransB=KokkosBatched::Trans::NoTranspose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, HandleType=KokkosBatched::BatchedGemmHandle, ScalarType=default_scalar={double}, AViewType=vector_view_type_3d,
                      BViewType=vector_view_type_3d, CViewType=vector_view_type_3d, ArgBoundsCheck=KokkosBatched::BoundsCheck::No, ArgAlphaFmaTag=KokkosBatched::AlphaTag::Yes, TILE_M=32, TILE_N=32, TILE_K=8]" at line 489 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp"
            instantiation of "int KokkosBatched::BatchedGemm(BatchedGemmHandleType *, ScalarType, const AViewType &, const BViewType &, ScalarType, const CViewType &) [with ArgTransA=KokkosBatched::Trans::NoTranspose, ArgTransB=KokkosBatched::Trans::NoTranspose, ArgBatchSzDim=KokkosBatched::BatchLayout::Right, BatchedGemmHandleType=KokkosBatched::BatchedGemmHandle,
                      ScalarType=default_scalar={double}, AViewType=vector_view_type_3d, BViewType=vector_view_type_3d, CViewType=vector_view_type_3d]" at line 497 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"
            instantiation of "void __do_gemm_parallel_batched_heuristic_template(options_t, gemm_args_t) [with algo_tag=void, blocking_type=void, device_type=default_device, algo_mode=void]" at line 589 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"
            instantiation of "void __do_gemm_parallel_batched_heuristic(options_t, gemm_args_t) [with algo_tag=void, blocking_type=void, device_type=default_device, algo_mode=void]" at line 2265 of "/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp"

[ 88%] Linking CXX executable KokkosKernels_wiki_spmv

[ 88%] Built target KokkosKernels_wiki_spmv

Scanning dependencies of target KokkosKernels_wiki_crsmatrix

[ 88%] Building CXX object example/wiki/sparse/CMakeFiles/KokkosKernels_wiki_crsmatrix.dir/KokkosSparse_wiki_crsmatrix.cpp.o

[ 88%] Linking CXX executable KokkosKernels_wiki_spadd

[ 88%] Built target KokkosKernels_wiki_spadd

[ 88%] Linking CXX executable KokkosKernels_wiki_spgemm

Scanning dependencies of target KokkosKernels_wiki_gauss_seidel

[ 88%] Building CXX object example/wiki/sparse/CMakeFiles/KokkosKernels_wiki_gauss_seidel.dir/KokkosSparse_wiki_gauss_seidel.cpp.o

compilation aborted for /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_perf_test.cpp (code 2)

make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 2

make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2

make[1]: *** Waiting for unfinished jobs....

[ 88%] Built target KokkosKernels_wiki_spgemm

[ 89%] Linking CXX executable KokkosKernels_wiki_crsmatrix

[ 89%] Built target KokkosKernels_wiki_crsmatrix

compilation aborted for /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/kokkos-kernels/unit_test/threads/Test_Threads_Batched_Dense.cpp (code 2)

make[2]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_threads.dir/threads/Test_Threads_Batched_Dense.cpp.o] Error 2

make[1]: *** [unit_test/CMakeFiles/KokkosKernels_batched_dla_threads.dir/all] Error 2

[ 90%] Linking CXX executable KokkosKernels_batched_sla_threads

[ 91%] Linking CXX executable KokkosKernels_wiki_gauss_seidel

[ 91%] Built target KokkosKernels_batched_sla_threads

[ 91%] Built target KokkosKernels_wiki_gauss_seidel

[ 91%] Linking CXX executable sparse_kk_spmv

[ 91%] Built target sparse_kk_spmv

[ 91%] Linking CXX executable sparse_spmv_struct_tuning

[ 91%] Built target sparse_spmv_struct_tuning

[ 91%] Linking CXX executable KokkosKernels_common_threads

[ 91%] Built target KokkosKernels_common_threads

[ 92%] Linking CXX executable KokkosKernels_blas_threads

[ 92%] Built target KokkosKernels_blas_threads

[ 92%] Linking CXX executable KokkosKernels_graph_threads

[ 92%] Built target KokkosKernels_graph_threads

[ 92%] Linking CXX executable KokkosKernels_sparse_threads

[ 92%] Built target KokkosKernels_sparse_threads

make: *** [all] Error 2

#######################################################

PASSED TESTS

#######################################################

#######################################################

FAILED TESTS

#######################################################

intel-18.1.163-OpenMP-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 intel/compilers/18.1.163



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=OpenMP --arch=SKX --compiler=/home/projects/x86-64/intel/compilers/2018/compilers_and_libraries_2018.1.163/linux/bin/intel64/icpc --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=mkl    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.714/TestAll_2022-01-06_20.20.56/intel/18.1.163/OpenMP-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

intel-18.1.163-Pthread-release (build failed)

#######################################################


Reproducer instructions:


Load modules:


    source /etc/profile.d/modules.sh
    module purge
    module load cmake/3.19.3 intel/compilers/18.1.163



$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread --arch=SKX --compiler=/home/projects/x86-64/intel/compilers/2018/compilers_and_libraries_2018.1.163/linux/bin/intel64/icpc --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=mkl    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_Tpls_INTEL18/KokkosKernels_PullRequest_Tpls_INTEL18.714/TestAll_2022-01-06_20.20.56/intel/18.1.163/Pthread-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1014771

salloc: Job allocation 1014771 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE
Console Output (last 100 lines) : KokkosKernels_PullRequest_CLANG1001 # 119 (click to expand) 

In file included from /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_perf_test.cpp:46:
In file included from /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp:56:
In file included from /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:591:
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:370:35: error: comparison of integers of different signs: 'unsigned int' and 'int' [-Werror,-Wsign-compare]
                  for (kk = 0; kk < __k - TILE_K; kk += TILE_K) {
                               ~~ ^ ~~~~~~~~~~~~
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/KokkosKernels_PullRequest_CLANG1001.119/TestAll_2022-01-06_20.21.05/clang/10.0.1/Pthread_Serial-release/kokkos-install/include/Threads/Kokkos_Threads_Parallel.hpp:290:7: note: in instantiation of member function 'KokkosBatched::Impl::BatchedDblBufGemm, Kokkos::View, Kokkos::View, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::No, 32, 32, 8>::Functor::operator()' requested here
      functor(member);
      ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/KokkosKernels_PullRequest_CLANG1001.119/TestAll_2022-01-06_20.21.05/clang/10.0.1/Pthread_Serial-release/kokkos-install/include/Threads/Kokkos_Threads_Parallel.hpp:329:18: note: in instantiation of function template specialization 'Kokkos::Impl::ParallelFor, Kokkos::View, Kokkos::View, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::No, 32, 32, 8>::Functor, Kokkos::TeamPolicy, Kokkos::Threads>::exec_team' requested here
    ParallelFor::exec_team(
                 ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/KokkosKernels_PullRequest_CLANG1001.119/TestAll_2022-01-06_20.21.05/clang/10.0.1/Pthread_Serial-release/kokkos-install/include/Threads/Kokkos_Threads_Parallel.hpp:352:38: note: in instantiation of member function 'Kokkos::Impl::ParallelFor, Kokkos::View, Kokkos::View, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::No, 32, 32, 8>::Functor, Kokkos::TeamPolicy, Kokkos::Threads>::exec' requested here
    ThreadsExec::start(&ParallelFor::exec, this);
                                     ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/KokkosKernels_PullRequest_CLANG1001.119/TestAll_2022-01-06_20.21.05/clang/10.0.1/Pthread_Serial-release/kokkos-install/include/Kokkos_Parallel.hpp:144:11: note: in instantiation of member function 'Kokkos::Impl::ParallelFor, Kokkos::View, Kokkos::View, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::No, 32, 32, 8>::Functor, Kokkos::TeamPolicy, Kokkos::Threads>::execute' requested here
  closure.execute();
          ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/KokkosKernels_PullRequest_CLANG1001.119/TestAll_2022-01-06_20.21.05/clang/10.0.1/Pthread_Serial-release/kokkos-install/include/Kokkos_Parallel.hpp:175:13: note: in instantiation of function template specialization 'Kokkos::parallel_for, KokkosBatched::Impl::BatchedDblBufGemm, Kokkos::View, Kokkos::View, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::No, 32, 32, 8>::Functor >' requested here
  ::Kokkos::parallel_for(policy, functor, str);
            ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:196:13: note: (skipping 1 context in backtrace; use -ftemplate-backtrace-limit=0 to see all)
    Kokkos::parallel_for("BatchedDblBufGemm", team_policy, functor);
            ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/dense/impl/KokkosBatched_Gemm_DblBuf_Impl.hpp:113:5: note: in instantiation of member function 'KokkosBatched::Impl::BatchedDblBufGemm, Kokkos::View, Kokkos::View, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::No, 32, 32, 8>::__run' requested here
    __run();
    ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/src/batched/dense/KokkosBatched_Gemm_Decl.hpp:515:22: note: in instantiation of member function 'KokkosBatched::Impl::BatchedDblBufGemm, Kokkos::View, Kokkos::View, KokkosBatched::BoundsCheck::Yes, KokkosBatched::AlphaTag::No, 32, 32, 8>::invoke' requested here
                    .invoke();
                     ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp:507:22: note: in instantiation of function template specialization 'KokkosBatched::BatchedGemm, Kokkos::View, Kokkos::View >' requested here
      KokkosBatched::BatchedGemm(
                     ^
/home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/kokkos-kernels/perf_test/blas/blas3/KokkosBlas3_gemm_perf_test.hpp:587:5: note: in instantiation of function template specialization '__do_gemm_parallel_batched_heuristic_template' requested here
    __do_gemm_parallel_batched_heuristic_template' requested here
      __do_gemm_parallel_batched_heuristic);
      ^
fatal error: too many errors emitted, stopping now [-ferror-limit=]
20 errors generated.
make[2]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/KokkosBlas3_perf_test.cpp.o] Error 1
make[1]: *** [perf_test/blas/blas3/CMakeFiles/KokkosBlas3_perf_test.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
Scanning dependencies of target KokkosKernels_batched_sla_serial
[ 82%] Building CXX object unit_test/CMakeFiles/KokkosKernels_batched_sla_serial.dir/Test_Main.cpp.o
[ 82%] Building CXX object unit_test/CMakeFiles/KokkosKernels_batched_sla_serial.dir/serial/Test_Serial_Batched_Sparse.cpp.o
[ 82%] Linking CXX executable sparse_spgemm_jacobi
[ 82%] Built target sparse_spgemm_jacobi
[ 83%] Linking CXX executable KokkosBlas_perf_test
[ 83%] Built target KokkosBlas_perf_test
[ 84%] Linking CXX executable sparse_gs
[ 85%] Linking CXX executable sparse_sptrsv_supernode
[ 85%] Built target sparse_gs
[ 85%] Built target sparse_sptrsv_supernode
[ 86%] Linking CXX executable KokkosBlas3_gemm_perf_test
[ 86%] Built target KokkosBlas3_gemm_perf_test
[ 86%] Linking CXX executable KokkosBlas2_gemv_perf_test
[ 86%] Built target KokkosBlas2_gemv_perf_test
[ 86%] Linking CXX executable sparse_kk_spmv
[ 86%] Built target sparse_kk_spmv
[ 87%] Linking CXX executable KokkosKernels_batched_sla_serial
[ 87%] Built target KokkosKernels_batched_sla_serial
[ 87%] Linking CXX executable KokkosKernels_graph_threads
[ 87%] Built target KokkosKernels_graph_threads
[ 87%] Linking CXX executable KokkosKernels_blas_serial
[ 87%] Built target KokkosKernels_blas_serial
make: *** [all] Error 2
#######################################################
PASSED TESTS
#######################################################
#######################################################
FAILED TESTS
#######################################################
clang-10.0.1-Pthread_Serial-release (build failed)
#######################################################
  # Reproducer instructions:
  #   Load modules:
        source /etc/profile.d/modules.sh
        module purge
        module load cmake/3.19.3 clang/10.0.1

$KOKKOSKERNELS_PATH/cm_generate_makefile.bash --with-devices=Pthread,Serial --arch=SKX --compiler=/home/projects/x86-64/spack/opt/spack/linux-rhel7-x86_64/gcc-10.2.0/llvm-10.0.1-nldepabrxk2zcykcq7rlky5sr53hnm63/bin/clang++ --cxxflags="-O3 -Wall -Wunused-parameter -Wshadow -pedantic -Werror -Wsign-compare -Wtype-limits -Wuninitialized " --cxxstandard="14" --ldflags=""   --kokkos-path=$KOKKOS_PATH --kokkoskernels-path=$KOKKOSKERNELS_PATH --with-scalars='double,complex_double' --with-ordinals=int --with-offsets=int,size_t --with-layouts=LayoutLeft --with-tpls=    --with-options= --with-cuda-options=   --no-examples


To reload modules, reconfigure, rebuild, and retest directly from this failing build do the following:


  # Move to the build directory
    cd /home/jenkins/blake-new/workspace/KokkosKernels_PullRequest_CLANG1001/KokkosKernels_PullRequest_CLANG1001.119/TestAll_2022-01-06_20.21.05/clang/10.0.1/Pthread_Serial-release
  # To reload modules
    source ./reload_modules.sh
  # To reconfigure
    ./call_generate_makefile.sh
  # To rebuild
    make -j
  # To retest
    ctest -V



#######################################################

salloc: Relinquishing job allocation 1014772

salloc: Job allocation 1014772 has been revoked.

Build step 'Execute shell' marked build as failure

Finished: FAILURE

@kokkos-devops-admin
Copy link

Status Flag 'Pre-Test Inspection' - Auto Inspected - Inspection Is Not Necessary for this Pull Request.

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Testing Jenkins Projects:

Pull Request Auto Testing STARTING (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740

  • Build Num: 80
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight

  • Build Num: 79
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 737
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 384
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 728
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 716
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_CLANG1001

  • Build Num: 121
  • Status: STARTED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Using Repos:

Repo: KOKKOSKERNELS (vqd8a/kokkos-kernels)
  • Branch: batched_gemm_fix_alpha
  • SHA: 9b1ed7c
  • Mode: TEST_REPO

Pull Request Author: vqd8a

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Jenkins Testing: all Jobs PASSED

Pull Request Auto Testing has PASSED (click to expand)

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA9_GCC720_Light_Tpls_GCC720_GCC740

  • Build Num: 80
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_CUDA10_Tpls_CUDA10_LayoutRight

  • Build Num: 79
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720

  • Build Num: 737
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_GCC720_Light_LayoutRight

  • Build Num: 384
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_GCC720

  • Build Num: 728
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_Tpls_INTEL18

  • Build Num: 716
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

Build Information

Test Name: KokkosKernels_PullRequest_CLANG1001

  • Build Num: 121
  • Status: PASSED

Jenkins Parameters

Parameter Name Value
KOKKOSKERNELS_SOURCE_BRANCH batched_gemm_fix_alpha
KOKKOSKERNELS_SOURCE_REPO https://github.com/vqd8a/kokkos-kernels
KOKKOSKERNELS_SOURCE_SHA 9b1ed7c
KOKKOSKERNELS_TARGET_BRANCH develop
KOKKOSKERNELS_TARGET_REPO https://github.com/kokkos/kokkos-kernels
KOKKOSKERNELS_TARGET_SHA 056443b
PR_LABELS
PULLREQUESTNUM 1239
TEST_REPO_ALIAS KOKKOSKERNELS

@kokkos-devops-admin
Copy link

Status Flag 'Pre-Merge Inspection' - - This Pull Request Requires Inspection... The code must be inspected by a member of the Team before Testing/Merging
THE LAST COMMIT TO THIS PULL REQUEST HAS NOT BEEN REVIEWED YET!

@kokkos-devops-admin
Copy link

All Jobs Finished; status = PASSED, However Inspection must be performed before merge can occur...

e10harvey
e10harvey approved these changes Jan 7, 2022
View reviewed changes
Copy link
Contributor

@e10harvey e10harvey left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you, @vqd8a !

@kokkos-devops-admin
Copy link

Status Flag 'Pre-Merge Inspection' - SUCCESS: The last commit to this Pull Request has been INSPECTED AND APPROVED by [ e10harvey ]!

@kokkos-devops-admin
Copy link

Status Flag 'Pull Request AutoTester' - Pull Request MUST BE MERGED MANUALLY BY Project Team - This Repo does not support Automerge

@e10harvey e10harvey merged commit 8635901 into kokkos:develop Jan 7, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@e10harvey e10harvey e10harvey approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@vqd8a @kokkos-devops-admin @e10harvey