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

spgemm unit test: update cusparse macro check #294

Merged
merged 2 commits into from
Sep 28, 2018
Merged

spgemm unit test: update cusparse macro check #294

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
53ea507
spgemm unit test: update cusparse macro check
ndellingwood Sep 13, 2018
4698865
Test_Sparse_spgemm.hpp: Disable CUSPARSE spgemm test
ndellingwood Sep 28, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions unit_test/sparse/Test_Sparse_spgemm.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -287,9 +287,9 @@ void test_spgemm(lno_t numRows, size_type nnz, lno_t bandwidth, lno_t row_size_v
crsMat_t output_mat2;
run_spgemm<crsMat_t, device>(input_mat, input_mat, SPGEMM_DEBUG, output_mat2);

SPGEMMAlgorithm algorithms [] = {SPGEMM_KK_MEMORY, SPGEMM_KK_SPEED, SPGEMM_KK_MEMSPEED, SPGEMM_CUSPARSE,SPGEMM_MKL};
SPGEMMAlgorithm algorithms [] = {SPGEMM_KK_MEMORY, SPGEMM_KK_SPEED, SPGEMM_KK_MEMSPEED, /*SPGEMM_CUSPARSE, */SPGEMM_MKL};

for (int ii = 0; ii < 5; ++ii){
for (int ii = 0; ii < 4; ++ii){

SPGEMMAlgorithm spgemm_algorithm = algorithms[ii];

Expand All @@ -301,7 +301,7 @@ void test_spgemm(lno_t numRows, size_type nnz, lno_t bandwidth, lno_t row_size_v
case SPGEMM_CUSPARSE:
//TODO: add these test failure cases for cusparse too.
algo = "SPGEMM_CUSPARSE";
#ifndef KERNELS_HAVE_CUSPARSE
#if !defined(KERNELS_HAVE_CUSPARSE) && !defined(KOKKOSKERNELS_ENABLE_TPL_CUSPARSE)
Copy link
Contributor

Choose a reason for hiding this comment

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

Did we check this modification pass the test in kokkoskernels with cusparse enabled ?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Not yet, trying to get the Trilinos build on White going.
Are there extra settings to use cusparse like with mkl? For example, adding an extra cxxflag, setting an a path variable, etc? I haven't built kokkos-kernels with cusparse before

Copy link
Contributor

Choose a reason for hiding this comment

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

I am not sure. One problematic thing is that "cmake configure" may not match to "make configure". We have two build systems and cmake configure is not tested nor updated in the kokkoskernels level. cusparse or cublas should be ON by default when you test on cuda machines; however, it is possible that some macro variables may not set correctly. Let's wait until your test on white is done.

is_expected_to_fail = true;
#endif
break;
Expand Down