diff --git a/.github/workflows/pkgci_regression_test.yml b/.github/workflows/pkgci_regression_test.yml index 4a7554020865..98a6e2b8c8c2 100644 --- a/.github/workflows/pkgci_regression_test.yml +++ b/.github/workflows/pkgci_regression_test.yml @@ -307,21 +307,24 @@ jobs: --durations=0 \ --config-files=${SDXL_VAE_CONFIG_FILE_PATH} + # Note: mi250 benchmark times are more lenient than mi300 (allowing about + # 10% deviation from observed averages), since the mi250 runners we use + # are more unstable and we care most about peak performance on mi300. - name: "Running SDXL rocm pipeline benchmark (mi250)" if: contains(matrix.name, 'rocm_mi250_gfx90a') run: | source ${VENV_DIR}/bin/activate pytest SHARK-TestSuite/iree_tests/benchmarks/sdxl/benchmark_sdxl_rocm.py \ - --goldentime-rocm-e2e-ms 1340.0 \ - --goldentime-rocm-unet-ms 342.0 \ - --goldentime-rocm-clip-ms 17.5 \ - --goldentime-rocm-vae-ms 300.0 \ + --goldentime-rocm-e2e-ms 1450.0 \ + --goldentime-rocm-unet-ms 370.0 \ + --goldentime-rocm-clip-ms 18.5 \ + --goldentime-rocm-vae-ms 315.0 \ --goldendispatch-rocm-unet 1714 \ --goldendispatch-rocm-clip 1569 \ --goldendispatch-rocm-vae 248 \ - --goldensize-rocm-unet-bytes 2073609 \ - --goldensize-rocm-clip-bytes 783848 \ - --goldensize-rocm-vae-bytes 764909 \ + --goldensize-rocm-unet-bytes 2280000 \ + --goldensize-rocm-clip-bytes 860000 \ + --goldensize-rocm-vae-bytes 840000 \ --gpu-number 6 \ --rocm-chip gfx90a \ --log-cli-level=info \ @@ -341,9 +344,9 @@ jobs: --goldendispatch-rocm-unet 1714 \ --goldendispatch-rocm-clip 1569 \ --goldendispatch-rocm-vae 248 \ - --goldensize-rocm-unet-bytes 2065289 \ - --goldensize-rocm-clip-bytes 783848 \ - --goldensize-rocm-vae-bytes 765869 \ + --goldensize-rocm-unet-bytes 2270000 \ + --goldensize-rocm-clip-bytes 860000 \ + --goldensize-rocm-vae-bytes 840000 \ --gpu-number 0 \ --rocm-chip gfx942 \ --log-cli-level=info \