From f07c96c0e244c9c05ae28268af9d1811ac7488d9 Mon Sep 17 00:00:00 2001 From: Scott Todd Date: Thu, 11 Jul 2024 17:45:50 -0700 Subject: [PATCH] Round up sdxl golden dispatch sizes and mi250 times by 10%. (#17879) See [this discussion on Discord](https://discord.com/channels/689900678990135345/689957613152239638/1261059802214305913). These are change detector tests with _some_ use, but exact checking is too noisy and is causing significant churn across PRs and postsubmit CI runs. We could change the test script to allow a certain error range, but for now just increase the thresholds used in `<=` checks by about 10% (then drop a few digits to 0 so we don't give the appearance of high precision). ci-exactly: build_packages,regression_test --- .github/workflows/pkgci_regression_test.yml | 23 ++++++++++++--------- 1 file changed, 13 insertions(+), 10 deletions(-) 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 \