From 712c63d94f81a6e75b41fc69d6939a08f5d38c43 Mon Sep 17 00:00:00 2001 From: Viacheslav Astrakhantsev <48382010+NISHIY-EKSDEE@users.noreply.github.com> Date: Mon, 23 Sep 2024 17:50:15 +0200 Subject: [PATCH 1/5] Change instance label --- .github/workflows/fbgemm_gpu_ci_rocm.yml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/fbgemm_gpu_ci_rocm.yml b/.github/workflows/fbgemm_gpu_ci_rocm.yml index f3fca6f5bf..4d04ccbab7 100644 --- a/.github/workflows/fbgemm_gpu_ci_rocm.yml +++ b/.github/workflows/fbgemm_gpu_ci_rocm.yml @@ -60,7 +60,7 @@ jobs: fail-fast: false matrix: host-machine: [ - { arch: x86, instance: "linux.24xlarge" }, + { arch: x86, instance: "gfx90a" }, ] container-image: [ "ubuntu:20.04" ] python-version: [ "3.8", "3.9", "3.10", "3.11", "3.12" ] @@ -138,7 +138,7 @@ jobs: fail-fast: false matrix: host-machine: [ - { arch: x86, instance: "rocm" }, + { arch: x86, instance: "gfx90a" }, ] # ROCm machines are limited, so we only test a subset of Python versions python-version: [ "3.12" ] From 2b608ed8842df3ebe29b4584e73cfa4aff057984 Mon Sep 17 00:00:00 2001 From: Viacheslav Astrakhantsev <48382010+NISHIY-EKSDEE@users.noreply.github.com> Date: Tue, 24 Sep 2024 14:36:05 +0200 Subject: [PATCH 2/5] Change rocm version --- .github/workflows/fbgemm_gpu_ci_rocm.yml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/fbgemm_gpu_ci_rocm.yml b/.github/workflows/fbgemm_gpu_ci_rocm.yml index 4d04ccbab7..89c451feef 100644 --- a/.github/workflows/fbgemm_gpu_ci_rocm.yml +++ b/.github/workflows/fbgemm_gpu_ci_rocm.yml @@ -64,7 +64,7 @@ jobs: ] container-image: [ "ubuntu:20.04" ] python-version: [ "3.8", "3.9", "3.10", "3.11", "3.12" ] - rocm-version: [ "6.0.2" ] + rocm-version: [ "6.2" ] compiler: [ "gcc", "clang" ] steps: @@ -142,7 +142,7 @@ jobs: ] # ROCm machines are limited, so we only test a subset of Python versions python-version: [ "3.12" ] - rocm-version: [ "6.0.2" ] + rocm-version: [ "6.2" ] compiler: [ "gcc", "clang" ] needs: build_artifact From a378f1972b54a218622b3a0922369c6a0d2763e4 Mon Sep 17 00:00:00 2001 From: Viacheslav Astrakhantsev <48382010+NISHIY-EKSDEE@users.noreply.github.com> Date: Tue, 24 Sep 2024 18:28:14 +0200 Subject: [PATCH 3/5] Remove python3.8 --- .github/workflows/fbgemm_gpu_ci_rocm.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/fbgemm_gpu_ci_rocm.yml b/.github/workflows/fbgemm_gpu_ci_rocm.yml index 89c451feef..2dc047364f 100644 --- a/.github/workflows/fbgemm_gpu_ci_rocm.yml +++ b/.github/workflows/fbgemm_gpu_ci_rocm.yml @@ -63,7 +63,7 @@ jobs: { arch: x86, instance: "gfx90a" }, ] container-image: [ "ubuntu:20.04" ] - python-version: [ "3.8", "3.9", "3.10", "3.11", "3.12" ] + python-version: [ "3.9", "3.10", "3.11", "3.12" ] rocm-version: [ "6.2" ] compiler: [ "gcc", "clang" ] From bbca0942d091a2fc1ea4aa220d295261697bd3ae Mon Sep 17 00:00:00 2001 From: Viacheslav Astrakhantsev <48382010+NISHIY-EKSDEE@users.noreply.github.com> Date: Wed, 25 Sep 2024 11:58:43 +0200 Subject: [PATCH 4/5] Remove timeout for tests --- .github/workflows/fbgemm_gpu_ci_rocm.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/fbgemm_gpu_ci_rocm.yml b/.github/workflows/fbgemm_gpu_ci_rocm.yml index 2dc047364f..1797414321 100644 --- a/.github/workflows/fbgemm_gpu_ci_rocm.yml +++ b/.github/workflows/fbgemm_gpu_ci_rocm.yml @@ -190,5 +190,5 @@ jobs: run: . $PRELUDE; install_fbgemm_gpu_wheel $BUILD_ENV *.whl - name: Test with PyTest - timeout-minutes: 20 + # timeout-minutes: 20 run: . $PRELUDE; cd fbgemm_gpu/test; run_fbgemm_gpu_tests $BUILD_ENV rocm From 33eb3984aaf24b53130be25b6fdbf08559e2b758 Mon Sep 17 00:00:00 2001 From: Viacheslav Astrakhantsev <48382010+NISHIY-EKSDEE@users.noreply.github.com> Date: Fri, 27 Sep 2024 19:20:38 +0200 Subject: [PATCH 5/5] Return timeout for tests --- .github/workflows/fbgemm_gpu_ci_rocm.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/fbgemm_gpu_ci_rocm.yml b/.github/workflows/fbgemm_gpu_ci_rocm.yml index 1797414321..2dc047364f 100644 --- a/.github/workflows/fbgemm_gpu_ci_rocm.yml +++ b/.github/workflows/fbgemm_gpu_ci_rocm.yml @@ -190,5 +190,5 @@ jobs: run: . $PRELUDE; install_fbgemm_gpu_wheel $BUILD_ENV *.whl - name: Test with PyTest - # timeout-minutes: 20 + timeout-minutes: 20 run: . $PRELUDE; cd fbgemm_gpu/test; run_fbgemm_gpu_tests $BUILD_ENV rocm