Update iree test cache location for new mi250 cluster (#18083)
As we move to using the Alpha 2 mi250 cluster, each home directory only
has 100GB available to it. There is a shared storage for each group (our
being aig_sharks) where we get access to 10 TB. So, this is updating the
cache location to use that. Previously when using home directory, the
100gb got filled up and CI went down for the mi250 last night.
diff --git a/.github/workflows/pkgci_regression_test.yml b/.github/workflows/pkgci_regression_test.yml
index d2d7c0f..e21c447 100644
--- a/.github/workflows/pkgci_regression_test.yml
+++ b/.github/workflows/pkgci_regression_test.yml
@@ -139,17 +139,21 @@
# CPU
- name: cpu_llvm_task
models-config-file: models_cpu_llvm_task.json
+ iree-tests-cache: ~/iree_tests_cache
runs-on: nodai-amdgpu-w7900-x86-64
# AMD GPU
- name: amdgpu_rocm_mi250_gfx90a
models-config-file: models_gpu_rocm_gfx90a.json
+ iree-tests-cache: /groups/aig_sharks/iree-tests-cache
runs-on: nodai-amdgpu-mi250-x86-64
- name: amdgpu_rocm_mi300_gfx942
models-config-file: models_gpu_rocm_gfx942.json
+ iree-tests-cache: ~/iree_tests_cache
runs-on: nodai-amdgpu-mi300-x86-64
- name: amdgpu_vulkan
models-config-file: models_gpu_vulkan.json
+ iree-tests-cache: ~/iree_tests_cache
runs-on: nodai-amdgpu-w7900-x86-64
# NVIDIA GPU
@@ -163,7 +167,7 @@
env:
PACKAGE_DOWNLOAD_DIR: ${{ github.workspace }}/.packages
IREERS_ARTIFACT_DIR: ${{ github.workspace }}/artifacts
- IREE_TEST_FILES: ~/iree_tests_cache
+ IREE_TEST_FILES: ${{ matrix.iree-tests-cache }}
IREE_TEST_PATH_EXTENSION: ${{ github.workspace }}/build_tools/pkgci/external_test_suite
MODELS_CONFIG_FILE_PATH: build_tools/pkgci/external_test_suite/${{ matrix.models-config-file }}
VENV_DIR: ${{ github.workspace }}/venv
@@ -243,21 +247,24 @@
- name: cpu_llvm_task
models-config-file: models_cpu_llvm_task.json
backend: cpu
+ iree-tests-cache: ~/iree_tests_cache
runs-on: nodai-amdgpu-w7900-x86-64
# AMD GPU
- name: amdgpu_rocm_mi250_gfx90a
rocm-chip: gfx90a
backend: rocm
+ iree-tests-cache: /groups/aig_sharks/iree-tests-cache
runs-on: nodai-amdgpu-mi250-x86-64
- name: amdgpu_rocm_mi300_gfx942
rocm-chip: gfx942
backend: rocm
+ iree-tests-cache: ~/iree_tests_cache
runs-on: nodai-amdgpu-mi300-x86-64
env:
PACKAGE_DOWNLOAD_DIR: ${{ github.workspace }}/.packages
IREERS_ARTIFACT_DIR: ${{ github.workspace }}/artifacts
- IREE_TEST_FILES: ~/iree_tests_cache
+ IREE_TEST_FILES: ${{ matrix.iree-tests-cache }}
IREE_TEST_PATH_EXTENSION: ${{ github.workspace }}/build_tools/pkgci/external_test_suite
VENV_DIR: ${{ github.workspace }}/venv
LD_LIBRARY_PATH: /home/esaimana/Python-3.11.9