Skip to content

Commit

Permalink
Combine job CI check
Browse files Browse the repository at this point in the history
  • Loading branch information
Aswinmcw committed Nov 14, 2024
1 parent ed03f77 commit e803b9c
Showing 1 changed file with 16 additions and 7 deletions.
23 changes: 16 additions & 7 deletions .github/workflows/t3000-model-perf-tests-impl.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -22,8 +22,7 @@ jobs:
{ name: "t3k LLM llama3 model perf tests", model: "llama3", model-type: "LLM", arch: wormhole_b0, cmd: run_t3000_llama3_tests, timeout: 60, owner_id: U03PUAKE719}, # Miguel Tairum
{ name: "t3k LLM falcon40b model perf tests", model: "falcon40b", model-type: "LLM", arch: wormhole_b0, cmd: run_t3000_falcon40b_tests, timeout: 75, owner_id: U053W15B6JF}, # Djordje Ivanovic
{ name: "t3k CNN resnet50 model perf tests", model: "resnet50", model-type: "CNN", arch: wormhole_b0, cmd: run_t3000_resnet50_tests, timeout: 75, owner_id: U013121KDH9}, # Austin Ho
{ name: "t3k CCL all_gather perf tests", model: "all_gather", arch: wormhole_b0, cmd: run_t3000_ccl_all_gather_perf_tests, timeout: 75, tracy: true, owner_id: ULMEPM2MA}, # Sean Nijjar
{ name: "t3k CCL reduce_scatter perf tests", model: "reduce_scatter", arch: wormhole_b0, cmd: run_t3000_ccl_reduce_scatter_perf_tests, timeout: 75, tracy: true, owner_id: ULMEPM2MA}, # Sean Nijjar
{ name: "t3k CCL perf tests", arch: wormhole_b0, cmd: run_t3000_ccl_all_gather_perf_tests && run_t3000_ccl_reduce_scatter_perf_tests, timeout: 75, tracy: true, owner_id: ULMEPM2MA}, # Sean Nijjar
#{ name: "t3k CNN model perf tests ", model-type: "CNN", arch: wormhole_b0, cmd: run_t3000_cnn_tests, timeout: 120, owner_id: }, #No tests are being run?
]
name: ${{ matrix.test-group.name }}
Expand Down Expand Up @@ -81,15 +80,25 @@ jobs:
run: |
TODAY=$(date +%Y_%m_%d)
PERF_REPORT_FILENAME_MODELS="Models_Perf_${TODAY}.csv"
PERF_REPORT_FILENAME_CCL="CCL_${{ matrix.test-group.model }}_Perf_${TODAY}.csv"
PERF_REPORT_FILENAME_CCL_ALL_GATHER="CCL_all_gather_Perf_${TODAY}.csv"
PERF_REPORT_FILENAME_CCL_REDUCE_SCATTER="CCL_reduce_scatter_Perf_${TODAY}.csv"
if [ "${{ matrix.test-group.tracy }}" == "true" ]; then
if [ -f "$PERF_REPORT_FILENAME_CCL" ]; then
echo "Found CCL Perf report: $PERF_REPORT_FILENAME_CCL"
echo "perf_report_filename=$PERF_REPORT_FILENAME_CCL" >> "$GITHUB_OUTPUT"
else
found_reports=false
if [ -f "$PERF_REPORT_FILENAME_CCL_ALL_GATHER" ]; then
echo "Found CCL AllGather Perf report: $PERF_REPORT_FILENAME_CCL_ALL_GATHER"
echo "perf_report_filename_all_gather=$PERF_REPORT_FILENAME_CCL_ALL_GATHER" >> "$GITHUB_OUTPUT"
found_reports=true
fi
if [ -f "$PERF_REPORT_FILENAME_CCL_REDUCE_SCATTER" ]; then
echo "Found CCL ReduceScatter Perf report: $PERF_REPORT_FILENAME_CCL_REDUCE_SCATTER"
echo "perf_report_filename_reduce_scatter=$PERF_REPORT_FILENAME_CCL_REDUCE_SCATTER" >> "$GITHUB_OUTPUT"
found_reports=true
fi
if [ "$found_reports" = false ]; then
echo "No CCL perf report found for today."
exit 1
fi
fi
else
if [ -f "$PERF_REPORT_FILENAME_MODELS" ]; then
echo "Found Models Perf report: $PERF_REPORT_FILENAME_MODELS"
Expand Down

0 comments on commit e803b9c

Please sign in to comment.