microsoft/mscclpp
1
0
Fork 0
mirror of https://github.com/microsoft/mscclpp.git synced 2026-05-12 09:17:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

NCCL API CI Test for ReduceScatter (#465)

Browse Source 
Co-authored-by: Binyang Li <binyli@microsoft.com>
This commit is contained in:
Caio Rocha
2025-03-17 13:58:32 -07:00
committed by GitHub
parent f124dc1df9
commit b6a179faff
1 changed files with 16 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
.azure-pipelines/nccl-api-test.yaml
View File

@@ -158,6 +158,22 @@ jobs:
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_EXECUTION_PLAN_DIR=/root/mscclpp/msccl-users/execution-files /root/nccl-tests/build/all_gather_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20"'
workingDirectory: '$(System.DefaultWorkingDirectory)'
- task: Bash@3
name: RunNcclReduceScatterTest
displayName: Run NCCL Reduce Scatter Test
inputs:
targetType: 'inline'
script: |
set -e
HOSTFILE=$(System.DefaultWorkingDirectory)/mscclpp/test/deploy/hostfile_ci
ROOT_DIR=$(System.DefaultWorkingDirectory)/mscclpp
SSH_OPTION="StrictHostKeyChecking=no"
KeyFilePath=${SSHKEYFILE_SECUREFILEPATH}
parallel-ssh -i -t 0 -h ${HOSTFILE} -x "-i ${KeyFilePath}" \
-O $SSH_OPTION 'sudo docker exec -t mscclpp-test bash -c "\
cd /root/mscclpp; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_EXECUTION_PLAN_DIR=/root/mscclpp/msccl-users/execution-files /root/nccl-tests/build/reduce_scatter_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20"'
workingDirectory: '$(System.DefaultWorkingDirectory)'
- task: AzureCLI@2
name: StopVMSS