Skip to content
102 changes: 102 additions & 0 deletions .azure-pipelines/nccl-api-test.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -175,6 +175,108 @@ 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/reduce_scatter_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20"'
workingDirectory: '$(System.DefaultWorkingDirectory)'

- task: Bash@3
name: InstallNccl
displayName: Install NCCL
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 $SSH_OPTION 'sudo docker exec -t mscclpp-test bash -c " \
cd; git clone https://github.com/NVIDIA/nccl.git; \
cd nccl; \
make -j src.build NVCC_GENCODE="-gencode=arch=compute_80,code=sm_80""'
workingDirectory: '$(System.DefaultWorkingDirectory)'

- task: Bash@3
name: RunNcclAllGatherFallbaclkToNcclTest
displayName: Run NCCL AllGather Test with or without Fallback to NCCL operation
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 $SSH_OPTION 'sudo docker exec -t mscclpp-test bash -c "\
cd /root/mscclpp; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so /root/nccl-tests/build/all_gather_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="all" /root/nccl-tests/build/all_gather_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="allgather" /root/nccl-tests/build/all_gather_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="allgather,allreduce" /root/nccl-tests/build/all_gather_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="allreduce" /root/nccl-tests/build/all_gather_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20"'
workingDirectory: '$(System.DefaultWorkingDirectory)'

- task: Bash@3
name: RunNcclAllReduceFallbaclkToNcclTest
displayName: Run NCCL AllReduce Test with or without Fallback to NCCL operation
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 $SSH_OPTION 'sudo docker exec -t mscclpp-test bash -c "\
cd /root/mscclpp; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so /root/nccl-tests/build/all_reduce_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="all" /root/nccl-tests/build/all_reduce_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="allreduce" /root/nccl-tests/build/all_reduce_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="allreduce,allgather" /root/nccl-tests/build/all_reduce_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="allgather" /root/nccl-tests/build/all_reduce_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20"'
workingDirectory: '$(System.DefaultWorkingDirectory)'

- task: Bash@3
name: RunNcclBroadcastFallbaclkToNcclTest
displayName: Run NCCL Broadcast Test with or without Fallback to NCCL operation
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 $SSH_OPTION 'sudo docker exec -t mscclpp-test bash -c "\
cd /root/mscclpp; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so /root/nccl-tests/build/broadcast_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="all" /root/nccl-tests/build/broadcast_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="broadcast" /root/nccl-tests/build/broadcast_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="broadcast,allgather" /root/nccl-tests/build/broadcast_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="allreduce" /root/nccl-tests/build/broadcast_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20"'
workingDirectory: '$(System.DefaultWorkingDirectory)'

- task: Bash@3
name: RunNcclReduceScatterFallbaclkToNcclTest
displayName: Run NCCL ReduceScatter Test with or without Fallback to NCCL operation
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 $SSH_OPTION 'sudo docker exec -t mscclpp-test bash -c "\
cd /root/mscclpp; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so /root/nccl-tests/build/reduce_scatter_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="all" /root/nccl-tests/build/reduce_scatter_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="reducescatter" /root/nccl-tests/build/reduce_scatter_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="reducescatter,allgather" /root/nccl-tests/build/reduce_scatter_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20; \
mpirun -np 8 --bind-to numa --allow-run-as-root -x LD_PRELOAD=/root/mscclpp/build/apps/nccl/libmscclpp_nccl.so -x NCCL_DEBUG=WARN -x MSCCLPP_ENABLE_NCCL_FALLBACK=TRUE -x MSCCLPP_NCCL_LIB_PATH=/root/nccl/build/lib/libnccl.so -x MSCCLPP_FORCE_NCCL_FALLBACK_OPERATION="broadcast" -x MSCCLPP_EXECUTION_PLAN_DIR=/root/mscclpp/msccl-users/execution-files /root/nccl-tests/build/reduce_scatter_perf -b 1K -e 1G -f 2 -d half -G 20 -w 10 -n 20"'
workingDirectory: '$(System.DefaultWorkingDirectory)'

- task: AzureCLI@2
name: StopVMSS
displayName: Deallocate VMSS
Expand Down
Loading