Skip to content

[skip ci] TEST ONLY #1230

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
dpressle wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

[skip ci] TEST ONLY #1230

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .ci/scripts/env.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,4 +17,4 @@ export CONFIGS_DIR="${SRC_ROOT_DIR}/.ci/configs"

# DLRM MASTER_PORT
export MASTER_PORT="12346"
export DOCKER_SSH_PORT="12345"
export DOCKER_SSH_PORT="${DOCKER_SSH_PORT:-12345}"
6 changes: 3 additions & 3 deletions .ci/scripts/run_dlrm.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ mpirun \
-np $NP \
--hostfile ${HOSTFILE} \
--map-by node \
--mca plm_rsh_args '-p 12345' \
--mca plm_rsh_args "-p ${DOCKER_SSH_PORT}" \
-x PATH \
-x LD_LIBRARY_PATH \
hostname
Expand All @@ -42,7 +42,7 @@ mpirun \
-np $NP \
--hostfile ${HOSTFILE} \
--map-by node \
--mca plm_rsh_args '-p 12345' \
--mca plm_rsh_args "-p ${DOCKER_SSH_PORT}" \
-x PATH \
-x LD_LIBRARY_PATH \
cat /proc/1/cgroup
Expand All @@ -52,7 +52,7 @@ mpirun \
-np $NP \
--hostfile ${HOSTFILE} \
--map-by node \
--mca plm_rsh_args '-p 12345' \
--mca plm_rsh_args "-p ${DOCKER_SSH_PORT}" \
-x PATH \
-x LD_LIBRARY_PATH \
-x MASTER_ADDR \
Expand Down
2 changes: 1 addition & 1 deletion .ci/scripts/run_tests_ucc_mpi.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,7 @@ function mpi_params {
fi
echo "-np $((nnodes*ppn)) --oversubscribe --hostfile ${HOSTFILE} \
--map-by ppr:$ppn:node --bind-to socket \
-x PATH -x LD_LIBRARY_PATH --mca opal_common_ucx_opal_mem_hooks 1 --mca plm_rsh_args -p12345 \
-x PATH -x LD_LIBRARY_PATH --mca opal_common_ucx_opal_mem_hooks 1 --mca plm_rsh_args -p${DOCKER_SSH_PORT} \
--mca coll ^ucc,hcoll \
-x UCX_NET_DEVICES=$DEV:1"
}
Expand Down
18 changes: 18 additions & 0 deletions .ci/scripts/run_tests_ucc_nvls.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
#!/bin/bash -eEx


SCRIPT_DIR="$(
cd "$(dirname "$0")"
pwd -P
)"
cd "${SCRIPT_DIR}"
. "${SCRIPT_DIR}/env.sh"

export OMPI_MCA_coll=^hcoll
export OMPI_MCA_coll_ucc_enable=0
export UCC_TLS=cuda,ucp
export UCC_LOG_LEVEL=info
export UCC_TL_CUDA_NVLS_SM_COUNT=20
export UCC_TL_CUDA_TUNE=allreduce:cuda:@0

/opt/nvidia/bin/ucc/build/bin/ucc_perftest -c allreduce -F -m cuda -b 1k -e 32M -d bfloat16 -o sum
12 changes: 12 additions & 0 deletions .ci/scripts/run_tests_ucc_nvls_slurm.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
#!/bin/bash -eEx


SCRIPT_DIR="$(
cd "$(dirname "$0")"
pwd -P
)"
cd "${SCRIPT_DIR}"
. "${SCRIPT_DIR}/env.sh"

# slurm_command_prefix="scctl client connect --"
scctl client connect -- srun --jobid=${JOB_ID} --nodes=2 --mpi=pmix --cpu-bind=verbose --ntasks-per-node=1 --gpus-per-node=1 --container-image=${DOCKER_IMAGE_NAME} /opt/nvidia/src/ucc/.ci/scripts/run_tests_ucc_nvls.sh
Loading