[Bugfix][CI/Build][Hardware][AMD] Shard ID parameters in AMD tests running parallel jobs (#9279)

Signed-off-by: Hissu Hyvarinen <hissu.hyvarinen@amd.com>
This commit is contained in:
hissu-hyvarinen
2024-11-04 21:37:46 +02:00
committed by GitHub
parent 1c45f4c385
commit 5208dc7a20
2 changed files with 12 additions and 6 deletions

View File

@@ -107,11 +107,12 @@ fi
PARALLEL_JOB_COUNT=8
# check if the command contains shard flag, we will run all shards in parallel because the host have 8 GPUs.
if [[ $commands == *"--shard-id="* ]]; then
# assign job count as the number of shards used
commands=${commands//"--num-shards= "/"--num-shards=${PARALLEL_JOB_COUNT} "}
for GPU in $(seq 0 $(($PARALLEL_JOB_COUNT-1))); do
#replace shard arguments
commands=${commands//"--shard-id= "/"--shard-id=${GPU} "}
commands=${commands//"--num-shards= "/"--num-shards=${PARALLEL_JOB_COUNT} "}
echo "Shard ${GPU} commands:$commands"
# assign shard-id for each shard
commands_gpu=${commands//"--shard-id= "/"--shard-id=${GPU} "}
echo "Shard ${GPU} commands:$commands_gpu"
docker run \
--device /dev/kfd --device /dev/dri \
--network host \
@@ -123,7 +124,7 @@ if [[ $commands == *"--shard-id="* ]]; then
-e HF_HOME=${HF_MOUNT} \
--name ${container_name}_${GPU} \
${image_name} \
/bin/bash -c "${commands}" \
/bin/bash -c "${commands_gpu}" \
|& while read -r line; do echo ">>Shard $GPU: $line"; done &
PIDS+=($!)
done