Skip to content

Test K100-AI #72331

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

Open
wants to merge 15 commits into
base: develop
Choose a base branch
from
Open

Test K100-AI #72331

Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
ae916f9
Test K100-AI
tianshuo78520a Apr 17, 2025
4e54b56
test
tianshuo78520a Apr 17, 2025
acd29c6
test NUM_PROC
tianshuo78520a Apr 27, 2025
db6903d
test
tianshuo78520a Apr 28, 2025
5e7484b
test k100-ai
tianshuo78520a Apr 30, 2025
1b6002c
test k100-ai
tianshuo78520a Apr 30, 2025
8cd5b29
fix
tianshuo78520a Apr 30, 2025
5963dbc
test
tianshuo78520a May 6, 2025
7bb8453
fix
tianshuo78520a May 6, 2025
5c0b197
fix
tianshuo78520a May 6, 2025
e2dadb8
Fix
tianshuo78520a May 7, 2025
9c38c9e
test
tianshuo78520a May 7, 2025
1ae8532
test
tianshuo78520a May 8, 2025
36fe6b5
fix
tianshuo78520a May 9, 2025
0d4070f
test
tianshuo78520a May 12, 2025
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
8 changes: 5 additions & 3 deletions paddle/scripts/paddle_build.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1556,7 +1556,8 @@ function card_test() {
# 2 card for P800 ci
CUDA_DEVICE_COUNT=2
elif [[ "${WITH_ROCM}" == "ON" ]]; then
CUDA_DEVICE_COUNT=$(rocm-smi -i | grep DCU | wc -l)
CUDA_DEVICE_COUNT=`echo $HIP_VISIBLE_DEVICES | tr ',' '\n' | wc -l`
IFS=',' read -ra DEVICE_ARRAY <<< "$HIP_VISIBLE_DEVICES"
elif [[ "${WITH_IPU}" == "ON" ]]; then
CUDA_DEVICE_COUNT=1
else
Expand Down Expand Up @@ -1586,6 +1587,7 @@ function card_test() {
trap 'caught_error' CHLD
tmpfile_rand=`date +%s%N`
NUM_PROC=$[CUDA_DEVICE_COUNT/$cardnumber]
export parallel_job=2
echo "****************************************************************"
echo "***These unittests run $parallel_job job each time with $cardnumber GPU***"
echo "****************************************************************"
Expand Down Expand Up @@ -1617,7 +1619,7 @@ function card_test() {
(ctest -I $i,,$NUM_PROC -R "($testcases)" -E "($disable_ut_quickly)" ${run_label_mode} -V --timeout 120 -j $parallel_job | tee $tmpfile; test ${PIPESTATUS[0]} -eq 0) &
else
if [[ "$WITH_ROCM" == "ON" ]]; then
(env HIP_VISIBLE_DEVICES=$cuda_list ctest -I $i,,$NUM_PROC -R "($testcases)" -E "($disable_ut_quickly)" ${run_label_mode} --timeout 120 -V -j $parallel_job | tee $tmpfile; test ${PIPESTATUS[0]} -eq 0) &
(env HIP_VISIBLE_DEVICES=${DEVICE_ARRAY[$i]} ctest -I $i,,$NUM_PROC -R "($testcases)" -E "($disable_ut_quickly)" ${run_label_mode} --timeout 120 -V -j $parallel_job | tee $tmpfile; test ${PIPESTATUS[0]} -eq 0) &
elif [[ "$WITH_XPU" == "ON" ]]; then
(env XPU_VISIBLE_DEVICES=$cuda_list_str ctest -I $i,,$NUM_PROC -R "($testcases)" -E "($disable_ut_quickly)" ${run_label_mode} --timeout 120 -V -j $parallel_job | tee $tmpfile; test ${PIPESTATUS[0]} -eq 0) &
else
Expand All @@ -1629,7 +1631,7 @@ function card_test() {
(ctest -I $i,,$NUM_PROC -R "($testcases)" -E "($disable_ut_quickly)" ${run_label_mode} --timeout 120 --output-on-failure -j $parallel_job | tee $tmpfile; test ${PIPESTATUS[0]} -eq 0) &
else
if [[ "$WITH_ROCM" == "ON" ]]; then
(env HIP_VISIBLE_DEVICES=$cuda_list ctest -I $i,,$NUM_PROC -R "($testcases)" -E "($disable_ut_quickly)" ${run_label_mode} --timeout 120 --output-on-failure -j $parallel_job | tee $tmpfile; test ${PIPESTATUS[0]} -eq 0) &
(env HIP_VISIBLE_DEVICES=${DEVICE_ARRAY[$i]} ctest -I $i,,$NUM_PROC -R "($testcases)" -E "($disable_ut_quickly)" ${run_label_mode} --timeout 120 --output-on-failure -j $parallel_job | tee $tmpfile; test ${PIPESTATUS[0]} -eq 0) &
elif [[ "$WITH_XPU" == "ON" ]]; then
(env XPU_VISIBLE_DEVICES=$cuda_list_str ctest -I $i,,$NUM_PROC -R "($testcases)" -E "($disable_ut_quickly)" ${run_label_mode} --timeout 120 --output-on-failure -j $parallel_job | tee $tmpfile; test ${PIPESTATUS[0]} -eq 0) &
else
Expand Down
Loading