[libc] Honour LIBC_GPU_TEST_JOBS in lit test runs (#193797)
Under CTest, LIBC_GPU_TEST_JOBS controlled a ninja job pool that limited concurrent GPU test processes. The AMD GPU buildbot sets this to 4 to avoid overloading the GPU driver. When running tests via lit, this constraint was lost because lit uses its own -j flag (defaulting to nproc, or set to 64 on the AMD bot via LLVM_LIT_ARGS). All GPU loader processes launched simultaneously, leading to hangs from GPU resource exhaustion. Propagated LIBC_GPU_TEST_JOBS into the lit site config as a parallelism group so lit throttles GPU test concurrency independently of the global -j setting.
This commit is contained in:
@@ -29,6 +29,7 @@ if(LIBC_GPU_TEST_JOBS)
|
||||
set_property(GLOBAL PROPERTY JOB_POOLS LIBC_GPU_TEST_POOL=${LIBC_GPU_TEST_JOBS})
|
||||
set(LIBC_HERMETIC_TEST_JOB_POOL JOB_POOL LIBC_GPU_TEST_POOL)
|
||||
else()
|
||||
set(LIBC_GPU_TEST_JOBS 1)
|
||||
set_property(GLOBAL PROPERTY JOB_POOLS LIBC_GPU_TEST_POOL=1)
|
||||
set(LIBC_HERMETIC_TEST_JOB_POOL JOB_POOL LIBC_GPU_TEST_POOL)
|
||||
endif()
|
||||
|
||||
@@ -40,3 +40,8 @@ if hasattr(config, "llvm_tools_dir") and config.llvm_tools_dir:
|
||||
[config.llvm_tools_dir, config.environment.get("PATH", "")]
|
||||
)
|
||||
|
||||
# Limit concurrent GPU tests to avoid overloading the GPU driver.
|
||||
libc_gpu_test_jobs = "@LIBC_GPU_TEST_JOBS@"
|
||||
if libc_gpu_test_jobs:
|
||||
lit_config.parallelism_groups["libc-gpu"] = int(libc_gpu_test_jobs)
|
||||
config.parallelism_group = "libc-gpu"
|
||||
|
||||
Reference in New Issue
Block a user