shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[Offload] Return error rather than dropping it (#148609)

Browse Source
This commit is contained in:
Ross Brunton 2025-07-14 14:05:58 +01:00 committed by GitHub
parent eb4de577da
commit a71187e976
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
offload/plugins-nextgen/cuda/src/rtl.cpp
View File

@ -1311,7 +1311,7 @@ Error CUDAKernelTy::launchImpl(GenericDeviceTy &GenericDevice,
if (MaxDynCGroupMem >= MaxDynCGroupMemLimit) {
CUresult AttrResult = cuFuncSetAttribute(
Func, CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES, MaxDynCGroupMem);
Plugin::check(
return Plugin::check(
AttrResult,
"Error in cuLaunchKernel while setting the memory limits: %s");
MaxDynCGroupMemLimit = MaxDynCGroupMem;