Skip to content

[HIP] fix host-used external kernel #83870

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

Merged
merged 1 commit into from
Mar 8, 2024
Merged

[HIP] fix host-used external kernel #83870

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
5 changes: 4 additions & 1 deletion clang/lib/Sema/SemaCUDA.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -895,7 +895,10 @@ bool Sema::CheckCUDACall(SourceLocation Loc, FunctionDecl *Callee) {
if (DiagKind == SemaDiagnosticBuilder::K_Nop) {
// For -fgpu-rdc, keep track of external kernels used by host functions.
if (LangOpts.CUDAIsDevice && LangOpts.GPURelocatableDeviceCode &&
Callee->hasAttr<CUDAGlobalAttr>() && !Callee->isDefined())
Callee->hasAttr<CUDAGlobalAttr>() && !Callee->isDefined() &&
(!Caller || (!Caller->getDescribedFunctionTemplate() &&
getASTContext().GetGVALinkageForFunction(Caller) ==
GVA_StrongExternal)))
getASTContext().CUDAExternalDeviceDeclODRUsedByHost.insert(Callee);
return true;
}
Expand Down
5 changes: 4 additions & 1 deletion clang/lib/Sema/SemaExpr.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19218,7 +19218,10 @@ MarkVarDeclODRUsed(ValueDecl *V, SourceLocation Loc, Sema &SemaRef,
// externalize the static device side variable ODR-used by host code.
if (!Var->hasExternalStorage())
SemaRef.getASTContext().CUDADeviceVarODRUsedByHost.insert(Var);
else if (SemaRef.LangOpts.GPURelocatableDeviceCode)
else if (SemaRef.LangOpts.GPURelocatableDeviceCode &&
(!FD || (!FD->getDescribedFunctionTemplate() &&
SemaRef.getASTContext().GetGVALinkageForFunction(FD) ==
GVA_StrongExternal)))
SemaRef.getASTContext().CUDAExternalDeviceDeclODRUsedByHost.insert(Var);
}
}
Expand Down
13 changes: 13 additions & 0 deletions clang/test/CodeGenCUDA/host-used-extern.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@

// NEG-NOT: @__clang_gpu_used_external = {{.*}} @_Z7kernel2v
// NEG-NOT: @__clang_gpu_used_external = {{.*}} @_Z7kernel3v
// NEG-NOT: @__clang_gpu_used_external = {{.*}} @_Z7kernel5v
// NEG-NOT: @__clang_gpu_used_external = {{.*}} @var2
// NEG-NOT: @__clang_gpu_used_external = {{.*}} @var3
// NEG-NOT: @__clang_gpu_used_external = {{.*}} @ext_shvar
Expand All @@ -44,6 +45,10 @@ __global__ void kernel3();
// kernel4 is marked as used even though it is not called.
__global__ void kernel4();

// kernel5 is not marked as used since it is called by host function
// with weak_odr linkage, which may be dropped by linker.
__global__ void kernel5();

extern __device__ int var1;

__device__ int var2;
Expand All @@ -67,3 +72,11 @@ __global__ void test_lambda_using_extern_shared() {
};
lambda();
}

template<class T>
void template_caller() {
kernel5<<<1, 1>>>();
var1 = 1;
}

template void template_caller<int>();