================
@@ -424,6 +424,34 @@ void
CGNVCUDARuntime::emitDeviceStubBodyNew(CodeGenFunction &CGF,
CGM.CreateRuntimeFunction(FTy, LaunchKernelName);
CGF.EmitCall(FI, CGCallee::forDirect(cudaLaunchKernelFn), ReturnValueSlot(),
LaunchKernelArgs);
+
+ // To prevent CUDA device stub functions from being merged by ICF in MSVC
+ // environment, create an unique global variable for each kernel and write to
+ // the variable in the device stub.
+ if (CGM.getContext().getTargetInfo().getCXXABI().isMicrosoft() &&
+ !CGF.getLangOpts().HIP) {
+ llvm::Function *KernelFunction = llvm::cast<llvm::Function>(Kernel);
+ if (KernelFunction->hasComdat()) {
----------------
rnk wrote:
ICF may apply to all functions under
[`/Gy`](https://learn.microsoft.com/en-us/cpp/build/reference/gy-enable-function-level-linking?view=msvc-170),
and those are not reflected in the IR, so I would just do this for all kernels.
https://github.com/llvm/llvm-project/pull/90155
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
