================
@@ -351,12 +353,24 @@ Address
CGNVCUDARuntime::prepareKernelArgsLLVMOffload(CodeGenFunction &CGF,
"kernel_launch_params");
auto KernelArgsSize = CGM.getDataLayout().getTypeAllocSize(KernelArgsTy);
+
+ // Avoid accounting the tail padding for CUDA.
+ auto KernelArgsSizeNoTailPadding = llvm::TypeSize::getZero();
+ if (auto N = KernelArgsTy->getNumElements()) {
+ auto *SL = CGM.getDataLayout().getStructLayout(KernelArgsTy);
+ KernelArgsSizeNoTailPadding = SL->getElementOffset(N - 1);
+ KernelArgsSizeNoTailPadding += CGM.getDataLayout().getTypeAllocSize(
+ KernelArgsTy->getElementType(N - 1));
----------------
kevinsala wrote:
If there is a cleaner way of getting this information, please let me know.
https://github.com/llvm/llvm-project/pull/156229
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
