Author: Shangwu Yao Date: 2022-07-22T20:30:15Z New Revision: 31d8dbd1e5b4ee0fd04bfeb3a64d8f9f33260905
URL: https://github.com/llvm/llvm-project/commit/31d8dbd1e5b4ee0fd04bfeb3a64d8f9f33260905 DIFF: https://github.com/llvm/llvm-project/commit/31d8dbd1e5b4ee0fd04bfeb3a64d8f9f33260905.diff LOG: [CUDA/SPIR-V] Force passing aggregate type byval This patch forces copying aggregate type in kernel arguments by value when compiling CUDA targeting SPIR-V. The original behavior is not passing by value when there is any of destructor, copy constructor and move constructor defined by user. This patch makes the behavior of SPIR-V generated from CUDA follow the CUDA spec (https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#global-function-argument-processing), and matches the NVPTX implementation ( https://github.com/llvm/llvm-project/blob/41958f76d8a2c47484fa176cba1de565cfe84de7/clang/lib/CodeGen/TargetInfo.cpp#L7241). Differential Revision: https://reviews.llvm.org/D130387 Added: clang/test/CodeGenCUDASPIRV/copy-aggregate-byval.cu Modified: clang/lib/CodeGen/TargetInfo.cpp Removed: ################################################################################ diff --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp index e8ee5533104ca..fc0952e68a667 100644 --- a/clang/lib/CodeGen/TargetInfo.cpp +++ b/clang/lib/CodeGen/TargetInfo.cpp @@ -10449,6 +10449,15 @@ ABIArgInfo SPIRVABIInfo::classifyKernelArgumentType(QualType Ty) const { LTy = llvm::PointerType::getWithSamePointeeType(PtrTy, GlobalAS); return ABIArgInfo::getDirect(LTy, 0, nullptr, false); } + + // Force copying aggregate type in kernel arguments by value when + // compiling CUDA targeting SPIR-V. This is required for the object + // copied to be valid on the device. + // This behavior follows the CUDA spec + // https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#global-function-argument-processing, + // and matches the NVPTX implementation. + if (isAggregateTypeForABI(Ty)) + return getNaturalAlignIndirect(Ty, /* byval */ true); } return classifyArgumentType(Ty); } diff --git a/clang/test/CodeGenCUDASPIRV/copy-aggregate-byval.cu b/clang/test/CodeGenCUDASPIRV/copy-aggregate-byval.cu new file mode 100644 index 0000000000000..bceca4d4ee5d6 --- /dev/null +++ b/clang/test/CodeGenCUDASPIRV/copy-aggregate-byval.cu @@ -0,0 +1,25 @@ +// Tests CUDA kernel arguments get copied by value when targeting SPIR-V, even with +// destructor, copy constructor or move constructor defined by user. + +// RUN: %clang -Xclang -no-opaque-pointers -emit-llvm --cuda-device-only --offload=spirv32 \ +// RUN: -nocudalib -nocudainc %s -o %t.bc -c 2>&1 +// RUN: llvm-dis %t.bc -o %t.ll +// RUN: FileCheck %s --input-file=%t.ll + +// RUN: %clang -Xclang -no-opaque-pointers -emit-llvm --cuda-device-only --offload=spirv64 \ +// RUN: -nocudalib -nocudainc %s -o %t.bc -c 2>&1 +// RUN: llvm-dis %t.bc -o %t.ll +// RUN: FileCheck %s --input-file=%t.ll + +class GpuData { + public: + __attribute__((host)) __attribute__((device)) GpuData(int* src) {} + __attribute__((host)) __attribute__((device)) ~GpuData() {} + __attribute__((host)) __attribute__((device)) GpuData(const GpuData& other) {} + __attribute__((host)) __attribute__((device)) GpuData(GpuData&& other) {} +}; + +// CHECK: define +// CHECK-SAME: spir_kernel void @_Z6kernel7GpuData(%class.GpuData* noundef byval(%class.GpuData) align + +__attribute__((global)) void kernel(GpuData output) {} _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
