[PATCH] D130387: [CUDA/SPIR-V] Force passing aggregate type byval

[Shangwu Yao via Phabricator via cfe-commits]

shangwuyao created this revision.
shangwuyao added reviewers: jlebar, mkuper, tra, yaxunl.
Herald added subscribers: mattd, ThomasRaoux.
Herald added a project: All.
shangwuyao requested review of this revision.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

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).


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D130387

Files:
  clang/lib/CodeGen/TargetInfo.cpp
  clang/test/CodeGenCUDASPIRV/copy-aggregate-byval.cu


Index: clang/test/CodeGenCUDASPIRV/copy-aggregate-byval.cu
===================================================================
--- /dev/null
+++ 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) {}
Index: clang/lib/CodeGen/TargetInfo.cpp
===================================================================
--- clang/lib/CodeGen/TargetInfo.cpp
+++ clang/lib/CodeGen/TargetInfo.cpp
@@ -10446,6 +10446,10 @@
       LTy = llvm::PointerType::getWithSamePointeeType(PtrTy, GlobalAS);
       return ABIArgInfo::getDirect(LTy, 0, nullptr, false);
     }
+
+    if (isAggregateTypeForABI(Ty)) {
+      return getNaturalAlignIndirect(Ty, /* byval */ true);
+    }
   }
   return classifyArgumentType(Ty);
 }



Index: clang/test/CodeGenCUDASPIRV/copy-aggregate-byval.cu
===================================================================
--- /dev/null
+++ 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) {}
Index: clang/lib/CodeGen/TargetInfo.cpp
===================================================================
--- clang/lib/CodeGen/TargetInfo.cpp
+++ clang/lib/CodeGen/TargetInfo.cpp
@@ -10446,6 +10446,10 @@
       LTy = llvm::PointerType::getWithSamePointeeType(PtrTy, GlobalAS);
       return ABIArgInfo::getDirect(LTy, 0, nullptr, false);
     }
+
+    if (isAggregateTypeForABI(Ty)) {
+      return getNaturalAlignIndirect(Ty, /* byval */ true);
+    }
   }
   return classifyArgumentType(Ty);
 }

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits