[PATCH] D45223: [CUDA] Set LLVM calling convention for CUDA kernel

[Yaxun Liu via Phabricator via cfe-commits]

yaxunl updated this revision to Diff 143001.
yaxunl retitled this revision from "[CUDA] Fix overloading resolution failure due to kernel calling convention" to "[CUDA] Set LLVM calling convention for CUDA kernel".
yaxunl edited the summary of this revision.
yaxunl added a comment.

Use CodeGen approach.


https://reviews.llvm.org/D45223

Files:
  lib/CodeGen/CodeGenModule.cpp
  lib/CodeGen/TargetInfo.cpp
  lib/CodeGen/TargetInfo.h
  test/CodeGenCUDA/kernel-amdgcn.cu


Index: test/CodeGenCUDA/kernel-amdgcn.cu
===================================================================
--- /dev/null
+++ test/CodeGenCUDA/kernel-amdgcn.cu
@@ -0,0 +1,41 @@
+// RUN: %clang_cc1 -triple amdgcn -fcuda-is-device -emit-llvm %s -o - | FileCheck %s
+#include "Inputs/cuda.h"
+
+// CHECK: define amdgpu_kernel void @_ZN1A6kernelEv
+class A {
+public:
+  static __global__ void kernel(){}
+};
+
+// CHECK: define void @_Z10non_kernelv
+__device__ void non_kernel(){}
+
+// CHECK: define amdgpu_kernel void @_Z6kerneli
+__global__ void kernel(int x) {
+  non_kernel();
+}
+
+// CHECK: define amdgpu_kernel void @_Z11EmptyKernelIvEvv
+template <typename T>
+__global__ void EmptyKernel(void) {}
+
+struct Dummy {
+  /// Type definition of the EmptyKernel kernel entry point
+  typedef void (*EmptyKernelPtr)();
+  EmptyKernelPtr Empty() { return EmptyKernel<void>; } 
+};
+
+// CHECK: define amdgpu_kernel void @_Z15template_kernelI1AEvT_
+template<class T>
+__global__ void template_kernel(T x) {}
+
+void launch(void *f);
+
+int main() {
+  Dummy D;
+  launch((void*)A::kernel);
+  launch((void*)kernel);
+  launch((void*)template_kernel<A>);
+  launch((void*)D.Empty());
+  return 0;
+}
Index: lib/CodeGen/TargetInfo.h
===================================================================
--- lib/CodeGen/TargetInfo.h
+++ lib/CodeGen/TargetInfo.h
@@ -301,6 +301,8 @@
   /// mangled name of functions declared within an extern "C" region and marked
   /// as 'used', and having internal linkage.
   virtual bool shouldEmitStaticExternCAliases() const { return true; }
+
+  virtual void setCUDAKernelCallingConvention(llvm::Function *F) const {}
 };
 
 } // namespace CodeGen
Index: lib/CodeGen/TargetInfo.cpp
===================================================================
--- lib/CodeGen/TargetInfo.cpp
+++ lib/CodeGen/TargetInfo.cpp
@@ -7652,6 +7652,7 @@
                             llvm::Function *BlockInvokeFunc,
                             llvm::Value *BlockLiteral) const override;
   bool shouldEmitStaticExternCAliases() const override;
+  void setCUDAKernelCallingConvention(llvm::Function *F) const override;
 };
 }
 
@@ -7787,6 +7788,11 @@
   return false;
 }
 
+void AMDGPUTargetCodeGenInfo::setCUDAKernelCallingConvention(
+    llvm::Function *F) const {
+  F->setCallingConv(llvm::CallingConv::AMDGPU_KERNEL);
+}
+
 //===----------------------------------------------------------------------===//
 // SPARC v8 ABI Implementation.
 // Based on the SPARC Compliance Definition version 2.4.1.
Index: lib/CodeGen/CodeGenModule.cpp
===================================================================
--- lib/CodeGen/CodeGenModule.cpp
+++ lib/CodeGen/CodeGenModule.cpp
@@ -3608,6 +3608,9 @@
 
   MaybeHandleStaticInExternC(D, Fn);
 
+  if (D->hasAttr<CUDAGlobalAttr>())
+    getTargetCodeGenInfo().setCUDAKernelCallingConvention(Fn);
+
   maybeSetTrivialComdat(*D, *Fn);
 
   CodeGenFunction(*this).GenerateCode(D, Fn, FI);


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D45223.143001.patch
Type: text/x-patch
Size: 2950 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20180418/e197ffa6/attachment.bin>