[CUDA][HIP] Check calling convention based on function target

MSVC header files using vectorcall to differentiate overloaded functions, which
causes failure for AMDGPU target. This is because clang does not check function
calling convention based on function target.

This patch checks calling convention using the proper target info.

Differential Revision: https://reviews.llvm.org/D57716

llvm-svn: 354929

2 files changed, 33 insertions, 1 deletions

diff --git a/clang/lib/Sema/SemaDeclAttr.cpp b/clang/lib/Sema/SemaDeclAttr.cpp
index a0b4c53b1a7..157c18a9e49 100644
--- a/clang/lib/Sema/SemaDeclAttr.cpp
+++ b/clang/lib/Sema/SemaDeclAttr.cpp
@@ -4615,8 +4615,36 @@ bool Sema::CheckCallingConvAttr(const ParsedAttr &Attrs, CallingConv &CC,
   default: llvm_unreachable("unexpected attribute kind");
   }
 
+  TargetInfo::CallingConvCheckResult A = TargetInfo::CCCR_OK;
   const TargetInfo &TI = Context.getTargetInfo();
-  TargetInfo::CallingConvCheckResult A = TI.checkCallingConvention(CC);
+  auto *Aux = Context.getAuxTargetInfo();
+  if (LangOpts.CUDA) {
+    auto CudaTarget = IdentifyCUDATarget(FD);
+    bool CheckHost = false, CheckDevice = false;
+    switch (CudaTarget) {
+    case CFT_HostDevice:
+      CheckHost = true;
+      CheckDevice = true;
+      break;
+    case CFT_Host:
+      CheckHost = true;
+      break;
+    case CFT_Device:
+    case CFT_Global:
+      CheckDevice = true;
+      break;
+    case CFT_InvalidTarget:
+      llvm_unreachable("unexpected cuda target");
+    }
+    auto *HostTI = LangOpts.CUDAIsDevice ? Aux : &TI;
+    auto *DeviceTI = LangOpts.CUDAIsDevice ? &TI : Aux;
+    if (CheckHost && HostTI)
+      A = HostTI->checkCallingConvention(CC);
+    if (A == TargetInfo::CCCR_OK && CheckDevice && DeviceTI)
+      A = DeviceTI->checkCallingConvention(CC);
+  } else {
+    A = TI.checkCallingConvention(CC);
+  }
   if (A != TargetInfo::CCCR_OK) {
     if (A == TargetInfo::CCCR_Warning)
       Diag(Attrs.getLoc(), diag::warn_cconv_ignored) << Attrs;
diff --git a/clang/test/SemaCUDA/amdgpu-windows-vectorcall.cu b/clang/test/SemaCUDA/amdgpu-windows-vectorcall.cu
new file mode 100644
index 00000000000..7636572f698
--- /dev/null
+++ b/clang/test/SemaCUDA/amdgpu-windows-vectorcall.cu
@@ -0,0 +1,4 @@
+// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -aux-triple x86_64-pc-windows-msvc -fms-compatibility -fcuda-is-device -fsyntax-only -verify %s
+
+__cdecl void hostf1();
+__vectorcall void (*hostf2)() = hostf1; // expected-error {{cannot initialize a variable of type 'void ((*))() __attribute__((vectorcall))' with an lvalue of type 'void () __attribute__((cdecl))'}}