[clang][Sema][SYCL] Fix MSVC STL usage on AMDGPU (#135979)

clang/lib/Sema/SemaDeclAttr.cpp

@@ -5544,12 +5544,12 @@ bool Sema::CheckCallingConvAttr(const ParsedAttr &Attrs, CallingConv &CC,
   }
 
   TargetInfo::CallingConvCheckResult A = TargetInfo::CCCR_OK;
+  auto *Aux = Context.getAuxTargetInfo();
   // CUDA functions may have host and/or device attributes which indicate
   // their targeted execution environment, therefore the calling convention
   // of functions in CUDA should be checked against the target deduced based
   // on their host/device attributes.
   if (LangOpts.CUDA) {
-    auto *Aux = Context.getAuxTargetInfo();
     assert(FD || CFT != CUDAFunctionTarget::InvalidTarget);
     auto CudaTarget = FD ? CUDA().IdentifyTarget(FD) : CFT;
     bool CheckHost = false, CheckDevice = false;
@@ -5574,6 +5574,15 @@ bool Sema::CheckCallingConvAttr(const ParsedAttr &Attrs, CallingConv &CC,
       A = HostTI->checkCallingConvention(CC);
     if (A == TargetInfo::CCCR_OK && CheckDevice && DeviceTI)
       A = DeviceTI->checkCallingConvention(CC);
+  } else if (LangOpts.SYCLIsDevice && TI.getTriple().isAMDGPU() &&
+             CC == CC_X86VectorCall) {
+    // Assuming SYCL Device AMDGPU CC_X86VectorCall functions are always to be
+    // emitted on the host. The MSVC STL has CC-based specializations so we
+    // cannot change the CC to be the default as that will cause a clash with
+    // another specialization.
+    A = TI.checkCallingConvention(CC);
+    if (Aux && A != TargetInfo::CCCR_OK)
+      A = Aux->checkCallingConvention(CC);
   } else {
     A = TI.checkCallingConvention(CC);
   }

clang/test/SemaSYCL/Inputs/vectorcall.hpp

@@ -0,0 +1,18 @@
+
+template <typename F> struct A{};
+
+template <typename Ret, typename C, typename... Args> struct A<Ret (             C::*)(Args...) noexcept> { static constexpr int value = 0; };
+template <typename Ret, typename C, typename... Args> struct A<Ret (__vectorcall C::*)(Args...) noexcept> { static constexpr int value = 1; };
+
+template <typename F> constexpr int A_v = A<F>::value;
+
+struct B
+{
+    void f() noexcept {}
+    void __vectorcall g() noexcept {}
+};
+
+int main()
+{
+    return A_v<decltype(&B::f)> + A_v<decltype(&B::g)>;
+}

clang/test/SemaSYCL/sycl-cconv-win.cpp

@@ -0,0 +1,5 @@
+// RUN: %clang_cc1 -isystem %S/Inputs/ -fsycl-is-device -triple amdgcn-amd-hsa -aux-triple x86_64-pc-windows-msvc -fsyntax-only -verify %s
+
+// expected-no-diagnostics
+
+#include <vectorcall.hpp>