Set calling convention for CUDA kernel

This patch sets target specific calling convention for CUDA kernels in IR.

Patch by Greg Rodgers.
Revised and lit test added by Yaxun Liu.

Differential Revision: https://reviews.llvm.org/D44747

llvm-svn: 328795

3 files changed, 23 insertions, 1 deletions

diff --git a/clang/lib/Sema/SemaExpr.cpp b/clang/lib/Sema/SemaExpr.cpp
index c0533f7cc7d..d87c21c0b17 100644
--- a/clang/lib/Sema/SemaExpr.cpp
+++ b/clang/lib/Sema/SemaExpr.cpp
@@ -25,6 +25,7 @@
 #include "clang/AST/ExprObjC.h"
 #include "clang/AST/ExprOpenMP.h"
 #include "clang/AST/RecursiveASTVisitor.h"
+#include "clang/AST/Type.h"
 #include "clang/AST/TypeLoc.h"
 #include "clang/Basic/PartialDiagnostic.h"
 #include "clang/Basic/SourceManager.h"
@@ -1657,6 +1658,16 @@ Sema::BuildDeclRefExpr(ValueDecl *D, QualType Ty, ExprValueKind VK,
       isa<VarDecl>(D) &&
       NeedToCaptureVariable(cast<VarDecl>(D), NameInfo.getLoc());
 
+  // Drop CUDA kernel calling convention since it is invisible to the user
+  // in DRE.
+  if (const auto *FT = Ty->getAs<FunctionType>()) {
+    if (FT->getCallConv() == CC_CUDAKernel) {
+      FT = Context.adjustFunctionType(FT,
+                                      FT->getExtInfo().withCallingConv(CC_C));
+      Ty = QualType(FT, Ty.getQualifiers().getAsOpaqueValue());
+    }
+  }
+
   DeclRefExpr *E;
   if (isa<VarTemplateSpecializationDecl>(D)) {
     VarTemplateSpecializationDecl *VarSpec =
diff --git a/clang/lib/Sema/SemaOverload.cpp b/clang/lib/Sema/SemaOverload.cpp
index dea1c2efe9d..e917bcc1cc2 100644
--- a/clang/lib/Sema/SemaOverload.cpp
+++ b/clang/lib/Sema/SemaOverload.cpp
@@ -1481,7 +1481,6 @@ bool Sema::IsFunctionConversion(QualType FromType, QualType ToType,
                  .getTypePtr());
       Changed = true;
     }
-
     // Convert FromFPT's ExtParameterInfo if necessary. The conversion is valid
     // only if the ExtParameterInfo lists of the two function prototypes can be
     // merged and the merged list is identical to ToFPT's ExtParameterInfo list.
diff --git a/clang/lib/Sema/SemaType.cpp b/clang/lib/Sema/SemaType.cpp
index 00bb21ff307..7bcc5b66fb7 100644
--- a/clang/lib/Sema/SemaType.cpp
+++ b/clang/lib/Sema/SemaType.cpp
@@ -3316,6 +3316,18 @@ getCCForDeclaratorChunk(Sema &S, Declarator &D,
   CallingConv CC = S.Context.getDefaultCallingConvention(FTI.isVariadic,
                                                          IsCXXInstanceMethod);
 
+  // Attribute AT_CUDAGlobal affects the calling convention for AMDGPU targets.
+  // This is the simplest place to infer calling convention for CUDA kernels.
+  if (S.getLangOpts().CUDA && S.getLangOpts().CUDAIsDevice) {
+    for (const AttributeList *Attr = D.getDeclSpec().getAttributes().getList();
+         Attr; Attr = Attr->getNext()) {
+      if (Attr->getKind() == AttributeList::AT_CUDAGlobal) {
+        CC = CC_CUDAKernel;
+        break;
+      }
+    }
+  }
+
   // Attribute AT_OpenCLKernel affects the calling convention for SPIR
   // and AMDGPU targets, hence it cannot be treated as a calling
   // convention attribute. This is the simplest place to infer