1 files changed, 26 insertions, 20 deletions

diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index b3d02f1f51c..b1feefe9f0d 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -2493,6 +2493,8 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
 
     llvm::Type *QueueTy = ConvertType(getContext().OCLQueueTy);
     llvm::Type *RangeTy = ConvertType(getContext().OCLNDRangeTy);
+    llvm::Type *GenericVoidPtrTy = Builder.getInt8PtrTy(
+        getContext().getTargetAddressSpace(LangAS::opencl_generic));
 
     llvm::Value *Queue = EmitScalarExpr(E->getArg(0));
     llvm::Value *Flags = EmitScalarExpr(E->getArg(1));
@@ -2502,12 +2504,12 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
       // The most basic form of the call with parameters:
       // queue_t, kernel_enqueue_flags_t, ndrange_t, block(void)
       Name = "__enqueue_kernel_basic";
-      llvm::Type *ArgTys[] = {QueueTy, Int32Ty, RangeTy, Int8PtrTy};
+      llvm::Type *ArgTys[] = {QueueTy, Int32Ty, RangeTy, GenericVoidPtrTy};
       llvm::FunctionType *FTy = llvm::FunctionType::get(
           Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys, 4), false);
 
-      llvm::Value *Block =
-          Builder.CreateBitCast(EmitScalarExpr(E->getArg(3)), Int8PtrTy);
+      llvm::Value *Block = Builder.CreatePointerCast(
+          EmitScalarExpr(E->getArg(3)), GenericVoidPtrTy);
 
       return RValue::get(Builder.CreateCall(
           CGM.CreateRuntimeFunction(FTy, Name), {Queue, Flags, Range, Block}));
@@ -2518,14 +2520,14 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
     if (E->getArg(3)->getType()->isBlockPointerType()) {
       // No events passed, but has variadic arguments.
       Name = "__enqueue_kernel_vaargs";
-      llvm::Value *Block =
-          Builder.CreateBitCast(EmitScalarExpr(E->getArg(3)), Int8PtrTy);
+      llvm::Value *Block = Builder.CreatePointerCast(
+          EmitScalarExpr(E->getArg(3)), GenericVoidPtrTy);
       // Create a vector of the arguments, as well as a constant value to
       // express to the runtime the number of variadic arguments.
       std::vector<llvm::Value *> Args = {Queue, Flags, Range, Block,
                                          ConstantInt::get(IntTy, NumArgs - 4)};
-      std::vector<llvm::Type *> ArgTys = {QueueTy, IntTy, RangeTy, Int8PtrTy,
-                                          IntTy};
+      std::vector<llvm::Type *> ArgTys = {QueueTy, IntTy, RangeTy,
+                                          GenericVoidPtrTy, IntTy};
 
       // Each of the following arguments specifies the size of the corresponding
       // argument passed to the enqueued block.
@@ -2555,12 +2557,12 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
       // Convert to generic address space.
       EventList = Builder.CreatePointerCast(EventList, EventPtrTy);
       ClkEvent = Builder.CreatePointerCast(ClkEvent, EventPtrTy);
-      llvm::Value *Block =
-          Builder.CreateBitCast(EmitScalarExpr(E->getArg(6)), Int8PtrTy);
+      llvm::Value *Block = Builder.CreatePointerCast(
+          EmitScalarExpr(E->getArg(6)), GenericVoidPtrTy);
 
-      std::vector<llvm::Type *> ArgTys = {QueueTy,  Int32Ty,    RangeTy,
-                                          Int32Ty,  EventPtrTy, EventPtrTy,
-                                          Int8PtrTy};
+      std::vector<llvm::Type *> ArgTys = {
+          QueueTy,    Int32Ty,    RangeTy,         Int32Ty,
+          EventPtrTy, EventPtrTy, GenericVoidPtrTy};
 
       std::vector<llvm::Value *> Args = {Queue,     Flags,    Range, NumEvents,
                                          EventList, ClkEvent, Block};
@@ -2596,20 +2598,24 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
   // OpenCL v2.0 s6.13.17.6 - Kernel query functions need bitcast of block
   // parameter.
   case Builtin::BIget_kernel_work_group_size: {
+    llvm::Type *GenericVoidPtrTy = Builder.getInt8PtrTy(
+        getContext().getTargetAddressSpace(LangAS::opencl_generic));
     Value *Arg = EmitScalarExpr(E->getArg(0));
-    Arg = Builder.CreateBitCast(Arg, Int8PtrTy);
-    return RValue::get(
-        Builder.CreateCall(CGM.CreateRuntimeFunction(
-                               llvm::FunctionType::get(IntTy, Int8PtrTy, false),
-                               "__get_kernel_work_group_size_impl"),
-                           Arg));
+    Arg = Builder.CreatePointerCast(Arg, GenericVoidPtrTy);
+    return RValue::get(Builder.CreateCall(
+        CGM.CreateRuntimeFunction(
+            llvm::FunctionType::get(IntTy, GenericVoidPtrTy, false),
+            "__get_kernel_work_group_size_impl"),
+        Arg));
   }
   case Builtin::BIget_kernel_preferred_work_group_size_multiple: {
+    llvm::Type *GenericVoidPtrTy = Builder.getInt8PtrTy(
+        getContext().getTargetAddressSpace(LangAS::opencl_generic));
     Value *Arg = EmitScalarExpr(E->getArg(0));
-    Arg = Builder.CreateBitCast(Arg, Int8PtrTy);
+    Arg = Builder.CreatePointerCast(Arg, GenericVoidPtrTy);
     return RValue::get(Builder.CreateCall(
         CGM.CreateRuntimeFunction(
-            llvm::FunctionType::get(IntTy, Int8PtrTy, false),
+            llvm::FunctionType::get(IntTy, GenericVoidPtrTy, false),
             "__get_kernel_preferred_work_group_multiple_impl"),
         Arg));
   }