[OpenCL] Add missing address spaces in IR generation of Blocks

[Anastasia]

Summary

ObjC IR generation for Blocks currently:
I. Generates local to block variable declaration block literal in case it contains captures.
II. Global variable block literal in case it doesn't have any captures.

The address spaces are missing however if we use this generation for OpenCL.

This patch:

• keeps default private address space for blocks generated as local variables (case I from above);
• adds global address space for global block literals (case II from the above);
• makes the block invoke function and enqueue_kernel prototype with the generic AS block pointer parameter to accommodate both private and global AS cases.
• adds block handling into default AS because it's implemented as a special pointer type (BlockPointer) in the frontend and therefore it is used as a pointer everywhere. This is also needed to accommodate both private and global address space blocks for the two cases described above.
• removes ObjC RT specific symbols (NSConcreteStackBlock and NSConcreteGlobalBlock) in the OpenCL mode.

[Anastasia]

Ping! @yaxunl, Sam do you think you will have time to look into this?

[yaxunl]

lib/CodeGen/CGBlocks.cpp

723

should use CGM.getNullPointer to create a null pointer.

1126

should use CGM.getNullPointer to create a null pointer.

[Anastasia]

Switched to getNullPointer helper.

[Anastasia]

lib/CodeGen/CGBlocks.cpp

723

Btw, does it mean we can no longer use generic llvm::Constant::getNullValue helper for PointerTypes? This feels wrong! Is it possible to extend the helper?

Also I find it a bit counter intuitive to use getNullPointer with the second argument QualType for the case like this where we don't have an actual AST type. Why is it needed? Some documentation might be helpful here. :) Could we extend this helper to use default second argument or an overload with one argument only.

[yaxunl]

lib/CodeGen/CGBlocks.cpp

726

The QualType needs to be the real QualType corresponding to the LLVM type, otherwise it won't work on targets with non-zero null pointer.

1129

same issue as above.

test/CodeGenOpenCL/cl20-device-side-enqueue.cl

3

Can we add a run line for triple amdgcn-amd-amdhsa-opencl to make sure the null pointer is generated correctly?

[yaxunl]

lib/CodeGen/CGBlocks.cpp

723

The LLVM type may not have sufficient information, so in general situation QualType is needed. The comment before getNullPointer declaration explains the meaning of the parameters:

/// Get target specific null pointer.
/// \param T is the LLVM type of the null pointer.
/// \param QT is the clang QualType of the null pointer.
/// \return ConstantPointerNull with the given type \p T.
/// Each target can override it to return its own desired constant value.
virtual llvm::Constant *getNullPointer(const CodeGen::CodeGenModule &CGM,
    llvm::PointerType *T, QualType QT) const;

[Anastasia]

Updated NULL ptr generation and added separate CodeGen test for checking amended Block generation behaviour in OpenCL!

[Anastasia]

test/CodeGenOpenCL/cl20-device-side-enqueue.cl

3

I added a new test (above). This one gets too complicated!

[yaxunl]

LGTM. Thanks!

[Anastasia]

Committed in r 293286

lib/AST/Expr.cpp

case CK_CopyAndAutoreleaseBlockObject:
     goto CheckNoBasePath;
 
   case CK_FunctionToPointerDecay:
     assert(getType()->isPointerType());
     assert(getSubExpr()->getType()->isFunctionType());
     goto CheckNoBasePath;
 
   case CK_AddressSpaceConversion:
-    assert(getType()->isPointerType());
-    assert(getSubExpr()->getType()->isPointerType());
+    assert(getType()->isPointerType() || getType()->isBlockPointerType());
+    assert(getSubExpr()->getType()->isPointerType() ||
+           getSubExpr()->getType()->isBlockPointerType());
     assert(getType()->getPointeeType().getAddressSpace() !=
            getSubExpr()->getType()->getPointeeType().getAddressSpace());
   // These should not have an inheritance path.
   case CK_Dynamic:
   case CK_ToUnion:
   case CK_ArrayToPointerDecay:
   case CK_NullToMemberPointer:
   case CK_NullToPointer:

lib/CodeGen/CGBlocks.cpp

llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo) {
   blockFn = llvm::ConstantExpr::getBitCast(blockFn, VoidPtrTy);
 
   // If there is nothing to capture, we can emit this as a global block.
   if (blockInfo.CanBeGlobal)
     return buildGlobalBlock(CGM, blockInfo, blockFn);
 
   // Otherwise, we have to emit this as a local block.
 
-  llvm::Constant *isa = CGM.getNSConcreteStackBlock();
+  llvm::Constant *isa =
+      (!CGM.getContext().getLangOpts().OpenCL)
+          ? CGM.getNSConcreteStackBlock()
+          : CGM.getNullPointer(cast<llvm::PointerType>(
+                                   CGM.getNSConcreteStackBlock()->getType()),
+                               QualType());
   isa = llvm::ConstantExpr::getBitCast(isa, VoidPtrTy);
 
   // Build the block descriptor.
   llvm::Constant *descriptor = buildBlockDescriptor(CGM, blockInfo);
 
   Address blockAddr = blockInfo.LocalAddress;
   assert(blockAddr.isValid() && "block has no address!");
 
if (!CI.isByRef()) {
       EHScopeStack::stable_iterator cleanup = capture.getCleanup();
       if (cleanup.isValid())
         ActivateCleanupBlock(cleanup, blockInfo.DominatingIP);
     }
   }
 
   // Cast to the converted block-pointer type, which happens (somewhat
   // unfortunately) to be a pointer to function type.
-  llvm::Value *result =
-    Builder.CreateBitCast(blockAddr.getPointer(),
-                          ConvertType(blockInfo.getBlockExpr()->getType()));
+  llvm::Value *result = Builder.CreatePointerCast(
+      blockAddr.getPointer(), ConvertType(blockInfo.getBlockExpr()->getType()));
 
   return result;
 }
 
 
 llvm::Type *CodeGenModule::getBlockDescriptorType() {
   if (BlockDescriptorType)
     return BlockDescriptorType;

 RValue CodeGenFunction::EmitBlockCallExpr(const CallExpr *E, 
                                           ReturnValueSlot ReturnValue) {
   const BlockPointerType *BPT =
     E->getCallee()->getType()->getAs<BlockPointerType>();
 
   llvm::Value *BlockPtr = EmitScalarExpr(E->getCallee());
 
   // Get a pointer to the generic block literal.
+  // For OpenCL we generate generic AS void ptr to be able to reuse the same
+  // block definition for blocks with captures generated as private AS local
+  // variables and without captures generated as global AS program scope
+  // variables.
+  unsigned AddrSpace = 0;
+  if (getLangOpts().OpenCL)
+    AddrSpace = getContext().getTargetAddressSpace(LangAS::opencl_generic);
+
   llvm::Type *BlockLiteralTy =
-    llvm::PointerType::getUnqual(CGM.getGenericBlockLiteralType());
+      llvm::PointerType::get(CGM.getGenericBlockLiteralType(), AddrSpace);
 
   // Bitcast the callee to a block literal.
-  BlockPtr = Builder.CreateBitCast(BlockPtr, BlockLiteralTy, "block.literal");
+  BlockPtr =
+      Builder.CreatePointerCast(BlockPtr, BlockLiteralTy, "block.literal");
 
   // Get the function pointer from the literal.
   llvm::Value *FuncPtr =
     Builder.CreateStructGEP(CGM.getGenericBlockLiteralType(), BlockPtr, 3);
 
-  BlockPtr = Builder.CreateBitCast(BlockPtr, VoidPtrTy);
 
   // Add the block literal.
   CallArgList Args;
-  Args.add(RValue::get(BlockPtr), getContext().VoidPtrTy);
+
+  QualType VoidPtrQualTy = getContext().VoidPtrTy;
+  llvm::Type *GenericVoidPtrTy = VoidPtrTy;
+  if (getLangOpts().OpenCL) {
+    GenericVoidPtrTy = Builder.getInt8PtrTy(
+        getContext().getTargetAddressSpace(LangAS::opencl_generic));
+    VoidPtrQualTy =
+        getContext().getPointerType(getContext().getAddrSpaceQualType(
+            getContext().VoidTy, LangAS::opencl_generic));
+  }
+
+  BlockPtr = Builder.CreatePointerCast(BlockPtr, GenericVoidPtrTy);
+  Args.add(RValue::get(BlockPtr), VoidPtrQualTy);
 
   QualType FnType = BPT->getPointeeType();
 
   // And the rest of the arguments.
   EmitCallArgs(Args, FnType->getAs<FunctionProtoType>(), E->arguments());
 
   // Load the function.
   llvm::Value *Func = Builder.CreateAlignedLoad(FuncPtr, getPointerAlign());
static llvm::Constant *buildGlobalBlock(CodeGenModule &CGM,
   assert(!CGM.getAddrOfGlobalBlockIfEmitted(blockInfo.BlockExpression) &&
          "Refusing to re-emit a global block.");
 
   // Generate the constants for the block literal initializer.
   ConstantInitBuilder builder(CGM);
   auto fields = builder.beginStruct();
 
   // isa
-  fields.add(CGM.getNSConcreteGlobalBlock());
+  fields.add(
+      (!CGM.getContext().getLangOpts().OpenCL)
+          ? CGM.getNSConcreteGlobalBlock()
+          : CGM.getNullPointer(cast<llvm::PointerType>(
+                                   CGM.getNSConcreteGlobalBlock()->getType()),
+                               QualType()));
 
   // __flags
   BlockFlags flags = BLOCK_IS_GLOBAL | BLOCK_HAS_SIGNATURE;
   if (blockInfo.UsesStret) flags |= BLOCK_USE_STRET;
                                       
   fields.addInt(CGM.IntTy, flags.getBitMask());
 
   // Reserved
   fields.addInt(CGM.IntTy, 0);
 
   // Function
   fields.add(blockFn);
 
   // Descriptor
   fields.add(buildBlockDescriptor(CGM, blockInfo));
 
-  llvm::Constant *literal =
-    fields.finishAndCreateGlobal("__block_literal_global",
-                                 blockInfo.BlockAlign,
-                                 /*constant*/ true);
+  unsigned AddrSpace = 0;
+  if (CGM.getContext().getLangOpts().OpenCL)
+    AddrSpace = CGM.getContext().getTargetAddressSpace(LangAS::opencl_global);
+
+  llvm::Constant *literal = fields.finishAndCreateGlobal(
+      "__block_literal_global", blockInfo.BlockAlign,
+      /*constant*/ true, llvm::GlobalVariable::InternalLinkage, AddrSpace);
 
   // Return a constant of the appropriately-casted type.
   llvm::Type *RequiredType =
     CGM.getTypes().ConvertType(blockInfo.getBlockExpr()->getType());
   llvm::Constant *Result =
-      llvm::ConstantExpr::getBitCast(literal, RequiredType);
+      llvm::ConstantExpr::getPointerCast(literal, RequiredType);
   CGM.setAddrOfGlobalBlock(blockInfo.BlockExpression, Result);
   return Result;
 }
 
 void CodeGenFunction::setBlockContextParameter(const ImplicitParamDecl *D,
                                                unsigned argNum,
                                                llvm::Value *arg) {
   assert(BlockInfo && "not emitting prologue of block invocation function?!");
if (CGDebugInfo *DI = getDebugInfo()) {
     }
   }
 
   SourceLocation StartLoc = BlockInfo->getBlockExpr()->getBody()->getLocStart();
   ApplyDebugLocation Scope(*this, StartLoc);
 
   // Instead of messing around with LocalDeclMap, just set the value
   // directly as BlockPointer.
-  BlockPointer = Builder.CreateBitCast(arg,
-                                       BlockInfo->StructureType->getPointerTo(),
-                                       "block");
+  BlockPointer = Builder.CreatePointerCast(
+      arg,
+      BlockInfo->StructureType->getPointerTo(
+          getContext().getLangOpts().OpenCL
+              ? getContext().getTargetAddressSpace(LangAS::opencl_generic)
+              : 0),
 }
 
 Address CodeGenFunction::LoadBlockStruct() {
   assert(BlockInfo && "not in a block invocation function!");
   assert(BlockPointer && "no block pointer set!");
   return Address(BlockPointer, BlockInfo->BlockAlign);
 }
 
CodeGenFunction::GenerateBlockFunction(GlobalDecl GD,
   // Begin building the function declaration.
 
   // Build the argument list.
   FunctionArgList args;
 
   // The first argument is the block pointer.  Just take it as a void*
   // and cast it later.
   QualType selfTy = getContext().VoidPtrTy;
+
+  // For OpenCL passed block pointer can be private AS local variable or
+  // global AS program scope variable (for the case with and without captures).
+  // Generic AS is used therefore to be able to accomodate both private and
+  // generic AS in one implementation.
+  if (getLangOpts().OpenCL)
+    selfTy = getContext().getPointerType(getContext().getAddrSpaceQualType(
+        getContext().VoidTy, LangAS::opencl_generic));
+
   IdentifierInfo *II = &CGM.getContext().Idents.get(".block_descriptor");
 
   ImplicitParamDecl selfDecl(getContext(), const_cast<BlockDecl*>(blockDecl),
                              SourceLocation(), II, selfTy);
   args.push_back(&selfDecl);
 
   // Now add the rest of the parameters.
   args.append(blockDecl->param_begin(), blockDecl->param_end());

lib/CodeGen/CGBuiltin.cpp

   // OpenCL v2.0, s6.13.17 - Enqueue kernel function.
   // It contains four different overload formats specified in Table 6.13.17.1.
   case Builtin::BIenqueue_kernel: {
     StringRef Name; // Generated function call name
     unsigned NumArgs = E->getNumArgs();
 
     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));
     llvm::Value *Range = EmitScalarExpr(E->getArg(2));
 
     if (NumArgs == 4) {
       // 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}));
     }
     assert(NumArgs >= 5 && "Invalid enqueue_kernel signature");
 
     // Could have events and/or vaargs.
     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.
       for (unsigned I = 4/*Position of the first size arg*/; I < NumArgs; ++I)
         Args.push_back(
             Builder.CreateZExtOrTrunc(EmitScalarExpr(E->getArg(I)), SizeTy));
 
       llvm::FunctionType *FTy = llvm::FunctionType::get(
if (NumArgs >= 7) {
       llvm::Value *EventList =
           E->getArg(4)->getType()->isArrayType()
               ? EmitArrayToPointerDecay(E->getArg(4)).getPointer()
               : EmitScalarExpr(E->getArg(4));
       llvm::Value *ClkEvent = EmitScalarExpr(E->getArg(5));
       // 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};
 
       if (NumArgs == 7) {
         // Has events but no variadics.
         Name = "__enqueue_kernel_basic_events";
         llvm::FunctionType *FTy = llvm::FunctionType::get(
if (NumArgs >= 7) {
       return RValue::get(
           Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
                              llvm::ArrayRef<llvm::Value *>(Args)));
     }
   }
   // 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),
   }
   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));
   }
   case Builtin::BIprintf:
     if (getLangOpts().CUDA && getLangOpts().CUDAIsDevice)
       return EmitCUDADevicePrintfCallExpr(E, ReturnValue);
     break;
   case Builtin::BI__builtin_canonicalize:

lib/Sema/SemaExpr.cpp

checkBlockPointerTypesForAssignment(Sema &S, QualType LHSType,
 
   // In C++, the types have to match exactly.
   if (S.getLangOpts().CPlusPlus)
     return Sema::IncompatibleBlockPointer;
 
   Sema::AssignConvertType ConvTy = Sema::Compatible;
 
   // For blocks we enforce that qualifiers are identical.
-  if (lhptee.getLocalQualifiers() != rhptee.getLocalQualifiers())
+  Qualifiers LQuals = lhptee.getLocalQualifiers();
+  Qualifiers RQuals = rhptee.getLocalQualifiers();
+  if (S.getLangOpts().OpenCL) {
+    LQuals.removeAddressSpace();
+    RQuals.removeAddressSpace();
+  }
+  if (LQuals != RQuals)
     ConvTy = Sema::CompatiblePointerDiscardsQualifiers;
 
   if (!S.Context.typesAreBlockPointerCompatible(LHSType, RHSType))
     return Sema::IncompatibleBlockPointer;
 
   return ConvTy;
 }
 
if (isa<ObjCObjectPointerType>(RHSType)) {
 
       Kind = CK_BitCast;
       return IncompatiblePointer;
     }
 
     // U^ -> void*
     if (RHSType->getAs<BlockPointerType>()) {
       if (LHSPointer->getPointeeType()->isVoidType()) {
-        Kind = CK_BitCast;
+        unsigned AddrSpaceL = LHSPointer->getPointeeType().getAddressSpace();
+        unsigned AddrSpaceR = RHSType->getAs<BlockPointerType>()
+                                  ->getPointeeType()
+                                  .getAddressSpace();
+        Kind =
+            AddrSpaceL != AddrSpaceR ? CK_AddressSpaceConversion : CK_BitCast;
         return Compatible;
       }
     }
 
     return Incompatible;
   }
 
   // Conversions to block pointers.
   if (isa<BlockPointerType>(LHSType)) {
     // U^ -> T^
     if (RHSType->isBlockPointerType()) {
-      Kind = CK_BitCast;
+      unsigned AddrSpaceL = LHSType->getAs<BlockPointerType>()
+                                ->getPointeeType()
+                                .getAddressSpace();
+      unsigned AddrSpaceR = RHSType->getAs<BlockPointerType>()
+                                ->getPointeeType()
+                                .getAddressSpace();
+      Kind = AddrSpaceL != AddrSpaceR ? CK_AddressSpaceConversion : CK_BitCast;
       return checkBlockPointerTypesForAssignment(*this, LHSType, RHSType);
     }
 
     // int or null -> T^
     if (RHSType->isIntegerType()) {
       Kind = CK_IntegralToPointer; // FIXME: null
       return IntToBlockPointer;
     }

lib/Sema/SemaType.cpp

static void processTypeAttrs(TypeProcessingState &state, QualType &type,
   // (...)
   // Pointers that are declared without pointing to a named address space point
   // to the generic address space.
   if (state.getSema().getLangOpts().OpenCLVersion >= 200 &&
       !hasOpenCLAddressSpace && type.getAddressSpace() == 0 &&
       (TAL == TAL_DeclSpec || TAL == TAL_DeclChunk)) {
     Declarator &D = state.getDeclarator();
     if (state.getCurrentChunkIndex() > 0 &&
+        (D.getTypeObject(state.getCurrentChunkIndex() - 1).Kind ==
+             DeclaratorChunk::Pointer ||
          D.getTypeObject(state.getCurrentChunkIndex() - 1).Kind ==
-            DeclaratorChunk::Pointer) {
+             DeclaratorChunk::BlockPointer)) {
       type = state.getSema().Context.getAddrSpaceQualType(
           type, LangAS::opencl_generic);
     } else if (state.getCurrentChunkIndex() == 0 &&
                D.getContext() == Declarator::FileContext &&
                !D.isFunctionDeclarator() && !D.isFunctionDefinition() &&
                D.getDeclSpec().getStorageClassSpec() != DeclSpec::SCS_typedef &&
                !type->isSamplerT())
       type = state.getSema().Context.getAddrSpaceQualType(

test/CodeGenOpenCL/cl20-device-side-enqueue.cl

 // RUN: %clang_cc1 %s -cl-std=CL2.0 -ffake-address-space-map -O0 -emit-llvm -o - -triple "spir-unknown-unknown" | FileCheck %s --check-prefix=COMMON --check-prefix=B32
 // RUN: %clang_cc1 %s -cl-std=CL2.0 -ffake-address-space-map -O0 -emit-llvm -o - -triple "spir64-unknown-unknown" | FileCheck %s --check-prefix=COMMON --check-prefix=B64
 
 typedef void (^bl_t)(local void *);
-
 // N.B. The check here only exists to set BL_GLOBAL
-// COMMON: @block_G = {{.*}}bitcast ([[BL_GLOBAL:[^@]+@__block_literal_global(\.[0-9]+)?]]
+// COMMON: @block_G =  addrspace(1) constant void (i8 addrspace(3)*) addrspace(4)* addrspacecast (void (i8 addrspace(3)*) addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* [[BL_GLOBAL:@__block_literal_global(\.[0-9]+)?]] to void (i8 addrspace(3)*) addrspace(1)*) to void (i8 addrspace(3)*) addrspace(4)*)
 const bl_t block_G = (bl_t) ^ (local void *a) {};
 
 kernel void device_side_enqueue(global int *a, global int *b, int i) {
   // COMMON: %default_queue = alloca %opencl.queue_t*
   queue_t default_queue;
   // COMMON: %flags = alloca i32
   unsigned flags = 0;
   // COMMON: %ndrange = alloca %opencl.ndrange_t*
   ndrange_t ndrange;
   // COMMON: %clk_event = alloca %opencl.clk_event_t*
   clk_event_t clk_event;
   // COMMON: %event_wait_list = alloca %opencl.clk_event_t*
   clk_event_t event_wait_list;
   // COMMON: %event_wait_list2 = alloca [1 x %opencl.clk_event_t*]
   clk_event_t event_wait_list2[] = {clk_event};
 
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // COMMON: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange
   // COMMON: [[BL:%[0-9]+]] = bitcast <{ i8*, i32, i32, i8*, %struct.__block_descriptor addrspace(2)*, i32{{.*}}, i32{{.*}}, i32{{.*}} }>* %block to void ()*
-  // COMMON: [[BL_I8:%[0-9]+]] = bitcast void ()* [[BL]] to i8*
-  // COMMON: call i32 @__enqueue_kernel_basic(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* [[BL_I8]])
+  // COMMON: [[BL_I8:%[0-9]+]] = addrspacecast void ()* [[BL]] to i8 addrspace(4)*
+  // COMMON: call i32 @__enqueue_kernel_basic(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8 addrspace(4)* [[BL_I8]])
   enqueue_kernel(default_queue, flags, ndrange,
                  ^(void) {
                    a[i] = b[i];
                  });
 
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // COMMON: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange
   // COMMON: [[WAIT_EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** %event_wait_list to %opencl.clk_event_t{{.*}}* addrspace(4)*
   // COMMON: [[EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** %clk_event to %opencl.clk_event_t{{.*}}* addrspace(4)*
   // COMMON: [[BL:%[0-9]+]] = bitcast <{ i8*, i32, i32, i8*, %struct.__block_descriptor addrspace(2)*, i32{{.*}}, i32{{.*}}, i32{{.*}} }>* %block3 to void ()*
-  // COMMON: [[BL_I8:%[0-9]+]] = bitcast void ()* [[BL]] to i8*
-  // COMMON: call i32 @__enqueue_kernel_basic_events(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %opencl.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}}* addrspace(4)* [[WAIT_EVNT]], %opencl.clk_event_t{{.*}}* addrspace(4)* [[EVNT]], i8* [[BL_I8]])
+  // COMMON: [[BL_I8:%[0-9]+]] = addrspacecast void ()* [[BL]] to i8 addrspace(4)*
+  // COMMON: call i32 @__enqueue_kernel_basic_events(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %opencl.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}}* addrspace(4)* [[WAIT_EVNT]], %opencl.clk_event_t{{.*}}* addrspace(4)* [[EVNT]], i8 addrspace(4)* [[BL_I8]])
   enqueue_kernel(default_queue, flags, ndrange, 2, &event_wait_list, &clk_event,
                  ^(void) {
                    a[i] = b[i];
                  });
 
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // COMMON: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange
-  // B32: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i32 256)
-  // B64: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i64 256)
+  // B32: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8 addrspace(4)*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32 256)
+  // B64: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8 addrspace(4)*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i64 256)
   enqueue_kernel(default_queue, flags, ndrange,
                  ^(local void *p) {
                    return;
                  },
                  256);
   char c;
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // COMMON: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange
   // B32: [[SIZE:%[0-9]+]] = zext i8 {{%[0-9]+}} to i32
-  // B32: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i32 [[SIZE]])
+  // B32: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8 addrspace(4)*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32 [[SIZE]])
   // B64: [[SIZE:%[0-9]+]] = zext i8 {{%[0-9]+}} to i64
-  // B64: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i64 [[SIZE]])
+  // B64: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8 addrspace(4)*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i64 [[SIZE]])
   enqueue_kernel(default_queue, flags, ndrange,
                  ^(local void *p) {
                    return;
                  },
                  c);
 
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // COMMON: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange
   // COMMON: [[AD:%arraydecay[0-9]*]] = getelementptr inbounds [1 x %opencl.clk_event_t*], [1 x %opencl.clk_event_t*]* %event_wait_list2, i32 0, i32 0
   // COMMON: [[WAIT_EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** [[AD]] to %opencl.clk_event_t{{.*}}* addrspace(4)*
   // COMMON: [[EVNT:%[0-9]+]]  = addrspacecast %opencl.clk_event_t{{.*}}** %clk_event to %opencl.clk_event_t{{.*}}* addrspace(4)*
-  // B32: call i32 (%opencl.queue_t{{.*}}*, i32,  %opencl.ndrange_t*, i32, %opencl.clk_event_t{{.*}}* addrspace(4)*, %opencl.clk_event_t{{.*}}* addrspace(4)*, i8*, i32, ...) @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %opencl.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}} [[WAIT_EVNT]], %opencl.clk_event_t{{.*}} [[EVNT]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i32 256)
-  // B64: call i32 (%opencl.queue_t{{.*}}*, i32,  %opencl.ndrange_t*, i32, %opencl.clk_event_t{{.*}}* addrspace(4)*, %opencl.clk_event_t{{.*}}* addrspace(4)*, i8*, i32, ...) @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %opencl.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}} [[WAIT_EVNT]], %opencl.clk_event_t{{.*}} [[EVNT]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i64 256)
+  // B32: call i32 (%opencl.queue_t{{.*}}*, i32,  %opencl.ndrange_t*, i32, %opencl.clk_event_t{{.*}}* addrspace(4)*, %opencl.clk_event_t{{.*}}* addrspace(4)*, i8 addrspace(4)*, i32, ...) @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %opencl.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}} [[WAIT_EVNT]], %opencl.clk_event_t{{.*}} [[EVNT]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32 256)
+  // B64: call i32 (%opencl.queue_t{{.*}}*, i32,  %opencl.ndrange_t*, i32, %opencl.clk_event_t{{.*}}* addrspace(4)*, %opencl.clk_event_t{{.*}}* addrspace(4)*, i8 addrspace(4)*, i32, ...) @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %opencl.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}} [[WAIT_EVNT]], %opencl.clk_event_t{{.*}} [[EVNT]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i64 256)
   enqueue_kernel(default_queue, flags, ndrange, 2, event_wait_list2, &clk_event,
                  ^(local void *p) {
                    return;
                  },
                  256);
 
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // COMMON: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange
   // COMMON: [[AD:%arraydecay[0-9]*]] = getelementptr inbounds [1 x %opencl.clk_event_t*], [1 x %opencl.clk_event_t*]* %event_wait_list2, i32 0, i32 0
   // COMMON: [[WAIT_EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** [[AD]] to %opencl.clk_event_t{{.*}}* addrspace(4)*
   // COMMON: [[EVNT:%[0-9]+]]  = addrspacecast %opencl.clk_event_t{{.*}}** %clk_event to %opencl.clk_event_t{{.*}}* addrspace(4)*
   // B32: [[SIZE:%[0-9]+]] = zext i8 {{%[0-9]+}} to i32
-  // B32: call i32 (%opencl.queue_t{{.*}}*, i32,  %opencl.ndrange_t*, i32, %opencl.clk_event_t{{.*}}* addrspace(4)*, %opencl.clk_event_t{{.*}}* addrspace(4)*, i8*, i32, ...) @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %opencl.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}}* addrspace(4)* [[WAIT_EVNT]], %opencl.clk_event_t{{.*}}* addrspace(4)* [[EVNT]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i32 [[SIZE]])
+  // B32: call i32 (%opencl.queue_t{{.*}}*, i32,  %opencl.ndrange_t*, i32, %opencl.clk_event_t{{.*}}* addrspace(4)*, %opencl.clk_event_t{{.*}}* addrspace(4)*, i8 addrspace(4)*, i32, ...) @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %opencl.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}}* addrspace(4)* [[WAIT_EVNT]], %opencl.clk_event_t{{.*}}* addrspace(4)* [[EVNT]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32 [[SIZE]])
   // B64: [[SIZE:%[0-9]+]] = zext i8 {{%[0-9]+}} to i64
-  // B64: call i32 (%opencl.queue_t{{.*}}*, i32,  %opencl.ndrange_t*, i32, %opencl.clk_event_t{{.*}}* addrspace(4)*, %opencl.clk_event_t{{.*}}* addrspace(4)*, i8*, i32, ...) @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %opencl.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}}* addrspace(4)* [[WAIT_EVNT]], %opencl.clk_event_t{{.*}}* addrspace(4)* [[EVNT]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i64 [[SIZE]])
+  // B64: call i32 (%opencl.queue_t{{.*}}*, i32,  %opencl.ndrange_t*, i32, %opencl.clk_event_t{{.*}}* addrspace(4)*, %opencl.clk_event_t{{.*}}* addrspace(4)*, i8 addrspace(4)*, i32, ...) @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %opencl.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}}* addrspace(4)* [[WAIT_EVNT]], %opencl.clk_event_t{{.*}}* addrspace(4)* [[EVNT]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i64 [[SIZE]])
   enqueue_kernel(default_queue, flags, ndrange, 2, event_wait_list2, &clk_event,
                  ^(local void *p) {
                    return;
                  },
                  c);
 
   long l;
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // COMMON: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange
   // B32: [[SIZE:%[0-9]+]] = trunc i64 {{%[0-9]+}} to i32
-  // B32: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i32 [[SIZE]])
+  // B32: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8 addrspace(4)*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32 [[SIZE]])
   // B64: [[SIZE:%[0-9]+]] = load i64, i64* %l
-  // B64: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i64 [[SIZE]])
+  // B64: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8 addrspace(4)*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i64 [[SIZE]])
   enqueue_kernel(default_queue, flags, ndrange,
                  ^(local void *p) {
                    return;
                  },
                  l);
 
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t*, %opencl.queue_t** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // COMMON: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange
-  // B32: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i32 0)
-  // B64: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i64 4294967296)
+  // B32: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8 addrspace(4)*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32 0)
+  // B64: call i32 (%opencl.queue_t{{.*}}*, i32, %opencl.ndrange_t*, i8 addrspace(4)*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i64 4294967296)
   enqueue_kernel(default_queue, flags, ndrange,
                  ^(local void *p) {
                    return;
                  },
                  4294967296L);
 
   // The full type of these expressions are long (and repeated elsewhere), so we
   // capture it as part of the regex for convenience and clarity.
-  // COMMON: store void ()* bitcast ([[BL_A:[^@]+@__block_literal_global.[0-9]+]] to void ()*), void ()** %block_A
+  // COMMON: store void () addrspace(4)* addrspacecast (void () addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* [[BL_A:@__block_literal_global(\.[0-9]+)?]] to void () addrspace(1)*) to void () addrspace(4)*), void () addrspace(4)** %block_A
   void (^const block_A)(void) = ^{
     return;
   };
 
-  // COMMON: store void (i8 addrspace(3)*)* bitcast ([[BL_B:[^@]+@__block_literal_global.[0-9]+]] to void (i8 addrspace(3)*)*), void (i8 addrspace(3)*)** %block_B
+  // COMMON: store void (i8 addrspace(3)*) addrspace(4)* addrspacecast (void (i8 addrspace(3)*) addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* [[BL_B:@__block_literal_global(\.[0-9]+)?]] to void (i8 addrspace(3)*) addrspace(1)*) to void (i8 addrspace(3)*) addrspace(4)*), void (i8 addrspace(3)*) addrspace(4)** %block_B
   void (^const block_B)(local void *) = ^(local void *a) {
     return;
   };
 
-  // COMMON: call i32 @__get_kernel_work_group_size_impl(i8* bitcast ([[BL_A]] to i8*))
+  // COMMON: call i32 @__get_kernel_work_group_size_impl(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* [[BL_A]] to i8 addrspace(1)*) to i8 addrspace(4)*))
   unsigned size = get_kernel_work_group_size(block_A);
-  // COMMON: call i32 @__get_kernel_work_group_size_impl(i8* bitcast ([[BL_B]] to i8*))
+  // COMMON: call i32 @__get_kernel_work_group_size_impl(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* [[BL_B]] to i8 addrspace(1)*) to i8 addrspace(4)*))
   size = get_kernel_work_group_size(block_B);
-  // COMMON: call i32 @__get_kernel_preferred_work_group_multiple_impl(i8* bitcast ([[BL_A]] to i8*))
+  // COMMON: call i32 @__get_kernel_preferred_work_group_multiple_impl(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* [[BL_A]] to i8 addrspace(1)*) to i8 addrspace(4)*))
   size = get_kernel_preferred_work_group_size_multiple(block_A);
-  // COMMON: call i32 @__get_kernel_preferred_work_group_multiple_impl(i8* bitcast ([[BL_GLOBAL]] to i8*))
+  // COMMON: call i32 @__get_kernel_preferred_work_group_multiple_impl(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* [[BL_GLOBAL]] to i8 addrspace(1)*) to i8 addrspace(4)*))
   size = get_kernel_preferred_work_group_size_multiple(block_G);
 }

test/SemaOpenCL/invalid-block.cl

 // RUN: %clang_cc1 -verify -fblocks -cl-std=CL2.0 %s
 
 // OpenCL v2.0 s6.12.5
 void f0(int (^const bl)());
 // All blocks declarations must be const qualified and initialized.
 void f1() {
-  int (^bl1)() = ^() {return 1;};
-  int (^const bl2)() = ^(){return 1;};
+  int (^bl1)(void) = ^() {
+    return 1;
+  };
+  int (^const bl2)(void) = ^() {
+    return 1;
+  };
   f0(bl1);
   f0(bl2);
-  bl1 = bl2; // expected-error{{invalid operands to binary expression ('int (^const)()' and 'int (^const)()')}}
+  bl1 = bl2;          // expected-error{{invalid operands to binary expression ('int (__generic ^const)(void)' and 'int (__generic ^const)(void)')}}
   int (^const bl3)(); // expected-error{{invalid block variable declaration - must be initialized}}
 }
 
 // A block with extern storage class is not allowed.
-extern int (^bl)() = ^(){return 1;}; // expected-error{{invalid block variable declaration - using 'extern' storage class is disallowed}}
+extern int (^bl)(void) = ^() { // expected-error{{invalid block variable declaration - using 'extern' storage class is disallowed}}
+  return 1;
+};
 void f2() {
-  extern int (^bl)() = ^(){return 1;}; // expected-error{{invalid block variable declaration - using 'extern' storage class is disallowed}}
+  extern int (^bl)(void) = ^() { // expected-error{{invalid block variable declaration - using 'extern' storage class is disallowed}}
+    return 1;
+  };
 }
 
 // A block cannot be the return value of a function.
 typedef int (^bl_t)(void);
-bl_t f3(bl_t bl); // expected-error{{declaring function return value of type 'bl_t' (aka 'int (^const)(void)') is not allowed}}
+bl_t f3(bl_t bl); // expected-error{{declaring function return value of type 'bl_t' (aka 'int (__generic ^const)(void)') is not allowed}}
 
 struct bl_s {
-  int (^bl)(void); // expected-error {{the 'int (^const)(void)' type cannot be used to declare a structure or union field}}
+  int (^bl)(void); // expected-error {{the 'int (__generic ^const)(void)' type cannot be used to declare a structure or union field}}
 };
 
 void f4() {
   __block int a = 10; // expected-error {{the __block storage type is not permitted}}
 }
 
 // A block with variadic argument is not allowed.
 int (^bl)(int, ...) = ^int(int I, ...) { // expected-error {{invalid prototype, variadic arguments are not allowed in OpenCL}} expected-error {{invalid prototype, variadic arguments are not allowed in OpenCL}}
   return 0;
 };
 typedef int (^bl1_t)(int, ...); // expected-error {{invalid prototype, variadic arguments are not allowed in OpenCL}}
 
 // A block can't be used to declare an array
 typedef int (^bl2_t)(int);
 void f5(int i) {
   bl2_t bl1 = ^(int i) {
     return 1;
   };
   bl2_t bl2 = ^(int i) {
     return 2;
   };
-  bl2_t arr[] = {bl1, bl2}; // expected-error {{array of 'bl2_t' (aka 'int (^const)(int)') type is invalid in OpenCL}}
+  bl2_t arr[] = {bl1, bl2}; // expected-error {{array of 'bl2_t' (aka 'int (__generic ^const)(int)') type is invalid in OpenCL}}
   int tmp = i ? bl1(i)      // expected-error {{block type cannot be used as expression in ternary expression in OpenCL}}
               : bl2(i);     // expected-error {{block type cannot be used as expression in ternary expression in OpenCL}}
 }
 // A block pointer type and all pointer operations are disallowed
-void f6(bl2_t *bl_ptr) { // expected-error{{pointer to type '__generic bl2_t' (aka 'int (^const __generic)(int)') is invalid in OpenCL}}
+void f6(bl2_t *bl_ptr) { // expected-error{{pointer to type '__generic bl2_t' (aka 'int (__generic ^const __generic)(int)') is invalid in OpenCL}}
   bl2_t bl = ^(int i) {
     return 1;
   };
-  bl2_t *p; // expected-error {{pointer to type '__generic bl2_t' (aka 'int (^const __generic)(int)') is invalid in OpenCL}}
-  *bl;      // expected-error {{invalid argument type 'bl2_t' (aka 'int (^const)(int)') to unary expression}}
-  &bl;      // expected-error {{invalid argument type 'bl2_t' (aka 'int (^const)(int)') to unary expression}}
+  bl2_t *p; // expected-error {{pointer to type '__generic bl2_t' (aka 'int (__generic ^const __generic)(int)') is invalid in OpenCL}}
+  *bl;      // expected-error {{invalid argument type 'bl2_t' (aka 'int (__generic ^const)(int)') to unary expression}}
+  &bl;      // expected-error {{invalid argument type 'bl2_t' (aka 'int (__generic ^const)(int)') to unary expression}}
 }