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

Modify ObjC blocks impl wrt address spaces as follows:

- keep default private address space for blocks generated
as local variables (with captures);

- add global address space for global block literals (no captures);

- make the block invoke function and enqueue_kernel prototype with
the generic AS block pointer parameter to accommodate both
private and global AS cases from above;

- add 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 AS blocks for the two cases above.

- removes ObjC RT specific symbols (NSConcreteStackBlock and
NSConcreteGlobalBlock) in the OpenCL mode.

Review: https://reviews.llvm.org/D28814

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@293286 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/AST/Expr.cpp b/lib/AST/Expr.cpp
index 14f31d0c6b8ce5dff7b1c14ae420dbb280b87ef3..366e5bf404fc2734ade877e40ebf6a0a159869a7 100644 (file)
--- a/lib/AST/Expr.cpp
+++ b/lib/AST/Expr.cpp
@@ -1571,8 +1571,9 @@ bool CastExpr::CastConsistency() const {
     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.

diff --git a/lib/CodeGen/CGBlocks.cpp b/lib/CodeGen/CGBlocks.cpp
index b250b9a32b181e16b35fb4ac9e8e125a26fdf14b..53288a69e2d4c679cffae68dc2710acec2bf0683 100644 (file)
--- a/lib/CodeGen/CGBlocks.cpp
+++ b/lib/CodeGen/CGBlocks.cpp
@@ -718,7 +718,12 @@ llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo) {
 
   // 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(getContext().VoidPtrTy));
   isa = llvm::ConstantExpr::getBitCast(isa, VoidPtrTy);
 
   // Build the block descriptor.
@@ -906,9 +911,8 @@ llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo) {
 
   // 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;
 }
@@ -976,21 +980,41 @@ RValue CodeGenFunction::EmitBlockCallExpr(const CallExpr *E,
   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();
 
@@ -1097,7 +1121,12 @@ static llvm::Constant *buildGlobalBlock(CodeGenModule &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(CGM.getContext().VoidPtrTy)));
 
   // __flags
   BlockFlags flags = BLOCK_IS_GLOBAL | BLOCK_HAS_SIGNATURE;
@@ -1114,16 +1143,19 @@ static llvm::Constant *buildGlobalBlock(CodeGenModule &CGM,
   // 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;
 }
@@ -1155,9 +1187,13 @@ void CodeGenFunction::setBlockContextParameter(const ImplicitParamDecl *D,
 
   // 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),
+      "block");
 }
 
 Address CodeGenFunction::LoadBlockStruct() {
@@ -1196,6 +1232,15 @@ CodeGenFunction::GenerateBlockFunction(GlobalDecl GD,
   // 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),

diff --git a/lib/CodeGen/CGBuiltin.cpp b/lib/CodeGen/CGBuiltin.cpp
index b3d02f1f51c611290056f1a04020ab690ec507c3..b1feefe9f0de98536a8a7469c1be7d1432340999 100644 (file)
--- a/lib/CodeGen/CGBuiltin.cpp
+++ b/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));
   }

diff --git a/lib/Sema/SemaExpr.cpp b/lib/Sema/SemaExpr.cpp
index 43242390597a571c9e4f1f786bb49cb0a496ca07..ca57a413e91bac0769d1025557704692d91c82f4 100644 (file)
--- a/lib/Sema/SemaExpr.cpp
+++ b/lib/Sema/SemaExpr.cpp
@@ -7405,7 +7405,13 @@ checkBlockPointerTypesForAssignment(Sema &S, QualType LHSType,
   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))
@@ -7630,7 +7636,12 @@ Sema::CheckAssignmentConstraints(QualType LHSType, ExprResult &RHS,
     // 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;
       }
     }
@@ -7642,7 +7653,13 @@ Sema::CheckAssignmentConstraints(QualType LHSType, ExprResult &RHS,
   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);
     }
 

diff --git a/lib/Sema/SemaType.cpp b/lib/Sema/SemaType.cpp
index e4995bd2206469bf4ff6f1a6741a8b0b0a17b519..92a2ecc22759e864d1f79427700aafd968898e74 100644 (file)
--- a/lib/Sema/SemaType.cpp
+++ b/lib/Sema/SemaType.cpp
@@ -6942,8 +6942,10 @@ static void processTypeAttrs(TypeProcessingState &state, QualType &type,
       (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 ||
+         D.getTypeObject(state.getCurrentChunkIndex() - 1).Kind ==
+             DeclaratorChunk::BlockPointer)) {
       type = state.getSema().Context.getAddrSpaceQualType(
           type, LangAS::opencl_generic);
     } else if (state.getCurrentChunkIndex() == 0 &&

diff --git a/test/CodeGenOpenCL/blocks.cl b/test/CodeGenOpenCL/blocks.cl
new file mode 100644 (file)
index 0000000..375c539
--- /dev/null
+++ b/test/CodeGenOpenCL/blocks.cl
@@ -0,0 +1,19 @@
+// RUN: %clang_cc1 %s -cl-std=CL2.0 -emit-llvm -o - -O0 -triple spir-unknown-unknown | FileCheck %s --check-prefix=COMMON
+// RUN: %clang_cc1 %s -cl-std=CL2.0 -emit-llvm -o - -O0 -triple amdgcn-amd-amdhsa-opencl | FileCheck %s --check-prefix=AMD
+
+// Checking for null instead of @__NSConcreteGlobalBlock symbol
+// COMMON: @__block_literal_global = internal addrspace(1) constant { i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } { i8** null
+// AMD: @__block_literal_global = internal addrspace(1) constant { i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } { i8** addrspacecast (i8* addrspace(4)* null to i8**)
+void (^block_A)(local void *) = ^(local void *a) {
+  return;
+};
+
+void foo(){
+  int i;
+// Checking for null instead of @_NSConcreteStackBlock symbol
+// COMMON: store i8* null, i8** %block.isa
+// AMD: store i8* addrspacecast (i8 addrspace(4)* null to i8*), i8** %block.isa,
+  int (^ block_B)(void) = ^{
+    return i;
+  };
+}

diff --git a/test/CodeGenOpenCL/cl20-device-side-enqueue.cl b/test/CodeGenOpenCL/cl20-device-side-enqueue.cl
index add13b9e3fc472f0dda2e794a0a9fd019fe4d7b4..fdfb199944dc790dbf3edcc67f1fb1a7cb1dd6df 100644 (file)
--- a/test/CodeGenOpenCL/cl20-device-side-enqueue.cl
+++ b/test/CodeGenOpenCL/cl20-device-side-enqueue.cl
@@ -2,9 +2,8 @@
 // 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) {
@@ -25,8 +24,8 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
   // 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];
@@ -38,8 +37,8 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
   // 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];
@@ -48,8 +47,8 @@ kernel void device_side_enqueue(global int *a, global int *b, int 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;
@@ -60,9 +59,9 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
   // 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;
@@ -75,8 +74,8 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
   // 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;
@@ -90,9 +89,9 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
   // 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;
@@ -104,9 +103,9 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
   // 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;
@@ -116,8 +115,8 @@ kernel void device_side_enqueue(global int *a, global int *b, int 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 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;
@@ -126,22 +125,22 @@ kernel void device_side_enqueue(global int *a, global int *b, int i) {
 
   // 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);
 }

diff --git a/test/SemaOpenCL/invalid-block.cl b/test/SemaOpenCL/invalid-block.cl
index a9eac1c2b582d14b20f17b2344b4eb158c41efb2..598784c95a0665d83dcc93ddf0afe04d06dcea09 100644 (file)
--- a/test/SemaOpenCL/invalid-block.cl
+++ b/test/SemaOpenCL/invalid-block.cl
@@ -4,26 +4,34 @@
 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() {
@@ -45,16 +53,16 @@ void f5(int i) {
   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}}
 }