Index: lib/CodeGen/CGBlocks.cpp =================================================================== --- lib/CodeGen/CGBlocks.cpp +++ lib/CodeGen/CGBlocks.cpp @@ -14,6 +14,7 @@ #include "CGBlocks.h" #include "CGDebugInfo.h" #include "CGObjCRuntime.h" +#include "CGOpenCLRuntime.h" #include "CodeGenFunction.h" #include "CodeGenModule.h" #include "ConstantEmitter.h" @@ -302,21 +303,37 @@ static void initializeForBlockHeader(CodeGenModule &CGM, CGBlockInfo &info, SmallVectorImpl &elementTypes) { - // The header is basically 'struct { void *; int; int; void *; void *; }'. - // Assert that that struct is packed. - assert(CGM.getIntSize() <= CGM.getPointerSize()); - assert(CGM.getIntAlign() <= CGM.getPointerAlign()); - assert((2 * CGM.getIntSize()).isMultipleOf(CGM.getPointerAlign())); - - info.BlockAlign = CGM.getPointerAlign(); - info.BlockSize = 3 * CGM.getPointerSize() + 2 * CGM.getIntSize(); assert(elementTypes.empty()); - elementTypes.push_back(CGM.VoidPtrTy); - elementTypes.push_back(CGM.IntTy); - elementTypes.push_back(CGM.IntTy); - elementTypes.push_back(CGM.VoidPtrTy); - elementTypes.push_back(CGM.getBlockDescriptorType()); + if (CGM.getLangOpts().OpenCL) { + // The header is basically 'struct { int; int; generic void *; }'. + // Assert that that struct is packed. + auto GenPtrAlign = CharUnits::fromQuantity( + CGM.getTarget().getPointerAlign(LangAS::opencl_generic) / 8); + auto GenPtrSize = CharUnits::fromQuantity( + CGM.getTarget().getPointerWidth(LangAS::opencl_generic) / 8); + assert(CGM.getIntSize() <= GenPtrSize); + assert(CGM.getIntAlign() <= GenPtrAlign); + assert((2 * CGM.getIntSize()).isMultipleOf(GenPtrAlign)); + info.BlockAlign = GenPtrAlign; + info.BlockSize = GenPtrSize + 2 * CGM.getIntSize(); + elementTypes.push_back(CGM.IntTy); + elementTypes.push_back(CGM.IntTy); + elementTypes.push_back(CGM.getOpenCLRuntime().getGenericVoidPointerType()); + } else { + // The header is basically 'struct { void *; int; int; void *; void *; }'. + // Assert that that struct is packed. + assert(CGM.getIntSize() <= CGM.getPointerSize()); + assert(CGM.getIntAlign() <= CGM.getPointerAlign()); + assert((2 * CGM.getIntSize()).isMultipleOf(CGM.getPointerAlign())); + info.BlockAlign = CGM.getPointerAlign(); + info.BlockSize = 3 * CGM.getPointerSize() + 2 * CGM.getIntSize(); + elementTypes.push_back(CGM.VoidPtrTy); + elementTypes.push_back(CGM.IntTy); + elementTypes.push_back(CGM.IntTy); + elementTypes.push_back(CGM.VoidPtrTy); + elementTypes.push_back(CGM.getBlockDescriptorType()); + } } static QualType getCaptureFieldType(const CodeGenFunction &CGF, @@ -720,13 +737,19 @@ } llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo) { + bool IsOpenCL = CGM.getContext().getLangOpts().OpenCL; + auto GenVoidPtrTy = + IsOpenCL ? CGM.getOpenCLRuntime().getGenericVoidPointerType() : VoidPtrTy; + unsigned GenVoidPtrAddr = IsOpenCL ? LangAS::opencl_generic : LangAS::Default; + auto GenVoidPtrSize = CharUnits::fromQuantity( + CGM.getTarget().getPointerWidth(GenVoidPtrAddr) / 8); // Using the computed layout, generate the actual block function. bool isLambdaConv = blockInfo.getBlockDecl()->isConversionFromLambda(); llvm::Constant *blockFn = CodeGenFunction(CGM, true).GenerateBlockFunction(CurGD, blockInfo, LocalDeclMap, isLambdaConv); - blockFn = llvm::ConstantExpr::getBitCast(blockFn, VoidPtrTy); + blockFn = llvm::ConstantExpr::getPointerCast(blockFn, GenVoidPtrTy); // If there is nothing to capture, we can emit this as a global block. if (blockInfo.CanBeGlobal) @@ -734,26 +757,30 @@ // Otherwise, we have to emit this as a local block. - llvm::Constant *isa = - (!CGM.getContext().getLangOpts().OpenCL) - ? CGM.getNSConcreteStackBlock() - : CGM.getNullPointer(VoidPtrPtrTy, - CGM.getContext().getPointerType( - QualType(CGM.getContext().VoidPtrTy))); - 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!"); - // Compute the initial on-stack block flags. - BlockFlags flags = BLOCK_HAS_SIGNATURE; - if (blockInfo.HasCapturedVariableLayout) flags |= BLOCK_HAS_EXTENDED_LAYOUT; - if (blockInfo.NeedsCopyDispose) flags |= BLOCK_HAS_COPY_DISPOSE; - if (blockInfo.HasCXXObject) flags |= BLOCK_HAS_CXX_OBJ; - if (blockInfo.UsesStret) flags |= BLOCK_USE_STRET; + llvm::Constant *isa; + llvm::Constant *descriptor; + BlockFlags flags; + if (!IsOpenCL) { + isa = llvm::ConstantExpr::getBitCast(CGM.getNSConcreteStackBlock(), + VoidPtrTy); + + // Build the block descriptor. + descriptor = buildBlockDescriptor(CGM, blockInfo); + + // Compute the initial on-stack block flags. + flags = BLOCK_HAS_SIGNATURE; + if (blockInfo.HasCapturedVariableLayout) + flags |= BLOCK_HAS_EXTENDED_LAYOUT; + if (blockInfo.NeedsCopyDispose) + flags |= BLOCK_HAS_COPY_DISPOSE; + if (blockInfo.HasCXXObject) + flags |= BLOCK_HAS_CXX_OBJ; + if (blockInfo.UsesStret) + flags |= BLOCK_USE_STRET; + } auto projectField = [&](unsigned index, CharUnits offset, const Twine &name) -> Address { @@ -777,13 +804,23 @@ index++; }; - addHeaderField(isa, getPointerSize(), "block.isa"); - addHeaderField(llvm::ConstantInt::get(IntTy, flags.getBitMask()), - getIntSize(), "block.flags"); - addHeaderField(llvm::ConstantInt::get(IntTy, 0), - getIntSize(), "block.reserved"); - addHeaderField(blockFn, getPointerSize(), "block.invoke"); - addHeaderField(descriptor, getPointerSize(), "block.descriptor"); + if (!IsOpenCL) { + addHeaderField(isa, getPointerSize(), "block.isa"); + addHeaderField(llvm::ConstantInt::get(IntTy, flags.getBitMask()), + getIntSize(), "block.flags"); + addHeaderField(llvm::ConstantInt::get(IntTy, 0), getIntSize(), + "block.reserved"); + } else { + addHeaderField( + llvm::ConstantInt::get(IntTy, blockInfo.BlockSize.getQuantity()), + getIntSize(), "block.size"); + addHeaderField( + llvm::ConstantInt::get(IntTy, blockInfo.BlockAlign.getQuantity()), + getIntSize(), "block.align"); + } + addHeaderField(blockFn, GenVoidPtrSize, "block.invoke"); + if (!IsOpenCL) + addHeaderField(descriptor, getPointerSize(), "block.descriptor"); } // Finally, capture all the values into the block. @@ -993,7 +1030,7 @@ return GenericBlockLiteralType; } -RValue CodeGenFunction::EmitBlockCallExpr(const CallExpr *E, +RValue CodeGenFunction::EmitBlockCallExpr(const CallExpr *E, ReturnValueSlot ReturnValue) { const BlockPointerType *BPT = E->getCallee()->getType()->getAs(); @@ -1018,8 +1055,8 @@ // Get the function pointer from the literal. llvm::Value *FuncPtr = - Builder.CreateStructGEP(CGM.getGenericBlockLiteralType(), BlockPtr, 3); - + Builder.CreateStructGEP(CGM.getGenericBlockLiteralType(), BlockPtr, + CGM.getLangOpts().OpenCL ? 0 : 3); // Add the block literal. CallArgList Args; @@ -1027,8 +1064,7 @@ QualType VoidPtrQualTy = getContext().VoidPtrTy; llvm::Type *GenericVoidPtrTy = VoidPtrTy; if (getLangOpts().OpenCL) { - GenericVoidPtrTy = Builder.getInt8PtrTy( - getContext().getTargetAddressSpace(LangAS::opencl_generic)); + GenericVoidPtrTy = CGM.getOpenCLRuntime().getGenericVoidPointerType(); VoidPtrQualTy = getContext().getPointerType(getContext().getAddrSpaceQualType( getContext().VoidTy, LangAS::opencl_generic)); @@ -1053,7 +1089,7 @@ llvm::Type *BlockFTy = CGM.getTypes().GetFunctionType(FnInfo); llvm::Type *BlockFTyPtr = llvm::PointerType::getUnqual(BlockFTy); - Func = Builder.CreateBitCast(Func, BlockFTyPtr); + Func = Builder.CreatePointerCast(Func, BlockFTyPtr); // Prepare the callee. CGCallee Callee(CGCalleeInfo(), Func); @@ -1122,7 +1158,11 @@ LocalDeclMap, false); } - blockFn = llvm::ConstantExpr::getBitCast(blockFn, VoidPtrTy); + auto GenVoidPtrTy = getContext().getLangOpts().OpenCL + ? getOpenCLRuntime().getGenericVoidPointerType() + : VoidPtrTy; + + blockFn = llvm::ConstantExpr::getPointerCast(blockFn, GenVoidPtrTy); return buildGlobalBlock(*this, blockInfo, blockFn); } @@ -1141,27 +1181,32 @@ ConstantInitBuilder builder(CGM); auto fields = builder.beginStruct(); - // isa - fields.add((!CGM.getContext().getLangOpts().OpenCL) - ? CGM.getNSConcreteGlobalBlock() - : CGM.getNullPointer(CGM.VoidPtrPtrTy, - CGM.getContext().getPointerType(QualType( - CGM.getContext().VoidPtrTy)))); + bool IsOpenCL = CGM.getLangOpts().OpenCL; + if (!IsOpenCL) { + // isa + fields.add(CGM.getNSConcreteGlobalBlock()); - // __flags - BlockFlags flags = BLOCK_IS_GLOBAL | BLOCK_HAS_SIGNATURE; - if (blockInfo.UsesStret) flags |= BLOCK_USE_STRET; - - fields.addInt(CGM.IntTy, flags.getBitMask()); + // __flags + BlockFlags flags = BLOCK_IS_GLOBAL | BLOCK_HAS_SIGNATURE; + if (blockInfo.UsesStret) + flags |= BLOCK_USE_STRET; - // Reserved - fields.addInt(CGM.IntTy, 0); + fields.addInt(CGM.IntTy, flags.getBitMask()); + + // Reserved + fields.addInt(CGM.IntTy, 0); + } else { + fields.addInt(CGM.IntTy, blockInfo.BlockSize.getQuantity()); + fields.addInt(CGM.IntTy, blockInfo.BlockAlign.getQuantity()); + } // Function fields.add(blockFn); - // Descriptor - fields.add(buildBlockDescriptor(CGM, blockInfo)); + if (!IsOpenCL) { + // Descriptor + fields.add(buildBlockDescriptor(CGM, blockInfo)); + } unsigned AddrSpace = 0; if (CGM.getContext().getLangOpts().OpenCL) Index: lib/CodeGen/CGOpenCLRuntime.h =================================================================== --- lib/CodeGen/CGOpenCLRuntime.h +++ lib/CodeGen/CGOpenCLRuntime.h @@ -59,6 +59,9 @@ // \brief Returnes a value which indicates the alignment in bytes of the pipe // element. virtual llvm::Value *getPipeElemAlign(const Expr *PipeArg); + + /// \return __generic void* type. + llvm::PointerType *getGenericVoidPointerType(); }; } Index: lib/CodeGen/CGOpenCLRuntime.cpp =================================================================== --- lib/CodeGen/CGOpenCLRuntime.cpp +++ lib/CodeGen/CGOpenCLRuntime.cpp @@ -103,3 +103,9 @@ .getQuantity(); return llvm::ConstantInt::get(Int32Ty, TypeSize, false); } + +llvm::PointerType *CGOpenCLRuntime::getGenericVoidPointerType() { + return llvm::IntegerType::getInt8PtrTy( + CGM.getLLVMContext(), + CGM.getContext().getTargetAddressSpace(LangAS::opencl_generic)); +} Index: test/CodeGen/blocks-opencl.cl =================================================================== --- test/CodeGen/blocks-opencl.cl +++ test/CodeGen/blocks-opencl.cl @@ -1,11 +1,12 @@ // RUN: %clang_cc1 -O0 %s -ffake-address-space-map -emit-llvm -o - -fblocks -triple x86_64-unknown-unknown | FileCheck %s +// RUN: %clang_cc1 -O0 %s -emit-llvm -o - -fblocks -triple amdgcn | FileCheck %s // This used to crash due to trying to generate a bitcase from a cstring // in the constant address space to i8* in AS0. void dummy(float (^const op)(float)) { } -// CHECK: i8 addrspace(2)* getelementptr inbounds ([9 x i8], [9 x i8] addrspace(2)* @.str, i32 0, i32 0) +// CHECK-NOT: @.str kernel void test_block() { Index: test/CodeGenOpenCL/blocks.cl =================================================================== --- test/CodeGenOpenCL/blocks.cl +++ test/CodeGenOpenCL/blocks.cl @@ -1,17 +1,48 @@ -// RUN: %clang_cc1 %s -cl-std=CL2.0 -emit-llvm -o - -O0 -triple spir-unknown-unknown | FileCheck -check-prefix=GENERIC -check-prefix=COMMON %s -// RUN: %clang_cc1 %s -cl-std=CL2.0 -emit-llvm -o - -O0 -triple amdgcn-amd-amdhsa-opencl | FileCheck -check-prefix=AMD -check-prefix=COMMON %s +// RUN: %clang_cc1 %s -cl-std=CL2.0 -emit-llvm -o - -O0 -triple spir-unknown-unknown | FileCheck -check-prefixes=COMMON,SPIR %s +// RUN: %clang_cc1 %s -cl-std=CL2.0 -emit-llvm -o - -O0 -triple amdgcn-amd-amdhsa-opencl | FileCheck -check-prefixes=COMMON,AMD %s -// 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 +// SPIR: @__block_literal_global = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 12, i32 4, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* @block_A_block_invoke to i8*) to i8 addrspace(4)*) } +// AMD: @__block_literal_global = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 16, i32 8, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* @block_A_block_invoke to i8*) to i8 addrspace(4)*) } +// COMMON-NOT: .str + +// COMMON-LABEL: define internal {{.*}}void @block_A_block_invoke(i8 addrspace(4)* %.block_descriptor, i8 addrspace(3)* %a) void (^block_A)(local void *) = ^(local void *a) { return; }; +// COMMON-LABEL: define {{.*}}void @foo() void foo(){ int i; -// Checking for null instead of @_NSConcreteStackBlock symbol -// COMMON: store i8* null, i8** %block.isa + // COMMON-NOT: store i8* null, i8** %block.isa + // COMMON: %[[block_size:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %block, i32 0, i32 0 + // SPIR: store i32 16, i32* %[[block_size]] + // AMD: store i32 20, i32* %[[block_size]] + // COMMON: %[[block_align:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %block, i32 0, i32 1 + // SPIR: store i32 4, i32* %[[block_align]] + // AMD: store i32 8, i32* %[[block_align]] + // COMMON: %[[block_invoke:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block:.*]], i32 0, i32 2 + // COMMON: store i8 addrspace(4)* addrspacecast (i8* bitcast (i32 (i8 addrspace(4)*)* @__foo_block_invoke to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %[[block_invoke]] + // COMMON: %[[block_captured:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]], i32 0, i32 3 + // COMMON: %[[r0:.*]] = load i32, i32* %i + // COMMON: store i32 %[[r0]], i32* %[[block_captured]], + // COMMON: %[[r1:.*]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]] to i32 ()* + // COMMON: %[[r2:.*]] = addrspacecast i32 ()* %[[r1]] to i32 () addrspace(4)* + // COMMON: store i32 () addrspace(4)* %[[r2]], i32 () addrspace(4)** %[[block_B:.*]], + // COMMON: %[[r3:.*]] = load i32 () addrspace(4)*, i32 () addrspace(4)** %[[block_B]] + // COMMON: %[[block_literal:.*]] = bitcast i32 () addrspace(4)* %3 to %struct.__block_literal_generic addrspace(4)* + // COMMON: %[[r4:.*]] = getelementptr inbounds %struct.__block_literal_generic, %struct.__block_literal_generic addrspace(4)* %[[block_literal]], i32 0, i32 0 + // COMMON: %[[r5:.*]] = bitcast %struct.__block_literal_generic addrspace(4)* %[[block_literal]] to i8 addrspace(4)* + // COMMON: %[[r6:.*]] = load i8*, i8* addrspace(4)* %[[r4]] + // COMMON: %[[r7:.*]] = bitcast i8* %[[r6]] to i32 (i8 addrspace(4)*)* + // COMMON: call {{.*}}i32 %[[r7]](i8 addrspace(4)* %[[r5]]) + int (^ block_B)(void) = ^{ return i; }; + block_B(); } + +// COMMON-LABEL: define internal {{.*}}i32 @__foo_block_invoke(i8 addrspace(4)* %.block_descriptor) +// COMMON: %[[block:.*]] = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i8 addrspace(4)*, i32 }> addrspace(4)* +// COMMON: %[[block_capture_addr:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }> addrspace(4)* %[[block]], i32 0, i32 3 +// COMMON: %[[r1:.*]] = load i32, i32 addrspace(4)* %[[block_capture_addr]] Index: test/CodeGenOpenCL/cl20-device-side-enqueue.cl =================================================================== --- test/CodeGenOpenCL/cl20-device-side-enqueue.cl +++ test/CodeGenOpenCL/cl20-device-side-enqueue.cl @@ -7,7 +7,7 @@ typedef struct {int a;} ndrange_t; // N.B. The check here only exists to set BL_GLOBAL -// 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)*) +// COMMON: @block_G = addrspace(1) constant void (i8 addrspace(3)*) addrspace(4)* addrspacecast (void (i8 addrspace(3)*) addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } 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) { @@ -27,9 +27,10 @@ // COMMON: [[NDR:%[a-z0-9]+]] = alloca %struct.ndrange_t, align 4 // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags - // COMMON: [[BL:%[0-9]+]] = bitcast <{ i8*, i32, i32, i8*, %struct.__block_descriptor addrspace(2)*, i32{{.*}}, i32{{.*}}, i32{{.*}} }>* %block to void ()* + // B32: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32, i32 addrspace(1)* }>* %block to void ()* + // B64: [[BL:%[0-9]+]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 addrspace(1)*, i32 addrspace(1)*, i32 }>* %block to void ()* // 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]], %struct.ndrange_t* byval [[NDR]]{{(.[0-9]+)?}}, i8 addrspace(4)* [[BL_I8]]) + // COMMON: call i32 @__enqueue_kernel_basic(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* byval [[NDR]]{{([0-9]+)?}}, i8 addrspace(4)* [[BL_I8]]) enqueue_kernel(default_queue, flags, ndrange, ^(void) { a[i] = b[i]; @@ -39,7 +40,7 @@ // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags // 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:%[0-9]+]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32{{.*}}, i32{{.*}}, i32{{.*}} }>* %block3 to void ()* // 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]], %struct.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, @@ -52,11 +53,11 @@ // B32: %[[TMP:.*]] = alloca [1 x i32] // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0 // B32: store i32 256, i32* %[[TMP1]], align 4 - // B32: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{(.[0-9]+)?}}, 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* %[[TMP1]]) + // B32: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32* %[[TMP1]]) // B64: %[[TMP:.*]] = alloca [1 x i64] // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0 // B64: store i64 256, i64* %[[TMP1]], align 8 - // B64: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{(.[0-9]+)?}}, 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* %[[TMP1]]) + // B64: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i64* %[[TMP1]]) enqueue_kernel(default_queue, flags, ndrange, ^(local void *p) { return; @@ -68,11 +69,11 @@ // B32: %[[TMP:.*]] = alloca [1 x i32] // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0 // B32: store i32 %{{.*}}, i32* %[[TMP1]], align 4 - // B32: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{(.[0-9]+)?}}, 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* %[[TMP1]]) + // B32: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32* %[[TMP1]]) // B64: %[[TMP:.*]] = alloca [1 x i64] // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0 // B64: store i64 %{{.*}}, i64* %[[TMP1]], align 8 - // B64: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{(.[0-9]+)?}}, 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* %[[TMP1]]) + // B64: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i64* %[[TMP1]]) enqueue_kernel(default_queue, flags, ndrange, ^(local void *p) { return; @@ -87,11 +88,11 @@ // B32: %[[TMP:.*]] = alloca [1 x i32] // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0 // B32: store i32 256, i32* %[[TMP1]], align 4 - // B32: call i32 @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.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* %[[TMP1]]) + // B32: call i32 @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}} [[WAIT_EVNT]], %opencl.clk_event_t{{.*}} [[EVNT]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32* %[[TMP1]]) // B64: %[[TMP:.*]] = alloca [1 x i64] // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0 // B64: store i64 256, i64* %[[TMP1]], align 8 - // B64: call i32 @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.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* %[[TMP1]]) + // B64: call i32 @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}} [[WAIT_EVNT]], %opencl.clk_event_t{{.*}} [[EVNT]], i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i64* %[[TMP1]]) enqueue_kernel(default_queue, flags, ndrange, 2, event_wait_list2, &clk_event, ^(local void *p) { return; @@ -106,11 +107,11 @@ // B32: %[[TMP:.*]] = alloca [1 x i32] // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0 // B32: store i32 %{{.*}}, i32* %[[TMP1]], align 4 - // B32: call i32 @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.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* %[[TMP1]]) + // B32: call i32 @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.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 ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32* %[[TMP1]]) // B64: %[[TMP:.*]] = alloca [1 x i64] // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0 // B64: store i64 %{{.*}}, i64* %[[TMP1]], align 8 - // B64: call i32 @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.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* %[[TMP1]]) + // B64: call i32 @__enqueue_kernel_events_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.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 ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i64* %[[TMP1]]) enqueue_kernel(default_queue, flags, ndrange, 2, event_wait_list2, &clk_event, ^(local void *p) { return; @@ -123,11 +124,11 @@ // B32: %[[TMP:.*]] = alloca [1 x i32] // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0 // B32: store i32 %{{.*}}, i32* %[[TMP1]], align 4 - // B32: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{(.[0-9]+)?}}, 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* %[[TMP1]]) + // B32: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32* %[[TMP1]]) // B64: %[[TMP:.*]] = alloca [1 x i64] // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0 // B64: store i64 %{{.*}}, i64* %[[TMP1]], align 8 - // B64: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{(.[0-9]+)?}}, 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* %[[TMP1]]) + // B64: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i64* %[[TMP1]]) enqueue_kernel(default_queue, flags, ndrange, ^(local void *p) { return; @@ -143,7 +144,7 @@ // B32: store i32 2, i32* %[[TMP2]], align 4 // B32: %[[TMP3:.*]] = getelementptr [3 x i32], [3 x i32]* %[[TMP]], i32 0, i32 2 // B32: store i32 4, i32* %[[TMP3]], align 4 - // B32: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{(.[0-9]+)?}}, 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 3, i32* %[[TMP1]]) + // B32: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 3, i32* %[[TMP1]]) // B64: %[[TMP:.*]] = alloca [3 x i64] // B64: %[[TMP1:.*]] = getelementptr [3 x i64], [3 x i64]* %[[TMP]], i32 0, i32 0 // B64: store i64 1, i64* %[[TMP1]], align 8 @@ -151,7 +152,7 @@ // B64: store i64 2, i64* %[[TMP2]], align 8 // B64: %[[TMP3:.*]] = getelementptr [3 x i64], [3 x i64]* %[[TMP]], i32 0, i32 2 // B64: store i64 4, i64* %[[TMP3]], align 8 - // B64: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{(.[0-9]+)?}}, 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 3, i64* %[[TMP1]]) + // B64: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 3, i64* %[[TMP1]]) enqueue_kernel(default_queue, flags, ndrange, ^(local void *p1, local void *p2, local void *p3) { return; @@ -163,11 +164,11 @@ // B32: %[[TMP:.*]] = alloca [1 x i32] // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0 // B32: store i32 0, i32* %[[TMP1]], align 4 - // B32: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{(.[0-9]+)?}}, 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* %[[TMP1]]) + // B32: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i32* %[[TMP1]]) // B64: %[[TMP:.*]] = alloca [1 x i64] // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0 // B64: store i64 4294967296, i64* %[[TMP1]], align 8 - // B64: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{(.[0-9]+)?}}, 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* %[[TMP1]]) + // B64: call i32 @__enqueue_kernel_vaargs(%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* @__block_literal_global{{(.[0-9]+)?}} to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1, i64* %[[TMP1]]) enqueue_kernel(default_queue, flags, ndrange, ^(local void *p) { return; @@ -176,27 +177,27 @@ // 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 () 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 + // COMMON: store void () addrspace(4)* addrspacecast (void () addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } 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)*) 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 + // COMMON: store void (i8 addrspace(3)*) addrspace(4)* addrspacecast (void (i8 addrspace(3)*) addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } 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 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)*)) + // COMMON: call i32 @__get_kernel_work_group_size_impl(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } 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 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)*)) + // COMMON: call i32 @__get_kernel_work_group_size_impl(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } 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 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)*)) + // COMMON: call i32 @__get_kernel_preferred_work_group_multiple_impl(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } 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 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)*)) + // COMMON: call i32 @__get_kernel_preferred_work_group_multiple_impl(i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* [[BL_GLOBAL]] to i8 addrspace(1)*) to i8 addrspace(4)*)) size = get_kernel_preferred_work_group_size_multiple(block_G); - // COMMON: call i32 @__get_kernel_max_sub_group_size_for_ndrange_impl(%struct.ndrange_t* {{.*}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* {{.*}} to i8 addrspace(1)*) to i8 addrspace(4)*)) + // COMMON: call i32 @__get_kernel_max_sub_group_size_for_ndrange_impl(%struct.ndrange_t* {{.*}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* {{.*}} to i8 addrspace(1)*) to i8 addrspace(4)*)) size = get_kernel_max_sub_group_size_for_ndrange(ndrange, ^(){}); - // COMMON: call i32 @__get_kernel_sub_group_count_for_ndrange_impl(%struct.ndrange_t* {{.*}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor addrspace(2)* } addrspace(1)* {{.*}} to i8 addrspace(1)*) to i8 addrspace(4)*)) + // COMMON: call i32 @__get_kernel_sub_group_count_for_ndrange_impl(%struct.ndrange_t* {{.*}}, i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32, i8 addrspace(4)* } addrspace(1)* {{.*}} to i8 addrspace(1)*) to i8 addrspace(4)*)) size = get_kernel_sub_group_count_for_ndrange(ndrange, ^(){}); }