yaxunl created this revision. Herald added subscribers: nhaehnle, wdng. There is an incoming change in LLVM allowing alloca to return a private pointer which does not pointing to address space 0:
https://reviews.llvm.org/D31042#03b9d490 After this change is committed, alloca will return a pointer pointing to an address space specified by the data layout (so called alloca addr space, which is the last component of the data layout, e.g. A5 indicating alloca address space is 5). A data layout not specifying alloca address space will assume it is 0, therefore keeping the original behaviour. Clang codegen needs to make corresponding changes to account for the API change of alloca. The change is straightforward. Basically when creating alloca, use the alloca address space specified by the data layout. For OpenCL, the private address space qualifier is 0 in AST. Before this change, 0 address space qualifier is always mapped to target address space 0. As now target private address space is specified by alloca address space in data layout, address space qualifier 0 needs to be mapped to alloca addr space specified by the data layout. This change has no impact on targets whose alloca addr space is 0. https://reviews.llvm.org/D31404 Files: include/clang/AST/ASTContext.h lib/AST/ASTContext.cpp lib/Basic/Targets.cpp lib/CodeGen/CGBuiltin.cpp lib/CodeGen/CGCall.cpp lib/CodeGen/CGDecl.cpp lib/CodeGen/CGExpr.cpp lib/CodeGen/CGObjCGNU.cpp test/CodeGenOpenCL/address-spaces.cl test/CodeGenOpenCL/amdgpu-env-amdgiz.cl test/CodeGenOpenCL/vla.cl
Index: test/CodeGenOpenCL/vla.cl =================================================================== --- test/CodeGenOpenCL/vla.cl +++ test/CodeGenOpenCL/vla.cl @@ -1,18 +1,26 @@ -// RUN: %clang_cc1 -emit-llvm -triple "spir-unknown-unknown" -O0 -cl-std=CL2.0 -o - %s | FileCheck %s +// RUN: %clang_cc1 -emit-llvm -triple "spir-unknown-unknown" -O0 -cl-std=CL2.0 -o - %s | FileCheck -check-prefixes=CHECK,SPIR %s +// RUN: %clang_cc1 -emit-llvm -triple amdgcn-amd-amdhsa-opencl -O0 -cl-std=CL2.0 -o - %s | FileCheck -check-prefixes=CHECK,SPIR %s +// RUN: %clang_cc1 -emit-llvm -triple amdgcn-amd-amdhsa-amdgizcl -O0 -cl-std=CL2.0 -o - %s | FileCheck -check-prefixes=CHECK,GIZ %s constant int sz0 = 5; -// CHECK: @sz0 = addrspace(2) constant i32 5 +// SPIR: @sz0 = addrspace(2) constant i32 5 +// GIZ: @sz0 = addrspace(4) constant i32 5 const global int sz1 = 16; // CHECK: @sz1 = addrspace(1) constant i32 16 const constant int sz2 = 8; -// CHECK: @sz2 = addrspace(2) constant i32 8 +// SPIR: @sz2 = addrspace(2) constant i32 8 +// GIZ: @sz2 = addrspace(4) constant i32 8 // CHECK: @testvla.vla2 = internal addrspace(3) global [8 x i16] undef kernel void testvla() { int vla0[sz0]; -// CHECK: %vla0 = alloca [5 x i32] +// SPIR: %vla0 = alloca [5 x i32] +// SPIR-NOT: %vla0 = alloca [5 x i32]{{.*}}addrspace +// GIZ: %vla0 = alloca [5 x i32]{{.*}}addrspace(5) char vla1[sz1]; -// CHECK: %vla1 = alloca [16 x i8] +// SPIR: %vla1 = alloca [16 x i8] +// SPIR-NOT: %vla1 = alloca [16 x i8]{{.*}}addrspace +// GIZ: %vla1 = alloca [16 x i8]{{.*}}addrspace(5) local short vla2[sz2]; } Index: test/CodeGenOpenCL/amdgpu-env-amdgiz.cl =================================================================== --- test/CodeGenOpenCL/amdgpu-env-amdgiz.cl +++ test/CodeGenOpenCL/amdgpu-env-amdgiz.cl @@ -4,6 +4,6 @@ // RUN: %clang_cc1 %s -O0 -triple amdgcn---amdgizcl -emit-llvm -o - | FileCheck -check-prefix=GIZ %s // CHECK: target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64" -// GIZ: target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64" +// GIZ: target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5" void foo(void) {} Index: test/CodeGenOpenCL/address-spaces.cl =================================================================== --- test/CodeGenOpenCL/address-spaces.cl +++ test/CodeGenOpenCL/address-spaces.cl @@ -1,44 +1,57 @@ -// RUN: %clang_cc1 %s -O0 -ffake-address-space-map -emit-llvm -o - | FileCheck %s -// RUN: %clang_cc1 %s -O0 -DCL20 -cl-std=CL2.0 -ffake-address-space-map -emit-llvm -o - | FileCheck %s --check-prefix=CL20 - -// CHECK: i32* %arg +// RUN: %clang_cc1 %s -O0 -ffake-address-space-map -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK,SPIR +// RUN: %clang_cc1 %s -O0 -DCL20 -cl-std=CL2.0 -ffake-address-space-map -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20SPIR +// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-opencl -emit-llvm -o - | FileCheck --check-prefixes=CHECK,SPIR %s +// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-opencl -DCL20 -cl-std=CL2.0 -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20SPIR +// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-amdgizcl -emit-llvm -o - | FileCheck %s -check-prefixes=CHECK,GIZ +// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-amdgizcl -DCL20 -cl-std=CL2.0 -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20GIZ + +// SPIR: i32* %arg +// GIZ: i32 addrspace(5)* %arg void f__p(__private int *arg) {} // CHECK: i32 addrspace(1)* %arg void f__g(__global int *arg) {} // CHECK: i32 addrspace(3)* %arg void f__l(__local int *arg) {} -// CHECK: i32 addrspace(2)* %arg +// SPIR: i32 addrspace(2)* %arg +// GIZ: i32 addrspace(4)* %arg void f__c(__constant int *arg) {} -// CHECK: i32* %arg +// SPIR: i32* %arg +// GIZ: i32 addrspace(5)* %arg void fp(private int *arg) {} // CHECK: i32 addrspace(1)* %arg void fg(global int *arg) {} // CHECK: i32 addrspace(3)* %arg void fl(local int *arg) {} -// CHECK: i32 addrspace(2)* %arg +// SPIR: i32 addrspace(2)* %arg +// GIZ: i32 addrspace(4)* %arg void fc(constant int *arg) {} #ifdef CL20 int i; // CL20-DAG: @i = common addrspace(1) global i32 0 int *ptr; -// CL20-DAG: @ptr = common addrspace(1) global i32 addrspace(4)* null +// CL20SPIR-DAG: @ptr = common addrspace(1) global i32 addrspace(4)* null +// CL20GIZ-DAG: @ptr = common addrspace(1) global i32* null #endif -// CHECK: i32* %arg -// CL20-DAG: i32 addrspace(4)* %arg +// SPIR: i32* %arg +// GIZ: i32 addrspace(5)* %arg +// CL20SPIR-DAG: i32 addrspace(4)* %arg +// CL20GIZ-DAG: i32* %arg void f(int *arg) { int i; -// CHECK: %i = alloca i32, -// CL20-DAG: %i = alloca i32, +// SPIR: %i = alloca i32, +// GIZ: %i = alloca i32{{.*}}addrspace(5) +// CL20SPIR-DAG: %i = alloca i32, +// CL20GIZ-DAG: %i = alloca i32{{.*}}addrspace(5) #ifdef CL20 static int ii; Index: lib/CodeGen/CGObjCGNU.cpp =================================================================== --- lib/CodeGen/CGObjCGNU.cpp +++ lib/CodeGen/CGObjCGNU.cpp @@ -1330,8 +1330,8 @@ Receiver->getType(), IdTy, nullptr); // FIXME: Is this really supposed to be a dynamic alloca? - Address ObjCSuper = Address(Builder.CreateAlloca(ObjCSuperTy), - CGF.getPointerAlign()); + Address ObjCSuper = Address(Builder.CreateAlloca(CGM.getDataLayout(), + ObjCSuperTy), CGF.getPointerAlign()); Builder.CreateStore(Receiver, Builder.CreateStructGEP(ObjCSuper, 0, CharUnits::Zero())); Index: lib/CodeGen/CGExpr.cpp =================================================================== --- lib/CodeGen/CGExpr.cpp +++ lib/CodeGen/CGExpr.cpp @@ -71,7 +71,8 @@ /// block. llvm::AllocaInst *CodeGenFunction::CreateTempAlloca(llvm::Type *Ty, const Twine &Name) { - return new llvm::AllocaInst(Ty, nullptr, Name, AllocaInsertPt); + return new llvm::AllocaInst(Ty, CGM.getDataLayout().getAllocaAddrSpace(), + nullptr, Name, AllocaInsertPt); } /// CreateDefaultAlignTempAlloca - This creates an alloca with the Index: lib/CodeGen/CGDecl.cpp =================================================================== --- lib/CodeGen/CGDecl.cpp +++ lib/CodeGen/CGDecl.cpp @@ -1096,7 +1096,8 @@ llvm::Type *llvmTy = ConvertTypeForMem(elementType); // Allocate memory for the array. - llvm::AllocaInst *vla = Builder.CreateAlloca(llvmTy, elementCount, "vla"); + llvm::AllocaInst *vla = Builder.CreateAlloca(CGM.getDataLayout(), + llvmTy, elementCount, "vla"); vla->setAlignment(alignment.getQuantity()); address = Address(vla, alignment); Index: lib/CodeGen/CGCall.cpp =================================================================== --- lib/CodeGen/CGCall.cpp +++ lib/CodeGen/CGCall.cpp @@ -3715,7 +3715,8 @@ llvm::AllocaInst *AI; if (IP) { IP = IP->getNextNode(); - AI = new llvm::AllocaInst(ArgStruct, "argmem", IP); + AI = new llvm::AllocaInst(ArgStruct, + CGM.getDataLayout().getAllocaAddrSpace(), "argmem", IP); } else { AI = CreateTempAlloca(ArgStruct, "argmem"); } Index: lib/CodeGen/CGBuiltin.cpp =================================================================== --- lib/CodeGen/CGBuiltin.cpp +++ lib/CodeGen/CGBuiltin.cpp @@ -1193,7 +1193,8 @@ CGM.getContext() .toCharUnitsFromBits(TI.getSuitableAlign()) .getQuantity(); - AllocaInst *AI = Builder.CreateAlloca(Builder.getInt8Ty(), Size); + AllocaInst *AI = Builder.CreateAlloca(CGM.getDataLayout(), + Builder.getInt8Ty(), Size); AI->setAlignment(SuitableAlignmentInBytes); return RValue::get(AI); } @@ -1205,7 +1206,8 @@ unsigned AlignmentInBits = AlignmentInBitsCI->getZExtValue(); unsigned AlignmentInBytes = CGM.getContext().toCharUnitsFromBits(AlignmentInBits).getQuantity(); - AllocaInst *AI = Builder.CreateAlloca(Builder.getInt8Ty(), Size); + AllocaInst *AI = Builder.CreateAlloca(CGM.getDataLayout(), + Builder.getInt8Ty(), Size); AI->setAlignment(AlignmentInBytes); return RValue::get(AI); } Index: lib/Basic/Targets.cpp =================================================================== --- lib/Basic/Targets.cpp +++ lib/Basic/Targets.cpp @@ -2064,7 +2064,7 @@ static const char *const DataLayoutStringSIGenericIsZero = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32" "-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128" - "-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"; + "-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5"; class AMDGPUTargetInfo final : public TargetInfo { static const Builtin::Info BuiltinInfo[]; @@ -2139,6 +2139,7 @@ (IsGenericZero ? DataLayoutStringSIGenericIsZero : DataLayoutStringSIPrivateIsZero) : DataLayoutStringR600); + assert(DataLayout->getAllocaAddrSpace() == AS.Private); AddrSpaceMap = IsGenericZero ? &AMDGPUGenericIsZeroMap : &AMDGPUPrivateIsZeroMap; Index: lib/AST/ASTContext.cpp =================================================================== --- lib/AST/ASTContext.cpp +++ lib/AST/ASTContext.cpp @@ -9544,6 +9544,16 @@ return getTargetInfo().getNullPointerValue(AS); } +unsigned ASTContext::getTargetAddressSpace(unsigned AS) const { + // For OpenCL, the address space qualifier is 0 in AST. + if (AS == 0 && LangOpts.OpenCL) + return getTargetInfo().getDataLayout().getAllocaAddrSpace(); + if (AS < LangAS::Offset || AS >= LangAS::Offset + LangAS::Count) + return AS; + else + return (*AddrSpaceMap)[AS - LangAS::Offset]; +} + // Explicitly instantiate this in case a Redeclarable<T> is used from a TU that // doesn't include ASTContext.h template Index: include/clang/AST/ASTContext.h =================================================================== --- include/clang/AST/ASTContext.h +++ include/clang/AST/ASTContext.h @@ -2308,12 +2308,7 @@ return getTargetAddressSpace(Q.getAddressSpace()); } - unsigned getTargetAddressSpace(unsigned AS) const { - if (AS < LangAS::Offset || AS >= LangAS::Offset + LangAS::Count) - return AS; - else - return (*AddrSpaceMap)[AS - LangAS::Offset]; - } + unsigned getTargetAddressSpace(unsigned AS) const; /// Get target-dependent integer value for null pointer which is used for /// constant folding.
_______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits