[OpenCL] Fixes bug of missing OCL version metadata on the AMDGCN target

Added the opencl.ocl.version metadata to be emitted with amdgcn. Created a static function emitOCLVerMD which is shared between triple spir and target amdgcn.

Also added new testcases to existing test file, spir_version.cl inside test/CodeGenOpenCL.

Patch by Aaron En Ye Shi.

Differential Revision: https://reviews.llvm.org/D22424

llvm-svn: 276010
This commit is contained in:
Yaxun Liu 2016-07-19 19:39:45 +00:00
parent 633d749da7
commit f2e8ab2566
2 changed files with 42 additions and 18 deletions

View File

@ -6836,6 +6836,8 @@ public:
}
static void appendOpenCLVersionMD (CodeGen::CodeGenModule &CGM);
void AMDGPUTargetCodeGenInfo::setTargetAttributes(
const Decl *D,
llvm::GlobalValue *GV,
@ -6857,8 +6859,10 @@ void AMDGPUTargetCodeGenInfo::setTargetAttributes(
if (NumSGPR != 0)
F->addFnAttr("amdgpu_num_sgpr", llvm::utostr(NumSGPR));
}
}
appendOpenCLVersionMD(M);
}
unsigned AMDGPUTargetCodeGenInfo::getOpenCLKernelCallingConv() const {
return llvm::CallingConv::AMDGPU_KERNEL;
@ -7530,6 +7534,13 @@ void SPIRTargetCodeGenInfo::emitTargetMD(const Decl *D, llvm::GlobalValue *GV,
llvm::NamedMDNode *SPIRVerMD =
M.getOrInsertNamedMetadata("opencl.spir.version");
SPIRVerMD->addOperand(llvm::MDNode::get(Ctx, SPIRVerElts));
appendOpenCLVersionMD(CGM);
}
static void appendOpenCLVersionMD (CodeGen::CodeGenModule &CGM) {
llvm::LLVMContext &Ctx = CGM.getModule().getContext();
llvm::Type *Int32Ty = llvm::Type::getInt32Ty(Ctx);
llvm::Module &M = CGM.getModule();
// SPIR v2.0 s2.13 - The OpenCL version used by the module is stored in the
// opencl.ocl.version named metadata node.
llvm::Metadata *OCLVerElts[] = {

View File

@ -1,18 +1,31 @@
// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - | FileCheck %s --check-prefix=CL10
// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - -cl-std=CL1.2 | FileCheck %s --check-prefix=CL12
// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - -cl-std=CL2.0 | FileCheck %s --check-prefix=CL20
// RUN: %clang_cc1 %s -triple "spir64-unknown-unknown" -emit-llvm -o - | FileCheck %s --check-prefix=CL10
// RUN: %clang_cc1 %s -triple "spir64-unknown-unknown" -emit-llvm -o - -cl-std=CL1.2 | FileCheck %s --check-prefix=CL12
// RUN: %clang_cc1 %s -triple "spir64-unknown-unknown" -emit-llvm -o - -cl-std=CL2.0 | FileCheck %s --check-prefix=CL20
// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - | FileCheck %s --check-prefix=CHECK-SPIR-CL10
// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - -cl-std=CL1.2 | FileCheck %s --check-prefix=CHECK-SPIR-CL12
// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - -cl-std=CL2.0 | FileCheck %s --check-prefix=CHECK-SPIR-CL20
// RUN: %clang_cc1 %s -triple "spir64-unknown-unknown" -emit-llvm -o - | FileCheck %s --check-prefix=CHECK-SPIR-CL10
// RUN: %clang_cc1 %s -triple "spir64-unknown-unknown" -emit-llvm -o - -cl-std=CL1.2 | FileCheck %s --check-prefix=CHECK-SPIR-CL12
// RUN: %clang_cc1 %s -triple "spir64-unknown-unknown" -emit-llvm -o - -cl-std=CL2.0 | FileCheck %s --check-prefix=CHECK-SPIR-CL20
// RUN: %clang_cc1 %s -triple "amdgcn--amdhsa" -emit-llvm -o - | FileCheck %s --check-prefix=CHECK-AMDGCN-CL10
// RUN: %clang_cc1 %s -triple "amdgcn--amdhsa" -emit-llvm -o - -cl-std=CL1.2 | FileCheck %s --check-prefix=CHECK-AMDGCN-CL12
// RUN: %clang_cc1 %s -triple "amdgcn--amdhsa" -emit-llvm -o - -cl-std=CL2.0 | FileCheck %s --check-prefix=CHECK-AMDGCN-CL20
kernel void foo() {}
// CL10: !opencl.spir.version = !{[[SPIR:![0-9]+]]}
// CL10: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
// CL10: [[SPIR]] = !{i32 2, i32 0}
// CL10: [[OCL]] = !{i32 1, i32 0}
// CL12: !opencl.spir.version = !{[[SPIR:![0-9]+]]}
// CL12: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
// CL12: [[SPIR]] = !{i32 2, i32 0}
// CL12: [[OCL]] = !{i32 1, i32 2}
// CL20: !opencl.spir.version = !{[[SPIR:![0-9]+]]}
// CL20: !opencl.ocl.version = !{[[SPIR:![0-9]+]]}
// CL20: [[SPIR]] = !{i32 2, i32 0}
// CHECK-SPIR-CL10: !opencl.spir.version = !{[[SPIR:![0-9]+]]}
// CHECK-SPIR-CL10: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
// CHECK-SPIR-CL10: [[SPIR]] = !{i32 2, i32 0}
// CHECK-SPIR-CL10: [[OCL]] = !{i32 1, i32 0}
// CHECK-SPIR-CL12: !opencl.spir.version = !{[[SPIR:![0-9]+]]}
// CHECK-SPIR-CL12: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
// CHECK-SPIR-CL12: [[SPIR]] = !{i32 2, i32 0}
// CHECK-SPIR-CL12: [[OCL]] = !{i32 1, i32 2}
// CHECK-SPIR-CL20: !opencl.spir.version = !{[[SPIR:![0-9]+]]}
// CHECK-SPIR-CL20: !opencl.ocl.version = !{[[SPIR:![0-9]+]]}
// CHECK-SPIR-CL20: [[SPIR]] = !{i32 2, i32 0}
// CHECK-AMDGCN-CL10: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
// CHECK-AMDGCN-CL10: [[OCL]] = !{i32 1, i32 0}
// CHECK-AMDGCN-CL12: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
// CHECK-AMDGCN-CL12: [[OCL]] = !{i32 1, i32 2}
// CHECK-AMDGCN-CL20: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
// CHECK-AMDGCN-CL20: [[OCL]] = !{i32 2, i32 0}