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

[ashi1]

Summary

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.

[yaxunl]

LGTM. Thanks!

[Anastasia]

Apart from function renaming LGTM!

lib/CodeGen/TargetInfo.cpp

6839 ↗

(On Diff #64181)

Could we rename to appendOpenCLVersionMD?

[ashi1]

Revised based on Anastasia's comments. Now using new function name appendOpenCLVersionMD(

cfe/trunk/lib/CodeGen/TargetInfo.cpp

AMDGPUTargetCodeGenInfo(CodeGenTypes &CGT)
     : TargetCodeGenInfo(new DefaultABIInfo(CGT)) {}
   void setTargetAttributes(const Decl *D, llvm::GlobalValue *GV,
                            CodeGen::CodeGenModule &M) const override;
   unsigned getOpenCLKernelCallingConv() const override;
 };
 
 }
 
+static void appendOpenCLVersionMD (CodeGen::CodeGenModule &CGM);
+
 void AMDGPUTargetCodeGenInfo::setTargetAttributes(
   const Decl *D,
   llvm::GlobalValue *GV,
   CodeGen::CodeGenModule &M) const {
   const FunctionDecl *FD = dyn_cast_or_null<FunctionDecl>(D);
   if (!FD)
     return;
 
   if (const auto Attr = FD->getAttr<AMDGPUNumVGPRAttr>()) {
     llvm::Function *F = cast<llvm::Function>(GV);
     uint32_t NumVGPR = Attr->getNumVGPR();
     if (NumVGPR != 0)
       F->addFnAttr("amdgpu_num_vgpr", llvm::utostr(NumVGPR));
   }
 
   if (const auto Attr = FD->getAttr<AMDGPUNumSGPRAttr>()) {
     llvm::Function *F = cast<llvm::Function>(GV);
     unsigned NumSGPR = Attr->getNumSGPR();
     if (NumSGPR != 0)
       F->addFnAttr("amdgpu_num_sgpr", llvm::utostr(NumSGPR));
   }
-}
 
+  appendOpenCLVersionMD(M);
+}
+
 
 unsigned AMDGPUTargetCodeGenInfo::getOpenCLKernelCallingConv() const {
   return llvm::CallingConv::AMDGPU_KERNEL;
 }
 
 //===----------------------------------------------------------------------===//
 // SPARC v8 ABI Implementation.
 // Based on the SPARC Compliance Definition version 2.4.1.
void SPIRTargetCodeGenInfo::emitTargetMD(const Decl *D, llvm::GlobalValue *GV,
   // SPIR v2.0 s2.12 - The SPIR version used by the module is stored in the
   // opencl.spir.version named metadata.
   llvm::Metadata *SPIRVerElts[] = {
       llvm::ConstantAsMetadata::get(llvm::ConstantInt::get(Int32Ty, 2)),
       llvm::ConstantAsMetadata::get(llvm::ConstantInt::get(Int32Ty, 0))};
   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[] = {
       llvm::ConstantAsMetadata::get(llvm::ConstantInt::get(
           Int32Ty, CGM.getLangOpts().OpenCLVersion / 100)),
       llvm::ConstantAsMetadata::get(llvm::ConstantInt::get(
           Int32Ty, (CGM.getLangOpts().OpenCLVersion % 100) / 10))};
   llvm::NamedMDNode *OCLVerMD =

cfe/trunk/test/CodeGenOpenCL/spir_version.cl

-// 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}
 No newline at end of file