Provides AMDGCN and NVPTX specific specialization of getGPUWarpSize, getGPUThreadID, and getGPUNumThreads methods. Adds tests for AMDGCN codegen for these methods in generic and simd modes. Also changes the precondition in InitTempAlloca to be slightly more permissive. Useful for AMDGCN OpenMP codegen where allocas are created with a cast to an address space. Reviewed By: ABataev Differential Revision: https://reviews.llvm.org/D84260
44 lines
1.4 KiB
C++
44 lines
1.4 KiB
C++
//===----- CGOpenMPRuntimeNVPTX.h - Interface to OpenMP NVPTX Runtimes ----===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This provides a class for OpenMP runtime code generation specialized to NVPTX
|
|
// targets from generalized CGOpenMPRuntimeGPU class.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_CLANG_LIB_CODEGEN_CGOPENMPRUNTIMENVPTX_H
|
|
#define LLVM_CLANG_LIB_CODEGEN_CGOPENMPRUNTIMENVPTX_H
|
|
|
|
#include "CGOpenMPRuntime.h"
|
|
#include "CGOpenMPRuntimeGPU.h"
|
|
#include "CodeGenFunction.h"
|
|
#include "clang/AST/StmtOpenMP.h"
|
|
|
|
namespace clang {
|
|
namespace CodeGen {
|
|
|
|
class CGOpenMPRuntimeNVPTX final : public CGOpenMPRuntimeGPU {
|
|
|
|
public:
|
|
explicit CGOpenMPRuntimeNVPTX(CodeGenModule &CGM);
|
|
|
|
/// Get the GPU warp size.
|
|
llvm::Value *getGPUWarpSize(CodeGenFunction &CGF) override;
|
|
|
|
/// Get the id of the current thread on the GPU.
|
|
llvm::Value *getGPUThreadID(CodeGenFunction &CGF) override;
|
|
|
|
/// Get the maximum number of threads in a block of the GPU.
|
|
llvm::Value *getGPUNumThreads(CodeGenFunction &CGF) override;
|
|
};
|
|
|
|
} // CodeGen namespace.
|
|
} // clang namespace.
|
|
|
|
#endif // LLVM_CLANG_LIB_CODEGEN_CGOPENMPRUNTIMENVPTX_H
|