CGOpenMPRuntimeAMDGCN.cpp
2.24 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
//===-- CGOpenMPRuntimeAMDGCN.cpp - Interface to OpenMP AMDGCN 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
// AMDGCN targets from generalized CGOpenMPRuntimeGPU class.
//
//===----------------------------------------------------------------------===//
#include "CGOpenMPRuntimeAMDGCN.h"
#include "CGOpenMPRuntimeGPU.h"
#include "CodeGenFunction.h"
#include "clang/AST/Attr.h"
#include "clang/AST/DeclOpenMP.h"
#include "clang/AST/StmtOpenMP.h"
#include "clang/AST/StmtVisitor.h"
#include "clang/Basic/Cuda.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/IR/IntrinsicsAMDGPU.h"
using namespace clang;
using namespace CodeGen;
using namespace llvm::omp;
CGOpenMPRuntimeAMDGCN::CGOpenMPRuntimeAMDGCN(CodeGenModule &CGM)
: CGOpenMPRuntimeGPU(CGM) {
if (!CGM.getLangOpts().OpenMPIsDevice)
llvm_unreachable("OpenMP AMDGCN can only handle device code.");
}
llvm::Value *CGOpenMPRuntimeAMDGCN::getGPUWarpSize(CodeGenFunction &CGF) {
CGBuilderTy &Bld = CGF.Builder;
// return constant compile-time target-specific warp size
unsigned WarpSize = CGF.getTarget().getGridValue(llvm::omp::GV_Warp_Size);
return Bld.getInt32(WarpSize);
}
llvm::Value *CGOpenMPRuntimeAMDGCN::getGPUThreadID(CodeGenFunction &CGF) {
CGBuilderTy &Bld = CGF.Builder;
llvm::Function *F =
CGF.CGM.getIntrinsic(llvm::Intrinsic::amdgcn_workitem_id_x);
return Bld.CreateCall(F, llvm::None, "nvptx_tid");
}
llvm::Value *CGOpenMPRuntimeAMDGCN::getGPUNumThreads(CodeGenFunction &CGF) {
CGBuilderTy &Bld = CGF.Builder;
llvm::Module *M = &CGF.CGM.getModule();
const char *LocSize = "__ockl_get_local_size";
llvm::Function *F = M->getFunction(LocSize);
if (!F) {
F = llvm::Function::Create(
llvm::FunctionType::get(CGF.Int64Ty, {CGF.Int32Ty}, false),
llvm::GlobalVariable::ExternalLinkage, LocSize, &CGF.CGM.getModule());
}
return Bld.CreateTrunc(
Bld.CreateCall(F, {Bld.getInt32(0)}, "nvptx_num_threads"), CGF.Int32Ty);
}