maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[OpenMP] Use the OpenMP-IR-Builder 

This is a follow up patch to use the OpenMP-IR-Builder, as discussed on
the mailing list ([1] and later) and at the US Dev Meeting'19.

[1] http://lists.flang-compiler.org/pipermail/flang-dev_lists.flang-compiler.org/2019-May/000197.html

Reviewers: kiranchandramohan, ABataev, RaviNarayanaswamy, gtbercea, grokos, sdmitriev, JonChesterfield, hfinkel, fghanim

Subscribers: ppenzin, penzn, llvm-commits, cfe-commits, jfb, guansong, bollu, hiraditya, mgorny

Tags: #clang

Differential Revision: https://reviews.llvm.org/D69922
This commit is contained in:
Johannes Doerfert 2019-11-04 23:00:36 -06:00
parent f978ea4983
commit b3c06db456
11 changed files with 73 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
clang/include/clang/Basic/LangOptions.def
View File

@ -213,6 +213,7 @@ LANGOPT(OpenMPSimd , 1, 0, "Use SIMD only OpenMP support.")
LANGOPT(OpenMPUseTLS , 1, 0, "Use TLS for threadprivates or runtime calls")
LANGOPT(OpenMPIsDevice , 1, 0, "Generate code only for OpenMP target device")
LANGOPT(OpenMPCUDAMode , 1, 0, "Generate code for OpenMP pragmas in SIMT/SPMD mode")
LANGOPT(OpenMPIRBuilder , 1, 0, "Use the experimental OpenMP-IR-Builder codegen path.")
LANGOPT(OpenMPCUDAForceFullRuntime , 1, 0, "Force to use full runtime in all constructs when offloading to CUDA devices")
LANGOPT(OpenMPCUDANumSMs , 32, 0, "Number of SMs for CUDA devices.")
LANGOPT(OpenMPCUDABlocksPerSM , 32, 0, "Number of blocks per SM for CUDA devices.")

2
clang/include/clang/Driver/Options.td
View File

@ -1656,6 +1656,8 @@ def fnoopenmp_relocatable_target : Flag<["-"], "fnoopenmp-relocatable-target">,
Group<f_Group>, Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
def fopenmp_simd : Flag<["-"], "fopenmp-simd">, Group<f_Group>, Flags<[CC1Option, NoArgumentUnused]>,
HelpText<"Emit OpenMP code only for SIMD-based constructs.">;
def fopenmp_enable_irbuilder : Flag<["-"], "fopenmp-enable-irbuilder">, Group<f_Group>, Flags<[CC1Option, NoArgumentUnused, HelpHidden]>,
HelpText<"Use the experimental OpenMP-IR-Builder codegen path.">;
def fno_openmp_simd : Flag<["-"], "fno-openmp-simd">, Group<f_Group>, Flags<[CC1Option, NoArgumentUnused]>;
def fopenmp_cuda_mode : Flag<["-"], "fopenmp-cuda-mode">, Group<f_Group>,
Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;

27
clang/lib/CodeGen/CGOpenMPRuntime.cpp
View File

@ -23,6 +23,7 @@
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/SetOperations.h"
#include "llvm/Bitcode/BitcodeReader.h"
#include "llvm/Frontend/OpenMP/OMPIRBuilder.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/Value.h"
@ -3481,6 +3482,29 @@ void CGOpenMPRuntime::getDefaultScheduleAndChunk(
void CGOpenMPRuntime::emitBarrierCall(CodeGenFunction &CGF, SourceLocation Loc,
OpenMPDirectiveKind Kind, bool EmitChecks,
bool ForceSimpleCall) {
// Check if we should use the OMPBuilder
auto *OMPRegionInfo =
dyn_cast_or_null<CGOpenMPRegionInfo>(CGF.CapturedStmtInfo);
llvm::OpenMPIRBuilder *OMPBuilder = CGF.CGM.getOpenMPIRBuilder();
if (OMPBuilder) {
// TODO: Move cancelation point handling into the IRBuilder.
if (EmitChecks && !ForceSimpleCall && OMPRegionInfo &&
OMPRegionInfo->hasCancel() && CGF.Builder.GetInsertBlock()) {
CGBuilderTy::InsertPointGuard IPG(CGF.Builder);
llvm::BasicBlock *ExitBB = CGF.createBasicBlock(
".cancel.exit", CGF.Builder.GetInsertBlock()->getParent());
OMPBuilder->setCancellationBlock(ExitBB);
CGF.Builder.SetInsertPoint(ExitBB);
CodeGenFunction::JumpDest CancelDestination =
CGF.getOMPCancelDestination(OMPRegionInfo->getDirectiveKind());
CGF.EmitBranchThroughCleanup(CancelDestination);
}
auto IP = OMPBuilder->CreateBarrier(CGF.Builder, Kind, ForceSimpleCall,
EmitChecks);
CGF.Builder.restoreIP(IP);
return;
}
if (!CGF.HaveInsertPoint())
return;
// Build call __kmpc_cancel_barrier(loc, thread_id);
@ -3490,8 +3514,7 @@ void CGOpenMPRuntime::emitBarrierCall(CodeGenFunction &CGF, SourceLocation Loc,
// thread_id);
llvm::Value *Args[] = {emitUpdateLocation(CGF, Loc, Flags),
getThreadID(CGF, Loc)};
if (auto *OMPRegionInfo =
dyn_cast_or_null<CGOpenMPRegionInfo>(CGF.CapturedStmtInfo)) {
if (OMPRegionInfo) {
if (!ForceSimpleCall && OMPRegionInfo->hasCancel()) {
llvm::Value *Result = CGF.EmitRuntimeCall(
createRuntimeFunction(OMPRTL__kmpc_cancel_barrier), Args);

1
clang/lib/CodeGen/CMakeLists.txt
View File

@ -5,6 +5,7 @@ set(LLVM_LINK_COMPONENTS
Core
Coroutines
Coverage
FrontendOpenMP
IPO
IRReader
AggressiveInstCombine

9
clang/lib/CodeGen/CodeGenModule.cpp
View File

@ -47,6 +47,7 @@
#include "llvm/ADT/StringSwitch.h"
#include "llvm/ADT/Triple.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Frontend/OpenMP/OMPIRBuilder.h"
#include "llvm/IR/CallingConv.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Intrinsics.h"
@ -218,6 +219,14 @@ void CodeGenModule::createOpenMPRuntime() {
OpenMPRuntime.reset(new CGOpenMPRuntime(*this));
break;
}
// The OpenMP-IR-Builder should eventually replace the above runtime codegens
// but we are not there yet so they both reside in CGModule for now and the
// OpenMP-IR-Builder is opt-in only.
if (LangOpts.OpenMPIRBuilder) {
OMPBuilder.reset(new llvm::OpenMPIRBuilder(TheModule));
OMPBuilder->initialize();
}
}
void CodeGenModule::createCUDARuntime() {

5
clang/lib/CodeGen/CodeGenModule.h
View File

@ -44,6 +44,7 @@ class GlobalValue;
class DataLayout;
class FunctionType;
class LLVMContext;
class OpenMPIRBuilder;
class IndexedInstrProfReader;
}
@ -321,6 +322,7 @@ private:
std::unique_ptr<CGObjCRuntime> ObjCRuntime;
std::unique_ptr<CGOpenCLRuntime> OpenCLRuntime;
std::unique_ptr<CGOpenMPRuntime> OpenMPRuntime;
std::unique_ptr<llvm::OpenMPIRBuilder> OMPBuilder;
std::unique_ptr<CGCUDARuntime> CUDARuntime;
std::unique_ptr<CGDebugInfo> DebugInfo;
std::unique_ptr<ObjCEntrypoints> ObjCData;
@ -587,6 +589,9 @@ public:
return *OpenMPRuntime;
}
/// Return a pointer to the configured OpenMPIRBuilder, if any.
llvm::OpenMPIRBuilder *getOpenMPIRBuilder() { return OMPBuilder.get(); }
/// Return a reference to the configured CUDA runtime.
CGCUDARuntime &getCUDARuntime() {
assert(CUDARuntime != nullptr);

1
clang/lib/Driver/ToolChains/Clang.cpp
View File

@ -4955,6 +4955,7 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
CmdArgs.push_back("-fnoopenmp-use-tls");
Args.AddLastArg(CmdArgs, options::OPT_fopenmp_simd,
options::OPT_fno_openmp_simd);
Args.AddAllArgs(CmdArgs, options::OPT_fopenmp_enable_irbuilder);
Args.AddAllArgs(CmdArgs, options::OPT_fopenmp_version_EQ);
Args.AddAllArgs(CmdArgs, options::OPT_fopenmp_cuda_number_of_sm_EQ);
Args.AddAllArgs(CmdArgs, options::OPT_fopenmp_cuda_blocks_per_sm_EQ);

2
clang/lib/Frontend/CompilerInvocation.cpp
View File

@ -3014,6 +3014,8 @@ static void ParseLangArgs(LangOptions &Opts, ArgList &Args, InputKind IK,
Opts.OpenMP && !Args.hasArg(options::OPT_fnoopenmp_use_tls);
Opts.OpenMPIsDevice =
Opts.OpenMP && Args.hasArg(options::OPT_fopenmp_is_device);
Opts.OpenMPIRBuilder =
Opts.OpenMP && Args.hasArg(options::OPT_fopenmp_enable_irbuilder);
bool IsTargetSpecified =
Opts.OpenMPIsDevice || Args.hasArg(options::OPT_fopenmp_targets_EQ);

6
clang/test/Driver/fopenmp.c
View File

@ -124,6 +124,12 @@
// CHECK-LD-STATIC-IOMP5-NO-BDYNAMIC: "-{{B?}}static" {{.*}} "-liomp5"
// CHECK-LD-STATIC-IOMP5-NO-BDYNAMIC-NOT: "-Bdynamic"
//
// RUN: %clang -target x86_64-linux-gnu -fopenmp -fopenmp-enable-irbuilder -c %s -### 2>&1 | FileCheck %s --check-prefix=CHECK-CC1-OPENMPIRBUILDER
//
// CHECK-CC1-OPENMPIRBUILDER: "-cc1"
// CHECK-CC1-OPENMPIRBUILDER-SAME: "-fopenmp"
// CHECK-CC1-OPENMPIRBUILDER-SAME: "-fopenmp-enable-irbuilder"
//
// We'd like to check that the default is sane, but until we have the ability
// to *always* semantically analyze OpenMP without always generating runtime
// calls (in the event of an unsupported runtime), we don't have a good way to

19
clang/test/OpenMP/barrier_codegen.cpp
View File

@ -1,6 +1,14 @@
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefixes=CHECK,CLANGCG
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK,CLANGCG
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -fopenmp-enable-irbuilder -emit-llvm %s -o - | FileCheck %s --check-prefixes=CHECK,IRBUILDER
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -fopenmp-enable-irbuilder -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -fopenmp-enable-irbuilder -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK,IRBUILDER
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -fopenmp-enable-irbuilder -mllvm -openmp-ir-builder-optimistic-attributes -emit-llvm %s -o - | FileCheck %s --check-prefixes=CHECK,IRBUILDER_OPT
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -fopenmp-enable-irbuilder -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -fopenmp-enable-irbuilder -mllvm -openmp-ir-builder-optimistic-attributes -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK,IRBUILDER_OPT
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple x86_64-unknown-unknown -emit-pch -o %t %s
@ -34,6 +42,13 @@ int main(int argc, char **argv) {
return tmain(argc) + tmain(argv[0][0]) + a;
}
// CLANGCG: declare i32 @__kmpc_global_thread_num(%struct.ident_t*)
// CLANGCG-NOT: #
// IRBUILDER: ; Function Attrs: nounwind
// IRBUILDER-NEXT: declare i32 @__kmpc_global_thread_num(%struct.ident_t*) #
// IRBUILDER_OPT: ; Function Attrs: nofree nosync nounwind readonly
// IRBUILDER_OPT-NEXT: declare i32 @__kmpc_global_thread_num(%struct.ident_t*) #
// CHECK: define {{.+}} [[TMAIN_INT]](
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT_T]]* [[LOC]])
// CHECK: call void @__kmpc_barrier([[IDENT_T]]* [[EXPLICIT_BARRIER_LOC]], i32 [[GTID]])

4
clang/test/OpenMP/cancel_codegen.cpp
View File

@ -2,6 +2,10 @@
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple x86_64-apple-darwin13.4.0 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -std=c++11 -include-pch %t -fsyntax-only -verify %s -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - | FileCheck %s
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-enable-irbuilder -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -fopenmp-enable-irbuilder -x c++ -std=c++11 -triple x86_64-apple-darwin13.4.0 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -fopenmp-enable-irbuilder -std=c++11 -include-pch %t -fsyntax-only -verify %s -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - | FileCheck %s
// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - %s | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple x86_64-apple-darwin13.4.0 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -std=c++11 -include-pch %t -fsyntax-only -verify %s -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s