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

[OpenMP] Further adjustments of nvptx runtime functions 

Pass in default value of 1, similar to previous commit r318836.

Differential Revision: https://reviews.llvm.org/D41012

llvm-svn: 321486
This commit is contained in:
Jonas Hahnfeld 2017-12-27 10:39:56 +00:00
parent 4452100a5a
commit fa059ba59e
3 changed files with 24 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
View File

@ -33,10 +33,11 @@ enum OpenMPRTLFunctionNVPTX {
/// \brief Call to void __kmpc_spmd_kernel_deinit();
OMPRTL_NVPTX__kmpc_spmd_kernel_deinit,
/// \brief Call to void __kmpc_kernel_prepare_parallel(void
/// *outlined_function, void ***args, kmp_int32 nArgs);
/// *outlined_function, void ***args, kmp_int32 nArgs, int16_t
/// IsOMPRuntimeInitialized);
OMPRTL_NVPTX__kmpc_kernel_prepare_parallel,
/// \brief Call to bool __kmpc_kernel_parallel(void **outlined_function, void
/// ***args);
/// ***args, int16_t IsOMPRuntimeInitialized);
OMPRTL_NVPTX__kmpc_kernel_parallel,
/// \brief Call to void __kmpc_kernel_end_parallel();
OMPRTL_NVPTX__kmpc_kernel_end_parallel,
@ -521,7 +522,9 @@ void CGOpenMPRuntimeNVPTX::emitWorkerLoop(CodeGenFunction &CGF,
// Set up shared arguments
Address SharedArgs =
CGF.CreateDefaultAlignTempAlloca(CGF.Int8PtrPtrTy, "shared_args");
llvm::Value *Args[] = {WorkFn.getPointer(), SharedArgs.getPointer()};
// TODO: Optimize runtime initialization and pass in correct value.
llvm::Value *Args[] = {WorkFn.getPointer(), SharedArgs.getPointer(),
/*RequiresOMPRuntime=*/Bld.getInt16(1)};
llvm::Value *Ret = CGF.EmitRuntimeCall(
createNVPTXRuntimeFunction(OMPRTL_NVPTX__kmpc_kernel_parallel), Args);
Bld.CreateStore(Bld.CreateZExt(Ret, CGF.Int8Ty), ExecStatus);
@ -637,18 +640,21 @@ CGOpenMPRuntimeNVPTX::createNVPTXRuntimeFunction(unsigned Function) {
}
case OMPRTL_NVPTX__kmpc_kernel_prepare_parallel: {
/// Build void __kmpc_kernel_prepare_parallel(
/// void *outlined_function, void ***args, kmp_int32 nArgs);
/// void *outlined_function, void ***args, kmp_int32 nArgs, int16_t
/// IsOMPRuntimeInitialized);
llvm::Type *TypeParams[] = {CGM.Int8PtrTy,
CGM.Int8PtrPtrTy->getPointerTo(0), CGM.Int32Ty};
CGM.Int8PtrPtrTy->getPointerTo(0), CGM.Int32Ty,
CGM.Int16Ty};
llvm::FunctionType *FnTy =
llvm::FunctionType::get(CGM.VoidTy, TypeParams, /*isVarArg*/ false);
RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_kernel_prepare_parallel");
break;
}
case OMPRTL_NVPTX__kmpc_kernel_parallel: {
/// Build bool __kmpc_kernel_parallel(void **outlined_function, void ***args);
/// Build bool __kmpc_kernel_parallel(void **outlined_function, void
/// ***args, int16_t IsOMPRuntimeInitialized);
llvm::Type *TypeParams[] = {CGM.Int8PtrPtrTy,
CGM.Int8PtrPtrTy->getPointerTo(0)};
CGM.Int8PtrPtrTy->getPointerTo(0), CGM.Int16Ty};
llvm::Type *RetTy = CGM.getTypes().ConvertType(CGM.getContext().BoolTy);
llvm::FunctionType *FnTy =
llvm::FunctionType::get(RetTy, TypeParams, /*isVarArg*/ false);
@ -949,8 +955,10 @@ void CGOpenMPRuntimeNVPTX::emitGenericParallelCall(
CGF.CreateDefaultAlignTempAlloca(CGF.VoidPtrPtrTy,
"shared_args");
llvm::Value *SharedArgsPtr = SharedArgs.getPointer();
// TODO: Optimize runtime initialization and pass in correct value.
llvm::Value *Args[] = {ID, SharedArgsPtr,
Bld.getInt32(CapturedVars.size())};
Bld.getInt32(CapturedVars.size()),
/*RequiresOMPRuntime=*/Bld.getInt16(1)};
CGF.EmitRuntimeCall(
createNVPTXRuntimeFunction(OMPRTL_NVPTX__kmpc_kernel_prepare_parallel),
@ -970,9 +978,10 @@ void CGOpenMPRuntimeNVPTX::emitGenericParallelCall(
Idx++;
}
} else {
llvm::Value *Args[] = {ID,
llvm::ConstantPointerNull::get(CGF.VoidPtrPtrTy->getPointerTo(0)),
/*nArgs=*/Bld.getInt32(0)};
// TODO: Optimize runtime initialization and pass in correct value.
llvm::Value *Args[] = {
ID, llvm::ConstantPointerNull::get(CGF.VoidPtrPtrTy->getPointerTo(0)),
/*nArgs=*/Bld.getInt32(0), /*RequiresOMPRuntime=*/Bld.getInt16(1)};
CGF.EmitRuntimeCall(
createNVPTXRuntimeFunction(OMPRTL_NVPTX__kmpc_kernel_prepare_parallel),
Args);

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

@ -24,7 +24,7 @@ void test_ds(){
// CK1: define internal void @__omp_offloading_{{.*}}test_ds{{.*}}worker() [[ATTR1:#.*]] {
// CK1: [[SHAREDARGS:%.+]] = alloca i8**
// CK1: call i1 @__kmpc_kernel_parallel(i8** %work_fn, i8*** [[SHAREDARGS]])
// CK1: call i1 @__kmpc_kernel_parallel(i8** %work_fn, i8*** [[SHAREDARGS]], i16 1)
// CK1: [[SHARGSTMP:%.+]] = load i8**, i8*** [[SHAREDARGS]]
// CK1: call void @__omp_outlined___wrapper{{.*}}({{.*}}, i8** [[SHARGSTMP]])
@ -32,7 +32,7 @@ void test_ds(){
// CK1: {{.*}}define void @__omp_offloading{{.*}}test_ds{{.*}}() [[ATTR2:#.*]] {
// CK1: [[SHAREDARGS1:%.+]] = alloca i8**
// CK1: call void @__kmpc_kernel_prepare_parallel({{.*}}, i8*** [[SHAREDARGS1]], i32 1)
// CK1: call void @__kmpc_kernel_prepare_parallel({{.*}}, i8*** [[SHAREDARGS1]], i32 1, i16 1)
// CK1: [[SHARGSTMP1:%.+]] = load i8**, i8*** [[SHAREDARGS1]]
// CK1: [[SHARGSTMP2:%.+]] = getelementptr inbounds i8*, i8** [[SHARGSTMP1]]
// CK1: [[SHAREDVAR:%.+]] = bitcast i32* {{.*}} to i8*

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

@ -60,7 +60,7 @@ int bar(int n){
//
// CHECK: [[AWAIT_WORK]]
// CHECK: call void @llvm.nvvm.barrier0()
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]], i8*** %shared_args)
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]], i8*** %shared_args, i16 1)
// CHECK: [[KPRB:%.+]] = zext i1 [[KPR]] to i8
// store i8 [[KPRB]], i8* [[OMP_EXEC_STATUS]], align 1
// CHECK: [[WORK:%.+]] = load i8*, i8** [[OMP_WORK_FN]],
@ -148,7 +148,7 @@ int bar(int n){
//
// CHECK: [[AWAIT_WORK]]
// CHECK: call void @llvm.nvvm.barrier0()
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]], i8*** %shared_args)
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]], i8*** %shared_args, i16 1)
// CHECK: [[KPRB:%.+]] = zext i1 [[KPR]] to i8
// store i8 [[KPRB]], i8* [[OMP_EXEC_STATUS]], align 1
// CHECK: [[WORK:%.+]] = load i8*, i8** [[OMP_WORK_FN]],