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

[OpenMP][NFC] Remove unused (always fixed) arguments 

There are various runtime calls in the device runtime with unused, or
always fixed, arguments. This is bad for all sorts of reasons. Clean up
two before as we match them in OpenMPOpt now.

Reviewed By: JonChesterfield

Differential Revision: https://reviews.llvm.org/D83268
This commit is contained in:
Johannes Doerfert 2020-07-06 19:13:37 -05:00
parent 256e4d46a6
commit c98699582a
9 changed files with 28 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
View File

@ -38,11 +38,9 @@ enum OpenMPRTLFunctionNVPTX {
/// Call to void __kmpc_spmd_kernel_deinit_v2(int16_t RequiresOMPRuntime);
OMPRTL_NVPTX__kmpc_spmd_kernel_deinit_v2,
/// Call to void __kmpc_kernel_prepare_parallel(void
/// *outlined_function, int16_t
/// IsOMPRuntimeInitialized);
/// *outlined_function);
OMPRTL_NVPTX__kmpc_kernel_prepare_parallel,
/// Call to bool __kmpc_kernel_parallel(void **outlined_function,
/// int16_t IsOMPRuntimeInitialized);
/// Call to bool __kmpc_kernel_parallel(void **outlined_function);
OMPRTL_NVPTX__kmpc_kernel_parallel,
/// Call to void __kmpc_kernel_end_parallel();
OMPRTL_NVPTX__kmpc_kernel_end_parallel,
@ -1466,8 +1464,7 @@ void CGOpenMPRuntimeNVPTX::emitWorkerLoop(CodeGenFunction &CGF,
CGF.InitTempAlloca(WorkFn, llvm::Constant::getNullValue(CGF.Int8PtrTy));
// TODO: Optimize runtime initialization and pass in correct value.
llvm::Value *Args[] = {WorkFn.getPointer(),
/*RequiresOMPRuntime=*/Bld.getInt16(1)};
llvm::Value *Args[] = {WorkFn.getPointer()};
llvm::Value *Ret = CGF.EmitRuntimeCall(
createNVPTXRuntimeFunction(OMPRTL_NVPTX__kmpc_kernel_parallel), Args);
Bld.CreateStore(Bld.CreateZExt(Ret, CGF.Int8Ty), ExecStatus);
@ -1595,17 +1592,16 @@ CGOpenMPRuntimeNVPTX::createNVPTXRuntimeFunction(unsigned Function) {
}
case OMPRTL_NVPTX__kmpc_kernel_prepare_parallel: {
/// Build void __kmpc_kernel_prepare_parallel(
/// void *outlined_function, int16_t IsOMPRuntimeInitialized);
llvm::Type *TypeParams[] = {CGM.Int8PtrTy, CGM.Int16Ty};
/// void *outlined_function);
llvm::Type *TypeParams[] = {CGM.Int8PtrTy};
auto *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,
/// int16_t IsOMPRuntimeInitialized);
llvm::Type *TypeParams[] = {CGM.Int8PtrPtrTy, CGM.Int16Ty};
/// Build bool __kmpc_kernel_parallel(void **outlined_function);
llvm::Type *TypeParams[] = {CGM.Int8PtrPtrTy};
llvm::Type *RetTy = CGM.getTypes().ConvertType(CGM.getContext().BoolTy);
auto *FnTy =
llvm::FunctionType::get(RetTy, TypeParams, /*isVarArg*/ false);
@ -2569,7 +2565,7 @@ void CGOpenMPRuntimeNVPTX::emitNonSPMDParallelCall(
llvm::Value *ID = Bld.CreateBitOrPointerCast(WFn, CGM.Int8PtrTy);
// Prepare for parallel region. Indicate the outlined function.
llvm::Value *Args[] = {ID, /*RequiresOMPRuntime=*/Bld.getInt16(1)};
llvm::Value *Args[] = {ID};
CGF.EmitRuntimeCall(
createNVPTXRuntimeFunction(OMPRTL_NVPTX__kmpc_kernel_prepare_parallel),
Args);

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

@ -55,7 +55,7 @@ void test_ds(){
// CK1: [[A:%.+]] = getelementptr inbounds %struct._globalized_locals_ty, %struct._globalized_locals_ty* [[GLOBALSTACK2]], i32 0, i32 0
// CK1: [[B:%.+]] = getelementptr inbounds %struct._globalized_locals_ty, %struct._globalized_locals_ty* [[GLOBALSTACK2]], i32 0, i32 1
// CK1: store i32 10, i32* [[A]]
// CK1: call void @__kmpc_kernel_prepare_parallel({{.*}}, i16 1)
// CK1: call void @__kmpc_kernel_prepare_parallel({{.*}})
// CK1: call void @__kmpc_begin_sharing_variables(i8*** [[SHAREDARGS1]], i64 1)
// CK1: [[SHARGSTMP1:%.+]] = load i8**, i8*** [[SHAREDARGS1]]
// CK1: [[SHARGSTMP2:%.+]] = getelementptr inbounds i8*, i8** [[SHARGSTMP1]], i64 0
@ -65,7 +65,7 @@ void test_ds(){
// CK1: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CK1: call void @__kmpc_end_sharing_variables()
// CK1: store i32 100, i32* [[B]]
// CK1: call void @__kmpc_kernel_prepare_parallel({{.*}}, i16 1)
// CK1: call void @__kmpc_kernel_prepare_parallel({{.*}})
// CK1: call void @__kmpc_begin_sharing_variables(i8*** [[SHAREDARGS2]], i64 2)
// CK1: [[SHARGSTMP3:%.+]] = load i8**, i8*** [[SHAREDARGS2]]
// CK1: [[SHARGSTMP4:%.+]] = getelementptr inbounds i8*, i8** [[SHARGSTMP3]], i64 0

10
clang/test/OpenMP/nvptx_parallel_codegen.cpp
View File

@ -92,7 +92,7 @@ int bar(int n){
//
// CHECK: [[AWAIT_WORK]]
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0) #[[#CONVERGENT:]]
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]]
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]])
// CHECK: [[KPRB:%.+]] = zext i1 [[KPR]] to i8
// store i8 [[KPRB]], i8* [[OMP_EXEC_STATUS]], align 1
// CHECK: [[WORK:%.+]] = load i8*, i8** [[OMP_WORK_FN]],
@ -166,13 +166,13 @@ int bar(int n){
// CHECK-DAG: [[MWS:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.warpsize()
// CHECK: [[MTMP1:%.+]] = sub nuw i32 [[MNTH]], [[MWS]]
// CHECK: call void @__kmpc_kernel_init(i32 [[MTMP1]]
// CHECK: call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void (i16, i32)* [[PARALLEL_FN1]]_wrapper to i8*),
// CHECK: call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void (i16, i32)* [[PARALLEL_FN1]]_wrapper to i8*))
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: call void @__kmpc_serialized_parallel(
// CHECK: {{call|invoke}} void [[PARALLEL_FN3:@.+]](
// CHECK: call void @__kmpc_end_serialized_parallel(
// CHECK: call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void (i16, i32)* [[PARALLEL_FN2]]_wrapper to i8*),
// CHECK: call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void (i16, i32)* [[PARALLEL_FN2]]_wrapper to i8*))
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK-64-DAG: load i32, i32* [[REF_A]]
@ -211,7 +211,7 @@ int bar(int n){
//
// CHECK: [[AWAIT_WORK]]
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]],
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]])
// CHECK: [[KPRB:%.+]] = zext i1 [[KPR]] to i8
// store i8 [[KPRB]], i8* [[OMP_EXEC_STATUS]], align 1
// CHECK: [[WORK:%.+]] = load i8*, i8** [[OMP_WORK_FN]],
@ -291,7 +291,7 @@ int bar(int n){
// CHECK: br i1 [[CMP]], label {{%?}}[[IF_THEN:.+]], label {{%?}}[[IF_ELSE:.+]]
//
// CHECK: [[IF_THEN]]
// CHECK: call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void (i16, i32)* [[PARALLEL_FN4]]_wrapper to i8*),
// CHECK: call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void (i16, i32)* [[PARALLEL_FN4]]_wrapper to i8*))
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: br label {{%?}}[[IF_END:.+]]

2
clang/test/OpenMP/nvptx_target_codegen.cpp
View File

@ -612,7 +612,7 @@ int baz(int f, double &a) {
// CHECK: call void @__kmpc_end_serialized_parallel(%struct.ident_t* [[UNKNOWN]], i32 [[GTID]])
// CHECK: br label
// CHECK: call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void (i16, i32)* @{{.+}} to i8*), i16 1)
// CHECK: call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void (i16, i32)* @{{.+}} to i8*))
// CHECK: call void @__kmpc_begin_sharing_variables(i8*** [[SHARED_PTR:%.+]], i{{64|32}} 2)
// CHECK: [[SHARED:%.+]] = load i8**, i8*** [[SHARED_PTR]],
// CHECK: [[REF:%.+]] = getelementptr inbounds i8*, i8** [[SHARED]], i{{64|32}} 0

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

@ -68,7 +68,7 @@ int bar(int n){
//
// CHECK: [[AWAIT_WORK]]
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]], i16 1)
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]])
// CHECK: [[KPRB:%.+]] = zext i1 [[KPR]] to i8
// store i8 [[KPRB]], i8* [[OMP_EXEC_STATUS]], align 1
// CHECK: [[WORK:%.+]] = load i8*, i8** [[OMP_WORK_FN]],
@ -154,7 +154,7 @@ int bar(int n){
//
// CHECK: [[AWAIT_WORK]]
// CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]], i16 1)
// CHECK: [[KPR:%.+]] = call i1 @__kmpc_kernel_parallel(i8** [[OMP_WORK_FN]])
// CHECK: [[KPRB:%.+]] = zext i1 [[KPR]] to i8
// store i8 [[KPRB]], i8* [[OMP_EXEC_STATUS]], align 1
// CHECK: [[WORK:%.+]] = load i8*, i8** [[OMP_WORK_FN]],

2
clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp
View File

@ -88,7 +88,7 @@ int bar(int n){
// CHECK: [[I_ADDR:%.+]] = getelementptr inbounds [[GLOB_TY]], [[GLOB_TY]]* [[RD]], i32 0, i32 0
//
// CHECK: call void @__kmpc_for_static_init_4(
// CHECK: call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void (i16, i32)* @{{.+}} to i8*), i16 1)
// CHECK: call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void (i16, i32)* @{{.+}} to i8*))
// CHECK: call void @__kmpc_begin_sharing_variables(i8*** [[SHARED_VARS_PTR:%.+]], i{{64|32}} 1)
// CHECK: [[SHARED_VARS_BUF:%.+]] = load i8**, i8*** [[SHARED_VARS_PTR]],
// CHECK: [[VARS_BUF:%.+]] = getelementptr inbounds i8*, i8** [[SHARED_VARS_BUF]], i{{64|32}} 0

5
llvm/include/llvm/Frontend/OpenMP/OMPKinds.def
View File

@ -584,6 +584,11 @@ __OMP_RTL(__tgt_push_mapper_component, false, Void, VoidPtr, VoidPtr, VoidPtr,
__OMP_RTL(__kmpc_task_allow_completion_event, false, VoidPtr, IdentPtr,
/* Int */ Int32, /* kmp_task_t */ VoidPtr)
/// Note that device runtime functions (in the following) do not necessarily
/// need attributes as we expect to see the definitions.
__OMP_RTL(__kmpc_kernel_parallel, false, Int1, VoidPtrPtr)
__OMP_RTL(__kmpc_kernel_prepare_parallel, false, Void, VoidPtr)
__OMP_RTL(__last, false, Void, )
#undef __OMP_RTL

9
openmp/libomptarget/deviceRTLs/common/src/parallel.cu
View File

@ -72,10 +72,8 @@ INLINE static uint16_t determineNumberOfThreads(uint16_t NumThreadsClause,
}
// This routine is always called by the team master..
EXTERN void __kmpc_kernel_prepare_parallel(void *WorkFn,
int16_t IsOMPRuntimeInitialized) {
EXTERN void __kmpc_kernel_prepare_parallel(void *WorkFn) {
PRINT0(LD_IO, "call to __kmpc_kernel_prepare_parallel\n");
ASSERT0(LT_FUSSY, IsOMPRuntimeInitialized, "Expected initialized runtime.");
omptarget_nvptx_workFn = WorkFn;
@ -120,12 +118,9 @@ EXTERN void __kmpc_kernel_prepare_parallel(void *WorkFn,
// returns True if this thread is active, else False.
//
// Only the worker threads call this routine.
EXTERN bool __kmpc_kernel_parallel(void **WorkFn,
int16_t IsOMPRuntimeInitialized) {
EXTERN bool __kmpc_kernel_parallel(void **WorkFn) {
PRINT0(LD_IO | LD_PAR, "call to __kmpc_kernel_parallel\n");
ASSERT0(LT_FUSSY, IsOMPRuntimeInitialized, "Expected initialized runtime.");
// Work function and arguments for L1 parallel region.
*WorkFn = omptarget_nvptx_workFn;

6
openmp/libomptarget/deviceRTLs/interface.h
View File

@ -424,10 +424,8 @@ EXTERN void __kmpc_kernel_deinit(int16_t IsOMPRuntimeInitialized);
EXTERN void __kmpc_spmd_kernel_init(int ThreadLimit, int16_t RequiresOMPRuntime,
int16_t RequiresDataSharing);
EXTERN void __kmpc_spmd_kernel_deinit_v2(int16_t RequiresOMPRuntime);
EXTERN void __kmpc_kernel_prepare_parallel(void *WorkFn,
int16_t IsOMPRuntimeInitialized);
EXTERN bool __kmpc_kernel_parallel(void **WorkFn,
int16_t IsOMPRuntimeInitialized);
EXTERN void __kmpc_kernel_prepare_parallel(void *WorkFn);
EXTERN bool __kmpc_kernel_parallel(void **WorkFn);
EXTERN void __kmpc_kernel_end_parallel();
EXTERN void __kmpc_data_sharing_init_stack();