[OpenMP] Add a new version of the SPMD deinit kernel function

Summary: This patch adds a new runtime for the SPMD deinit kernel function which replaces the previous function. The new function takes as argument the flag which signals whether the runtime is required or not. This enables the compiler to optimize out the part of the deinit function which are not needed.

Reviewers: ABataev, caomhin

Reviewed By: ABataev

Subscribers: jholewinski, guansong, cfe-commits

Differential Revision: https://reviews.llvm.org/D54970

llvm-svn: 347915
This commit is contained in:
Gheorghe-Teodor Bercea 2018-11-29 20:53:49 +00:00
parent 66d9a752b9
commit 2b40470c61
9 changed files with 31 additions and 27 deletions

View File

@ -33,8 +33,8 @@ enum OpenMPRTLFunctionNVPTX {
/// Call to void __kmpc_spmd_kernel_init(kmp_int32 thread_limit,
/// int16_t RequiresOMPRuntime, int16_t RequiresDataSharing);
OMPRTL_NVPTX__kmpc_spmd_kernel_init,
/// Call to void __kmpc_spmd_kernel_deinit();
OMPRTL_NVPTX__kmpc_spmd_kernel_deinit,
/// 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);
@ -1413,8 +1413,11 @@ void CGOpenMPRuntimeNVPTX::emitSPMDEntryFooter(CodeGenFunction &CGF,
CGF.EmitBlock(OMPDeInitBB);
// DeInitialize the OMP state in the runtime; called by all active threads.
llvm::Value *Args[] = {/*RequiresOMPRuntime=*/
CGF.Builder.getInt16(RequiresFullRuntime ? 1 : 0)};
CGF.EmitRuntimeCall(
createNVPTXRuntimeFunction(OMPRTL_NVPTX__kmpc_spmd_kernel_deinit), None);
createNVPTXRuntimeFunction(
OMPRTL_NVPTX__kmpc_spmd_kernel_deinit_v2), Args);
CGF.EmitBranch(EST.ExitBB);
CGF.EmitBlock(EST.ExitBB);
@ -1597,11 +1600,12 @@ CGOpenMPRuntimeNVPTX::createNVPTXRuntimeFunction(unsigned Function) {
RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_spmd_kernel_init");
break;
}
case OMPRTL_NVPTX__kmpc_spmd_kernel_deinit: {
// Build void __kmpc_spmd_kernel_deinit();
case OMPRTL_NVPTX__kmpc_spmd_kernel_deinit_v2: {
// Build void __kmpc_spmd_kernel_deinit_v2(int16_t RequiresOMPRuntime);
llvm::Type *TypeParams[] = {CGM.Int16Ty};
auto *FnTy =
llvm::FunctionType::get(CGM.VoidTy, llvm::None, /*isVarArg*/ false);
RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_spmd_kernel_deinit");
llvm::FunctionType::get(CGM.VoidTy, TypeParams, /*isVarArg*/ false);
RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_spmd_kernel_deinit_v2");
break;
}
case OMPRTL_NVPTX__kmpc_kernel_prepare_parallel: {

View File

@ -68,7 +68,7 @@ int bar(int n){
// CHECK: br label {{%?}}[[DONE:.+]]
//
// CHECK: [[DONE]]
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK: br label {{%?}}[[EXIT:.+]]
//
// CHECK: [[EXIT]]
@ -111,7 +111,7 @@ int bar(int n){
// CHECK: br label {{%?}}[[DONE:.+]]
//
// CHECK: [[DONE]]
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK: br label {{%?}}[[EXIT:.+]]
//
// CHECK: [[EXIT]]

View File

@ -57,7 +57,7 @@ int bar(int n){
// CHECK: br label {{%?}}[[DONE:.+]]
//
// CHECK: [[DONE]]
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK: br label {{%?}}[[EXIT:.+]]
//
// CHECK: [[EXIT]]
@ -79,7 +79,7 @@ int bar(int n){
// CHECK: br label {{%?}}[[DONE:.+]]
//
// CHECK: [[DONE]]
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK: br label {{%?}}[[EXIT:.+]]
//
// CHECK: [[EXIT]]
@ -100,7 +100,7 @@ int bar(int n){
// CHECK: br label {{%?}}[[DONE:.+]]
//
// CHECK: [[DONE]]
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK: br label {{%?}}[[EXIT:.+]]
//
// CHECK: [[EXIT]]

View File

@ -60,7 +60,7 @@ int bar(int n){
//
// CHECK: [[EXECUTE]]
// CHECK: {{call|invoke}} void [[PFN:@.+]](i32*
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
//
//
// define internal void [[PFN]](
@ -254,7 +254,7 @@ int bar(int n){
//
// CHECK: [[EXECUTE]]
// CHECK: {{call|invoke}} void [[PFN1:@.+]](i32*
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
//
//
// define internal void [[PFN1]](
@ -527,7 +527,7 @@ int bar(int n){
//
// CHECK: [[EXECUTE]]
// CHECK: {{call|invoke}} void [[PFN2:@.+]](i32*
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
//
//
// define internal void [[PFN2]](

View File

@ -234,7 +234,7 @@ int bar(int n){
// CHECK: call void [[L0:@.+]](i32* %{{.+}}, i32* %{{.+}}, i16* %{{.*}})
// CHECK-NOT: call void @__kmpc_end_serialized_parallel(
// CHECK-NOT: call void @__kmpc_data_sharing_pop_stack(
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK: ret
// CHECK: define internal void [[L0]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i16* dereferenceable

View File

@ -84,7 +84,7 @@ int bar(int n){
// CHECK: {{call|invoke}} void [[OUTL1:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: call void @__kmpc_restore_team_static_memory(i16 1)
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: ret void
// CHECK: define internal void [[OUTL1]](
@ -98,7 +98,7 @@ int bar(int n){
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
// CHECK: {{call|invoke}} void [[OUTL2:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: ret void
// CHECK: define internal void [[OUTL2]](
@ -112,7 +112,7 @@ int bar(int n){
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
// CHECK: {{call|invoke}} void [[OUTL3:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: ret void
// CHECK: define internal void [[OUTL3]](
@ -204,7 +204,7 @@ int bar(int n){
// CHECK: [[DIST_INNER_LOOP_END]]:
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: ret void
// CHECK: define internal void [[OUTL4]](

View File

@ -32,7 +32,7 @@ int main(int argc, char **argv) {
// CHECK: call void @__kmpc_for_static_fini(%struct.ident_t* @
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: define internal void [[PARALLEL]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i{{64|32}} %{{.+}}, i{{64|32}} %{{.+}}, i{{64|32}} [[ARGC:%.+]], i32* dereferenceable{{.*}})
// CHECK-NOT: call i8* @__kmpc_data_sharing_push_stack(

View File

@ -79,7 +79,7 @@ int bar(int n){
// CHECK: {{call|invoke}} void [[OUTL1:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: call void @__kmpc_restore_team_static_memory(i16 1)
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: ret void
// CHECK: define internal void [[OUTL1]](
@ -93,7 +93,7 @@ int bar(int n){
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
// CHECK: {{call|invoke}} void [[OUTL2:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: ret void
// CHECK: define internal void [[OUTL2]](
@ -107,7 +107,7 @@ int bar(int n){
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
// CHECK: {{call|invoke}} void [[OUTL3:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: ret void
// CHECK: define internal void [[OUTL3]](
@ -123,7 +123,7 @@ int bar(int n){
// CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91, {{.+}}, {{.+}}, {{.+}}* [[COMB_UB]],
// CHECK: {{call|invoke}} void [[OUTL4:@.+]](
// CHECK: call void @__kmpc_for_static_fini(
// CHECK: call void @__kmpc_spmd_kernel_deinit()
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
// CHECK: ret void
// CHECK: define internal void [[OUTL4]](

View File

@ -98,6 +98,7 @@ int bar(int n){
// CHECK: define {{.*}}void [[T2:@__omp_offloading_.+template.+l43]](
//
// CHECK: {{call|invoke}} void [[T2]]_worker()
//
// CHECK: call void @__kmpc_kernel_init(
//
@ -176,7 +177,7 @@ int bar(int n){
//
// CHECK: [[EXIT]]
// call void @__kmpc_restore_team_static_memory(i16 1)
// CHECK: call void @__kmpc_spmd_kernel_deinit(
// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
// CHECK: define internal void [[OUTLINED]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i32* dereferenceable{{.+}}, i16* dereferenceable{{.+}})
//
@ -286,7 +287,6 @@ int bar(int n){
// CHECK: [[MAXV:%.+]] = phi i16 [ [[MAX1]], %[[DO_MAX]] ], [ [[MAX2]], %[[MAX_ELSE]] ]
// CHECK: store i16 [[MAXV]], i16* [[VAR2_LHS]],
// CHECK: ret void
//
// Shuffle and reduce function
// CHECK: define internal void [[PAR_SHUFFLE_REDUCE_FN]](i8*, i16 {{.*}}, i16 {{.*}}, i16 {{.*}})