forked from OSchip/llvm-project
[OPENMP, NVPTX] Do not globalize local variables in parallel regions.
In generic data-sharing mode we are allowed to not globalize local variables that escape their declaration context iff they are declared inside of the parallel region. We can do this because L2 parallel regions are executed sequentially and, thus, we do not need to put shared local variables in the global memory. llvm-svn: 336567
This commit is contained in:
Alexey Bataev
parent
47170b3153
commit
b99dcb5f31
|
|
@ -1554,29 +1554,22 @@ void CGOpenMPRuntimeNVPTX::emitNumTeamsClause(CodeGenFunction &CGF,
|
|||
llvm::Value *CGOpenMPRuntimeNVPTX::emitParallelOutlinedFunction(
|
||||
const OMPExecutableDirective &D, const VarDecl *ThreadIDVar,
|
||||
OpenMPDirectiveKind InnermostKind, const RegionCodeGenTy &CodeGen) {
|
||||
SourceLocation Loc = D.getLocStart();
|
||||
|
||||
// Emit target region as a standalone region.
|
||||
class NVPTXPrePostActionTy : public PrePostActionTy {
|
||||
SourceLocation &Loc;
|
||||
bool &IsInParallelRegion;
|
||||
bool PrevIsInParallelRegion;
|
||||
|
||||
public:
|
||||
NVPTXPrePostActionTy(SourceLocation &Loc, bool &IsInParallelRegion)
|
||||
: Loc(Loc), IsInParallelRegion(IsInParallelRegion) {}
|
||||
NVPTXPrePostActionTy(bool &IsInParallelRegion)
|
||||
: IsInParallelRegion(IsInParallelRegion) {}
|
||||
void Enter(CodeGenFunction &CGF) override {
|
||||
static_cast<CGOpenMPRuntimeNVPTX &>(CGF.CGM.getOpenMPRuntime())
|
||||
.emitGenericVarsProlog(CGF, Loc);
|
||||
PrevIsInParallelRegion = IsInParallelRegion;
|
||||
IsInParallelRegion = true;
|
||||
}
|
||||
void Exit(CodeGenFunction &CGF) override {
|
||||
IsInParallelRegion = PrevIsInParallelRegion;
|
||||
static_cast<CGOpenMPRuntimeNVPTX &>(CGF.CGM.getOpenMPRuntime())
|
||||
.emitGenericVarsEpilog(CGF);
|
||||
}
|
||||
} Action(Loc, IsInParallelRegion);
|
||||
} Action(IsInParallelRegion);
|
||||
CodeGen.setAction(Action);
|
||||
bool PrevIsInTargetMasterThreadRegion = IsInTargetMasterThreadRegion;
|
||||
IsInTargetMasterThreadRegion = false;
|
||||
|
|
|
|||
|
|
@ -24,12 +24,11 @@ int maini1() {
|
|||
|
||||
// parallel region
|
||||
// CHECK: define {{.*}}void @{{.*}}(i32* noalias {{.*}}, i32* noalias {{.*}}, i32* dereferenceable{{.*}})
|
||||
// CHECK: [[RES:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i64 4, i16 0)
|
||||
// CHECK: [[GLOBALS:%.+]] = bitcast i8* [[RES]] to [[GLOBAL_ST:%struct[.].*]]*
|
||||
// CHECK: [[B_ADDR:%.+]] = getelementptr inbounds [[GLOBAL_ST]], [[GLOBAL_ST]]* [[GLOBALS]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
|
||||
// CHECK-NOT: call i8* @__kmpc_data_sharing_push_stack(
|
||||
// CHECK: [[B_ADDR:%.+]] = alloca i32,
|
||||
// CHECK: call {{.*}}[[FOO:@.*foo.*]](i32* dereferenceable{{.*}} [[B_ADDR]])
|
||||
// CHECK: call {{.*}}[[BAR:@.*bar.*]]()
|
||||
// CHECK: call void @__kmpc_data_sharing_pop_stack(i8* [[RES]])
|
||||
// CHECK-NOT: call void @__kmpc_data_sharing_pop_stack(
|
||||
// CHECK: ret void
|
||||
|
||||
// CHECK: define {{.*}}[[FOO]](i32* dereferenceable{{.*}})
|
||||
|
|
|
|||
|
|
@ -83,11 +83,10 @@ void test_ds(){
|
|||
/// outlined function for the second parallel region ///
|
||||
|
||||
// CK1: define internal void @{{.+}}(i32* noalias %{{.+}}, i32* noalias %{{.+}}, i32* dereferenceable{{.+}}, i32* dereferenceable{{.+}})
|
||||
// CK1: [[RES:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i64 4, i16 0)
|
||||
// CK1: [[GLOBALS:%.+]] = bitcast i8* [[RES]] to [[GLOBAL_TY:%.+]]*
|
||||
// CK1: [[C_ADDR:%.+]] = getelementptr inbounds [[GLOBAL_TY]], [[GLOBAL_TY]]* [[GLOBALS]], i32 0, i32 0
|
||||
// CK1-NOT: call i8* @__kmpc_data_sharing_push_stack(
|
||||
// CK1: [[C_ADDR:%.+]] = alloca i32,
|
||||
// CK1: store i32* [[C_ADDR]], i32** %
|
||||
// CK1: call void @__kmpc_data_sharing_pop_stack(i8* [[RES]])
|
||||
// CK1i-NOT: call void @__kmpc_data_sharing_pop_stack(
|
||||
|
||||
/// ========= In the data sharing wrapper function ========= ///
|
||||
|
||||
|
|
|
|||
|
|
@ -44,8 +44,8 @@ int main(int argc, char **argv) {
|
|||
// CHECK: call void @__kmpc_data_sharing_pop_stack(i8* [[PTR]])
|
||||
|
||||
// CHECK: define internal void [[PARALLEL]](
|
||||
// CHECK: [[PTR:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{64|32}} 4, i16 0)
|
||||
// CHECK-NOT: call i8* @__kmpc_data_sharing_push_stack(
|
||||
|
||||
// CHECK: call void @__kmpc_data_sharing_pop_stack(i8* [[PTR]])
|
||||
// CHECK-NOT: call void @__kmpc_data_sharing_pop_stack(
|
||||
|
||||
#endif
|
||||
|
|
|
|||
|
|
@ -34,20 +34,33 @@ int main(int argc, char **argv) {
|
|||
|
||||
// CHECK: call void @__kmpc_spmd_kernel_deinit()
|
||||
|
||||
// CHECK: define internal void [[PARALLEL]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i{{64|32}} %{{.+}}, i{{64|32}} %{{.+}}, i{{64|32}} %{{.+}}, i32* dereferenceable{{.*}})
|
||||
// CHECK: [[RES:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{64|32}} 8, i16 0)
|
||||
// CHECK: [[GLOBALS:%.+]] = bitcast i8* [[RES]] to [[GLOBAL_TY:%.+]]*
|
||||
// CHECK: [[I:%.+]] = getelementptr inbounds [[GLOBAL_TY]], [[GLOBAL_TY]]* [[GLOBALS]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
|
||||
// CHECK: [[ARGC_VAL:%.+]] = load i32, i32* %
|
||||
// CHECK: [[ARGC:%.+]] = getelementptr inbounds [[GLOBAL_TY]], [[GLOBAL_TY]]* [[GLOBALS]], i{{[0-9]+}} 0, i{{[0-9]+}} 1
|
||||
// CHECK: store i32 [[ARGC_VAL]], i32* [[ARGC]],
|
||||
// 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(
|
||||
// CHECK: alloca i{{[0-9]+}},
|
||||
// CHECK: alloca i{{[0-9]+}},
|
||||
// CHECK: [[ARGC_ADDR:%.+]] = alloca i{{32|64}},
|
||||
// CHECK: alloca i{{[0-9]+}},
|
||||
// CHECK: alloca i{{[0-9]+}},
|
||||
// CHECK: alloca i{{[0-9]+}},
|
||||
// CHECK: alloca i{{[0-9]+}},
|
||||
// CHECK: alloca i{{[0-9]+}},
|
||||
// CHECK: alloca i{{[0-9]+}},
|
||||
// CHECK: alloca i{{[0-9]+}},
|
||||
// CHECK: alloca i{{[0-9]+}},
|
||||
// CHECK: alloca i{{[0-9]+}},
|
||||
// CHECK: alloca i{{[0-9]+}},
|
||||
// CHECK: [[I:%.+]] = alloca i32,
|
||||
// CHECK-32: store i32 [[ARGC]], i32* [[ARGC_ADDR]],
|
||||
// CHECK-64: store i{{64|32}} [[ARGC]], i{{64|32}}* [[ARGC_ADDR]],
|
||||
// CHECK-64: [[ARGC:%.+]] = bitcast i64* [[ARGC_ADDR]] to i32*
|
||||
|
||||
// CHECK: call void @__kmpc_for_static_init_4(
|
||||
// CHECK: call i32 [[FOO:@.+foo.+]](i32* [[I]])
|
||||
// CHECK: call i32 [[FOO]](i32* %{{.+}})
|
||||
// CHECK: call i32 [[FOO]](i32* [[ARGC]])
|
||||
// CHECK-32: call i32 [[FOO]](i32* [[ARGC_ADDR]])
|
||||
// CHECK-64: call i32 [[FOO]](i32* [[ARGC]])
|
||||
// CHECK: call void @__kmpc_for_static_fini(
|
||||
|
||||
// CHECK: call void @__kmpc_data_sharing_pop_stack(i8* [[RES]])
|
||||
// CHECK-NOT: call void @__kmpc_data_sharing_pop_stack(
|
||||
|
||||
#endif
|
||||
|
|
|
|||
Loading…
Reference in New Issue