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

[OPENMP 4.5] Initial codegen for 'taskloop simd' directive. 

OpenMP 4.5 defines 'taskloop simd' directive, which is combined
directive for 'taskloop' and 'simd' directives. Patch adds initial
codegen support for this directive and its 2 basic clauses 'safelen' and
'simdlen'.

llvm-svn: 267872
This commit is contained in:
Alexey Bataev 2016-04-28 12:14:51 +00:00
parent 5556a5cf3b
commit 1e73ef3882
3 changed files with 217 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
clang/lib/CodeGen/CGStmtOpenMP.cpp
View File

@ -3383,6 +3383,9 @@ void CodeGenFunction::EmitOMPTaskLoopBasedDirective(const OMPLoopDirective &S) {
CGF.incrementProfileCounter(&S);
}
if (isOpenMPSimdDirective(S.getDirectiveKind()))
CGF.EmitOMPSimdInit(S);
OMPPrivateScope LoopScope(CGF);
// Emit helper vars inits.
enum { LowerBound = 5, UpperBound, Stride, LastIter };
@ -3449,12 +3452,5 @@ void CodeGenFunction::EmitOMPTaskLoopDirective(const OMPTaskLoopDirective &S) {
void CodeGenFunction::EmitOMPTaskLoopSimdDirective(
const OMPTaskLoopSimdDirective &S) {
// emit the code inside the construct for now
OMPLexicalScope Scope(*this, S, /*AsInlined=*/true);
CGM.getOpenMPRuntime().emitInlinedDirective(
*this, OMPD_taskloop_simd, [&S](CodeGenFunction &CGF, PrePostActionTy &) {
OMPLoopScope PreInitScope(CGF, S);
CGF.EmitStmt(
cast<CapturedStmt>(S.getAssociatedStmt())->getCapturedStmt());
});
EmitOMPTaskLoopBasedDirective(S);
}

11
clang/lib/Sema/SemaOpenMP.cpp
View File

@ -1720,7 +1720,8 @@ void Sema::ActOnOpenMPRegionStart(OpenMPDirectiveKind DKind, Scope *CurScope) {
Params);
break;
}
case OMPD_taskloop: {
case OMPD_taskloop:
case OMPD_taskloop_simd: {
QualType KmpInt32Ty =
Context.getIntTypeForBitwidth(/*DestWidth=*/32, /*Signed=*/1);
QualType KmpUInt64Ty =
@ -1754,14 +1755,6 @@ void Sema::ActOnOpenMPRegionStart(OpenMPDirectiveKind DKind, Scope *CurScope) {
Context, AlwaysInlineAttr::Keyword_forceinline, SourceRange()));
break;
}
case OMPD_taskloop_simd: {
Sema::CapturedParamNameType Params[] = {
std::make_pair(StringRef(), QualType()) // __context with shared vars
};
ActOnCapturedRegionStart(DSAStack->getConstructLoc(), CurScope, CR_OpenMP,
Params);
break;
}
case OMPD_distribute: {
Sema::CapturedParamNameType Params[] = {
std::make_pair(StringRef(), QualType()) // __context with shared vars

211
clang/test/OpenMP/taskloop_simd_codegen.cpp Normal file
View File

@ -0,0 +1,211 @@
// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -x c++ -emit-llvm %s -o - -femit-all-decls | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - -femit-all-decls | FileCheck %s
// expected-no-diagnostics
// REQUIRES: x86-registered-target
#ifndef HEADER
#define HEADER
// CHECK-LABEL: @main
int main(int argc, char **argv) {
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num(%ident_t* [[DEFLOC:@.+]])
// CHECK: [[TASKV:%.+]] = call i8* @__kmpc_omp_task_alloc(%ident_t* [[DEFLOC]], i32 [[GTID]], i32 1, i64 64, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, [[TDP_TY:%.+]]*)* [[TASK1:@.+]] to i32 (i32, i8*)*))
// CHECK: [[TASK:%.+]] = bitcast i8* [[TASKV]] to [[TDP_TY]]*
// CHECK: [[TASK_DATA:%.+]] = getelementptr inbounds [[TDP_TY]], [[TDP_TY]]* [[TASK]], i32 0, i32 0
// CHECK: getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 3
// CHECK: store i32 (i32, i8*)* null, i32 (i32, i8*)** %{{.+}}
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 4
// CHECK: store i64 0, i64* [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 5
// CHECK: store i64 9, i64* [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 6
// CHECK: store i64 1, i64* [[ST]],
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
// CHECK: call void @__kmpc_taskloop(%ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 0, i64 0, i8* null)
#pragma omp taskloop simd
for (int i = 0; i < 10; ++i)
;
// CHECK: [[TASKV:%.+]] = call i8* @__kmpc_omp_task_alloc(%ident_t* [[DEFLOC]], i32 [[GTID]], i32 1, i64 64, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, [[TDP_TY:%.+]]*)* [[TASK2:@.+]] to i32 (i32, i8*)*))
// CHECK: [[TASK:%.+]] = bitcast i8* [[TASKV]] to [[TDP_TY]]*
// CHECK: [[TASK_DATA:%.+]] = getelementptr inbounds [[TDP_TY]], [[TDP_TY]]* [[TASK]], i32 0, i32 0
// CHECK: getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 3
// CHECK: store i32 (i32, i8*)* null, i32 (i32, i8*)** %{{.+}}
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 4
// CHECK: store i64 0, i64* [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 5
// CHECK: store i64 9, i64* [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 6
// CHECK: store i64 1, i64* [[ST]],
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
// CHECK: [[GRAINSIZE:%.+]] = zext i32 %{{.+}} to i64
// CHECK: call void @__kmpc_taskloop(%ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 1, i32 1, i64 [[GRAINSIZE]], i8* null)
#pragma omp taskloop simd nogroup grainsize(argc) simdlen(4)
for (int i = 0; i < 10; ++i)
;
// CHECK: [[TASKV:%.+]] = call i8* @__kmpc_omp_task_alloc(%ident_t* [[DEFLOC]], i32 [[GTID]], i32 1, i64 64, i64 24, i32 (i32, i8*)* bitcast (i32 (i32, [[TDP_TY:%.+]]*)* [[TASK3:@.+]] to i32 (i32, i8*)*))
// CHECK: [[TASK:%.+]] = bitcast i8* [[TASKV]] to [[TDP_TY]]*
// CHECK: [[TASK_DATA:%.+]] = getelementptr inbounds [[TDP_TY]], [[TDP_TY]]* [[TASK]], i32 0, i32 0
// CHECK: getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 3
// CHECK: store i32 (i32, i8*)* null, i32 (i32, i8*)** %{{.+}}
// CHECK: [[IF:%.+]] = icmp ne i32 %{{.+}}, 0
// CHECK: [[IF_INT:%.+]] = sext i1 [[IF]] to i32
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 4
// CHECK: store i64 0, i64* [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 5
// CHECK: store i64 %{{.+}}, i64* [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 6
// CHECK: store i64 1, i64* [[ST]],
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
// CHECK: call void @__kmpc_taskloop(%ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 [[IF_INT]], i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 2, i64 4, i8* null)
int i;
#pragma omp taskloop simd if(argc) shared(argc, argv) collapse(2) num_tasks(4) safelen(32)
for (i = 0; i < argc; ++i)
for (int j = argc; j < argv[argc][argc]; ++j)
;
}
// CHECK: define internal i32 [[TASK1]](
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* %{{.+}}, i32 0, i32 4
// CHECK: [[DOWN_VAL:%.+]] = load i64, i64* [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 5
// CHECK: [[UP_VAL:%.+]] = load i64, i64* [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 6
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
// CHECK: [[LITER:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 7
// CHECK: [[LITER_VAL:%.+]] = load i32, i32* [[LITER]],
// CHECK: store i64 [[DOWN_VAL]], i64* [[LB:%[^,]+]],
// CHECK: store i64 [[UP_VAL]], i64* [[UB:%[^,]+]],
// CHECK: store i64 [[ST_VAL]], i64* [[ST:%[^,]+]],
// CHECK: store i32 [[LITER_VAL]], i32* [[LITER:%[^,]+]],
// CHECK: [[LB_VAL:%.+]] = load i64, i64* [[LB]],
// CHECK: [[LB_I32:%.+]] = trunc i64 [[LB_VAL]] to i32
// CHECK: store i32 [[LB_I32]], i32* [[CNT:%.+]],
// CHECK: br label
// CHECK: [[VAL:%.+]] = load i32, i32* [[CNT]],{{.*}}!llvm.mem.parallel_loop_access [[LOOP1:!.+]]
// CHECK: [[VAL_I64:%.+]] = sext i32 [[VAL]] to i64
// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]],{{.*}}!llvm.mem.parallel_loop_access [[LOOP1]]
// CHECK: [[CMP:%.+]] = icmp ule i64 [[VAL_I64]], [[UB_VAL]]
// CHECK: br i1 [[CMP]], label %{{.+}}, label %{{.+}}
// CHECK: load i32, i32* %{{.*}}!llvm.mem.parallel_loop_access [[LOOP1]]
// CHECK: store i32 %{{.*}}!llvm.mem.parallel_loop_access [[LOOP1]]
// CHECK: load i32, i32* %{{.*}}!llvm.mem.parallel_loop_access [[LOOP1]]
// CHECK: add nsw i32 %{{.+}}, 1
// CHECK: store i32 %{{.+}}, i32* %{{.*}}!llvm.mem.parallel_loop_access [[LOOP1]]
// CHECK: br label %{{.*}}!llvm.loop [[LOOP1]]
// CHECK: ret i32 0
// CHECK: define internal i32 [[TASK2]](
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* %{{.+}}, i32 0, i32 4
// CHECK: [[DOWN_VAL:%.+]] = load i64, i64* [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 5
// CHECK: [[UP_VAL:%.+]] = load i64, i64* [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 6
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
// CHECK: [[LITER:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 7
// CHECK: [[LITER_VAL:%.+]] = load i32, i32* [[LITER]],
// CHECK: store i64 [[DOWN_VAL]], i64* [[LB:%[^,]+]],
// CHECK: store i64 [[UP_VAL]], i64* [[UB:%[^,]+]],
// CHECK: store i64 [[ST_VAL]], i64* [[ST:%[^,]+]],
// CHECK: store i32 [[LITER_VAL]], i32* [[LITER:%[^,]+]],
// CHECK: [[LB_VAL:%.+]] = load i64, i64* [[LB]],
// CHECK: [[LB_I32:%.+]] = trunc i64 [[LB_VAL]] to i32
// CHECK: store i32 [[LB_I32]], i32* [[CNT:%.+]],
// CHECK: br label
// CHECK: [[VAL:%.+]] = load i32, i32* [[CNT]],{{.*}}!llvm.mem.parallel_loop_access [[LOOP2:!.+]]
// CHECK: [[VAL_I64:%.+]] = sext i32 [[VAL]] to i64
// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]],{{.*}}!llvm.mem.parallel_loop_access [[LOOP2]]
// CHECK: [[CMP:%.+]] = icmp ule i64 [[VAL_I64]], [[UB_VAL]]
// CHECK: br i1 [[CMP]], label %{{.+}}, label %{{.+}}
// CHECK: load i32, i32* %{{.*}}!llvm.mem.parallel_loop_access [[LOOP2]]
// CHECK: store i32 %{{.*}}!llvm.mem.parallel_loop_access [[LOOP2]]
// CHECK: load i32, i32* %{{.*}}!llvm.mem.parallel_loop_access [[LOOP2]]
// CHECK: add nsw i32 %{{.+}}, 1
// CHECK: store i32 %{{.+}}, i32* %{{.*}}!llvm.mem.parallel_loop_access [[LOOP2]]
// CHECK: br label %{{.*}}!llvm.loop [[LOOP2]]
// CHECK: ret i32 0
// CHECK: define internal i32 [[TASK3]](
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* %{{.+}}, i32 0, i32 4
// CHECK: [[DOWN_VAL:%.+]] = load i64, i64* [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 5
// CHECK: [[UP_VAL:%.+]] = load i64, i64* [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 6
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
// CHECK: [[LITER:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 7
// CHECK: [[LITER_VAL:%.+]] = load i32, i32* [[LITER]],
// CHECK: store i64 [[DOWN_VAL]], i64* [[LB:%[^,]+]],
// CHECK: store i64 [[UP_VAL]], i64* [[UB:%[^,]+]],
// CHECK: store i64 [[ST_VAL]], i64* [[ST:%[^,]+]],
// CHECK: store i32 [[LITER_VAL]], i32* [[LITER:%[^,]+]],
// CHECK: [[LB_VAL:%.+]] = load i64, i64* [[LB]],
// CHECK: store i64 [[LB_VAL]], i64* [[CNT:%.+]],
// CHECK: br label
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK: br label %{{.*}}!llvm.loop
// CHECK: ret i32 0
// CHECK-LABEL: @_ZN1SC2Ei
struct S {
int a;
S(int c) {
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num(%ident_t* [[DEFLOC:@.+]])
// CHECK: [[TASKV:%.+]] = call i8* @__kmpc_omp_task_alloc(%ident_t* [[DEFLOC]], i32 [[GTID]], i32 1, i64 64, i64 16, i32 (i32, i8*)* bitcast (i32 (i32, [[TDP_TY:%.+]]*)* [[TASK4:@.+]] to i32 (i32, i8*)*))
// CHECK: [[TASK:%.+]] = bitcast i8* [[TASKV]] to [[TDP_TY]]*
// CHECK: [[TASK_DATA:%.+]] = getelementptr inbounds [[TDP_TY]], [[TDP_TY]]* [[TASK]], i32 0, i32 0
// CHECK: getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 3
// CHECK: store i32 (i32, i8*)* null, i32 (i32, i8*)** %{{.+}}
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 4
// CHECK: store i64 0, i64* [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 5
// CHECK: store i64 %{{.+}}, i64* [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 6
// CHECK: store i64 1, i64* [[ST]],
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
// CHECK: [[NUM_TASKS:%.+]] = zext i32 %{{.+}} to i64
// CHECK: call void @__kmpc_taskloop(%ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 2, i64 [[NUM_TASKS]], i8* null)
#pragma omp taskloop simd shared(c) num_tasks(a) simdlen(64) safelen(8)
for (a = 0; a < c; ++a)
;
}
} s(1);
// CHECK: define internal i32 [[TASK4]](
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* %{{.+}}, i32 0, i32 4
// CHECK: [[DOWN_VAL:%.+]] = load i64, i64* [[DOWN]],
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 5
// CHECK: [[UP_VAL:%.+]] = load i64, i64* [[UP]],
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 6
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
// CHECK: [[LITER:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 7
// CHECK: [[LITER_VAL:%.+]] = load i32, i32* [[LITER]],
// CHECK: store i64 [[DOWN_VAL]], i64* [[LB:%[^,]+]],
// CHECK: store i64 [[UP_VAL]], i64* [[UB:%[^,]+]],
// CHECK: store i64 [[ST_VAL]], i64* [[ST:%[^,]+]],
// CHECK: store i32 [[LITER_VAL]], i32* [[LITER:%[^,]+]],
// CHECK: [[LB_VAL:%.+]] = load i64, i64* [[LB]],
// CHECK: [[LB_I32:%.+]] = trunc i64 [[LB_VAL]] to i32
// CHECK: store i32 [[LB_I32]], i32* [[CNT:%.+]],
// CHECK: br label
// CHECK: [[VAL:%.+]] = load i32, i32* [[CNT]],
// CHECK: [[VAL_I64:%.+]] = sext i32 [[VAL]] to i64
// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]],
// CHECK: [[CMP:%.+]] = icmp ule i64 [[VAL_I64]], [[UB_VAL]]
// CHECK: br i1 [[CMP]], label %{{.+}}, label %{{.+}}
// CHECK: load i32, i32* %
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK: store i32 %
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK: load i32, i32* %
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK: add nsw i32 %{{.+}}, 1
// CHECK: store i32 %{{.+}}, i32* %
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK: br label %{{.*}}!llvm.loop
// CHECK: ret i32 0
// CHECK: !{!"llvm.loop.vectorize.enable", i1 true}
// CHECK: !{!"llvm.loop.vectorize.width", i32 4}
// CHECK: !{!"llvm.loop.vectorize.width", i32 32}
// CHECK: !{!"llvm.loop.vectorize.width", i32 64}
#endif