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

[OPENMP] Generate !llvm.mem.loop_parallel_access metadata for loops with dynamic/guided scheduling. 

Inner bodies of OpenMP worksharing loop-based constructs with dynamic or guided scheduling are allowed to be marked with !llvm.mem.parallel_loop_access metadata for better optimization. Worksharing constructs with static scheduling cannot be marked this way (according to OpenMP standard "A data dependence between the same logical iterations in two such loops is guaranteed").
Constructs with auto and runtime scheduling are also not marked because automatically chosen scheduling may be static also.
Differential Revision: http://reviews.llvm.org/D9518

llvm-svn: 236693
This commit is contained in:
Alexey Bataev 2015-05-07 04:25:17 +00:00
parent 4fce73aabf
commit 53223c986c
3 changed files with 16 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
clang/lib/CodeGen/CGStmtOpenMP.cpp
View File

@ -886,6 +886,11 @@ void CodeGenFunction::EmitOMPForOuterLoop(OpenMPScheduleClauseKind ScheduleKind,
bool DynamicWithOrderedClause =
Dynamic && S.getSingleClause(OMPC_ordered) != nullptr;
SourceLocation Loc = S.getLocStart();
// Generate !llvm.loop.parallel metadata for loads and stores for loops with
// dynamic/guided scheduling and without ordered clause.
LoopStack.setParallel((ScheduleKind == OMPC_SCHEDULE_dynamic ||
ScheduleKind == OMPC_SCHEDULE_guided) &&
!DynamicWithOrderedClause);
EmitOMPInnerLoop(
S, LoopScope.requiresCleanups(), S.getCond(/*SeparateIter=*/false),
S.getInc(),

9
clang/test/OpenMP/for_codegen.cpp
View File

@ -41,6 +41,7 @@ void without_schedule_clause(float *a, float *b, float *c, float *d) {
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
a[i] = b[i] * c[i] * d[i];
// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}
// CHECK-NEXT: [[ADD1_2:%.+]] = add nsw i32 [[IV1_2]], 1
@ -81,6 +82,7 @@ void static_not_chunked(float *a, float *b, float *c, float *d) {
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
a[i] = b[i] * c[i] * d[i];
// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}
// CHECK-NEXT: [[ADD1_2:%.+]] = add nsw i32 [[IV1_2]], 1
@ -129,6 +131,7 @@ void static_chunked(float *a, float *b, float *c, float *d) {
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
a[i] = b[i] * c[i] * d[i];
// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}
// CHECK-NEXT: [[ADD1_2:%.+]] = add i32 [[IV1_2]], 1
@ -180,7 +183,7 @@ void dynamic1(float *a, float *b, float *c, float *d) {
// CHECK-NEXT: store i64 [[CALC_I_2]], i64* [[LC_I:.+]]
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}!llvm.mem.parallel_loop_access
a[i] = b[i] * c[i] * d[i];
// CHECK: [[IV1_2:%.+]] = load i64, i64* [[OMP_IV]]{{.*}}
// CHECK-NEXT: [[ADD1_2:%.+]] = add i64 [[IV1_2]], 1
@ -221,7 +224,7 @@ void guided7(float *a, float *b, float *c, float *d) {
// CHECK-NEXT: store i64 [[CALC_I_2]], i64* [[LC_I:.+]]
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}!llvm.mem.parallel_loop_access
a[i] = b[i] * c[i] * d[i];
// CHECK: [[IV1_2:%.+]] = load i64, i64* [[OMP_IV]]{{.*}}
// CHECK-NEXT: [[ADD1_2:%.+]] = add i64 [[IV1_2]], 1
@ -266,6 +269,7 @@ void test_auto(float *a, float *b, float *c, float *d) {
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
a[i] = b[i] * c[i] * d[i];
// CHECK: [[IV1_2:%.+]] = load i64, i64* [[OMP_IV]]{{.*}}
// CHECK-NEXT: [[ADD1_2:%.+]] = add nsw i64 [[IV1_2]], 1
@ -307,6 +311,7 @@ void runtime(float *a, float *b, float *c, float *d) {
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
a[i] = b[i] * c[i] * d[i];
// CHECK: [[IV1_2:%.+]] = load i32, i32* [[OMP_IV]]{{.*}}
// CHECK-NEXT: [[ADD1_2:%.+]] = add nsw i32 [[IV1_2]], 1

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

@ -39,6 +39,7 @@ void static_not_chunked(float *a, float *b, float *c, float *d) {
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK-NEXT: call void @__kmpc_end_ordered([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// ... end of ordered region ...
#pragma omp ordered
@ -86,6 +87,7 @@ void dynamic1(float *a, float *b, float *c, float *d) {
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK-NEXT: call void @__kmpc_end_ordered([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// ... end of ordered region ...
#pragma omp ordered
@ -139,6 +141,7 @@ void test_auto(float *a, float *b, float *c, float *d) {
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK-NEXT: call void @__kmpc_end_ordered([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// ... end of ordered region ...
#pragma omp ordered
@ -189,6 +192,7 @@ void runtime(float *a, float *b, float *c, float *d) {
// ... loop body ...
// End of body: store into a[i]:
// CHECK: store float [[RESULT:%.+]], float* {{%.+}}
// CHECK-NOT: !llvm.mem.parallel_loop_access
// CHECK-NEXT: call void @__kmpc_end_ordered([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]])
// ... end of ordered region ...
#pragma omp ordered