[OPENMP5]Use nonmonotonic modifier by default for non-static and

non-ordered loops.

According to OpenMP 5.0, 2.9.2 Worksharing-Loop Construct, Desription, If the static schedule kind is specified or if the ordered clause is specified, and if the nonmonotonic modifier is not specified, the effect is as if the monotonic modifier is specified. Otherwise, unless the monotonic modifier is specified, the effect is as if the nonmonotonic modifier is specified.
The first part of this requirement is implemented in runtime. Patch adds
support for the second, nonmonotonic, part of this requirement.

llvm-svn: 369801

2 files changed, 33 insertions, 13 deletions

diff --git a/clang/lib/CodeGen/CGOpenMPRuntime.cpp b/clang/lib/CodeGen/CGOpenMPRuntime.cpp
index 84211e33b87..99fa0790e90 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntime.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntime.cpp
@@ -3509,7 +3509,7 @@ bool CGOpenMPRuntime::isDynamic(OpenMPScheduleClauseKind ScheduleKind) const {
   return Schedule != OMP_sch_static;
 }
 
-static int addMonoNonMonoModifier(OpenMPSchedType Schedule,
+static int addMonoNonMonoModifier(CodeGenModule &CGM, OpenMPSchedType Schedule,
                                   OpenMPScheduleClauseModifier M1,
                                   OpenMPScheduleClauseModifier M2) {
   int Modifier = 0;
@@ -3543,6 +3543,18 @@ static int addMonoNonMonoModifier(OpenMPSchedType Schedule,
   case OMPC_SCHEDULE_MODIFIER_unknown:
     break;
   }
+  // OpenMP 5.0, 2.9.2 Worksharing-Loop Construct, Desription.
+  // If the static schedule kind is specified or if the ordered clause is
+  // specified, and if the nonmonotonic modifier is not specified, the effect is
+  // as if the monotonic modifier is specified. Otherwise, unless the monotonic
+  // modifier is specified, the effect is as if the nonmonotonic modifier is
+  // specified.
+  if (CGM.getLangOpts().OpenMP >= 50 && Modifier == 0) {
+    if (!(Schedule == OMP_sch_static_chunked || Schedule == OMP_sch_static ||
+          Schedule == OMP_sch_static_balanced_chunked ||
+          Schedule == OMP_ord_static_chunked || Schedule == OMP_ord_static))
+      Modifier = OMP_sch_modifier_nonmonotonic;
+  }
   return Schedule | Modifier;
 }
 
@@ -3567,13 +3579,14 @@ void CGOpenMPRuntime::emitForDispatchInit(
   llvm::Value *Chunk = DispatchValues.Chunk ? DispatchValues.Chunk
                                             : CGF.Builder.getIntN(IVSize, 1);
   llvm::Value *Args[] = {
-      emitUpdateLocation(CGF, Loc), getThreadID(CGF, Loc),
+      emitUpdateLocation(CGF, Loc),
+      getThreadID(CGF, Loc),
       CGF.Builder.getInt32(addMonoNonMonoModifier(
-          Schedule, ScheduleKind.M1, ScheduleKind.M2)), // Schedule type
-      DispatchValues.LB,                                // Lower
-      DispatchValues.UB,                                // Upper
-      CGF.Builder.getIntN(IVSize, 1),                   // Stride
-      Chunk                                             // Chunk
+          CGM, Schedule, ScheduleKind.M1, ScheduleKind.M2)), // Schedule type
+      DispatchValues.LB,                                     // Lower
+      DispatchValues.UB,                                     // Upper
+      CGF.Builder.getIntN(IVSize, 1),                        // Stride
+      Chunk                                                  // Chunk
   };
   CGF.EmitRuntimeCall(createDispatchInitFunction(IVSize, IVSigned), Args);
 }
@@ -3615,7 +3628,7 @@ static void emitForStaticInitCall(
   llvm::Value *Args[] = {
       UpdateLocation,
       ThreadId,
-      CGF.Builder.getInt32(addMonoNonMonoModifier(Schedule, M1,
+      CGF.Builder.getInt32(addMonoNonMonoModifier(CGF.CGM, Schedule, M1,
                                                   M2)), // Schedule type
       Values.IL.getPointer(),                           // &isLastIter
       Values.LB.getPointer(),                           // &LB
diff --git a/clang/test/OpenMP/for_codegen.cpp b/clang/test/OpenMP/for_codegen.cpp
index 80afa1c9452..756d6ccebf4 100644
--- a/clang/test/OpenMP/for_codegen.cpp
+++ b/clang/test/OpenMP/for_codegen.cpp
@@ -1,10 +1,14 @@
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -fexceptions -fcxx-exceptions -o - -fsanitize-address-use-after-scope | FileCheck %s --check-prefix=CHECK --check-prefix=LIFETIME
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -fexceptions -fcxx-exceptions -o - -fsanitize-address-use-after-scope | FileCheck %s --check-prefix=CHECK --check-prefix=LIFETIME --check-prefix=OMP45
+// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t -fopenmp-version=50 %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -std=c++11 -include-pch %t -verify %s -emit-llvm -o - -fopenmp-version=50 | FileCheck %s --check-prefix=CHECK --check-prefix=OMP5
 // RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK --check-prefix=OMP45
 // RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -fexceptions -fcxx-exceptions -debug-info-kind=line-tables-only -x c++ -emit-llvm %s -o - | FileCheck %s --check-prefix=TERM_DEBUG
 // RUN: %clang_cc1 -main-file-name for_codegen.cpp %s -o - -emit-llvm -fprofile-instrument=clang -fprofile-instrument-path=for_codegen-test.profraw | FileCheck %s --check-prefix=PROF-INSTR-PATH
 
 // RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -fexceptions -fcxx-exceptions -o - | FileCheck --check-prefix SIMD-ONLY0 %s
+// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t -fopenmp-version=50 %s
+// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -std=c++11 -include-pch %t -verify %s -emit-llvm -o - -fopenmp-version=50 | FileCheck --check-prefix SIMD-ONLY0 %s
 // RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t %s
 // RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
 // RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp-simd -fexceptions -fcxx-exceptions -debug-info-kind=line-tables-only -x c++ -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
@@ -398,7 +402,8 @@ void dynamic1(float *a, float *b, float *c, float *d) {
 void guided7(float *a, float *b, float *c, float *d) {
 // CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]])
   #pragma omp for schedule(guided, 7)
-// CHECK: call void @__kmpc_dispatch_init_8u([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 36, i64 0, i64 16908287, i64 1, i64 7)
+// OMP45: call void @__kmpc_dispatch_init_8u([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 36, i64 0, i64 16908287, i64 1, i64 7)
+// OMP5: call void @__kmpc_dispatch_init_8u([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 1073741860, i64 0, i64 16908287, i64 1, i64 7)
 //
 // CHECK: [[HASWORK:%.+]] = call i32 @__kmpc_dispatch_next_8u([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32* [[OMP_ISLAST:%[^,]+]], i64* [[OMP_LB:%[^,]+]], i64* [[OMP_UB:%[^,]+]], i64* [[OMP_ST:%[^,]+]])
 // CHECK-NEXT: [[O_CMP:%.+]] = icmp ne i32 [[HASWORK]], 0
@@ -442,7 +447,8 @@ void test_auto(float *a, float *b, float *c, float *d) {
   unsigned int y = 0;
 // CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]])
   #pragma omp for schedule(auto) collapse(2)
-// CHECK: call void @__kmpc_dispatch_init_8([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 38, i64 0, i64 [[LAST_ITER:%[^,]+]], i64 1, i64 1)
+// OMP45: call void @__kmpc_dispatch_init_8([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 38, i64 0, i64 [[LAST_ITER:%[^,]+]], i64 1, i64 1)
+// OMP5: call void @__kmpc_dispatch_init_8([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 1073741862, i64 0, i64 [[LAST_ITER:%[^,]+]], i64 1, i64 1)
 //
 // CHECK: [[HASWORK:%.+]] = call i32 @__kmpc_dispatch_next_8([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32* [[OMP_ISLAST:%[^,]+]], i64* [[OMP_LB:%[^,]+]], i64* [[OMP_UB:%[^,]+]], i64* [[OMP_ST:%[^,]+]])
 // CHECK-NEXT: [[O_CMP:%.+]] = icmp ne i32 [[HASWORK]], 0
@@ -486,7 +492,8 @@ void runtime(float *a, float *b, float *c, float *d) {
   int x = 0;
 // CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[IDENT_T_TY]]* [[DEFAULT_LOC:[@%].+]])
   #pragma omp for collapse(2) schedule(runtime)
-// CHECK: call void @__kmpc_dispatch_init_4([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 37, i32 0, i32 199, i32 1, i32 1)
+// OMP45: call void @__kmpc_dispatch_init_4([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 37, i32 0, i32 199, i32 1, i32 1)
+// OMP5: call void @__kmpc_dispatch_init_4([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32 1073741861, i32 0, i32 199, i32 1, i32 1)
 //
 // CHECK: [[HASWORK:%.+]] = call i32 @__kmpc_dispatch_next_4([[IDENT_T_TY]]* [[DEFAULT_LOC]], i32 [[GTID]], i32* [[OMP_ISLAST:%[^,]+]], i32* [[OMP_LB:%[^,]+]], i32* [[OMP_UB:%[^,]+]], i32* [[OMP_ST:%[^,]+]])
 // CHECK-NEXT: [[O_CMP:%.+]] = icmp ne i32 [[HASWORK]], 0