Applied remarks

Author: DominikAdamski

clang/include/clang/Driver/Options.td

@@ -3836,18 +3836,21 @@ let Group = f_Group in {
 
 def fopenmp_target_debug_EQ : Joined<["-"], "fopenmp-target-debug=">;
 def fopenmp_assume_teams_oversubscription : Flag<["-"], "fopenmp-assume-teams-oversubscription">,
-  HelpText<"Allow enforcement to ensure there are enough teams to cover the "
-           "loop iteration space. It may ignore environment variables. "
-           "If the fopenmp-assume-teams-oversubscription and "
-           "fopenmp-assume-threads-oversubscription flags are set, Flang may "
-           "generate more optimized OpenMP kernels for target teams distribute "
-           "parallel do pragmas.">;
+  HelpText<"Allow the optimizer to discretely increase the number of "
+           "teams. May cause ignore environment variables that set "
+           "the number of teams to be ignored. The combination of "
+           "-fopenmp-assume-teams-oversubscription "
+           "and -fopenmp-assume-threads-oversubscription "
+           "may allow the conversion of loops into sequential code by "
+           "ensuring that each team/thread executes at most one iteration.">;
 def fopenmp_assume_threads_oversubscription : Flag<["-"], "fopenmp-assume-threads-oversubscription">,
-  HelpText<"Assume threads oversubscription. If the "
-           "fopenmp-assume-teams-oversubscription and "
-           "fopenmp-assume-threads-oversubscription flags are set, Flang may "
-           "generate more optimized OpenMP kernels for target teams distribute "
-           "parallel do pragmas.">;
+  HelpText<"Allow the optimizer to discretely increase the number of "
+           "threads. May cause ignore environment variables that set "
+           "the number of threads to be ignored. The combination of "
+           "-fopenmp-assume-teams-oversubscription "
+           "and -fopenmp-assume-threads-oversubscription "
+           "may allow the conversion of loops into sequential code by "
+           "ensuring that each team/thread executes at most one iteration.">;
 def fno_openmp_assume_teams_oversubscription : Flag<["-"], "fno-openmp-assume-teams-oversubscription">,
   HelpText<"Do not assume teams oversubscription.">;
 def fno_openmp_assume_threads_oversubscription : Flag<["-"], "fno-openmp-assume-threads-oversubscription">,

llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp

@@ -5004,8 +5004,9 @@ static void createTargetLoopWorkshareCall(OpenMPIRBuilder *OMPBuilder,
   if (LoopType == WorksharingLoopType::DistributeForStaticLoop) {
     RealArgs.push_back(ConstantInt::get(TripCountTy, 0));
     RealArgs.push_back(ConstantInt::get(Builder.getInt8Ty(), NoLoop));
-  } else
+  } else {
     RealArgs.push_back(ConstantInt::get(Builder.getInt8Ty(), 0));
+  }
 
   Builder.CreateCall(RTLFn, RealArgs);
 }

mlir/include/mlir/Dialect/OpenMP/OpenMPEnums.td

@@ -234,7 +234,15 @@ def TargetRegionFlagsNoLoop : I32BitEnumAttrCaseBit<"no_loop", 3>;
 
 def TargetRegionFlags : OpenMP_BitEnumAttr<
     "TargetRegionFlags",
-    "target region property flags", [
+    "These flags describe properties of the target kernel. "
+    "TargetRegionFlagsGeneric - denotes generic kernel. "
+    "TargetRegionFlagsSpmd - denotes SPMD kernel. "
+    "TargetRegionFlagsNoLoop - denotes kernel where "
+    "num_teams * num_threads >= loop_trip_count. It allows the conversion "
+    "of loops into sequential code by ensuring that each team/thread "
+    "executes at most one iteration. "
+    "TargetRegionFlagsTripCount - checks if the loop trip count should be "
+    "calculated.", [
       TargetRegionFlagsNone,
       TargetRegionFlagsGeneric,
       TargetRegionFlagsSpmd,

mlir/lib/Dialect/OpenMP/IR/OpenMPDialect.cpp

@@ -2112,11 +2112,13 @@ static bool canPromoteToNoLoop(Operation *capturedOp, TeamsOp teamsOp,
   // num_teams clause can break no-loop teams/threads assumption.
   if (teamsOp.getNumTeamsUpper())
     return false;
+
   // Reduction kernels are slower in no-loop mode.
   if (teamsOp.getNumReductionVars())
     return false;
   if (wsLoopOp->getNumReductionVars())
     return false;
+
   // Check if the user allows the promotion of kernels to no-loop mode.
   OffloadModuleInterface offloadMod =
       capturedOp->getParentOfType<omp::OffloadModuleInterface>();

offload/test/offloading/fortran/target-no-loop.f90

@@ -1,4 +1,4 @@
-! REQUIRES: flang, amdgpu
+! REQUIRES: flang
 
 ! RUN: %libomptarget-compile-fortran-generic -O3  -fopenmp-assume-threads-oversubscription -fopenmp-assume-teams-oversubscription
 ! RUN: env LIBOMPTARGET_INFO=16 OMP_NUM_TEAMS=16 OMP_TEAMS_THREAD_LIMIT=16 %libomptarget-run-generic 2>&1 | %fcheck-generic