[OpenMP][NVPTX] Enable default scheduling for parallel for in non-SPMD cases.

[gtbercea]

Summary

This patch enables the choosing of the default schedule for parallel for loops even in non-SPMD cases.

[ABataev]

lib/CodeGen/CGOpenMPRuntimeNVPTX.h

350

Why do you need to change the type of the parameter?

[gtbercea]

Refactor.

[ABataev]

What about tests?

[gtbercea]

Add test.

[ABataev]

test/OpenMP/nvptx_parallel_for_codegen.cpp

44 ↗

(On Diff #171310)

Do not use names of the IR vars, use regular expressions.

[gtbercea]

Add test.

[gtbercea]

ping

[ABataev]

LG

lib/CodeGen/CGOpenMPRuntime.h

public:
   /// dist_schedule clause.
   virtual void getDefaultDistScheduleAndChunk(CodeGenFunction &CGF,
       const OMPLoopDirective &S, OpenMPDistScheduleClauseKind &ScheduleKind,
       llvm::Value *&Chunk) const {}
 
   /// Choose default schedule type and chunk value for the
   /// schedule clause.
   virtual void getDefaultScheduleAndChunk(CodeGenFunction &CGF,
-      const OMPLoopDirective &S, OpenMPScheduleClauseKind &ScheduleKind,
+      const OMPLoopDirective &S, OpenMPScheduleTy &ScheduleKind,
       llvm::Value *&Chunk) const {}
 
   /// Emits call of the outlined function with the provided arguments,
   /// translating these arguments to correct target-specific arguments.
   virtual void
   emitOutlinedFunctionCall(CodeGenFunction &CGF, SourceLocation Loc,
                            llvm::Value *OutlinedFn,
                            ArrayRef<llvm::Value *> Args = llvm::None) const;

lib/CodeGen/CGOpenMPRuntimeNVPTX.h

public:
 
   /// Choose a default value for the dist_schedule clause.
   void getDefaultDistScheduleAndChunk(CodeGenFunction &CGF,
       const OMPLoopDirective &S, OpenMPDistScheduleClauseKind &ScheduleKind,
       llvm::Value *&Chunk) const override;
 
   /// Choose a default value for the schedule clause.
   void getDefaultScheduleAndChunk(CodeGenFunction &CGF,
-      const OMPLoopDirective &S, OpenMPScheduleClauseKind &ScheduleKind,
+      const OMPLoopDirective &S, OpenMPScheduleTy &ScheduleKind,
       llvm::Value *&Chunk) const override;
 
 private:
   /// Track the execution mode when codegening directives within a target
   /// region. The appropriate mode (SPMD/NON-SPMD) is set on entry to the
   /// target region and used by containing directives such as 'parallel'
   /// to emit optimized code.
   ExecutionMode CurrentExecutionMode = EM_Unknown;

lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp

void CGOpenMPRuntimeNVPTX::getDefaultDistScheduleAndChunk(
     CodeGenFunction &CGF, const OMPLoopDirective &S,
     OpenMPDistScheduleClauseKind &ScheduleKind,
     llvm::Value *&Chunk) const {
   if (getExecutionMode() == CGOpenMPRuntimeNVPTX::EM_SPMD) {
     ScheduleKind = OMPC_DIST_SCHEDULE_static;
     Chunk = CGF.EmitScalarConversion(getNVPTXNumThreads(CGF),
         CGF.getContext().getIntTypeForBitwidth(32, /*Signed=*/0),
         S.getIterationVariable()->getType(), S.getBeginLoc());
+    return;
   }
+  CGOpenMPRuntime::getDefaultDistScheduleAndChunk(
+      CGF, S, ScheduleKind, Chunk);
 }
 
 void CGOpenMPRuntimeNVPTX::getDefaultScheduleAndChunk(
     CodeGenFunction &CGF, const OMPLoopDirective &S,
-    OpenMPScheduleClauseKind &ScheduleKind,
+    OpenMPScheduleTy &ScheduleKind,
     llvm::Value *&Chunk) const {
-  if (getExecutionMode() == CGOpenMPRuntimeNVPTX::EM_SPMD) {
-    ScheduleKind = OMPC_SCHEDULE_static;
-    Chunk = CGF.Builder.getIntN(CGF.getContext().getTypeSize(
-        S.getIterationVariable()->getType()), 1);
-  }
-}
+  ScheduleKind.Schedule = OMPC_SCHEDULE_static;

lib/CodeGen/CGStmtOpenMP.cpp

// Emit 'then' code.
           Chunk = EmitScalarExpr(Ch);
           Chunk = EmitScalarConversion(Chunk, Ch->getType(),
                                        S.getIterationVariable()->getType(),
                                        S.getBeginLoc());
         }
       } else {
         // Default behaviour for schedule clause.
         CGM.getOpenMPRuntime().getDefaultScheduleAndChunk(
-            *this, S, ScheduleKind.Schedule, Chunk);
+            *this, S, ScheduleKind, Chunk);
       }
       const unsigned IVSize = getContext().getTypeSize(IVExpr->getType());
       const bool IVSigned = IVExpr->getType()->hasSignedIntegerRepresentation();
       // OpenMP 4.5, 2.7.1 Loop Construct, Description.
       // If the static schedule kind is specified or if the ordered clause is
       // specified, and if no monotonic modifier is specified, the effect will
       // be as if the monotonic modifier was specified.
       if (RT.isStaticNonchunked(ScheduleKind.Schedule,