1 files changed, 118 insertions, 10 deletions
diff --git a/lib/CodeGen/CGOpenMPRuntimeNVPTX.h b/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
index 4010b46a4cbd..ae25e94759e6 100644
--- a/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
+++ b/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
@@ -43,6 +43,8 @@ private:
     void createWorkerFunction(CodeGenModule &CGM);
   };
 
+  bool isInSpmdExecutionMode() const;
+
   /// \brief Emit the worker function for the current target region.
   void emitWorkerFunction(WorkerFunctionState &WST);
 
@@ -58,11 +60,12 @@ private:
   /// function.
   void emitGenericEntryFooter(CodeGenFunction &CGF, EntryFunctionState &EST);
 
-  /// \brief Returns specified OpenMP runtime function for the current OpenMP
-  /// implementation.  Specialized for the NVPTX device.
-  /// \param Function OpenMP runtime function.
-  /// \return Specified function.
-  llvm::Constant *createNVPTXRuntimeFunction(unsigned Function);
+  /// \brief Helper for Spmd mode target directive's entry function.
+  void emitSpmdEntryHeader(CodeGenFunction &CGF, EntryFunctionState &EST,
+                           const OMPExecutableDirective &D);
+
+  /// \brief Signal termination of Spmd mode execution.
+  void emitSpmdEntryFooter(CodeGenFunction &CGF, EntryFunctionState &EST);
 
   //
   // Base class overrides.
@@ -87,6 +90,22 @@ private:
                          llvm::Constant *&OutlinedFnID, bool IsOffloadEntry,
                          const RegionCodeGenTy &CodeGen);
 
+  /// \brief Emit outlined function specialized for the Single Program
+  /// Multiple Data programming model for applicable target directives on the
+  /// NVPTX device.
+  /// \param D Directive to emit.
+  /// \param ParentName Name of the function that encloses the target region.
+  /// \param OutlinedFn Outlined function value to be defined by this call.
+  /// \param OutlinedFnID Outlined function ID value to be defined by this call.
+  /// \param IsOffloadEntry True if the outlined function is an offload entry.
+  /// \param CodeGen Object containing the target statements.
+  /// An outlined function may not be an entry if, e.g. the if clause always
+  /// evaluates to false.
+  void emitSpmdKernel(const OMPExecutableDirective &D, StringRef ParentName,
+                      llvm::Function *&OutlinedFn,
+                      llvm::Constant *&OutlinedFnID, bool IsOffloadEntry,
+                      const RegionCodeGenTy &CodeGen);
+
   /// \brief Emit outlined function for 'target' directive on the NVPTX
   /// device.
   /// \param D Directive to emit.
@@ -118,6 +137,22 @@ private:
                                ArrayRef<llvm::Value *> CapturedVars,
                                const Expr *IfCond);
 
+  /// \brief Emits code for parallel or serial call of the \a OutlinedFn with
+  /// variables captured in a record which address is stored in \a
+  /// CapturedStruct.
+  /// This call is for a parallel directive within an SPMD target directive.
+  /// \param OutlinedFn Outlined function to be run in parallel threads. Type of
+  /// this function is void(*)(kmp_int32 *, kmp_int32, struct context_vars*).
+  /// \param CapturedVars A pointer to the record with the references to
+  /// variables used in \a OutlinedFn function.
+  /// \param IfCond Condition in the associated 'if' clause, if it was
+  /// specified, nullptr otherwise.
+  ///
+  void emitSpmdParallelCall(CodeGenFunction &CGF, SourceLocation Loc,
+                            llvm::Value *OutlinedFn,
+                            ArrayRef<llvm::Value *> CapturedVars,
+                            const Expr *IfCond);
+
 protected:
   /// \brief Get the function name of an outlined region.
   //  The name can be customized depending on the target.
@@ -129,6 +164,20 @@ protected:
 public:
   explicit CGOpenMPRuntimeNVPTX(CodeGenModule &CGM);
 
+  /// \brief Emit call to void __kmpc_push_proc_bind(ident_t *loc, kmp_int32
+  /// global_tid, int proc_bind) to generate code for 'proc_bind' clause.
+  virtual void emitProcBindClause(CodeGenFunction &CGF,
+                                  OpenMPProcBindClauseKind ProcBind,
+                                  SourceLocation Loc) override;
+
+  /// \brief Emits call to void __kmpc_push_num_threads(ident_t *loc, kmp_int32
+  /// global_tid, kmp_int32 num_threads) to generate code for 'num_threads'
+  /// clause.
+  /// \param NumThreads An integer value of threads.
+  virtual void emitNumThreadsClause(CodeGenFunction &CGF,
+                                    llvm::Value *NumThreads,
+                                    SourceLocation Loc) override;
+
   /// \brief This function ought to emit, in the general case, a call to
   // the openmp runtime kmpc_push_num_teams. In NVPTX backend it is not needed
   // as these numbers are obtained through the PTX grid and block configuration.
@@ -138,7 +187,22 @@ public:
                           const Expr *ThreadLimit, SourceLocation Loc) override;
 
   /// \brief Emits inlined function for the specified OpenMP parallel
-  //  directive but an inlined function for teams.
+  //  directive.
+  /// \a D. This outlined function has type void(*)(kmp_int32 *ThreadID,
+  /// kmp_int32 BoundID, struct context_vars*).
+  /// \param D OpenMP directive.
+  /// \param ThreadIDVar Variable for thread id in the current OpenMP region.
+  /// \param InnermostKind Kind of innermost directive (for simple directives it
+  /// is a directive itself, for combined - its innermost directive).
+  /// \param CodeGen Code generation sequence for the \a D directive.
+  llvm::Value *
+  emitParallelOutlinedFunction(const OMPExecutableDirective &D,
+                               const VarDecl *ThreadIDVar,
+                               OpenMPDirectiveKind InnermostKind,
+                               const RegionCodeGenTy &CodeGen) override;
+
+  /// \brief Emits inlined function for the specified OpenMP teams
+  //  directive.
   /// \a D. This outlined function has type void(*)(kmp_int32 *ThreadID,
   /// kmp_int32 BoundID, struct context_vars*).
   /// \param D OpenMP directive.
@@ -147,10 +211,10 @@ public:
   /// is a directive itself, for combined - its innermost directive).
   /// \param CodeGen Code generation sequence for the \a D directive.
   llvm::Value *
-  emitParallelOrTeamsOutlinedFunction(const OMPExecutableDirective &D,
-                                      const VarDecl *ThreadIDVar,
-                                      OpenMPDirectiveKind InnermostKind,
-                                      const RegionCodeGenTy &CodeGen) override;
+  emitTeamsOutlinedFunction(const OMPExecutableDirective &D,
+                            const VarDecl *ThreadIDVar,
+                            OpenMPDirectiveKind InnermostKind,
+                            const RegionCodeGenTy &CodeGen) override;
 
   /// \brief Emits code for teams call of the \a OutlinedFn with
   /// variables captured in a record which address is stored in \a
@@ -177,6 +241,50 @@ public:
                         llvm::Value *OutlinedFn,
                         ArrayRef<llvm::Value *> CapturedVars,
                         const Expr *IfCond) override;
+
+  /// Emit a code for reduction clause.
+  ///
+  /// \param Privates List of private copies for original reduction arguments.
+  /// \param LHSExprs List of LHS in \a ReductionOps reduction operations.
+  /// \param RHSExprs List of RHS in \a ReductionOps reduction operations.
+  /// \param ReductionOps List of reduction operations in form 'LHS binop RHS'
+  /// or 'operator binop(LHS, RHS)'.
+  /// \param Options List of options for reduction codegen:
+  ///     WithNowait true if parent directive has also nowait clause, false
+  ///     otherwise.
+  ///     SimpleReduction Emit reduction operation only. Used for omp simd
+  ///     directive on the host.
+  ///     ReductionKind The kind of reduction to perform.
+  virtual void emitReduction(CodeGenFunction &CGF, SourceLocation Loc,
+                             ArrayRef<const Expr *> Privates,
+                             ArrayRef<const Expr *> LHSExprs,
+                             ArrayRef<const Expr *> RHSExprs,
+                             ArrayRef<const Expr *> ReductionOps,
+                             ReductionOptionsTy Options) override;
+
+  /// Returns specified OpenMP runtime function for the current OpenMP
+  /// implementation.  Specialized for the NVPTX device.
+  /// \param Function OpenMP runtime function.
+  /// \return Specified function.
+  llvm::Constant *createNVPTXRuntimeFunction(unsigned Function);
+
+  /// Target codegen is specialized based on two programming models: the
+  /// 'generic' fork-join model of OpenMP, and a more GPU efficient 'spmd'
+  /// model for constructs like 'target parallel' that support it.
+  enum ExecutionMode {
+    /// Single Program Multiple Data.
+    Spmd,
+    /// Generic codegen to support fork-join model.
+    Generic,
+    Unknown,
+  };
+
+private:
+  // Track the execution mode when codegening directives within a target
+  // region. The appropriate mode (generic/spmd) is set on entry to the
+  // target region and used by containing directives such as 'parallel'
+  // to emit optimized code.
+  ExecutionMode CurrentExecutionMode;
 };
 
 } // CodeGen namespace.