[OpenMP] Lower taskyield using OpenMP IR Builder

[rogfer01]

Summary

This is similar to D69828.

Special codegen for enclosing untied tasks is still done in clang.

[jdoerfert]

LGTM.

@fghanim started a spreadsheet to coordinate our work:

https://docs.google.com/spreadsheets/d/1FvHPuSkGbl4mQZRAwCIndvQx9dQboffiD-xD0oqxgU0/edit?usp=sharing

Feel free to add directives there that you plan to work on.

[rogfer01]

ChangeLog:

• Rebase

[rogfer01]

ChangeLog:

• Rebase

clang/lib/CodeGen/CGOpenMPRuntime.cpp

void CGOpenMPRuntime::emitMasterRegion(CodeGenFunction &CGF,
   emitInlinedDirective(CGF, OMPD_master, MasterOpGen);
   Action.Done(CGF);
 }
 
 void CGOpenMPRuntime::emitTaskyieldCall(CodeGenFunction &CGF,
                                         SourceLocation Loc) {
   if (!CGF.HaveInsertPoint())
     return;
+  llvm::OpenMPIRBuilder *OMPBuilder = CGF.CGM.getOpenMPIRBuilder();
+  if (OMPBuilder) {
+    OMPBuilder->CreateTaskyield(CGF.Builder);
+  } else {
     // Build call __kmpc_omp_taskyield(loc, thread_id, 0);
     llvm::Value *Args[] = {
         emitUpdateLocation(CGF, Loc), getThreadID(CGF, Loc),
         llvm::ConstantInt::get(CGM.IntTy, /*V=*/0, /*isSigned=*/true)};
-  CGF.EmitRuntimeCall(createRuntimeFunction(OMPRTL__kmpc_omp_taskyield), Args);
+    CGF.EmitRuntimeCall(createRuntimeFunction(OMPRTL__kmpc_omp_taskyield),
+                        Args);
+  }
+
   if (auto *Region = dyn_cast_or_null<CGOpenMPRegionInfo>(CGF.CapturedStmtInfo))
     Region->emitUntiedSwitch(CGF);
 }
 
 void CGOpenMPRuntime::emitTaskgroupRegion(CodeGenFunction &CGF,
                                           const RegionCodeGenTy &TaskgroupOpGen,
                                           SourceLocation Loc) {
   if (!CGF.HaveInsertPoint())

clang/test/OpenMP/taskyield_codegen.cpp

 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s
 // RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -emit-pch -o %t %s
 // RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
+//
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-enable-irbuilder -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp -fopenmp-enable-irbuilder -x c++ -std=c++11 -triple x86_64-unknown-unknown -emit-pch -o %t %s
+// RUN: %clang_cc1 -fopenmp -fopenmp-enable-irbuilder -x c++ -triple x86_64-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
 
 // RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
 // RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple x86_64-unknown-unknown -emit-pch -o %t %s
 // RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
 // SIMD-ONLY0-NOT: {{__kmpc|__tgt}}
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER

llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h

public:
   ///
   /// \returns The insertion position *after* the parallel.
   IRBuilder<>::InsertPoint
   CreateParallel(const LocationDescription &Loc, BodyGenCallbackTy BodyGenCB,
                  PrivatizeCallbackTy PrivCB, FinalizeCallbackTy FiniCB,
                  Value *IfCondition, Value *NumThreads,
                  omp::ProcBindKind ProcBind, bool IsCancellable);
 
+
   /// Generator for '#omp flush'
   ///
   /// \param Loc The location where the flush directive was encountered
   void CreateFlush(const LocationDescription &Loc);
 
   /// Generator for '#omp taskwait'
   ///
   /// \param Loc The location where the taskwait directive was encountered.
   void CreateTaskwait(const LocationDescription& Loc);
 
+  /// Generator for '#omp taskyield'
+  ///
+  /// \param Loc The location where the taskyield directive was encountered.
+  void CreateTaskyield(const LocationDescription& Loc);
+
   ///}
 
 
 private:
   /// Update the internal location to \p Loc.
   bool updateToLocation(const LocationDescription &Loc) {
     Builder.restoreIP(Loc.IP);
     Builder.SetCurrentDebugLocation(Loc.DL);
return !FinalizationStack.empty() &&
            FinalizationStack.back().DK == DK;
   }
 
   /// Generate a taskwait runtime call.
   ///
   /// \param Loc The location at which the request originated and is fulfilled.
   void emitTaskwaitImpl(const LocationDescription &Loc);
 
+  /// Generate a taskyield runtime call.
+  ///
+  /// \param Loc The location at which the request originated and is fulfilled.
+  void emitTaskyieldImpl(const LocationDescription &Loc);
+
   /// Return the current thread ID.
   ///
   /// \param Ident The ident (ident_t*) describing the query origin.
   Value *getOrCreateThreadID(Value *Ident);
 
   /// The underlying LLVM-IR module
   Module &M;
 

llvm/include/llvm/Frontend/OpenMP/OMPKinds.def

 
 __OMP_RTL(__kmpc_barrier, false, Void, IdentPtr, Int32)
 __OMP_RTL(__kmpc_cancel, false, Int32, IdentPtr, Int32, Int32)
 __OMP_RTL(__kmpc_cancel_barrier, false, Int32, IdentPtr, Int32)
 __OMP_RTL(__kmpc_flush, false, Void, IdentPtr)
 __OMP_RTL(__kmpc_global_thread_num, false, Int32, IdentPtr)
 __OMP_RTL(__kmpc_fork_call, true, Void, IdentPtr, Int32, ParallelTaskPtr)
 __OMP_RTL(__kmpc_omp_taskwait, false, Int32, IdentPtr, Int32)
+__OMP_RTL(__kmpc_omp_taskyield, false, Int32, IdentPtr, Int32, Int32)
 __OMP_RTL(__kmpc_push_num_threads, false, Void, IdentPtr, Int32,
           /* Int */ Int32)
 __OMP_RTL(__kmpc_push_proc_bind, false, Void, IdentPtr, Int32, /* Int */ Int32)
 __OMP_RTL(__kmpc_serialized_parallel, false, Void, IdentPtr, Int32)
 __OMP_RTL(__kmpc_end_serialized_parallel, false, Void, IdentPtr, Int32)
 
 __OMP_RTL(omp_get_thread_num, false, Int32, )
 __OMP_RTL(omp_get_num_threads, false, Int32, )

llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp

Builder.CreateCall(getOrCreateRuntimeFunction(OMPRTL___kmpc_omp_taskwait),
                      Args);
 }
 
 void OpenMPIRBuilder::CreateTaskwait(const LocationDescription &Loc) {
   if (!updateToLocation(Loc))
     return;
   emitTaskwaitImpl(Loc);
 }
+
+void OpenMPIRBuilder::emitTaskyieldImpl(const LocationDescription &Loc) {
+  // Build call __kmpc_omp_taskyield(loc, thread_id, 0);
+  Constant *SrcLocStr = getOrCreateSrcLocStr(Loc);
+  Value *Ident = getOrCreateIdent(SrcLocStr);
+  Constant *I32Null = ConstantInt::getNullValue(Int32);
+  Value *Args[] = {Ident, getOrCreateThreadID(Ident), I32Null};
+
+  Builder.CreateCall(getOrCreateRuntimeFunction(OMPRTL___kmpc_omp_taskyield),
+                     Args);
+}
+
+void OpenMPIRBuilder::CreateTaskyield(const LocationDescription &Loc) {
+  if (!updateToLocation(Loc))
+    return;
+  emitTaskyieldImpl(Loc);
+}