[OpenMP][IRBuilder] Added if clause to task

[shraiysh]

Summary

This patch adds support for if clause to task construct in OpenMP
IRBuilder.

[shraiysh]

Rebase with main

[Meinersbur]

llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp

1453

[style] No Almost-Always-Auto in LLVM code.

Creating temporary instructions and removing them has issues. In addition to be inefficient, it creates issues if other code stores a pointer to it (eg. InsertPoint). Consider using splitBB which does not require a terminator.

[shraiysh]

Rebase with main. Adressed comment.

[shraiysh]

Ping for review.

[shraiysh]

Ping for review!

[raghavendhra]

LGTM

[shraiysh]

Rebase with main. Thanks for the review @raghavendhra.

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

public:
   /// Generator for `#omp task`
   ///
   /// \param Loc The location where the task construct was encountered.
   /// \param AllocaIP The insertion point to be used for alloca instructions.
   /// \param BodyGenCB Callback that will generate the region code.
   /// \param Tied True if the task is tied, false if the task is untied.
   /// \param Final i1 value which is `true` if the task is final, `false` if the
   ///              task is not final.
+  /// \param IfCondition i1 value. If it evaluates to `false`, an undeferred
+  ///                    task is generated, and the encountering thread must
+  ///                    suspend the current task region, for which execution
+  ///                    cannot be resumed until execution of the structured
+  ///                    block that is associated with the generated task is
+  ///                    completed.
   InsertPointTy createTask(const LocationDescription &Loc,
                            InsertPointTy AllocaIP, BodyGenCallbackTy BodyGenCB,
-                           bool Tied = true, Value *Final = nullptr);
+                           bool Tied = true, Value *Final = nullptr,
+                           Value *IfCondition = nullptr);
 
   /// Generator for the taskgroup construct
   ///
   /// \param Loc The location where the taskgroup construct was encountered.
   /// \param AllocaIP The insertion point to be used for alloca instructions.
   /// \param BodyGenCB Callback that will generate the region code.
   InsertPointTy createTaskgroup(const LocationDescription &Loc,
                                 InsertPointTy AllocaIP,

llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp

 #include "llvm/Analysis/CodeMetrics.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
 #include "llvm/Analysis/ScalarEvolution.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/IR/CFG.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DebugInfoMetadata.h"
+#include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/GlobalVariable.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/MDBuilder.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/IR/Value.h"
 #include "llvm/MC/TargetRegistry.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Target/TargetMachine.h"
void OpenMPIRBuilder::createTaskyield(const LocationDescription &Loc) {
   if (!updateToLocation(Loc))
     return;
   emitTaskyieldImpl(Loc);
 }
 
 OpenMPIRBuilder::InsertPointTy
 OpenMPIRBuilder::createTask(const LocationDescription &Loc,
                             InsertPointTy AllocaIP, BodyGenCallbackTy BodyGenCB,
-                            bool Tied, Value *Final) {
+                            bool Tied, Value *Final, Value *IfCondition) {
   if (!updateToLocation(Loc))
     return InsertPointTy();
 
   uint32_t SrcLocStrSize;
   Constant *SrcLocStr = getOrCreateSrcLocStr(Loc, SrcLocStrSize);
   Value *Ident = getOrCreateIdent(SrcLocStr, SrcLocStrSize);
   // The current basic block is split into four basic blocks. After outlining,
   // they will be mapped as follows:
OpenMPIRBuilder::createTask(const LocationDescription &Loc,
   BasicBlock *TaskBodyBB = splitBB(Builder, /*CreateBranch=*/true, "task.body");
   BasicBlock *TaskAllocaBB =
       splitBB(Builder, /*CreateBranch=*/true, "task.alloca");
 
   OutlineInfo OI;
   OI.EntryBB = TaskAllocaBB;
   OI.OuterAllocaBB = AllocaIP.getBlock();
   OI.ExitBB = TaskExitBB;
-  OI.PostOutlineCB = [this, Ident, Tied, Final](Function &OutlinedFn) {
+  OI.PostOutlineCB = [this, Ident, Tied, Final,
+                      IfCondition](Function &OutlinedFn) {
     // The input IR here looks like the following-
     // ```
     // func @current_fn() {
     //   outlined_fn(%args)
     // }
     // func @outlined_fn(%args) { ... }
     // ```
     //
OI.PostOutlineCB = [this, Ident, Tied, Final,
     // Copy the arguments for outlined function
     if (HasTaskData) {
       Value *TaskData = StaleCI->getArgOperand(0);
       Align Alignment = TaskData->getPointerAlignment(M.getDataLayout());
       Builder.CreateMemCpy(NewTaskData, Alignment, TaskData, Alignment,
                            TaskSize);
     }
 
+    // In the presence of the `if` clause, the following IR is generated:
+    //    ...
+    //    %data = call @__kmpc_omp_task_alloc(...)
+    //    br i1 %if_condition, label %then, label %else
+    //  then:
+    //    call @__kmpc_omp_task(...)
+    //    br label %exit
+    //  else:
+    //    call @__kmpc_omp_task_begin_if0(...)
+    //    call @wrapper_fn(...)
+    //    call @__kmpc_omp_task_complete_if0(...)
+    //    br label %exit
+    //  exit:
+    //    ...
+    if (IfCondition) {
+      // `SplitBlockAndInsertIfThenElse` requires the block to have a
+      // terminator.
+      BasicBlock *NewBasicBlock =
+          splitBB(Builder, /*CreateBranch=*/true, "if.end");
+      Instruction *IfTerminator =
+          NewBasicBlock->getSinglePredecessor()->getTerminator();
+      Instruction *ThenTI = IfTerminator, *ElseTI = nullptr;
+      Builder.SetInsertPoint(IfTerminator);
+      SplitBlockAndInsertIfThenElse(IfCondition, IfTerminator, &ThenTI,
+                                    &ElseTI);
+      Builder.SetInsertPoint(ElseTI);
+      Function *TaskBeginFn =
+          getOrCreateRuntimeFunctionPtr(OMPRTL___kmpc_omp_task_begin_if0);
+      Function *TaskCompleteFn =
+          getOrCreateRuntimeFunctionPtr(OMPRTL___kmpc_omp_task_complete_if0);
+      Builder.CreateCall(TaskBeginFn, {Ident, ThreadID, NewTaskData});
+      if (HasTaskData)
+        Builder.CreateCall(WrapperFunc, {ThreadID, NewTaskData});
+      else
+        Builder.CreateCall(WrapperFunc, {ThreadID});
+      Builder.CreateCall(TaskCompleteFn, {Ident, ThreadID, NewTaskData});
+      Builder.SetInsertPoint(ThenTI);
+    }
     // Emit the @__kmpc_omp_task runtime call to spawn the task
     Function *TaskFn = getOrCreateRuntimeFunctionPtr(OMPRTL___kmpc_omp_task);
     Builder.CreateCall(TaskFn, {Ident, ThreadID, NewTaskData});
 
     StaleCI->eraseFromParent();
 
     // Emit the body for wrapper function
     BasicBlock *WrapperEntryBB =

llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp

if (SelectInst *Select = dyn_cast<SelectInst>(op)) {
              TrueValue->getSExtValue() == 2 && FalseValue->getSExtValue() == 0;
     }
     return false;
   }));
 
   EXPECT_FALSE(verifyModule(*M, &errs()));
 }
 
+TEST_F(OpenMPIRBuilderTest, CreateTaskIfCondition) {
+  using InsertPointTy = OpenMPIRBuilder::InsertPointTy;
+  OpenMPIRBuilder OMPBuilder(*M);
+  OMPBuilder.initialize();
+  F->setName("func");
+  IRBuilder<> Builder(BB);
+  auto BodyGenCB = [&](InsertPointTy AllocaIP, InsertPointTy CodeGenIP) {};
+  IRBuilderBase::InsertPoint AllocaIP = Builder.saveIP();
+  BasicBlock *BodyBB = splitBB(Builder, /*CreateBranch=*/true, "alloca.split");
+  Builder.SetInsertPoint(BodyBB);
+  Value *IfCondition = Builder.CreateICmp(
+      CmpInst::Predicate::ICMP_EQ, F->getArg(0),
+      ConstantInt::get(Type::getInt32Ty(M->getContext()), 0U));
+  OpenMPIRBuilder::LocationDescription Loc(Builder.saveIP(), DL);
+  Builder.restoreIP(OMPBuilder.createTask(Loc, AllocaIP, BodyGenCB,
+                                          /*Tied=*/false, /*Final=*/nullptr,
+                                          IfCondition));
+  OMPBuilder.finalize();
+  Builder.CreateRetVoid();
+
+  EXPECT_FALSE(verifyModule(*M, &errs()));
+
+  CallInst *TaskAllocCall = dyn_cast<CallInst>(
+      OMPBuilder.getOrCreateRuntimeFunctionPtr(OMPRTL___kmpc_omp_task_alloc)
+          ->user_back());
+  ASSERT_NE(TaskAllocCall, nullptr);
+
+  // Check the branching is based on the if condition argument.
+  BranchInst *IfConditionBranchInst =
+      dyn_cast<BranchInst>(TaskAllocCall->getParent()->getTerminator());
+  ASSERT_NE(IfConditionBranchInst, nullptr);
+  ASSERT_TRUE(IfConditionBranchInst->isConditional());
+  EXPECT_EQ(IfConditionBranchInst->getCondition(), IfCondition);
+
+  // Check that the `__kmpc_omp_task` executes only in the then branch.
+  CallInst *TaskCall = dyn_cast<CallInst>(
+      OMPBuilder.getOrCreateRuntimeFunctionPtr(OMPRTL___kmpc_omp_task)
+          ->user_back());
+  ASSERT_NE(TaskCall, nullptr);
+  EXPECT_EQ(TaskCall->getParent(), IfConditionBranchInst->getSuccessor(0));
+
+  // Check that the OpenMP Runtime Functions specific to `if` clause execute
+  // only in the else branch. Also check that the function call is between the
+  // `__kmpc_omp_task_begin_if0` and `__kmpc_omp_task_complete_if0` calls.
+  CallInst *TaskBeginIfCall = dyn_cast<CallInst>(
+      OMPBuilder
+          .getOrCreateRuntimeFunctionPtr(OMPRTL___kmpc_omp_task_begin_if0)
+          ->user_back());
+  CallInst *TaskCompleteCall = dyn_cast<CallInst>(
+      OMPBuilder
+          .getOrCreateRuntimeFunctionPtr(OMPRTL___kmpc_omp_task_complete_if0)
+          ->user_back());
+  ASSERT_NE(TaskBeginIfCall, nullptr);
+  ASSERT_NE(TaskCompleteCall, nullptr);
+  Function *WrapperFunc =
+      dyn_cast<Function>(TaskAllocCall->getArgOperand(5)->stripPointerCasts());
+  ASSERT_NE(WrapperFunc, nullptr);
+  CallInst *WrapperFuncCall = dyn_cast<CallInst>(WrapperFunc->user_back());
+  ASSERT_NE(WrapperFuncCall, nullptr);
+  EXPECT_EQ(TaskBeginIfCall->getParent(),
+            IfConditionBranchInst->getSuccessor(1));
+  EXPECT_EQ(TaskBeginIfCall->getNextNonDebugInstruction(), WrapperFuncCall);
+  EXPECT_EQ(WrapperFuncCall->getNextNonDebugInstruction(), TaskCompleteCall);
+}
+
 TEST_F(OpenMPIRBuilderTest, CreateTaskgroup) {
   using InsertPointTy = OpenMPIRBuilder::InsertPointTy;
   OpenMPIRBuilder OMPBuilder(*M);
   OMPBuilder.initialize();
   F->setName("func");
   IRBuilder<> Builder(BB);
 
   AllocaInst *ValPtr32 = Builder.CreateAlloca(Builder.getInt32Ty());