[OpenMPIRBuilder] Add support for distribute-parallel-for/do constructs

This patch adds codegen for `kmpc_dist_for_static_init` runtime calls, used to
support worksharing a single loop across teams and threads. This can be used to
implement `distribute parallel for/do` support.

Author: skatrak

llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp

@@ -4130,6 +4130,23 @@ Expected<CanonicalLoopInfo *> OpenMPIRBuilder::createCanonicalLoop(
   return createCanonicalLoop(LoopLoc, BodyGen, TripCount, Name);
 }
 
+// Returns an LLVM function to call for initializing loop bounds using OpenMP
+// static scheduling for composite `distribute parallel for` depending on
+// `type`. Only i32 and i64 are supported by the runtime. Always interpret
+// integers as unsigned similarly to CanonicalLoopInfo.
+static FunctionCallee
+getKmpcDistForStaticInitForType(Type *Ty, Module &M,
+                                OpenMPIRBuilder &OMPBuilder) {
+  unsigned Bitwidth = Ty->getIntegerBitWidth();
+  if (Bitwidth == 32)
+    return OMPBuilder.getOrCreateRuntimeFunction(
+        M, omp::RuntimeFunction::OMPRTL___kmpc_dist_for_static_init_4u);
+  if (Bitwidth == 64)
+    return OMPBuilder.getOrCreateRuntimeFunction(
+        M, omp::RuntimeFunction::OMPRTL___kmpc_dist_for_static_init_8u);
+  llvm_unreachable("unknown OpenMP loop iterator bitwidth");
+}
+
 // Returns an LLVM function to call for initializing loop bounds using OpenMP
 // static scheduling depending on `type`. Only i32 and i64 are supported by the
 // runtime. Always interpret integers as unsigned similarly to
@@ -4164,7 +4181,10 @@ OpenMPIRBuilder::InsertPointOrErrorTy OpenMPIRBuilder::applyStaticWorkshareLoop(
   // Declare useful OpenMP runtime functions.
   Value *IV = CLI->getIndVar();
   Type *IVTy = IV->getType();
-  FunctionCallee StaticInit = getKmpcForStaticInitForType(IVTy, M, *this);
+  FunctionCallee StaticInit =
+      LoopType == WorksharingLoopType::DistributeForStaticLoop
+          ? getKmpcDistForStaticInitForType(IVTy, M, *this)
+          : getKmpcForStaticInitForType(IVTy, M, *this);
   FunctionCallee StaticFini =
       getOrCreateRuntimeFunction(M, omp::OMPRTL___kmpc_for_static_fini);
 
@@ -4200,9 +4220,15 @@ OpenMPIRBuilder::InsertPointOrErrorTy OpenMPIRBuilder::applyStaticWorkshareLoop(
 
   // Call the "init" function and update the trip count of the loop with the
   // value it produced.
-  Builder.CreateCall(StaticInit,
-                     {SrcLoc, ThreadNum, SchedulingType, PLastIter, PLowerBound,
-                      PUpperBound, PStride, One, Zero});
+  SmallVector<Value *, 10> Args(
+      {SrcLoc, ThreadNum, SchedulingType, PLastIter, PLowerBound, PUpperBound});
+  if (LoopType == WorksharingLoopType::DistributeForStaticLoop) {
+    Value *PDistUpperBound =
+        Builder.CreateAlloca(IVTy, nullptr, "p.distupperbound");
+    Args.push_back(PDistUpperBound);
+  }
+  Args.append({PStride, One, Zero});
+  Builder.CreateCall(StaticInit, Args);
   Value *LowerBound = Builder.CreateLoad(IVTy, PLowerBound);
   Value *InclusiveUpperBound = Builder.CreateLoad(IVTy, PUpperBound);
   Value *TripCountMinusOne = Builder.CreateSub(InclusiveUpperBound, LowerBound);