================
@@ -4434,10 +4497,24 @@ getKmpcForStaticLoopForType(Type *Ty, OpenMPIRBuilder
*OMPBuilder,
static void createTargetLoopWorkshareCall(
OpenMPIRBuilder *OMPBuilder, WorksharingLoopType LoopType,
BasicBlock *InsertBlock, Value *Ident, Value *LoopBodyArg,
- Type *ParallelTaskPtr, Value *TripCount, Function &LoopBodyFn) {
- Type *TripCountTy = TripCount->getType();
+ Type *ParallelTaskPtr, Value *TripCountOrig, Function &LoopBodyFn) {
Module &M = OMPBuilder->M;
IRBuilder<> &Builder = OMPBuilder->Builder;
+ Value *TripCount = TripCountOrig;
+ // The trip count is 1 larger than it should be for GPU, this is because
+ // of how the deviceRTL functions work with clang. TODO: make the trip
+ // count consistent between both so we don't have to subtract one here.
+ if (OMPBuilder->Config.isGPU()) {
+ Builder.restoreIP({InsertBlock, std::prev(InsertBlock->end())});
+ LLVMContext &Ctx = M.getContext();
+ Type *IVTy = TripCountOrig->getType();
+ Type *InternalIVTy = IVTy->getIntegerBitWidth() <= 32
+ ? Type::getInt32Ty(Ctx)
+ : Type::getInt64Ty(Ctx);
+ Constant *One = ConstantInt::get(InternalIVTy, 1);
+ TripCount = Builder.CreateSub(TripCountOrig, One, "modified_trip_count");
+ }
+ Type *TripCountTy = TripCount->getType();
----------------
skatrak wrote:
You're already aware of this, but just to make sure we don't forget, this and
changes to _mlir/test/Target/LLVMIR/omptarget-parallel-wsloop.mlir_,
_mlir/test/Target/LLVMIR/omptarget-wsloop-collapsed.mlir_ and
_mlir/test/Target/LLVMIR/omptarget-wsloop.mlir_ would have to be reverted if
#133435 is merged.
Also, I think _llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp_ would probably
make more sense to set `IsGPU=true` at that point.
https://github.com/llvm/llvm-project/pull/133310
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
