================
@@ -2591,8 +2597,49 @@ void OpenMPIRBuilder::emitReductionListCopy(
// Now that all active lanes have read the element in the
// Reduce list, shuffle over the value from the remote lane.
if (ShuffleInElement) {
- shuffleAndStore(AllocaIP, SrcElementAddr, DestElementAddr,
RI.ElementType,
- RemoteLaneOffset, ReductionArrayTy);
+ Type *ShuffleType = RI.ElementType;
+ Value *ShuffleSrcAddr = SrcElementAddr;
+ Value *ShuffleDestAddr = DestElementAddr;
+ Value *Zero = ConstantInt::get(Builder.getInt32Ty(), 0);
+ AllocaInst *LocalStorage = nullptr;
+
+ if (IsByRefElem) {
+ assert(RI.ByRefElementType && "Expected by-ref element type to be
set");
+ assert(RI.ByRefAllocatedType &&
+ "Expected by-ref allocated type to be set");
+ // For by-ref reductions, we need to copy from the remote lane the
+ // actual value of the partial reduction computed by that remote lane;
+ // rather than, for example, a pointer to that data or, even worse, a
+ // pointer to the descriptor of the by-ref reduction element.
+ ShuffleType = RI.ByRefElementType;
+
+ ShuffleSrcAddr = Builder.CreateGEP(RI.ByRefAllocatedType,
----------------
ergawy wrote:
Sorry for the late reply, I had to take some off. I think your suggestion would
be cleaner that my current approach. The only downside I see is that, now we
are leaking both Fortran and GPU-implemenation details to the op's definition.
But it will be clearer what the op is encapsulating. I will prototype your
suggestion and see how it looks like.
https://github.com/llvm/llvm-project/pull/165714
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
