================
@@ -21962,6 +21962,35 @@ SDValue tryLowerPartialReductionToWideAdd(SDNode *N,
return DAG.getNode(TopOpcode, DL, AccVT, BottomNode, ExtOp);
}
+static SDValue foldRevInvolution(SDNode *N) {
+ SDValue InnerRev = N->getOperand(1);
+ if (!InnerRev.hasOneUse())
+ return SDValue();
+
+ unsigned OuterIId = getIntrinsicID(N);
+ unsigned InnerIId = getIntrinsicID(InnerRev.getNode());
+ if (OuterIId != InnerIId)
+ return SDValue();
+
+ switch (OuterIId) {
+ case Intrinsic::aarch64_sve_revb:
+ case Intrinsic::aarch64_sve_revd:
+ case Intrinsic::aarch64_sve_revh:
+ case Intrinsic::aarch64_sve_revw:
+ if (N->getOperand(2) != InnerRev.getOperand(2) ||
+ N->getOperand(3) != InnerRev.getOperand(3))
+ return SDValue();
+ [[fallthrough]];
+ case Intrinsic::aarch64_sve_rev:
+ case Intrinsic::aarch64_sve_rev_b16:
+ case Intrinsic::aarch64_sve_rev_b32:
+ case Intrinsic::aarch64_sve_rev_b64:
+ return InnerRev.getOperand(1);
----------------
sdesmalen-arm wrote:
I don't think the combine on the predicated `rev[bhwd]` intrinsics is correct.
It would be if the governing predicate is `all true`. Otherwise the `rev`s
might be removed if the passthru is `poison` and the input is equal the other
rev result (rather than the source of the first `rev`, which is what the code
currently checks).
This is probably more an optimisation to do in InstCombine (see
`AArch64TTIImpl::instCombineIntrinsic`), but I'd suggest keeping this PR simple
and splitting that work out into a separate PR.
https://github.com/llvm/llvm-project/pull/116422
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
