[PATCH] D95245: [SVE] Add support for scalable vectorization of loops with int/fast FP reductions

[Kerry McLaughlin via Phabricator via llvm-commits]

kmclaughlin added inline comments.


================
Comment at: llvm/test/Transforms/LoopVectorize/AArch64/scalable-reductions.ll:470
+
+attributes #0 = { "no-nans-fp-math"="true" }
+
----------------
sdesmalen wrote:
> nit: use `nnan` directly in the fp operation instead of an attribute.
Hi @sdesmalen, these tests for fmin/fmax fail without the `no-nans-fp-math` attribute, I think because `RecurrenceDescriptor::isRecurrenceInstr` is just checking for the function attribute and not the flags on the instruction. I've created a separate patch (D96350) to try and address this.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D95245/new/

https://reviews.llvm.org/D95245