[PATCH] D104181: AMDGPU: Fix infinite loop in DAG combine with fneg + fma

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec accepted this revision.
rampitec added a comment.
This revision is now accepted and ready to land.

LGTM



================
Comment at: llvm/test/CodeGen/AMDGPU/fneg-combines.ll:2581
+; !isFNegFree. We were reporting false for v2f32 even though it will
+; be split into f32 where it will be free.
+; GCN-LABEL: {{^}}fneg_fma_fneg_dagcombine_loop:
----------------
It actually can be free even in packed f32 form with neg_lo/neg_hi with FeaturePackedFP32Ops.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D104181/new/

https://reviews.llvm.org/D104181