[PATCH] D51736: DAG: Change behavior of fminnum/fmaxnum nodes

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added inline comments.


================
Comment at: lib/Target/AMDGPU/SIInstructions.td:1654
+
+// class MinMaxModsPat<Instruction inst, SDPatternOperator op, ValueType Ty, bit packed = 0>
+//   : GCNPat<
----------------
There is a lot of commented code in the patch in different places.


https://reviews.llvm.org/D51736