[PATCH] D99505: [AMDGPU] Enable output modifiers for double precision instructions

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIFoldOperands.cpp:1776
         // instruction, and not the omod multiply.
-        if (IsIEEEMode || (!HasNSZ && !MI.getFlag(MachineInstr::FmNsz)) ||
-            !tryFoldOMod(MI))
+        if ((IsIEEEMode && !MI.getFlag(MachineInstr::FmNoNans)) ||
+            (!HasNSZ && !MI.getFlag(MachineInstr::FmNsz)) || !tryFoldOMod(MI))
----------------
arsenm wrote:
> This is a separate change
Also would need a comment explaining that ieee mode only changes snan behavior, nnan lets us ignore it.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D99505/new/

https://reviews.llvm.org/D99505