[PATCH] D37155: AMDGPU: Select clamp pattern with v2f16

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: lib/Target/AMDGPU/SIISelLowering.cpp:5687
+  // med3 for f16 is only available on gfx9+, and not available for v2f16.
+  if (VT == MVT::f32 || (VT == MVT::f16 && Subtarget->hasMed3_16())) {
+    // This isn't safe with signaling NaNs because in IEEE mode, min/max on a
----------------
rampitec wrote:
> Why did you change it from early return?
The inverted condition got more complicated and harder to read


https://reviews.llvm.org/D37155