[PATCH] D153544: [AMDGPU] Use V_FMA_MIX* more often

[Mateja Marjanovic via Phabricator via llvm-commits]

matejam added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/VOP3PInstructions.td:194
+
+  def : GCNPat <
+    (build_vector f16:$elt0, (fpround (any_fmul (f32 (VOP3PMadMixMods f32:$src0, i32:$src0_modifiers)),
----------------
I could add two more patterns similar to this one, with AMDGPUclamp.
One with elt0 as its first element and the other with lo_src* and hi_src*.


================
Comment at: llvm/test/CodeGen/AMDGPU/fdiv.f16.ll:3
-; RUN: llc -march=amdgcn -mcpu=fiji -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8PLUS %s
-; RUN: llc -march=amdgcn -mcpu=fiji -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8PLUS %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8PLUS %s
----------------
I guess this was an accident.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D153544/new/

https://reviews.llvm.org/D153544