[llvm] [AMDGPU] Improve codegen for copysign(x, fneg(y)) (PR #207178)

[Matt Arsenault via llvm-commits]

================
@@ -2932,11 +2948,31 @@ def : AMDGPUPat <
   (S_AND_B32 (S_MOV_B32 (i32 0x80000000)), $src1)
 >;
 
+def : AMDGPUPat <
+  (DivergentBinFrag<fcopysign> (f32 fpimm_zero), (fneg f32:$src1)),
+  (V_BFI_B32_e64 VGPR_32:$src1, (i32 0), (S_MOV_B32 (i32 0x80000000)))
+>;
+
 def : AMDGPUPat <
   (fcopysign (f32 fpimm_pos_zero), (f32 VGPR_32:$src1)),
   (V_AND_B32_e32 (S_MOV_B32 (i32 0x80000000)), $src1)
 >;
 
+def : AMDGPUPat <
----------------
arsenm wrote:

These 2 patterns are pretty similar, do both really fire?

https://github.com/llvm/llvm-project/pull/207178