[llvm-branch-commits] [llvm] AMDGPU: Legalize fminimum and fmaximum f32 for gfx950 (PR #117634)

[Matt Arsenault via llvm-branch-commits]

================
@@ -1234,6 +1234,23 @@ def : IntClampPat<V_MQSAD_PK_U16_U8_e64, int_amdgcn_mqsad_pk_u16_u8>;
 def : IntClampPat<V_QSAD_PK_U16_U8_e64, int_amdgcn_qsad_pk_u16_u8>;
 def : IntClampPat<V_MQSAD_U32_U8_e64, int_amdgcn_mqsad_u32_u8>;
 
+//===----------------------------------------------------------------------===//
+// Floating-point operation Patterns
+//===----------------------------------------------------------------------===//
+
+// Implement fminimum(x, y) by using minimum3(x, y, y)
+class MinimumMaximumByMinimum3Maximum3<SDPatternOperator node, ValueType vt,
+                                       Instruction inst> : GCNPat<
+  (vt (node (VOP3Mods vt:$src0, i32:$src0_mods), (VOP3Mods vt:$src1, i32:$src1_mods))),
+  (inst $src0_mods, $src0, $src1_mods, $src1, $src1_mods, $src1)
+>;
+
+// Prefer the real 2 operand form if legal
+let SubtargetPredicate = HasMinimum3Maximum3F32, AddedComplexity = -1000 in {
----------------
arsenm wrote:

The -1000 is really leftover debugging, will fix after the merge is completed 

https://github.com/llvm/llvm-project/pull/117634