[llvm] select v_sat_pk from two i16 or v2i16 (PR #121124)

[Matt Arsenault via llvm-commits]

================
@@ -315,6 +315,55 @@ def srl_16 : PatFrag<
   (ops node:$src0), (srl_oneuse node:$src0, (i32 16))
 >;
 
+def clamp_s16_u8 : PatFrag<
+  (ops node:$src),
+  (i16 (AMDGPUsmed3 $src, (i16 0), (i16 255)))
+>;
+
+def conc_lo_u8_i16 : PatFrags<
+  (ops node:$src0, node:$src1),
+  [
+    (or
+      (i16 $src0),
+      (shl (i16 $src1), (i16 8))
+    ),
+    (or
+      (and (i16 $src0), (i16 255)),
+      (shl (i16 $src1), (i16 8))
+    )
+  ]
+>;
+
+def clamp_v2i16_u8 : PatFrags<
+  (ops node:$src),
+  [
+    (v2i16 (smax (smin $src, (build_vector (i16 255), (i16 255))), (build_vector (i16 0), (i16 0)))),
+    (v2i16 (smin (smax $src, (build_vector (i16 0), (i16 0))), (build_vector (i16 255), (i16 255))))
+  ]
+>;
+
+def conc_lo_v2i16_i16 : PatFrags<
----------------
arsenm wrote:

Depends what you mean by "fragile" but for an optimization it doesn't require robustness. -100 for making v2i8 legal, that's a huge amount of effort for one operation. 

https://github.com/llvm/llvm-project/pull/121124