[PATCH] D144729: [AMDGPU] Select v_sat_pk_u8_i16

[Pierre van Houtryve via Phabricator via llvm-commits]

Pierre-vh added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIInstructions.td:2929
 
+multiclass V_SAT_PK_Pat<Instruction inst> { 
+  def: GCNPat<
----------------
Should this only be for vector operations? (use DivergentBinFrag?)


================
Comment at: llvm/lib/Target/AMDGPU/SIInstructions.td:2933-2934
+    (inst 
+      (V_LSHL_OR_B32_e64 VGPR_32:$hi, (S_MOV_B32 (i32 16)), 
+        (V_AND_B32_e64 VGPR_32:$lo, (S_MOV_B32 (i32 0xFFFF)))))
+  >;
----------------
Is it worth adding a GFX11/UniformBinFrag variant with S_PACK_LL?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D144729/new/

https://reviews.llvm.org/D144729