[PATCH] D156647: [AMDGPU] Extend f32 support for llvm.amdgcn.update.dpp intrinsic

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/VOP1Instructions.td:1205-1211
+def : GCNPat <
+  (f32 (int_amdgcn_update_dpp f32:$old, f32:$src, timm:$dpp_ctrl,
+                              timm:$row_mask, timm:$bank_mask,
+                              timm:$bound_ctrl)),
+  (V_MOV_B32_dpp VGPR_32:$old, VGPR_32:$src, (as_i32timm $dpp_ctrl),
+                 (as_i32timm $row_mask), (as_i32timm $bank_mask),
+                 (as_i1timm $bound_ctrl))
----------------
Can factor this into a pattern class and just instantiate twice


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D156647/new/

https://reviews.llvm.org/D156647