[PATCH] D140208: [AMDGPU] Improved wide multiplies

[Thomas Symalla via Phabricator via llvm-commits]

tsymalla added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/GlobalISel/mul-known-bits.i64.mir:11
 
-    ; GFX10-LABEL: name: v_mul_i64_zext_00
+    ; GFX10-LABEL: name: v_mul_i64_no_zext
     ; GFX10: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
----------------
Can you please pre-commit the tests based on the new test names so they don't show up in the diff?

Btw, it seems like gfx10 and gfx11 always get the same changes in the GMIR test. In that case, I'd rather remove the gfx11 tests and just execute one test. This keeps the GMIR test less cluttered.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D140208/new/

https://reviews.llvm.org/D140208