[PATCH] D80095: AMDGPU/GlobalISel: Fix splitting wide VALU, non-vector loads

Matt Arsenault via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Mon May 18 09:40:07 PDT 2020


arsenm closed this revision.
arsenm marked an inline comment as done.
arsenm added a comment.

4c70074e54348d8fb77f14583c6172e4377dc95e <https://reviews.llvm.org/rG4c70074e54348d8fb77f14583c6172e4377dc95e>



================
Comment at: llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-load.mir:44
+    %tmp0 = call i32 @llvm.amdgcn.workitem.id.x() #0
+    %constant.not.uniform = getelementptr i256, i256 addrspace(4)* %in, i32 %tmp0
+    %tmp2 = load i256, i256 addrspace(4)* %constant.not.uniform
----------------
kerbowa wrote:
> Random nit, the suffix for constant.not.uniform is not consistent with the other tests.
The type suffix on the value name just adds more effort when copying other tests. It should be removed from the rest


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80095/new/

https://reviews.llvm.org/D80095





More information about the llvm-commits mailing list