[PATCH] D138205: [AMDGPU] Add support for new LLVM vector types

Matt Arsenault via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Mon Nov 28 13:46:16 PST 2022


arsenm accepted this revision.
arsenm added a comment.
This revision is now accepted and ready to land.

LGTM. Tests may conflict with opaque pointer patches



================
Comment at: llvm/test/CodeGen/AMDGPU/load-global-f32.ll:102
+; R600: VTX_READ_128
+define amdgpu_kernel void @global_load_v10f32(<10 x float> addrspace(1)* %out, <10 x float> addrspace(1)* %in) #0 {
+entry:
----------------
New tests should use opaque pointers 


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D138205/new/

https://reviews.llvm.org/D138205



More information about the llvm-commits mailing list