[PATCH] D149589: AMDGPU: Drop and auto-upgrade llvm.amdgcn.ldexp to llvm.ldexp

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ldexp.f16.ll:6
-
-declare half @llvm.amdgcn.ldexp.f16(half %a, i32 %b)
-
----------------
Joe_Nash wrote:
> Should we not update these tests to use the generic intrinsic rather than delete them? I am working on Codegen for the new version of this instruction where src1 is 16-bit, and these tests are covering useful output.
New ones are added in D14327


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D149589/new/

https://reviews.llvm.org/D149589