[PATCH] D23286: AMDGPU/SI: Propose to redefine image load/store intrinsics

[Changpeng Fang via llvm-commits]

cfang added a comment.

> Mesa GL doesn't use R128. If the closed GL does, I don't know about it.

Just discussed with other compiler engineers. Compiler should expose existing hardware feature no matter it is currently used or not.


https://reviews.llvm.org/D23286