[PATCH] D92750: [VE] Add vrcp, vrsqrt, vcvt, vmrg, and vshf intrinsic instructions

[Simon Moll via Phabricator via llvm-commits]

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

I think we can do a better job when it comes to the intrinsic attributes.. eg there should be `nosync` on all vector arithmetic intrinsics, also `readnone` inaccurately obscures the dependence of floating-point ops on the rounding/exception mode configured in the PSW register.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D92750/new/

https://reviews.llvm.org/D92750