[PATCH] D74016: libclc/r600: Use target specific builtins to implement rsqrt and native_rsqrt

[Jan Vesely via Phabricator via llvm-commits]

jvesely added a comment.

In D74016#1865339 <https://reviews.llvm.org/D74016#1865339>, @awatry wrote:

> Looks good to me from a code standpoint.
>
> The test fails CTS before and after on my BARTS (6850), but that's when running libclc master with LLVM 9.0, so there might be a precision issue that's fixed in newer code. It doesn't make the issue worse, at least.


thanks.
that's surprising. does it fail for scalar only? do you have the asm dump?
I thought Barts and Turks were largely identical when it came to compute pipeline
This should really produce just single instruction so newer LLVM is unlikely to fix it.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D74016/new/

https://reviews.llvm.org/D74016