[PATCH] D118534: [X86] Introduce more common modern tunings into `generic`

Fri Feb 4 01:24:49 PST 2022

lebedev.ri added a comment.

In D118534#3296058 <https://reviews.llvm.org/D118534#3296058>, @pengfei wrote:

> In D118534#3295994 <https://reviews.llvm.org/D118534#3295994>, @lebedev.ri wrote:
>
>> Please split Znver changes into a separate review.
>> At least for znver3, i'm not really confident that `fsqrt` is fast,
>> https://www.agner.org/optimize/instruction_tables.pdf says ~25cy,
>> while NR takes ~19cy: https://godbolt.org/z/rK9ra4hse
>
> Although Agner's table says it's 8~21 and 22 for znver1 and znver2 respectively, the mca shows they are worse than znver3. Is it a bug in schedule model? I'd like to leave Znver tuning as is given I'm not familiar with them.

znver1/znver2 models are, well, leave a lot to be desired.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D118534/new/

https://reviews.llvm.org/D118534