[PATCH 0/8] Add sinf/cosf/sincosf CORE-MATH implementations

[Paul Zimmermann]

       Hi Wilco,

> I ran these on Neoverse V2 and added my old patches with traces from a game engine.
> I'm seeing major slowdowns:
> 
>              sinf	cosf
>      random  45.4%	45.2%
>       large  68.0%	53.4%
>        huge  19.4%	9.8%
> box2d-small  58.2%	100.2%
>  box2d-hard  56.7%	72.7%
> box2d-mixed  52.5%	54.4%
> 
> The box2d results are far worse since they are traces rather than randomized,
> so they run much faster due to fewer mispredictions. Latency is 2-3x lower for the
> same reason.
> 
> So improving the benchtests with traces would be a good idea, however it seems
> the CORE-MATH sinf/cosf implementation is significantly slower on modern cores
> even with random inputs.

please can you send me the data set for the box2d-small benchmark?
I'd like to reproduce your findings and analyze why CORE-MATH is so slow
on this benchmark.

Thank you,
Paul