Re: [PATCH v3 5/7] math: Remove powerpc e_hypot

[Adhemerval Zanella via Libc-alpha <libc-alpha@sourceware.org>]

On 10/11/2021 11:34, Wilco Dijkstra wrote:
> Hi Paul,
> 
>> The patches see poorer performance on Power10, also:
> 
> Was that with the last patch to remove the redirects as well? The latest version
> is still slower even with that on AArch64...
> 
> I think the new algorithm will always be slower due to the dependent sqrt and
> division. So it's hard to improve unless we only use it for special cases (eg. when
> ax and ay are close). Returning sqrt (fma (ax, ax, ay * ay)) is about twice as fast
> and gives just over 1 ULP, so we're losing a lot of performance for a small ULP
> improvement.

My main drive for this change is remove the arch-specific implementation in
favor of an implementation that might be optimized better by the compiler
without the need to extra hacks by arch-specific hooks (as I did for power7).

So I used a more precise implementation, at least on paper it stated that
with fma it might be overcome some performance implication of the more
precise algorithm.

Another option is to use the powerpc implementation which favor FP over integer
as the default one.