udiv_qr_4by2

[Niels Möller]

"Marco Bodrato" <bodrato at mail.dm.unipi.it> writes:

> Ciao,
>
> while some discussion on division emerges... Even if completely unrelated,
> I post a proposed patch to rearrange operations in udiv_qr_4by2.
> It should be faster, 

Looks good to me.

> even if I do not know how much it is actually used:
> almost all thresholds in
> https://gmplib.org/devel/thres/DIV_QR_2_PI2_THRESHOLD.html are
> MP_SIZE_T_MAX /* never */

I think it's supposed to be useful on architectures with high mul throughput but
poor latency.

Regards,
/Niels

-- 
Niels Möller. PGP-encrypted email is preferred. Keyid 368C6677.
Internet email is subject to wholesale government surveillance.