[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Wed, 30 Jan 2019 10:37:38 +0100
From: Szabolcs Nagy <nsz@...t70.net>
To: musl@...ts.openwall.com
Cc: Damian McGuckin <damianm@....com.au>
Subject: Re: Possible Mistype in exp.c
* Damian McGuckin <damianm@....com.au> [2019-01-30 12:18:54 +1100]:
> On Tue, 29 Jan 2019, Szabolcs Nagy wrote:
>
> > > > https://www.openwall.com/lists/musl/2018/12/08/1
>
> For some reason I missed this on the list.
>
> You were certainly busy integrating this.
>
> Is there any documentation on the Remez polynomials and the associated
> argument reductions done? Or is it a case of 'read the code'. ARM have
> certainly done a lot of work. It will be really interesting when that CPU
> gets a lot closer to the high end Xeon.
i work at arm and i did this work there so i know the background.
there is not much published about the algorithms (although there aren't
many new ideas in the code, it's mostly about optimizing for modern cpus),
but i plan to at least put the polynomial and lookup table generation
code in that repo.
the polynomial coefficients were generated with the sollya tool from
inria.
Powered by blists - more mailing lists
Confused about mailing lists and their use?
Read about mailing lists on Wikipedia
and check out these
guidelines on proper formatting of your messages.
