[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CA+TsHUBMtNgH8Eb3ZBXw-wkoTQ3GxwbUn9L6+WuQLGAR8HipdQ@mail.gmail.com>
Date: Mon, 9 Mar 2015 14:24:49 +0530
From: Sayantan Datta <std2048@...il.com>
To: john-dev <john-dev@...ts.openwall.com>
Subject: Re: 256/128 bit integer arithmatic
On Mon, Mar 9, 2015 at 1:07 AM, magnum <john.magnum@...hmail.com> wrote:
> They are emulated though, probably similar to using hi/lo 64-bit structs.
I have my own emulation based on 64bit uint in HI, LO configuration for
performing modulo operations specific to my requirements and it's much
faster than native 128bit modulo operations. I tried to do the three 64bit
modulo operations required for emulating 128bit modulo using avx intrinsics
but it turns out there are no integer division built_ins in gcc, let alone
modulo operations. No wonder modulo operations are slow!!
Regards,
Sayantan
Content of type "text/html" skipped
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.
