[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 14 Sep 2015 20:44:07 +0300
From: Solar Designer <solar@...nwall.com>
To: john-dev@...ts.openwall.com
Subject: Re: md5crypt mmxput*()
On Wed, Sep 09, 2015 at 03:00:01AM +0200, magnum wrote:
> On 2015-09-08 16:18, Solar Designer wrote:
> >Benchmarking: md5crypt, crypt(3) $1$ [MD5 128/128 XOP 4x2]... (8xOMP) DONE
> >Raw: 231680 c/s real, 28923 c/s virtual
>
> Code size, eh? This reminded me there is a "#pragma GCC optimize 3" in
> that file that I always found slightly dubious. We should verify how
> each format reacts to dropping that.
>
> Quick test for now, on bull; Enabled the switch for XOP, dropped that
> pragma:
>
> Benchmarking: md5crypt, crypt(3) $1$ [MD5 128/128 XOP 4x2]... (8xOMP) DONE
> Raw: 233472 c/s real, 29184 c/s virtual
I think you never committed this change? Since you also confirmed it
helping on AVX2, I think you should, unless you know of a regression.
> Then again, how about -O2 and *not* using switch?
>
> Benchmarking: md5crypt, crypt(3) $1$ [MD5 128/128 XOP 4x2]... (8xOMP) DONE
> Raw: 232960 c/s real, 29120 c/s virtual
>
> OK, that's inbetween. So before having tested any other format or arch,
> the pragma should go and the switch should be use for XOP too.
It seems so, and this makes sense.
> Apparently Jim added that pragma in 2013 while (I think) adding SHA-2,
> likely because Gosney's original code had it. I will do some testing!
Have you done more testing since?
Alexander
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.
