[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Sat, 16 Jun 2012 15:08:47 +0200
From: magnum <john.magnum@...hmail.com>
To: john-dev@...ts.openwall.com
Subject: Re: Re: [patch] optional new raw sha1 implemetation
On 2012-06-15 23:57, Simon Marechal wrote:
> On 06/15/2012 11:36 PM, Tavis Ormandy wrote:
>> Oops, good point. I'm not sure how to tell if it's available or not (I
>> think it was accidentally ommitted in some gcc releases), but gcc seems
>> to tolerate me writing my own, so I did that.
>>
>> I'll look into how to do it properly.
>
> I just pushed a "fix" that checks if we are using ICC. It should also
> fix the x86-64.S problem.
I pushed some trivial fixes for the sh!tload of compiler warnings I got
from the format.
For memrchr, my man page says to define _GNU_SOURCE before including
string.h but that did not help. After looking at the header I define
__USE_GNU instead, and undef it after including string.h. Not sure
what's up with that?
When building with the -native target and no icc-precompiled intrinsics,
I get the following benchmarks:
Benchmarking: Raw SHA-1 [SSE2i 8x]... DONE
Raw: 10961K c/s real, 10961K c/s virtual
Benchmarking: Raw SHA-1 (taviso sse4 build) [rawsha1_sse4]... DONE
Raw: 11963K c/s real, 11963K c/s virtual
magnum
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.
