Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Tue, 4 Dec 2007 13:51:36 -0500
From: Erik Winkler <ewinkler@...ls.com>
To: john-users@...ts.openwall.com
Subject: Re: bitslice MD5 (was: bitslice implementation of ORACLE hash cracking)

Finally got around to testing this on a PowerPC with altivec:

$gcc md5slice.c -o md5slice -Wall -s -O3 -fomit-frame-pointer -funroll- 
loops
$time ./md5slice
vector size = 32 bits
c09c4c1f 21876746 18aed2 70b452f0

real		0m1.847s
user	0m1.448s
sys		0m0.024s

$gcc md5slice.c -o md5slice -Wall -s -O3 -fomit-frame-pointer -funroll- 
loops -maltivec -DVECTOR
$ time ./md5slice
vector size = 128 bits
c09c4c1f 21876746 18aed2 70b452f0

real		0m0.545s
user	0m0.456s
sys		0m0.008s

The vectorized version shows a significant speed increase.  This is a  
1.33 Ghz G4 processor.

Erik


> On Athlon64 3200+ (2.0 GHz) running Linux/x86-64 (Owl-current), I get:
>
> amd!solar:~/md5slice$ gcc md5slice.c -o md5slice -Wall -s -O3 -fomit- 
> frame-pointer -funroll-loops
> amd!solar:~/md5slice$ time ./md5slice
> vector size = 64 bits
> c09c4c1f 21876746 18aed2 70b452f0
>
> real    0m0.463s
> user    0m0.460s
> sys     0m0.010s
>
> amd!solar:~/md5slice$ PATH=~/gcc-4.1.0/bin:$PATH gcc md5slice.c -o  
> md5slice -Wall -s -O3 -fomit-frame-pointer -funroll-loops -DVECTOR
> amd!solar:~/md5slice$ time ./md5slice
> vector size = 128 bits
> c09c4c1f 21876746 18aed2 70b452f0
>
> real    0m0.388s
> user    0m0.390s
> sys     0m0.000s

-- 
To unsubscribe, e-mail john-users-unsubscribe@...ts.openwall.com and reply
to the automated confirmation request that will be sent to you.

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.