john-users - RE: Speed of jtr on your machine?

Openwall wordlists collection for password cracking (20+ languages)
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date: Sat, 17 Sep 2011 22:03:40 -0400
From: "Robert Harris" <rs904c@...scape.net>
To: <john-users@...ts.openwall.com>
Subject: RE: Speed of jtr on your machine?

So, that version is compiled with the latest version of gcc (4.6.1).

-----Original Message-----
From: Bugtrace [mailto:bugtrace@...il.com] 
Sent: Saturday, September 17, 2011 3:49 AM
To: john-users@...ts.openwall.com
Subject: Re: [john-users] Speed of jtr on your machine?

Sorry.
In fact, it is compiled by Robert Harris

On Sat, Sep 17, 2011 at 3:46 PM, Bugtrace <bugtrace@...il.com> wrote:
> Guys, I download john-1.7.8-jumbo-5-Linux-x86-64(Compiled by Jim
> Fougeron) from
http://openwall.info/wiki/_media/john/john-1.7.8-jumbo-5-Linux-x86-64.tar.gz
?id=john%3Acustom-builds&cache=cache
>
> Faster than mine.
>
> pentest@...ntu:~/Downloads/john-1.7.8-jumbo-5-Linux-x86-64/run$ ./john
> --format=raw-md5 --test
> Benchmarking: Raw MD5 [gen]... Using raw-md5 mode, by linking to
> md5_gen(0) functions DONE
> Raw:    16789K c/s real, 16959K c/s virtual
>
> pentest@...ntu:~/Downloads/john-1.7.8-jumbo-5-Linux-x86-64/run$ ./john
> --format=phpass-md5 --test
> Benchmarking: PHPass MD5 [phpass-md5]... Using phpass mode, by linking
> to md5_gen(17) functions DONE
> Raw:    13360 c/s real, 13360 c/s virtual
>
>
> On Wed, Sep 14, 2011 at 5:52 AM, magnum <rawsmooth@...dband.net> wrote:
>> On 2011-09-13 18:50, jfoug wrote:
>>>>
>>>> Then I should look at that.  It 'should' give some signature that lists
>>>> it
>>>> was built using sse2 intrinsic functions.
>>>
>>> Here is what I see in a 32 bit intrinsic build (cygwin). Now, this is
not
>>> jumbo-5, but I did not think anything changed about how md5_gen is
built,
>>> since then.
>>>
>>> $ ../run/john -test -form=md5-gen
>>> Benchmarking:  md5_gen(0): md5($p)  (raw-md5)  [SSE2 16x4x2 (intr)]...
>>> DONE
>>> Raw:    9653K c/s
>>>
>>>
>>> I will later check this on my pen drive linux-64 system, to see if there
>>> are
>>> problems showing up there, which do not appear on this 32 bit build.
>>
>>
>> It shows correctly when using md5_gen(0) but not when using thin raw-md5:
>>
>> $ ./john -fo:"md5_gen(0)" -test
>> Benchmarking:  md5_gen(0): md5($p)  (raw-md5)  [SSE2 16x4x2 (intr)]...
DONE
>> Raw:    13832K c/s real, 13832K c/s virtual
>>
>> $ ./john --format=raw-md5 --test
>> Benchmarking: Raw MD5 [gen]... Using raw-md5 mode, by linking to
md5_gen(0)
>> functions DONE
>> Raw:    13858K c/s real, 13858K c/s virtual
>>
>> This is simply because the format (rawMD5go_fmt_plug.c) says so:
>> #define ALGORITHM_NAME                  "gen"
>>
>> It would be better if md5_gen replaced that. Perhaps it should when a
thin
>> format sets ALGORITHM_NAME to a null string?
>>
>>
>> Back to topic, Bugtrace's performance figures are very low for some
reason
>> or the other. What's the output from -test -fo:"md5_gen(0)"?
>>
>> magnum
>>
>