Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <4F1F15E1.6070104@linuxasylum.net>
Date: Tue, 24 Jan 2012 21:34:41 +0100
From: Samuele Giovanni Tonon <samu@...uxasylum.net>
To: john-dev@...ts.openwall.com
Subject: Re: OpenCL vs Test Suite

On 01/24/12 21:07, magnum wrote:
> I had a look at OpenCL patch rev 5 today. Some comments:
> 
> Here's raw-md5 in CPU:

that's nice however, rawmd5, nt and rawmd4 are not actively mantained
by me nor lukas : we just kept updating them but there has never been a
look in to depth to optimize the code.

If you could test with rawsha1, ssha, cryptmd5 and phpass that would be
best; at the moment rawsha1 is not comparable with CPU version, but i'm
working on it.

> I enclose a patch that applies to Test Suite v1.11. With that applied,
> you can test one [or more] formats "./jtrts.pl cryptmd5-opencl [...]",
> or all OpenCL formats "./jtrts.pl opencl". Some of these problems may be
> trivial, but hard to find without the test suite.

i've never used the test suite but i might have a run to see if the same
apply on my environment


> During manual testing I also saw other errors than the one reported
> during the test suite run:
> OpenCL error (CL_OUT_OF_HOST_MEMORY) in file (common-opencl.c) at line
> (72) - (Error creating context)
> OpenCL error (CL_OUT_OF_RESOURCES) in file (cryptmd5_opencl_fmt.c) at
> line (197) - (clFinish error)
> 
> ...and sometimes even just the self-test for raw-md5 failed (when not
> running X):
> Benchmarking: Raw MD5 [raw-md5-opencl]... FAILED (get_hash[0](4))
> 
> Maybe some/all of these problems are "caused" by my environment? BTW,
> when I tried running this with no X server active, I could see some
> spectacular "progress report" on the console screen: I assume John was
> using GPU memory that was part of my frame buffer. Is this normal? Is it
> bad?

with ati you need X and a user logged in to use OpenCL, on nvidia not,
however, as far as i know, nvidia official driver doesn't have framebuffer .
Never tried to use opencl on the "community" driver, i could give it a
try, unfortunately only on ati.
(my laptop has a dual video card intel/nvidia so i'm just running
X/framebuffer on the intel and using nvidia for opencl only)


> Am I supposed to be able to run a dual screen X at the same time as
> running OpenCL formats? John will just get less GPU memory? Too little?

john should not suffer any problem by having a dual screen or more..
well, if you have OpenGL and shiny effects enabled there could be some
problem but i assure you they would be noticeable (aka, mouse not
moving or moving in slow motion).

Thanks for your tests!

Cheers
Samuele

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.