Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [day] [month] [year] [list] 
Message-ID: <4F4D1955.70904@gmail.com>
Date: Tue, 28 Feb 2012 15:13:41 -0300
From: Claudio André <claudioandre.br@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: OpenCL erros

Sorry i haven't answered earlier, i subscribed only today at the dev list.

1. i'm using a SDK 2.6, updated driver, etc. [1], Ubuntu 11.10, updated, 
64 bits.

2. the GPU i was testing is a really poor moblile GPU. I'm not sure 
about the available memory, i know it is really short.
   But the point is, it is a valid one, OpenCL ready, etc. It runs MD5 
cracking, for instance.

Probably not all GPUs are going to be usefull in John in all hashes:
- Some minimun requirements?
- Tell the user about it?
- Put some tests in the software, give a better feedback?
- Review the code and Allow John to use weak GPUs?


Only my thoughts since i have some new (but poor) hardware.
Thanks


[1] By the way, ATISTREAMSDKROOT was renamed AMDAPPSDKROOT some time ago.


    Hi, if you guys want some feedback, below you can see an error

    Sheers
    ----

    OpenCL Platforms: 1
    OpenCL Platform: <<<AMD Accelerated Parallel Processing>>> 2
    device(s), using device: <<<Cedar>>>
    Max Group Work Size 128 Optimal local work size 32
    (to avoid this test on next run do export LWS=32)
    Local work size (LWS) 32, Keys per crypt (KPC) 2097152
    Benchmarking: Netscape LDAP SSHA OPENCL [salted SHA-1]... DONE
    Many salts:9532K c/s real, 19418K c/s virtual
    Only one salt:8525K c/s real, 14169K c/s virtual

    OpenCL Platforms: 1
    OpenCL Platform: <<<AMD Accelerated Parallel Processing>>> 2
    device(s), using device: <<<Cedar>>>
    Max Group Work Size 128 Optimal local work size 64
    (to avoid this test on next run do export LWS=64)
    Local work size (LWS) 64, Keys per crypt (KPC) 2097152
    Benchmarking: Raw MD5 [raw-md5-opencl]... DONE
    Raw:10399K c/s real, 16131K c/s virtual

    OpenCL Platforms: 1
    OpenCL Platform: <<<AMD Accelerated Parallel Processing>>> 2
    device(s), using device: <<<Cedar>>>
    Optimal Local work size 64
    Benchmarking: NT MD4 [OpenCL 1.0]... DONE
    Raw:7864K c/s real, 11915K c/s virtual

    OpenCL Platforms: 1
    OpenCL Platform: <<<AMD Accelerated Parallel Processing>>> 2
    device(s), using device: <<<Cedar>>>
    OpenCL error (CL_MAP_FAILURE) in file (opencl_rawsha1_fmt.c) at line
    (133) - (Error mapping page-locked memory saved_plain)
    ceu-dutra@...dutra-HP-G42-Notebook-PC:~/bin/john/openCL/run$






Content of type "text/html" skipped

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.