[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <e311a64e469dd333ac31b3670f2524cb@smtp.hushmail.com>
Date: Mon, 17 Feb 2014 18:12:29 +0100
From: magnum <john.magnum@...hmail.com>
To: john-dev@...ts.openwall.com
Subject: Re: Re: sha512crypt-opencl format fails in xeon phi coprocesor
On 2014-02-17 17:55, Claudio André wrote:
>> === Testing sha512crypt-opencl on MIC ===
>> Device 1: Intel(R) Many Integrated Core Acceleration Card
>> Exit code: 139
>>
>> 139 means segfault.
>>
>> Now that I've tried bleeding-jumbo on our 5110P, I am getting results
>> similar to what Mr Dupito posted.
>>
>> I suggest that we create you an account on our machine with the 5110P,
>> and you debug the issue.
>
> It is a good path to follow, but I saw a lot of errors in raw formats,
> event MD4 and MD5. And it doesn't make sense, "they are very simple code".
>
> Intel OpenCL driver/compiler creativity!?!?!
FWIW the tests I made so far on Super made me too suspect that the MIC
OpenCL driver is, to be diplomatic, somewhat immature. I got
disappointed enough not to bother even trying to work around issues.
Are there by any chance newer drivers available now?
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.
