Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Fri, 3 Aug 2012 00:18:34 +0800
From: myrice <>
Subject: Re: Result of hard core password generation on 7970

On Thu, Jul 26, 2012 at 1:05 AM, Bit Weasil <> wrote:
> I do not know if my previous email made it through.  I got an error from the
> mailing list server regarding a disk space error.
> Apologies if it goes through twice.
> The GPU is not a CPU - you cannot treat it like one!  You cannot safely
> treat it as "a bunch of CPUs running in parallel" - this leads to memory
> contention.  It must be coded as a very wide vector engine.
> The "hard coded" MD5 kernel is written like CPU code, not like GPU code.
> I see no use of local memory.  This is very bad.  Global memory is high
> bandwidth, but very high latency.
> You're doing a linear search through the main global memory to check
> passwords, as far as I can tell.  From each thread.  On many AMD GPUs, this
> does not broadcast the read (I believe nVidia will, at least on newer GPUs).

Thanks for your advice. I think NVidia could do broadcast but not sure
about AMD GPUs.

> Further, there's not a lookup bitmap in sight.  They're used for very good
> reasons, and are absolutely critical for good performance on the GPU.  I'm
> using a 3 layer bitmap system (local, global-but-cached,
> global-and-not-cached) to make sure I only do a binary search through the
> sorted hashes if there's a very high probability of finding the hash.  A
> walk through global memory space from one thread is incredibly expensive.

Yes, this is only first version of GPU password comparison. I am
implemting bitmap on GPU now and try to use local memory.


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.