Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Thu, 12 Apr 2012 12:29:40 +0530
Subject: Re: MSCash2 OpenCL (was: OpenCL tests on HD 7970)


I think this means that we're already quite close to optimal
> performance, and further optimizations may be in two areas: reducing the
> number of operations performed per password hashed (e.g., by making use
> of bitselect() and rotate(), not re-computing common subexpressions, etc.)
> and avoiding various stalls (apparently, the possible benefit here is
> limited to 15% now).

Reducing the ALU ops doesn't seem to have much impact on performance.  I
think the implementation more bottlenecked by the memory access.  Despite
I'm not going to ignore anything.


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.