Date: Tue, 27 Mar 2012 17:21:44 +0530 From: SAYANTAN DATTA <std2048@...il.com> To: john-dev@...ts.openwall.com Subject: Re: JtR: GPU for slow hashes On Sun, Mar 25, 2012 at 9:21 AM, Solar Designer <solar@...nwall.com> wrote: > On Sat, Mar 24, 2012 at 11:21:03PM -0400, SAYANTAN DATTA wrote: > > I have started working on OpenCL implementation of MSCash2 and I expect > to > > deliver the unoptimized version of codes on or before April 1(no April > > fool).Also I would like to know the estimated time required for the > > implementation above algorithm because its always better to test yourself > > against the clocks.Since I am at the end of my semester I am having a > > pretty busy schedule this week but I will try my best to deliver them as > > early as possible. > > Your proposed due date of April 1st for the initial implementation makes > sense to me considering that you're just getting involved in the project. > (For your second JtR format and on, you could try to complete initial > unoptimized implementations quicker - like in 2 days.) As to time > needed to debug and optimize the code, it can vary a lot (by format, > desired performance, person working on the task, etc.) - so I cannot > provide an estimate/expectation. > > > Since I'm using AMD/ATI GPU I won't be able to test against the cuda > > codes.Therefore, are there any standard results against which I can bench > > my codes? I am running on radeon hd 4890 . > > http://hashcat.net/oclhashcat-plus/ gives 132.1k c/s at MSCash2 on > "Ubuntu 11.10, 64 bit Catalyst 11.12 1x ATI hd5970 stock core clock". > According to the numbers from > http://en.wikipedia.org/wiki/Comparison_of_AMD_graphics_processing_units > your 4890 should do roughly: > > 132100*800*850/(3200*725) = 38719 c/s > > In fact, 4890 is probably a bit faster than 5770 due to higher memory > bandwidth. So it has relatively more bandwidth per core than 5970 does. > Thus, it might deliver a slightly higher speed than above - maybe 39k c/s > or so. You can try with oclHashcat-plus for yourself and let us know. > (Just do not reverse-engineer any hashcat code; ours has to be original.) > > Per this comparison: > http://www.tomshardware.com/reviews/radeon-5770-overclocking,2473-15.html > 4890 is in fact faster than 5770, although that's for gaming, so it > might not be relevant. > > Thanks, > > Alexander > Hi Alexander, I have a basic question regarding MSCash2. In above algorithm two inputs namely ussrname and password are used to produce a certain hash.Then the generated hash is compared with the stored value and if they are equal then the username and password entered are correct.Now we hit and try different values of password to produce a hash which matches the given value .So does this mean the username is some fixed string??i.e is the username known to us beforehand and we only have to guess the password?Right now my code assumes the username a fixed string.Is it all right?? Regards, -Sayantan 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.