Date: Fri, 3 May 2013 15:18:25 +0400 From: Solar Designer <solar@...nwall.com> To: john-dev@...ts.openwall.com Subject: Re: zip-opencl Dhiru, On Fri, May 03, 2013 at 03:17:17PM +0530, Dhiru Kholia wrote: > On 05/03/13 at 07:47am, Solar Designer wrote: > > While crypt_all() checks 2 bytes of PBKDF2 output only (and it can't > > quickly check more), it computes the full PBKDF2 output right away. > > cmp_exact() simply returns 1. This means that we both incur the false > > positives (and don't filter them out!) and incur the performance hit of > > computing the full PBKDF2 output. Instead, we should have the PBKDF2 on > > GPU compute only the 160-bit portion of PBKDF2 output that contains the > > required 2 bytes. We'll compute the rest of PBKDF2 output on CPU in > > cmp_exact() if necessary (usually it won't be) > > > > If I parse our test vectors right, it looks like for one of them we > > currently compute 2x160-bit of PBKDF2 output and for the other 4x160-bit, > > in both cases instead of just 1x160-bit that we actually have to compute. > > This optimization is now implemented in the CPU "zip" format. OK. This has doubled the speed at --test. Apparently, the second test vector is not used during benchmarking because we have BENCHMARK_LENGTH set to -1. I think that's fine for this format. > However, we would need to revert it in case we decide to implement > decryption and decompression later on. No, in that case we'd need to compute the rest of PBKDF2 output in cmp_exact(). It's quite dumb to compute the full PBKDF2 output right away simply because we need it once in 65536 passwords tested. > I am guessing that we would need to do partial decryption and > decompression to reduce / eliminate the false positives. > > Jim and magnum seem to be the right guys for this ;) Maybe, but if you work on it then you may learn something new. ;-) Thanks, Alexander
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.