Date: Thu, 10 May 2012 12:14:44 +0530 From: SAYANTAN DATTA <std2048@...il.com> To: john-dev@...ts.openwall.com Subject: Re: Sayantan: Weekly Report #3 Hi Alexander, Reduce BINARY_SIZE to 4, make other relevant adjustments. Then you > will in fact have false positives reaching cmp_exact(), and you'll need > to have cmp_exact() implemented for real. Move the "byte to hexstring" > conversion from crypt_all() to cmp_exact(), because you only need to > perform the conversion when you have a false positive, not all the time. > Or you may perform the reverse conversion there, such as by simply > calling binary() and using all of its returned 16 bytes, not just 4. > Did that. Now getting around 84k c/s without omp and upto 90k c/s with omp using very large value of kpc. pbkdf2_kernel.cl with the SHA1_part*() macros and SHA1() inline function > does indeed look better. Does it achieve the same performance as before? > Yes it does. Infact it performs better on GTX570. 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.