Date: Wed, 24 Aug 2011 20:47:18 +0200 From: magnum <rawsmooth@...dband.net> To: john-dev@...ts.openwall.com Subject: Re: Terrible performance of sha512 (crypt) hash audit on/for Solaris On 2011-08-24 20:36, Robert B. Harris wrote: > Secondly, I'm very surprised at how slow my real world run is, compared to the performance test. > See, the performance I experienced below for three different builds. Well, maybe just two builds, since omp4 and omp7 performed about the same. > Is the sha512 hash, or something else, to blame on this poor performance? > Why such a hudge difference between the test and actual? The test shows generic crypt() DES. Try applying my patch "0020" from the wiki (I'm pretty sure it can be applied right onto a plain jumbo-5) and then run it like this: $ ./john -test -format=crypt -sub=sha512 Benchmarking: generic crypt(3) [?/64]... (2xOMP) DONE Many salts: 444 c/s real, 225 c/s virtual Only one salt: 444 c/s real, 224 c/s virtual $ ./john -test -format=crypt -sub=sha256 Benchmarking: generic crypt(3) [?/64]... (2xOMP) DONE Many salts: 384 c/s real, 192 c/s virtual Only one salt: 384 c/s real, 192 c/s virtual magnum
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.