[REQ]benchmark function

[perlish]

if hashcat-lite and plus have the benchmark function like JTR,we will be much easier to compare which hardware config run faster.

Quote:[root@localhost run]# ./john --test
Benchmarking: Traditional DES [128/128 BS SSE2-16]... DONE
Many salts: 1880K c/s real, 1880K c/s virtual
Only one salt: 2792K c/s real, 2764K c/s virtual

Benchmarking: BSDI DES (x725) [128/128 BS SSE2-16]... DONE
Many salts: 92928 c/s real, 92928 c/s virtual
Only one salt: 90880 c/s real, 90880 c/s virtual

Benchmarking: FreeBSD MD5 [32/64 X2]... DONE
Raw: 11296 c/s real, 11296 c/s virtual

Benchmarking: OpenBSD Blowfish (x32) [32/64 X2]... DONE
Raw: 532 c/s real, 532 c/s virtual

Benchmarking: Kerberos AFS DES [48/64 4K]... DONE
Short: 361984 c/s real, 358400 c/s virtual
Long: 1082K c/s real, 1082K c/s virtual

Benchmarking: LM DES [128/128 BS SSE2-16]... DONE
Raw: 38372K c/s real, 38372K c/s virtual

Benchmarking: dynamic_0: md5($p) (raw-md5) [SSE2i 10x4x3]... DONE
Raw: 9925K c/s real, 9925K c/s virtual

Benchmarking: dynamic_1: md5($p.$s) (joomla) [SSE2i 10x4x3]... DONE
Many salts: 8368K c/s real, 8368K c/s virtual
Only one salt: 6737K c/s real, 6737K c/s virtual

Benchmarking: dynamic_2: md5(md5($p)) (e107) [SSE2i 10x4x3]... DONE
Raw: 5101K c/s real, 5101K c/s virtual

[blaz]

hashcat plus and light will always run faster as they're on gpu, it would be easy to create a script to run each format type wih --runtime 60 -n 800 --gpu-loops 1024. it would take too much code to have the script parse the output and provide a nice output like what JtR has. it should be noted that JtR uses a different system for its c/s, where hachcat uses c/s JtR uses c/s*hashes.

[atom]

This is what comes closest yet: http://thepasswordproject.com/oclhashcat_benchmarking

[perlish]

(05-17-2012 09:34 AM)atom Wrote:  This is what comes closest yet: http://thepasswordproject.com/oclhashcat_benchmarking

got it ,thank you,atom.