Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20150817144333.GB31572@openwall.com>
Date: Mon, 17 Aug 2015 17:43:33 +0300
From: Solar Designer <solar@...nwall.com>
To: john-dev@...ts.openwall.com
Subject: Re: FMT_OMP_BAD

On Mon, Aug 17, 2015 at 05:23:55PM +0300, Solar Designer wrote:
> wpapsk is in there by mistake.  It's a slow format that should show good
> OpenMP scaling, and it does when I test it now:
> 
> [solar@...er run]$ OMP_NUM_THREADS=1 ./john-omp -test -form=wpapsk
> Warning: OpenMP is disabled; a non-OpenMP build may be faster
> Benchmarking: wpapsk, WPA/WPA2 PSK [PBKDF2-SHA1 128/128 AVX 4x]... DONE
> Raw:    1308 c/s real, 1308 c/s virtual
> 
> [solar@...er run]$ OMP_NUM_THREADS=10 ./john-omp -test -form=wpapsk
> Will run 10 OpenMP threads
> Benchmarking: wpapsk, WPA/WPA2 PSK [PBKDF2-SHA1 128/128 AVX 4x]... (10xOMP) DONE
> Raw:    11560 c/s real, 1154 c/s virtual
> 
> There must have been some glitch during my benchmarks causing wpapsk to
> appear to scale poorly.

Confirmed that it was a glitch (unrelated server load?) by reviewing the
individual benchmarks' output.  wpapsk's benchmark at 10 threads was:

Benchmarking: wpapsk, WPA/WPA2 PSK [PBKDF2-SHA1 128/128 AVX 4x]... (10xOMP) DONE
Raw:    3120 c/s real, 311 c/s virtual

Nearby benchmarks (the previous and the next format benchmarked) look
unaffected.

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.