Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Date: Wed, 5 Jun 2013 00:28:24 +0200
From: Lukas Odzioba <lukas.odzioba@...il.com>
To: john-users@...ts.openwall.com
Subject: Phoronix Test Suite vs JtR

solar, all:
when I saw this article:
http://www.phoronix.com/scan.php?page=article&item=intel_4770k_linux&num=3
For me it was weird that 3770k is slower than 3470 (less L3,lower
clock, no HT, same architecture).
3470 - 38k c/s
3770k - 30k c/s

My first thought is that those two results were swapped accidentaly.
I asked about that author of this article and he kindly replied that
results were not swapped.

When I started digging I found what is really benchmarked here:
http://openbenchmarking.org/innhold/67d54b05cc821549302ae6ca623b8d4b4260aa00

Briefly I see some obvious flavs there:
-it uses 1.7.9-jumbo-7 but none of its features (for now it could be
better to test on 1.8.0)
-not using -format option during -test, so all formats are benchmarked
but only 1 value is parsed from the results
-custom build is not a good idea - we have proper architecture
dependent make targets
-openssl deps should be avoided to make results consistent between
platforms (not important in des,bf,md5crypt but someday someone might
want to add another format)
-MD5, Blowfish are our internal names what is beeing benchmarked are
md5crypt and bcrypt.
-maybe now we should use -fork instead of openmp

I also ran this test on my 3770k with the following results:
Blowfish 5817 Real C/S
MD5 41761 Real C/S -

I believe people here know the best how to use JtR as a benchmark and
we could help fix that.
I am also looking forward to hear comments, and how it could be improved.

Lukas

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.