[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-id: <55DC1613-CBA4-47DB-8E11-EEA6C21DEFBB@Erols.com>
Date: Mon, 10 Oct 2011 16:48:08 -0400
From: Erik Winkler <EWinkler@...ls.com>
To: john-dev@...ts.openwall.com
Subject: Benchmarks vs GCC version
I noted the following using two different gcc compilers with the default compiler flags on john-1.7.8-jumbo-7;
gcc 4.6.1 (MacOS 10.7):
../run/john -test=5 -format:DES
Benchmarking: Traditional DES [128/128 BS SSE2-16]... DONE
Many salts: 1961K c/s real, 1961K c/s virtual
Only one salt: 1687K c/s real, 1690K c/s virtual
../run/john -test=5 -format:LM
Benchmarking: LM DES [128/128 BS SSE2-16]... DONE
Raw: 10450K c/s real, 10450K c/s virtual
gcc 4.2.1 (Xcode 4.1 on MacOS 10.7):
../run/john -test=5 -format:DES
Benchmarking: Traditional DES [128/128 BS SSE2-16]... DONE
Many salts: 2521K c/s real, 2521K c/s virtual
Only one salt: 2016K c/s real, 2016K c/s virtual
../run/john -test=5 -format:LM
Benchmarking: LM DES [128/128 BS SSE2-16]... DONE
Raw: 12210K c/s real, 12210K c/s virtual
Why is the gcc 4.2.1 code significantly faster than the 4.6.1 code? Is it because of the SSE2 intrinsics code used with gcc 4.6.1?
Thanks,
Erik
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.
