Date: Mon, 20 Oct 2008 07:46:35 -0300 From: Nahuel Grisolía <nahuel.grisolia@...il.com> To: john-users@...ts.openwall.com Subject: Re: fast freebsd MD5 implementation Simon Marechal wrote: > Solar Designer wrote : >> Athlon 64 3000+ 2.0 GHz >> old code: 8970 c/s >> 4x: 7060 >> 8x: 4500 >> 12x: 5100 >> 16x: 5100 >> 20x: 5020 >> >> Q6600 2.4 GHz (one core): >> old code: 10200 c/s >> 4x: 14844 >> 8x: 9592 >> 12x: 9374 >> 16x: 3200 >> 20x: 3100 > > My GCC tests are from version 4.1.3, which is old. I had a friend tweak > the source with 4.3, and he could get 5000 k/s on the laptop where i > tested the following: > > With ICC 10.1, U7600, 1.2ghz, 32bits > 4x: 7628 > 8x; 11300 > 12x: 10200 > 16x: 7950 > > This is interesting, as I assumed 3 was the best, based on BarSW > results. But I suppose it would be true only in 64bit mode. > Sorry for this kind of stupid question.. but... what "c/s" means? and what about those 12X, 16X...? Thanx in advance. -- To unsubscribe, e-mail john-users-unsubscribe@...ts.openwall.com and reply to the automated confirmation request that will be sent to you.
Powered by blists - more mailing lists
Powered by Openwall GNU/*/Linux - Powered by OpenVZ