[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20060427230328.GA18791@openwall.com>
Date: Fri, 28 Apr 2006 03:03:28 +0400
From: Solar Designer <solar@...nwall.com>
To: john-users@...ts.openwall.com
Subject: Re: Performance tuning
On SSE vs. MMX:
On Fri, Apr 28, 2006 at 12:35:54AM +0200, sebastian.rother@...erlin.de wrote:
> Wouldn`t it be better to benchmark /during compilation) on the CPU itself
> wich kind of implementation performs faster?
This makes sense - and John has been doing that kind of thing in
"generic" and 32-bit SPARC builds. But this approach also has several
disadvantages. Most likely, I'll leave it for "generic" only in the
next official release.
> You may benchmarked it on AMD CPUs but also on AMD64-base CPUs?
I've benchmarked the 32-bit-with-SSE code (effectively 128-bit) on
32-bit and 64-bit AMD CPUs. They behaved almost the same.
Sorry, I did not record the exact CPU types. If I have a spare moment
for this, I'll re-test and post the results in here.
> (Also P4 != P4.. wich core?
Indeed. Generally, newer P4s seemed to perform worse with MMX (slower
per-MHz) than older ones did - making the use of SSE more desirable.
--
Alexander Peslyak <solar at openwall.com>
GPG key ID: B35D3598 fp: 6429 0D7E F130 C13E C929 6447 73C3 A290 B35D 3598
http://www.openwall.com - bringing security into open computing environments
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.
