Re: Performance tests of some AES implementations in C

From: Jean-Luc Cooke (jlcooke_at_engsoc.carleton.ca)
Date: 07/03/03


Date: 3 Jul 2003 07:44:22 -0700

Tom St Denis <tomstdenis@iahu.ca> wrote in message news:<UxKMa.46987$x4o.3313@news04.bloor.is.net.cable.rogers.com>...
> Christophe Devine wrote:
> > * gcc 3.3 without optimization flags
> >
> > ks (keys/s) enc. (bytes/s) dec. (bytes/s)
> > devine 447602.53 22149007.99 21558548.32
> > gladman 703920.48 22065922.98 21129782.90
> > mks 170851.10 20100502.79 19621669.83
> > nist 41707.69 295926.72 172438.71
> > tom 623074.29 17086076.19 19242102.24
>
> For the sake of contributing to the thread....
>
> On my Debian box with an Athlon 2400+ [gcc 3.3]
>
> ks (keys/s) enc. (bytes/s) dec. (bytes/s)
> devine 1760067.57 40673140.35 35350133.15
> gladman 2182333.95 40026516.45 40237402.44
> mks 331105.00 39797529.53 39509588.86
> nist 156884.53 778774.10 512502.56
> tom 2125805.20 49022613.99 46669001.00

gcc-2.95 -O on a deb athlon-xp 1.4Ghz
         ks (keys/s) enc. (bytes/s) dec. (bytes/s)
devine 703598.55 45031100.49 45106001.44
gladman 1325275.64 36091309.91 31204290.60
mks 285111.49 34578520.82 33876056.04
nist 124635.29 667357.38 442012.57
tom 2039026.99 34485732.68 39874892.12
jlcooke 3747634.30 31499782.40 15742298.83

with gcc-3.0 on same machine
         ks (keys/s) enc. (bytes/s) dec. (bytes/s)
devine 704657.09 45293703.65 45119989.58
gladman 1335131.26 36087646.65 31209464.96
mks 284756.27 34572917.74 33891124.43
nist 123806.05 666985.15 441882.68
tom 2042358.55 34463448.53 39845101.99
jlcooke 3747212.90 31501334.96 15738969.08

gcc-3.0 with -O6 gave:
         ks (keys/s) enc. (bytes/s) dec. (bytes/s)
devine 1017754.73 25855033.34 29015469.56
gladman 1174115.45 24131274.77 21877199.75
mks 272644.50 34448977.76 34109684.37
nist 140653.01 765026.03 506706.97
tom 1999720.02 25703431.35 33613799.75
jlcooke 3805826.63 26396759.01 11019928.43

well done folks.

JLC



Relevant Pages