hi,
i'll definetly have a look at the old posts if i find them. :-)
thank you very much for this mail. it has really helped me understanding
a bit more of what i was doing. now, results really make sense.
hardware disabled
=================
openssl speed -elapsed
sign verify sign/s verify/s
rsa 512 bits 0.0015s 0.0002s 676.4 6309.0
rsa 1024 bits 0.0089s 0.0004s 111.7 2255.0
rsa 2048 bits 0.0518s 0.0015s 19.3 676.0
rsa 4096 bits 0.3418s 0.0052s 2.9 192.2
hardware enabled
================
openssl speed -elapsed -engine chil
sign verify sign/s verify/s
rsa 512 bits 0.0042s 0.0024s 239.5 415.3
rsa 1024 bits 0.0121s 0.0035s 82.5 282.5
rsa 2048 bits 0.0597s 0.0073s 16.8 136.1
rsa 4096 bits 0.3917s 0.0215s 2.6 46.6
with hardware enabled now i get 82.5 signs which i guess, as you said,
is using just one processor from the nShield (which has two). so if it
used the two processors it would do 165 signs more or less (nShiled is
supposed to do 150 operations for second).
as you can see, hardware is slower. my box is an Intel P4 at 1,4 GHz and
is a bit faster than the processors in the nShiled (i think the model
i'm trying is one of the worstest). i've tried the hardware version of
my program with a multiprocess and i've gain more performace (uses two
processors).
but, what if i use a dual pentium box with P4 at 2GHz or a fastest
machine? this will be faster and cheaper than the cryptographic
hardware. eventhough, the cryptographic hardware has more fetures than
just do operations (at least the nShield), which may be is the good
thing.
anyway, everything makes more sense now. thank you very much.
best regards,
aleix
______________________________________________________________________
OpenSSL Project http://www.openssl.org
User Support Mailing List [EMAIL PROTECTED]
Automated List Manager [EMAIL PROTECTED]
