[13241] in cryptography@c2.net mail archive
Re: faster modexp()? cipheractive
daemon@ATHENA.MIT.EDU (Bill Stewart)
Sun May 11 20:37:18 2003
X-Original-To: cryptography@metzdowd.com
X-Original-To: cryptography@metzdowd.com
Date: Sun, 11 May 2003 16:36:45 -0700
To: <cypherpunks@lne.com>
From: Bill Stewart <bill.stewart@pobox.com>
Cc: cryptography@metzdowd.com
In-Reply-To: <3EBD45DA.90F5258B@cdc.gov>
At 11:32 AM 05/10/2003 -0700, Major Variola (ret) wrote:
>Forwarded from cryptography list... note that this company has a
>download of their fast RSA library (its probably an assembly hack)
>
>Anyone heard of these guys? An Isreali technology firm that claims to
>have a new patent-pending process for modexp that's 3-6 times faster
>depending on playtform.
>
>URL is at http://www.com/technology/technology.htm
http://www.cipheractive.com/technology/technology.htm
I haven't downloaded and seen whether you need to disassemble the
free crippleware to figure out what it's really doing,
but my friend John Doe tried unsuccessfully to do so,
and perhaps a human will respond to the log messages tomorrow.
It wants some kind of public key, probably a raw hex RSA key.
Two obvious methods for them to use are
- some interesting mathematical breakthrough like Montgomery Multiplication
only faster
(ok, how to make such a breakthrough isn't obvious,
but what to do with it if you had one is.)
- no new math, just building a modexp library that uses
vector processing features on Intel-like chips like SSE / SSE2 / etc.
---------------------------------------------------------------------
The Cryptography Mailing List
Unsubscribe by sending "unsubscribe cryptography" to majordomo@metzdowd.com
