[20382] in cryptography@c2.net mail archive
Re: bounded storage model - why is R organized as 2-d array?
daemon@ATHENA.MIT.EDU (Steven M. Bellovin)
Thu Mar 9 13:00:16 2006
X-Original-To: cryptography@metzdowd.com
X-Original-To: cryptography@metzdowd.com
Date: Thu, 9 Mar 2006 10:14:43 -0500
From: "Steven M. Bellovin" <smb@cs.columbia.edu>
To: alex@alten.org
Cc: solinym@gmail.com, cryptography@metzdowd.com
In-Reply-To: <20060309071058.ECC719E848@ws6-2.us4.outblaze.com>
On Thu, 09 Mar 2006 02:10:58 -0500
alex@alten.org wrote:
> This is very useful for encrypting things like video
> streams without an expensive hardware cryptographic accelerator card.
>
I think you vastly overestimate how much hardware one needs to do
something like AES. I ran
dd if=/dev/zero bs=32k count=1024| openssl speed aes-128-cbc
on a 1500 Mhz Athlon. It reported speeds of ~27.5 MBps, or 220 Mbps.
Even video isn't that fast, and that's a slow CPU by today's standards.
Also -- I don't know how large these random tables have to be, but if
they don't fit in cache the cipher will be quite slow -- memory
bandwidth hasn't increased nearly as rapidly as CPU speed; modern
machines utterly rely on their caches.
--Steven M. Bellovin, http://www.cs.columbia.edu/~smb
---------------------------------------------------------------------
The Cryptography Mailing List
Unsubscribe by sending "unsubscribe cryptography" to majordomo@metzdowd.com
