[cryptography] [tahoe-dev] pycryptopp benchmarks

Eugen Leitl eugen at leitl.org
Thu Mar 22 17:30:12 EDT 2012


----- Forwarded message from Brian Warner <warner at lothar.com> -----

From: Brian Warner <warner at lothar.com>
Date: Thu, 22 Mar 2012 12:09:40 -0700
To: tahoe-dev at tahoe-lafs.org
Subject: Re: [tahoe-dev] pycryptopp benchmarks
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6;
	rv:11.0) Gecko/20120313 Thunderbird/11.0
Reply-To: Tahoe-LAFS development <tahoe-dev at tahoe-lafs.org>

On 3/21/12 11:00 AM, Zooko Wilcox-O'Hearn wrote:

> On 64-bit servers, the it costs something around 10 *nanoseconds* per
> byte, and on François's little low-power ARM box, it costs about 200
> nanoseconds per byte.

FYI, djb and friends just published a paper about high-speed crypto on
ARM processors with the "NEON" vector instruction set (which includes
the iPad 1 and iPhone 4), specifically the NaCl algorithms (Salsa20,
Poly1305, Curve25519, and Ed25519). They got encryption down to 5.6 CPU
cycles per byte.

 http://cr.yp.to/highspeed/neoncrypto-20120320.pdf

cheers,
 -Brian
_______________________________________________
tahoe-dev mailing list
tahoe-dev at tahoe-lafs.org
http://tahoe-lafs.org/cgi-bin/mailman/listinfo/tahoe-dev

----- End forwarded message -----
-- 
Eugen* Leitl <a href="http://leitl.org">leitl</a> http://leitl.org
______________________________________________________________
ICBM: 48.07100, 11.36820 http://www.ativel.com http://postbiota.org
8B29F6BE: 099D 78BA 2FD3 B014 B08A  7779 75B0 2443 8B29 F6BE



More information about the cryptography mailing list