Re: Timings issue

From: Brian Gladman (fake_at_nowhere.org)
Date: 06/20/03 

Date: Fri, 20 Jun 2003 09:01:47 +0100

"R3769" <r3769@aol.com> wrote in message
news:20030619234430.11559.00000712@mb-m13.aol.com...
> ><K%tIa.759$y32.265@newssvr19.news.prodigy.com>
> >
> >On Thu, 19 Jun 2003 17:19:49 -0700, R3769 wrote:
> >
> >
> >>>I wonder if this is the right newsgroup for this.
> >>
> >> Seems to me sci.crypt has a lot of this type of discussion lately.
> >> Neither sci nor crypt I would think.
> >
> > You mean to say that timings of implementations of cryptographic
> >algorithms on different platforms are not relevant to cryptography? If
> >you do, I respectfully disagree.
> >
>
> Fair enough. A little crypt and even less sci. The whole issue reminds
me of
> a discussion I had twenty years ago with a software guy whose DES
> implementation was faster than Intel's new chip. Kind of curious at the
time,
> but how important is that fact today?

In my experience it is still very important to many people.

In particular the world of products with embedded microcontrollers is highly
competitive and a few pennies (cents) on product costs often count heavily.

Hence if an algorithm can be made to work more efficiently on a less costly
processor, products can be bought to market at lower cost. And when there
are millions of units this can really count.

> Now if you all want to compare cycles per secure-byte I personally would
find
> it more interesting.

Sometimes the tricks used to get speed can reduce security but many of those
who build high speed code are also experts in how to design code that
designed for secure use.

   Brian Gladman

Relevant Pages

  • Re: New 2 Cryptography
    ... Newsgroups: sci.crypt ... > cryptography and I thought I'd post here to ask a few questions. ... Also there is a question of licensing one or more algorithms, ... rounds of arithmetic operations, and you wind up with something that would ...
    (sci.crypt)
  • Re: Size of RN vs USN (Was: Germany Still Loses BB...) [OFFTOPIC, BUT INTERESTING]
    ... >>That would be news to the cryptography world. ... algorithms exist which would solve these problems in polynomial time ... Sometimes it takes a lot of machines working together, ... there is this hype about quantum computes. ...
    (soc.history.war.world-war-ii)
  • Re: Help please..
    ... likely you will find faster general-purpose implementations ... than LAPACK on general-purpose platforms. ... compile the source code for your target. ... ESPRIT algorithms some ten years ago. ...
    (comp.dsp)
  • Re: crypt equivalent for Win32 platform?
    ... no means an expert, nor even possibly a novice in cryptography, but it pains ... Learn what a cipher is, a hash, cipher ... modes, key transformations, et al. ... your preferred local Win32 newsgroup for implementations to use. ...
    (comp.lang.c)
  • Re: [PATCH resend][CRYPTO]: RSA algorithm patch
    ... I'd rather code to the PKCS#1 RSA Cryptography Standard ... if not using constant-time crypto implementations) and not ... and combined attacks can give enough information. ... in security there is always a threshold, ...
    (Linux-Kernel)