From owner-chemistry@ccl.net Sun Jan 29 22:43:00 2006
From: "Andrew Fant fant(~)pobox.com" <owner-chemistry=-=server.ccl.net>
To: CCL
Subject: CCL: MD software question.
Message-Id: <-30692-060129203713-1920-vVnbMertR7Wom+XGkuQ5TA=-=server.ccl.net>
X-Original-From: Andrew Fant <fant[#]pobox.com>
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Date: Sun, 29 Jan 2006 17:49:46 -0500
MIME-Version: 1.0


Sent to CCL by: Andrew Fant [fant]_[pobox.com]
Mrcel and James both made good points that I won't bother duplicating here.  One 
other thing to bear in mind is that while the math(s) involved in MD is 
relatively straightforward, doing it efficiently usually isn't.  Even in 
single-threaded code, there are a whole constellation of 
tricks/shortcuts/advanced techniques that can make things go much faster (an 
order of magnitude or more) compared to what a naive undergrad might achieve 
left to their own devices.  And when you get into parallel processing, it 
becomes even more hairy.

Andy

-- 
Andrew Fant    | And when the night is cloudy    | This space to let
Molecular Geek | There is still a light          |----------------------
fant%%pobox.com | That shines on me               | Disclaimer:  I don't
Boston, MA     | Shine until tomorrow, Let it be | even speak for myself