From chemistry-request@server.ccl.net  Tue Feb 29 13:17:14 2000
Received: from mailsrv.engr.uconn.edu (mailsrv.engr.uconn.edu [137.99.21.179])
	by server.ccl.net (8.8.7/8.8.7) with ESMTP id NAA28326
	for <chemistry@ccl.net>; Tue, 29 Feb 2000 13:17:13 -0500
Received: from engr.uconn.edu (IDENT:bhupen@camd [137.99.9.39])
	by mailsrv.engr.uconn.edu (8.9.1a/8.9.1) with ESMTP id NAA03884
	for <chemistry@ccl.net>; Tue, 29 Feb 2000 13:19:19 -0500 (EST)
Sender: bhupen@engr.uconn.edu
Message-ID: <38BBEBBD.93CEBE07@engr.uconn.edu>
Date: Tue, 29 Feb 2000 10:54:37 -0500
From: Bhupendra Wakankar <bhupen@engr.uconn.edu>
Organization: University of Connecticut
X-Mailer: Mozilla 4.7 [en] (X11; I; Linux 2.2.5-15smp i686)
X-Accept-Language: en
MIME-Version: 1.0
To: CCL_posting <chemistry@ccl.net>
Subject: NT parallel cluster
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit

Dear CCLers,
Hi.

We have 6 computers in our lab (4 running on WINNT and 2 on RedHat 6.0).
I use the Linux PC's for my computations while the 4 NT PC's stay
relatively idle. All these PC's are fairly powerful (> 400MHz
multiprocessor Pentiums) and thus have untapped number crunching power.
I am wondering if it is possible to build a parallel cluster using these
4 NT PC's (and better still, using all 6 PC's). 

Almost all network of PC clusters that I read about on the web run under
Linux. Is there any particular reason for not choosing NT (lack of
parallel programs perhaps ?). 

I would also like to know if there are any DFT programs (parallel/single
processor, free/commercial) running on Windows NT?

Thanks in advance,

Regards,
Bhupendra

