Inefficiency comments

[Nick Maliszewskyj]

Ray Osborn wrote:
> 
> Mark Koennecke wrote:
> >        At the bottomline I'am reluctant to add vData (and much more
> >complexity)
> >        to the NeXus API as long as nobody has proven with a profiler output
> >        that his program spends most of its time writing NeXus. And it is
> >        proven that vData are so much more efficient. Even then (case 1,
> >        profiler) I would rather prefer to investigate if our data can not be
> >        structured more efficiently.
> 
> I'm sympathetic to this viewpoint.  I just wanted to point out that we need
> to do some benchmark tests, following the negative APS experience, and
> should do them soon before NeXus is too well-established in its current
> form.  Does anyone have the time to do so?  Actually, this issue will come
> up at the forthcoming imageNCIF workshop to be held at Brookhaven in
> October, because one of the reasons they give for rejecting HDF is that it
> can't cope with their data rates (4MB/s).  They have invited someone from
> NeXus to attend.
> 
> Ray
> 
> ------------------------------------------------------
> Dr Ray Osborn                  Tel: +1 (630) 252-9011
> Materials Science Division     Fax: +1 (630) 252-7777
> Argonne National Laboratory    E-mail: ROsborn at anl.gov
> Argonne, IL 60439-4845

I can take a stab at benchmarking. The range of platforms available to me is
somewhat limited, though. I can do linux (on Intel Pentia), irix, and possibly
vms (on a VAX 4000).

Nick

-- 
|_    |_  |_  |_________________   Nicholas C. Maliszewskyj
|__   |_  |_  |_         |_        NIST Center for Neutron Research 
|_\_  |_  |_  |_         |_        National Institute of 
|_ \_ |_  |_  |______    |_                  Standards & Technology
|_  \_|_  |_       |_    |_        Bldg 235, Rm E123         
|_   \__  |_       |_    |_        Gaithersburg, MD 20899
|_    \_  |__________    |_        nickm at rrdjazz.nist.gov
--------------------------------------------------------------------------------
Return-Path: <nickm at rrdjazz.nist.gov>
Received: from dns2.anl.gov by ipns.pns.anl.gov (MX V4.2 AXP) with SMTP; Tue,
          09 Sep 1997 11:48:35 CST
Received: from osborn.msd.anl.gov (osborn.msd.anl.gov [146.139.244.39]) by
          dns2.anl.gov (8.6.11/8.6.11) with ESMTP id LAA07374 for
          <ROsborn at anl.gov>; Tue, 9 Sep 1997 11:48:31 -0500
Received: from dns2.anl.gov (146.139.254.3) by osborn.msd.anl.gov with SMTP
          (Eudora Internet Mail Server 1.1.2); Tue, 9 Sep 1997 11:48:03 -0500
Received: from rrdjazz.nist.gov (rrdjazz.nist.gov [129.6.120.31]) by
          dns2.anl.gov (8.6.11/8.6.11) with ESMTP id LAA07342 for
          <napi at anl.gov>; Tue, 9 Sep 1997 11:47:57 -0500
Received: from rrdjazz.nist.gov by rrdjazz.nist.gov via ESMTP
          (950413.SGI.8.6.12/930416.SGI) id MAA14266; Tue, 9 Sep 1997 12:44:02
          -0400
Message-ID: <34157DB1.E35E654A at rrdjazz.nist.gov>