If I’m recalling correctly, there were two issues here.

 

  1. general simplicity of the approach
  2. failure semantics – would it be possible to define the failure semantics of array operations (i.e. partial failures) in a way that was precise enough for interop?

 

Also, although array ops are not in the base case, they are in the initial set of extensions to the base case proposed in the use case document.

 

Glenn

 

 

 


From: owner-ogsa-hpcp-wg@ggf.org [mailto:owner-ogsa-hpcp-wg@ggf.org] On Behalf Of Ian Foster
Sent: Monday, August 21, 2006 3:44 AM
To: Steven Newhouse; humphrey@cs.virginia.edu
Cc: ogsa-hpcp-wg@ggf.org
Subject: Re: [ogsa-hpcp-wg] Minutes for OGSA HPC Profile telecon (Aug 18 2006)

 

I am also concerned about this. We've never had vector operations in Globus, but Chris Smith argued eloquently for their importance in the early stages of BES, and so I became convinced that we need them.

Ian.


At 09:34 PM 8/20/2006 +0100, Steven Newhouse wrote:

    AI-HPCP-0818c: Marvin Theimer will add first draft of section 4 to
            HPC Basic Profile that restricts BES operations to
            singletons


Could you expand on this... having the BES interface support operations on vectors of activities has been fairly important. Is this is what you are planning to remove?

Is this a profile restriction or an edit on the main BES document?

Steven
--
----------------------------------------------------------------
Dr Steven Newhouse   Mob:+44(0)7920489420  Tel:+44(0)23 80598789
Director, Open Middleware Infrastructure Institute-UK (OMII-UK)
c/o Suite 6005, Faraday Building (B21), Highfield Campus,
Southampton University, Highfield, Southampton, SO17 1BJUK

_______________________________________________________________
Ian Foster -- Weblog: http://ianfoster.typepad.com
Computation Institute: www.ci.uchicago.edu & www.ci.anl.gov
Argonne: MCS/221, 9700 S. Cass Ave, Argonne, IL 60439
Chicago: Rm 405, 5640 S. Ellis Ave, Chicago, IL 60637
Tel: +1 630 252 4619 --- Globus Alliance: www.globus.org