Software Coordinating Committee Conference Call
		     February 1, 2007 1:00 PM EST
			  Recorder: C. DeTar


Present: 

   Brower, DeTar, Levkova, Efstathiadis, Watson, Scholz, Osborn,  
   Holmgren, Simone, Jung, Gottlieb, Fowler, Zhang, Basak

Absent:

   Mawhinney, Pochinski, Khoriaty, Joo, Clark, Renner, Edwards 

=====================================================================
** Action items

   [ After the call concluded ?Steve introduced Subhasish Basak: ]

 Gottlieb:

   My new postdoc, who is partially funded by SciDAC is Subhasish Basak. 
   His email address is sbasak@indiana.edu


Plan for miminal CRE implementation
   (Chip/Balint, Don, Statos)

   Watson: After our new machine is operational, we will
     flip 6n to 64-bit.  So the Infiniband queue will be homogeneous
     We will turn off the 4g cluster
   Holmgren: We need to have a subcommittee meeting soon
   Brower: The next two Thursdays are open for this meeting.
   Holmgren: Chip, Balint, and Stratos.  Let's meet next week via
      three-party call.
   Brower: Partition the tasks into trivial and long range.
      

Workflow for benchmarking
    (Rob Fowler)

    [ see benchmark_workflow_figs.pdf sent yesterday ]

  Fowler: The easiest way to read the figure is from back to front.
    This is for GAMESS, the Chemistry application.
    It shows the level of detail needed for specifying our workflow system
    under Taverna.  
    Fig 2 is for benchmarking and Fig 1 is for compilation
    All the operations are encapsulated in grid services.
    It would be a fairly simple harness for our application.
    Jeff Tilson at RENCI is a good resource for Don.

  Holmgren: There seems to be some interoperability, which is good.
     Taverna can interoperate to some extent with Kepler.
     We still haven't found one where the running is simplified
     to the extent we would like -- e.g. talking directly with PBS.
     We'd like to be able to adapt one to our needs.

  Brower: I will be going to a SciDAC meeting next Tuesday.
     Could you send me names of the PERI people who will be coming?

  Holmgren: It would be good for someone to check over 
     on www.usqcd.org to be sure we don't have missing links.

News on Asqtad/RHMC on QCDOC?
   (Chulwoo, Carleton)

    Jung: We are working on it.

Benchmarking MILC 7.4.0

   DeTar: Ying, you sent me a message that I haven't had time to
     respond to.

Slides for BU SciDAC October workshop

   Brower: I posted them.  Please send any talks that may be missing.


Postponed the following:

News on performance on DW Level 3 codes for BG/L
   (Andrew, Chulwoo, James,Balint)

When do we start to prototype and design API for multi-core?
   (Robert,...)


Committee conference concluded at 1:30 PM EST.  
Next call Feb 15 at 1:00 PM EST

======================================================================