Re: Performance testing of C/R

From: Brent Gorda (bgorda_at_lbl.gov)
Date: Tue Feb 25 2003 - 11:44:24 PST


I'm about to submit a request for summer students to the "Center for
Science and Engineering".  They have funds to pay for a limited number
of students (maybe 3-5 for all of CS).  They want us to try to come up
with 1/2 the funds to extend their reach.  Students cost $4750 for a 10
week stint.

I'm going to send in the current 3 positions we have in FTG: UPC, Vector
study, and C/R batch systems.

What's the call on whether we should try for someone to do some timings
on C/R on the filesystem GUPFS equipment?  Should I try to move forward
with this?

Brent

On Wed, 2003-02-19 at 19:27, jcduell_at_lbl_dot_gov wrote:
> On Wed, Feb 19, 2003 at 03:03:38PM -0800, Brent Gorda wrote:
> > Mike is seeing 1.4 GByte/sec on the Yottayotta box.  Insert lots of
> > disclaimers (like no file system ;-), but that is a pretty interesting
> > number.  I think some straightforward (ie student) work on this front
> > might net you all a good paper or some excellent PR.
> 
> Yeah, that does sound interesting.  I think we'll want to look at
> various filesystem optimizations in the future, and this would be a good
> start.
> 
> So what's the story with interns this summer?  Did we get any funding?
> 
> -- 
> Jason Duell             Future Technologies Group
> <jcduell_at_lbl_dot_gov>       High Performance Computing Research Dept.
> Tel: +1-510-495-2354    Lawrence Berkeley National Laboratory
>