Re: [Beowulf] help on island model

2006-03-10 Thread Jeremy Baker
In spite of it being in "unfit" individuals only,if you lose those individuals you lose any possibility of ever gettingthat gene right!   An artificial Founder's Effect.    Vermont's sugar maple trees are migrating north towards Canada. In the new territory, the ideal genotype for the region's soi

Re: [Beowulf] Tools for graphing (creating graphics of) execution sequences

2006-03-10 Thread Eric Thibodeau
Le Vendredi 10 Mars 2006 03:22, Fred L Youhanaie a écrit : > > > if only I could find a tool that is scaled to CPU times ;) > > > > The Gantt chart was definately what I was thinking of...without even > > knowing > > it. Thanks! > > It may be worthwhile searching for "gantt" on sourceforge

Re: [Beowulf] g77 limits...

2006-03-10 Thread Toon Moene
Robert G. Brown wrote: Ah, yeah. Let me embarrass myself even further. My first foray into this territory was maybe 1978 or so when I was still a tender young first year graduate student and the computing world was punch cards and IBM 370's that were slower and stupider than my palm pilot is t

Re: [Beowulf] Tools for graphing (creating graphics of) execution sequences

2006-03-10 Thread Fred L Youhanaie
if only I could find a tool that is scaled to CPU times ;) The Gantt chart was definately what I was thinking of...without even knowing it. Thanks! It may be worthwhile searching for "gantt" on sourceforge, but I don't think you will be able to get down to the cpu timescales. If you like

Re: [Beowulf] Tools for graphing (creating graphics of) execution sequences

2006-03-10 Thread Eric Thibodeau
Hi Fred, Thanks a mil for this insight. Actually, it's the first time I see someone refer to project management as being similar to parallel processing. In fact, the optimisation of projects, with critical paths, milestones, simultaneous ends/beginings and dependancy makes of this appr

Re: [Beowulf] A bit OT - scientific workstations - recommendations

2006-03-10 Thread Andrew M.A. Cater
On Fri, Mar 10, 2006 at 09:39:50PM +, John Hearns wrote: > On Fri, 2006-03-10 at 14:47 -0500, Douglas Eadline wrote: > > > > > I have heard stories about some of the first vacuum tube computers where a > > a full time technician walked around inside the computer > > and replaced blown out tub

Re: [Beowulf] A bit OT - scientific workstations - recommendations

2006-03-10 Thread John Hearns
On Fri, 2006-03-10 at 14:47 -0500, Douglas Eadline wrote: > > I have heard stories about some of the first vacuum tube computers where a > a full time technician walked around inside the computer > and replaced blown out tubes - between every program run. I tend to > think this has a certain myth

Re: [Beowulf] A bit OT - scientific workstations - recommendations

2006-03-10 Thread Justin Moore
> I have heard stories about some of the first vacuum tube computers where a > a full time technician walked around inside the computer > and replaced blown out tubes - between every program run. I tend to > think this has a certain myth aspect to this story, but like all myths it > probably has s

Re: [Beowulf] top500: the game, the lifestyle

2006-03-10 Thread Craig Tierney
Mark Hahn wrote: does anyone know why the submission deadline for top500 is so far in advance of the list's publication? The bigger your system, the less the deadline applies. Craig ___ Beowulf mailing list, Beowulf@beowulf.org To change your subs

Re: [Beowulf] A bit OT - scientific workstations - recommendations

2006-03-10 Thread Douglas Eadline
--snipage-- > Unless, of course, you > have so large a cluster (and budget) that assigning a whole FTE admin > who does NOTHING but hardware maintenance from a local warehouse of > spare parts is cost effective... I have heard stories about some of the first vacuum tube computers where a a f

Re: [Beowulf] top500: the game, the lifestyle

2006-03-10 Thread Patrick Geoffray
Mark Hahn wrote: does anyone know why the submission deadline for top500 is so far in advance of the list's publication? Because everybody ignores it ? Patrick -- Patrick Geoffray Myricom, Inc. http://www.myri.com ___ Beowulf mailing list, Beowulf@be

[Beowulf] top500: the game, the lifestyle

2006-03-10 Thread Mark Hahn
does anyone know why the submission deadline for top500 is so far in advance of the list's publication? thanks, mark hahn. ___ Beowulf mailing list, Beowulf@beowulf.org To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.

Re: [Beowulf] Problem using mpich2 and scalapack

2006-03-10 Thread Joachim Worringen
Ivan Paganini: I am trying to use at the same time some mpich2 routines and scalapack. My code is written in fortran90, and I am using pgi There's an MPICH2 mailing list (listed on MPICH2 home page) which in this case might help you better. Joachim -- Joachim Worringen - NEC C&C research l

[Beowulf] Re: newbies' dilemma / firewire? (Hahn) (Will) (Geoffray) (Lindahl)

2006-03-10 Thread Ed Karns
On Mar 9, 2006, at 7:32 PM, [EMAIL PROTECTED] wrote:Michael Will wrote: Infiniband with DDR is already at 20Gbps over CX4 copper Over 3 meters cables thick as firehose. 5 meters if you like to play with fire. There is a time when fiber is the right thing to do. However, WDM solutions are still ex

[Beowulf] Re: newbies' dilemma / firewire? (Hahn) (Will)

2006-03-10 Thread Ed Karns
On Mar 9, 2006, at 7:32 PM, [EMAIL PROTECTED] wrote:Infiniband with DDR is already at 20Gbps over CX4 copper " The 4X InfiniBand protocol extends the existing 1X protocol by supporting up to four 2.5Gb/sec dual-simplex connections for an effective duplex transmission speed of 10Gb/sec. ... " (From

Re: [Beowulf] help on island model

2006-03-10 Thread Robert G. Brown
On Thu, 9 Mar 2006, Jeremy Baker wrote: How CS has used the island model to extrapolate the design of a model for software/hardware dynamics is beyond my knowledge base. Biology has been my learn'n. The point of Island models in GAs is that how well a GA works is a rather delicate balance betw