Re: [Beowulf] IEEE 1588 (PTP) - a better cluster clock?

On 7/25/07, Patrick Ohly <[EMAIL PROTECTED]> wrote: Thanks for pointing that out. In general BTime looks similar in spirit to PTP; let me point out similarities and differences below. I thought so too. PTPd at some point also had a kernel patch to obtain time stamps for packets, but replaced

Re: [Beowulf] hardware question: building a cluster node/ student workstation

Scientific Linux (RHEL 4) AMD 4400+ x2 Athlon 64 (dual core, 2MB L2) Abit nf-95 motherboard (cheapest socket 939 board at the time) 2GB RAM, DDR 400 200GB SATA hard drive integrated graphics, sound, 10/100 LAN all my pennies are paper-thin: this actually seems fairly generous, at least in cpu an

Re: [Beowulf] purse strings

Thanks everyone for you replies, I've had quite a few off list too. For an assignment if you were wondering. Cheers, Andy On 25/07/07, Greg Lindahl <[EMAIL PROTECTED]> wrote: On Wed, Jul 25, 2007 at 05:16:03PM +0200, Geoff Galitz wrote: > I'm not so sure the process really differs between ac

Re: [Beowulf] purse strings

On Wed, Jul 25, 2007 at 05:16:03PM +0200, Geoff Galitz wrote: > I'm not so sure the process really differs between academia and the > commerial sector. I work in both regularly and in my experience they are > quite similar. I've done both and they're wildly different, because all my academic b

[Beowulf] [PCGRID08] CFP for Workshop on Desktop Grids and Volunteer Computing Systems

CALL FOR PAPERS Second Workshop on Desktop Grids and Volunteer Computing Systems (PCGrid 2008) held in conjunction with the IEEE International Parallel & Distributed Processing Symposium (IPDPS) April, 2008 Miami, Florida, U.S.A. web site: http://pcgrid.lri.fr Desktop grids and volunteer computi

[Beowulf] hardware question: building a cluster node/ student workstation

About a year ago I put together a small cluster of linux workstations for students in our department. At the time, I was conservative with spending money and outfitted each node with something like: Scientific Linux (RHEL 4) AMD 4400+ x2 Athlon 64 (dual core, 2MB L2) Abit nf-95 motherboard (chea

Re: [Beowulf] MPI2007 out - strange pop2 results?

Completely agreed. The fact of the matter is that companies, who by nature are quite knowledgeable regarding their product, are very good references for problems, information, and benchmarks on their own product and certainly belong on the list. I've personally been able to learn a great deal

Re: [Beowulf] purse strings

1) The people (or person) that will evaluate the technical material, and recommend a decision 2) The person (or people) that will make the *final* decision 3) The person that will sign the check. Whom you address, how, and with what material is well beyond the scope of this, or any, email lis

Re: [Beowulf] purse strings

On Wed, Jul 25, 2007 at 02:58:12PM +0100, andrew holway wrote: > Hi, > > If a large organisation is thinking about purchasing a HPC machine who > would make the final decision. Who would you be pointing your > marketing towards? There are three types of people involved in this process in such an

[Beowulf] purse strings

Hi, If a large organisation is thinking about purchasing a HPC machine who would make the final decision. Who would you be pointing your marketing towards? Do you think this differs from academia to the commercial sector? Cheers Andy ___ Beowulf mail

Re: [Beowulf] IEEE 1588 (PTP) - a better cluster clock?

On Tue, 2007-07-24 at 16:51 -0600, Andrew Shewmaker wrote: > On 7/18/07, Patrick Ohly <[EMAIL PROTECTED]> wrote: > > * Have you heard of PTP and considered to use it in clusters? > > * How would applications or clusters benefit from a better > > cluster-wide clock? > > * W