Subject: Re: inquiring
From: Ana Gusmao (angusmao@model.iag.usp.br)
Date: Tue Oct 20 1998 - 09:06:27 MDT
On Sun, 18 Oct 1998, Q Xu wrote:
> Hi Friends,
Hi Q Xu,
I also have some questions in the same directions as yours.
>
> We are going to run ccm3. But we have not got our computation tools.
>
> Now we are in the position of either buying a Sun Ultra 10 workstation
> (512 MB memory and 300 MHZ speed) or 4 pentium PCs (128 MB memory and 300
> MHZ speed for each).
If we buy PCs, we have got to install windows NT and
> some Parallel Virtual Machine (PVM) software to hook PCs to have it work as
> a single parallel computer.
>
> As we understand, 4 PCs should run 4 times faster than a single sun
> workstation because each PC processor has the same speed (300 MHZ) as the
> workstation and 4 PCs can compute at the same time. Is this concept right?
I am not sure but I think this kind of arregement would have a loss
of performance due to the connection between the PCs (a bottle neck
problem). My information is that this problem can cause until a
30 percent loss in performance.
> We do not have much idea about how to compare them. Should we buy PCs or a
> workstation?
>
Thas is also one of my doubts.
Solaris also runs in a PC plataform. So if is it true that
the Pentium II processors can work in parallel, we can have a
parallel machine using a Pentiun II processors working under
solaris. Is it possible ? I don't know ... but I guess would
be much easy to handle them a clusters of PCs.
| | Ana Maria Gusmao | |
| | | |
| | Universidade de Sao Paulo (USP) | |
| | Instituto Astronomico e Geofisico (IAG) | |
| | Dep. de Ciencias Atmosfericas (DCA) | |
| | E-Mail: angusmao@iag.usp.br | |
| | | |
| | DCA/IAG/USP - Rua do Matao 1226, | |
| | CEP 05508-900 SP/SP, Brasil | |
This archive was generated by hypermail 2b27 : Thu Jun 01 2000 - 09:07:07 MDT