NEC-LIST: Suggestions for fastest Intel architecture

From: Wan Juang Foo <fwj_at_email.domain.hidden>
Date: Fri, 12 Oct 2001 12:02:16 +0800

I belive the bottleneck is now with the (data rates of the) hard disk. If
you are refering to systems using ATA100 (viz-a-viz ATA66 or perhaps SCSIw
), the ATA100 is a small improvement over the ATA66. It takes ages to save
the contents from the RAM into the harddisk.

Just my 2 cents...

:-)

Tim Foo

----- Forwarded by Wan Juang Foo/ece/staff/npnet on 10/12/01 10:32 AM -----
                                                                                                                               
                    Ed Troy
                    <est0_at_lehigh. To: nec-list_at_gweep.ca
                    edu> cc: (bcc: Wan Juang Foo/ece/staff/npnet)
                    Sent by: Subject: NEC-LIST: Suggestions for fastest Intel architecture
                    nec-list-admi
                    n_at_gweep.ca
                                                                                                                               
                                                                                                                               
                    10/12/01
                    12:00 AM
                                                                                                                               
                                                                                                                               

I am looking to upgrade my computer facility. I currently run a dual
processor PIII running at 600 MHz with 784 megs of 100 MHz SDRAM. I hear
conflicting information on how fast the PIV is compared to some of the
PIII's, but the PIV can run at up to 2 GHz, whereas I don't see any PIII
chips that can run, reliably, at much more than 1.2 GHZ. Granted, 1.2 GHz
is faster than 600 MHz, but only twice as fast. Also, I don't see any
multiprocessor PIV's, at least not yet. I like using a multi-processor unit
because I usually have at least 7 or 8 programs running at one time, at
least one of which is often doing some intensive number crunching. Thus,
even though the number-cruncher does not run any faster than it would in a
single processor unit, I can use the machine for multiple tasks without
things slowing down. (I know the number cruncher would run faster if it was
multi-threaded, but I am not aware of many programs that are
multi-threaded, at least not yet.) It also seems like the PIV motherboards
use SDRAM, rather than RAMBUS, like some of the PIII machines, and I would
think RAMBUS would make a big difference in crunching numbers, especially
in EM type problems, where the required memory can often grow very quickly.
I would think the ideal would be a multi-processor PIV using RAMBUS at,
say, 1.8 GHz, but I don't believe that configuration exists. I've also
heard that the Athelon is a better chip for number crunching, but I am very
nervous about going to anything but Intel, since I have been burned so many
times by "compatible" computer things. It almost always seems that there is
an obscure "gothcha" somewhere, and I always seem to find it!

Also, does anyone know a site that performs and publishes hard ratings, in
terms of speed, of the various motherboard/processor combinations?

TIA,
Ed

--
The NEC-List mailing list <nec-list_at_gweep.ca>
http://www.gweep.ca/mailman/listinfo.cgi/nec-list
-- 
The NEC-List mailing list <nec-list_at_gweep.ca>
http://www.gweep.ca/mailman/listinfo.cgi/nec-list
Received on Fri Oct 12 2001 - 01:06:46 EDT

This archive was generated by hypermail 2.2.0 : Sat Oct 02 2010 - 00:10:41 EDT