[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Performance issues
From: |
Bill Northcott |
Subject: |
Performance issues |
Date: |
Fri, 31 Jan 2003 11:12:51 +1100 |
> >
> Motherboards like Tyan Trinity GC-SL (for Pentium 4, not even a Xeon)
> have PCI-X slots run 64 bits wide @ 133 Mhz.
They are not common. The standard Intel chip sets only support
32bit/33MHz PCI on P4 computers.
>With a SCSI RAID
> controller two U320 SCSI channels you could do 640 MB/sec and still
> have bandwidth to spare. Plain old bus-mastered PCI 2.2 can do 133
> MB/sec.
Data thoughput is not necessarily the main issue unless you are using very
large data files like video.
Latency is much more important in most applications. Which is why high
end Macs and powerful number crunchers use Level 3 cache memory and modern
RAID controllers boast Gigabytes of DRAM and very sophisticated caching
algoritms.
Pentium 4 PCs are primarily optimised for playing 3D games for the
sensible reason that the games players are the ones who buy the high end
machines. The best datapaths on the board are between the CPU and the
Video card, which is as it should be for such use. It is not usually the
way you want to optimise for general dataprocessing.
OTOH Apple optimise their machines for handling large files and use a CPU
with a vector processor which is extremely fast at performing tasks such
as video and audio compression and image processing effects. This is
obviously because Apple's power user want those attributes. Chacun a son
gout.
Bill Northcott
==================================
Swarm-Support is for discussion of the technical details of the day
to day usage of Swarm. For list administration needs (esp.
[un]subscribing), please send a message to <address@hidden>
with "help" in the body of the message.
- Swarm-gcj does work on Redhat 8.0, Paul E. Johnson, 2003/01/28
- Multithreading question, Darold Higa, 2003/01/28
- Re: Multithreading question, gepr, 2003/01/29
- RE: Multithreading question, Darold Higa, 2003/01/29
- RE: Multithreading question, gepr, 2003/01/29
- RE: Multithreading question, gepr, 2003/01/29
- RE: Multithreading question, Bill Northcott, 2003/01/29
- Re: Multithreading question, Marcus G. Daniels, 2003/01/30
- Performance issues,
Bill Northcott <=
- Re: Performance issues, Marcus G. Daniels, 2003/01/31
- Re: Performance issues, Steve Railsback, 2003/01/31
- Re: Performance issues, Marcus G. Daniels, 2003/01/31
Re: Multithreading question, Matteo Morini, 2003/01/29
RE: Multithreading question, Darold Higa, 2003/01/29
Re: Multithreading question, Marcus G. Daniels, 2003/01/29
Re: Multithreading question, Gregory R Madey, 2003/01/29