Greetings,
I've just committed support for the 533MHz FSB version of Intel
Clearwater and the E7501 northbridge.
It's not well tested yet, but it does etherboot the kernel.
G'day,
sjames
--
-------------------------steven james, director of research, linux labs
... ........ ..... .... 230 peachtree st nw ste 701
the original linux labs atlanta.ga.us 30303
-since 1995 http://www.linuxlabs.com…
[View More] office 404.577.7747 fax 404.577.7743
-----------------------------------------------------------------------
[View Less]
> > This seems to imply I don't need a Disk-on-Chip unit, separate Flash
>> chip, or Flash programmer (unless I goof up, in which case the Flash
>> programmer can be used to restore the original BIOS). Is this
>> correct?
>
>That's right. DOC is not necessary, but would be a nice option to have.
>DOC not only reduces traffic, but also allows some fancy features, eg kexec.
I don't expect traffic or features to be a problem, as with OpenMOSIX
the slave …
[View More]would be running almost nothing autonomously.
> > FWIW, I'm planning to use Gentoo Linux, which should say something
>> about my proficiency level. IOW, I'm not averse to compiling things
>> and generally fiddling around, but the existence of a nearly
>> plug-and-play solution is encouraging (and likely to satisfy my
>> supervisor more easily).
>
>For fb support, you need sisfb_lite patch. If you don't need fb, stock
>kernel might work.
I probably don't need video at all, except to make sure the box boots
properly. Even for that, I could probably get away with serial
console, as I think the master will have two spare serial ports. :o)
I'll try your stock image first as a proof of concept, then build an
OpenMOSIX kernel and image using the least number of patches
necessary. Gentoo include an OpenMOSIX-patched kernel source tree,
which is nice of them, so I only need to worry about the LinuxBIOS
patches and hackery.
I'm guessing that if I use the vendor-supplied BIOS flash utility, I
don't need to muck around with MTD drivers, right? Looking at the
HOWTOs, that method seems to be extremely icky at the moment,
requiring kernel source edits. I don't mind getting a single floppy
drive, and moving it between slaves for this step.
--
--------------------------------------------------------------
from: Jonathan "Chromatix" Morton
mail: chromi(a)chromatix.demon.co.uk
website: http://www.chromatix.uklinux.net/
tagline: The key to knowledge is not to rely on people to teach you it.
[View Less]
dear all:
I have developed a linuxbios debug system succefully.I introduced gdb stub into my system. In my system ,developers can debug linuxbios at source code level. I setup the stub at the beginning of the begin of the function of hardwaremain, the first c function.Now the system can
excute the function of "step",'step into" "step out" ,"breakpoint"and so on. but the system has not been tested fully.
I wonder if my design is usefull to others.
by the way, I have several question.I will …
[View More]appreciate anyone's any idea!
my question are as follows:
1. As we know, traditonal BIOS not only do some initialization work, but also put some data about the hardware in somewhere.BIOS even offer some routine such as intx( I know that In linux souce file "setup.s",int10, int13and int15 are used),but linuxbios doesn't offer.
my question is: what is the mininal need of linux kernel's starting?
what data does It need in detail? where does the data need to be placed in detail?
what routine does linux kernel need for it's starting ?
how does linuxbios offer these data and routines?
2. the second question is about PCI. I found that in linuxbios, some PCI initialization work is done.as we know ,in linux kernel, the same work was be done.Some linuxbios PCI initialization code is even the same with linux kernel. my question is:
if the initialization in linuxbios is necessary?
3. my third question is about etherboot.
I get a ide-patch of etherboot, and I succefully boot my system via IDE .I have read the code for a long time,but still have no idea about it. I found it seems does not do the same as setup.s,the kernel loader of traditional linux.who can explain it to me?
I know there are some clever and experienced man in this site.I am very interested in this topic and admire all the man with good skills.I am looking forward to some help.
best regards!
yours HaimingWang
[View Less]
> > Thus I obtained an effective performance figure of 2.0 MFLOPS/MHz,
>> versus Athlon-XP figure of 0.5 (for both x87 and SSE) and Pentium-4
>> figure of 0.4 (for SSE). This is not hype - this is me reading the
>> documentation and doing the maths.
>
>This is an estimate, not a benchmark. It would be interesting what the
>Apple C compiler would make from your code. Your code seems to map to
>AltiVec very well, this is pretty rare.
My algorithm is made …
[View More]up of standard matrix operations, such as
multiplies and inversions. By transposing one of the matrices
beforehand, the individual operations are mostly sequential in terms
of memory access and uniform in terms of operation, which means it
does map very well to vector code.
It would probably also benefit from 3DNOW on the Athlon, but I
understand x86 assembly code is a lot hairier, and certainly my
compiler is unable to generate 3DNOW code by itself. As a result,
I've been unable to determine how much benefit I might see.
>Have G4 with equivalent MHz rating of Athlons been sold lately? It seems
>Athlons are clocked at twice the speed of G4s.
>What is the cost of a refurbished G4 system vs. a bunch of recent Athlons?
>I think the MFlops/$ benchmark is more interesting.
For comparable prices, I can get an 867MHz dual G4, or three single
Athlon-XPs at 1666MHz. Given that I can get four times the
performance per clock per CPU with the G4, it's a net win - as I
posted earlier, 3500 against 2500 MFLOPS. I'm still concerned about
the potential of having to use Windows software though, and that's
likely to sway the final decision.
Another worthwhile comparison might be in terms of MFLOPS per watt,
and that would be particularly relevant to larger clusters, where
power consumption and heat become significant environmental factors.
I understand a 1GHz G4+ is at around 15-20W maximum, which I'd assume
is while running Altivec code (and would go down with the vector
units not in use). By comparison, Athlons seem to average around
50W, depending on the particular core type and clock speed, and are
unable to shut down functional units that are not in use.
--
--------------------------------------------------------------
from: Jonathan "Chromatix" Morton
mail: chromi(a)chromatix.demon.co.uk
website: http://www.chromatix.uklinux.net/
tagline: The key to knowledge is not to rely on people to teach you it.
[View Less]
>I agree with your reasoning - cheap motherboards are readily available.
>
>For use at home, however, I looked at the mini-ITX motherboards.
>Less CPU performance of course, but low power and low cost.
I don't think there'll be power problems with such a small number
(initially just 2) of slaves, really. I'm constrained by a fairly
tight capital budget, designed to make 1 good PC, and I found I could
turn it into one respectable PC plus two cheap slaves.
If I really wanted to …
[View More]push the CPU-power envelope, I'd get a
refurbished PowerMac. I still might. The cluster would give me an
aggregate 2500 MFLOPS, while a previous-model Mac would give me 3500
for about the same price (both figures being what the compiler alone
can do). The only thing holding me back from that, is the
possibility of needing to run high-end physical-simulation software
that is probably only available for Windows. (Yes, I know about PC
emulation software, but it takes a large performance hit.)
BTW, this setup is officially to allow me to move my personal
machines off the desk and back home! They're currently an Athlon
1.2GHz and a Duron 800, plus a Pentium-MMX and a 486 that are used as
servers.
>I also have a PC-chips 810MLR, which we used for Linuxbios work last
>summer. I do hate to say it, but Linuxbios does work, but PCChips
>have a rather bad reputation.
Given the price, this isn't *so* surprising, but given the price it's
also easy to "forgive and replace". Because they are slaves, it's
easy to take one offline if it goes bad, and take time over getting
it replaced (probably under warranty). I hope LinuxBIOS is more
flexible than the rather anaemic status page suggests.
>If someone else is paying, from a grant, then think about getting a
>cluster with better hardware, say using Tyan or Supermicro motherboards.
I will have to see if any are available at a comparable price. I do
know that finding a case big enough to fit a Tiger into, while still
keeping the price down, could be a real pain. But then, SMP boards
tend not to be designed to be cheap. :)
That is a good point though - I should look at putting a pair of SMP
machines together, and see how the price compares. However, I think
the single SMP I priced was scraping the budget already - Athlon-MPs
are priced noticeably higher than their single equivalents, which
definitely hurts when compared to clusters of single-CPU slaves.
>A little more capital cost will result in much less grief later.
>And also think about the cases - do you have room for a pile of big
>ATX cases?
Let me see, right now the desk has one full-tower and one midi-tower
ATX, one AT, and one low-profile desktop, plus two monitors, at least
three keyboards, plus a laptop, all piled on and around it. I'm
planning to replace all that with one large medium-tower and two midi
ATXs, plus one monitor and one keyboard. I don't think space is a
problem. :-)
>Where is your department?
Lancaster, UK.
--
--------------------------------------------------------------
from: Jonathan "Chromatix" Morton
mail: chromi(a)chromatix.demon.co.uk
website: http://www.chromatix.uklinux.net/
tagline: The key to knowledge is not to rely on people to teach you it.
[View Less]
Jonathan Morton wrote:
> If I really wanted to push the CPU-power envelope, I'd get a refurbished
> PowerMac. I still might. The cluster would give me an aggregate 2500
> MFLOPS, while a previous-model Mac would give me 3500 for about the
is this supposed to be funny or do you really believe S. Job's jokes?
;)
bye!!!
ciao
as
--
How to build a lirc receiver
http://www.manoweb.com/alesan/lirc
Background: I want to get the most CPU power out of a limited budget,
for use with a research project involving signal processing. So far,
apart from buying a refurbished Mac, the best solution seems to be
building an OpenMOSIX cluster using Athlon-XPs.
I plan to use a "master" computer with a slightly faster CPU than the
slaves, and fitted with a full-function m/board and peripherals. The
master does not need to run LinuxBIOS, but it's existence means it
should be easy to build kernel …
[View More]variants to test, without risking loss
of machine functionality.
To keep the cost of each slave as low as possible, I want to
eliminate all storage hardware from them, including floppy drive.
This means booting Linux over NFS, and/or installing part of it in
the BIOS chip. Hence my interest in LinuxBIOS. If I will need
significant extra hardware to reliably install LinuxBIOS, I might
just as well boot from floppy.
So far, I've identified a PC-Chips 810 board from one of my suppliers:
http://www.aria.co.uk/ProductInfoComm.asp?ID=2050
which will be fitted with an Athlon-XP 2000+, some RAM, a case, a
PSU, and nothing else whatsoever. Total slave cost in this
configuration is under £160 including VAT.
Because this will be used in an academic Engineering department,
there will probably be a Flash and/or EEPROM programmer lying around
somewhere, that I can use rather than swapping BIOS chips.
Can anyone provide guidance on my chances of success, and how easy
this is likely to be?
--
--------------------------------------------------------------
from: Jonathan "Chromatix" Morton
mail: chromi(a)chromatix.demon.co.uk
website: http://www.chromatix.uklinux.net/
tagline: The key to knowledge is not to rely on people to teach you it.
[View Less]
Looks like status page is not being updated, eg 787 is not in the list.
-Andrew
--
Andrew Ip
Email: aip(a)cwlinux.com
Tel: (852) 2542 2046
Fax: (852) 2542 2036
Mobile: (852) 9201 9866
Cwlinux Limited
Unit 202B 2/F Lai Cheong Factory Building,
479-479A Castle Peak Road,
Lai Chi Kok, Kowloon,
Hong Kong.
Tel: (852)2542 2046
Fax: (852)2542 2036
For public pgp key, please obtain it from http://www.keyserver.net/en.
----- Original Message -----
From: "ollie lho" <ollie(a)sis.com.tw>
To: <riskin(a)263.net>
Cc: <aip(a)cwlinux.com>,<jerj(a)coplanar.net>,"LinuxBIOS Mailing List" <linuxbios(a)clustermatic.org>,"Ronald G Minnich" <rminnich(a)lanl.gov>
Sent: 2003-02-21 20:29:46
Subject: Re: How to initialize USB controller in LinuxBios?
>On Fri, 2003-02-21 at 10:26, riskin(a)263.net wrote:
>Do you really have any idea about USB controller ?? USB controller
>does not …
[View More]require IP address space, it uses MMIO address space which
>is called non-prefetchable memory in PCI spec. The controller does
>not need any special init stuff. I don't think USB is supported by
>2.2.x kernel neither. Why do you insist using 2.2.x kernel ?
>
>--
>ollie lho <ollie(a)sis.com.tw>
I don't want to use 2.2.x kernel,but for some reasons,
I must use the version.
I don't know about USB controller indeed.
But why do I see "I/O" addresses in standard bios environment
on other boxes(not sis630e chipset),instead of non-prefetchable memory?
In addition,there are patches supporting USB in 2.2.x kernel.I have
successfully tried it on standard bios environment with 2.2.x kernel.
Thanks,
riskin
==========================
263电子邮件-信赖邮自专业
[View Less]