coreboot

coreboot@coreboot.org

6 participants
39706 discussions

Re: Low cost cluster
by Jonathan Morton 25 Feb '03

25 Feb '03

> > 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 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.

2 1

Re: Low cost cluster
by Jonathan Morton 25 Feb '03

25 Feb '03

>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 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.

2 3

Re: Low cost cluster
by Alessio Sangalli 25 Feb '03

25 Feb '03

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

2 1

Getting a small cluster running - PC-Chips 810
by Jonathan Morton 25 Feb '03

25 Feb '03

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 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.

4 3

Status page
by Andrew Ip 24 Feb '03

24 Feb '03

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.

1 0

Re:Re: How to initialize USB controller in LinuxBios?
by riskin＠263.net 23 Feb '03

23 Feb '03

----- 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 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

3 3

gx1 ram size error
by zhu shi song 23 Feb '03

23 Feb '03

now i can boot my ec3 mainboard, but linuxbios can only find 32M ram, but I have 256M RAM. do you meet such problem? ec3 mainboard specification: processor: on-board NS GX1 233MHZ(fanless) chipset: NS CS5530A System Memory: one SDRAM DIMM BIOS: 2Mbit Flash BIOS solid state disk: support diskonchip 2000 --------------------------------- Do you Yahoo!? Yahoo! Tax Center - forms, calculators, tips, and more

3 2

2 questions.. 1. laptops and linuxbios, 2. bios-savior for laptops?
by Nicholas Mistry 21 Feb '03

21 Feb '03

ok, sorry for the dual post, but they are somewhat related. 1. I havent really put much thought to using linuxbios on a laptop, but a recent post has planted a bug in my brain to try and get it to work on some of the older laptops i have laying around. How many people have tried to get linux bios on their laptops, and how well does it work. this issue now prompts this quesion: 2. What type of "bios savior" options are there for laptops? or is that just a pipe dream at this point? -N

4 4

help
by xu xuning 21 Feb '03

21 Feb '03

Hello everyone: I have used Kernel-2.4.19_CWLINUX_4 from http://www.cwlinux.com/downloads/linuxbios-sdk/kernel/2.4.19/ but failed! my machine is winfast6300 MA Pro (doc md2800-d08 on i686), and through the console ( i use hypertrm.exe from windows on another machine),the information is following: ###################################################### LinuxBIOS-1.0.0 Mon Jan 20 15:34:48 EST 2003 starting... Copying LinuxBIOS to ram. LinuxBIOS-1.0.0 Mon Jan 20 15:34:48 EST 2003 booting... Finding PCI configuration type. PCI: Using configuration type 1 handle_superio start, s 0000ce80 nsuperio 1 s->super 0000e1f8 handle_superio Pass 0, check #0, s 0000ce80 s->super 0000e1f8 handle_superio: Pass 0, Superio SiS 950 handle_superio port 0x0, defaultport 0x2e handle_superio Using port 0x2e handle_superio Pass 0, done #0 handle_superio done Scanning PCI bus...PCI: PCI: 00:00.0 [1039/0630] PCI: 00:00.1 [1039/5513] PCI: 00:01.0 [1039/0008] PCI: 00:01.1 [1039/0900] PCI: 00:01.2 [1039/7001] PCI: 00:01.3 [1039/7001] PCI: 00:01.4 [1039/7018] PCI: 00:01.6 [1039/7013] PCI: 00:02.0 [1039/0001] PCI: pci_scan_bus for bus 1 PCI: 01:00.0 [1039/6300] PCI: pci_scan_bus returning with max=01 PCI: pci_scan_bus returning with max=01 done totalram:56M Initializing CPU #0 Updating microcode microcode_info: sig = 0x00000683 pf=0x00000010 rev = 0x00000000 Enabling cache... Setting fixed MTRRs(0-88 Setting fixed MTRRs(0-16) type:HB DONE fixed MTRRs Setting variable MTRR 0 , base: 0MB,range: 32MB,type HB Setting variable MTRR 1 , base: 32MB,range: 16MB, type HB Setting variable MTRR 2, base: 48MB, range: 8MB, type HB DONE variable MTRRs Clear out the extra MTRR's call intel_enable_fixed_mtrr() call intel_enable_var_mtrr() Leave setup_mtrrs done. Max cpuid index :2 Vendor ID :GenuineIntel Processor Type :0x00 Processor Family :0x06 Processor Model :0x08 Processor Mask Processor Stepping:0x03 Feature flags :0x0383fbff Cache/TLB descriptor values: 1 reads required Desc 0x01 : Instr TLB:4KB pages, 4-way set assoc,32 entries Desc 0x02 : Instr TLB:4MB pages,fully assoc,2 entries Desc 0x03 : Data TLB: 4KB pages,4-way set assoc, 64 entries Desc 0x00 : null Desc 0x00 : null Desc 0x00 : null Desc 0x00 : null Desc 0x00 : null Desc 0x00 : null Desc 0x00 : null Desc 0x00 : null Desc 0x41 : L2 Unified cache: 128K bytes, 4-way set assoc, 32 byte line size Desc 0x08 : Inst cache: 16K bytes,4-way set assoc,32 byte line size Desc 0x04 : Data TLB:4MB pages,4-way set assoc,8 entries Desc 0x0c : Data cache:16K bytes,2-way or 4-way or 4-way set assoc,32 byte line size MTRR check Fixed MTRRs: Enabled Variable MTRRs: Enabled Configuring L2 cache...CPU signature of 680 so no L2 cache configuration Enable Cache done. Disabling local apic...done CPU #0 Initialized Allocating PCI resources... ASSIGN RESOURCES, bus 0 PCI: 00:00.0 10 <- [0x8000000 - 0xfbffffff] mem PCI: 00:00.1 10 <- [0x00002c90 - 0x00002c93] io PCI: 00:00.1 14 <- [0x00002ca0 - 0x00002ca3] io PCI: 00:00.1 18 <- [0x00002cb0 - 0x00002cb3] io PCI: 00:00.1 1c <- [0x00002cc0 - 0x00002cc3] io PCI: 00:00.1 20 <- [0x00002c80 - 0x00002c83] io PCI: 00:00.1 10 <- [0x00002000 - 0x000020ff] io PCI: 00:01.1 14 <- [0xfc100000 - 0xfc100fff] mem PCI: 00:01.2 10 <- [0xfc101000 - 0xfc101fff] mem PCI: 00:01.3 10 <- [0xfc102000 - 0xfc102fff] mem PCI: 00:01.4 10 <- [0x00002400 - 0x000024ff] io PCI: 00:01.4 14 <- [0xfc103000 - 0 PCI: 00:01.6 10 <- [0x00002800 - 0x000028ff] io PCI: 00:01.6 14 <- [0x00002c00 - 0x00002c7f] io PCI: 00:02.0 1c <- [0x00001000 - 0x00001fff] bus 1 io PCI: 00:02.0 24 <- [0xf0000000 - 0xf7ffffff] bus 1 prefmem PCI: 00:02.0 20 <- [0xfc000000 - 0xfc0fffff] bus 1 mem ASSIGN RESOURCES, bus 1 PCI: 01:00.0 10 <- [0xf0000000 - 0xf7ffffff] prefmem PCI: 01:00.0 14 <- [0xfc000000 - 0xfc01ffff] mem PCI: 01:00.0 18 <- [0x00001000 - 0x0000107f] io Allocating VGA resource done. Enabling PCI resourcess...PCI: 00:00.0 cmd <- 0 PCI: 00:00.1 cmd <- 01 PCI: 00:01.0 cmd <- 0c PCI: 00:01.1 cmd <- 03 PCI: 00:01.2 cmd <- 02 PCI: 00:01.3 cmd <- 02 PCI: 00:01.4 cmd <- 03 PCI: 00:01.6 cmd <- 01 PCI: 00:02.0 cmd <- 27 PCI: 01:00.0 cmd <- 03 done. Initializing PCI devices... PCI devices initialized Enabled in SIS 503 regs 0x40 and 0x45 Now try to turn off shadow device for SiS 630 is 0x127ec Shadow memory disabled in SiS 630 handle_superio start, s 0000ce80 nsuperio 1 s->super 0000e1f8 handle_superio Pass 1, check #0, s 0000ce80 s->super 0000e1f8 handle_superio: Pass 1, Superio SiS 950 handle_superio port 0x2e, defaultport 0x2e handle_superio Using port 0x2e handle_superio Pass 1, done #0 handle_superio done Winfast 6300 (and similar)...Entering the initregs process Southbridge fixup done for SIS 503 handle_superio start, s 0000ce80 nsuperio 1 s->super 0000e1f8 handle_superio Pass 2, check #0, s 0000ce80 s->super 0000e1f8 handle_superio: Pass 2, Superio SiS 950 handle_superio port 0x2e, defaultport 0x2e handle_superio Using port 0x2e Call finishup handle_superio Pass 2, done #0 handle_superio done Checking IRQ routing tables.../opt/cwlinux/freebios/src/arch/i386/lib/pirq_routing.c: 23: check_pirq_routiing_table() - irq_routing_table located at : 0x0000a94 done. Copying IRQ routing tables to 0xf0000...done. Wrote linuxbios table at : 00000500 - 0000067c checksum 7c69 Jumping to linuxbiosmain()... Welcome to start32, the open sourced starter. This space will eventually hold more diagnostic information. Jamuary 2000 , James Hendricks, Dale Webster,and Ron Version 0.1 init_bytes Gunzip setup gunzip_setup output data is 0x00100000 Gunzipping boot code 42:fill_inbuf() - ram buffer:-0x0001afe4 done memcpy_from_doc_mil 52:fill_inbuf() - nvram:0x00010000 block_count:0 inbuf[0] is 0x1f flush 0x00100000 count 0x00008000 flush 0x00108000 count 0x00008000 flush 0x00110000 count 0x00008000 flush 0x00118000 count 0x00008000 done memcpy_from_doc_mil 52:fill_inbuf() - nvram:0x00020000 block_count:1 inbuf[0] is 0x3b flush 0x00120000 count 0x00008000 flush 0x00128000 co flush 0x00130000 count 0x00008000 done memcpy_from_doc_mil 52:fill_inbuf() - nvram:0x00030000 block_count:2 inbuf[0] is 0xf1 flush 0x00138000 count 0x00008000 flush 0x00140000 count 0x00008000 flush 0x00148000 count 0x00008000 flush 0x00150000 count 0x00008000 done memcpy_from_doc_mil 52:fill_inbuf() - nvram:0x00040000 block_count:3 inbuf[0] is 0xe2 flush 0x00158000 count 0x00008000 flush 0x00160000 count 0x00008000 flush 0x00168000 count 0x00008000 done memcpy_from_doc_mil 52:fill_inbuf() - nvram:0x0 inbuf[0] is 0x4d flush 0x00170000 count 0x00008000 flush 0x00178000 count 0x00008000 flush 0x00180000 count 0x00008000 flush 0x00188000 count 0x00008000 done memcpy_from_doc_mil 52:fill_inbuf() - nvram:0x00060000 block_count:5 inbuf[0] is 0x7e flush 0x00190000 count 0x00008000 flush 0x00198000 count 0x00008000 flush 0x001a0000 count 0x00008000 done memcpy_from_doc_mil 52:fill_inbuf() - nvram:0x00070000 block_count:6 inbuf[0] is 0x5d flush 0x001a8000 count 0x00008000 flush 0x001b0000 count 0x00008000 flush 0x001b8000 count 0x00008000 flush 0x001c0000 count 0x00008000 done memcpy_from_doc_mil 52:fill_inbuf() - nvram:0x00080000 block_count:7 inbuf[0] is 0x2d flush 0x001c8000 count 0x00008000 flush 0x001d0000 count 0x00008000 flush 0x001d8000 count 0x00008000 flush 0x001e0000 count 0x00008000 done memcpy_from_doc_mil 52:fill_inbuf() - nvram:0x00090000 block_count:8 inbuf[0] is 0x6b flush 0x001e8000 count 0x00008000 flush 0x001f0000 count 0x00008000 flush 0x001f8000 count 0x00008000 flush 0x00200000 count 0x00008000 flush 0x00208000 count 0x00008000 flush 0x00210000 count 0x00008000 done memcpy_from_doc_mil 52:fill_inbuf() - nvram:0x000a0000 block_count:9 inbuf[0] is 0x6e flush 0x00218000 count 0x00008000 flush 0x00220000 count 0x00008000 flush 0x00228000 count 0x00008000 flush 0x00230000 count 0x00008000 done memcpy_from_doc_mil 52:fill_inbuf() - nvram:0x000b0000 block_count:10 inbuf[0] is 0x32 flush 0x00238000 count 0x00008000 flush 0x00240000 count 0x00008000 flush 0x00248000 count 0x00008000 flush 0x00250000 count 0x00003de0 <1001> fini_bytes command line - [root=/dev/nftla console=ttyS0,115200 console=/dev/tty5 CONSOLE=/ dev/tty5 video=sisfb:640x480-8@60,font:VGA8x16] Jumping to boot code ################################################################## On my LinuxBIOS machine ,cann't get into the system and only a picture ! So can you tell me what's wrong with me and how to do next? thanks a lot! _________________________________________________________________ 免费下载 MSN Explorer: http://explorer.msn.com/lccn/

5 5

Information
by Xavier Pegenaute 21 Feb '03

21 Feb '03

Hi, i'm new in the list and i'd like know more things about put Kernel Linux in flashrom. 1) i'd like know a right map of a flashrom.At the moment i know that Bios code start at 0xf000h in 16 bits mode, in 0xc000h, there is VGA bios. 2) i want test your work with simulator like bochs, is there some document to try it ..? Yes, i well-read the information in your web. And all aditional docs will be a good thing. Thanks. Xavi.

2 1

Jump to page:

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

coreboot