November 2003 - openSUSE AMD64 - openSUSE Mailing Lists

gnat Ada compiler
by Legg, David 13 Nov '03

13 Nov '03

We installed the 8.2 beta9 for AMD64 on our Dual Opteron box and tried compiling a very simple multi-task Ada program using gnatmake. When the program executed, it said: "failed run-time assertion : Tasking not implemented on this configuration" It would be useful for the RPM to configure the compiler and run-time libraries so that multi-task Ada programs running natively on AMD64 use the available SMP support in the kernel. As it is, programs with tasks in do not execute at all. Has this been fixed in the latest SuSE AMD64? Regards, David Legg

3 3

Getting Suse 9 for AMD64
by Doug Diehnelt 13 Nov '03

13 Nov '03

Anybody know where I can buy a copy of above other than the SUSE web store? I ordered a copy close to two weeks ago and the only response I can get back from SUSE is that they don't know when they are going to get anymore in. TIA Doug Diehnelt

3 2

RE: [suse-amd64] Getting Suse 9 for AMD64
by Miller, Daniel J. 12 Nov '03

12 Nov '03

Their list of resellers is here: http://www.suse.com/us/company/suse/retailers/index.html But none seem to have Professional Edition for AMD64, yet. You could try calling Amazon, Linux Central, etc. and see if any of them are getting boxed product soon (or already have but haven't updated their web sites). Dan -----Original Message----- From: Doug Diehnelt [mailto:dougdieh@nationwide.net] Sent: Wednesday, November 12, 2003 2:13 PM To: suse-amd64(a)suse.com Subject: [suse-amd64] Getting Suse 9 for AMD64 Anybody know where I can buy a copy of above other than the SUSE web store? I ordered a copy close to two weeks ago and the only response I can get back from SUSE is that they don't know when they are going to get anymore in. TIA Doug Diehnelt -- Check the List-Unsubscribe header to unsubscribe For additional commands, email: suse-amd64-help(a)suse.com

3 3

RE: [suse-amd64] Getting Suse 9 for AMD64
by marc.miller＠amd.com 12 Nov '03

12 Nov '03

Amazon.com, and it's available in the U.S. now (as of just under 2 weeks ago, I believe). -----Original Message----- From: Doug Diehnelt [mailto:dougdieh@nationwide.net] Sent: Wednesday, November 12, 2003 12:13 PM To: suse-amd64(a)suse.com Subject: [suse-amd64] Getting Suse 9 for AMD64 Anybody know where I can buy a copy of above other than the SUSE web store? I ordered a copy close to two weeks ago and the only response I can get back from SUSE is that they don't know when they are going to get anymore in. TIA Doug Diehnelt -- Check the List-Unsubscribe header to unsubscribe For additional commands, email: suse-amd64-help(a)suse.com

1 0

Suse 9.0 Pro AMD 64 - Athon64 vs. Opteron
by Holger Froening 12 Nov '03

12 Nov '03

Hello, is it possible to use the Suse 9.0 Pro AMD64 with Opterons or are there any problems? On the Suse website only the Athlon64 is mentioned, not the Opteron. Generally, what is the difference between the Pro and the SLES version? And last, does anybody know when the SLES9 is about to come? And very last, a freaky question: Does anybody uses the 64bit Suse together with NIS+? Should I expect problems? (I know, I always have to expect problems with NIS+ :-) ) Thanks a lot, Holger -- Holger Fröning (mailto:holger@ra.ti.uni-mannheim.de) University of Mannheim - Computer Architecture Group URL: http://ra.ti.uni-mannheim.de -------------------------------------------------------

3 2

Glitch in SLES8 United Linux SP3
by Stephen Williams 12 Nov '03

12 Nov '03

(OK, I'm all bug reports. Hate me yet?-) I installed UnitedLinux SP3, and found one little bit of a glitch. An NFS client (a RedHat 7.3 pentium) had trouble talking to the updated SLES8 Opteron system. The network chip (in an HDAMB system) is a: 02:06.0 Ethernet controller: Broadcom Corporation NetXtreme BCM5702 Gigabit Ethernet (rev 02) Writes by the i386 system to an NFS directory on the SLES8 system tended to get stuck, with the i386 system apparently sending tons of fragments that the SLES8 system was rejecting. (Unfortunately, I didn't save a tcpdump log.) Revering to k_smp-2.4.19-256 fixed the problem and that is where I set now. -- Steve Williams "The woods are lovely, dark and deep. steve at icarus.com But I have promises to keep, http://www.icarus.com and lines to code before I sleep, http://www.picturel.com And lines to code before I sleep."

2 2

RE: [suse-amd64] Disappointing 9.0 Pro AMD64 DVD install
by marc.miller＠amd.com 12 Nov '03

12 Nov '03

Pardon me if I'm stating the obvious, but when I opened my box of SUSE LINUX 9.0 64-bit, the DVD was packaged upside-down. Unless you turn it over as you insert it into the DVD drive, the "side 2" label will be up and your computer will be unable to boot the source code. Are you quite certain that you are booting from the correct side of the DVD (label "side 1" faced up)? -----Original Message----- From: David Carter [mailto:dcarter@opnet.com] Sent: Wednesday, November 12, 2003 8:02 AM To: Andreas Jaeger Cc: SUSE Linux; suse-amd64(a)suse.com Subject: Re: [suse-amd64] Disappointing 9.0 Pro AMD64 DVD install On Wed, 2003-11-12 at 10:46, Andreas Jaeger wrote: > David Carter <dcarter(a)opnet.com> writes: > > > System config info is attached. > > Thanks, I looked through it and couldn't find anything wrong - but at > this point you have a working system, so this might be the reason. > > > Short form: > > Tyan S2880 with onboard video > > That one works fine, we have tested it. > > > 1xIDE used as secondary drive, W*@#$%^s operating system on this one. > > 1xSATA used as boot drive, SIIG SATA controller as the onboard Promise > > controller has issues > > The onboard Promise does not work and we have not tested the SIIG > driver. Maybe some confusion because of these two? I'll check that > we do testing in similar environments for 9.1. > > Looking at Linux I noticed that the SATA drive is /dev/hde and the IDE > is /dev/hda. That different numbering might be a problem... This is probably going to be a common setup, as I'm using an external card for SATA, and on board I/O for regular IDE (including the DVD). The one combo I never tried was the DVD on /dev/hda. I don't think this should make a difference, but I'll try it over the next couple of days and see... > > > Samsung SM-352B/T806 CD-R/RW-DVD (that's with the latest firmware) > > Andreas -- --------------------------------- David Carter <mailto:dcarter@opnet.com> Senior Modeling Engineer OPNET Technologies, Inc. <http://www.opnet.com/> phone 240.497.3000 x2743 ==================================================== Register for OPNET's Online Technology Workshops http://www.opnet.com/TechWorkshops/ ====================================================

1 0

Re: [suse-amd64] Disappointing 9.0 Pro AMD64 DVD install
by Andreas Jaeger 12 Nov '03

12 Nov '03

David Carter <dcarter(a)opnet.com> writes: > System config info is attached. Thanks, I looked through it and couldn't find anything wrong - but at this point you have a working system, so this might be the reason. > Short form: > Tyan S2880 with onboard video That one works fine, we have tested it. > 1xIDE used as secondary drive, W*@#$%^s operating system on this one. > 1xSATA used as boot drive, SIIG SATA controller as the onboard Promise > controller has issues The onboard Promise does not work and we have not tested the SIIG driver. Maybe some confusion because of these two? I'll check that we do testing in similar environments for 9.1. Looking at Linux I noticed that the SATA drive is /dev/hde and the IDE is /dev/hda. That different numbering might be a problem... > Samsung SM-352B/T806 CD-R/RW-DVD (that's with the latest firmware) Andreas -- Andreas Jaeger, aj(a)suse.de, http://www.suse.de/~aj SuSE Linux AG, Deutschherrnstr. 15-19, 90429 Nürnberg, Germany GPG fingerprint = 93A3 365E CE47 B889 DF7F FED1 389A 563C C272 A126

2 1

Disappointing 9.0 Pro AMD64 DVD install
by David Carter 12 Nov '03

12 Nov '03

Well folks, I've been around Linux since the 0.98 kernel days and I've never had a more frustrating install. I've noticed from the lists that I'm not alone, with a lot of suggestions ranging from checking the media to castrating chickens under a full moon, but no one solution seems sufficient. I've tried manually specifying which drive was the cdrom, removing the CD drive from the same IDE chain, verifying the media, changing the drivers, and even doing an FTP install, all of which claimed that I had no packages available for installation. Finally I had to create a partition, copy from the DVD onto it (when will it be possible to install without installing windows first? I tried it from rescue mode and that didn't work either!), and installing from it. All in all I spent about 20 hours getting this loaded. My tech support case is still pending. And have I mentioned how useful the FAQ's are? If this OS is ever to catch on like it can and should, there need to be a couple of things happen: 1. When you ship only on DVD, the DVD install should work. Period. This wasn't a download.. I paid money for it. The lists suggest that this prolem has been around for a while, so the support should be better. 2. When you have as many problems with a DVD install as this list indicates, it's a good idea to condense these suggestions into an FAQ or a knowledge base entry. As of 4 this morning it wasn't. With the demise of consumer Red Hat, there's a window of opportunity open here... especially in the AMD64 arena. I plan on using the product for a while, but that will change if future experiences are like this one. And I still don't know what the problem actually was... Dave

2 1

SLES8 vs. Microtech USB Cameramate
by Stephen Williams 11 Nov '03

11 Nov '03

I have SLES8 with the latest (precompiled) kernel updates on an AMD64 (HDAMB) system. I also have a Microtech USB Cameramate compact flash/smart card reader. It appears that it does not work. It recognizes it as a usb-storage device, but that's it. It *appears* that the Microtech CompactFlash (DPCM) support is not enabled in the kernel, but I cannot find a kernel compile .config file to check. (Also, I'd *rather* stick with mainstread kernel binaries if I can. Don't really want to o off in a tangent and confuse the Yast2 updates.) -- Steve Williams "The woods are lovely, dark and deep. steve at icarus.com But I have promises to keep, http://www.icarus.com and lines to code before I sleep, http://www.picturel.com And lines to code before I sleep."

3 6

RE: [suse-amd64] Compatable hardware for SuSE 9.0 AMD64 version
by Emile van Mierlo 10 Nov '03

10 Nov '03

> I've installed the SuSE 9.0 2 days ago on 'Tyan Tiger K8W (S2875) dual > Opteron' with Adaptec SCSI, Plextor 708 DVD, NikkonScanner and so on. Does that Plextor PX-708A DVD/CD Recorder fully work as well? Emile

3 3

4-way opteron boards
by Mark Horton 10 Nov '03

10 Nov '03

I apologize since this is off topic but I've seen a few references to 4-way opteron boards on this mailing list. I've also seen some indications that AMD has a 4-way board called 'Quartet'. Does anyone know how to purchase this board? I have looked around the net extensively and I've seen fully built systems. For instance, Penguin Computing has a 4P system for less than $9,000 (US). Not a bad price but still a little bit high since I really only need the motherboard. Mark

3 2

SK8N S-ATA in 32-bit mode
by michael12＠mindspring.com 10 Nov '03

10 Nov '03

Hi all, After reading the digest of emails concerning the S-ATA drivers in 64-bit mode, I have some questions whose answers I probably overlooked: If I install the standard (32-bit) version of Suse on my SK8N, will it recognize the S-ATA during the install? If not, will I be able to install drivers after the install to recognize and use the S-ATA drive? Thanks in advance, Michael White

2 1

SuSE Linux AMD64 ver 9.
by Mark Morgan Adams 09 Nov '03

09 Nov '03

I have seen references to an amd64 version of SuSE Linux version 9 on DVD. Where can I get a copy? Thanks. Mark M. Adams. _________________________________________________________________ MSN Messenger with backgrounds, emoticons and more. http://www.msnmessenger-download.com/tracking/cdp_customize

2 1

Re: [suse-amd64] Installation of SUSE 9.0 AMD 64 Version on latest motherboards
by John McCorquodale 09 Nov '03

09 Nov '03

> Did some testing for you. Running dga kills the driver, no two ways > about it. It doesn't, however, kill the machine. I can ssh in from > another machine, kill off X and restart X without any difficulties at > all. All you see in the screen are lines as though the display is out of > sync. I tried a few different things, dropping the color depth to 16 > bit, turning off the nvidia logo and it didn't make any difference. Yeah, this is exactly the same behavior I see on ATI cards as well. It seems to be something about that board. I'm still working on something that'll dump out the northbridge, 8131 and 8151 configuration registers so we can see how BIOS is setting things up and figure out what's going on. Whatever is causing the dga hang is probably related, but it's worth noting that my framebuffer code doesn't hang, it just becomes very slow. I haven't debugged into the X server yet to track the dga hang; it doesn't seem like a path likely to lead to a solution to my actual problem (bad agp throughput). > BTW, how did you get the figures you quoted for the AGP throughput ? (It > may have been using dga - but not an option here, even trying dga > > dga_test and then monitoring the file from the remote machine showing > nothing at all - definitely hung X.) I wrote a kernel module that maps the framebuffer, sets up write combining and sets AGP fast writes, then does a tight-loop microbenchmark. It's still available at: http://viz.cacr.caltech.edu/dl/fbtest-0.1.tar.bz2 If you're interested enough to grab it and try it, let me know! I'd love to hear that somebody has replicated my experiment. It's also worth noting that if Andi is correct the 8151 is behind the 8131, which means it's sitting on an 8-bit hypertransport link. There's an 8151 erratum where it hangs running HT at 800 MHz, so all the HT links in the S2885 are clocked at 600 MHz (except the Opteron-to-Opteron one, which runs at 800). What this means is that the maximum theoretical b/w to the AGP chip is 600*2 = 1.2GB/s. Subtracting 20% for PCI address transmission overhead, that leaves 960 MB/s theoretical maximum one should ever see to the 8151 on the S2885. That's less than AGP 4x peak b/w, so best case the board should only be thought of as AGP 3.5x, not the 8x that the AGP connector happens to signal at. I'd be totally happy if I could get even close to that out of the board, but at the moment the max I've been able to get is 270 MB/s on a AGP v2 card and about 320 MB/s on an AGP v3 card. This is with 2GB RAM installed and the Tyan v1.01 BIOS. If you install 8GB of RAM, your AGP performance will drop to about 10 MB/s and write-combining will fail because of some broken way BIOS sets things up (which I haven't finished figuring out yet; many hangs lie down that road). Based on favorable response from Tyan, I think I can get the 8GB thing fixed once I figure out how it is and how it ought to be. I still don't understand how AGP performance can be the ~ 300MB/s that it is, and figuring that out is a separate question. Feel free to volunteer crazy ideas. I'm only just getting into this whole chip configuration register thing, so everybody should continue telling me things I ought to already know, 'cause I probably don't. :) -mcq

2 2

Panic on Opteron with 2.6 kernel and 8GB
by Peter Rundberg 08 Nov '03

08 Nov '03

Hi, When using the 2.6.0-test kernel (up to and including test9-bk11) on Opteron systems with 8GB memory I get a kernel panic during boot. I have tried this on a dual machine (Tyan Thunder K8W) and on a quad machine (AMD mainboard??), both with 8GB memory. Is this a known issue with the 2.6 kernels or is there some config option that has to be set to make it work. /peter

2 1

Re: [suse-amd64] Installation of SUSE 9.0 AMD 64 Version on latest motherboards
by John McCorquodale 07 Nov '03

07 Nov '03

> > Yes, you need the -139 kernel from > > ftp.suse.com/pub/people/aj/Kernel-AMD64/ > > to support AGP, > > to be more precise to support AGP on that Tyan board that has both > PCI-X and AGP. Near all other boards work with AGP with the default 9.0 > kernel. Although you'll probably want to run the board with < 3GB of RAM if you want to use AGP, at least in 1.01 of the BIOS. I'm seeing mediocre (~270MB/s) fast-writes (on any card) with 2GB of system RAM, and when I install 8GB of system RAM, that drops to a pathetic 30MB/s. I _should_ be seeing 2GB/s on AGP 8x. This fast-write performance probably translates into similar AGP DMA performance, 'tho I have yet to verify this. I am in slow (on my part) conversation with Tyan about this. I'm trying now to read out the 8151's config registers to see what state BIOS is leaving things in and maybe figure out what's up. Whenever a clue begins to form in my mind, I'll forward it along to the list. :) On a related topic: has anybody got DGA to work on this Tyan board, on any kernel and any graphics card? It always hangs the system for me. I'm interested in knowing what write b/w (the "b" key) people see when running /usr/X11R6/bin/dga on this board, especially on nVidia boards with this mystical 64-bit driver somebody mentioned earlier. Cheerio, -mcq

3 2

Installation of SUSE 9.0 AMD 64 Version on latest motherboards
by Graeme Docherty 06 Nov '03

06 Nov '03

Hi Can anyone who has tried, please tell me if any of the latest motherboards provide an 'out of the box' install of SUSE 9.0 AMD-64 without the need for kernel patching. Particularly looking at the MSI, Gigabye and Asus boards, running nVidia and VIA chipsets. I'm tending to lean towards the VIA chipset boards (K8T800), so any guidance would be appreciated. Regards Graeme This e-mail transmission is intended for the named addressee only. Its contents are private and confidential and should not be read, copied, disclosed or distributed to or by any other person. If you have received this transmission in error, please notify the sender immediately by e-mail or telephone (0141 585 6363), delete the contents of this transmission, destroy any copies made and no action should be taken which places reliance on its contents. Copyright Hanon Solutions Limited. All rights reserved. No part of this communication may be reproduced without the prior written permission of Hanon Solutions Limited.

5 6

packages needed for SLES 8 AMD64
by Jasjeet Sekhon 05 Nov '03

05 Nov '03

Hi, I'm running SLES 8 AMD64 and I would like to install some packages which are not available for SLES 8 AMD64 such as xemacs, latex and ispell. Would it be a bad idea to take such packages and their dependencies from SLES 8.2 beta or Professional 9 AMD64? I don't *need* these packages, certainly not at the price of making the system unstable. As an aside, am I the only one worried about the Novell purchase of SuSE? Cheers, Jas. ====================================== Jasjeet S. Sekhon Assistant Professor Harvard University Center for Basic Research in the Social Sciences jsekhon(a)fas.harvard.edu http://jsekhon.fas.harvard.edu/ Office: 617.496.2426 Fax: 617.496.5149 ======================================

3 2

known vncserver issues?
by Jasjeet Sekhon 05 Nov '03

05 Nov '03

Hi, Does anyone know of OS stability issues related to vncserver for SLES 8? My opteron server has crashes a couple of times. Each time I was using vncserver and connecting with vncviewer (from RH 9 systems using tight compression). I'm trying to figure out if this is a hardware or software problem. The OS is up-to-date and the hardware is: Polywell 2200A Dual Opteron ATX MB w/VGA,SATA,2LAN 2xAMD Opteron Processor Model 244 (64bit-1.8GHz) 8xDDR 333MHz 512M SDRAM PC2700 Memory ECC/Register 460W Power Supply for Dual CPU 2xWD 250GB Ultra-100 IDE 7200RPM 8MB HD 3Ware 7000-2 Port IDE RAID Controller In any case, a service person will check out the machine in 24 hours.... Cheers, Jas.

2 1

RE: [suse-amd64] IFC and SUSE 9.0
by Daniel Kidger 05 Nov '03

05 Nov '03

Martyn, > I have just insatlled intel fortran compiler on SUSE 9.0 > (with x86_64 opteron). When i try and link any fortran > program I get the error > > :/root/$ ifc test.f > program TEST > > 4 Lines Compiled > ld: skipping incompatible > /opt/intel/compiler70/ia32/lib/libintrins.a when searching > for -lintrins > ld: cannot find -lintrins This is a simple one - ifc will call upon the standard linker on the Opteron, which (naturally) defaults to making 64-bit binaries. Tell it to make 32bit binaries with "-Wl,-m elf_i386" and .. hey presto - it works. viz: --- cut here -- dan@quad0:~> cat hello.f print*,"Hello World" end dan@quad0:~> ifc hello.f -Wl,-m elf_i386 main program 3 Lines Compiled dan@quad0:~> file ./a.out ./a.out: ELF 32-bit LSB executable, Intel 80386, version 1 (SYSV), dynamically linked (uses shared libs), not stripped dan@quad0:~> ./a.out Hello World --- cut here -- Yours, Daniel. -------------------------------------------------------------- Dr. Dan Kidger, Quadrics Ltd. daniel.kidger(a)quadrics.com One Bridewell St., Bristol, BS1 2AA, UK 0117 915 5505 ----------------------- www.quadrics.com --------------------

1 0

IFC and SUSE 9.0
by Wheeler, Dr M.D. 05 Nov '03

05 Nov '03

I have just insatlled intel fortran compiler on SUSE 9.0 (with x86_64 opteron). When i try and link any fortran program I get the error :/root/$ ifc test.f program TEST 4 Lines Compiled ld: skipping incompatible /opt/intel/compiler70/ia32/lib/libintrins.a when searching for -lintrins ld: cannot find -lintrins Does anyone know what this means?? Thanks Martyn ---------------------------------------------- Dr. Martyn D. Wheeler Department of Chemistry University of Leicester University Road Leicester, LE1 7RH, UK. Tel (office): +44 (0)116 252 3985 Tel (lab): +44 (0)116 252 2115 Fax: +44 (0)116 252 3789 Email: martyn.wheeler(a)le.ac.uk http://www.le.ac.uk/chemistry/staff/mdw10.html

1 0

Re: [suse-amd64] Tyan S2885ANRF AGP framebuffer write slowness?
by Andi Kleen 05 Nov '03

05 Nov '03

On Wed, Nov 05, 2003 at 01:03:10AM -0800, John McCorquodale wrote: > > Most likely the aperture is there and you are messing with the IOMMU > > mappings. > > Yeah, I'm investigating that now. Figuring out how to read the aperture setup > out of the 8151. I've been talking to Tyan, they don't seem to have a solid > AGP configuration picture. Look in /var/log/boot.msg The kernel reads it and prints it early in boot. There are unfortunately multiple ways to store this (latest kernel should handle all this), it can be put into any northbridge and into the AGP bridge. Windows centric BIOS put it into the AGP bridge. > > > Does it go away when you boot with iommu=memaper=2 (this will make your > > system lose some memory) > > I will try this next time I'm in my office. It's worth noting that I've tried > most ATI video cards and the bad performance results are always the same, even > with AGP110 cards ('tho the 110 gets slightly faster due presumably to the > wider datapath; it's not a factor of two 'tho). > > I'll post a big writeup of this; I'm getting it together now but it'll spill > into tomorrow (getting sleepy). > > But while I've got you here, two questions: > > 1) It couldn't be that the AGP framebuffer is getting indirected through the > IOMMU when I map it through PCI-space or something like that could it? The frame buffer is normally not redirected through the AGP aperture. AGP aperture/IOMMU is to remap multiple mainboard ram areas to a single continuous bus area as seen from the AGP/PCI side. Frame buffer is a direct mmio area pointing to memory on the card. > > 2) Any clue why Tyan's BIOS would set the AGP aperture (and surrounding > address space to uncachable in the MTRR)? Setting the AGP aperture and the PCI hole (that is around it) to uncachable is standard and ok. Write combining MTRRs are set by the OS (the Xserver on Linux) > > It's also worth noting that changing video cards around changes the size of > the entry in the MTRR: sometimes it's 512MB, sometimes it's 1GB. The "missing > memory" varies with the size of this MTRR entry. That is because they have different sized PCI resources that are mapped there. > > > Overall it sounds more like hardware/BIOS issues than a Linux problem. I > > would recommend to contact Tyan. You could also try a different video card. > > I agree that the MTRR/missing memory is probably BIOS. But how is it possible Missing memory is a probably a minor BIOS problem or maybe unavoidable depending on your memory setup. The memory controller can map a single DIMM only in a single chunk and there has to be holeless memory < 4GB (Windows among others require this). The aperture and MMIO mappings also have to be <4GB. If the BIOS is unable to map the DIMMs completely around the hole containing aperture/MMIO you will lose memory. > to misconfigure hardware to the point that mere accesses to physical address > space get so much slower? It's a bus; it's just clocked. It seems to get Using cached access on a framebuffer/aperture is normally incredible slow. Frame buffer access is best using write combining. > Still in the dark really, but that's not reason not to send a verbose message > to the list! :) Just that you did not cc it to the list... Doing that now because the explanations may be useful to others. -Andi

1 0

Tyan S2885ANRF AGP framebuffer write slowness?
by John McCorquodale 05 Nov '03

05 Nov '03

Andreas and other interested folks, I just grabbed the 2.4.21-139 kernel, built it and installed it on my Tyan S2885ANRF. It now finds the 8151 AGP controller correctly, and seems to correctly identify both AGP110 (ATI X1) and older AGP v2 cards, go into 4x/8x modes fine and the like. However, if you take video-card-of-your-choice, map its framebuffer and set the AGP bridge for fast writes, the write bandwidth to the framebuffer is BAD. About a factor of 40 slower than it should be. A 1x card writes at about 18MB/s, a 4x card at 25 and an 8x card at 48MB/s. These numbers should be 256MB/s, 1GB/s and 2GB/s. Under no circumstances (1x, fast writes off) should the bandwidth be less than 256MB/s. I've tired this on lots of 760MPX machines and get the performance I expect, but I am at a loss as to what could possibly be causing this slowness. I notice that the Tyan board sets up the MTRR for the whole PCI physical address space to be uncachable: linux:~ # cat /proc/mtrr reg00: base=0xc0000000 (3072MB), size=1024MB: uncachable, count=1 reg01: base=0xbe000000 (3040MB), size= 32MB: uncachable, count=1 In previous framebuffer drivers, I have set the MTRR for the frame buffer to be write combining, which does have an effect on performance ('tho I've never known the effect to be a factor of 40!). I'd like to do the same thing on the Tyan board, but unsetting the c0000000-ffffffff uncacheable MTRR, or fragmenting it so that everything in that region EXCEPT the framebuffer is uncacheable both quickly lead to system crasshes (why? how could caching the framebuffer hang the system in text mode (corrupt screen contents, sure)? is this a race while the region is uncacheable?) It seems there's something strange going on. Could this be some kind of IOMMU interaction? The AGP aperture ends up at e0000000, which I cover with an uncacheable MTRR entry when I try the fragments, so I don't THINK I'm hurting anything. Any ideas why it could possibly be so slow or what I might do to get it back up to reasonable write speeds? Hard to do video when you can only get 2 frames/sec into the card's RAM. Thanks! -mcq

4 5