The Ultimate Museum PC Update

A quick update on the Ultimate Museum PC (should it be called simply the UMPC?). The system is currently using a Supermicro P6DBE board with 2x Pentium 850MHz (Coppermine, 100MHz FSB) processors, 1GB RAM, a 120GB IDE disk, an ATAPI DVD-ROM drive, a SoundBlaster AWE32 PnP, a 3Com 100Mbps Ethernet controller. The graphics question has not been entirely settled yet; see below for more.

The system has been very stable so far. Perhaps unsurprisingly—nothing is overclocked and all components are on the higher end of the quality spectrum (if a decade-plus old). The disk was moved from the older BP6-based system and already contained DOS, OS/2, and Windows XP.

Getting Windows XP to run prompted some cursing, occasioned by Windows’ brain damaged “Plug and Play” implementation. Windows XP kept starting to boot but then simply resetting the system (perhaps a triple fault?), without any indication what might be going wrong. Safe mode etc. made no difference. OS/2 had no trouble booting up, which was an indication that the hardware was probably fine. The cause of the problem was perhaps obvious to anyone familiar with Windows XP’s quirks…

Windows had been installed with the ACPI HAL, but between BIOS upgrades, clearing the CMOS, and testing various BIOS setting, the ACPI support in the BIOS ended up being disabled. Incidentally, enabling ACPI in the P6DBE BIOS is anything but obvious: the power management setting must be “disabled”.

Once ACPI was re-enabled, Windows XP had no trouble booting. That prompted the installation of Sandra 2001 to verify that the system is performing as it should (it is), as well as the addition of 3DMark 2000 and 3DMark 2001SE to help find the right graphics card.

The Ultimate Museum Graphics Card

Finding the “best” graphics card isn’t entirely straightforward. The objective is to find something close to the best performing card with can operate in a 3.3V AGP 2x slot. For logistical reasons, the card should have both VGA and DVI output. PCI cards weren’t considered (perhaps a mistake?) on the assumption that the interface would be too limiting compared to AGP 2x; the maximum PCI bandwidth is 133 MB/s, while AGP 2x can deliver 533 MB/s, moreover an AGP device uses a separate bus where it doesn’t have to compete for bandwidth with other devices.

It’s worth noting that finding a graphics card with AGP 2x support is easy (at least on eBay and the like), but finding a fast graphics card with AGP 2x support is much harder. All newer graphics card typically only support AGP 8x and aren’t backwards compatible with old AGP motherboards due to different voltage.

The obvious contenders are nVIDIA and ATI. Matrox cards are relatively uninteresting due to their noticeably lower 3D performance, even though, say, a Matrox G450 is a very fine graphics card otherwise. “Other” brands like S3 weren’t even considered.

Around 2003, both nVIDIA and ATI stopped making their high-end graphics chips compatible with AGP 2x. ATI’s top of the line model and king of 3D performance back then was Radeon 9800 XT. Unfortunately the 9800 XT is based on the R360 GPU with no AGP 2x support. However, the older and only slightly slower Radeon 9800 Pro (R350) can still be used in the old 440BX boards.

Sapphire 9800 Pro Atlantis

A slight complication is that Radeon 9800 Pro existed in several variants, with the newer ones no longer being AGP 2x compatible. On pictures, this is easy to distinguish by checking whether the AGP connector has two notches (AGP 2x compatible) or just one (not AGP 2x compatible).

In theory, ATI’s fastest would be a Radeon 9800 Pro with 256MB RAM. In practice, these cards turned out to be very hard to find, while 9800 Pros with 128MB RAM are plentiful and only slightly slower. The lower amount of memory reportedly didn’t make noticeable difference for games of the era.

On the nVIDIA side, one obvious choice is the FX5950 Ultra. This was a direct competitor of the Radeon 9800 Pro/XT, with very similar performance levels but generally slightly slower than the 9800 XT. It is currently unclear whether any newer nVIDIA cards with AGP 2x supports might have been actually faster than the FX5950 Ultra.


Performance aside, there is also driver support to consider. Both the ATIs and the nVIDIAs are of course well supported under Windows, but with other operating systems things look a bit different. For OS/2, Radeons are clearly the better choice. For X11, nVIDIA might be better as long as a particular release is supported by nVIDIA’s own drivers. Since ATI was more open about providing programming documentation, the Radeons tend to be generally better supported under “alternative” operating systems.

A week or two after the initial research, the new old graphics cards arrived. There’s a nVIDIA FX5950 Ultra built by MSI (FX5950U-VTD256) and a Sapphire Radeon 9800 Pro Atlantis.

The nVIDIA has large heatsinks and fans on both sides of the card. The ATI is purely passively cooled with massive heatsinks. The passive cooling is both good and bad news—the card is absolutely quiet, but it’s also wider, and just barely fits on the P6DBE board (the processors get in the way a bit). On other motherboards it might not fit at all. Both cards require a separate power supply cable to be plugged in.

Here’s how the two cards do in benchmarks; for comparison, the figures for the older Radeon 9700 Pro are also listed. Again this is with a Supermicro P6DBE board, 2x Pentium III 850 MHz at 100MHz FSB, 1GB SDRAM.

  • MSI nVIDIA FX5950 Ultra (256MB)
    • 3DMark 2001 SE: 6511 3D marks
    • 3DMark 2000: 5173 3D marks
  • Sapphire ATI Radeon 9800 Pro (128MB)
      • 3DMark 2001SE: 6750 3D marks
      • 3DMark 2000: 5357 3D marks
  • ATI Radeon 9700 Pro (128MB)
    • 3DMark 2001SE: 6674 3D Marks
    • 3DMark 2000: 5351 3D marks

Despite the smaller video RAM size (128 MB vs. 256 MB), the Radeon 9800 Pro has a slight edge in 3DMark. That said, the difference is clearly not big enough to be a deciding factor. If anything, both cards are a bit overpowered for the Ultimate Museum PC. It’s also worth noting that the older Radeon 9700 Pro does almost as well as the 9800 Pro and still a tad better than the FX9590 Ultra, at least in the default benchmarks.

In a quick real-world test (the original Max Payne running at 1680×1050, 32bpp), both cards performed very well indeed with no discernible differences.

Possible Improvements

With 1GB SDRAM, the system is maxed out in terms of memory capacity. A 120GB IDE disk is also about the largest that can be used without hitting the 128MB BIOS limit. Either of the above mentioned graphics cards is probably fairly close to the fastest a 440BX-based board can handle.

The weak spot is the CPU. Without slockets or overclocking, the board could take a 1GHz processor. Unfortunately, the 100MHz FSB Coppermine Pentium IIIs are quite hard to find, especially in Slot 1 form factor. With the use of slockets, 1.1GHz processors could be used, but then there are two problems: the 100MHz FSB variants are again hard to find, and because only Socket 370 variants existed, slockets would be required. That brings another problem—finding slockets which support dual-CPU Pentium III operation. Many slockets support dual (Mendocino) Celerons, but not Pentium IIIs. Slockets are easy to find, but slockets known to support dual Pentium IIIs are apparently more or less extinct.

Another avenue yet to be explored is installing Windows 7 (32-bit, obviously) on the Ultimate Museum PC… just to see how painful it might be.

To be continued…

This entry was posted in PC hardware. Bookmark the permalink.

21 Responses to The Ultimate Museum PC Update

  1. Yuhong Bao says:

    The problem is that different HALs are used for ACPI and non-ACPI mode, and disabling ACPI will cause the ACPI HALs to stop working.

  2. Yuhong Bao says:

    Actually, this was already mentioned above, sorry.

  3. pixelgazer says:

    Thanks for the update. I was right in the middle of my research for the ‘best’ AGP 2x graphics card and was narrowing in on the ATI 9000 series and I hadn’t looked at NVIDIA yet. Again you saved me a bunch of time. Thanks!

    Now if only I could convince the ebay seller in Germany to sell and ship be the ASUS P2B-DS to me in Canada I’d be all set to follow in your foot steps.


  4. z180 says:

    the Geforce 6200 with NV44A is the last official AGP 2x card.
    The 6800 without bridge chip is compatible, too.

  5. ampharos says:

    My preferred vintage box has a Rage Pro in it. Little slow, and widescreen only works on Linux, but it’s a good card.

    Of course, dual P3s are always awesome.

  6. michaln says:

    Last official AGP 2x card, yes… but is it also the best? (I just don’t know.)

  7. pixelgazer says:

    The other thing we may need to consider is driver availability.

    The ATI 9800 Pro supports 98/Me, 2000 and XP. I don’t know if you need drivers for NT, OS/2 or the earlier Windows. I’m hoping not.

    The NVIDIA FX5950 Ultra seems to have drivers specific for Windows NT 4.0 SP6 and lists Windows 95 as supported with the 98/ME drivers. There also seems to be support for Linux, Solaris, and FreeBSD.


  8. I used to use an ATI Mach32 PCI card, as it was 8514/a compatible so things like old OS/2, Windows 3.0 could run in high rez.. Although 8514 modes were incompatible with flat screen stuff, it only worked well on CRTs.

  9. michaln says:

    Yes, I need drivers for OS/2… and the Radeon ones are much better than the nVIDIA ones. The reason is that nVIDIA did not give out any information to 3rd-party developers while ATI did.

    And no, I don’t need drivers for Windows 3.x or anything like that… if I did, I’d have to plug in some much older card (of which I have plenty).

  10. michaln says:

    I have one of those. I also have an ISA ATI 8514/Ultra, the kind without a VGA chip which needed an internal pass-through cable 🙂

    Haven’t played with one of those lately but those should be well supported under just about any old OS.

  11. Foofy Doof says:

    I have almost this same configuration, still running 24/7 as a server every day:
    P6DBE @ 103MHz bus
    2x Intel Pentium IIIE SECC2 cC0 – 800MHz & 850MHz (yes, mixing works!)
    1GB Micron PC100 ECC SDRAM (all week 42, 2001)
    Nvidia Geforce FX5200 128MB AGP 2x
    Realtek Gigabit Ethernet PCI

  12. Michal Necasek says:

    Very cool! Those boards and CPUs rock 🙂

  13. stergios78 says:

    The site and idea about the reviving of old hardware is just wonderful. I just fund it googling for old hardware.
    Please dont punish the old machine with win7. Windows XP SP3 is the last logical OS for the old UMPC (rockstable, but also slow). The PIII rocked the place in the past.

    My UMPC Specs: Asus P2B-B, 1GHz PIII Slot 1, 512MB RAM (2x256MB PC133), 80GB + 20GB HDDs (both with errors but still work), ATI Radeon 9000 AGP, Creative SB 16 ISA, NEC DVD RW DL 7170A, Realtek 8139 PCI LAN and Intel Pro/100, 5x USB 2.0 NEC PCI Controller, Seasonic 200W AT and LXLE Linux 7.0.4 (no PAE Kernel).

    In the past i used the machine with a SCSI SATA Controller and 2x 400GB drives (booting from the array, my first NAS).

    The only problems with the old machine:
    – For utilizing 768MB RAM, the voltage for 3 dimms is just to low. The only chance to max the ram: 2x256MB dual sided and 1x 128MB single sided = 640MB max.
    – Watch videos on youtube. There is no Hardware accelaration with old AGP grafics possible. The CPU must handle the whole work. Everything over 240p is not watchable. The effort of expensive and hot GPU dont worth the money for the upgrade. The Geforce 6200 AGP, Radeon 9200 LE are maybe the best silent solutions for the UMPC.

  14. Michal Necasek says:

    Actually AGP (and even PCI) graphics cards are quite capable of video acceleration, and most Pentium II class machines should be capable of DVD playback given adequate graphics hardware and drivers. But I don’t know exactly what youtube uses. If it’s some H.264 stuff then that’s probably not supported by old drivers/hardware.

  15. >Windows had been installed with the ACPI HAL, but between BIOS upgrades, clearing the CMOS, and testing various BIOS setting, the ACPI support in the BIOS ended up being disabled. Incidentally, enabling ACPI in the P6DBE BIOS is anything but obvious: the power management setting must be “disabled”.

    >The problem is that different HALs are used for ACPI and non-ACPI mode, and disabling ACPI will cause the ACPI HALs to stop working.

    Why doesn’t Windows try each HAL in turn when it boots and automatically select the one that matches the CMOS settings?

  16. (Sorry if this is a stupid question.)

  17. Michal Necasek says:

    You’d have to ask Microsoft 🙂 The reality is that up to NT 5.2 (Windows Sever 2003, Windows XP x64), Windows was one of the least plug-and-play operating systems, locking up, rebooting, or if you were lucky, producing a BSOD in response to anything from moving the installed OS to a different system to changing a BIOS setting. I think that’s just where NT’s age was really showing. With NT 6.0 (Vista) Microsoft made things a lot more dynamic and I believe reduced the number of HALs a lot.

  18. Yuhong Bao says:

    Even then 32-bit Windows Vista and 7 still had two HAL for PIC and APIC systems (because it took so long for laptops etc to support the APIC), and there is a “Detect HAL” option in msconfig.

  19. Michal Necasek says:

    I know many ThinkPads had the APIC disabled in hardware. I also suspect some “other” x86 CPU vendors (IDT, Transmeta, and such) didn’t have APICs at all. So yeah, laptops with no APIC were not uncommon in Vista times. The Core Duo changed that, but that was only in 2006.

  20. Yuhong Bao says:

    What changed it was the fixing of the APIC and C2/C3 errata (see spec updates) in ICH4M. Even then it of course took time, but it is mandatory for 64-bit Windows for example. And yea, this is especially fun when switching from a Pentium III to a VIA C3 CPU on a newer board that support the APIC. (I think later VIA C7 and Transmeta Efficeon CPUs did support the APIC BTW)

  21. Yuhong Bao says:

    The code that determines the HAL is in winload!OslpDetermineKernelHal in Windows Vista and 7 BTW.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.