Slashdot Mirror


NVIDIA's nForce Professional and Tyan's Words

CoffeeJunked writes "There's a lot of buzz about dual-core CPUs and with the release of the nForce Professional chipset from nVidia, there's a lot of buzz about the future of SMP machines as we know them. LinuxHardware.org has just published a couple of articles that get to the heart of the new chipset and what board manufacturers will be doing with them. The first article covers the chipsets and boards, while the second article is an interview with Tyan about what to expect from them this year. It's a good read all around."

138 comments

  1. The boards look great, except... by RebelWebmaster · · Score: 3, Insightful

    Where are the SATA connectors?!?!?! I find it amazing that the K8WE only has 2 and the K8SER 4. While we're on the topic, having at least 1 PCIe x1 slot would be nice. These high end server boards are being outclassed by nForce4 SLI motherboards. (And for the record, using more than 4 SATA ports is very doable)

    1. Re:The boards look great, except... by lachlan76 · · Score: 3, Insightful

      High end servers sure aren't gonna be using SATA...

    2. Re:The boards look great, except... by Anonymous Coward · · Score: 1, Informative

      Well the nForce Pro 2200 and 2050 each have 4 SATA ports, so a 4 chip solution could have 16 SATA connectors on the motherboard. Why a motherboard maker doesn't try and fit on the connectors I do not know.

    3. Re:The boards look great, except... by Benaiah · · Score: 0

      why not? SATA is already capable of faster speeds than scuzzie. + more convenient. THe asus k8n delux nforce motherboard has 8xSATA. I know my workmate just got 1. SWEET

    4. Re:The boards look great, except... by jred · · Score: 4, Insightful

      CPU load. SCSI puts much less of a load on your CPU than (s)ata does.

      SATA rocks, though.

      --

      jred
      I'm not a mechanic but I play one in my garage...
    5. Re:The boards look great, except... by LiquidRaptor · · Score: 1

      What world are you living in that sata drives are faster than scsi? The connector may be able to provide more throughput but it's kinda liking hooking a firehose up to a normal spigot instead of a garden hose. The drives just can't push the data through fast enough.

    6. Re:The boards look great, except... by Anonymous Coward · · Score: 3, Informative

      Sorry but 10K rpm SCSI drives (not to mention 15K) pound even Raptors extrememly hard in the performance arena. Look it up. No, here you go:

      http://techreport.com/reviews/2005q1/maxtor-diamon dmax10/index.x?pg=4

    7. Re:The boards look great, except... by Anonymous Coward · · Score: 1, Informative

      What fool modded this up?
      Mod parent down down down.
      It's not true in any way. SATA is not faster than SCSI in any benchmark. More convenient? How in the hell is SATA more convenient than SCSI? That's like saying your right sock is more convenient than your left sock...wtf? Then the poster goes on to mention that the "asus k8n delux nforce motherboard has 8xSATA." And that makes SATA a better choice than SCSI in what way? Oh because your "workmate just got 1" and it is and I quote "SWEET". WTF is happening to slashdot when drivel like this is getting modded up?

      I fear as the average age of slashdot users goes down so does the quality of posts. Slashdot is slowly turning into the forums at HardOCP.

    8. Re:The boards look great, except... by cg0def · · Score: 2, Informative

      If you really know anything about high end workstations and server design you would never ask why there are notmore than 4 sata connectors. When it comes to servers sata drives are used for storage of data that is not accessed often and scsi drives are used for data that needs to be easily available. Too bad serial scsi is not out yet but that will come too. Plus 4 sata connectors give you way over a terrabyte of storage and that would be enough for the kind of application that you are thinking about. After all this is not a storage array.

    9. Re:The boards look great, except... by lachlan76 · · Score: 1

      Because the best drives are SCSI.

    10. Re:The boards look great, except... by obeythefist · · Score: 1

      Know anyone selling 15K rpm SATA drives? I know a lot of companies selling 15K rpm SCSI drives. If you're serious about RAID performance, and you can afford the really high end gear, why settle for an onboard controller anyway, when you could be running a serious controller with onboard cache?

      --
      I am government man, come from the government. The government has sent me. -- G.I.R.
    11. Re:The boards look great, except... by dasunt · · Score: 3, Insightful

      CPU load. SCSI puts much less of a load on your CPU than (s)ata does.

      Depending on the task, the CPU for PATA/SATA isn't that bad.

      For fileservers, on a price/capacity ratio, SATA will kick SCSI's ass to the curb and back. While SCSI is faster, and, on average, more reliable, SATA is often 'good enough'.

      Or imagine a webserver with huge amounts of memory. For performance, SATA and SCSI will be roughly equal, since most files will be cached in the memory.

      What about a DNS server: Again, the performance of the system should be dependent on memory, not the hard drive speeds.

      Don't forget firewalls. SATA is fast enough for log files, and the CPU shouldn't be a bottleneck unless your firewall rules are extremely complex.

      I wouldn't use SATA in a database server or in any other application with a lot of random disk reads/writes, but it has its uses, even in servers.

    12. Re:The boards look great, except... by Negatyfus · · Score: 1

      Except that SATA is pretty new and currently not very reliable. We get lots of problems with SATA in servers here, such as time-outs and such. Weird stuff and for my new desktop machine, I'm gonna go with IDE.

    13. Re:The boards look great, except... by gl4ss · · Score: 1

      You'd use dedicated proper raid boards with them maybe, instead of soft-raid sillyness?

      --
      world was created 5 seconds before this post as it is.
    14. Re:The boards look great, except... by Homology · · Score: 2, Informative
      For fileservers, on a price/capacity ratio, SATA will kick SCSI's ass to the curb and back. While SCSI is faster, and, on average, more reliable, SATA is often 'good enough'.

      If you buy a SATA drive you can expect the same relability as a IDE drive. An exception is WD Raptor that has a MTBF of 1.2 million hours full duty cycle, like SCSI drives.

    15. Re:The boards look great, except... by ckaminski · · Score: 2, Interesting

      Why the fuck, oh why, oh why, cannot these damn onboard RAID or Hardware RAID chipsets provide a standard IDE emulation interface so that volume one, consisting of a RAID 1 mirror of physical disk 1 and 2 appear as one logical disk 1 to the Operating system? WHY!?!?!?!?!

      I'm set to dump my Promise SuperTrak for an IDE enclosure with built in mirroring that presents the disk as a single IDE mirror. I'm sick of being unable to do kernel upgrades because my vendors driver is randomly incompatible with certain versions...

      I could understand needing a driver for management capabilities, but the Linux driver for the Supertrak doesn't implement those...

      http://arcoide.com/miva/merchant.mv?Screen=PROD& St ore_Code=ADPS&Product_Code=EzRAID&Category_Code=EZ _FAMILY

    16. Re:The boards look great, except... by NeuralAbyss · · Score: 3, Informative

      I've got a SuperTrak (the 12 drive version) running on a Linux 2.4 server running Debian. Make sure you enable the non-Windows OS option on the card (changes it to I2O operation), and turn on I2O options in kernel config. Works like a charm.. appears as one device.

    17. Re:The boards look great, except... by Anonymous Coward · · Score: 0

      Serial SCSI. Don't they call that "fibre channel"? Or maybe "firewire"? (Yes, both of those are based on the SCSI command set, although the transport layer differs.)

    18. Re:The boards look great, except... by gl4ss · · Score: 1

      wouldn't that depend on what the pata, sata or scsci is connected to?

      if you're using an expensive, PROPER, raid card why there'd be difference in cpu usage in sata vs. pata vs. scsi?

      --
      world was created 5 seconds before this post as it is.
    19. Re:The boards look great, except... by Anonymous Coward · · Score: 0

      I fear as the average age of slashdot users goes down so does the quality of posts. Slashdot is slowly turning into the forums at HardOCP.

      Troll, troll, troll.

      Bitter much? It's not such a good thing for you to be throwing around insults about the younger population on Slashdot. I agree that such stuff shouldn't be modded up, but I'm sure there are just as many "old geezers" being lazy and not researching before modding as young people. This is a general problem of laziness instead of age.

      I don't have time to sit around and talk, I have a lab to teach. I, for one, thing you are in serious need of an attitude adjustment before insulting an entire (large) sector of any population.

    20. Re:The boards look great, except... by xouumalperxe · · Score: 1

      yeah, the asus sli motherboard has 8 SATA ports... anyway, the x16 slots are compatible with the x1 ones, so no hard done there. In fact you can turn a x16 card into a x1 one by taping the extrac connectors. Saw it done somewhere on grapics cards, to assess exactly how much bandwidth they ACTUALLY used from those x16 lanes :)

    21. Re:The boards look great, except... by Anonymous Coward · · Score: 0

      what SATA gives you any way? current HDs are not that fast so they have to use SATA yet. when they are that fast, your current MB will be useless any way.

    22. Re:The boards look great, except... by bombshelter13 · · Score: 1

      Could someone give me a link to something that uses a PCI-E x1 slot? So far all the PCI-E cards I've seen have been graphics cards using the x16 slot.

    23. Re:The boards look great, except... by cowbutt · · Score: 1
      It's not true in any way. SATA is not faster than SCSI in any benchmark.

      How about 4 spindles of [S]ATA, RAID1[0]'ed vs. a single SCSI spindle of the same size as the array for the same price?

      I've not benchmarked it, but I would expect the [S]ATA to be faster AND more reliable, given WD or Seagate discs.

    24. Re:The boards look great, except... by Jason+Hood · · Score: 2, Informative

      CPU load. SCSI puts much less of a load on your CPU than (s)ata does.

      That completely depends on the controller used. SATA unlike PATA, can easily reach or exceed specs for SCSI in terms of speeds/latency/load.

      --
      Are you intolerant of intolerant people?
    25. Re:The boards look great, except... by TheGavster · · Score: 1

      Did you see the PCI-X slots? That's where you put your high-end SCSI RAID controller, and get much faster access than you'll ever see over the SATA ports.

      --
      "Because Science" is one step from "Because old book". Try "Because of my experiment testing my falsifiable assertion".
    26. Re:The boards look great, except... by warrendodge · · Score: 1
      Timeout errors with PATA/SATA drives in server and RAID configurations are covered in this Western Digital document.

      http://westerndigital.com/en/library/sata/2579-001 098.pdf

      Essentially, regular desktop drives will try for a very long time to correct read errors. RAID controllers will only wait about 8 seconds for a read. If the drive takes longer than that, the controller will treat it as failed and remove it from service. So WD offers a series of drives that will only try to correct errors for a short time and then return an error to the controller if they can't fix it in time.

    27. Re:The boards look great, except... by codeguy007 · · Score: 1

      The onboard SATA isn't as good as the add in Cards and most people with be add these cards if they can.

      The reason there are more SATA ports is because you may want to support 4 drives but not want to require the use of your PCI-X slot because you need it for a Myrinet card or other additional add in cards. K8WE gives you a lot more options.

  2. Talk about useless. by Anonymous Coward · · Score: 5, Insightful

    So, they are designing a chipset for servers, which will run linux or bsd, but they refuse to provide docs or hardware to linux and bsd developers, meaning their shit is always poorly supported. Hooray.

    1. Re:Talk about useless. by Anonymous Coward · · Score: 1, Insightful

      What makes you think that nVidia is desinging these boards to run anything but Windows? They're still afraid that someone is going to copy their hardware through their driver source. Ridiculous.

    2. Re:Talk about useless. by Anonymous Coward · · Score: 5, Interesting

      I'm a bit concerned about the nforce4, from what i read already, there are 3 models, a "normal" nforce4, a "ultra" nforce4, and a "sli" nforce4. But altough you can't use SLI on the non-sli models, there are ways to enable SLI, on at least the ultra model ( http://www.anandtech.com/printarticle.aspx?i=2322/ ).
      To quote the article, "Just as quickly, we learned that nVidia was not happy with this "SLI hack" and they changed their drivers quickly so that "semi-SLI would not work with current and later Forceware drivers." It appears that the later Forceware drivers check the chipset ID and if the driver sees "Ultra", then SLI is not enabled. MSI decided to kill the "semi-SLI" board because it would be a nightmare supporting a board that would only run with older nVidia SLI drivers."

      So, how will this be (un)supported by the opensource community? Is nvidia doing to chipsets what they did to graphic cards? Everyone remembers how they locked out rgb overlays and unified front+back buffers from the geforce4 cards, altough the chips had the funcionality built-in, the drivers would disable these features, and save them for the more expensive quadro cards (there were some quick fixes for this, for windows, mainly rivatuner and softquadro4).
      Does this means that now they're going to lock-out funcionality available on the chipset to maximize profit? I can't imagine how (linux) kernel developers will support a chipset which relies on closed drivers to enable or disable a specific funcionality, and judging by nvidia's attitude in the graphic cards department (which has a point, up to a certain extent nevertheless), i can't imagine nvidia releasing the specs for opensource drivers for this chipset, therefore loosing the income from the sli model, which would become redundant.
      Do we now have to taint the kernel with chipset drivers? If so, i'm out of it, this is certainly a chipset to avoid.

    3. Re:Talk about useless. by DarkMantle · · Score: 1

      However, since they release drivers (that work great) for linux (dunno bout bsd, I don't use it) how is this a problem. Ok, since the NIC is part of the chipset I need to have the drivers before I can get network, no big deal, use a seperate machine and a blank cd.

      Where's the problem?

      --
      DarkMantle I been bored, so I started a blog.
    4. Re:Talk about useless. by Illissius · · Score: 1

      Just want to point out that they're not using the drivers to disable features on the lower chipsets by default. If you read the article you link to, you have to do a hardware mod to enable the functionality first; they're then disabling support for these hacked chipsets in their drivers. So it sucks, but it's not like they're relying on cheap software hacks to differentiate their products; rather using them to prevent people from removing their cheap hardware hacks.

      --
      Work is punishment for failing to procrastinate effectively.
  3. The New Tyan Boards using the Nvidia Chipset by rchatterjee · · Score: 5, Informative
    1. Re:The New Tyan Boards using the Nvidia Chipset by Kris_J · · Score: 1

      Whoooooo! Looking forward to putting together an SLI monster with the K8WE.

  4. Free Drivers by gustgr · · Score: 4, Interesting

    Finally, NVIDIA's SLI has been a hot topic here because, as of yet, we haven't seen Linux drivers that support this hot new feature. When we talked to NVIDIA about this we were finally given a time-line which stated that it may be a couple of months still.

    If the drivers were free software someone skilled enough would hack the missing features. Isn't about time to nVidia change its mind and release the sources?

    1. Re:Free Drivers by Jah-Wren+Ryel · · Score: 3, Interesting

      If the drivers were free software someone skilled enough would hack the missing features. Isn't about time to nVidia change its mind and release the sources?

      Tell that to David Kirk nvidia's chief scientist whose, "sense is that developers on those platforms are quite happy with our efforts" as a justification for not going open source. Plus some totally bizarro bullshit about "hackers tak[ing] bad advantage of raw hardware interfaces."

      It is telling that he did not pull out the old, tried and true "competition sensitive" bullshit that so many hardware vendors have been hiding behind since day one.

      --
      When information is power, privacy is freedom.
    2. Re:Free Drivers by Ziviyr · · Score: 1

      How about the old "we have licensed tech in there that disallows us from opensourcing it" line.

      That one made a bit of sense.

      --

      Someone set us up the bomb, so shine we are!
    3. Re:Free Drivers by bit01 · · Score: 1

      How about the old "we have licensed tech in there that disallows us from opensourcing it" line.

      That one made a bit of sense.

      It does if they explicitly state what the "licensed" tech is that's blocking the opensourcing. If they don't then it's just BS.

      ---

      Are you a creator or a consumer?

    4. Re:Free Drivers by Anonymous Coward · · Score: 0

      Anybody else think "disallows" is a bit uncromulent?

      Why not just say "forbids" (or "prevents")?

      I don't even understand what disallowing actually is. (Come on, stop to think about it. What do you do when you "disallow"?)

    5. Re:Free Drivers by Vanders · · Score: 2, Insightful

      That makes a little bit of sense for 3D graphics drivers, maybe. It doesn't make the slightest bit of sense for a Gigabit ethernet controller, a SATA controller or even an audio DSP. These sorts of components are being churned out by different manufacturers across the world, and most of them have freely available documentation.

      Even more bizare, nVidia contributed Gigabit patches to the forcedeth driver. Yet they not only continue to produce their own closed driver, they still refuse to release specs. It boggles the mind.

    6. Re:Free Drivers by Anonymous Coward · · Score: 0

      Why should they open source there drivers? If they don't want to and you don't like it, don't buy their stuff!

    7. Re:Free Drivers by ipjohnson · · Score: 1

      So if the documentation for these chips is free as you said why are you complaining?

    8. Re:Free Drivers by Anonymous Coward · · Score: 0

      You wern't paying attention. Documentation for other chips is usually freely available. Documentation of nVidia chips is not. If you want to support nVidia devices properly and you're not Linux, not having documentation or Open drivers is a major pain in the ass.

    9. Re:Free Drivers by alien+at+large · · Score: 1
      Plus some totally bizarro bullshit about "hackers tak[ing] bad advantage of raw hardware interfaces."

      Actually it's not all that bizarro. DMA allows hardware devices to access memory without the cpu knowing about it. So a malicious user that can get a graphic card (or a nic or any other DMA device) to manipulate memory through the DMA mechanism could circumvent mechanisms like pax and other security mechanisms to some degree. And with GPU's getting more accessible to programmers that risk is increasing. Imho mr. Kirk has a point.

    10. Re:Free Drivers by Jah-Wren+Ryel · · Score: 1

      I knew exactly what he was referring too and it is still a dumbass point for a variety of reasons:

      a) Relies on security through obscurity, so if a dedicated hacker reverse engineers a vulnerability in the nvidia proprietary driver, it will never get fixed unless the vulnerability is used in a virus or something widespread enough to get noticed by nvidia versus getting the many eyeballs effect and possibly nipping it in the bud before an exploit is ever created.

      b) As you point out, applicable to, in lesser and greater degrees, ALL programmable i/o devices.

      c) Correctly implemented drivers are suppossed to prevent exactly that kind of exploit. 10 to 1, nvidia's linux engineers are nowhere near as akamai as Linus's lieutenants and the chance of an incorrectly implemented driver getting past nvidia QA is higher than getting it past Linus and his chain of command.

      --
      When information is power, privacy is freedom.
  5. The K8WE has 4 by attemptedgoalie · · Score: 3, Informative

    The picture doesn't label the other two. They're down by the SCSI controller pointing forward instead of up. They're also on the RAID with the ones in the picture.

    Trust me.

    (I have one of these boards at my desk.)

    --
    My mom says I'm cool.
  6. Nvidia Taking a Stand by FiberOpPraise · · Score: 2, Insightful

    Just a few years ago, Nvidia was practically unheard of in the motherboard market. They slowly crept in with the relase of nforce/nforce2/nforce3/nforce4 chipsets. Having an integrated video card and chipset is somewhat advantageous despite the driver troubles that linux users face. Nvidia is slowly gaining market share over motherboard chipsets, I see this as a good thing. My NForce systems are working great and so far everything has been smooth. If Nvidia keeps up with the great work and frequent updates of their chipset, I will be a satisfied customer. How do you feel about Nvidia presence in the motherboard market?

    1. Re:Nvidia Taking a Stand by Hack+Jandy · · Score: 1

      However, you forget that Nvidia hasn't actually integrated a GPU in their core logic since the nforce2 chipset. ATI, Intel, SIS and sometimes VIA release IGP solutions for every chipset revision. Perhaps Nvidia found that IGP sales hurt their discrete solutions?

    2. Re:Nvidia Taking a Stand by MojoStan · · Score: 2, Insightful
      Just a few years ago, Nvidia was practically unheard of in the motherboard market... How do you feel about Nvidia presence in the motherboard market?

      Before NVIDIA entered the chipset market with nForce, I didn't seriously consider buying AMD Athlon CPUs because I thought the previous "consumer" chipsets (VIA, SiS, ALi) sucked ass. Maybe I'm being a little harsh about the pre-nForce Athlon "cheapsets." However, I felt a lot more comfortable using the relatively reliable and robust Intel chipsets, even though I thought the Athlon was the better CPU.

      To me, the chipset is just as important as the CPU when choosing a computer platform. NVIDIA gives the AMD platform a lot more credibility.

      --
      TO START
      PRESS ANY KEY

      Where's the 'ANY' key? I see Esk, Kitarl, and Pig-Up...

    3. Re:Nvidia Taking a Stand by MojoStan · · Score: 3, Interesting
      However, you forget that Nvidia hasn't actually integrated a GPU in their core logic since the nforce2 chipset... Perhaps Nvidia found that IGP sales hurt their discrete solutions?

      Perhaps. But I think another possibility is that the nForce3 chipset was not meant for "budget/mainstream" users, but for "enthusiasts." As we all know, enthusiasts don't want integrated graphics that share memory with the system.

      The nForce4 chipset, on the other hand, does look like it's aimed at budget/mainstream users as well as enthusiasts. But with PCI Express and TurboCache, NVIDIA might have a cheap solution that's better than integrated graphics.

      PCI Express x16 has more bandwidth than AGP (4 GB/s upstream and downstream) and allows writes directly from the GPU to system RAM. This allows a non-integrated graphics card to share memory with the system without the huge performance hit that AGP would have caused.

      Instead of integrated graphics, maybe NVIDIA is planning to "bundle" their cheap TurboCache cards with nForce4 motherboards. That seems cool to me.

      --
      TO START
      PRESS ANY KEY

      Where's the 'ANY' key? I see Esk, Kitarl, and Pig-Up...

    4. Re:Nvidia Taking a Stand by Anonymous Coward · · Score: 1, Interesting

      Waaaay agreed! I had previously only run Pentiums because the AMD systems I built for other people (pre-nForce) were always flakey (although I have had good luck with VIA/Pentium platforms. Go figure.).

      Then I built and AMD box with a nForce chipset.

      And it rocked!

      And I built another one. And another one. And another one. Some weirdnesses with the nForce chipset aside, the boxes were as stable as any of my Pentium boxes (maybe even more stable). That's including Intel chipsets in Intel boxes.

      So now I'm waiting for the K8WE to be released so I can build my own AMD box.

      The chipset is way overlooked, and is just as much a part of an uber box as anything else.

    5. Re:Nvidia Taking a Stand by Anonymous Coward · · Score: 0

      To me, the chipset is just as important as the CPU when choosing a computer platform. NVIDIA gives the AMD platform a lot more credibility.

      Alas, ATI has entered the venue too. The credibility is going down again. :*(

      (This from a "proud" Radeon 9600 owner, with latest drivers and games full of incomphrehensible bugs and glitches, sorely missing the easy life with the previous Geforce 2. Look forward to my business again, Nvidia.)

    6. Re:Nvidia Taking a Stand by Hack+Jandy · · Score: 1

      Instead of integrated graphics, maybe NVIDIA is planning to "bundle" their cheap TurboCache cards with nForce4 motherboards.

      I concur. It doesn't sound cool to be but it does sound like progress.

    7. Re:Nvidia Taking a Stand by CactusInvasion · · Score: 1

      You would find it ironical that the integrated video on the Tyan server board is an Ati Rage, then.

  7. brains on the side by Doc+Ruby · · Score: 1

    Can I config a dual-P4 machine to run X clients on one CPU, and my X server on the other CPU, with the nVidia machine displaying the server output? That's the kind of Linux multiprocessing I like.

    --

    --
    make install -not war

    1. Re:brains on the side by mvdw · · Score: 2, Informative

      You don't have to. It all happens transparently: I have a dual-CPU athlon MP setup at home, and I can confirm that it happens just like that. Each process starts on the processor with the least loading.

    2. Re:brains on the side by XMichael · · Score: 2, Informative

      Quote: Can I config a dual-P4 machine to run X clients on one CPU, and my X server on the other CPU, with the nVidia machine displaying the server output? That's the kind of Linux multiprocessing I like.

      Of course you can, this isn't a NVidia, Intel or AMD thing, its a Linux thing. The operating system is responsible for deciding which processor to assign the work too.

    3. Re:brains on the side by pipingguy · · Score: 1


      Me too. I'm not moving to dual Opterons until Windows and more applications are 64 bit/multi-threaded. Overall, I've found dual CPUs to be a bit overrated but I don't use the machine as a server, just for lower level CAD as the most stressful use. Dual CPUs won't help while digitizing video (I.E., you won't be able to do something else while it happens).

    4. Re:brains on the side by Anonymous Coward · · Score: 0

      Of course not. That would be stupid.

      The operating system runs processes at the front of the queue on whichever processor is available.

      To tie X clients to one CPU and the X server to the other -- besides being impossible, short of hacking the kernel -- would only hurt performance.

    5. Re:brains on the side by ckaminski · · Score: 1

      That, IMHO, is untrue. Remembering that most modern OSes, like Windows NT from 3.1 to Windows 20003 and recent incarnations of the Linux kernel are fully preemptible, ANY user will benefit from the addition of a second CPU or Dual Core processor.

      I can state emphatically that with the most demanding graphics application I have ever used, Pro/ENGINEER (CAD/CAM), I was successfully able to run a full regression suite while building the software tools that build Pro/ENGINEER.

      You will definitely be able to digitize video and do other work at the same time. You may not approach the full potential, but in general your two CPUs will nearly approach 180% with mainstream tasks.

    6. Re:brains on the side by rasz · · Score: 0

      >dual-P4

      there are NO dual-P4 machines, P4 is not SMP

    7. Re:brains on the side by ckaminski · · Score: 3, Informative

      Many operating systems have a concept of processor affinity, whereby due to caching issues wish to ensure that thread/process migration from CPUs does not occur. WindowsNT once had a problem whereby you could ensure that after every context switch your thread had migrated to a new processor, invalidating it's cached data and killing performance. Some applications require this sort of thing, and if you want to ensure that this migration behavior occurs as little as possible, then you can set affinity flags that clue the OS into this fact. It will then attempt to migrate your thread only as a last resort.

      So, Windows can do this, even though it's only a guideline, as opposed to a true enforcement. I understand Linux has this capability, however I'm not positive.

    8. Re:brains on the side by ttys00 · · Score: 1

      Linux does indeed have the capability.

    9. Re:brains on the side by puetzk · · Score: 1

      linux is capable of forcing assignments, but it's also aware of cache effects as a factor when making its decision about scheduling. So you generally don't need to override it, it tries to avoid thrashing a process from CPU-to-CPU anyway.

      --
      The Matrix is going down for reboot now! Stopping reality: OK. The system is halted.
    10. Re:brains on the side by Doc+Ruby · · Score: 1

      As the other, helpful replies to your post demonstrate, *you* are stupid. It's possible, it's practical, and Linux kernel programmers have spent time making it work. Shut up and let actual people with their brains up front post the answers, Anonymous rectocerebral Coward.

      --

      --
      make install -not war

    11. Re:brains on the side by Doc+Ruby · · Score: 1

      Wrong. Trivially proven so, to boot.

      --

      --
      make install -not war

    12. Re:brains on the side by rasz · · Score: 0

      proven what ? that there are P4 Xeons ? WOW what a newsflash ... :/
      There are SMP Xeons, but P4 can be at max SMT

    13. Re:brains on the side by Doc+Ruby · · Score: 1

      Proven:

      1> There are SMP P4 computers:

      (From just one of over 143,000 results):
      "This time PC manufacturers are upset because Pentium 4 Xeons in a four way symmetric multiprocessing (SMP) configuration are thoroughly thrashed by a chip that Intel wants to consign to the microprocessor gulag."

      P4 SMP has performance problems, but that's exactly why kernel support for scheduling partitions is important. Many of the results I posted are complaints about performance, but they all prove that P4 SMP exists.

      2: Your doesn't know when you're beat.

      --

      --
      make install -not war

    14. Re:brains on the side by rasz · · Score: 0

      >Pentium 4 Xeons

      I see that discussion with you is pointles, so go to intel.com and find this P4 SMP, not P4 Xeon but P4 SMP.

    15. Re:brains on the side by Doc+Ruby · · Score: 1

      Of course it's pointless, if you somehow believe that a P4 Xeon is not a P4.

      --

      --
      make install -not war

    16. Re:brains on the side by pipingguy · · Score: 1


      I've only ever used the machine with AutoCAD (overkill, really) but I might be installing PDS and Design Review.

      My experience with digitizing old VHS tape of my son two years ago was that I couldn't touch anything while the process was happening. Perhaps everything wasn't configured properly and now that I think back the problem might have been with converting the avi files to another format.

  8. Anandtech article was quite interesting... by Bob-o-Matic! · · Score: 4, Informative

    Normal view: http://www.anandtech.com/cpuchipsets/showdoc.aspx? i=2327

    All in one page/"print" version: http://www.anandtech.com/printarticle.aspx?i=2327

    Lots of intersting possibilities. Seems to me that given a motivated/visionary motherboard maker, the only real limits are based on the form factor. Is there a super-ATX out there that would allow for say 8 PCI-e slots, 16+ hard drives, and all the rest of the goodies, all in one case?

    Some will ask if there really is a need for this. Anandtech's Derek Wilson points out that having all the onboard disk controllers could add up to substantial savings-- apparantly expansion card controllers are quite pricey.

    Now, if only those Opteron 8XX processors didn't cost $8XX... (or thereabouts... you get the idea!)

    1. Re:Anandtech article was quite interesting... by natron+2.0 · · Score: 1

      HEY BOB!

  9. Free Drivers-"Trusting" computing. by Anonymous Coward · · Score: 0

    "That one made a bit of sense."

    Only if you think "trust me" should be the future model OSS should work under.

    1. Re:Free Drivers-"Trusting" computing. by Anonymous Coward · · Score: 1, Insightful

      "Only if you think "trust me" should be the future model OSS should work under."

      it's worked so far...

  10. Talk about useless-The Inner Limits. by Anonymous Coward · · Score: 0

    Makes you want to run out and buy a video card in celebration.

    So which is it people? Principle or practical?*

    *And remember there's no "do over". Choose wisely.

  11. I'd at least respect honesty. by Anonymous Coward · · Score: 4, Insightful

    "We use our drivers to cheat on benchmarks, and if we released info for people to write a driver, it would show our hardware's not as good as we pretend."

  12. Not really. by Anonymous Coward · · Score: 0

    RHELWS3u4 works very, very nicely on the K8WE with an Nvidia FX3400.

    Maybe some of the vendors haven't publically released their drivers...

    Be patient...

  13. Nvidia Taking a Stand-Over OSS Graves. by Anonymous Coward · · Score: 1

    "How do you feel about Nvidia presence in the motherboard market?"

    I feel a disturbance in the force as suddenly a thousand motherboard makers are snuffed out.*

    *Jokes aside. the problem isn't with the chipset, but the attitude towards specs and other information that developers need that's being propogated. Today it's Nvidia. Next could be VIA. Then Intel after them, and so on down the line were if you want OSS to run on that hardware. It will not be on our terms, but theirs (DRM, Trusted computing).

  14. nvidia and Linux drivers by jgarzik · · Score: 4, Informative
    As a for-what-it's-worth from a Linux driver author...

    nvidia SATA status and other Linux SATA info.

    nvidia wrote the SATA driver that's current in the Linux kernel, and has generally been helpful in addressing problems that arise in it.

    Although the ethernet driver ("forcedeth") was indeed reverse-engineered, nvidia eventually lent their support behind the effort: they contributed gigabit ethernet support to the driver.

    The video stuff is still closed, of course.

    Jeff
    1. Re:nvidia and Linux drivers by Anonymous Coward · · Score: 0

      Does your sata driver support smart commands yet?

    2. Re:nvidia and Linux drivers by jgarzik · · Score: 1
      Yes, it's supported SMART commands via a patch for months now.

      We're just waiting on SCSI to finalize its "ATA passthru" drafts before the patch can go to mainline.

  15. nvidia and Linux drivers-Reversing the flow. by Anonymous Coward · · Score: 0

    "Although the ethernet driver ("forcedeth") was indeed reverse-engineered, nvidia eventually lent their support behind the effort: they contributed gigabit ethernet support to the driver."

    Maybe. But the point is that they shouldn't have needed reverse-engineering. Video I can understand, but not an ethernet driver.

    1. Re:nvidia and Linux drivers-Reversing the flow. by Anonymous Coward · · Score: 0

      "Maybe. But the point is that they shouldn't have needed reverse-engineering. Video I can understand, but not an ethernet driver."

      nvidia was probably just covering their ass. I'm sure they want the drivers out there, but they probably some component they licensed from someone who might sue if they opened it directly.

  16. This says it all for upgrades on that board. by BrookHarty · · Score: 2, Interesting

    Dual core support on Tyan's Opteron platforms, is a feature we are very much looking forward to providing to all of our current and future customers. Unfortunately while its not possible at this time to directly comment on whether support will be implemented on the S2885, S2895 or other models from Tyan, customers should be pleased to know we are working to ensure compatibility on platforms going forward.

    Dual cores are such a major upgrade, why buy any SMP motherboard when 2 months it cant support the next generation SMP cpus...

    1. Re:This says it all for upgrades on that board. by PhrostyMcByte · · Score: 1

      Think I read somewhere that dual core CPUs from AMD are supposed to fit in the same slots

    2. Re:This says it all for upgrades on that board. by drsmithy · · Score: 1

      You'd be a brave man to invest in first-generation dual-core hardware...

    3. Re:This says it all for upgrades on that board. by Anonymous Coward · · Score: 0

      They said they dont know if their BIOS will be able to support it. Scary.

    4. Re:This says it all for upgrades on that board. by Namarrgon · · Score: 1
      Sounds like they're just covering their arses to me.

      I see no particular reason why they couldn't add dualcore support to their BIOS - the hardware is pin-compatible, their customers are certainly going to want it, and AMD would probably help them ahead of anyone to get it right.

      But, as always, buy hardware for only what it does today, and you'll never be disappointed tomorrow.

      --
      Why would anyone engrave "Elbereth"?
  17. As a Dell laptop user... by setagllib · · Score: 2, Interesting

    ...who previously had an nVidia Go 5200FX (or whatever order those tokens are meant to come in), and now a Radeon 9000, I can only say I'd rather have out-of-tree drivers that work perfectly for a good card than half-baked drivers for an average card (where good/bad are measured in usability, not necessarily performance).

    The Radeon under Linux (and I assume anywhere with an XOrg server) is a huge pain. Doesn't manually switch output displays with Fn+F8 like it should, and xv [the direct output mode, not the graphics program] only goes to the lappy panel, never to an external monitor. It might be a really trivial change in the driver source, but in the mean time it's an uneccessary frustration.

    --
    Sam ty sig.
    1. Re:As a Dell laptop user... by whovian · · Score: 1

      Maybe it's a matter of your X config or the hardware itself. I use a compaq notebook with a Radeon 9000/9200 under xorg and radeonfb. The external monitor port just happened to be on when I first tried it. In fact, hitting Fn+F4 doesn't even turn off the signal. (btw, there's also the 'flgrx' driver, but i haven't tried it.)

      --
      To-do List: Receive telemarketing call during a tornado warning. Check.
  18. Enough throughput for HD editing? by Thaidog · · Score: 1

    If you check out the Tezro from SGI you'll notice it has 4 pci-x controller chips to get the throughput high enough for reatime editing of multiple streams of HD 4.4.4. I wounder if any of these configurations can handle that kind of thoughput?

    --

    ||| I still can't believe Parkay's not butter.

  19. My Favorite MB Manufacturer by niko9 · · Score: 0

    In a world full of cheap rush to production "enthusiast" motherboards packed to the gills with all kinds of generic no frills crap (i.e. cheap onboard sound, useless on board NIC's and 2 or even three cheap software RAID controllers), it's nice to know that my favorite motherboards manufacture is still producing quality rock-solid no-nonsense motherboards.

    I've been a big fan since the pentium II days. Nary a reboot or even a hickup with these motherboards.

    The only thing that concerns me is the Nvidia chipset and Linux compatibility.

    Rock on Tyan!

    1. Re:My Favorite MB Manufacturer by Nik13 · · Score: 2, Insightful

      I don't know what you're talking about. Bundling nice and important features (increasing value) is a good thing. Cheap onboard sound? Most these motherboards have 8 channel digital sound. A comparable creative (no thanks!) sound card cost almost as much as the motherboard alone. Useless onboard NIC? I don't know which ones you've tried, but I have yet to see one give me problems, from crappy ECS K7S5A motherboards to nice GBit lan on Asus boards. They just work. Cheap software RAID? If you want hardware RAID, go buy a "real" controller. It'll cost you a LOT more than the whole board does. For a lot of people, it's VERY valueable. No more promise-brand cards to buy that cost more than the mobo to do that. What's next? "I don't want no crappy onboard USB2? No Firewire?" I'm looking at a Gigabyte GA-K8NXP-SLI and the ASUS A8N-SLI Deluxe right now. They may be a bit more expensive, but they have nice things on them like 16x SATA RAID, SATA2, 2x GB LAN, 802.11g, IEE1394B, 8 channel digital audio (depending on which one you like better). Might look like crap to you, but it sure looks like a lot of nice stuff to me. And no, I'm no "enthusiast", overclocker, nor gamer. It's just a nice board with everything one needs or just about. No need to buy a bunch of 100$ PCI cards to have a complete system.

      --
      ///<sig />
    2. Re:My Favorite MB Manufacturer by karakal · · Score: 1

      You never did listen to the "output" of onboard-Sound, didn't you? I still like my PCI-Sound cards for the better sound (and yes, they cost almost as much as the mobo) but if you only use on better speakers, you will hear the difference. and i saw no 16x SATA on these two boards you mentioned. And what should I do with 2GB NICs connected via PCI-Bus??? This IS crap!

    3. Re:My Favorite MB Manufacturer by Nik13 · · Score: 1

      Who said ANALOG onboard sound? (anybody uses that still? all spdif here). spdif wise, unless you count jitter, there is no difference - actually, the nforce chipsets have the lead on this point. Speakers are a non issue. About the 16x SATA, I guess I shouldn't have trusted what the store I checked mentionned ("ASUS A8N-SLI Deluxe Dual DDR 2x PCI-E, 16x SATA RAID, 2x GB Lan"), but it still has quite a few connections. Which is always nice to have... 2 GB Nics? It is useful. We have servers with redundant NICs - and GB Nics. Why not have best of both worlds bundled? At home, you could use it to bridge your network - saving to buy a expensive GB switch for a few PCs. It can't hurt, can't be worse than a single 100BT. There's plenty of just as expensive barebone, featureless motherboards if you want, asking you to keep overpriced PCI card businesses alive.

      --
      ///<sig />
    4. Re:My Favorite MB Manufacturer by karakal · · Score: 1

      I too have many of my servers with GB-NICs. but only PCI-X (Hooray on my Macs *g*). Tell me how you want to use SPDIF on multi-channel-output. As far as I know, no Chipset can do realtime-encoding to DTS or Dolby-Digital.

    5. Re:My Favorite MB Manufacturer by Nik13 · · Score: 1

      PCI-E GB Nics aren't cheap, and we're really just starting to have boards that have the slots. The normal PCI ones I have (at home) still work very well, and it definately beats having 100BT instead. I'm all for taking expensive hardware and making it a commodity on most motherboards, like they already added USB2 and Firewire. As for the spdif output, you're wrong. You can either pass AC3 or DTS audio from such as source to it's output, or play normal stereo sources as 2.0 - even on 20$ cards. The added strenght of the nforce chipsets over the expensive PCI cards here is that in fact, it actually CAN do realtime Dolby Digital encoding @ 640kbps (I have yet to see a DVD use over 448) if you want it to. Also, don't forget spdif can pass Linear PCM, not just DD/AC3 and DTS (and then passthru the AC3/DTS when playing it instead).

      --
      ///<sig />
    6. Re:My Favorite MB Manufacturer by karakal · · Score: 0, Troll

      I know all that. But you can't encode DTS-streams with such hardware, when you (for example) have multiple audio-streams and arranging them in a acoustical surround-environment. And who wants Dolby Digital?? and even this is not well supported. So, the only possibility is an analog 5.1 input on your soundsystem and an analog 5.1 output on your soundcard. And in that onboard-Sound sucks. And another factor: I bought a SATA Hardware-Raid from Adaptec new from my Dealer for just EUR 49. So what the hack bother with some crappy onboard adapters? My clients (and myself too) are working in a high-availability environment, so I can't just switch motherboards, because the RAID-Adapter is broken. (maybe there is no chance to get another motherboard, so all data is lost, and restoring costs time) And so I don't need motherboard crammed full with lots off stuff noone is ever going to use... I want light motherboards with better performance (and lesser features) for an acceptable price.

    7. Re:My Favorite MB Manufacturer by Nik13 · · Score: 1

      There is no real need to encode to anything, I don't even know why you're onto that. Linear PCM works for normal sound, and they pass real AC3/DTS sound just fine. And all is very well supported. Never had a single glitch (unlike say, with my 350$ SB Live 5.1 Platinum, which BSOD'ed any KT133 chipset PC, had broken AC3 passthru basically until XP was out). No way I'd use analog sound, there's no need for it whatsoever. As for RAID, if you're really into a high availability scenario, then you should be using a real server. You're missing the intended market completely. And as far as the broken adapter, no motherboards available and all, that's FUD. 99%+ chances are - one of your drives will fail - not the board. And since you're into a high availability setup, you should be using a real server with hardware raid 0+5/5+0, and not even be looking at these. People buy these and throw a couple 200GB SATA drives in raid0 for cheap. Works very well for home use or non mission critical stuff, and the price is quite right too. Some motherboards hardly over 49$ have SATA RAID. There's no point of trying to save 5$ off the board and not including it when a lot of people will miss the feature. Again, there are other boards on the market without that if you don't want them, but there is definately people who use all these features, especially when it's all bundled at a decent price and good support.

      --
      ///<sig />
    8. Re:My Favorite MB Manufacturer by Anonymous Coward · · Score: 0

      And you are missing my point too ;-)
      We are using Asus-Boards, but try to get such boards, with as less features as available. Then we throw in some SATA-RAID Adapter (that's what costs EUR 49) and have some very reliable setup. (for very less money, instead buying some high-avail. solution from Tandem or Bull)
      And the problem with not compatible RAID-Setup: We had it with many customers more than once, that not the drives in the array were broken, but the motherboard, in which they were used. If there is , e.g., a Highpoint RAID Adapter onboard, go on and try to get the Array working with a SIL-based Adapter.
      The Audiofeatures I was mentioning, wasn't some plain playback of some DVD stuff or something like that. I am too into mixing and remastering of audio. And there is no (affordable) solution available, which encodes my own surround-mixed audio to DTS or Dolby Digital and transfers the sound over the SPDIF port of the soundcard.

    9. Re:My Favorite MB Manufacturer by Anonymous Coward · · Score: 0

      A cheap motherboard with a addon RAID controller is hardly cheaper and it takes up a slot. As for the audio, if you really were into that, perhaps you wouldn't be clueless, and you'd know it works great as Linear PCM over spdif, no need to encode it... But anybody into audio would know that.

  20. Very fast machines by tinrobot · · Score: 2, Interesting

    I have a pre-release Dual Opteron/NForce machine from an unnamed manufacturer sitting right here next to my desk. We haven't finished benchmarking, but so far, it's wicked fast.

  21. Whoopididoo! by MikShapi · · Score: 1

    On one hand, they keep mentioning SLI, SLI, SLI.
    On the other hand, These mobos are server mobos, loaded with stuff I frankly could do without, like SATA2 (IIRC, the fastest hard-drives out there are barely 50% of the way saturating a SATA1 link), Firewire, 8 memory slots and PCI-X.

    What SLI croud need is a simple mobo with a simple feature set, a couple of PCIex1 slots, the two full x16's, the USB, audio, double GbE & the works as offerd by the 2200, and a couple of 939-pin sockets coming from a decent mobo maker like Gigabyte that doesn't charge double for it's badge (read: ASUS, TYAN, etc.)

    All in a sub-200$ box.

    Then all of us who can dish out the cash for an SLI setup accompanied by two (wish nVidia drivers supported more) monitors/projectors, crank up the resolution to max on both and enjoy the scenery.

    That'll be the day.

    --
    -
    1. Re:Whoopididoo! by Max+Romantschuk · · Score: 1

      What SLI croud need is a simple mobo with a simple feature set, a couple of PCIex1 slots, the two full x16's, the USB, audio, double GbE & the works as offerd by the 2200, and a couple of 939-pin sockets coming from a decent mobo maker like Gigabyte that doesn't charge double for it's badge (read: ASUS, TYAN, etc.)

      Please explain. The Opteron uses Socket 940. Newer Athlon 64s use Socket 939. The Athlon 64 won't work in an MP system unless some fancy hack is performed (if at all).

      What exactly are you aiming for here?

      --
      .: Max Romantschuk :: http://max.romantschuk.fi/
    2. Re:Whoopididoo! by MonMotha · · Score: 1

      Tyan isn't targeting you. Tyan is targeting people who want to build PC workstations. These are people who have uses for multiple gigabytes of RAM (think simulations) or PCI-X slots (SCSI RAID controllers). Tyan isn't really targeting PC gamers here. They're obviously trying to appeal to the market, but Tyan has traditionally gone for the workstation and low-end server crowd (people who do work with their computers) with their Thunder series.

      Asus is generally the maker of boards in your target range. Check them out. Yes, they do charge a premium, but they make high quality motherboards in my experience.

      <rant>

      Gigabyte doesn't. I have a 7VTXH and it's a marvel of engineering badness. There's a finicky timing issue whenever all three DRAM slots are populated that I have yet to resolve (and yes, the RAM is on their approved list and is of generally high quality, and no, the RAM is not faulty). I had to ship it back to them no less than three times due to a bad flash chip. Once is acceptable (it didn't immediatley go bad and so could probably pass initial QA), but it would have been nice if they'd just replaced it or extensively tested it after reprogramming it. Also, fat lot of good their "dual BIOS" feature did; I still had a brick. If they'd not solder the damn chip to the board (socket it, folks), I could at least program it myself since I do have a flash programmer.

      The board's ACPI is also a bit flakey, but being a desktop board of the age it is, I can live with that (it's good enough that I can usually get by with leaving ACPI enabled).

      </rant>

  22. Re:As long as we are all slaves by ckaminski · · Score: 1

    Excuse me? 32 bit Windows has been multiprocessor capable since WindowsNT 3.1 was released in 1993. Modern/recent incarnations are even better at it. Windows is no limitation to multiprocessing, today or in the future. Applications aren't even the limitation. Everyone running a modern OS (Linux/Windows/OSX) will benefit from Dual Core. Since even the most recent Linux kernel is almost completely preemptible, there's little reason to not move to dual core architectures from an application standpoint. EVERYONE will benefit.

  23. Nop linux users are looking at 64 bit not 32 by Anonymous Coward · · Score: 0

    Linux has been tested on as far as I know upto 512 processors. Kinda a lot more than windows well and truely tested.

    Linux drivers are built with spinlocks. Windows problem could be the large set of home user single processor drivers how many have spinlocks in them.

    I cannot remmber when linux became mult processor but would not have been far behind.(thinking it only started in 1991) Also I cannot rember when it first went 64 bit please not the Athlon 64 bit is not the first 64 bit chip that linux used.

    1. Re:Nop linux users are looking at 64 bit not 32 by scharkalvin · · Score: 1

      The first Linux 64 bit port was probably the Alpha port, and THAT goes back quite a bit.
      Guessing the superspark was the second.

  24. Summary Title by kaellinn18 · · Score: 1

    Did anyone else read the summary title as NVIDIA's nForce Professional and Cyan's Worlds? No more Uru for me...

    --

    --------
    This isn't the sig you're looking for. Move along.
  25. Not gonna get two full x16 slots for $200 by Namarrgon · · Score: 1
    A 2200 chip doesn't have the necessary 32 PCIe lanes, nor does it have dual GbE. Only way to get that is with a 2200 and a 2050 as well, and you won't see that under $200.

    Besides, if SLI gaming is your big thing, two full x16 slots is overkill, and won't affect your framerates more than 1% at best. Two x8 slots will be plenty for anything around or on the horizon.

    Sounds to me like you want one of the existing nForce4 SLI boards from Gigabyte, with a drop-in dual-core Opteron to go with it. All you need, nothing you don't.

    --
    Why would anyone engrave "Elbereth"?
  26. Enforced affinity by Namarrgon · · Score: 1

    TaskManager can do this under Windows - the user can force any app onto specific CPU(s), and it won't migrate the app at all.

    --
    Why would anyone engrave "Elbereth"?
  27. Wrong by drw · · Score: 1

    AMD has gone to great lengths to make sure their dual-core processors work in current Opteron motherboards. The worst case would be that you would need to upgrade your BIOS, but the power requirements for these chips will be under the maximum that AMD has been telling motherboard makers to support.

    The only downside is that they will always be behind in regards to clock speed compared to their single-core processors. I think somewhere in the 2.0 GHz range at initial launch.

    1. Re:Wrong by ipjohnson · · Score: 1

      Yeah but thats fine because my K8W has 2 242s, so going to a 2.0Ghz dual core when they are ready sounds awesome.

  28. Ummm... by EmagGeek · · Score: 1

    Wow?

  29. Tyan and LinuxBIOS by DeathPenguin · · Score: 1

    Just check out the work Yinghai Lu has been doing on LinuxBIOS for Tyan boards. He even has it working for nVidia Crush K8s based Tyan boards.

  30. Re:As long as we are all slaves by zymano · · Score: 0, Troll

    Your probably one of the idiots that modded me a Troll. But thats ok. I have too much Karma shit anyways.

    xp can't do multiprocessing.

  31. Tyans last Dual Opteron Workstation sucked by Neuroelectronic · · Score: 1
    The S2885 They talk about is unstable.

    I know I am running it. It has alot of problems with the AGP. Alot of games crash it. Not very compatable with RAM. (check their website to find "authorized" ram models) the drivers that were supposed to fix this made it worse. They don't even uninstall cleanly! Their BIOS is Still in beta! This motherboard was released years ago. There is no excuse for this, it's a $500 motherboard

    1. Re:Tyans last Dual Opteron Workstation sucked by Anonymous Coward · · Score: 0

      Looks to me like they have something non-Beta, and have had subsequent releases since '03. You're not making much sense with that statement.

      http://tyan.com/support/html/b_s2885.html

  32. Re:As long as we are all slaves by ckaminski · · Score: 1

    I don't mod, but thanks for calling me an idiot.

  33. Re:As long as we are all slaves by ckaminski · · Score: 1

    That article you linked to explicitly states that XP Professional is fully capable of SMP... There's nothing preventing Microsoft from doing a dual-core WindowsUpdate for those people who do install XP Home to enable dual core support, and nothing preventing them from releasing a service pack to OEMs to support dual core on default installs.

    I'm don't remember seeing them state this will be a future policy, but their committment to support dual core as single CPU's for the sake of per-CPU licensing would seem to indicate that this is a future possibility.

  34. Re:As long as we are all slaves by zymano · · Score: 1

    But they will lose $$$.

  35. You are a moron. by Anonymous Coward · · Score: 0

    First of all, if you think having to download binary drivers on a seperate machine, and burn them to a cd to install on your machine is not a problem, then you are retarded. Second, I do use BSD, and nvidia doesn't release any drivers. Third, I also use linux, and I won't use binary only drivers that could be hiding hardware problems, or creating security problems.

    Considering everyone else can manage to release info for their chipsets, and if I buy any motherboard without nvidia shit on it I can use it just fine in all my chosen OS's, there is simply no reason to buy this crap. And if you do buy it, you are encouraging them to be ever more secretive and problematic.

    1. Re:You are a moron. by DarkMantle · · Score: 1

      ...and I won't use binary only drivers...

      So I'm guessing you won't use binary only software either. My question is, do you read all the source code to all the programs and drivers you use? If not, you still don't know if they're hiding problems with the hardware, or have hacked routines for quick fixes to problems.

      In which case your argument is moot.

      And since I'm running nForce2 system, dual boot, I can tell you right now the only problem I have with linux is it doesn't seem to like my raid. And that's NOT an nVidia issue.

      --
      DarkMantle I been bored, so I started a blog.
  36. Ummm... where are the extra hardware INTERRUPTS? by macraig · · Score: 1

    Great, so there's all this extra POTENTIAL connectivity for devices and peripherals. Now where's the extra hardware interrupts and controllers to support a system with more than just a few of those things enabled at once? If we're still stuck in neutral with the same 16 interrupts we've had for almost TWO DECADES, what the heck is the point? Even the extra four "virtualized" interrupts created by my current motherboard (in Windows, at least) hasn't helped avoid interrupt conflicts. I've had to remove devices and dedicate another system to them because there simply weren't enough interrupts to support ALL the on-board devices and a couple extra PCI cards as well. So, would somebody please tell me WHY all this "advancement" is so important when we're still handcuffed with the same 16 hardware interrupts that were available in an IBM PC AT?

  37. Re:As long as we are all slaves by ckaminski · · Score: 1

    I don't understand. It's either: release software that works with dual core CPUs, or get replaced by software that does. Or ensure that only XP Pro gets installed on dual core CPUs, and I don't think that's going to be acceptable to OEMs fighting with tight profit margins.

    They don't have a choice. Microsoft has the cushion to take the profit hit...