Slashdot Mirror
Quad PCIe Motherboard
SlipKid writes "PCI Express Graphics cards have allowed for some new and innovative ways to increase rendering horsepower in Desktops and Workstations. Recent introductions of NVIDIA's SLI and ATI's CrossFire technology have enabled dual PCIe Graphics cards in a
load-sharing architecture. Motherboard manufacturers are jumping into the fray now and Gigabyte has released a Quad PCI Express graphics enabled motherboard, capable of running four cards at once. The board is not capable of running Quad SLI, mostly due to lack of NVIDIA driver support currently but it does offer support for eight simultaneous display outputs on four Graphics cards."
Well, $topic pretty much says it all. More PCIe-slots, great, but it'd be nice if there were stuff besides graphics-adapters to push in.
Even if you could do Quad SLI, would it make that much of a difference in performance? At what point would splitting the rendering task be more work than it's worth?
And let the extraction of consumer surplus begin! I thought dual-card sli was bad -- this is becoming insidious. The number of applications (in the old fashioned sense, as in 'a thing one does') for which this is useful ... I can count them on one hand. The number of fools who are going to be (perhaps rightly, perhaps wrongly) made to part with yet more of their money to have 'quad card setup man!' ... will be legion.
I like the idea of an eight-head computer. I wonder what the price difference would be to equip a computer lab with octoheads instead of singles.
In fact, if I could get some long enough wires, every television in my house could be just another head of one master computer. Master Control! Huzzah!
Carpe Daemon
Yes, but does it support Quad-opteron in 1U ? Now that would be cool.
/ 11/1424258
http://hardware.slashdot.org/article.pl?sid=06/03
......surround pr0n.
I like the idea of an eight-head computer. I wonder what the price difference would be to equip a computer lab with octoheads instead of singles.
Why would you do this? You risk losing eight desktops instead of just one to a single component failure (eg, a faulty motherboard).
Standard entry-level desktops and workstations are commodity items now: their prices are so low, and they are so easy to acquire that I doubt that there would be much in the way of cost savings to be had when comparing eight single-CPU PCs to one eight-headed hydra.
Don't forget, to be able to run standard applications at the same speed as even the cheapest of today's desktops the hydra solution would have to have a serious amount of processing power, memory, etc. Once you factor all those things into the equation then you'll soon realise that, in almost every case, there is little or nothing (financially, technically or even physically) to be gained from going down that road.
Of course, a home is a little different from a computer lab. For one thing, in a home solution any bottlenecks would be fewer in number and far less severe than they would be in a lab environment, which makes such a solution more viable.
Even so, I know that I for one would rather prefer a dedicated desktop, a dedicated home theatre PC, etc connected by a LAN/WAN than a single-PC, all-my-eggs-in-one-basket solution.
"Accept that some days you are the pigeon, and some days you are the statue." - David Brent, Wernham Hogg
( 4 Displays * 4 PCI Express X16 slots = 16 Screens ) +
( 4 Displays * 2 PCI Express x1 slots = 8 Screens ) +
( 2 Displays * 1 PCI slot = 2 Screens )
= a total of 26 displays.
It's a pity it is not an multiprocessor opteron system...
See 2005 April's How Many Desktop PCs Can One Server Replace?
Note I didn't say optimal performance or peak effenciey or any other term to make it seem like more cards would just equal "OMFG MORE FPS, YESSZZZ!". No. With games like BF2 that are starting to require specific actual components of stuff coupled with how much things like DirectX are a huge huge factor in games, you are going to need massive amounts of GPU power to get alot of stuff to run.
I mean (not to plug them or anything) but look at games like Project Offset, which plans for real-time rendering of everything no cutscenes nothing. The processing power of that game is going to be astronomical. I bet it will hit at the least a 2 PCI-E card requirement with at least 1.5 or 2 gigs of ram and 3.0+ GHZ processor, probably 3.4+. And we all remember how systematically intense past games like Farcry were, imagine cranking out a game that's five times as powerful as Farcray or even P:O you're going to require so much raw processing power it's insane.
Which itself is within the true nature of computing, technology evolves, advances, grows faster or more powerful or more advanced. I still think it's sad though, I mean you look at some of the top of the line cards these days required for games, they are insanely priced (200,300 even 400-500 or more). And yes while you can go with something slightly slower and save alot of money, as I originally said I think it will hit the point where they simply will not run without X amount of cards or equipment. Just like I can't run modern games like BF2 or HL2 on my current setup, same thing in a few years for people wanting that hot new title that needs quad cards. The price will be fucking outrageous too. You thought $400 for an Xbox 2 was bad, wait until you need to drop $300 per graphics card, two three or four times plus all the other components just to play games.
Nvidia and ATI are wetting themselves awaiting that day. Why sell them one GPU when Game X they want needs quad cards to even execute.
Aw Frell this
Sheesh, talk about compensating for the lack of something else...
There did not appear to be much written in the review on the way the PCIe lanes could be configured. The default apparently has that the four physical 16-lane slots are electrically 1-lane, 16-lane, 16-lane and 1-lane respectively.
What excites me about such a board is the possibility of having simultaneously a fast SLI rendering set-up, together with fast I/O with 10Gbit ethernet and SAS. Having everything on PCIe rather than a mix of PCIe for graphics and PCI-X for I/O cards would allow more flexibility (at least, once there is a bit more range available in PCIe non-graphics cards!). Yet, if the configuration of channels only allows 1-lane on all but two of the slots, then it's not going to work out.
Um, right. If by 'NVIDIA' you mean '3DFX' and by 'recent' you mean 'ten years ago'.
Sheesh. Kids these days, they got no respect.
I would love to see a quad-Opteron mobo with four x16 PCIe slots but arranged in a way that traffic is spread across all HT links. So that I could use it to put 4 PCIe SATA cards, and have the highest possible read/write I/O throughput for a Linux software RAID array. Hardware RAID is out of the question, since no constructor offers a way to create arrays of disks across 3 or more cards. An Opteron has 3 HT links, 2 of them could be used as coherent links to other CPU's, and 1 of them could be used as a link to an external PCIe bridge chipset. The solution I would like to see implemented is one where 4 PCIe bridge chipsets would be connected to their own Opteron, via their own HT link. And each PCIe bridge chipset could provide at least one 16x slot.
Some numbers: each of the four x16 PCIe bus would allow for 2500 MT/s * 16 bits / 8 = 5000 MB/s of traffic in each direction. And each of the 4 HT links: 1600 MT/s * 16 bits / 8 = 3200 MB/s. The global amount of I/O would be 3200 MB/s * 4 = 12.8 GB/s in each direction ! (HT links are the bottleneck). To resolve this bottleneck AMD would either need to increase their width from 16x16 to 32x32 bits or need to increase the signal freq from 800 MHz to 1.25 GHz (current limit is 1 GHz for coherent links and 800 MHz for the ones facing outside worlds -- chipsets seem to lag a little bit regarding HT frequency).
But for some reason no constructor has ever designed such a board (Tyan only did it with 2 PCIe chipsets on their S2895 mobo). Why oh why is that the case ?! Seems like nobody understands the true potential of HT. This could provide a low-cost solution to so many perf issues I have seen in the various companies I have worked for... Argh !
Finally a board that can run a 2 card nVidia SLI configuration alongside a 2 card ATI crossfire config.
No more bickering which one runs this or that game better - just use the right tool for the job, no swapping of cards required.
Granted, you'd have to move to Antarctica to cool this sucker, but that should be no problem as long as the pizza delivery guy can get there, too. And just think of all the heating equipment you can replace with this rig...
"I'm not anti-anything, I'm anti-everything, it fits better." - Sole
This Motherboard will better option for them who wants to run 8 moniter at a time ...... but i don't think in day to day ususal computing this is having any importance as u u willl not be having any PCI slots. so fitting a sound card or TV tuner card will be a problem. but people doing video editing or photo editing can be really benefitted from this. and about quad SLI i will say dual GPU on single card is better option but still u will be wasting all the PCI slots. i don't think we need 4x7900GTX even we are playing with 25xx X 16xx resolution. a normal SLI of 2 card will do fine for that. so i think it will nbe useful for professionals and games sud stay away from this.
i work for money, if u want loyalty, Go get a Dog.
This could be nice for a big VMware setup but, if my memory serves me right, VMware has problems with multi head setups. Assuming it works, I may need to look for a larger desk!
I don't know why, but since i'm on /. and it includes support for more displays i automaticly think of porn. Maybe it's the crowd ....
nVidia Quad SLI is based around two dual GPU video cards running as a pair on a motherboard with two PCIe slots.
http://www.active-hardware.com/english/reviews/div /b210.htm PC Buddy allowed for 5 KVM hookups to a win 98 pc..
(one original, 4 buddies) I installed one once- it worked well.... but it was mostly used as a second browsing terminal....
every day http://en.wikipedia.org/wiki/Special:Random
Some people say its really bad thing happening as it would raise the performance requirements of games.
BULL** it will make some EXTRA highend stuff possible. The games are designed for something thats more mainstream, and very highend systems are for extra eye candy. The game companies probably cannot convince majority of their target market to upgrade to SLI. So majority of the money is from those who don't have SLI systems.
But what does quad sli give us.
Well first use comes to my mind is 30" displays, you know the thing that has slightly over double the pixels to 20" displays. You need twice the power to run equal 3D performance on 30" compared to 20". Or 4 times the low end displays.
Another point is antialiasing requires some performance out of card.
QUAD SLI isn't cheap so it won't be mainstream, so it won't be MAIN target for game developers. However its supported.
One use for QUAD SLI is when making a game you need to design the game for performance of typical system in 4-5 years. It is probably twice or quadruple the performance of current highend think the memory bandwith of SINGLE card has quadrupled in that time frame. Also there is more than 12 times the computational performance increase.
As for free slots. There is 7 places on the case where to put a card. For game system a soundcard is a must, that gives 2 free slots with quad SLI. For gaming those two slots *COULD* get nic or some extra raid card. But neither of those are top of list items since the onboard ones could be considered good enough.
Only problem though that with 4 gfx cards dualslot cooling isn't reasonable. Some highend cards don't have dual slot cooling already, and water cooling IS option for these kind of priceye highend systems.
Emacs is good operating system, but it has one flaw: Its text editor could be better.
It seems like a good theory, but in practice only about a half-dozen is practical. The problem mainly comes down to distributing the cables. You can use USB hubs and repeaters to make the keyboard and mouse cables manageable, but the video cabling is where it becomes tricky. Those cables are THICK, and the signal degrades noticeably with the cheap ones. Also, no manufacturer that I know of supports more than 16 heads on a system. You may be able to get away with 16 ATI and 16 NVidia, though.
Not only is cable routing a nightmare, but maintenance is also difficult. Every time you plug in a new keyboard or mouse (probably because somebody sat on it or spilled something on it), you have to figure out how to address it to reassign it to the monitor where it belongs.
If you're just running a bunch of kiosks (say, book searching at the library), this will work OK. You still have to deal with masses of cables running along the floor, though.
But let's say you want to allow word processing also. Now you have to allow people to plug in floppies and/or USB keys to allow people to save/load their files. This is a problem because the user who plugs in a device will have no clue how to access it (it will be assigned some random device number which isn't associated with anything).
What if you want to run a real computer lab, though? That just isn't feasible. Any computer program can easily use up 100% of the CPU, making the system slow for the whole lab. Back when CPUs were expensive this was something you just had to live with. I remember back in college when a big CS assignment was due, the computers had horrible response time because somebody was always compiling. And any sort of maintenance that would require only taking down an individual machine (e.g. kernel security updates) now requires taking down the whole lab.
By the time you pay $600 for those quad-head video cards, $100 of cables and hubs for each station, and $100 per seat for the hydra software, you're better off buying cheap computers.
dom
This is what your gaming rig will look like:
http://pbx.mine.nu/artwork/gamingrig.png
Userful Desktop Multiplier (TM) v2.0 Supports Ten Displays but that is mearly a limit of the hardware, not the OS.
Consider a server in the middle of a cross + of alcoves. Each "arm" is limited to 7.5 meters from the "desktop server". Allocate 2.5m each side at each inside corner users and 1.5m for three users either side of the arms.
4 + 8 * 3 = 28. Easy fit.
Yyyyyuck! RAID5 is a great technology but repeatedly moving the heads from the beginning to the end of the disks during multiple large sequential read/write operations is surely not the way to get the experience of eight single drives.
Try it out, you may not have a busy database but try creating a RAID5 set, then formatting it into 3 partitions. One small at each the very beginning and end of the set, one large in the middle. See what kind've throughputs you can get when you attempt to access partitions A and C simultaneously with large reads and/or writes.
My money is on a drastic decrease in performance, and life of the drives.
ALSO.
The more you are waiting on this raidset to perform IO operations, the more CPU waste you are accumulating. Waiting on I/O is an extremely painful way to spend CPU time.
but it does offer support for eight simultaneous display outputs on four Graphics cards.
Cool! Now I can fight myself in a lightsaber battle on 8 different screens!
He who knows best knows how little he knows. - Thomas Jefferson
By alocating one external hub to each "station" you can use HAL config script to "alocate" the each hub to its station. All it takes then is to customise the GNOME/X Display Manager to grant read write access to devices pluged into that hub for the user logging in to the X session.
A little cement on the hub could lock in the keyboard and mouse.
Recent introductions of NVIDIA's SLI and ATI's CrossFire technology have enabled dual PCIe Graphics cards in a load-sharing architecture.
Great. Fine. Wonderful. Where are the drivers for FreeBSD?
The above setup may not be really suitable for full screen 30fps multimedia movies ( I have experimented with VLC viewer running as a local application on PII 400 LTSP stations -- works very well ) but thats not what it's primary role.
horizontal, not vertical, obviously..
which is totally what she said
Heat. The main reason I dumped my SLI setup - and yes I have a custom-built Danger Den watercooled setup and I can assure you the heat from SLI is simply not worth it - let alone the fact that in 3 months it will be obsolete by the release of some uber single card.
You left out the proper OS. You seem to be suggesting doing this on Windows! ? Yikes!
A better way would be to run Windows in VM's only when you need Windows sessions. Host them on Linux. You'll get better support for multiple monitors that way. Spyware could still be a problem, but a contained one, since the firewall on the host could detect outgoing spyware/trojan connection attempts.
This sig kills fascists.
removes a lot of hair, the second razor pushes down and gets the fine stuble, the third razor prevents that five o'clock shadow, the forth razor removes a fine layer of skin, the fifth razor removes another layer of skin...
I glanced briefly at TFA and immediately closed it having seen the motherboard they used for this. I have had nothing but heartache using Gigabyte products, and strongly discourage others from using them as well. If you go to Newegg and read some of the reviews, you'll see what I mean. Here's an example: GA-K8N51GMF-9 . They have other boards with similar complaints being posted.
Call me vindictive, but the headache I've gone through struggling with Gigabyte's products and tech support makes me very biased on this topic.
"You will pay for your lack of vision..." - Emperor Palpatine to Ray Charles
>Why would a soundcard need a 16 lane PCI-e slot?
I never claimed it would, so why are you busy bulding strawmen? I just said I'd like a larger selection of PCIe periphals to chose from than just graphics-adapters (and the occasional high-end RAID-controller).
The reasons are as numerous as they are obvious; PCIe is here to replace AGP and PCI, not just AGP. Having to have PCI and PCIe likely makes everything more expensive. Having to partition board-space in PCI and PCIe slots is bad -- I'd rather have 6-7 PCIe slots to use as I will, than having to decide up front on a partition of PCI and PCIe which is ill suited for adapting to changes in configuration. Do I buy a board with 3 PCI and 2PCIe or one with 2PCI and 3PCIe? There's a lot less flexibility here than if everything was just PCIe.
Most of these resource hog games are all FPS's anyway. Not only will they price themselves out of the market from hardware demands but people won't keep spending big $ on new hardware just to play the same old shoot-em-ups. I wouldn't be surprised if there is a backlash and people go for retro games that were played on 8-bit systems. I'm seeing some of that now to be honest. The bigger the game demands doesn't mean it is better, look at chess.
It is by the juice of the coffee bean that thoughts acquire speed, the teeth acquire stains. The stains become a warning
whats the big deal with this? the latest announced SLI chipsets that should be available soon from nVidia already say they support 4 video card SLI... wait til you can get a board soon with one of those newer nForce chipsets.
A week ago, scientists created the hottest temperature ever seen on earth but had no idea how they did it.
This week, following NVidia's earlier announcement of 2 GPUs per card in a tie-in with Dell, Gigabyte anounces a 4xPCIe motherboard.
Millions of nerds, picturing 8 high end GPUs in one small box, sagely nod their heads and say, "Ah!"
The limit on multi-track audio comes from disk speeds (it tends to require a large amount of random access and thus performs below it's ideal speed) but more just from practicality. It takes a lot of citcutry to properly capture 24/192 audio. MOTU makes audio interfaces that will capture and output 12 channels of 24-bit 192kHz audio at the same time (as in 12 channeils in, 12 out). You can stick 4 of these on a single 424 interface card, the PCI (now PCIe as well) card that goes in your computer. The limitation of 4 total interfaces isn't one of bus speed, but rather routing of the DSP on on the chip and practicality of fitting the ports on the card.
Eight screens makes a really cool video wall... well, except for that big HOLE in the middle!!
Looks like graphics/motherboard companies are getting their innovative ideas from the "shaving" industry. Soon enough the motherboards/video cards will vibrate to clean those jaggies out of your monitor! 1AA battery required.
Add that Matrox triple head to go thingie: http://www.matrox.com/graphics/offhome/th2go/home. cfm
And enjoy 3 times the screens! A video wall running on one computer!
No idea if it would work...
Remember that those "graphics cards" are high-performance processors that can perform more "general purpose" tasks: GPGPU. I'd love to see a Linux kernel that is basically just a task scheduler for distributing computing among a network of GPGPU cards on these multiple PCI buses. Scalable desktop supercomputers running Linux apps.
--
make install -not war
Make sure that you have two seperate configuration files, and that you start X by specifying the specific one for each screen. You need at least one USB keyboard and mouse. You need to specify precisely which video card you are using, and which USB keyboard/mouse devices (versus the PS2 keyboard and mouse). You can't just use /dev/input/mice or /dev/input/keyboard, because they multiplex PS2 and USB devices (usually used in laptops).
I believe GDM can be set up to do this (one login screen per monitor/keyboard pair) but I'm not sure of the details. I imagine you'd need to make a change or two in your inittab to start it on another vt referencing the alternate GDM config (which in turn holds the custom X command line + differing config files)
THIS THING CAN TURN ON A DIME, MACROSSZERO STYLE ALSO FUCK BETA, ~NYORON
Yes, but with faster hardware always on the horizon, is there a real push for highly optimized software for 3D games?
Or would they prefer to be first to market at the expensive of a bit slower (fps) game? After all, if they don't push too hard to make the software run fast/efficiently, it will push the hardware companies to advertise/sell faster cards.... And when one gets a faster video card, they tend to want to try it on as many games as possible....
This motherboard has been out for at least 4 months, maybe even 6 months. Ive lost track.
Either way, this isnt news, but thanks for reposting.
Despite the fact that quad sli isnt readily available currently, Nvidia is already in the works for it to become available. Initially they will be offering it through companies such as dell (dell is actually the first company to have it available), but in the later developments they will be supporting it openly.
In reality this board is just a grab for attention from gigabyte.
My first thought about this was that it would make a great HPC box. I think boxes like this might move the i/O folks to x16 pciE. As far as I know nothing besides graphics has gone past x8. InfinBand SDR 4X and some 10GE cards could go to x16 and have dual ports. Finally a port that could run that dual port DDR 4X IB card...or that SDR 12X IB card. Bandwidth for I/O is getting better all the time...at some point it will get close enough to memory speeds that a whole new set of distributed applications will become possible.
-ack
-- soldack
By now, there are three computers used in this house, plus a fourth when I'm home for vacation, because there are four people who live here. There's also two TVs, one much bigger than the other, because my mother likes to have the TV on sometimes in the kitchen while she cooks/cleans/whatever, and everyone else likes to watch the much larger TV in the other room.
Even if you count my laptop/desktop as one, since if (in theory) the laptop was powerful enough, I wouldn't need the desktop, that's still six heads.
So yes, a hydra-like solution would be great. I do have one serious doubt, though:
Games.
Two of the four computers are serious gaming rigs. Could one dual-core system with three nVidia cards replace two separate systems, each with their own nVidia card? Would the cables around the house cause noticeable lag between a mouse signal going off to the hydra and coming back to the screen? And would it leave adequate power left over for web browsing and office work, especially considering how much RAM Quicken eats up, and how much CPU Flash eats up?
My guess is that it could be made to work, but I'm far too chicken to try yet.
Don't thank God, thank a doctor!
What gives? If you're going to do something as mind-boggling as stack enough GPUs togeather for four computers, let's atleast support four cores... Add in Sun's hardware domain manager, and maybe we could get four workstations out of one box.. or two workstations and a server.. or two servers.. Does anyone else see this as the next inevitable step in computing after EFI?
Any fool can criticise, condemn, and complain, and most fools do. - Benjamin Franklin
I guess Power Mac G5s have it for several months, four PCIe slots, 16x, 8x, and two 4x. I remember advertisment metioning eight displays connected to single Mac.
Unless you were actually going to run 4 graphics cards, there really wouldn't be much point, I mean who is actually going to use a x/16/8/8 or an 8/8/16/x configuration? Neither of these modes allow you to do SLi as slots 2 and 3 are at different speeds, so really you only options are 8/8/8/8 or 1/16/16/1.
All the other high-end boards run SLi at x16 anyway, but at that price point the rest of them are offering better sound (MSI Diamond) or perhaps better cooling solutions like this ASUS board.
Perhaps if you were running 4 PCI-E x1 cards it might be worth it, however if you're running SLi you already lose access to a PCI and a PCIEx1 slot anyway, leaving you with just three x1s. It'd be a smarter move to go for a boards that has say, two x1s, one x4 and a couple of normal PCI slots for backwards compatability (like on the ASUS linked above).
Also, a lot is sacrificed in flexability, for example, if you have a full length GTX card you lose access to IDE-1, and the poorly placed capacitors near the CPU means you'll have trouble installing large aftermarket HSFs, and if you're spending this much on your PC, then you definitely should NOT be using the Intel standard HSF. Those pesky capacitors also mean you have to hit the graphics card release with pliers if you have a beefy card, with there being scarce room for fingers between the card heatsink and the capacitors (Reference: AtomicMPC Issue 62).
A big plus to Gigabyte for Innovation, but it's not really a practicle solution.
PS: The board's been around to two months =S.