Forgot your password?
typodupeerror

Nvidia Working on a CPU+GPU Combo 178

Posted by Zonk
from the that-will-keep-them-out-of-trouble-for-a-while dept.
Max Romantschuk writes "Nvidia is apparently working on an x86 CPU with integrated graphics. The target market seems to be OEMs, but what other prospects could a solution like this have? Given recent development with projects like Folding@Home's GPU client you can't help but wonder about the possibilities of a CPU with an integrated GPU. Things like video encoding and decoding, audio processing and other applications could benefit a lot from a low latency CPU+GPU combo. What if you could put multiple chips like these in one machine? With AMD+ATI and Intel's own integrated graphics, will basic GPU functionality be integrated in all CPU's eventually? Will dedicated graphics cards become a niche product for enthusiasts and pros, like audio cards already largely have?" The article is from the Inquirer, so a dash of salt might make this more palatable.
This discussion has been archived. No new comments can be posted.

Nvidia Working on a CPU+GPU Combo

Comments Filter:
  • by eldavojohn (898314) * <eldavojohn.gmail@com> on Friday October 20, 2006 @12:26PM (#16517577) Journal
    Sounds like Nvidia is just firing back at the ATI-AMD claim from two months ago [theinquirer.net]. Oh, you say that you're integrating GPUs and CPUs? "Well, we can say that too!"

    What I don't understand is that I thought GPUs were made to offload a lot of graphics computations from the CPU. So why are we merging them again? Isn't a GPU supposed to be an auxillary CPU only for graphics? I'm so confused.

    What I'm not confused about is the sentence from the above article:
    DAAMIT engineers will be looking to shift to 65 nanometre if not even to 45 nanometre to make such a complex chip as a CPU/GPU possible.
    Oh, I've worked with my fair share of DAAMIT engineers. They're the ones that go, "Yeah, it's pretty good but ... DAAMIT, we just need more power!"
    • by everphilski (877346) on Friday October 20, 2006 @12:32PM (#16517669) Journal
      What I don't understand is that I thought GPUs were made to offload a lot of graphics computations from the CPU. So why are we merging them again?

      a really, really fast pipe. It is a lot quicker to push stuff from CPU->GPU when they are on the same piece of silicon, versus the PCIe or AGP bus. Speed is what matters, it doesn't look like they are moving the load one way or another (although moving some load from CPU->GPU for vector based stuff would be cool if they had a general purpose toolkit, which I'd imagine one of these three companies will think about).
      • Re: (Score:3, Insightful)

        by Ironsides (739422)
        Then why not just have some connections that come straight out of the CPU and go directly to a graphics card, bypassing any bus entirely?
        • by drinkypoo (153816) <martin.espinoza@gmail.com> on Friday October 20, 2006 @12:49PM (#16517871) Homepage Journal
          ATI/AMD is working on that right now. I think it comes after the next rev of hypertransport.
        • by ultranova (717540)

          Then why not just have some connections that come straight out of the CPU and go directly to a graphics card, bypassing any bus entirely?

          That's the whole point here: put the CPU and GPU right next to each other and wire them together. You see, the nearer they are to each other, the less time it takes for electric impulses to travel from one to the other, and the faster the communication is.

          And, of course, the reason number one: you get a guaranteed GPU sale for each CPU sale - goodbye pesky competitio

          • by Ironsides (739422) on Friday October 20, 2006 @01:49PM (#16518679) Homepage Journal
            And, of course, the reason number one: you get a guaranteed GPU sale for each CPU sale - goodbye pesky competition ;).

            And vice versa. This might work where someone wants an embeded GPU for low to medium end graphics. However, I doubt gamers would like the idea of having to purchase a new CPU evertime a new GPU comes out and vice versa.

            There's something to be said for physically discrete components.
        • by stevenm86 (780116) on Friday October 20, 2006 @02:38PM (#16519475)
          That's sort of the point of building them on the same die. You can't just run a wire to it, as it would be quite slow. Wires tend to have parasitic inductances and capacitances, so the setup and hold times on the lines would be too large to provide a benefit.
        • by TeknoHog (164938)
          Then why not just have some connections that come straight out of the CPU and go directly to a graphics card, bypassing any bus entirely?
          I think it was done sometime in the past and it was called AGP.
      • A cyclic process? (Score:5, Insightful)

        by Kadin2048 (468275) <slashdot.kadin@xoxFREEBSDy.net minus bsd> on Friday October 20, 2006 @12:49PM (#16517867) Homepage Journal
        A while ago -- and maybe it was in the Slashdot discussion about ATI, I'm not sure -- somebody described a cycle in computer design, where various components are built-in monolithically, then broken out as separate components, and then swallowed back up into monolithic designs again.

        Graphics chips seem to have done this cycle at least once; perhaps now we're just looking at the next stage in the cycle? We've had graphics as a separate component from the processor for a while, perhaps the next stage in the cycle is for them to combine together into a G/CPU, to take advantage of the design gains in general-purpose processors.

        Then at some point down the road, the GPU (or more likely, various GPU-like functional units) might get separated back out onto their own silicon, as more application-specific processors become advantageous once again.
        • Re:A cyclic process? (Score:5, Informative)

          by shizzle (686334) on Friday October 20, 2006 @12:56PM (#16517943)
          Yup, the idea is pushing 30 years old now, and came out of the earliest work on graphics processors. The term "wheel of reincarnation" came from "On the Design of Display Processors", T.H. Myer and I. E. Sutherland, Communications of the ACM, Vol 11, No. 6, June 1968.

          http://www.cap-lore.com/Hardware/Wheel.html [cap-lore.com]

          • by gstoddart (321705)
            The term "wheel of reincarnation" came from "On the Design of Display Processors"

            I won't dispute that the term in a technical usage was coined by them. But, it's basically a borrowed term from Hindu/Buddhist stuff who have believed in reincarnation and the wheel of life for a few thousand years.

            Cheers
        • Re:A cyclic process? (Score:4, Informative)

          by levork (160540) on Friday October 20, 2006 @12:58PM (#16517981) Homepage
          This is known as the wheel of reincarnation [catb.org], and has come up several times in the last forty years of graphics hardware.
        • by asuffield (111848)

          A while ago -- and maybe it was in the Slashdot discussion about ATI, I'm not sure -- somebody described a cycle in computer design, where various components are built-in monolithically, then broken out as separate components, and then swallowed back up into monolithic designs again.

          Graphics chips seem to have done this cycle at least once; perhaps now we're just looking at the next stage in the cycle?

          Frankly, I hope this is the last stage in the cycle - at least until we have some radical changes in how pr

        • Intel has tried to integrate specialized I/O on their chips more than once, a nd so have other companies. Then they end up with something neither best in either and become commercial failures.
        • Re: (Score:2, Funny)

          Ohh... do you think that I could get a trademark on "G/CPU" and then try and auction it off to the two compaines?
      • by purpledinoz (573045) on Friday October 20, 2006 @12:51PM (#16517889)
        It seems like this type of product would be marketed towards the budget segment, which really doesn't care about graphics performance. However, the huge advantage of having a GPU on the same silicon as the CPU would be a big boost in performance. The low cost advantage has already been attained with the integrated graphics chipsets (like nForce). So that would mean this might be marketed towards the high-performance crowd.

        But I highly doubt that nVidia will be able to get a CPU out that out-performs an Intel or AMD, which the high-performance junkies would want. Intel and AMD put a HUGE amount of money into research, development, and fabrication to attain their performance. This is going to be interesting to watch. Hopefully nVidia doesn't dig themselves into a hole with this attempt.
        • Re: (Score:3, Interesting)

          by Doctor Memory (6336)

          But I highly doubt that nVidia will be able to get a CPU out that out-performs an Intel or AMD

          Maybe they don't have to. If they can just make something that can accelerate MMX/3D Now (sort of a graphics pre-processor) and plug that into a Socket F [theregister.co.uk] slot, it'd be like a two-stage accelerator: first accelerate the calculations that produce the graphics, then accelerate the display. Maybe they could find a way to do a micro-op translation of MMX instructions into something more RISC-like, and run them on a RI

      • by NerveGas (168686) on Friday October 20, 2006 @01:32PM (#16518455)
        I don't think that the CPU->GPU pipe is any limitation. Going from AGP 4x->8X gave very little speed benefit, and on PCI-E connections, you have to go from the normal 16x down to a 4x before you see any slowdown.

        Memory size and bandwidth are the usual limitations. Remember that if you want 2x AA, you double your memory usage, and if you want 4x AA, you quadruple it. So, that game that needed 128 megs on the video card, with 4x AA, can suddenly need 512.

        steve
        • by julesh (229690) on Friday October 20, 2006 @02:40PM (#16519509)
          Memory size and bandwidth are the usual limitations. Remember that if you want 2x AA, you double your memory usage, and if you want 4x AA, you quadruple it. So, that game that needed 128 megs on the video card, with 4x AA, can suddenly need 512.

          Of course with the GPU integrated into the CPU you wouldn't need card-based RAM at all. You'd process your video on system RAM, and it would be as fast as the GPU accessing its own RAM at the moment is (not shit like shared-memory video cards are at the moment). This results in flexibility: if you're only using 128MB of RAM for your graphics, you can reuse the other 384MB as additional system RAM.
          • Not so much (Score:5, Informative)

            by Sycraft-fu (314770) on Friday October 20, 2006 @02:56PM (#16519745)
            System RAM is SLOW compared to GPU RAM. PCIe actually allows very high speed access to system RAM, but the RAM itself is too slow for GPUs. That's one of the reasons their RAM amounts are so small, they use higher speed and thus more expensive RAM. Also because of the speed you end up dealing with cooling and signal issues which makes it impractical (or perhaps impossible) to simply stick it in addon slots to allow for upgrades.

            Even fast as it is, it's still slower than the GPU would really like.

            What you've suggested is already done by low end accelerators like the Intel GMA 950. Works ok, but as I said, slow.

            Unless you are willing to start dropping serious amounts of cash on system RAM, we'll be needing to stick with dedicated video RAM here for some time.
            • Re: (Score:2, Troll)

              by julesh (229690)
              System RAM is SLOW compared to GPU RAM.

              Huh? All the systems on this lineup [tomshardware.co.uk] use standard PC3200 (DDR400) RAM. Which is the same RAM that you could use as system RAM with many motherboards (e.g. this one [micom.co.uk]). I don't see why the RAM would be faster on the video card than in the main system...?

              Also, a GPU inside the CPU would get to benefit from the CPU's cache, which would usually contain any data that had recently been modified by the main redraw thread, thus eliminating the need to go out to get data from t
              • by Sycraft-fu (314770) on Friday October 20, 2006 @03:34PM (#16520287)
                Yes the SYSTEMS Tom used to test have normal speed ram for systems. Duh. The graphics cards, however, have much faster RAM. For example my system at home has DDR2-667 RAM. That's spec'd to run at 333MHz which is 667MHz is DDR RAM speak. My graphics card, a 7800GT, on the other hand has RAM clocked at 600MHz, or 1200MHz in RAM speak.

                Not a small difference, really. My system RAM is rated to somewhere around 10GB/second max bandwidth (it gets like 6 in actuality). The graphics card? 54GB/sec.

                Video cards have fast RAM subsystems. They use fast, expensive chips and they have controllers designed for blazing fast (and exclusive) access. You can't just throw normal, slow, system RAM at it and expect it to perform the same.
                • Video cards have fast RAM subsystems. They use fast, expensive chips and they have controllers designed for blazing fast (and exclusive) access. You can't just throw normal, slow, system RAM at it and expect it to perform the same.

                  Of course, Nvidia could plan to use blazingly fast RAM like that used on video cards now as the system RAM on motherboards supporting their CPU-GPU hybrid, which would solve the problem nicely, though it might drive the price up quite a bit. (Then again, it would improve system pe

              • Huh? All the systems on this lineup use standard PC3200 (DDR400) RAM. Which is the same RAM that you could use as system RAM with many motherboards (e.g. this one). I don't see why the RAM would be faster on the video card than in the main system...?

                You are correct that those systems are using DDR RAM. But graphics cards (including the cards in those machines) use other, more expensive, faster RAM, like GDDR3.
        • Actually only the size of the frame buffer is multiplied, i.e. a scene at 1024x768x32 bit would take 3 MB without anti-aliasing, and at 1600x1200x32 bit 7.3 MB. With 4xFSAA those scenes would take 12 MB and 29.2 MB respectively. The rest of the memory is used for texture & vertex data, and other miscellaneous stuff like shaders. Those don't grow in size with the display resolution.
        • Re: (Score:3, Informative)

          by 644bd346996 (1012333)
          Having the GPU on the same chip or die as the CPU would reduce the latency by several orders of magnitude and allow a much higher clock for the bus between the two. The memory access could also be improved dramatically, depending on how it was implemented.

          I think the first example of this integration we see will use the HyperTransport bus and a single package with CPU and GPU on different dies, though fabbed on the same process. This could be done with an existing AMD socket and motherboard.

          Before this happ
    • by LWATCDR (28044) on Friday October 20, 2006 @12:39PM (#16517749) Homepage Journal
      Well think of it like floating point.
      At one time floating point was done by software it still is one some cpus.
      Then floating point co-processors became available. For some applications you really needed to speed up floating point so it was worth shelling out the big bucks for a chip to speed it up. This is very similar to what we have now with graphics cards.
      Finally CPUs had floating point units put right on the die. Later DSP like instructions where added to CPUs.

      We are getting to the point where 3d graphics are mandatory. Tying it closer to the CPU is now a logical choice.
      • by TheRaven64 (641858) on Friday October 20, 2006 @12:55PM (#16517931) Journal
        It's not just floating point. Originally, CPUs did integer ops and comparisons/branches. Some of the things that were external chips and are now found on (some) CPU dies include:
        1. Memory Management Units. Even in microcomputers there are some (old m68k machines) that have an off-chip MMU (and some, like the 8086 that just don't have one).
        2. Floating Point Units. The 80486 was the first x86 chip to put one of these on-die.
        3. SIMD units. Formerly only found in high-end machines as dedicated chips, now on a lot of CPUs.
        4. DSPs. Again, formerly dedicated hardware, now found on-die in a few of TI's ARM-based cores.
        A GPU these days is very programmable. It's basically a highly parallel stream processor. Integrating it onto the CPU makes a lot of sense.
        • by LWATCDR (28044) on Friday October 20, 2006 @01:39PM (#16518555) Homepage Journal
          Exactly.
          I was using floating point as an example.
          I don't know if Nvidia can pull this off without a partner. Too build a really good X86 core isn't easy. I wonder if they may not do a PPC or Arm core instead. That could make nVidia a big player in the cell phone and mobile video market. At some point there will be portable HD-DVD players.

          My crystal ball says.
          AMD will produce these products.
          1. A low end CPU it integrated GPU for the Vista market. This will be a nice inexpensive option for home and corporate users. It might also end up in some set-top boxes. This will the next generation Geode.
          2 A family of medium and high end video products that use Hyperchannel to interface with Opteron and Athlon64 line.

          Intel will
          Adopt Hyperchannel or reinvent it. Once we hit four cores Intel will hit a front bus wall.
          Intel will produce a replacement for the Celeron that is Duo2Core with integrated graphics on one die. This is to compete with AMD new integrated solution.
          Intel will not go in to the high end graphics line.

          nVidia will fail to produce an X86+GPU to compete with AMD and Intel.
          nVidia produces an integrated ARM+GPU and dominates the embedded market. Soon every cellphone and media player has an nVidia chipset at it's heart. ARM and nVidia merge.

          Of course I am just making all this up but so what, electrons are cheap.
        • by NerveGas (168686)
          I'm not sure if it does. Modern GPUs occupy a large die, run at slow clock speeds, and have an enormous transistor count. CPUs, on the other hand, have fewer transistors, smaller dies, and higher clock speeds.

          Your CPU isn't going to work well at the 200-400 MHz of a GPU, and you're not going to make a huge GPU die run at 2 GHz to get your CPU to work well. I think that their CPUs will be closer to Via's C3 than a P4/Athlon 64.
          • by joto (134244)
            Now, I'm not a hardware engineer, but I fail to see why having different parts of a chip running at different clock-speeds is such a big issue. After all, what you need in your example above, is a circuit that counts to somewhere between 5 and 10 before you send out a clock-pulse. I don't think that's to complicated to put on a chip that is intended to include both a modern CPU and GPU.
        • by dargaud (518470)
          I have a general question relating to this. How can you compile a program that stays compatible with all those kinds of processor 'options' ? It's been a while since I last did some compiler work (okay, 15 years), but how can you have a program that uses FPU instructions if there's an FPU coprocessor or on-die available and and still work if not, and so on for GPU, DSP, SIMD, etc... Do you have tests and branches each time one of those instructions should be used that uses a library if not available ? In th
          • by Intron (870560) on Friday October 20, 2006 @02:58PM (#16519787)
            Typically, unimplemented instructions cause an exception. The operation can then be emulated in software.
          • by joto (134244) on Friday October 20, 2006 @03:25PM (#16520173)
            There are a couple of strategies:
            1. Write a specialized program that will only run at a single computer, the one the programmer owns, as everything is specialized and optimized for his/her hardware. If other people needs to run the program, write a new one, or at the very least use some other compiler options.
            2. Don't use non-portable features. Always go for the lowest common denominator.
            3. Manually testing for existence of coprocessor at each FPU instruction, branch to emulator if FPU doesn't exist.
            4. Same as above, but tests are inserted automatically by the compiler.
            5. Test for existence of coprocessor at start of program execution. If FPU doesn't exist, dynamically replace all FPU instructions with branches to emulator routines
            6. Same as above, but done automatically by the OS program loader
            7. Make it mandatory for CPUs to: either support the FPU instructions (with a coprocessor if necessary); or to issue some sort of trap/interrupt that can be used by software such as the OS kernel/libc to use an emulator routine instead.

            I believe the last option (option 7) is what x86/87 CPU/FPU combo actually used. That's why there is a coprocessor-prefix in front of the FPU instructions. They are not just unused opcodes.

            Option 5 (and sometimes even 3) is commonly used for MMX/3dNOW/SSE/SSE2/SSE3/whatever instructions.

            Unless they *really* need nonportable features, most programmers tend to go with option 2.

      • by arth1 (260657) on Friday October 20, 2006 @01:24PM (#16518355) Homepage Journal
        At one time floating point was done by software it still is one some cpus.
        Then floating point co-processors became available. For some applications you really needed to speed up floating point so it was worth shelling out the big bucks for a chip to speed it up.

        Then people started using floats for the convenience, not because the accuracy was needed, and performance suffered greatly as a result. Granted, there are a lot of situations where accuracy is needed in 3D, but many of the calculations that are done could be better done in integer math and table lookups.
        Does it often matter whether a pixel has position (542,396) or (542.0518434,395.97862456)?
        Using a lookup table of twice the resolution (or two tables where there's non-square pixels) will give you enough precision for pixel-perfect placement, and can quite often speed up things remarkably. Alas, this, and many other techniques have been mostly forgotten, and it's easier to leave it to the MMU or graphics card, even if you compute the same unneccessary calculations and conversions a million times.

        Fast MMUs, CPU extensions and 3D graphics routines are good, but I'm not too sure they're always used correctly. Does a new game that's fifty times as graphically advanced as a game from six years ago really need a thousand times the processing power, or is it just easier to throw hardware at a problem?
        • by LWATCDR (28044) on Friday October 20, 2006 @01:45PM (#16518629) Homepage Journal
          I am an old school programmer so I tend to use ints a lot. The sad truth if that float using SSE are as fast and sometimes faster than the old tricks we used to avoid floats!
          Yes we live in an upside down world where floats are faster than ints some times.
           
        • Re: (Score:3, Informative)

          by daVinci1980 (73174)
          Does it often matter whether a pixel has position (542,396) or (542.0518434,395.97862456)?

          Yes. It absolutely matters. It makes a huge difference in image quality.

          It matters when we go to sample textures, it matters when we enable AA, it matters.
          • Re: (Score:3, Informative)

            by arth1 (260657)
            Yes. It absolutely matters. It makes a huge difference in image quality.

            No, it doesn't. Note that I said pixel, not coordinate.
            The coordinates should be as accurate as possible, but having a pixel more accurate than twice the resolution of the display serves very little purpose.
            • Re: (Score:3, Informative)

              by daVinci1980 (73174)

              You'd be mistaken [virginia.edu]. See the slide on Texture Mapping.

              Perspective divide is performed before texture sampling. This is necessary to get proper texture step sizes, for correct sampling of the texture onto the pixel.

              Fractional pixel locations are also used in antialiasing.
        • by Sycraft-fu (314770) on Friday October 20, 2006 @03:05PM (#16519905)
          1) Processors are wicked fast at floating point these days. Have a look at the benchmarks a modern chip using SSE2 can do some time. Integer doesn't inherently mean faster, and chips these days have badass FPUs.

          2) For many things, it DOES make a difference. You might ask why do we need more than 24-bit (or 32-bit if you consider the alpha channel) integer colour? After all, it's enough to look highly realistic. Yes well that's fine for a final image, but you don't want to do the computation like that. Why? Rounding errors. You find that with iterative things like shaders doing them integer adds up to nasty errors which equals nasty colours and jaggies. There's a reason why pro software does it as 128-bit FP (32-bits per colour channel) and why cards are now going that way as well.

          3) In modern games, everything is handled in the GPU anyhow. The CPU sends over the the data and the GPU does all the transform, lighting, texturing and rasterizing. The CPU really is responsible for very little. With vertex shaders the GPU even handles a good deal of the animation these days. The reason is that not only is it more functional but it's waaaaay faster. You can spend all the time you like trying to make a nice optimised integer T&L path in the CPU, the GPU will blow it away. You actually find that some older games run slower than new ones because they rely on the CPU to do the initial rendering phases like T&L before handing it off, whereas newer games let the GPU handle it and thus run faster even though having higher detail.
        • by joto (134244)

          Does it often matter whether a pixel has position (542,396) or (542.0518434,395.97862456)?

          Per definition, no.

          But does it matter whether the programmer has to create and populate lookup-tables, with lots of manual tweaking to find the right compromize between memory usage (cache issues), few branches (lookup must be fast), accuracy (lookup must be correct), etc... when the alternative is to simply call sin(x)?

          Alas, this, and many other techniques have been mostly forgotten, and it's easier to leave it

    • Re: (Score:3, Interesting)

      by Ryan Amos (16972)
      It is; but if you combine them on the same die with a large shared cache and the on-chip memory controller... you can see where I'm going with this. Think of it as a separate CPU, just printed on the same silicon wafer. That means you only need 1 fan to cool it and you can lose a lot of heat producing power management circuitry on the video card.

      Obviously this is not going to be ideal for high end gaming rigs; but it will improve the quality of integrated video chipsets on lower end and even mid range PCs.
      • Re: (Score:3, Informative)

        by MojoStan (776183)

        ... if you combine them on the same die with a large shared cache and the on-chip memory controller... you can see where I'm going with this. Think of it as a separate CPU, just printed on the same silicon wafer. That means you only need 1 fan to cool it and you can lose a lot of heat producing power management circuitry on the video card.

        Obviously this is not going to be ideal for high end gaming rigs; but it will improve the quality of integrated video chipsets on lower end and even mid range PCs.

        Do y

    • They are merging them, but I doubt one cpu will do both. This will be more like 2 cores where 1 core does sequential instruction processing, and other is a more vector processor where you have to do the same operation over a lot of data. Sounds pretty interesting since you will be able to use the vector processor as a more general purpose cpu to do other things. The challenge will be solving the problem of cores competing for the bus bandwidth.
    • by mikael (484)
      What I don't understand is that I thought GPUs were made to offload a lot of graphics computations from the CPU. So why are we merging them again? Isn't a GPU supposed to be an auxillary CPU only for graphics? I'm so confused.

      GPU's are so powerful now, that some of the latest high-end scientific visualisation applications will actually do calculations on a supercomputer, transfer the data across to a PC, and then use the CPU to process the data so it can be visualised on the GPU in real-time. Similarly for
    • Re: (Score:3, Informative)

      What I don't understand is that I thought GPUs were made to offload a lot of graphics computations from the CPU. So why are we merging them again? Isn't a GPU supposed to be an auxillary CPU only for graphics? I'm so confused.

      You're partially right. GPUs were made to execute the algorithms developed for graphically-intensive programs directly in silicon... thus avoiding the need to run compiled code within an operating system, which entails LOTS of overhead. Being able to do this directly on dedicated h

    • by *weasel (174362)
      Having a specialized GPU made sense when processors were single-core.

      Now that processors have multiple cores, many of which are left looking for a job to do - it makes sense to bring the GPU back to the main die.

      The result will produce an immediate performance boost for Joe Sixpack, at lower manufacturer cost.
    • Re: (Score:3, Interesting)

      by nine-times (778537)

      What I don't understand is that I thought GPUs were made to offload a lot of graphics computations from the CPU. So why are we merging them again? Isn't a GPU supposed to be an auxillary CPU only for graphics? I'm so confused.

      You've already gotten some good answers here, but I'll throw in something that I haven't seen anyone else mention explicitly: GPUs aren't only being used for 3D animation anymore. GPUs started because, in order to make graphics for games better, you needed a specialized processor to

    • Re: (Score:2, Insightful)

      by FlyingGuy (989135)

      As other have replied its all about the bus speed. The amount of time it takes to move data from chip to chip can insert enormous overhead.

      Think back a little to the DEC Alpha. Now the ALPHA chip in and of itself was not really that remarkable. What was so VERY remarkable about the Alpha system was its bus switching. It was blazingly fast and could handle monster amounts of data from main memory to CPU, GPU, etc. The reason ( mostly ) that its now sitting in HP's vault is that the bus switch was/is re

    • Once upon a time, there were mainframes, and computing was good. Only it was only good for large universities, governments, and a handful of corporations.

      Then, there came minicomputers. Fewer components meant smaller machine with smaller prices. Banks, small colleges, and even some high schools got into the game. My high school had an AS/400.

      Then came the micros. These are what we call PCs now. They started as hobbyist toys. Then, the chips got more powerful and more memory was put in them, and they started
  • by purpledinoz (573045) on Friday October 20, 2006 @12:30PM (#16517637)
    AMD and Intel have their own fabs that are at the leading edge of semiconductor technology. I highly doubt that nVidia will open up a fab for their chips. But who knows, IBM may produce their chips for them.

    I think the better option would be to have a graphics chip fit into a Socket 939 on a dual socket motherboard, with an AMD chip. It will have a high-speed link through hyper-transport, and would act just like a co-processor. I'm no chip designer, so I have no idea what the pros/cons of this are, or if it's even possible.
    • by drinkypoo (153816)
      You'd also need more hardware on the board, like the video memory and the RAMDAC, not to mention the ports to plug in your display. Those could be on a riser, though, and expressed like any slot card, including the DAC.
    • AMD and Intel have their own fabs that are at the leading edge of semiconductor technology. I highly doubt that nVidia will open up a fab for their chips. But who knows, IBM may produce their chips for them.
      Why not just stick with TSMC? It's not like TSMC doesn't also have a few gagillion dollars to spend on process development. Is there something wrong with Nvidia's current chips?
  • How much heat do integrated graphics solutions put out?

    I can't imagine it is that much
    (since they mostly suck)
  • With integration.. (Score:3, Interesting)

    by Hangin10 (704729) on Friday October 20, 2006 @12:30PM (#16517643)
    With this integration, does that mean a standard for 3-d? No more Nvidia/ATI drivers. The OSDEV guys would love this if it came to that. But how would this integration work? A co-processor space like MIPS? If so, does that mean that graphics calculations have somewhat been moved back to the CPU? And what about the actual workings itself, I'm guessing the actual registers would still be memory mapped in someway (or I/O ports for x86, whatever).

    I'm thinking way too much. It did alleviate boredom for about a minute though...
  • by Salvance (1014001) on Friday October 20, 2006 @12:32PM (#16517661) Homepage Journal
    Unless Nvidia is partnering with Intel to release this chip, I think they're getting too far out of their confort zone to be successful. Sure, a dual or even quad core chip with half of the cores handling graphics would be great, but can Nvidia deliver? I doubt it ... look how many companies have gone down the tubes after spending millions/billions after trying to make an x86 compatible chip, let alone trying to integrate top end graphics as well.

    Nvidia is a fantastic graphics card company - they should continue to innovate focus on what they're good at rather than try to play follow the leader in an arena they know nothing about.
    • by TheRaven64 (641858) on Friday October 20, 2006 @01:07PM (#16518113) Journal
      The thing is, it doesn't need to be a very good x86 chip. Something like a VIA C7 is enough for most uses, if coupled with a reasonable GPU. I can imagine something like this being very popular in the sub-notebook (which used to mean smaller-than-letter-paper but now means not-as-fat-as-our-other-products) arena where power usage is king. If the CPU and GPU are on the same die then this gives some serious potential for good power management, especially if the memory controller is also on-die. This makes for very simple motherboard designs (and simple = cheap), so it could be very popular.
      • The thing is, it doesn't need to be a very good x86 chip. Something like a VIA C7 is enough for most uses, if coupled with a reasonable GPU.
        Especially if they just shove several of them together onto the die. Everyone is going to be focusing more on software that can take advantage of multiple CPUs for the next couple of years, and nVidia can ride the coattails of that with a nice, simple in-order-execution design. Put 16 or so of those onto your chip with a good GPU, and you might get pretty good perform
      • CPUs are very important for good games, and only getting more so. You think MS paid for a 3 core PPC CPU in the 360 for fun? If a low power cheap part would do the trick, they'd have jumped on it.

        Even after you've offloaded all the graphics, there's still a ton to be done. AI, physics, and sound to name just three. Fire up a copy of Oblivion some time and you'll be amazed how hard it hits the CPU. It even makes use of dual cores, if they are available. Yes, a prime factor in game speed is having a GPU that
        • Not every computer is for games, you know. Not even more than like 10%. The cheap Wal*Mart Special, the mass produced home/corporate desktop, is where the real money is.
          • Don't need good graphics. An Intel GMA950 does just fine for desktop use. Hell, it actually can play older games, and is enough to handle AeroGlass in Vista.

            The problem is the GP seems to think that nVidia would have a viable market combining their excellent graphics chips with shitty processors. Nope, not so much. If you want a good graphics card, you pretty much by definition also want a good processor. There are actually plenty of people who can use a good processor and have no need for a good video card
  • I smell a pattern (Score:3, Interesting)

    by doti (966971) on Friday October 20, 2006 @12:32PM (#16517673) Homepage
    There seems to be a cycle of integrating and decoupling things.
    We had separated math co-processors, that later were integrated in the CPU.
    Then the separated GPU, which will soon be integrated back too.
  • by cplusplus (782679) on Friday October 20, 2006 @12:35PM (#16517709) Journal
    GPUs are going the way of the math co-processor. I think it's inevitable.
  • patents (Score:2, Insightful)

    by chipace (671930)
    It's quite clear that the AMD-ATI merger was to aquire the IP and expertise necessary to integrate gpu core(s) on the same die as cpu core(s). Nvidia does not have to actually market a design, but rather patent some key concepts, and this could provide revenue or protection.

    I would very much doubt that they could compete with AMD and Intel who have already patented many x86 cpu concepts.

    It's a shame that Intel has decided not to buy nvidia, and go it alone with it's own design staff.
  • Thank MicroSoft (Score:5, Interesting)

    by powerlord (28156) on Friday October 20, 2006 @12:43PM (#16517811) Journal
    Okay, I admit, I haven't RTFA yet, but if GPUs do get folded back into CPUs, I think we need to thank MS.

    No. ... Seriously. Think for a minute.

    The major driving force right now in GPU development and purchase are games.

    The major factor that they have to contend with is DirectX.

    As of DirectXv10. A card either IS, or IS NOT compliant. None of this "We are 67.3% compliant".

    This provides a known target that can be reached. I wouldn't be surprised if the DirectX10 (video) featureset becomes synonymous with 'VGA Graphics' given enough time.

    Yeah, sure, MS will come out with DX11, and those CPUs won't be compatible, but so what?, If you upgrade your CPU and GPU regularly anyway to maintain the 'killer rig', why not just upgrade them together? :)
    • by Kjella (173770)
      If you upgrade your CPU and GPU regularly anyway to maintain the 'killer rig', why not just upgrade them together? :)

      Don't know about you, but for me graphics and CPU still aren't in sync. I imagine for most gamers it's still that way. More often than not you want to swap your graphics card, and your CPU *only* if it's holding back the GPU, which is far from always. I'd say you can at least live two generations of GPU cards on the same CPU. Still, for the "all-in-one" market that wouldn't go off buying a se
    • by asuffield (111848)

      As of DirectXv10. A card either IS, or IS NOT compliant. None of this "We are 67.3% compliant".

      While this is a deliberate feature of DirectX, it's nowhere near as useful as you suggest. What is specified and complied with is the set of instructions which the card will accept. What is not specified is what it will do with those instructions - a card is considered to be DirectX compliant even if it has many rendering errors in the output. GPU makers can and do take a great many liberties with this, and that's

  • by sudog (101964) on Friday October 20, 2006 @12:56PM (#16517939) Homepage
    Why is everyone getting excited about this? Now we're going to have a CPU that's only partially documented, and we lose even moreso to closed-source blobs.

    This isn't a good thing unless they also release documentation for it!
  • by Orange Crush (934731) on Friday October 20, 2006 @01:04PM (#16518065)
    The article is from the Inquirer, so a dash of salt might make this more palatable.

    I prefer my articles with a dash of accuracy.

  • Niche market? (Score:4, Insightful)

    by gstoddart (321705) on Friday October 20, 2006 @01:08PM (#16518117) Homepage
    Will dedicated graphics cards become a niche product for enthusiasts and pros, like audio cards already largely have?

    Haven't they already???

    The vast majority of machines (at least, from my experience, which could not be broad enough) seem to be shipping with integrated graphics on the motherboard. Certainly, my last 3 computers have had this.

    Granted, I buy on the trailing edge since I don't need gamer performance, but I kind of thought most consumer machines were no longer using a separate graphics card.

    Anyone have any meaningful statistics as opposed to my purely anecdotal observations?
    • Re: (Score:3, Insightful)

      by gbjbaanb (229885)
      Its hardly a niche market - every server wants onboard graphics, mainly because they don't need to be superpowerful. I imagine this is similar - a low-powered CPU on the same chipset as the graphics chip (and no doubt the network chip) would make making motherboards a bit cheaper, or give them more capabilities that they currently have to have managed with software installed as a driver.

      I really doubt the CPU part is going to compete with the latest super-quadcore chips from AMD or Intel, so no-one will us
      • by gstoddart (321705)

        I really doubt the CPU part is going to compete with the latest super-quadcore chips from AMD or Intel, so no-one will use it for a mainstream computer.

        What about the latest quad-core chips are mainstream??? Those are specialty products if there ever was a specialty product. Except for high-end gamers and people doing really specialized tasks, who actually needs one of them? I bet I couldn't tax one for anything I do.

        Nowadays, so many motherboards have video, lan, sound, IDE controller, possibly RAID, an

  • by Animats (122034) on Friday October 20, 2006 @01:10PM (#16518147) Homepage

    I've been expecting this for a while, ever since the transistor count of the GPU passed that of the CPU. Actually, I thought it would happen sooner. It's certainly time. Putting more transistors into a single CPU doesn't help any more, which is why we now have "multicore" machines. So it's time to put more of the computer into a single part.

    NVidia already makes the nForce line, the "everything but the CPU" part, with graphics, Ethernet, disk interface, etc. If they stick a CPU in there, they have a whole computer.

    Chip designers can license x86 implementations; they don't have to be redesigned from scratch. This isn't going to be a tough job for NVidia.

    What we're headed for is the one-chip "value PC", the one that sits on every corporate desk. That's where the best price/performance is.

    • by LesPaul75 (571752)
      Well, the thing about a high-end CPU is that it's something like 80% custom logic, where a GPU is much more "standard cell" design. So the fact that NVIDIA is good at GPUs with lots of transistors doesn't mean that it will be easy for them to build a CPU. It will be very difficult to build something competitive with Intel and AMD. But if anyone out there right now has a shot at it, it's NVIDIA. Licensing of the x86 architecture is going to be a sticky issue.

      Something that's interesting about this, if t
    • by ceoyoyo (59147)
      The problem with gluing the GPU and CPU together is that it'll be a humongous chip, with low yields and therefore very expensive -- more expensive than a comparable CPU and GPU separately.

  • by DeathPenguin (449875) * on Friday October 20, 2006 @01:23PM (#16518345)
    When I saw this headline I immediately thought of this article [wired.com], an interview with Jen-Hsun Huang (CEO: nVidia) by Wired dated July '02. In it, the intention of overthrowing Intel is made quite clear, and ironically enough they even mention the speculation from a time when it was rumored that nVidia and AMD would merge.

    It's actually a very good article for those interested in nVidia's history and Huang's mentality. Paul Otellini [intel.com] ought to be afraid. Very afraid.
  • by Etyenne (4915)
    Will dedicated graphics cards become a niche product for enthusiasts and pros, like audio cards already largely have?

    It already is.

  • "what other prospects could a solution like this have?"

    Duh. Gaming consoles. Add memory, a sound controller, and some sort of storage, and you're in business.

  • There's certain advantages to having (A) the GPU functionality integrated in the CPU (cost, certain performance aspects, others) and some to having it (B) in a separate GPU (more easily upgraded, more real estate, less heat problems)...

    Every once in a while an unrelated tech innovation comes around that benefits (A) or (B) in some indirect fashion. It could be faster bus speeds, more sophisticated GPU instruction sets, etc etc etc. Doesn't really matter what they are, but they happen all the time and each m
  • Integration is the key to cost reduction, performance improvement and power efficiency.

    L2 cache used to be external. Then they integrated it when technology and performance allowed. L3 cache then became external while L2 was integrated; now you can buy processors with all this inside. Put the memory controller inside the CPU and you no longer need to spread out high (er than CPU core voltage) IO lines with nasty length requirements between Northbridge and CPU, and can clock the bus faster. Put the ethernet
  • If you could preload half the code you run on the CPU over to a CPU/GPU chip, and cut down buss use by >50% by utilizing a 'smart' GPU chip, this should enhance overall system performance by tons in graphic intensive applications. Not to mention that it simplifies simpler system needs (say embedded or wireless) for smaller systems that require less space but provide required functionality with high graphics performance. Just my thought
  • What if you could put multiple chips like these in one machine?

    They'd probably be obsolete in three months, as opposed to one month ;)
  • Nvidia doesn't really have a choice in this matter. They need to at least explore the option of creating a CPU or be relegated to niche status.

    It's pretty clear that both Intel and AMD are intent on swallowing up the lower 3/4 (hand-waving guess) of the GPU market over the next few years. And I believe that ATI will still be fighting it out at the top end over that remaining 25%.

    That would leave Nvidea as a niche player in the uber high end, making GPUs strictly for graphics professionals and gamers with t
  • Imagine a GPU that plugs into the existing Xeon (Core 2 versions) socket. Now the four-core CPU in the other socket can talk to it over the memory bus. Put a separate bus on the "far side" for the GPU's local memory and/or framebuffer.

Life would be so much easier if we could just look at the source code. -- Dave Olson

Working...