Slashdot Mirror
ATI's 1GB Video Card
Signify writes "ATI recently released pics and info about it's upcoming FireGL V7350 graphics card. The card features 1GB of GDDR3 Memory and a workstation graphics accelerator. From the article: 'The high clock rates of these new graphics cards, combined with full 128-bit precision and extremely high levels of parallel processing, result in floating point processing power that exceeds a 3GHz Pentium processor by a staggering seven times, claims the company.'"
- You have an OpenGL driver for the GPU and a JIT for shader language programs. This means you can completely throw out the instruction set between minor revisions if you want to. An x86 CPU must mimic bugs in the 486 to be compatible with software that relied on them.
- You have an easy problem. Graphics processing is embarrassingly parallel. You can pretty much render every pixel in your scene independently[1]. This means that you can almost double the performance simply by doubling the number of execution units. To see how well this works for general purpose code, see Itanium.
- The code you are running is fairly deterministic and unbranching. Up until a year or two ago, GPUs didn't even support branch instructions. If you needed a branch, you executed both code paths and threw the result you didn't need away. Now, branches exist, but they are very expensive. This doesn't matter, since they are only used every few thousand cycles. In contrast general purpose code has (on average) one branch every 7 cycles.
GPUs and CPUs are very different animals. If all you want is floating point performance, then you can get a large FPGA and program it as an enormous array of FPUs. This will give you many times the maximum theoretical floating point throughput of a 3GHz P4, but will be almost completely useful for over 99% of tasks.[1] True of ray tracing. Almost true of current graphics techniques.
I am TheRaven on Soylent News
ATI's opengl drivers are flakey on their non firegl line of cards. Some suspect thats by design.
Graphic card makers should get with the program and stop releasing firegl's and quadros. Just release really kick ass 3d accelerators for all.
That way we can all have full opengl support and not the lame opengl game drivers by ATI. Nvidia's gaming card opengl drivers are better than ATIs
This is a workstation card, not a games card. The people buying this are likely to be either CAD/CAM people with models that are over 512MB (the workstation it plugs into will probably have a minimum of 8GB of RAM), or researches doing GPUPU things. To people in the second category, it's not a graphics card it's a very fast vector co-processor (think SSE/AltiVec, only a lot more so).
I am TheRaven on Soylent News
Appreciate the joke, but for folks out there who think he is serious, Microsoft has said that the Intel GMA 900 and ATI Radeon X200 are the minimum graphics cards for using the "new" DirectX GUI. Vista will work on computers with less graphics systems, but in a compatability mode similar to Windows XP's GUI.
Explained in detail above. Suffice it to say that CPUs and GPUs are radically different. With GPU's, ATI can throw out old architectures and create new ones whenever they want (quite often). Since the hardware is accessed by a driver, the user isn't limited in what programs they can use. With CPU's, everyone is stuck with x86, which was invented in the 1980s. You can't break compatability with x86. GPUs do mostly simple floating point calcuations. Therefore, they are basically massively parallel FPUs. If they need to do a non-floating point calculation, they are quite slow. CPUs can do floating point calculations, but also many other types of calculations, and are about equally good at everything. For the sake of heat, power consumption, size, and cost, the FPU on a CPU is not nearly as large as a GPU. If each processing unit on a CPU was the size/power of a specialized processor (GPU, ect...), the chip would be gigantic, and so would be hard to make, expensive to buy, consume massive amounts of power, and emit unimaginable heat.
Ok, I cannot beleive the absurd number of posts I am seeing from lamers who think this thing is for video games. Hello People! Both ATI and NVidia have had seperate high-end workstation lines for years now! This is nothing new. Where have you people been?
This card is for people who need serious rendering of high detailed scenes and 3D objects, not serious frame rates for games. For applications where image quality, complexity, and accuracy are much more important than frame rate. The GPUs in these high end workstation cards are geared in a totaly different manner and actually suck for video games! These are great for CAD/CAM, medical imaging (like from CAT and EBT scanners), chemical modeling, and lots of other hard core scientific and 3D developement type stuff.
However, how difficult would it be to write an operating system that offloaded floating point operations to the GPU, and everything else to the CPU.
Funny you should mention that. The Intel 386 (and up) architecture has built in support for a floating point coprocessor, so it can offload floating point operations. In the early days, you could buy a 387 math coprocessor to accelerate floating point performance. Then Intel integrated the 387 coprocessor onto the 486 series cpus, and today we just know it as "the floating point unit" (although it's been much revised, parallelized, and super-scaled).
As for offloading to a GPU, well... that's what we do today. It's called Direct3D, or Mesa, or Glide, or your favorite 3D acceleration library. The problem with this approach is that it requires very specialized code. It's not something that can be automatically done for just any code, as the overhead of loading the GPU, setting up the data, and retrieving the results would far exceed the performance gains. In only extereme cases does it pay off: the workload has to be extremely parallelizable, with almost no branching and predictable calculations. Basically what it ends up is that the algorithm has to be extensively tailered to the GPU. Even IBM has had major issues offloading general purpose operations to their special processing units, and those are much more closely coupled to the CPU.