Slashdot Mirror

Isn't this just a driver limitation? Does the AGP bus have a unidirectionality built into it?

There is some serious interest in utilizing graphics hardware for non-graphical computation. The GPU would be treated like a co-processor. It would function in relation to the CPU in a manner analogous to the way MMX, SSE, and Altivec, relate to standard instructions. This site is a kind of focal point for people researching the notion.

Probably something you can find on the General Purpose GPU site.

I've toyed with shaders some and implemented a system for image processing on GPUs. Quite a lot of fun really, though we didn't do any comparisons with CPU to see how much faster it was. (That project isn't published anywhere though.)

is there any Free software capable of exploiting the general computing power of modern video cards?

A quick Googling revealed the following:
- BrookGPU
- GPGPU

This might also be interesting: GPGPU /Arvid

To hell with the die size, check out the power requirements. There's two, TWO! power connectors for that thing. Damn, they've created a monster. I wonder how fast it can run GPGPU apps...

Peercy and Olano (Click on "PDF" in the upper right)

Presentation

ASHLI

GPGPU

More than Moore's Law

Moore's law : still for wimps

Using programmable graphics hardware (possibly through OpenGL) for final rendering is not that far off. (Definitely not in real-time, but as a more cost-effective way to do it, anyway.) Especially with the massive parallelism of rendering, and the fact that GPUs are far outpacing CPUs in terms of their speed and transistor counts.

OpenGL is much more similar to micropolygon rendering (REYES) than it is to raytracing in the first place. The shaders are where you spend all of your time, anyway.

Heck, do you think nVIDIA bought ExLuna (Larry Gritz, author of BMRT, and former Pixar employee) just for the fun of it?

Software for translating from RenderMan Shading Language to Cg?

And what about RenderMonkey supporting RenderMan?

Do you even remember PixelFlow from Pixar? Do you see the name Marc Olano on that paper? The same Marc Olano who talks about rendering on consumer-level graphics hardware? These things have far more in common than you seem to realize.

I thought most renderman stuff was rendered, not raytraced?

I'm sure you've seen the raytracing OpenGL examples such as nVidia's

The OpenGL 1.0 pipeline is great for games, CAD, etc. The future of OpenGL is basically "here is a really powerful parallel processor (AKA pixel shader) and some memory (AKA textures), go use/abuse this in anyway you like."

There are a lot of people working on General Purpose ways to program the GPU/VPU such as BrookGPU. Moving forward graphics chips look less like old style OpenGL where the chip is hardwired to support up to 8 lights, gouraud shading, and a texture, and more like a giant processing farm that will be good at certain tasks (render farm) and worse at others (compile farm). I belive raytracing will be one of the tasks future GPU/VPUs are good at.

Pico-BTX is still a bit bigger than Mini-ITX and it only solves the cooling issue when used in a fairly standard (albeit small) desktop case.

Has anyone figured out how to use the floating point power in their graphics cards for non-video applicaitons?

Actually yes, some people have started doing floating point in graphics cards. Check out what the GP GPU people are doing in this regard. The latest and greatest GPUs from nVidia and ATI actually offers a LOT of theoretical processing power, significantly more than the latest P4 or Opteron chips (or IBM PPC 970/Apple G5 chips for that matter). They also offer a whole boatload of memory bandwidht, another very important consideration for FP work.

There are some downsides though. First off GPUs are essentially vector processors. This is not necessarily a bad thing (the fastest supercomputer in the world, Earth Simulator, uses vector processors), but some code does not lend itself well to vector processing and other code needs to be reworked. Perhaps a bigger concern is that GPUs only handle single-precision floating point. This is perfectly acceptable for the purpose they were designed for, but they could cause problems for more general pupose FP work which sometimes requires double precision FP. There's also the issue of non-ECC memory on the cards.

Still, they are interesting from an academic point of view. Of course, on the other hand, CPUs have started incorporating some vector processing aspects of their own. SSE/SSE2 and Altivec are designed as vector processing units as well.

There actually IS a way to do math on GPUs, take a look at what these people are doing. I don't know if there is any software yet that will run on Macs and OS X, I think most of it is targeting PCs running Linux, but at least in theory you can do some some pretty high performance math on GPUs.

Of course, there are some downsides to this. First off, it only works on the latest and greatest generation of GPUs that are programable (the Radeon 9600 should qualify here). Second, GPUs only support single-precision floating point math, not the double-precision needed by a lot of complex computing. Third, GPUs are rather powerful vector processors, which are somewhat different than general purpose processors. This is not entirely a bad thing, the Earth Simulator is a giant vector processor as well, but some applications don't work as well on vector processors.

www.gpgpu.org

Very cool. Vector/Graphics processors could one day overtake General processors. They are way more energy efficient too.

• 25 gigaflop CS301 clearspeed vector microprocessor
• clearspeed
• General Purpose Computation Using Graphics Hardware -Gpgu.org
• Is it behind IBM's cell processor ??? hmmmm
• IBM and Texas University's Trips 1 trillion ips vector processor

Here's the link.

graphics cards as general processors

Graphics cards used for general computing

Graphics cards used for general computing

The chip is a vector processor like major 3d graphics cards.

It's a great idea and something that people on slash ,including me,have talked about everytime a powerful graphics card has come out.

The compiler will be key.

Anything that can steal the thunder of INTEL & AMD is fine by me. Their processors are heat emitting loads of crap. If you noticed the amount of wattage that this new chip uses , it's because of the architecture and not fancy transistor technology.

Now you all know that Intel , Sun, Ibm, and Amd do not make efficient processors.