A friend just sent me this article, and it's really interesting. Perhaps it is a repost, but i haven't seen it here before...

http://www.tomshardware.com/hardnew...902_135943.html


Audio supercomputer hidden in your graphics card?

By Wolfgang Gruener, Senior Editor

September 2, 2004 - 13:59 EST

Cambridge (MA) - Nvidia's graphic cards may have much more to offer than simply drawing pixels on the screen: A startup company has found a way to translate audio signals into graphics, run them through the graphics card and overcome a common issue of limited audio effect processing performance in computers.

It is not unusual that professional music artists run into performance barriers even with the most powerful computers today. Multi-track recording still is a challenging and sometimes frustrating task. James Cann from BionicFX in Massachusetts however noticed that audio processing task does not have to happen just in the CPU. His Audio Video Exchange technology (AVEX) converts digital audio in graphics data and then performs effect calculations using the 3D architecture of Nvidia GPUs. Compared to the capability of just six GFlops of a typical CPU, Nvidia's chips can reach more than 40 GFlops, according to Cann.


"This technology allows music hobbyists and professional artists to run studio quality audio effects at high sample rates on their desktop computer," he said. Cann's invention is purely software-based and is not capable substituting a sound chip. The approach exploits the video card 3D chip, which usually is idle when users are working with multi-track recording software. "It's a great resource to use as a coprocessor," Cann said. "AVEX is designed to reduce the CPU load by moving the processing to the video card for certain types of audio effects when making music." Cann said that the technology is purely targeted at music enthusiasts and at this time brings no advantages for applications such as gaming.

But if Cann is right, audio effect processing might be just a starting point how a GPU could be used for other applications. He believes that several other software types could be greatly enhanced in the same way, such as Genomics or SETI. "The GPU has some numeric precision issues that need to be worked out for scientific applications to be possible, but the thought of performing the computations on a resource theoretically capable of 50 and more GFlops of the GPU instead of five GFlops of the CPU is exciting," he said.

So far Cann cannot take as much performance away from the GPU as he would like. "Right now, getting the data back from the video card is very slow, so the overall performance isn't even close to the theoretical max of the card. I am hoping that the PCI Express architecture will resolve this. This will mean more instances of effects running at higher sample rates," he said.

Still, there is significant boost of performance and reduce the load for CPU for people who are using applications such as Cubase, Ableton Live, and other VST compatible hosts. Cann's first commercial application will be BionicReverb, which is expected to go into public and free beta in October. The final version is scheduled to be released at the Winter NAMM Conference in January 2005.

BionicReverb is an impulse response reverberation effect that runs as a plug-in inside VST compatible multi-track recording software. The audio effect is generated by combining an impulse response file with digital audio. Impulse response files are created by firing a starter pistol inside a location, such as Carnegie Hall, and recording the echoing sound waves. Combining the two files through mathematical convolution is a CPU intensive process that is reduced by moving expensive calculations onto the GPU. Amateur and professional guitarists, singers, pianists, and other musicians will be able to create performances in their home or studio that sound exactly like they were recorded in famous locations around the world, according to Cann.

At this time, Cann plans to only support Nvidia graphics cards. "When I started, ATI had a problem with floating point data. I have heard they have resolved it, but I won't have time to purchase and research their newest cards until after this is released," he said.

Pricing was not announced yet, but Cann says he will make his technology available for "far less" than the cost of professional studio DSP solutions which can run into the high five-figure range. He estimates the price will be somewhere between $200-$800.

___________________
http://nyman.stabilt.se
http://www.myspace.com/andersnyman

sounds awesome.

makes me wonder why they didn't think of using the AGP port as a interface for a sound card. It's much faster and we audio ppl don't really care much about graphics!

___________________

'-.SgtFoo.-'
My SoundCloud

Pretty interesting. I wonder if it will overheat the card though with such a workload.

___________________

cool, finally! you can do any maths at all on a GPU, so it's *perfect* for running as an audio DSP.

if you get an nVidia 6800 or better, then you get good floating point precision too.

___________________

Monsoon - Astrosurf

Yay! This will be great for those of us who play games and have good 3d cards (like me). Thumbs up to the guy who invented this.

___________________
America is like a melting pot. The people at the bottom get burned and the scum floats to the top.

Oh sweet maybe I don;t need to get a new comp!!

Well if I remember well, the UAD-1 is based on a video chipset. So the discovery isn't so groundbreaking as they claim. The great trick those guys from BionicFX is just they were able to use the standard GPU and find a trick to process sound with it, and revert it back to the normal state afterwards. That's the genious part of their stuff.

I think the genious is that you don't have to buy a damn UAD1 card!!!What i'm thinking is, what cards this thing will support. I have a feeling that Nvidia is funding this thing(or will buy into) and they are gonna start pushing new cards that are compatible or better for this purpose, and it wont be supported on older cards like me TNT2 Pro.

Don't know the details of BionicFX, but on any GPU with vertex + pixel shaders and render-to-texture you can perform arbitrary maths calculations, all a graphics card is is a super-dedicated parallel maths machine. So the TNT2 probably won't cut it, because although it can can do maths in hardware, it is harder to program ( no programmable shaders )

Also, so far GPUs have used low-precision maths because the output is 8 bits per pixel colour (32 bit colour). They've also had a limit on how many instructions they can perform.

But with the latest cards, i.e the nVidia 6800 and up ( pixel shader 3.0 cards ) you can do full floating point maths, and pretty much an arbitrary amount of calculations. This means they behave pretty much like a general-purpose CPU; only they are heaps more focussed and dedicated to doing massive maths calculations.

For example, there's a couple of games companies out there that are doing physics calculations on the graphics card already.

Good on them (BionicFX) for doing what they are doing! 'tis a fine idea!

___________________

Monsoon - Astrosurf

quote:

Originally posted by SgtFoo sounds awesome. makes me wonder why they didn't think of using the AGP port as a interface for a sound card. It's much faster and we audio ppl don't really care much about graphics!

yes, it is much faster, but the audio does not need that kind of bandwidth.
the speed of PCI bus is 132 megabytes per second - and this is definitely more than enough for any transfer of audio data.
btw, it is pretty hard to find a new pci graphics card nowadays. also, new boards will have new pci-x standard (as a matter of fact, those boards already exist, like Supermicro P4SCT+II).
the problem with audio is processing power of today's cpus, and that's why this is a good idea.
the point is that these guys use nvidia gpu for audio processing (and not agp slot for audio transfer), which is great, but it would be even better that steinberg, or cakewalk or other vst host programmers include this option for their hosts, and to support ati cards. only their plugins will use this, but we still have to see how do those plugins sound. i don't think their convolution reverb will be used more than SIR if it does not sound that good. btw, they are saying the prices of their plugins will be less than the equivalent hardware units - but who can sell a reverb plugin for 500 USD nowadays?

quote:

Originally posted by moth Pretty interesting. I wonder if it will overheat the card though with such a workload.

i think it much less of a workload than running doom3, or deus ex 2
consider this - when you play a game, your card pumps out as many frames as it can - so, basically, when you play any 3d game you put your gfx card to a 100% stress for 3-4-6-whatever hours without stopping. with audio, this does not happen.

Sounds very cool. I hope it will be widely available soon.

___________________



insignificant cor member alliance