Tuesday, January 29, 2008

Nvidia to Work on the First Mac GPGPU Architecture

Free Image Hosting at www.ImageShack.us
The General-Purpose Graphics Processing Unit (GPGPU) is a new class of graphics processor that can perform the same logical operations that were reserved for a system's primary CPU
.

These GPGPUs allow the system speed up processing of non-graphics applications and got into the spotlight with the advent of ATI's R600 GPU. Nvidia could not stay away from the boiling pot, so it invented the CUDA (Computer Unified Device Architecture) architecture, currently compatible with the new graphics cards in the GeForce 8 series.

The main idea that lies behind the GPGPU is to use the GPU computing power for non-graphics related actions. These general-purpose processing units are built following a parallel design, so they are the perfect tool for calculations.

Moreover, they can face higher workloads than the common CPUs, such as ray-tracing, scientific computing applications, database operations, cryptography, physics-based simulation engines, and video, audio and digital image processing. The two competing graphics companies figured out that the GPGPU technology can unleash incredible powers, that allow the GPU perform new and (probably) useful tasks.

Nvidia is allegedly working on a GPGPU system to suit Apple's Mac Pro workstations, since these processors boost digital video and audio professionals in sound effects processing, video decoding and post processing. This feature will tie the knots between Apple and Hollywood even tighter than before. Well, this does not mean that just any Mac owner will be able to direct their own version of Star Wars at home, but they will surely be a performance booster.

"In science applications, calculations have seen speed boosts from a 45 times to as much as 415 times in processing MRI scans for hospitals. Increases such as this can mean the difference between using a single system and a whole computer cluster to do the same work", the company says.

There is no word on when the GPGPU-enabled graphics cards will kick in, but it is supposed that Nvidia is working at full load now. We'll have yet to see how capable the Apple – Nvidia affair will be to give birth to a compatible Mac OS X driver to work with the cards.

Nvidia to Work on the First Mac GPGPU Architecture

Free Image Hosting at www.ImageShack.us
The General-Purpose Graphics Processing Unit (GPGPU) is a new class of graphics processor that can perform the same logical operations that were reserved for a system's primary CPU
.

These GPGPUs allow the system speed up processing of non-graphics applications and got into the spotlight with the advent of ATI's R600 GPU. Nvidia could not stay away from the boiling pot, so it invented the CUDA (Computer Unified Device Architecture) architecture, currently compatible with the new graphics cards in the GeForce 8 series.

The main idea that lies behind the GPGPU is to use the GPU computing power for non-graphics related actions. These general-purpose processing units are built following a parallel design, so they are the perfect tool for calculations.

Moreover, they can face higher workloads than the common CPUs, such as ray-tracing, scientific computing applications, database operations, cryptography, physics-based simulation engines, and video, audio and digital image processing. The two competing graphics companies figured out that the GPGPU technology can unleash incredible powers, that allow the GPU perform new and (probably) useful tasks.

Nvidia is allegedly working on a GPGPU system to suit Apple's Mac Pro workstations, since these processors boost digital video and audio professionals in sound effects processing, video decoding and post processing. This feature will tie the knots between Apple and Hollywood even tighter than before. Well, this does not mean that just any Mac owner will be able to direct their own version of Star Wars at home, but they will surely be a performance booster.

"In science applications, calculations have seen speed boosts from a 45 times to as much as 415 times in processing MRI scans for hospitals. Increases such as this can mean the difference between using a single system and a whole computer cluster to do the same work", the company says.

There is no word on when the GPGPU-enabled graphics cards will kick in, but it is supposed that Nvidia is working at full load now. We'll have yet to see how capable the Apple – Nvidia affair will be to give birth to a compatible Mac OS X driver to work with the cards.