Engineers boost computer processor performance by over 20 percent

Feb 07, 2012

Researchers from North Carolina State University have developed a new technique that allows graphics processing units (GPUs) and central processing units (CPUs) on a single chip to collaborate – boosting processor performance by an average of more than 20 percent.

"Chip manufacturers are now creating processors that have a 'fused architecture,' meaning that they include CPUs and GPUs on a single chip," says Dr. Huiyang Zhou, an associate professor of electrical and computer engineering who co-authored a paper on the research. "This approach decreases manufacturing costs and makes computers more energy efficient. However, the CPU cores and GPU cores still work almost exclusively on separate functions. They rarely collaborate to execute any given program, so they aren't as efficient as they could be. That's the issue we're trying to resolve."

GPUs were initially designed to execute graphics programs, and they are capable of executing many individual functions very quickly. CPUs, or the "brains" of a computer, have less computational power – but are better able to perform more complex tasks.

"Our approach is to allow the GPU cores to execute computational functions, and have CPU cores pre-fetch the data the GPUs will need from off-chip main memory," Zhou says.

"This is more efficient because it allows CPUs and GPUs to do what they are good at. GPUs are good at performing computations. CPUs are good at making decisions and flexible data retrieval."

In other words, CPUs and GPUs fetch data from off-chip main memory at approximately the same speed, but GPUs can execute the functions that use that data more quickly. So, if a CPU determines what data a GPU will need in advance, and fetches it from off-chip main memory, that allows the GPU to focus on executing the functions themselves – and the overall process takes less time.

In preliminary testing, Zhou's team found that its new approach improved fused processor performance by an average of 21.4 percent.

This approach has not been possible in the past, Zhou adds, because CPUs and GPUs were located on separate chips.

Explore further: Singing the same tune: Scientists develop novel ways of separating birdsong sources

More information: The paper, "CPU-Assisted GPGPU on Fused CPU-GPU Architectures," will be presented Feb. 27 at the 18th International Symposium on High Performance Computer Architecture, in New Orleans. The paper was co-authored by NC State Ph.D. students Yi Yang and Ping Xiang, and by Mike Mantor of Advanced Micro Devices (AMD). The research was funded by the National Science Foundation and AMD.

Related Stories

Software tool helps tap into the power of graphics processing

May 17, 2010

Today's computers rely on powerful graphics processing units (GPUs) to create the spectacular graphics in video games. In fact, these GPUs are now more powerful than the traditional central processing units (CPUs) - or brains ...

NVIDIA GPUs power world's fastest supercomputer

Oct 29, 2010

(PhysOrg.com) -- NVIDIA has built the worldэs fastest supercomputer using 7,000 of its graphics processor chips. With a horsepower equivalent to 175,000 laptop computers, its sustained performance is ...

Video-game technology may speed development of new drugs

Nov 03, 2010

Parents may frown upon video games, but the technology used in the wildly popular games is quietly fostering a revolution in speeding the development of new products and potentially life-saving drugs. That's the topic of ...

New computer cluster gets its grunt from games

Nov 25, 2009

Technology designed to blast aliens in computer games is part of a new GPU (Graphics Processing Units) computer cluster that will process CSIRO research data thousands of times faster and more efficiently ...

Graphics chips speed up medical imaging

Sep 04, 2009

Beyond just jazzing up video games, one of the growing array of applications being found for the powerful graphics-oriented chips that Nvidia and Advanced Micro Devices sell is in speeding up medical imaging, which can be ...

Recommended for you

CIA director reverses himself on Senate spying

2 minutes ago

For months, CIA Director John Brennan had stood firm in his insistence that the CIA had little to be ashamed of after searching the computers of the Senate Intelligence Committee. His defiant posture quickly ...

Tesla says decision on battery factory months away

8 minutes ago

(AP)—Electric car maker Tesla Motors said Thursday that it is preparing a site near Reno, Nevada, as a possible location for its new battery factory, but is still evaluating other sites.

Taking great ideas from the lab to the fab

11 hours ago

A "valley of death" is well-known to entrepreneurs—the lull between government funding for research and industry support for prototypes and products. To confront this problem, in 2013 the National Science ...

User comments : 3

Adjust slider to filter visible comments by rank

Display comments: newest first

Husky
5 / 5 (1) Feb 07, 2012
i guess this was sofware prefetching to level 1 cache by dedicatred benchmarks, but still good proof of the way to go, now make a hardware predicter/fetcher
gmurphy
not rated yet Feb 07, 2012
Didn't the Itanium architecture aspire towards this?, the concept works well as long as you've got a compiler which can translate from your C code into this parallel execution format, easier said than done, tbh.
CapitalismPrevails
1 / 5 (1) Feb 07, 2012
Maybe we will have duo core CPU GPU core processors in the future.