Sign up for our newsletter and get the latest HPC news and analysis.

A Big Step Toward Exascale Application Programmability and Performance

On May 15, 2012, NVIDIA announced several innovative technologies aimed at improving the performance and energy efficiency of the Kepler GPUs, along with opening up a new class of applications and algorithms – creating a larger ecosystem of developers and applications for the GPU landscape.

Two of these innovations in particular caught our attention.

The first is Hyper-Q—a technology that enables multiple CPU cores to simultaneously use the CUDA architecture cores on a single Kepler GPU. The idea here is to dramatically increases GPU utilization while slashing CPU idle times and advancing programmability. Hyper-Q is enabled in CUDA 5, and we can expect to see it used heavily with standard MPI codes. Hyper-Q offers great promise for dealing with concurrency issues as we scale to much larger systems.

There is more to this article: The Exascale Report is premium content. To read the rest of this article, please register here. If you were a paid subscriber to the original Exascale Report, you will need to re-register here on insideHPC.
Forgot password?

Resource Links: