5x Speedups with NVIDIA GPU Computing program
Hundreds of Researchers, Scientists Sign Up in Program's First Two Weeks
Hundreds of scientists and researchers around the world have registered for the program since it was announced two weeks ago. Some have achieved 5x application speed-ups in as little as one day of programming.
Directives enable parallel programmers to provide simple hints to the compiler, identifying which areas of code to accelerate, without requiring programmers to modify or adapt the underlying code itself. By exposing parallelism to the compiler, directives allow the compiler to do the detailed work of mapping the computation onto the accelerator.
The program allows users to accelerate their applications on NVIDIA® Tesla™ GPUs using the PGI Accelerator compiler, and guarantees at least 2x speed-up of their applications in four weeks or less. Interested developers can register for a free 30-day trial at the NVIDIA "2x in 4 Weeks. Guaranteed." web site.
Initial results reported by program participants include:
- A postdoctoral fellow at the Netherlands Institute for Radio Astronomy (ASTRON) and the University of Groningen is benefiting in his work to understand the origins of the universe using tens-of-thousands of low-frequency antennas of the LOFAR telescope. Within five days of using directives, he was able to accelerate his image-reconstruction application by 5.6x.
- A global manufacturer of navigation systems is speeding up its research involving algorithms for real-time object detection in image sequences. Using directives and GPUs, a developer accelerated the production application by 5x in one week.
- A postdoctoral researcher at the University of Texas at San Antonio is on a mission to better understand the effects of solvents on proteins. By applying directives, he accelerated his application 5x in a single day.
The "2x in 4 Weeks. Guaranteed." program was designed to prepare developers for the coming wave of directives-based solutions based on the new OpenACC™ parallel programming standard. Announced at SC11 in November, the OpenACC program is designed to enable the millions of scientific and technical programmers to easily take advantage of the transformative power of heterogeneous CPU/GPU computing systems.
The OpenACC standard is anticipated to benefit a broad range of programmers working in chemistry, biology, physics, data analytics, weather and climate, intelligence, and many other fields. Existing compilers from Cray, PGI and CAPS are expected to provide initial support for the OpenACC standard beginning in December 2011, and continuing into 2012.
For more information or to participate in the "2x in 4 Weeks. Guaranteed." program, visit the NVIDIA web site, or download the program FAQ. For more information about OpenACC, visit the OpenACC web site. To learn more about Tesla GPUs, visit the Tesla web site.
Data taken from http://pressroom.nvidia.com/easyir/customrel.do?easyirid=A0D622CE9F579F09&version=live&prid=829921&releasejsp=release_157&xhtml=true Share this post on 5x Speedups with NVIDIA GPU Computing program