More Apps Now Support NVIDIA GPU Accelerators

The NVIDIA (News - Alert) family of GPU accelerators, according to company officials, has now become more the versatile with another 70 popular applications announcing support for its GPU acceleration this year. The total number applications available to researchers, engineers and designers are now above 200.

Three of the newest applications to offer GPU acceleration include ANSYS Fluent, which allows engineers to develop more aerodynamic cars and planes. This application can save millions of dollars in fuel expenses. It also includes MSC (News - Alert) Nastran, which is a GPU-accelerated structural mechanics simulation application which companies can improve noise, vibration and harshness (NVH) performance.

Finally, it also includes CHARMM's GPU acceleration, which allows a more accurate study of important proteins involved in disease.

GPU computing is the use of a GPU (graphics processing unit) together with a CPU to improve general-purpose scientific and engineering applications. GPU computing has rapidly become an industry standard, enjoyed by millions of users worldwide and adopted by virtually all computing vendors and is pioneered five years ago by NVIDIA.

“GPU computing first gained momentum among researchers who could download CUDA to accelerate their own applications for scientific discovery and research," said Addison Snell, chief executive officer of Intersect360 Research. "We are now in a new era where more commercial software is GPU-optimized, providing accelerated options across the full spectrum of engineering and business computing.”

Recently, the company introduced the NVIDIA Tesla K20 family of GPU accelerators, which provide improved performance and efficiency in a number of ways. This is the technology that powers Titan, the world's fastest supercomputer. The new Tesla K20 family is armed with the Tesla K20X accelerator; the major product of NVIDIA's Tesla accelerated computing product line. Kepler HPC architecture grants users three times the performance. It is applicable to a broader range of scientific computing applications.