Nvidia on Monday announced the availability of its fastest-ever GPU accelerator for supercomputing and high-performance computing (HPC) applications.
The Tesla K40 GPU accelerator has double the memory of the Tesla K20X, until now Nvidia's top GPU accelerator, and delivers a 40 percent performance boost over its predecessor.
'GPU accelerators have gone mainstream in the HPC and supercomputing industries, enabling engineers and researchers to consistently drive innovation and scientific discovery,' Sumit Gupta, general manager of Tesla Accelerated Computing products at Nvidia, said in a statement. 'With the breakthrough performance and higher memory capacity of the Tesla K40 GPU, enterprise customers can quickly crunch through massive volumes of data generated by their big data analytics applications.'
The Tesla K40 is based on Nvidia's Kepler graphics processing architecture and sports 2,880 GPU cores supporting the graphics chip maker's CUDA parallel programming language. The most powerful graphics platform Nvidia has built to date has a whopping 12GB of GDDR5 memory, supports the PCIe 3.0 interconnect, and uses the company's Dynamic Parallelism technology to 'enable GPU threads to dynamically spawn new threads, enabling users to quickly and easily crunch through adaptive and dynamic data structures.'
The Tesla K40 also features a technology familiar to CPU users, the ability to throttle up cores with converted power headroom. Called Nvidia GPU Boost, this user-controlled performance enhancer can 'unlock the untapped performance of a broad range of applications,' according to Nvidia.
The new GPU accelerator is now available but isn't likely to be implemented in working supercomputing and HPC systems for a couple of months. Many of the systems listed on the new Top500 supercomputer list released this week already use the Tesla K20X accelerator.
One of the first Nvidia partners to deploy the Tesla K40 will be the Texas Advanced Computing Center (TACC) at the University of Texas at Austin, which is building a remote visualization and data analysis system called 'Maverick,' scheduled to go online in January.
'The Tesla K40 GPU accelerators will help researchers crunch through massive volumes of big data and gain new insights through large-scale, sophisticated visualizations. With Nvidia GPUs, Maverick will provide researchers powerful interactive capabilities to advance their most complex scientific challenges,' said Kelly Gaither, director of Visualization at TACC.
Teaming Up With Big Blue Meanwhile, Nvidia has also announced a long-term collaboration with IBM to 'supercharge the corporate data center' with the development of GPU-accelerated enterprise software applications run on systems using IBM's Power processors.
Nvidia called the partnership the initial step in bringing GPU accelerator technology 'beyond the realm of supercomputing and into the heart of enterprise-scale data centers' for the first time.
Along with Google, Nvidia was one of the biggest names to sign on with IBM's new OpenPOWER Consortium in August, an effort by the computing giant to rekindle the flagging fortunes of its once-dominant processor architecture through licensing and allowing more third-party insight into the IP than ever before.
'This partnership will bring supercomputer performance to the corporate data center, expanding the use of GPU accelerators well beyond the traditional supercomputing and technical computing markets,' Ian Buck, vice president of Accelerated Computing at Nvidia, said in a statement.
'It will also provide existing supercomputing and high-performance computing customers with new choices and technologies to build powerful, energy-efficient systems that drive innovation and scientific discovery.'
Post a Comment