<img src=”http://media2.hpcwire.com/hpcwire/nvidia_gpu_graphic.jpg” alt=”” width=”94″ height=”65″ />This week at NVIDIA’s GPU Technology Conference, the priorities for GPU computing’s future, including providing snappy access to high memory bandwidth, were cited as critical to growing user ranks. The energy consumption, data volume and velocity requirements are giving way to new, more efficient and higher bandwidth approaches, including Volta, which was revealed during the keynote event.
<img src=”http://media2.hpcwire.com/hpcwire/Penguin_Computing_logo_172x.jpg” alt=”” width=”101″ height=”59″ />Penguin Computing keeps finding increasing demand for servers that go heavy on the GPUs (or other coprocessors). Based on feedback from one such customer, it has designed the Relion 2808GT server, which it says now has the highest compute density of any server on the market.
<img src=”http://media2.hpcwire.com/hpcwire/CSCS_Cray_XC30_thumbnail.jpg” alt=”” width=”95″ height=”82″ />During his keynote address for the annual GPU Technology Conference, NVIDIA CEO Jen-Hsun Huang revealed that the Swiss National Supercomputing Center (CSCS) is building Europe’s fastest GPU-accelerated supercomputer, an extension of a Cray system that was announced last year. This will be the first Cray supercomputer equipped with Intel Xeon processors and NVIDA GPUs.
NVIDIA GeForce GRID, a cloud gaming platform announced at the 2012 GPU Technology Conference (GTC), seeks to reduce the the latency associated with cloud gaming.
This week at GTC Asia in Beijing, NVIDIA highlighted a number of young companies making use of GPU computing during its Emerging Companies Summit. The companies selected fit into a range of HPC, cloud and mobile markets that are meeting an ever-expanding array of verticals, both in traditional high performance computing arenas and in broader consumer contexts.
Cloud computing is on the agenda for October’s GPU Technology Conference (GTC ’11) following a year full of news and case studies highlighting GPU-powered cloud resources.
There is increasing convergence between the once disparate worlds of GPUs and HPC. This gap is closing, particularly now that scientific and enterprise users are being granted access to GPU acceleration via on-demand HPC and GPU-driven services. Such offerings are expected to grow along with a rise in the number of applications available, marking what might be a new era for HPC and GPGPU both individually and as a unit.
At this year’s GPU Technology Conference in San Jose, GPU computing in the scientific and technical research space took center stage, almost to the point where it became possible, at least for a moment, to forget the gaming roots and movement from the mainstream to the deeply technical.
The NVIDIA GPU Technology Conference (GTC) kicked off on Tuesday amid a flurry of news that suggests the GPGPU HPC business is quickly moving into the mainstream. After just four years since the introduction of commercial-grade GPU computing, the technology has become firmly established and is poised to spill out across every application domain that has a need for data-parallel computing.