Nvidia's Tesla GPUs are now available for CUDA apps on Amazon's EC2 cloud computing service.
Nvidia is continuing its push into the world of high performance computing, having just announced a deal with Amazon that brings its Tesla GPU line to the company's Elastic Compute Cloud cluster.
The deal will see Amazon EC2 customers offered the option of creating Cluster GPU Instances, on which they can run CUDA code across a massive cluster of Tesla GPUs, paying only for the capacity they need for the duration they need it - a significant saving on buying the GPUs outright.
The Tesla GPUs are the same as those used to power China's Tianhe-1 supercomputer
, which has been officially named the fastest system in the world in this month's TOP500 list.
Speaking of the deal with Nvidia, Peter De Santis, general manager of Amazon's EC2 department, claimed that 'our customers now have the power of high performance computing, the efficiency and speed of GPUs and the highly available, scalable and affordable cloud environment our customers have come to expect from AWS.
Nvidia's Andy Keane, who has lead the company's markedly increased focus on GPGPU computing via its CUDA programming language in the last year, claimed that 'GPU supercomputing, through AWS, gives users a flexible computing facility that allows them to scale their computing needs based on user demand.
The partnership with Amazon marks the first time Nvidia's Tesla GPUs have been made available to users of a cloud computing service. Details on how much an on-demand Tianhe-1 of your very own will set you back, however, have not yet been provided.
Are you impressed that you can now get cloud-based access to the same hardware as powers the world's fastest supercomputer, or just wondering who will make use of the service rather than building their own desk-bound version like the University of Antwerp's FASTRA
? Share your thoughts over in the forums