May 10, 2013
Australian visual effects company, Animal Logic, is running one of the most powerful supercomputer implementations in Australia. But the firm behind such blockbusters as Legend of the Guardians and the Matrix Trilogy is considering a move to the public cloud to offload some of its rendering work, according to an article in the Sydney Morning Herald.
The paper reports that the digital media house upgraded its older rendering server farm to 450 new HP blade servers with Intel CPUs, giving it a capacity of nearly 10,000 cores in its IBM containerized datacenter, located next to its offices at Fox Studios in Sydney.
Animal Logic also relies on an EMC Isilon clustered storage system that provides about 500 TB of primary data storage.
It's a decent-sized setup to be sure, but lately, it's not keeping up with business growth, at least not during peak times. In the last nine months Animal Logic has taken on big projects like The Great Gatsby, Iron Man 3 and Walking with Dinosaurs for the BBC. The firm handled the extra work by securing additional resources from service provider Steam Engine.
What's attractive about the cloud model is its on-demand nature and elasticity. Because you only pay for what you use, it's possible to turn resources on and off as needed. This makes them a perfect fit for uneven peak workloads.
"We have definitely looked with great interest at Amazon Web Services and what they are offering," Animal Logic head of technical operations, Xavier Desdoigts, told the Sydney Morning Herald. "We are really trying to see whether it make sense for us to use those services."
Desdoigts likes the flexibility of the cloud model and he says the company is considering Amazon Web Services and Rackspace, but that won't stop them from procuring another big on-site system. For company's like Animal Logic, the focus isn't on winning the computing capacity race; it's about being able to service their clients and support the creative process. And that means using the tools available to them in smart ways.
"Will there be a mix of solutions? Absolutely,” notes Desdoigts.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?