Cloud Slam '09 - Cloud Computing Conference

Cloud storage is one of the fastest-growing segments in the storage industry due to its potential for lowering costs, removing the burden of managing and protecting data, and ultimately creating a new “virtual” tier of online storage. It has given rise to multiple innovative architectures, and could well be a harbinger of larger nearline storage trends. In this talk, we'll look at cloud storage architecture across multiple cloud providers, offering a detailed look at the architectural trends and innovations in cloud storage platforms, discussing how the various architectures differ from what end users have in their own data centers. We will also discuss the rise of some of the biggest breakthroughs in cloud storage, integrated content-aware compression and dedupe, which are ways of drastically reducing the space taken to store data, and also to move it across the WAN. The cloud offerings we will take a look at will be from Amazon AWS, Nirvanix, Microsoft, IBM, EMC and others. Some t

Cloud computing and virtualization go hand-in-hand. Virtualization separates the OS/application from the underlying commodity hardware. Yet today’s “clouds” still represent collections of small compute islands; users can choose their “cloud” as some fraction of a size of a standard server, but nothing larger. An enterprise using cloud computing as an IT infrastructure strategy needs true On Demand agility and scalability, where the size of the server provided by the cloud can be easily changed on-the-fly, and should have no limits. This session addresses how networking infrastructure, virtualization and commodity servers are evolving to enable On Demand IT for the cloud, finally enabling the dynamic data center.

Pathwork Diagnostics, Inc. develops molecular diagnostic tests to aid oncologists in the diagnosis of hard-to-identify cancer tumors by analyzing large libraries of gene expression profiles from tumor specimens which require massive amounts of computational power at certain peak times. Looking to avoid a large hardware investment while still meeting its processing needs, Pathwork turned to cloud computing and Univa UD's UniCloud product to build high-performance computing (HPC) clusters in the EC2 cloud, in order to perform their compute-intensive research and to meet peak processing needs – saving on CAPEX and OPEX while increasing the capacity to innovate. A few highlights from the case study: * "Our challenge was a perfect fit for cloud computing." * "Without UniCloud, some of our most advanced research would simply not be feasible." * "We're getting exactly what we need. We pay for HPC power only when we use it, using a cluster management system that's easy to use." * "The