AWS Official Blog

Launch Cluster Compute instances inside the Virtual Private Cloud

by Jeff Barr | on | | Comments

The AWS team has been at Bio-IT World in Boston this week, hearing from a range of scientists, academics and industry folks about how they are using the cloud to store, process and collaborate around the large volumes of data arriving from sources such as the 1000 Genomes Project. Customers have found that AWS is a good fit for their scientific computing needs, with available storage, compute and database services providing the building blocks for many of the fantastic tools powering modern research.

We launched the second generation of our high performance computing instance type, cc2.8xlarge, in November 2011 to support these kinds of workflows. This instance type is designed to address the needs of customers who want to run tightly coupled supercomputing applications in the elastic environment of the AWS cloud. Not only are they deployed on a high speed, full-bisection bandwidth 10 gigabit ethernet but they sport the fire breathing Intel Xeon E5 processors.

Since launch, we’ve heard that customers from fields such as life sciences, oil and gas, manufacturing, business computing and even space exploration would like to run high performance workloads in their Amazon Virtual Private Cloud environments for improved network management and isolation. Amazon VPC lets you provision a private, isolated section of the AWS Cloud where you can launch AWS resources in a virtual network that you define. Today, we’re announcing that cc2.8xlarge cluster computing instances are available in Amazon VPC. We’re also removing the beta tag.

The CC2 instances make Intel Xeon E5 processors, with support for AVX extensions, available to customers on demand, at scale, and we’ll be expanding the cc2.8xlarge instances to other regions in the future.

Let us know how you’re using high performance instances in your pipeline.

~ Matt