Amazon Adds High-Memory Cluster Instances to EC2

Amazon Web Services now wants customers to use its EC2 cloud infrastructure to perhaps sequence the human genome and perform other compute-intensive advanced analytics using in-memory databases such as HANA from its partner SAP.

The latest EC2 instance for in-memory computing is aimed at hosting applications that "have a voracious need for compute power, memory, and network bandwidth such as in-memory databases, graph databases, and memory intensive HPC," according to AWS evangelist Jeff Barr in a blog post.

Configured with a total of 88 ECUs (EC2 compute units), it's based on two Intel E5-2670 processors with NUMA (non-uniform memory access) support, 244 GB of RAM and two 120 GB solid state drives (SSDs) for instance storage. It requires hardware virtual machines (HVMs) and supports only Amazon Elastic Block Storage AMIs. It supports 10 Gbps networking.

"You can use it to run applications that are hungry for lots of memory and that can take advantage of 32 hyper-threaded cores (16 per processor)," Barr noted, adding that support for Intel's Turbo Boost feature also adds to the performance boost. "When the operating system requests the maximum possible processing power, the CPU increases the clock frequency while monitoring the number of active cores, the total power consumption and the processor temperature. The processor runs as fast as possible while staying within its documented temperature envelope."

Pricing starts at $3.50 per hour for Linux instances and $3.831 per hour for Windows instances, currently available in Amazon's U.S. East Region in Northern Virginia. Barr noted Amazon plans to make the instances available in other regions, though he didn't say when.

Posted by Jeffrey Schwartz on 01/22/2013 at 12:48 PM