The move to high performance computing comes on the heels of AWS cloud customers, like laboratories and other research facilities, looking to operate more computationally intensive and complex environments in the cloud, Amazon said in a blog post unveiling Cluster Compute Instances.
"Our customers have also asked us about the ability to run even larger and more computationally complex workloads in the cloud," Amazon said. "It is clear that people are now figuring out that they can do HPC (High-Performance Computing) in the cloud … With Cluster Compute Instances, you can now run many types of large-scale network-intensive jobs without losing the core advantages of EC2: a pay-as-you-go pricing model and the ability to scale up and down to meet your needs."
According to AWS, each Cluster Compute Instance consists of a pair of quad-core Intel Nehalem X5570 processors with a total of 33.5 EC2 Compute Units (ECU), 23 GB or RAM, and 1690 GB of local instance storage. Each instance costs $1.60 per hour.
Before Cluster Compute Instances for Amazon EC2, companies with high-performance computing needs required pricy in-house compute clusters and dedicated, purpose-built hardware. Now, users can access HPC capabilities on a pay-as-you-go and on-demand basis with no upfront investment, Amazon said.
"Because many HPC applications and other network-bound applications make heavy use of network communication, Cluster Compute Instances are connected using a 10 Gbps network," AWS noted. "Within this network you can create one or more placement groups of type 'cluster' and then launch Cluster Compute Instances within each group. Instances within each placement group of this type benefit from non-blocking bandwidth and low latency node to node communication."
Additionally, Amazon EC2 API's, the command line tools and Amazon's Web Services Management Console have been updated to support the creation and use of placement groups.
"Businesses and researchers have long been utilizing Amazon EC2 to run highly parallel workloads ranging from genomics sequence analysis and automotive design to financial modeling. At the same time, these customers have told us that many of their largest, most complex workloads required additional network performance," Peter De Santis, General Manager of Amazon EC2, said in a statement. "Cluster Compute Instances provide network latency and bandwidth that previously could only be obtained with expensive, capital intensive, custom-built compute clusters."
Amazon said it has benchmarked the HPC system and it would rank 146 on the list of the top 500 supercomputers.
"The only way to know if this is a genuine HPC setup is to benchmark it, and we've just finished doing so," Amazon wrote. "We ran the gold-standard High Performance Linpack benchmark on 880 Cluster Compute instances (7040 cores) and measured the overall performance at 41.82 TeraFLOPS using Intel's MPI (Message Passing Interface) and MKL (Math Kernel Library) libraries, along with their compiler suite. This result places us at position 146 on the top 500 list of supercomputers."