Amazon Brings HPC Cluster Instance to Europe
Inveterate utility computing vendor Amazon is spreading the HPC cloud love outside the US borders. This week, the company launched an HPC-level cluster in its facility in Ireland. The news was detailed in a blog announcement, which explained that Amazon’s Cluster Compute Eight Extra Large (cc2.8xl) instance type is now available in its EU West (Ireland) Region.
Until now, the US-East (Northern Virginia) Region was the only region to offer the cluster instance types, which includes cluster compute instances and cluster graphics processing unit (GPU) instances.
According to Deepak Singh, product manager at Amazon Web Services, the cloud provider was responding to customer demand. Life sciences, oil and gas, manufacturing, space exploration, and business computing users wanted to be able to launch an HPC instance type in Europe. The new offering went live on June 22, and all features of cc2.8xlarge instances are supported, including Amazon VPC.
Amazon’s HPC instances have been available to US users since 2010, but the technology has not been available for European users until now. If data privacy laws permitted it, they could launch US instances, but that meant dealing with trans-atlantic latency delays.
Writes AWS Evangelist Jeff Barr:
These instances are perfect for your compute and memory intensive HPC jobs. Each instance includes a pair of Intel Xeon processors, 60.5 GB of RAM, and 3.37 TB of instance storage. Each processor has 8 cores and Hyper-Threading is enabled, so you can execute up to 32 threads in parallel. Because these instances are members of our Cluster Compute family they are connected to a 10 Gigabit network, and can be members of a Placement Group for low latency connectivity to other CC2 instances, with full bisection bandwidth between them. You can launch these instances on demand, or you can bid for Spot Instances. You can also purchase Reserved Instances.
In case there were any doubts that this is a bonafide HPC offering, Barr reminds us that by stringing together 1,064 of these “eight extra large” instances, Amazon created a virtual supercomputer. With 17,024 cores and 65.968 TB of RAM, the mega-cluster achieved a top speed of 240 teraflops running the Linpack benchmark, earning it a 72nd place finish on the most-recent TOP500 list, announced last week at ISC’12.