Amazon Web Services has launched a new unit of computing, the Elastic Compute Cloud’s GPU Cluster Instance, to provide a form of supercomputing in its EC2 cloud for the masses.
The new supercomputing is based on NVIDIA Tesla M2050 processors and provides parallel processing for graphics rendering, simulations and other high performance computing (HPC) tasks, according to informationweek.com.
The new GPU Cluster Instance contains 33.5 Elastic Compute Units (ECUs), along with 22 GBs of memory, and is designed to run on a cluster of EC2 servers, making use of the EC2 Cluster 10 Gbs network.
1 Elastic Compute Unit of CPU power is the equivalent of a 2007 Intel Xeon or AMD Opteron chip running at 1 to 1.2 Ghz.
EC2 general manager Peter De Santis was quoted by the website as saying that the cloud based service follows Cluster Compute Instances, which are designed for customers who need additional network and CPU performance for their large and complex HPC workloads.
The GPU Cluster is intended to run jobs that can be subdivided into many smaller parallel processing jobs, according to the website.