NextIO has announced the general availability of the vCore Express 2090 GPU computing solution, designed especially for parallel computing applications using Nvidia Tesla 20-Series GPUs in cluster and datacenter deployments. The system features four massively parallel CUDA-enabled Tesla M2090 GPUs in a 1U chassis. Based on the massively-parallel Cuda GPU computing architecture, key capabilities of the vCore Express 2090 include 2,048 computing cores for accelerated scientific computations (512 cores per GPU), 2.6 Tflops for twice the precision performance (665 gigaflops per GPU), ECC memory for accuracy and reliability, and an L1/L2 cache for improved bandwidth and data sharing. The solution enables users to run GPU's outside of their servers, providing denser server configurations, easier lifecycle management and a lower overall cost of ownership.
Robert Roe looks at research from the University of Alaska that is using HPC to change the way we look at the movement of ice sheets
Robert Roe talks to cooling experts to find out what innovation lies ahead for HPC users