Tag: hpc cluster
The Weekly Top Five features the five biggest HPC stories of the week, condensed for your reading pleasure. This week, we cover the Cray/Sandia partership to found a knowledge institute; RenderStream’s FireStream-based workstations and servers; NVIDIA’s latest CUDA centers; Reservoir Labs and Intel’s extreme scale ambitions; and Jülich Supercomputing Centre’s new hybrid cluster.
With computational testbed, developers and researchers don’t have to worry about about breaking the supercomputer.
Measuring HPC cluster performance is no longer just a matter of running Linpack. A new open source benchmarking tool, called ClusterNumbers, has been developed in order to encapsulate a number of benchmarks that measure a variety of performance characteristics. In this article, ClusterNumbers progenitor Raul Gomez introduces the tool and explains the rationale for its use.
The Weekly Top Five covers the Intel-NVIDIA cross-licensing agreement, the arrival of a Cray supercomputer at Colorado State, advancements in the understanding of storage materials, the latest batch of AAAS Fellows, and UW-Madison’s new HPC cluster.
Desktop HPC and cloud computing challenge in-house clusters..
An outsource management team is the control point for the outsourcing of your infrastructure. Through this group, you maintain control over your infrastructure, and therefore can have full trust in your outsource partner (because you know exactly what you want, and you know how to measure if you are getting it).
When compared to the power the word “cloud” seems to wield, the concept of renting an HPC cluster can seem less attractive; however, with some vendors providing a virtualization-free environment with all of the on-demand appeal of clouds and minus the performance hitch, HPC-as-a-Service deserves a second look past the clouds.
Has the big multicore Xeon and Opteron server jumped the HPC shark?
SMP virtualization specialist ScaleMP has announced vSMP Foundation 3.0, the third generation of its virtual SMP solution for high performance computing clusters. The new release adds some much-needed updates, including increased scalability and additional hardware support.
The Software Tools for Academics and Researchers (STAR) group at MIT has created an open-source project called StarCluster that allows anyone to create HPC clusters on Amazon’s Elastic Compute Cloud (EC2) without needing to be a cloud expert.