Sign up for our newsletter and get the latest HPC news and analysis.

Mellanox Shows Record Performance with ConnectX-4 100Gb/s Interconnect Adapters

Mellanox

Today Mellanox announced world-record performance on its ConnectX-4 EDR 100Gb/s InfiniBand adapters.

Open Fabrics Workshop to Focus on Application Performance, NVM, and SoCs

Open Fabric Alliance

Today the Open Fabrics Alliance announced that their upcoming International OFS Developers’ Workshop will center around three major themes: Applications Performance, Non-Volatile Memory, and Systems-on-a-Chip (SoCs).

Video: Inside the Raijin Supercomputer Down Under

NCI_Raijin_web-1-695x462

In this video, Questacon visits NCI to take a look at Raijin, the southern hemisphere’s first petaflop super computer. “Raijin, named after the Shinto God of thunder, lightning and storms, is a Fujitsu Primergy high-performance, distributed-memory cluster, procured with funding from the Australian Government.”

Katie Antypas to Keynote OFA Developer’s Workshop

Katie Antypas

The OpenFabrics Alliance has announced the keynote talk for their Developers’ Workshop on Sunday, March 15 at 7.30 PM at the Marriott in Monterey CA.

iPlant Collaborative Bridges the Atlantic with Big Data

iplant

“Scientists from all over the world use iPlant to share data and computational methods,” said Matt Vaughn, Co-Principal Investigator of the iPlant Collaborative and site lead at TACC. “iPlant UK is a natural extension of our platform to support plant scientists in the U.K.”

Video: Tips and Tricks to Build Your Own HPC Cluster

steve

“Learn tips and tricks to build your own HPC cluster in an hour! We’ll provide details on how to integrate hardware such as Infiniband adapters, GPU’s, direct-contact liquid- cooling components, along with tips on how to manage resources and jobs, while at the same time performing a live demonstration of building an HPC cluster.”

Video: Interconnecting Future DoE Leadership Systems

rich

CORAL (Collaboration of Oak Ridge, Argonne and Lawrence Livermore National Labs) is a project that was launched in 2013 to develop the technology and meet the Department of Energy’s 2017-2018 leadership computing needs with supercomputers. The collaboration between Mellanox, IBM and NVIDIA was selected by the CORAL project team after a comprehensive evaluation of future technologies from a variety of vendors. The development of these supercomputers is well underway with installation expected in 2017.

Better Healthcare with High performance Parallelized Genomics Analysis

joe

Over at Scalability.org, Joe Landman writes that we are on the cusp of a healthcare revolution that will be sparked by high performance parallelized genomics analysis. Much of the awesomeness is in the algorithm, a massively parallel system that is described in depth here: “Churchill: an ultra-fast, deterministic, highly scalable and balanced parallelization strategy for the discovery of human genetic variation in clinical and population-scale genomics.”

Deploying Collaborative Multilevel Security at Big Data and HPC Scale

Multilevel Security Image

This article series is the first to explore the Seagate ClusterStor™ Secure Data Appliance, which is designed to address government and business enterprise need for collaborative and secure information sharing within a Multilevel Security (MLS) framework at Big Data and HPC Scale. Compared to prior methods, this provides vast cost savings in reduced capital equipment and networks as well as reduced operational complexity, floor space, weight, power, and cooling while satisfying today’s requirements for performance, collaborative secure data sharing, and availability.

The Register to Launch “The Platform” with News on Hyperscale

Nicole Hemsoth

This week The Register announced a new spin-off publication called The Platform. Headed up by former editors of HPCwire and EnterpriseTech, The Platform aims to provide in-depth coverage of the hyperscale side of datacenters.