Sign up for our newsletter and get the latest HPC news and analysis.
Send me information from insideHPC:


Video: Energy Efficient Computing using Dynamic Tuning

Lubomir Riha from IT4Innovations gave this talk as part of the POP HPC webinar series. “This webinar focused on tools designed to improve the energy-efficiency of HPC applications using a methodology of dynamic tuning of HPC applications, developed under the H2020 READEX project. The READEX methodology has been designed for exploiting the dynamic behaviour of software. At design time, different runtime situations (RTS) are detected and optimized system configurations are determined. RTSs with the same configuration are grouped into scenarios, forming the tuning model. At runtime, the tuning model is used to switch system configurations dynamically.”

Altair offers free training tools and software licensing in response to COVID-19

Over at the Altair Blog, CEO James Scapa writes that the company is offering free training tools and software licensing in response to COVID-19. “Altair can provide temporary software licenses for clients working from home without access to their enterprise Altair software solutions with no additional fees or charges. If customers wish to move their HyperWorks Units from on-premises to Altair hosted servers or require temporary software licenses, they should contact their account representative.”

UKRI Awards ARCHER2 Supercomputer Services Contract

UKRI has awarded contracts to run elements of the next national supercomputer, ARCHER2, which will represent a significant step forward in capability for the UK’s science community. ARCHER2 is provided by UKRI, EPCC, Cray (an HPE company) and the University of Edinburgh. “ARCHER2 will be a Cray Shasta system with an estimated peak performance of 28 PFLOP/s. The machine will have 5,848 compute nodes, each with dual AMD EPYC Zen2 (Rome) 64 core CPUs at 2.2GHz, giving 748,544 cores in total and 1.57 PBytes of total system memory.”

Job of the Week: HPC Systems Engineer at William & Mary

William & Mary in Virginia seeks an HPC Systems Engineer in our Job of the Week. “The HPC Systems Engineer provides day-to-day operations, maintenance and hardware engineering support for computer systems managed by the Research Computing (RC) within the Office of Information Technology. These systems include Linux-based HPC clusters; departmental servers and workstations under the control of RC; These systems and the applications that run on them are characterized by leading-edge computing, networking, and software technologies, complex and demanding computational requirements, and large data-sets.”

Atipa Technologies Joins Bright Reseller Program

Today Bright Computing announced that Atipa Technologies has become the latest company to join the Bright Computing Partner Program, as an Advanced Reseller. “Through our partnership with Bright Computing, we will incorporate Bright’s industry-leading cluster management technology into our HPC solutions so that our customers who are less familiar with the Linux command line or who do not have the financial resources to hire an experienced Linux sysadmin can dive in and start using the cluster on day one.”

Job of the Week: Linux System Administrator at UC Riverside

UC Riverside is seeking a Linux System Administrator in our Job of the Week. “UC Riverside’s research computing infrastructure is provided by a central HPC facility. This facility operates Linux clusters with over 6,000 CPU cores, 75TB of total system RAM and several GPU nodes. Big Data storage is handled by a centralized GPFS-based storage cluster with over 4PB of disk space for production and backup storage. The incumbent will be part of a team responsible for the systems administration of this HPC infrastructure, including development of software for parallel computing, network management, data security and user training.”

Full-spectrum HPC Scheduling

Our friends over at Altair explain how a meta-scheduler, or hierarchical scheduler, can be thought of as a private or team-based scheduler that uses shared underlying resources. Difficult workloads and special workloads are good candidates for meta-scheduling. Examples include sets of several hundred thousand short jobs, jobs with complex dependencies, and workflows that are continually introspected for status.

Bright Cluster Manager for Data Science Now Available at No Charge with Easy8

Today Bright Computing announced that Bright Cluster Manager for Data Science is now available at no charge as part of the Easy8 program. Launched in November of 2019, Easy8 is designed to put Bright’s award-winning cluster management software in the hands of every organization working with high-performance Linux clusters. Easy8 offers the full-featured Bright Cluster Manager software free for up to 8 nodes, and now includes Bright Cluster Manager for Data Science. Bright Cluster Manager automates the process of building and managing heterogeneous Linux clusters that span from your on-premise datacenter to the cloud, and to the edge.

Bright Computing adds more than 100 new customers In 2019

Commercial enterprises, research universities and government agencies are turning to Bright Cluster Manager to reduce complexity and increase flexibility of their high-performance clusters. Along these lines, the company just announced the addition of more than 100 organizations to its client list in 2019, including AMD, Caterpillar, GlaxoSmithKline, Saab, Northrop Grumman, Trek Bicycles, Samsung, General Dynamics, Lockheed Martin and BAE, as well as 19 government agencies and 28 leading universities.

LBNL Breaks New Ground in Data Center Optimization

Berkeley Lab has been at the forefront of efforts to design, build, and optimize energy-efficient hyperscale data centers. “In the march to exascale computing, there are real questions about the hard limits you run up against in terms of energy consumption and cooling loads,” Elliott said. “NERSC is very interested in optimizing its facilities to be leaders in energy-efficient HPC.”