MailChimp Developer

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


SHAPE Selects Eight Innovative HPC Projects for Access to PRACE Supercomputers

Today the SME HPC Adoption Program in Europe announced the winners from its recent Call for Proposals. SHAPE is a pan-European program supported by PRACE which aims to raise awareness and provide European SMEs with the expertise necessary to take advantage of the innovation possibilities created by HPC, thus increasing their competitiveness.

Video: Software-Defined Networking on InfiniBand Fabrics

A design for virtual Ethernet networks over IB is described. The virtual Ethernet networks are implemented as overlays on the IB network. They are managed in a flexible manner using software. Virtual networks can be created, removed, and assigned to servers dynamically using this software. A virtual network can exist entirely on the IB fabric, or it can have an uplink connecting it to physical Ethernet using a gateway. The virtual networks are represented on the servers by virtual network interfaces which can be used with para-virtualized I/O, SRIOV,and non-virtualized I/O. This technology has many uses: communication between applications which are not IB-aware, communication between IB-connected servers and Ethernet-connected servers, and multi-tenancy for cloud environments. It can be used in conjunction with OpenStack, such as for tenant networks.”

Live Report from LUG 2016 Day 3

In this special guest feature, Ken Strandberg offers this live report from Day 3 of the Lustre User Group meeting in Portland. “Rick Wagner from San Diego Supercomputing Center presented progress on his team’s replication tool that allows copying large blocks of storage from object storage to their disaster recovery durable storage system. Because rsync is not a tool for moving massive amounts of data, SDSC created recursive worker services running in parallel to have each worker handle a directory or group of files. The tool uses available Lustre clients, a RabbitMQ server, Celery scripts, and bash scripts.”

Now on Azure: Intel Cloud Edition for Lustre* Software

The Intel Cloud Edition for Lustre* Software is now available on Microsoft’s Azure platform. Intel Cloud Edition for Lustre Software on Azure is a scalable, parallel file system designed as the working file system for HPC or other IO intensive workloads. Built for use with the virtualized compute instances available from Microsoft Azure scalable cloud infrastructure, it is designed for dynamic, pay-as-you-go applications.

Live Report from LUG 2016 Day 2

In this special guest feature, Ken Strandberg offers this live report from Day 2 of the Lustre User Group meeting in Portland. “Scott Yockel from Harvard University shared how they are deploying Lustre across their massive three data centers up to 90 miles apart with 25 PB of storage, about half of which is Lustre. They’re using Docker containers and employing a backup strategy across the miles of every NFS system, parsing of the entire MDT, and includes 10k directories of small files.”

TYAN Rolls Out POWER8-Based 1U Server at OpenPOWER Summit

Today TYAN showcased the GT75-BP012, a new POWER8-based 1U server platform at the OpenPOWER Summit 2016 in San Jose. The 1U TYAN GT75-BP012 platform is a POWER8-based server solution that reveals the spirit of the OpenPOWER Foundation – resources and innovation are not limited to the community but are open to the world. “By building the ppc64 architecture in the 1U single-socket system, the TYAN GT75-BP012 provides huge memory footprint as well as outstanding performance for HPC and server virtualization applications.” said Albert Mu, Vice President of MITAC Computing Technology Corporation’s TYAN Business Unit.

Italy’s E4 Computer Engineering Builds HPC OpenPOWER Server

Italy’s E4 Computer Engineering announced that it has sealed an agreement with Wistron Corporation to market and distribute the OP205, the Company’s first POWER8 processor- based system in Italy and Europe. “We are very committed to OpenPOWER and we are going to great lengths to ensure we create a system that can be a reference for the Foundation’s amazing eco-system,” said Cosimo Gianfreda, CTO E4 Computer Engineering. “Wistron has worked for many years with many major players and we jumped at the opportunity of working together for this project. We know Europe is ready for OpenPOWER and we are actively encouraging its implementation in a number of Scientific and industrial environments”

Application Performance & Power Consumption on Intel Xeon Phi

“While new technology will be developed that reduces the power per operation needed, in today’s environments it is important to understand how an application affects power usage. For modern applications that have been optimized to take advantage of both the Intel Xeon CPU and the Intel Xeon Phi coprocessor, the hardware mentioned does include various power states, which can minimize the power consumption when idle.”

Live Report from LUG 2016 Day 1

“The Lustre User Group (LUG) 2016 conference is well under way. The morning of the first day was spent on looking at Lustre today and tomorrow and security developments in the code. Peter Jones and Andreas Dilger described what is in the newest release of Lustre 2.8 and will be in Lustre 2.9, targeted for release this fall, and beyond. These features include growing support for ZFS, security, multi-rail LNET, progressive file layouts, project quotas, and more.”

Supermicro Launches Total Solution for Lustre on ZFS

“With Supermicro’s 90 top-load 3.5” hot-swap bay JBOD as the storage core of our Lustre Pod Cluster, we maximize performance, density and capacity and simplify serviceability for massive scale HA storage deployments. Combining our preconfigured, validated 2U SuperStorage OSS, 1U Ultra SuperServer with Intel Enterprise Edition for Lustre software, and global service and support, Supermicro has the Total Solution for Lustre ready for HPC, Genomics and Big Data.”