MailChimp Developer

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


Materials Imaging and Data Sciences Converge at Oak Ridge Workshop

workshop

Oak Ridge National Lab recently hosted a Materials Imaging Workshop. Entitled “Big, Deep and Smart Data Analytics in Materials Imaging,” the workshop explored research opportunities and challenges arising as imaging and data sciences merge.

NEDO in Japan Funds Solar Research at TACC

At the signing ceremony, partners on the next-generation energy efficient data center give the "Hook 'em, Horns" hand sign. From left to right: NTTF Senior Executive Vice President Atsushi Ichihoshi, UT Austin President Gregory L. Fenves, Texas Secretary of State Carlos Casco, NEDO Executive Director Fumio Ueda. Photo by Marsha Miller.

Thanks to $13 Million in research funding from NEDO in Japan, the University of Texas at Austin will begin using alternative energy sources to power some of its HPC Clusters.

Supermicro Deploys Sango Supercomputer at OIST in Japan

Okinawa Institute of Science & Technology Graduate University Sango Supercomputer (PRNewsFoto/Super Micro Computer, Inc.)

Today Super Micro announced the deployment of a new supercomputer in Japan at the Okinawa Institute of Science and Technology Graduate University (OIST) supporting scientists and researchers focused on discovery and innovation in the life, physical and environmental sciences.

Lustre* at the Core of HPC and Big Data Convergence

HPC BIGDATA Convergence

Companies already using High-performance Computing (HPC) with a Lustre file system for simulations, such as those in the financial, oil and gas, and manufacturing sectors, want to convert some of their HPC cycles to Big Data analytics. This puts Lustre at the core of the convergence of Big Data and HPC.

Chips Evolve for Data Intensive Niches

chip

“Data centric workloads are growing in importance in high-performance computing and, in an industry that has been dominated by a handful of technologies for several years, this has led users to look for new technologies which better suit such jobs. The demand now is for low power, high memory, and I/O-intensive solutions, so there is a growing niche which can be addressed by solutions which are less focused on Flops performance.”

Argonne Selects Theta Supercomputer Early Science Projects

For one of the Theta ESP projects, University of Chicago scientist Alexei Khokhlov will continue his research into the deflagration-to-detonation transition process in hydrogen-oxygen mixtures. This image from a previous INCITE project shows weak ignition behind a reflected Mach=1.5 shock in a stoichiometric hydrogen-oxygen mixture at 0.1 atm initial pressure.

Today the Argonne Leadership Computing Facility (ALCF) announced the selection of six projects for its Theta Early Science Program (ESP), a collaborative effort designed to help prepare scientific applications for the architecture and scale of the new supercomputer.

Australia Connects to US Pacific Research Platform

US-West-Coast-Pacific-Research-Platform-partners.-Diagram-courtesy-Calit2-news

Today the California Institute for Telecommunications and Information Technology (Calit2) and Australia’s Academic and Research Network (AARNet) announced a partnership to connect Australian researchers to the US Pacific Research Platform (PRP), a next generation data sharing network linking research universities and supercomputing centers at unprecedented speeds.

Bringing HPC to the SME

secure cloud

Tom Wilkie reports from ISC 2015 on moves to make it easier for SMEs to access high-performance computing, and on why it matters.

Diablo Rolls Out All-Flash DDR4 Memory

Each Memory1 DIMM provides up to 4X more capacity than a DRAM DIMM. By leveraging the density and power advantages of NAND flash, Memory1 modules provide up to 256GB of system memory on a single module. This enables a dramatic increase in the memory capacity supported by each memory slot, each CPU, and each server.

Today Diablo Technologies announced the launch of Memory1, the first all-flash server system memory technology.

XSEDE Powers Polymer Research at MIT

Confined to a tube to approximate the spaghetti-like motion of entangled polymers, a rod–coil block copolymer (rod in blue, coils in pink) moves through a sea of molecules. Flow is impeded when a molecule with a rod passes through a curved portion of the tube (denoted in red). [Image credit: Muzhou “Mitchell” Wang and Christopher N. Lam, Massachusetts Institute of Technology.]

Researchers at MIT are using XSEDE resources to study polymers, the chemical compounds used to make plastic, rubber, and more.