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


Call for Participation: MSST Mass Storage Conference 2018

The 34th International Conference on Massive Storage Systems and Technologies (MSST 2018) has issued its Call for Participation. The event takes place May 14-16 in Santa Clara, California. “The conference invites you to share your research, ideas and solutions, as we continue to face challenges in the rapidly expanding need for massive, distributed storage solutions. Join us and learn about disruptive storage technologies and the challenges facing data centers, as the demand for massive amounts of data continues to increase. Join the discussion on webscale IT, and the demand on storage systems from IoT, healthcare, scientific research, and the continuing stream of smart applications (apps) for mobile devices.”

Resource Management Across the Private/Public Cloud Divide

This is the final entry in a insideHPC series of features that explores new resource management solutions for workload convergence, such as Bright Cluster Manager by Bright Computing. This article highlights how resource management systems that can manage clusters on-premises or in the cloud greatly simplify cluster management. That way, different tools do not have to be learned for managing a cluster based on whether it is located in the company data center or in the cloud.

Take the Exascale Resilience Survey from AllScale Europe

The European Horizon 2020 AllScale project has launched a survey on exascale resilience. “As we approach ExaScale, compute node failure will become commonplace. @AllScaleEurope wants to know how #HPC software developers view fault tolerance today, & how they plan to incorporate fault tolerance in their software in the ExaScale era.”

Supercomputing Graphene Applications in Nanoscale Electronics

Researchers at North Carolina State University are using the Blue Waters Supercomputer to explore graphene’s applications, including its use in nanoscale electronics and electrical DNA sequencing. “We’re looking at what’s beyond Moore’s law, whether one can devise very small transistors based on only one atomic layer, using new methods of making materials,” said Professor Jerry Bernholc, from North Carolina University. “We are looking at potential transistor structures consisting of a single layer of graphene, etched into lines of nanoribbons, where the carbon atoms are arranged like a chicken wire pattern. We are looking at which structures will function well, at a few atoms of width.”

Video: Computing Challenges at the Large Hadron Collider

CERN’s Maria Girona gave this talk at the HiPEAC 2018 conference in Manchester. “The Large Hadron Collider (LHC) is one of the largest and most complicated scientific apparata ever constructed. “In this keynote, I will discuss the challenges of capturing, storing and processing the large volumes of data generated at CERN. I will also discuss how these challenges will evolve towards the High-Luminosity Large Hadron Collider (HL-LHC), the upgrade programme scheduled to begin taking data in 2026 and to run into the 2030s, generating some 30 times more data than the LHC has currently produced.”

Radio Free HPC Looks at Diverging Chip Architectures in the Wake of Spectre and Meltdown

In this podcast, the Radio Free HPC team looks at the tradeoff between chip performance and security. In the aftermath of the recently disclosed Spectre and Meltdown exploits, Cryptograpy guru Paul Kocher from Rambus is calling for a divergence in processor architectures:

HACC: Fitting the Universe inside a Supercomputer

Nicholas Frontiere from the University of Chicago gave this talk at the DOE CSGF Program Review meeting. “In response to the plethora of data from current and future large-scale structure surveys of the universe, sophisticated simulations are required to obtain commensurate theoretical predictions. We have developed the Hardware/Hybrid Accelerated Cosmology Code (HACC), capable of sustained performance on powerful and architecturally diverse supercomputers to address this numerical challenge. We will investigate the numerical methods utilized to solve a problem that evolves trillions of particles, with a dynamic range of a million to one.”

Video: Deep Reinforcement Learning and Systems Infrastructure at DeepMind

In this video from HiPEAC 2018 in Manchester, Dan Belov from DeepMind describe the company’s machine learning technology and some of the challenges ahead. “DeepMind Inc. is well known for state of the art Deep Reinforcement Learning (DRL) algorithms such as DQN on Atari, A3C on DMLab and AlphaGo Zero. I would like to take you on a tour of challenges we encounter when training DRL agents on large workloads with hundreds of terabytes of data. I’ll talk about why DRL poses unique challenges when designing distributed systems and hardware as opposed to simple supervised learning. Finally I’d like to discuss opportunities for DRL to help systems design and operation.”

Adaptive Computing rolls out Moab HPC Suite 9.1.2

Today Adaptive Computing announced the release of Moab 9.1.2, an update which has undergone thousands of quality tests and includes scores of customer-requested enhancements. “Moab is a world leader in dynamically optimizing large-scale computing environments. It intelligently places and schedules workloads and adapts resources to optimize application performance, increase system utilization, and achieve organizational objectives. Moab’s unique intelligent and predictive capabilities evaluate the impact of future orchestration decisions across diverse workload domains (HPC, HTC, Big Data, Grid Computing, SOA, Data Centers, Cloud Brokerage, Workload Management, Enterprise Automation, Workflow Management, Server Consolidation, and Cloud Bursting); thereby optimizing cost reduction and speeding product delivery.”

Intel Rolls out new 3D NAND SSDs

Today, Intel announced the Intel SSD DC P4510 Series for data center applications. As a high performance storage device, the P4510 Series uses 64-layer TLC Intel 3D NAND to enable end users to do more per server, support broader workloads, and deliver space-efficient capacity. “The P4510 Series enables up to four times more terabytes per server and delivers up to 10 times better random read latency at 99.99 percent quality of service than previous generations. The drive can also deliver up to double the input-output operations per second (IOPS) per terabyte.”