Today Emu Technology announced that it has delivered an Emu Chick Memory Server to Oak Ridge National Laboratory. “ORNL intends to study the system for streaming graph analysis applications, sparse multilinear computations, and other memory-intensive problems, as we continue to test the potential of emerging computing technologies to further our mission within the DOE,” said Jeffrey S. Vetter, Director of the Future Technologies Group at ORNL’s Computer Science and Mathematics Division.
“This talk will provide empirical evidence from our Deep Speech work that application level performance (e.g. recognition accuracy) scales with data and compute, transforming some hard AI problems into problems of computational scale. It will describe the performance characteristics of Baidu’s deep learning workloads in detail, focusing on the recurrent neural networks used in Deep Speech as a case study. It will cover challenges to further improving performance, describe techniques that have allowed us to sustain 250 TFLOP/s when training a single model on a cluster of 128 GPUs, and discuss straightforward improvements that are likely to deliver even better performance.”
The 3rd Annual Seagate HPC User Forum is coming to SC16 on Nov. 14. “We’re venturing well beyond legacy boundaries. Are you confused about the real future of HPC storage? Is it all flash like the hype suggests? Are reliable spinning disks still going to be relevant? Is there a better answer? Join us Monday, November 14 from 4:00 – 7:00 p.m. at Seagate’s 3rd annual HPC User Forum to get your questions answered and learn about the newest HPC direction and innovations firsthand from four industry leaders.”
Today Dell EMC announced a new member of the Dell EMC Isilon product family. Designed around an all-flash, the Isilon scale-out family of NAS storage is designed to help IT organizations modernize their infrastructure and deliver on the capabilities of a digital business.
Designed specifically with researchers in mind, the Birmingham Environment for Academic Research (BEAR) Cloud will augment an already rich set of IT services at the University of Birmingham and will be used by academics across all disciplines, from Medicine to Archaeology, and Physics to Theology. “We are very proud of the new system, but building a research cloud isn’t easy,” said Simon Thompson, Research Computing Infrastructure Architect in IT Services at the University of Birmingham. “We challenged a range of carefully-selected partners to provide the underlying technology.”
In this video from the Microsoft Ignite Conference, Tejas Karmarkar describes how to run your HPC Simulations on Microsoft Azure – with UberCloud container technology. “High performance computing applications are some of the most challenging to run in the cloud due to requirements that can include fast processors, low-latency networking, parallel file systems, GPUs, and Linux. We show you how to run these engineering, research and scientific workloads in Microsoft Azure with performance equivalent to on-premises. We use customer case studies to illustrate the basic architecture and alternatives to help you get started with HPC in Azure.”
“While we often talk about the density advantages of containers, it’s the opposite approach that we use in the High Performance Computing world! Here, we use exactly 1 system container per node, giving it unlimited access to all of the host’s CPU, Memory, Disk, IO, and Network. And yet we can still leverage the management characteristics of containers — security, snapshots, live migration, and instant deployment to recycle each node in between jobs. In this talk, we’ll examine a reference architecture and some best practices around containers in HPC environments.”
The HPC Advisory Council has posted their agenda for their upcoming China Conference. The event takes place Oct. 26 in Xi’an, China. “We invite you to join us on Wednesday, October 26th, in Xi’an for our annual China Conference. This year’s agenda will focus on Deep learning, Artificial Intelligence, HPC productivity, advanced topics and futures. Join fellow technologists, researchers, developers, computational scientists and industry affiliates to discuss recent developments and future advancements in High Performance Computing.”
In this podcast, the Radio Free HPC team looks at the new OpenCAPI interconnect standard. “Released this week by the newly formed OpenCAPI Consortium, OpenCAPI provides an open, high-speed pathway for different types of technology – advanced memory, accelerators, networking and storage – to more tightly integrate their functions within servers. This data-centric approach to server design, which puts the compute power closer to the data, removes inefficiencies in traditional system architectures to help eliminate system bottlenecks and can significantly improve server performance.”
In this video from the HPC Advisory Council Spain Conference, Addison Snell from Intersect360 Research looks back over the past 10 years of HPC and provides predictions for the next 10 years. Intersect360 Research just released their Worldwide HPC 2015 Total Market Model and 2016–2020 Forecast.