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


Archives for January 2017

Video: Rescale Night Showcases HPC in the Cloud

“Billed as an exposition into ‘The Future of Cloud HPC Simulation,’ the event brought together experts in high-performance computing and simulation, cloud computing technologists, startup founders, and VC investors across the technology landscape. In addition to product demonstrations with Rescale engineers, including the popular Deep Learning workshop led by Mark Whitney, Rescale Director of Algorithms, booths featuring ANSYS, Microsoft Azure, Data Collective, and Microsoft Ventures offered interactive sessions for attendees.”

HPC4Mfg Industry Day Comes to San Diego March 2-3

HPC4Mfg will host their first annual High Performance Computing for Manufacturing Industry Engagement Day on March 2-3 in San Diego. With a theme of “Spurring Innovation in U.S. Manufacturing Through Advanced Computing,” the conference will bring together representatives from U.S. manufacturing, national laboratories, universities, and consortiums to discuss the recent advancements in manufacturing realized through the application of HPC and how leveraging HPC expertise through public-private partnerships has lowered the risk of adoption.

Argonne Annouces Early Science Projects for Aurora Supercomputer

Argonne has selected 10 computational science and engineering research projects for its Aurora Early Science Program starting this month. Aurora, a massively parallel, manycore Intel-Cray supercomputer, will be ALCF’s next leadership-class computing resource and is expected to arrive in 2018. The Early Science Program helps lay the path for hundreds of other users by doing actual science, using real scientific applications, to ready a future machine. “As with any bleeding edge resource, there’s testing and debugging that has to be done,” said ALCF Director of Science Katherine Riley.

In Memory Computing Speeds Results

In-Memory Computing can accelerate traditional applications by using a memory first design. Applicable to a wide range of domains, In-Memory Computing and In-Memory Data Grids take advantage of the latest trends in computer systems technology. “In-memory computing is designed to address some of the most critical and real-time task requirements today. This include real-time fraud detection, biometrics and border security and financial risk analytics. All of these use cases require very low latency access to data from very large amounts of data, which results in faster and more accurate decisions.”

HiPINEB Workshop on High Performance Networks Posts Agenda for February 5 in Austin

The IEEE International Workshop on High-Performance Interconnection Networks in the Exascale and Big-Data Era (HiPINEB) has published its program agenda. Held in conjunction with the IEEE HPCA 2017 Conference, HiPINEB takes place Feb 5, in Austin, Texas.

Cheyenne Supercomputer Triples Scientific Capability at NCAR

The National Center for Atmospheric Research (NCAR) is launching operations this month of one of the world’s most powerful and energy-efficient supercomputers, providing the nation with a major new tool to advance understanding of the atmospheric and related Earth system sciences. Named “Cheyenne,” the 5.34-petaflop system is capable of more than triple the amount of scientific computing performed by the previous NCAR supercomputer, Yellowstone. It also is three times more energy efficient.

Video: Modern Computing – Cloud, Distributed, & High Performance

Dr. Umit Catalyurek from Georgia Institute of Technology presented this talk as part of the USC Big Data to Knowledge series. “This lecture will be a brief crash course on computer architecture, high performance computing and parallel computing. We will, again very briefly, discuss how to classify computer architectures and applications, and what to look in applications to achieve best performance on different architectures.”

HPC User Forum Returns to Stuttgart Feb 28 – March 1

The IDC HPC User Forum, taking place at the HLRS premises in Stuttgart-Vaihingen on February 28 and March 1, will bring together the HPC community to hear experts from all of Europe and the USA. During the two-day event, one of the subjects will be the role of small and medium-sized enterprises (SME) in HPC.

25 Gigabit Ethernet Consortium Validates Multi-Vendor Interoperability

“In order to handle the increasing amount of data, server architectures all too often require multiple 10G ports. 25G Ethernet arrives just in time and has started its climb towards dominance as the leading server-to-ToR switch interconnect. As this transition occurs, plugfests assure users that 25G and greater speeds from different vendors will perform as advertised with solid plug-and-play interoperability,” said Vittal Balasubramanian, chair of the 25G/50G Ethernet Interop Committee and Principal Signal Integrity Engineer at Dell.

Radio Free HPC Interviews Henry’s Mom and Congratulates The UberCloud on New Funding

In this podcast, the Radio Free HPC team speaks to our special guest for the week: Binnie Coppersmith, also known as Henry’s Mom. It’s Binnie’s 80th birthday, and Dan wants to know once and for all if Henry is an alien, or at least why he is the way he is. After that, we look at why the UberCloud has received $1.7 Million in Pre-A Series funding. It’s great news for HPC in the Cloud.