Sign up for our newsletter and get the latest HPC news and analysis.

Interview: Why Software Defined Infrastructure Makes Sense for HPC

Jay Muelhoefer, IBM

“I came to IBM via the acquisition of Platform Computing. There’s also been other IBM assets around HPC, namely GPFS. What’s been the evolution of those items as well and how they really come together under this concept of software-defined infrastructure, and how we’re now taking these capabilities and expanding them into other initiatives that have sort of bled into the HPC space.”

IBM Platform Computing Delivers New HPC Cloud Offerings

HPC Cloud

Clusters that are purchased for specific applications tend not to be flexible as workloads change. What is needed is an infrastructure that can expand or contract as the workload changes. IBM, a recognized leader in High Performance Computing is applying its expertise in both HPC and Cloud computing to bring together the technologies to create the HPC Cloud.

Preparing for Advanced Manycore Architectures – and Implications on the Interconnect

Katie Antypas,
Services Department Head, National Energy Research Scientific Computing Center, Lawrence Berkeley National Laboratory

In this video from the 2015 OFS Developer’s Workshop, Katie Antypas from LBNL describes preparations for the Cori supercomputer. “We need to emphasize here that the Knights Landing processor is self-hosted, and so that means it’s not an accelerator. It’s not a coprocessor and the particular kernel processor that will be having for NERSC-8, will have more than 60 cores and it will have multiple hardware threads for the core. That’s a lot, right? Having 60 cores per node with multiple hardware threads. That a significant increase from both our Hopper and Edison system, which has 24 cores each.”

DDN Shows Strong Momentum for 2015


“As our 2014 results and momentum into the first quarter of 2015 demonstrate, DDN’s product strategy to offer integrated end-to-end solutions for large scale data problems is in high demand,” said Alex Bouzari, DDN CEO and co-founder. “DDN is leading the industry with innovation in application acceleration, high performance file systems and both private and public cloud enabling solutions.”

Using Benchmarks to Your Advantage

Jeff Layton

Over at Admin HPC, Jeff Layton from AWS writes that while benchmarks remains contentious in the HPC industry, they still can be very useful.

Quantifying The Dynamics of Your Superorganism Body Using Big Data Supercomputing


The human body is host to 100 trillion microorganisms, ten times the number of cells in the human body, and these microbes contain 100 times the number of DNA genes that our human DNA does. UC San Diego CSE Professor, Larry Smarr, discusses how data from these trillions of DNA bases are fed into supercomputers, resulting in innovative scalable visualization systems that allow for the examination of patterns that can be used to suggest new hypotheses for clinical application.

Interview: SGI’s Jorge Titinger on HPC Teamwork and other Lessons from Soccer


In this Purematter video, SGI CEO Jorge Titinger discusses the role that his experiences as a professional soccer player has had in both his professional development and his company’s success. He also provides insights into how SGI is leveraging High Performance Computing to scale innovation faster than ever before.

Video: Satoshi Matsuoka on the Outlook for HPC in 2022


In this video, Satoshi Matsuoka discusses the 2022 outlook for supercomputing as he accepts the IEEE Computer Society 2014 Sidney Fernbach Award. He received the award for his work on advanced infrastructural platforms, large-scale supercomputers, and heterogeneous GPU/CPU supercomputers.

ANSYS Modernizes Code for Intel Xeon Phi


Today ANSYS and Intel announced a collaboration to speed structural code on x86 processors.

Correct and Efficient Code – HYDRO2D

High Performance Parallelism

Simulation of physical processes such as the waves in an ocean or the wake behind a boat, although similar in a number of ways, require different approaches. With current systems designed with many parallel computational units, it is important to take advantage of the range of architectural features. Using HYDRO2D, the performance of the code can be examined and improved by taking advantage of a range of system features.