Tuesday, April 7, 2015

IBM Spectrum Scale Storage Slidecast

In this slidecast, Jim Gutowski and Scott Fadden from IBM describe the advantages IBM Spectrum Scale Storage brings to the enterprise. Watch the video presentation: http://wp.me/p3RLHQ-e0a Learn more: http://ibm.co/1y1QIrj

Friday, February 27, 2015

Deep Learning - Unreasonably Effective

In this podcast, Stephen Jones from Nvidia presents: Deep Learning - Unreasonably Effective.

Deep Learning is a new area of Machine Learning research, which has been introduced with the objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence. At the 2015 GPU Technology Conference, you can join the experts who are making groundbreaking improvements in a variety of deep learning applications, including image classification, video analytics, speech recognition, and natural language processing.
Watch the video presentation: http://wp.me/p3RLHQ-dTb

Wednesday, January 28, 2015

UberCloud - From Experiment to Marketplace

In this slidecast, Wolfgang Gentzsch presents: UberCloud - From Experiment to Marketplace. After 18 months of developing Docker container technology into high performance application containers for engineering and scientific simulations,  UberCloud announces the availability of high performance application containers on its online UberCloud Marketplace, for ANSYS Mechanical, Fluent, CFX, Workbench, Icepak, EM, LS-DYNA and LS-PrePost,  for CD-adapco STAR-CCM+,  and for OpenFOAM, and more in the pipeline. These application containers are portable on all in-house and cloud environments and allow seamless and transparent on-demand access to and use of applications and data in the cloud, with a look and feel identical to your workstation. View the Slides * Download the MP3Subscribe on iTunes * Subscribe to RSS  Sign up for our insideHPC Newletter.

Tuesday, December 9, 2014

Cycle Computing Powers 70-core AWS Cluster for HGST

Has Cloud HPC finally made it's way to the Missing Middle? In this podcast, Jason Stowe from Cycle Computing describes how the company enabled HGST to spin up a 70,000-core cluster from AWS and then return it 8 hours later.

Tuesday, November 25, 2014

Nvidia/IBM to Build Two Coral 100+ Petaflop Supercomputers in 2017

In this slidecast, Sumit Gupta from Nvidia describes the company's big win with IBM for two DOE supercomputers for deployment in 2017. The two machines will feature IBM POWER9 processors coupled with Nvidia's future Volta GPU technology. NVLink will be a critical piece of the architecture as well, along with a system interconnect powered by Mellanox.

QNIBTerminal Plus InfiniBand - Containerized MPI Workloads

In this slidecast, Christian Kniep presents: QNIBTerminal Plus InfiniBand - Containerized MPI Workloads. Watch the video presentation.

Friday, November 14, 2014

Dell Plans Exciting Panel Discussions at SC14

In this podcast, Dell Fellow Jimmy Pike describes coming attractions at the Dell booth #1739 at SC14.
Are you ready for what promises to be another successful SC? Join us at the Dell Beignet Theater for two fascinating panels hosted by Rich Brueckner, president, insideHPC.
HPC in the Cloud: The Overcast has Cleared Wednesday, Nov 19, 1:30 – 2:30 p.m. Panelists include:
  • Muhammad Atif, Ph.D., National Computational Infrastructure (NCI), The Australian National University (ANU)
  • Larry Smarr, Ph.D., UC San Diego
  • Roger Rintala, Intelligent Light
  • Boyd Wilson, Clemson University & Omnibond
SUMMARY:  Cloud delivery of HPC has progressed at a much slower rate than we've seen in the enterprise where it has become the standard way that business approaches IT. Has the day come where we will start to see private and public clouds at the defacto way we get things done in high performance computing? In this panel, we will hear from the thought leaders that are blazing these trails in practice every day, delivering utility computing cycles to scientists, researchers, and engineers.  

Data Intensive Computing:  The Gorilla behind the Computation Wednesday, Nov 19, 3:00 – 4:00 p.m. Panelists include:
  • Ken Buetow, Ph.D., Arizona State University
  • Erik Deumens, Ph.D.,University of Florida
  • Niall Gafney, Texas Advanced Computing Center (TACC)
  • William Law, Stanford University
SUMMARY: Back before the SC conference series, the pioneers of vector supercomputing soon found that their ability to ever-increase computation speeds was hampered by the ability to move and store data. While today’s HPC clusters have changed the way we compute, the Data Gorilla is as strong and formidable as ever. In this panel, you’ll hear from the vanguard of university researchers, who have embraced new technologies, methods, and approaches to data-intensive computing—even one’s inspired by the tremendous adoption of technologies as alien to HPC as Hadoop and MapReduce. Download the MP3 * Subscribe on iTunes * Subscribe to RSS