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


Video: Deep Learning at 15 Petaflops

Narayanan Sundaram gave this talk at the Intel HPC Developer Conference. “We present the first 15-PetaFLOP Deep Learning system for solving supervised and semi-supervised scientific pattern classification problems, optimized for Intel Xeon Phi. We use a hybrid of synchronous and asynchronous training to scale to ~9600 nodes of Cori on CNN and autoencoder networks.”

Jack Dongarra Presents: Overview of HPC and Energy Savings on NVIDIA’s V100

Jack Dongarra from the University of Tennessee gave this talk at SC17. “In this talk we will look at the current state of high performance computing and look to the future toward exascale. In addition, we will examine some issues that can help in reducing the power consumption for linear algebra computations.”

Mont-Blanc to Sponsor UPC Team at ISC 2018 Student Cluster Competition

The Mont-Blanc Project will once again sponsor a team at the upcoming ISC 2018 Student Cluster Competition. The sponsored team from the Universitat Politècnica de Catalunya / Barcelona Tech (UPC) will compete for the fourth time at ISC 2018, which takes place June 24– 28 in Frankfurt, Germany. “I am always impressed by the technical prowess exhibited by these young teams: the way they are turning our lessons into applied knowledge, through live benchmarking and on the fly troubleshooting is a great process and it triggers a positive loop in all of us.”

Michael Wolfe Presents: Why Iteration Space Tiling?

In this Invited Talk from SC17, Michael Wolfe from NVIDIA presents: Why Iteration Space Tiling? The talk is based on his noted paper, which won the SC17 Test of Time Award. “Tiling is well-known and has been included in many compilers and code transformation systems. The talk will explore the basic contribution of the SC1989 paper to the current state of iteration space tiling.”

Deep Learning and Automatic Differentiation from Theano to PyTorch

Inquisitive minds want to know what causes the universe to expand, how M-theory binds the smallest of the small particles or how social dynamics can lead to revolutions. “The way that statisticians answer these questions is with Approximate Bayesian Computation (ABC), which we learn on the first day of the summer school and which we combine with High Performance Computing. The second day focuses on a popular machine learning approach ‘Deep-learning’ which mimics the deep neural network structure in our brain, in order to predict complex phenomena of nature.”

Xtreme Design HPC Cloud Management Demo at SC17

In this video from SC17, Naoki Shibata from Xtreme Design demonstrates the company’s innovative solutions for deploying and managing HPC clouds. “Customers can use our easy-to-deploy turnkey HPC cluster system on public cloud, including setup of HPC middleware (OpenHPC-based packages), configuration of SLURM, OpenMPI, and OSS HPC applications such as OpenFOAM. The user can start the HPC cluster (submitting jobs) within 10 minutes on the public cloud. Our team is a technical startup for focusing HPC cloud technology.”

Video: Taking the Nanoscale to the Exascale

Theresa Windus from Iowa State University gave this Invited Talk at SC17. “This talk will focus on the challenges that computational chemistry faces in taking the equations that model the very small (molecules and the reactions they undergo) to efficient and scalable implementations on the very large computers of today and tomorrow. In particular, how do we take advantage of the newest architectures while preparing for the next generation of computers? “

SC17 Awards Ceremony and Conference Recap

In this video from SC17, Jeff Hollingsworth and Paul Hovland host the Conference Finale Event announcing the winners of the Best Paper, Best Poster, ACM Gordon Bell Prize, Student Cluster Challenge and other honors for our technical program. “The conference drew 12,753 attendees and featured a technical program spanning six days – marking the second largest SC conference of all time.”

Announcing a Series of Worldwide GPU Hackathons in 2018

ORNL is hosting a series of GPU Hackathons in 2018. The first event will take place March 5-9 at TU Dresden in Germany. “The goal of each Hackathon is for current or prospective user groups of large hybrid CPU-GPU systems to send teams of at least 3 developers along with either (1) a (potentially) scalable application that could benefit from GPU accelerators, or (2) an application running on accelerators that need optimization. There will be intensive mentoring during this 5-day hands-on workshop, with the goal that the teams leave with applications running on GPUs, or at least with a clear roadmap of how to get there. Our mentors come from national laboratories, universities, and vendors, and besides having extensive experience in programming GPUs, many of them develop the GPU-capable compilers and help define standards such as OpenACC and OpenMP.”

Swiss HPC Conference Returns to Lugano in April with Winter HPCXXL User Group

Today the HPC Advisory Council announced that registration is now open for the Swiss HPC Conference. The event takes place April 9-12 in Lugano, Switzerland. For the first time, the conference will be held in concert with the Winter HPCXXL User Group meeting. “We are very excited to organize a joint conference here in Lugano, bringing together the communities of HPCAC and HPCXXL,” said Hussein Harake, HPC system manager, CSCS. “We believe that such a collaboration will offer a unique opportunity for HPC professionals to discuss and share their knowledge and experiences.”