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


Memory Bandwidth and System Balance in HPC Systems

“This talk reviews the history of the changing balances between computation, memory latency, and memory bandwidth in deployed HPC systems, then discusses how the underlying technology changes led to these market shifts. Key metrics are the exponentially increasing relative performance cost of memory accesses and the massive increases in concurrency that are required to obtain increased memory throughput. New technologies (such as stacked DRAM) allow more pin bandwidth per package, but do not address the architectural issues that make high memory bandwidth expensive to support.”

HPC^NY Bringing High Peformance Computing to Industry

In this video, HPCNY staff describe their mission to bring high performance computing to industries in New York. HPCNY provides businesses and research organizations with access to world-class advanced computing expertise through accelerating the engineering and development path of complex, ground-breaking designs to reliable, accurate, innovative product and process performance that can provide competitive advantage.

Video: How GPUs are Remaking Cloud Computing

In this video from the Nvidia Booth at SC16, Jonathan Symonds from MapD presents: How GPUs are Remaking Cloud Computing. “This video discusses how price/performance characteristics of GPUs are changing the nature of cloud computing. The talk includes performance benchmarks on Google Cloud, Amazon Web Services and IBM Softlayer as well as a live demonstration.”

Beauty Meets HPC: An Overview of the Barcelona Supercomputing Center

“The multidisciplinary research team and computational facilities –including MareNostrum– make BSC an international centre of excellence in e-Science. Since its establishment in 2005, BSC has developed an active role in fostering HPC in Spain and Europe as an essential tool for international competitiveness in science and engineering. The center manages the Red Española de Supercomputación (RES), and is a hosting member of the Partnership for Advanced Computing in Europe (PRACE) initiative.”

SC16 Applies Advanced Computing for Social Change

In this video, Dr. Kelly Gaither from TACC describes how 20 students identified by XSEDE’s community engagement team participated in a four-day long cohort experience themed around social change at SC16. “The objectives of the program are to engage students in a social change challenge using visualization and data analytics to increase awareness, interest, and ultimately inspire students to continue their path in advanced computing careers; to increase the participation of students historically underserved in STEM at SC.”

CryoEM Demo on Dell PowerEdge C6320 at SC16

In this video from SC16, Garima Kochhar from Dell EMC describes the CryoEM Demo on the Dell PowerEdge C6320 rack server powered by Intel Xeon and Intel Xeon Phi. “This demo presents performance results for the 2D alignment and 2D classification phases of the Cryo-electron microscopy (Cryo-EM) data processing workflow using the new Intel Knights Landing architecture, and compares these results to the performance of the Intel Xeon E5-2600 v4 family.”

Building SCinet at SC16: The World’s Fastest Network

In this time-lapse video, a team of volunteers build the SCinet, the world’s fastest network at SC16. “Created each year for the conference, SCinet brings to life a very high-capacity network that supports the revolutionary applications and experiments that are a hallmark of the SC conference. SCinet links the convention center to research and commercial networks around the world. In doing so, SCinet serves as the platform for exhibitors to demonstrate the advanced computing resources of their home institutions and elsewhere by supporting a wide variety of bandwidth-driven applications including supercomputing and cloud computing.”

Video: Sand Casting Simulation for Manufacturing

In this video courtesy of DENIZCILLER, the sand casting process is simulated with ESI ProCAST and QuikCAST. “Simulations like this help foundry engineers understand how metal expands and contracts during the casting process, thereby predicting the final locations of shrinkage porosity. Several other possible defects can occur during a casting process causing imperfection to the final product. To reduce or eliminate these defects, a well-designed gating and feeding system needs to be developed.”

Parallware: LLVM-Based Tool for Guided Parallelization with OpenMP

Manuel Arenaz from Appentra presented this talk at the OpenMP booth at SC16. “Parallware is a new technology for static analysis of programs based on the production-grade LLVM compiler infrastructure. Using a fast, extensible hierarchical classification scheme to address dependence analysis, it discovers parallelism and annotates the source code with the most appropriate OpenMP & OpenACC directives.”

Thread and Memory Scaling Beyond Multicores

In this video, Stefanos Kaxiras from Uppsala University presents: Thread and Memory Scaling Beyond Multicores. “This talk will present the ArgoDSM, a modern, highly-scalable, user-level, distributed shared memory system for clusters. While DSMs have their roots in high-performance computing where the scaling of threads (computation) is the goal, we are witnessing a tremendous interest in Big Data workloads where memory scaling is the target. I will describe how ArgoDSM bridges these two worlds and forms a vehicle for research in Big Data and HPC alike.”