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


HPC News Bytes for May 15, 2015

hatnews

While we’re always on the lookout for HPC news, not everything makes it to the front page. Here are some notable items from this week.

Podcast: Satoshi Matsuoka on the Convergence of HPC and Big Data

satoshi

“Rapid growth in the use cases and demands for extreme computing and huge data processing is leading to convergence of the two infrastructures. The trend towards convergence is not only strategic however but rather inevitable as the Moore’s law ends such that sustained growth in data capabilities, not compute, will advance the capacity and thus the overall capacities towards accelerating research and ultimately the industry.”

Job of the Week: Computational Scientist at Engility

images

Engility is seeking a Computational Scientist in our Job of the Week. This position can be based in the following locations: AFRL (Ohio) , ARL (Maryland) , NRL (Washington DC) , ERDC (Mississippi), and Reston, Virginia.

Achieving Near-Native GPU Performance in the Cloud

John Paul Walters

“In this session we describe how GPUs can be used within virtual environments with near-native performance. We begin by showing GPU performance across four hypervisors: VMWare ESXi, KVM, Xen, and LXC. After showing that performance characteristics of each platform, we extend the results to the multi-node case with nodes interconnected by QDR InfiniBand. We demonstrate multi-node GPU performance using GPUDirect-enabled MPI, achieving efficiencies of 97-99% of a non-virtualized system.”

Video: Have Hard Disks Joined the Grateful Dead?

esg

Have spinning disk drives joined the Grateful Dead? That is the contention here in this video, where industry analyst Mark Peters from ESG dons his tie-dyed shirt and declares that flash is the new storage of choice in the datacenter.

Simulating Global Atmosphere with NICAM on TSUBAME2.5 Using OpenACC

openacc

“OpenACC was applied to the a global high-resolution atmosphere model named NICAM. We executed the dynamical core test without re-writing any specific kernel subroutines for GPU execution. Only 5% of the lines of source code were modified, demonstrating good portability. The results showed that the kernels generated by OpenACC achieved good performance, which was appropriate to the memory performance of GPU, as well as weak scalability. A large-scale simulation was carried out using 2560 GPUs, which achieved 60 TFLOPS.”

Podcast: Arden L. Bement on Blue Waters and the Future of HPC

Arden L. Bement

In this podcast from the 2015 NCSA Blue Waters Symposium, Arden L. Bement discusses the Blue Waters supercomputer and the future of HPC. Formerly Director of the NSF, Bement keynoted the symposium and is currently the Davis A. Ross Distinguished Professor Emeritus and Adjunct Professor of the College of Technology at Purdue University.

Video: Teaching Machines to Diagnose Cancer

ai

In this PBS video, Hari Sreenivasan reports on how tech firms are investing in the next generation of intelligent computer programs and in what ways the technology still lags behind humans. The report also takes a closer look at teaching machines to diagnose cancer.

Call for Papers: COMSOL Conference 2015

comsol

The 11th annual COMSOL Conference has issued its Call for Papers. As the world’s largest conference on multiphysics simulation, the event takes place Oct. 7-9 in Boston.

Scaling STAR-CCM+ to 55,000 Cores on Hornet

Hornet Supercomputer

Today CD-adapco announced a significant scalability milestone for its STAR-CCM+ CFD software. Optimized over the course of a year in collaboration with HLRS and SICOS BW, STAR-CCM+ was run on the entirety of the 1.045 PetaFlop Hermit cluster, managing to maintain perfect scalability beyond 55,000 cores.