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

Bill Dally Presents: Scientific Computing on GPUs


Bill Dally from Nvidia presented this talk at the Stanford HPC Conference. “HPC and data analytics share challenges of power, programmability, and scalability to realize their potential. The end of Dennard scaling has made all computing power limited, so that performance is determined by energy efficiency. With improvements in process technology offering little increase in efficiency innovations in architecture and circuits are required to maintain the expected performance scaling.”

Progress Check on OpenPOWER Consortium


Over at Clabby Analytics, Joe Clabby writes that the OpenPOWER Consortium has made progress since it was announced last year. With founding members Google, IBM, Mellanox, and Nvidia, OpenPOWER intends to build advanced server, networking, storage and GPU-acceleration technology aimed at delivering more choice, control and flexibility to developers of next-generation, hyperscale and cloud data centers.

Being Very Green with Tsubame 2.5 Towards 3.0 and Beyond to Exascale


“TSUBAME 2.5 succeeded TSUBAME 2.0 by upgrading all 4224 Tesla M2050 GPUs to Kepler K20x GPUs, achieving 5.76 / 17.1 Petaflops peak in double / single point precision respectively, latter the fastest in Japan. By overcoming several technical challenges, TSUBAME 2.5 exhibits x2-3 speedup and multi-petaflops performance for many applications, leading to TSUBAME 3.0 in 2015-16.”

Mont-Blanc Project Moves Forward with Funding through 2016


The European Commission has granted an additional €8 million Euros to extend the Mont-Blanc Project activities until September 2016. This funding comes on the heels of some significant milestones for the project, which endeavors to design a new type of energy-efficient computer architecture for Exascale systems.

Job of the Week: HPC Server and Processor Architect at Broadcom

Broadcom in Santa Clara is seeking an HPC Server and Processor Architect in our Job of the Week.

SDSC Wraps the Long-Tail Death Match at SC13


In this video, Rick Wagner from the San Diego Supercomputer Center describes the “Long-Tail Death Match,” a gaming competition running on a multipanel display at the SDSC booth at SC13. SDSC built the Meteor Cluster for the competition, a Beowulf cluster based on inexpensive Raspberry Pi computing devices.

Young Prodigy from Rex Computing Using Parallella Boards for HPC


In this video from the Emerging Technologies Booth at SC13, Thomas Sohmers from Rex Computing describes how the company is using ARM-powered Parallella boards from Adapteva as building blocks for low-energy HPC clusters.

Multicore DSPs from TI, “The Absolute Best at 10 Watts or Less”


In this video from SC13, Arnon Friedman from Texas Instruments describes how TI multicore DSP processors rule the roost for HPC computing at under 10 Watts. As an example of what’s possible, the company showcased the BrownDwarf DSP + ARM Supercomputer from nCore in the first public demonstration of an ARM Cortex-A15+Accelerator (DSP) high performance system.

HSA Heterogeneous System Architecture Overview


The HSA Foundation seeks to create applications that seamlessly blend scalar processing on the CPU, parallel processing on the GPU, and optimized processing on the DSP via high bandwidth shared memory access enabling greater application performance at low power consumption.

Sponsored Post: Asetek Innovates with Hot Water Cooling System


Asetek is the world’s leading supplier of liquid cooling systems for computers with over 1.5 million cooling systems shipped for workstations, desktop PCs and servers. Leveraging their proven technologies, the Asetek RackCDU™ Direct-to-Chip hot water cooling system delivers energy savings of up to 80% and server rack density increases of up to 2.5x-5x times compared to air-cooled data centers, with rapid ROI and low TCO.