high-performance computing
Gidel (booth #620) will showcase its FPGA- based Proc10A computation accelerator boasting up to 1.5 TFlops (IEEE 754-compliant) at breakthrough power efficiency of 30GFlops/W. Te Proc10A’s huge bandwidth capacity (up to 200Gb/s) and distinctive flexible architecture continues Gidel’s line of high- performance Proc boards enabling linear scalable computing as demonstrated on the Novo G, the world’s largest FPGA-based research supercomputer. Te Proc10A family utilises Altera Arria 10 FPGAs incorporating SoC dual-core ARM Cortex-A9 MPCore hard processor system (HPS) conjoined with shared
➤
networking, embedded and mobile products. Technologies including Automata Processing,
Hybrid Memory Cube, and NVDIMMs. Micron will also be participating in the
following activities: Steve Pawlowski, VP of Advanced Computing Solutions, will present in ISC’s Vendor Showdown on Monday 13 July at 1:27pm; Dean Klein, VP of advanced memory solutions, will give a panel talk on Memory Dynamics: Te Impending Expansion of the Memory Hierarchy, on Tuesday 14 July at 11:20am; Rich Murphy, director of advanced systems pathfinding, will participate in a BoF discussion on this year’s Graph 500; Dan Skinner, director of business development, will present in the Exhibitor Forum on Automata Processing on Wednesday, 15 July at 11:00am.
www.micron.com
Numerical Algorithms Group (NAG) (booth #510) provides expertise in HPC, algorithms, and numerical engineering. NAG HPC can bring substantial value to your entire HPC lifecycle. NAG experts have practical experience in procuring supercomputers and associated support services, as users of HPC in industry and academia, as technology experts, in HPC service management, and in strategy development. NAG consultants deliver trusted, impartial, and expert advice to a range of customers across government, academia and industry. For over four decades, NAG numerical
solutions have enabled performance improvements in applications requiring complex computation. Numerical routines in the NAG Library are parallelised for use on supercomputers and inherently flexible from many development packages, programming languages, and platforms. NAG’s numerical experts are available for the development of bespoke numerical codes, training individuals and teams, and delivering advanced numerical methods, such as Algorithmic Differentiation (AD) to improve
46 SCIENTIFIC COMPUTING WORLD
FPGA memory access providing low-latency and low-power solution for compute intensive complex algorithm applications. Te Proc10A is supported by OpenCL, a unified programming model for accelerating algorithms on heterogeneous systems. OpenCL allows the use of a C-based programming language for
developing code across different platforms such as CPUs, GPUs, DSPs and FPGAs. In 2015, Gidel will release its 10G Low-Latency TCP/IP UDP FPGA IP core targeting Financial Market applications.
www.gidel.com
computational quality of client solutions.
www.nag.co.uk
Panasas (booth #700) is a leader in hybrid scale-out NAS for unstructured data, driving industry and
research innovation by accelerating workflows and simplifying data management. ActiveStor appliances leverage the patented PanFS storage operating system and DirectFlow protocol to deliver high performance and reliability at scale from an appliance that is as easy to manage as it is fast to deploy. Panasas storage is optimised for the most demanding workloads in energy, government, life sciences, manufacturing, media and entertainment as well as university environments, and has been deployed in more than 50 countries.
www.panasas.com
Prace (booth 1201),will present highlights of results from its six HPC systems; workshops on Prace Training and Women in HPC; and BoF sessions on the Shape Programme for SMEs and Women in HPC with an industrial focus. Te winner of the annual Prace ISC award will also be announced during the exhibition. Visitors are invited to enjoy a cocktail reception, test their skills in a Tatra car race video game based on HPC simulations, and win valuable prizes in the traditional Prace Treasure Hunt. Prace, the Partnership for Advanced
Computing in Europe, is a persistent pan- European Research Infrastructure of world-class supercomputers in all major architectural classes. Prace powers excellent science and engineering in academia and industry, addressing society’s grand challenges and serving as a vital catalyst in fostering European competitiveness and economic growth.
www.prace-ri.eu
Q-Leap Networks (booth #654) will present the brand-new version 9.1 of Qlustar, its full-fledged HPC cluster
operating system (OS). It is the first and only professional Debian/Ubuntu based Linux cluster solution, providing many unique features. Qlustar’s core is a lightweight, modular
Compute/Storage/Cloud Node OS. As a whole, it is a complete Linux distribution based on Debian/ Ubuntu. Easy and consistent cluster setup, keeping track of hard- and soſtware failures, cluster operation with ease, speed and control: QluMan, Qlustar’s management and monitoring framework takes care of this and more. With Qlustar, node provisioning belongs to the past: Just assign an OS image to a node and (re)boot. Fully integrated support for Lustre/BeeGFS storage clusters, GPU computing and high- availability configurations are supported amongst others.
www.qlustar.com
Univa (booth #1120) presents Universal Resource Broker, powered by Grid Engine at ISC. Te new solution enables organizations to achieve massive scalability of shared data centre resources and lay the foundation for the Internet of Tings. It works seamlessly with legacy systems. Universal Resource Broker allows enterprises to create a single, virtual, high throughput and high performance compute pool out of distributed data centre resources by integrating batch, low-latency workload, data centre services and Big Data frameworks. Universal Resource Broker highlights include: advanced policies and lifecycle management; centralised arbitration and resource allocation; centrally manage distributed applications, data centre services and big data frameworks; unified accounting and reporting; run and manage existing Apache Mesos frameworks without modification with high availability and automatic service fail-over.
www.univa.com/products
Rogue Wave (booth #1152) provides soſtware development tools for mission- critical applications. Our trusted solutions address the growing complexity of building great soſtware and accelerate the value gained from code across the enterprise. Te Rogue Wave portfolio of complementary, cross- platform tools helps developers quickly build applications for strategic soſtware initiatives. With Rogue Wave, customers improve soſtware quality and ensure code integrity, while shortening development cycle times.
www.roguewave.com
@scwmagazine l
www.scientific-computing.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56