• December 2019
    M T W T F S S
    « Nov    
     1
    2345678
    9101112131415
    16171819202122
    23242526272829
    3031  

World’s Fastest Supercomputers Hit Higher Speeds with Linux

 ZDNet
Steven J. Vaughan-Nichols
November 18, 2019

The latest Top500 supercomputer ratings found Linux-powered supercomputers currently average 1.14 petaflops in speed, with the Oak Ridge National Laboratory’s Summit system topping the list with a High-Performance Linpack benchmark of 148.6 petaflops. Ranked second is Lawrence Livermore National Laboratory’s Sierra system, with a speed of 94.6 petaflops, despite using the same Power9 central-processing units and Nvidia Tesla V100 graphic-processing units as Summit. Although China owns nearly half the world’s fastest supercomputers, U.S. systems have a 37.8% aggregate performance share to China’ 31.9%. The Green500 list of the most energy-efficient supercomputers ranked the A64FX prototype the top system, with 16.9 gigaflops/watt. Meanwhile, HDR InfiniBand-based machines account for 40% of the Top500’s aggregate performance, and Ethernet-based systems account for 29%.

MORE

IBM Hopes to Change Weather Forecasting Around the Globe Using Big Data, Supercomputer

 CNBC
Steve Liesman
November 14, 2019

IBM has launched a global weather model that it says offers more accurate forecasts for the entire world and can provide details for regions as small as two miles wide. The Global High-Resolution Atmospheric Forecasting (GRAF) model runs only on IBM’s new DYEUS supercomputer, which will publish 12 trillion pieces of daily weather data and process hourly forecasts; many global weather models only update every six to 12 hours. Individuals can access data via the Weather Channel app on smartphones, and in other sources employing IBM data. DYEUS utilizes IBM’s Power 9 processing chips, and graphics processing units used in video gaming, to expedite visual output processing. GRAF, which IBM said can collect data from aircraft sensors and smartphones, will deliver forecasts of up to 15 hours for 26 million locations worldwide.

MORE

Graphene Enables Clock Rates in the Terahertz Range

 Helmholtz-Zentrum Dresden-Rossendorf
Christine Bohnet
September 10, 2018

Researchers at Helmholtz Zentrum Dresden-Rossendorf (HZDR), the University of Duisburg-Essen (UDE), and the Max Planck Institute for Polymer Research (MPI-P), all in Germany, have demonstrated that graphene can convert electronic signals with frequencies in the gigahertz range extremely efficiently into signals with several times higher frequency. The researchers used graphene containing many free electrons from the interaction of the graphene with the substrate onto which it is deposited, as well as with the ambient air. When these mobile electrons are excited by an oscillating electric field, they share their energy with the other electrons in the graphene, which react like a heated fluid. An electronic “vapor” forms within the graphene, causing rapid and strong changes in its conductivity. MPI-P researcher Mischa Bonn said, “We have demonstrated that carbon-based electronics can operate extremely efficiently at ultrafast rates. Ultrafast hybrid components made of graphene and traditional semiconductors are also conceivable.”

MORE

European Supercomputer Shines With Energy Efficiency eeNews Europe

Christoph Hammerschmidt
June 27, 2018

As Europe seeks to compete globally in developing innovative supercomputer architectures, the Julich Supercomputing Center (JSC) in Germany has launched JUWELS (Julich Wizard for European Leadership Science), marking significant progress in a new generation of flexible, modular supercomputers. JUWELS ranked 23rd on the most recent TOP500 supercomputer list, making it the fastest German system. JSC’s Thomas Lippert believes the modular design is critical to an affordable and energy-efficient technology that can aid forthcoming exascale systems. Lippert’s adaptable design concept, known as “Smart Exascale,” provides for a supercomputer with several specialized modules that can be dynamically and flexibly combined via software. The cluster module’s Intel Xeon 24-core Skylake CPUs allow for a theoretical peak performance of up to 12 petaflops, which equals the approximate computing power of 60,000 PCs. The module has extremely energy-efficient hot water cooling, allowing it to cool the majority of the waste heat with hot water directly with the outside air without additional cooling generators. Next year, JUWELS will receive a booster module for massively parallel applications that will multiply computing power. The cluster module reached a computing speed of 6.2 petaflops in initial test runs based on the Linpack benchmark.

MORE

Move Over, China: U.S. Is Again Home to World’s Speediest Supercomputer

The New York Times
Steve Lohr, June 8, 2018

Oak Ridge National Laboratory’s Summit system is expected to be named the world’s fastest supercomputer in the Top500 rankings coming out later this month, effectively ending China’s five-year reign at the top of the list, says the University of Tennessee’s Jack Dongarra. Summit can execute calculations of 200 petaflops a second, and is expected to help expedite the development of artificial intelligence and other technologies. Summit is more than twice as fast as the leading supercomputer ranked in the most recent Top 500 list in November, which is based at China’s National Supercomputing Center. Powering the Oak Ridge system are 9,216 central processors from IBM and 27,648 graphics processors from Nvidia interconnected by 185 miles of fiber-optic cable. Summit is viewed as a stopgap measure, as supercomputers five times faster are in the works both in the U.S. and overseas.

More

UT Austin’s New Supercomputer Stampede2 Storms Out of the Corral in Support of U.S. Scientists

UT News
Faith Singer-Villalobos
July 28, 2017

The University of Texas at Austin’s (UT Austin) Texas Advanced Computing Center (TACC) has launched Stampede2, the most powerful supercomputer at any U.S. university, which UT Austin president Gregory L. Fenves says will enable researchers “to take on the greatest challenges facing society.” Stampede2 was built with a $30-million National Science Foundation (NSF) grant, and its applications will include large-scale models and data analyses using thousands of processors simultaneously, and smaller computations or interactions via Web-based community platforms. TACC executive director Dan Stanzione predicts Stampede2 “will serve as the workhorse for our nation’s scientists and engineers, allowing them to improve our competitiveness and ensure that UT Austin remains a leader in computational research for the national open science community.” Stampede2 will have a peak performance of 18 petaflops while consuming half the power of Stampede1. It will be made available to researchers via NSF’s Extreme Science and Engineering Discovery

MORE

Google Plans to Demonstrate the Supremacy of Quantum Computing

IEEE Spectrum, Rachel Courtland
May 24, 2017

Google researchers say they plan to boost the volume of superconducting qubits built on integrated circuits (ICs) to create a 7×7 array and push operations to the limits of even the best supercomputers, demonstrating “quantum supremacy” by year’s end. The team says it will perform operations on a 49-qubit system that will trigger chaotic evolution yielding what appears to be random output, which classical computers can model for smaller systems. University of California, Santa Barbara professor John Martinis says the qubits constituting the array also could be employed to build larger “universal” quantum systems with error correction, capable of performing useful tasks such as decryption. Martinis says the challenge of scaling up the quantum IC involves maintaining qubits’ function without losing fidelity or boosting error rates. “Error rate and scaling tend to kind of compete against each other,” he notes. The team also sees the possibility of scaling up systems beyond 50 qubits without error correction.

 

MORE