[Due to the increasing size of the archives, each topic page now contains only the prior 365 days of content. Access to older stories is now solely through the Monthly Archive pages or the site search function.]
Cray unveils 100 petaflop XC30 supercomputer
November 08, 2012
|Cray XC30. Click to enlarge.|
Cray Inc. launched its next-generation high-end supercomputing system: the Cray XC30 supercomputer. Previously code-named “Cascade,” the Cray XC30 supercomputer combines the new Aries interconnect, Intel Xeon processors, Cray’s fully-integrated software environment, and innovative power and cooling technologies to create a production supercomputer that is designed to scale high performance computing (HPC) workloads of more than 100 petaflops.
The US Department of Energy’s (DOE) Oak Ridge National Laboratory recently launched its new 20 petaflop supercomputer, Titan—a hybrid-architecture Cray XK6 system. (Earlier post.)
High Performance Computing key enabler for accelerating development of high efficiency engines
November 05, 2012
|Increasing complexity of vehicle design is driving the need for better simulation and more powerful computers. Wagner and Pannala. Click to enlarge.|
The complexity of new and future vehicles—driven by the need for increasing fuel efficiency and decreasing emissions with ever-changing drive-cycle demands and environmental conditions—is adding unprecedented flexibility in design and driving the need for better simulation and more powerful computers, observed Dr. Robert M. Wagner, Director of the Fuels Engines and Emissions Research Center, and Dr. Sreekanth Pannala, Senior Research Staff Member in the Computing and Computational Sciences Directorate at Oak Ridge National Laboratory in a keynote talk at the recent Global Powertrain Conference.
Advances in high performance computing (HPC) resources are leading to a new frontier in engine and vehicle development, Wagner and Pannala suggested, including the ability to produce detailed simulations to generate benchmark data; engineering simulations to explore the design space (e.g., injector optimization at ORNL); and reduced models for design optimization and control strategies. In general, HPC can help solve problems which were once thought unsolvable, they noted.
DOE awards $62.5M to accelerate development of exascale supercomputers
August 07, 2012
Under an initiative called FastForward, the Department of Energy (DOE), Office of Science and the National Nuclear Security Administration (NNSA) have awarded $62.5 million in research and development (R&D) contracts to five leading companies in high performance computing to accelerate the development of next-generation exascale supercomputers critical for national defense, scientific research, energy security, and economic competitiveness.
AMD, IBM, Intel, Nvidia and Whamcloud received awards to advance “extreme scale” computing technology with the goal of funding innovative R&D of critical technologies needed to deliver next generation capabilities within a reasonable energy footprint. DOE missions require exascale systems that operate at quintillions of floating point operations per second. (Earlier post.)