Since 1986 - Covering the Fastest Computers in the World and the People Who Run Them

Language Flags

Topics » Processors

Features

Adapting Algorithms to Modern Hybrid Architectures

Aug 13, 2014 |

Technology, like other facets of life, commonly experiences cycles of rapid change followed by periods of relative stability. Computing has entered a stage of increased architectural diversity, as evidenced by the rise of accelerators, coprocessors, and other alternatives, like ARM processors. An international team of researchers explores how these various supercomputing architectures perform on parallelized turbulent Read more…

Compilers and More: MPI+X

Jul 16, 2014 |

At ISC’14, there was intense and continuing interest in the choice of a standard approach for programming the next generation HPC systems. While not guaranteed, many of these systems are likely to be large clusters of nodes with multicore CPUs and some sort of attached accelerators. A standard programming approach is necessary to convince developers, and Read more…

Student Supercomputing Competition Embraces GPU-Power

Jun 26, 2014 |

The third and final day of ISC14 concluded with a ceremony honoring one of the week’s most popular events, the Student Cluster Challenge. Taking home first prize for the second straight year was the team from the Centre for HPC (CHPC) in South Africa. Jointly sponsored by Dell, NVIDIA and Mellanox, the undergraduate team relied on Read more…

Micron, Intel Reveal Memory Slice of Knight’s Landing

Jun 24, 2014 |

As we move into the pre-exascale era, issues of power consumption, network bandwidth, I/O and other issues will continue to push increasing integration. This was a key theme during the International Supercomputing Conference this week in Germany where Intel’s Raj Hazra provided an early look into how it will integrate various pieces of the future Read more…

GPUs Add Up For ARM Chips In HPC

Jun 23, 2014 |

The first wave of credible 64-bit ARM processors are coming to market late this year or early next, and as is usually the case, the high-performance computing community is getting first crack at figuring out how these chips might be deployed to run various kinds of simulations more efficiently or cost effectively. Applied Micro, which Read more…

Short Takes

NVIDIA Boasts ‘Compelling HPC Solution’

Aug 20, 2014 |

Today marks the official release of the NVIDIA CUDA Toolkit version 6.5, which had previously been only available in its pre-release form. In a company blog post, NVIDIA’s Chief Technologist for GPU Computing Software Mark Harris covers the toolkit’s new features and improvements, including “support for CUDA Fortran in developer tools, user-defined callback functions in Read more…

Brainy IBM Chip Packs One Million Neuron Punch

Aug 7, 2014 |

IBM researchers have developed a super-efficient chip inspired by the functioning of the human brain. Named TrueNorth, the chip features 5.4 billion transistors arranged in a network of 4,096 neurosynaptic cores, yielding the equivalent of one million neurons and 256 million synapses. Despite being one of the largest CMOS chips ever built, TrueNorth consumes just 70mW during Read more…

Is This the Exascale Breakthrough We’ve Been Waiting For?

Aug 6, 2014 |

An animated video, narrated by the inimitable Professor Heinz Wolff, popped up on YouTube last month, detailing a prototype optical processor with some remarkable claims. The company behind the effort, UK-based startup Optalysys, says it is on track to deliver exascale levels of processing power on a standard-sized desktop computer within the next few years. Read more…

New Photoresist Could Add Years to Moore’s Law

Jul 17, 2014 |

Over the last five decades, microprocessors have gotten cheaper and more powerful as predicted by Gordon Moore’s famous observation, which states that the number of transistors on an integrated circuit doubles every two years. However, the limits of miniaturization can only go so far before crossing the quantum threshold. Currently there is some progress left Read more…

IBM Invests $3 Billion in Next-Gen Chip Design

Jul 14, 2014 |

The slow-down of Moore’s law has chip makers expanding their efforts beyond the scaling of silicon-based transistors to include the development of alternative materials and computing approaches. Such is the case with IBM, which last week launched a $3 billion research initiative focused on getting to “7 nanometers and beyond.” The five year program comes Read more…

Off the Wire

OLCF’s GPU Hackathon to Begin October 27

Aug 20, 2014 |

Aug. 20 — We are excited to announce OLCF’s first ever hackathon will take place the week of October 27th, 2014. Teams of developers will attend a 5-day intensive hands-on workshop guided by OpenACC mentors. These experts come from labs, universities and vendors and will guide your team from start to finish. What’s the Format? We’re looking Read more…

Clemson Named CUDA Teaching Center by NVIDIA

Aug 19, 2014 |

CLEMSON, S.C., Aug. 19 — Clemson University Monday announced that it has been named a CUDA Teaching Center by NVIDIA, the world leader in visual computing. As a CUDA Teaching Center, Clemson University plans to expand course offerings in cutting-edge computing techniques that could help researchers tackle a variety of challenges, from finding new cures to Read more…

NVIDIA VCA Now Shipping

Aug 13, 2014 |

VANCOUVER, British Columbia, Aug. 13 – NVIDIA today announced that its Visual Computing Appliance, known as the NVIDIA VCA, is now shipping. NVIDIA VCA dramatically accelerates ray tracing, enabling users to interact with computer models of such high visual fidelity that it can eliminate the need for 3D physical prototypes. Engineered and built by NVIDIA, the appliance was Read more…

NVIDIA Introduces New Quadro GPU Lineup

Aug 12, 2014 |

VANCOUVER, British Columbia, Aug. 12 – NVIDIA today unveiled its next generation of NVIDIA Quadro GPUs – providing new tools and technologies to meet the visual computing needs of the world’s leading designers, artists and scientists. The new lineup delivers an enterprise-grade visual computing platform with up to twice the application performance and data-handling capability of the previous generation. It Read more…

AMD FirePro S9150 Server Card Unveiled

Aug 6, 2014 |

SUNNYVALE, Calif., Aug. 6 — AMD today announced the AMD FirePro S9150 server card — the most powerful server Graphics Processing Unit (GPU) ever built for High Performance Computing. Based on the AMD Graphics Core Next (GCN) architecture, the first AMD architecture designed specifically with compute workloads in mind, the AMD FirePro S9150 server card Read more…