Back to Table of contents

Primeur weekly 2018-11-26

Focus

European Open Science Cloud catalogue for HPC: more animation than information ...

Exascale supercomputing

Bringing European parallel programming technology to the Exascale era ...

Berkeley Lab and Oak Ridge National Lab share 2018 ACM Gordon Bell Prize ...

Portugal supports Spanish application for pre-exascale EuroHPC supercomputer ...

Quantum computing

Spotting nature's own evolution of quantum tricks could transform quantum technology ...

Quantum artificial life created on the cloud ...

Quantum Machines raises $5.5 million to develop next generation of systems for quantum computers ...

Focus on Europe

Barcelona Supercomputing Center provides services to European Open Science Cloud portal ...

European Open Science Cloud Portal is now up and running ...

Atos was chosen to deliver Finland’s next supercomputer ...

Gauss Centre for Supercomputing sponsors Research Paper Award at ISC19 - Call for Papers is open ...

Middleware

Astronomy and particle physics combine forces for European Open Science Cloud ...

Hardware

Meet Michael, the supercomputer designed to accelerate UK research for EV batteries ...

Atos supports Indian government in its National Supercomputing Mission ...

LINE Corporation collaborates with Mellanox and Cumulus Networks to power advanced messaging platform ...

Dell EMC gains high performance computing momentum and expands portfolio ...

DOE machines dominate record-breaking SC18 ...

Supermicro extends industry-leading portfolio of NVIDIA GPU servers with new systems at GTC China ...

NVIDIA Turing T4 Cloud GPU adoption accelerates ...

Applications

Encouraging prospects for moon hunters ...

INCITE grants awarded to 62 computational research projects ...

NCSA's Student Cluster Competition team places third at SC18 ...

Call for HPC for Energy Innovation proposals ...

NVIDIA HGX-2 GPU-accelerated platform gains broad adoption ...

NVIDIA HGX-2 GPU-accelerated platform gains broad adoption


NVIDIA HGX-2 server platform
20 Nov 2018 Suzhou - NVIDIA has announced broad adoption of the NVIDIA HGX-2 server platform, the world's most powerful accelerated server platform, for AI deep learning, machine learning and high performance computing. Delivering two petaflops of compute performance in a single node, NVIDIA HGX-2 can run AI machine learning workloads nearly 550x faster, AI deep learning workloads nearly 300x faster and HPC workloads nearly 160x faster, all compared to a CPU-only server.

Leading technology companies around the world are taking advantage of HGX-2's record-setting performance. The newest adoptions announced today at GTC China include:

  • Baidu and Tencent are using HGX-2 for a wide range of even more powerful AI services, both for their internal use and for their Cloud customers.
  • Inspur is China's first to build an HGX-2 server. Its Inspur AI Super-Server AGX-5 is designed to solve the performance expansion problem of AI, deep learning and HPC.
  • Huawei, Lenovo and Sugon announced that they have become NVIDIA HGX-2 Cloud server platform partners.

Previously announced HGX-2 support and adoption comes from leading global server makers, including Foxconn, Inventec, QCT, Quanta, Supermicro, Wistron and Wiwynn. Additionally, Oracle announced last month its plans to bring the NVIDIA HGX-2 platform to Oracle Cloud Infrastructure in both bare-metal and virtual machine instances, giving customers access to a unified HPC and AI computing architecture.

"Leading technology companies are quickly taking advantage of HGX-2, the most powerful Cloud node in history", stated Ian Buck, vice president and general manager of Accelerated Computing at NVIDIA. "With HGX-2's unmatched compute power and versatile design, companies around the world are able to build new products and services that can scale to solve immense compute challenges and address some of the world's most pressing problems."

The HGX-2 Cloud server platform features multi-precision computing capabilities, providing unique flexibility to support the future of computing. It fuses high-precision FP64 and FP32 for accurate HPC, while also enabling faster, reduced-precision FP16 and INT8 for deep learning and machine learning.

The HGX-2 delivers unmatched compute power. It incorporates such breakthrough features as NVIDIA NVSwitch interconnect fabric, which seamlessly links 16 NVIDIA Tesla V100 Tensor Core GPUs to work as a single, giant GPU delivering two petaflops of AI performance. It also provides 0.5TB of memory and 16TB/s of aggregate memory bandwidth.
Source: NVIDIA

Back to Table of contents

Primeur weekly 2018-11-26

Focus

European Open Science Cloud catalogue for HPC: more animation than information ...

Exascale supercomputing

Bringing European parallel programming technology to the Exascale era ...

Berkeley Lab and Oak Ridge National Lab share 2018 ACM Gordon Bell Prize ...

Portugal supports Spanish application for pre-exascale EuroHPC supercomputer ...

Quantum computing

Spotting nature's own evolution of quantum tricks could transform quantum technology ...

Quantum artificial life created on the cloud ...

Quantum Machines raises $5.5 million to develop next generation of systems for quantum computers ...

Focus on Europe

Barcelona Supercomputing Center provides services to European Open Science Cloud portal ...

European Open Science Cloud Portal is now up and running ...

Atos was chosen to deliver Finland’s next supercomputer ...

Gauss Centre for Supercomputing sponsors Research Paper Award at ISC19 - Call for Papers is open ...

Middleware

Astronomy and particle physics combine forces for European Open Science Cloud ...

Hardware

Meet Michael, the supercomputer designed to accelerate UK research for EV batteries ...

Atos supports Indian government in its National Supercomputing Mission ...

LINE Corporation collaborates with Mellanox and Cumulus Networks to power advanced messaging platform ...

Dell EMC gains high performance computing momentum and expands portfolio ...

DOE machines dominate record-breaking SC18 ...

Supermicro extends industry-leading portfolio of NVIDIA GPU servers with new systems at GTC China ...

NVIDIA Turing T4 Cloud GPU adoption accelerates ...

Applications

Encouraging prospects for moon hunters ...

INCITE grants awarded to 62 computational research projects ...

NCSA's Student Cluster Competition team places third at SC18 ...

Call for HPC for Energy Innovation proposals ...

NVIDIA HGX-2 GPU-accelerated platform gains broad adoption ...