Overclocked NVIDIA DGX-2H Cluster Lands at #62 on the TOP500
In this video from SC18 in Dallas, Marc Hamilton from NVIDIA describe the all new overclocked DGX-2H supercomputer. Built by NVIDIA, a cluster of 32 DGX-2 devices was just ranked #62 on the TOP500 list of the world's fastest supercomputers.
Learn more: https://blogs.nvidia.com/blog/2018/11/09/sc18-dgx-2-us-national-labs/
Sign up for our insideHPC Newsletter: http://insidehpc.com/newsletter
Видео Overclocked NVIDIA DGX-2H Cluster Lands at #62 on the TOP500 канала InsideHPC Report
Learn more: https://blogs.nvidia.com/blog/2018/11/09/sc18-dgx-2-us-national-labs/
Sign up for our insideHPC Newsletter: http://insidehpc.com/newsletter
Видео Overclocked NVIDIA DGX-2H Cluster Lands at #62 on the TOP500 канала InsideHPC Report
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Enabling Applications to Exploit SmartNICs and FPGAs
NEC Accelerates HPC with Vector Computing at ISC 2018
Cray Sonexion Storage Takes Lustre to Infinite Scale
DAOS: Scale-Out Software-Defined Storage for HPC/Big Data/AI Convergence
Perlmutter: a 2020 Pre-Exascale GPU-Accelerated System for NERSC
Optics for the Cloud – A New Approach to Data Centre Technology
Managing Genomics Data with DDN at the Sanger Institute
Panel Discussion: The Convergence of AI and HPC
How AI is Reshaping HPC
Architecting Flash for Scale and Performance in HPC
E4-ARKA: ARM64+GPU+IB is Now Here
Kx Streaming Analytics Demo Easily Crunches 1.2 Billion NYC Taxi Data points using Intel Xeon Phi
NEC Steps up with SX-Aurora Vector Engine for HPC
An Update on CXL Specification Advancements
MCDRAM (High Bandwidth Memory) on Knights Landing
HIP and CAFFE Porting and Profiling with AMD's ROCm
Enhancing OFI for Invoking Acceleration Capabilities on an Integrated Networking/Accelerator FPGA...
Transtec Remote Visualization
Accelerating TensorFlow with RDMA for High-Performance Deep Learning
T10-DIF offload
The Kokkos C++ Performance Portability EcoSystem