The Accenture Engineering Compute (AEC) digital platform is a first mover in the industry with a highly differentiated AIML/analytics based Job-resource prediction and orchestration engine to ensure the most efficient placement of HPC workloads on-prem or in the cloud. The solution delivers dramatic gains in capital equipment utilization (~2x) , job throughput (~30%) and business agility with automated cloud bursting for HPC/Grid computing environments.
Video: Mellanox HDR InfiniBand Speeds HPC and Ai Applications with SHARP Technologies
November 26, 2018 by
In this video, Gilad Shainer from Mellanox describes how the company’s newly available HDR 200 Gigabit/sec InfiniBand solutions can speed up HPC and Ai applications. “We are proud to see the first Mellanox HDR InfiniBand ConnectX-6 adapters and Quantum switches based supercomputer in the world,” said Gilad Shainer, vice president of marketing at Mellanox Technologies. “The smart In-Network Computing acceleration engines that InfiniBand enables will deliver the highest performance, efficiency and scalability for the University of Michigan users, for both HPC and AI applications.”
Radio Free HPC Looks at TOP500 Trends on the Road to Exascale
November 26, 2018 by
In this podcast, the Radio Free HPC team looks at the semi-annual TOP500 BoF presentation by Jack Dongarra.
The TOP500 list of supercomputers serves as a “Who’s Who” in the field of High Performance Computing. “This BoF will present detailed analyses of the TOP500 and discuss the changes in the HPC marketplace during the past years. The BoF is meant as an open forum for discussion and feedback between the TOP500 authors and the user community.”
An Update on Piz Daint – the Fastest Supercomputer in Europe
November 25, 2018 by
In this video from SC18 in Dallas, Michele De Lorenzi from CSCS in Switzerland provides an update on Piz Daint, the fastest supercomputer in Europe. “Recently upgraded with two additional cabinets full of NVIDIA V100 GPUs, the Cray XC50 system comes in at #5 in the world with 21.23 Petaflops of performance on the LINPACK benchmark.”
Dr. Eng Lim Goh Fireside Chat on the Convergence of HPC & Ai
November 23, 2018 by
In this video from SC18, Dr. Eng Lim Goh from HPE describes the Convergence of HPC and Ai. “Data analytics and insights are fueling innovation across scientific research, product and service design, customer experience management, and process optimization. Real-time analytics with in-memory computing, big data analytics, insights from simulation and modeling fueled by HPC and predictive analytics with artificial intelligence (AI) are core capabilities required by data-driven organizations looking to gain competitive advantage with their digital transformation initiatives.”
Singularity Containers Power NVIDIA Full Galaxy Simulation
November 22, 2018 by
In this video from the NVIDIA Showcase event at SC18, Jensen Huang hosts a demo of Singularity containers running a full galaxy simulation. “This has to be the best Container demo ever,” said Huang. “As part of that effort, Huang announced new multi-node HPC and visualization containers for the NGC container registry, which allow supercomputing users to run GPU-accelerated applications on large-scale clusters. NVIDIA also announced a new NGC-Ready program, including workstations and servers from top vendors.”
AMD EPYC Powers Tyan Servers for Data-intensive Computing
November 21, 2018 by
In this video from SC18, Philip Maher from Tyan describes how the company is packaging AMD EPYC processors with innovative server configurations for tackling data-intensive workloads. “AMD EPYC processors are based on the 14nm “Zen” x86 core architecture with 32 cores and 64 threads, featuring 8 memory channels and up to16 DIMMs per socket. The new powerful processor allows TYAN to offer the optimal balance of computing, memory and I/O for the customers. By adopting the latest AMD EPYC processor technology, TYAN brings high memory channel bandwidth and PCI Express high speed I/O connectivity features to enterprises and datacenters.”
Video: ECP Launches Extreme-Scale Scientific Software Stack 0.1 Beta
November 20, 2018 by
Last week at SC18 in Dallas, the Exascale Computing Project released a portion of the next version of collaboratively developed products that compose the ECP software stack, including libraries and embedded software compilers. “Mike Heroux, ECP Software Technology director, said in an interview at SC18 that the software pieces in this release represent new capabilities and, in most instances, are highly tested and quite robust, and point toward exascale computing architectures.”
Record SC18 Attendance a Bellwether for Growth in HPC Market
November 20, 2018 by
The SC18 conference drew a record-breaking 13,071 attendees, making it the largest SC conference of all time. As the premier international conference showcasing high performance computing, networking, storage, and analysis, the conference and exhibition infused the local economy with more than $40 million in revenue, according to the local Dallas Convention Bureau.
Overclocked NVIDIA DGX-2H Cluster Lands at #61 on the TOP500
November 19, 2018 by
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 36 DGX-2H devices with 3 Petaflops of LINPACK performance was just ranked #62 on the TOP500 list of the world’s fastest supercomputers.
