All the best to everyone in 2024! A number of interesting things happened in HPC-AI last week, here’s a brief (5:18) run-down: Gelsinger’s updated Intel view on Moore’s Law; TSMC’s 1nm chip plans, Arizona fab labor dispute; Huawei’s improved financials,; DARPA’s “utility scale” quantum….
HPC News Bytes 20240103: Gelsinger on Moore’s Law, TSMC 1nm Plans, Huawei Financials, DARPA’s Quantum Project
January 3, 2024 by
Huawei OceanStor Pacific Scale-Out Storage Tops IO500 Rankings
June 9, 2023 by
The release of the latest IO500 ranking, the world’s most authoritative storage performance metric, revealed that the Cheeloo-1 system led the way in the 10-node rankings, thanks to the system’s use of Huawei OceanStor Pacific scale-out storage capabilities. The IO500 ranking evaluates….
NWP Development with Nearly 10x Higher Performance Provided by Huawei OceanStor Pacific Scale-Out Storage
May 30, 2023 by
ISC is an annual global event in which high performance computing (HPC) users and technology providers come together to discuss the prospects of HPC in different areas. A concerns to us all is weather forecasting….
From 24 Hours to 7 Minutes, Huawei OceanStor Pacific Accelerates Genome Sequencing
May 19, 2023 by
International Supercomputing Conference (ISC) is an annual conference that showcases the key technologies in the supercomputing field. It brings together experts from multiple specialist fields, including research into life sciences and genetics to shed light on the origins and mysteries in our lives. HPC….
The true cost of AI innovation
April 7, 2020 by
“As the world’s attention has shifted to climate change, the field of AI is beginning to take note of its carbon cost. Research done at the Allen Institute for AI by Roy Schwartz et al. raises the question of whether efficiency, alongside accuracy, should become an important factor in AI research, and suggests that AI scientists ought to deliberate if the massive computational power needed for expensive processing of models, colossal amounts of training data, or huge numbers of experiments is justified by the degree of improvement in accuracy.”
Why Hardware Acceleration Is The Next Battleground In Processor Design
June 14, 2019 by
In this special guest feature, Theodore Omtzigt from Stillwater Supercomputing writes that as workloads specialize due to scale, hardware accelerated solutions will continue to be cheaper than approaches that utilize general purpose components. “If you’re a CIO who manages integrations of third-party hardware and software, be aware of new hardware acceleration technologies that can reduce the cost of service delivery by orders of magnitude.”
Podcast: Multicore Scaling Slow Down, and Fooling AI
March 25, 2019 by
In this podcast, the Radio Free HPC team has an animated discussion about multicore scaling, how easy it seems to be to mislead AI systems, and some good sized catches of the week. “As CPU performance improvements have slowed down, we’ve seen the semiconductor industry move towards accelerator cards to provide dramatically better results. Nvidia has been a major beneficiary of this shift, but it’s part of the same trend driving research into neural network accelerators, FPGAs, and products like Google’s TPU.”
Video: Frontiers of AI Deployments in HPC on Arm
February 10, 2019 by
In this video from Arm HPC Asia 2019, Elsie Wahlig leads a panel discussion on Frontiers of AI deployments in HPC on Arm. “Topics at the workshop covered all aspects of the Arm server ecosystem, from chip design, hardware, software architecture and standardization to performance tuning, and applications in biology, medicine, meteorology, astronomy, geography etc. It is exciting to see that Arm servers are being used in so many areas, contributing significantly to the global economy.”
Huawei Unveils “Industry’s Highest-Performance ARM-based CPU”
January 7, 2019 by
Today, Huawei announced “the industry’s highest-performance ARM-based CPU.” Called Kunpeng 920, the new CPU is designed to boost the development of computing in big data, distributed storage, and ARM-native application scenarios. “Kunpeng 920 integrates 64 cores at a frequency of 2.6 GHz. This chipset integrates 8-channel DDR4, and memory bandwidth exceeds incumbent offerings by 46%. System integration is also increased significantly through the two 100G RoCE ports. Kunpeng 920 supports PCIe 4.0 and CCIX interfaces, and provides 640 Gbps total bandwidth. In addition, the single-slot speed is twice that of the incumbent offering, effectively improving the performance of storage and various accelerators.”
Atos Launches Open Edge and HPC Initiative for the coming 5G World
October 11, 2018 by
Today Atos announced a joint effort with E4, the Jülich Supecomputing Centre, Fraunhofer FOKUS, Huawei, Mellanox, and SUSE to help shorten time-to-market for HPC and Edge deployments. “Collaborative and grassroots initiatives focused on solving real world problems are the hallmark of a vibrant ecosystem,” said Jean-Marc Denis, Head of Strategy, BigData and Security at Atos. “Addressing the challenge of supporting one trillion connected devices requires today’s infrastructure to evolve. Only the Arm ecosystem has the flexibility, scalability, and technical breadth to bring best-in-class solutions to market in areas as diverse as edge and high-performance compute.”
