RIKEN Supercomputer Is Number One in the World on the Demanding HPCG Benchmark Test
Authors: Alex Larzelere, Bob Sorensen, Earl Joseph, Steve Conway and Alex Norton
Publication Date: June 2018
Length: 3 pages
At SC17 in Denver, the Japanese RIKEN K computer emerged for the third straight time as the world’s most powerful supercomputer based on the High Performance Conjugate Gradient (HPCG) benchmark list. Although China’s Tianhe-2 supercomputer has been widely seen as number one in the world based on its LINPAC rating, the HPCG test that the K computer excelled on may be more representative of the range of real-world HPC problems encounter by users. Riken’s K computer has been either number one or two since the HPCG list came out in 2014.
The AI Hardware Summit: A Recap
Alex Norton, Bob Sorensen, Steve Conway and Earl Joseph
This inaugural, two-day AI Hardware summit held in Mountain View, California, at the Computer History Museum, brought together researchers, vendors, and users to explore the development of the AI ecosystem from a hardware perspective. Large companies, startups, and analysts joined to hear over 30 speakers and roundtables. Although the overall theme was all AI hardware, many of the presentations focused on AI processors and the work that is being done to design hardware to further the development of the evolving and growing field of AI, machine learning, and deep learning.
November 2018 | Quick Take
ORNL Announces Newest Leadership HPC: It’s More Than Just Exaflops
The Department of Energy at Oak Ridge National Laboratory (ORNL) recently announced plans for the development of a 1.5 exaflops system called Frontier to be delivered in 2021. US HPC maker Cray and chip maker AMD are the two key US commercial partners in this effort. Despite numerous press articles centered on the 1.5 exaflops peak performance of Frontier, ORNL's original RFP released in April of 2018 clearly called out the diverse workload requirements that Frontier would have to successfully handle that span the traditional modeling and simulation sector, big data analysis, and AI applications, while demonstrating a 50X improvement in solving key DOE science problems that today run at the 20 petaflops level. To meet those ambitious goals, strong support from DOE's companion $1.7 billion Exascale Computing Project (ECP) will be critical.
May 2019 | Quick Take