Hewlett Packard Enterprise to build TSUBAME4.0 supercomputer for Tokyo Tech

Hewlett Packard Enterprise (HPE) has been chosen to construct the TSUBAME4.0 by the Tokyo Institute of Technology (Tokyo Tech) Global Scientific Information and Computing Center (GSIC).

TSUBAME4.0 is an advanced supercomputer aimed at accelerating artificial intelligence (AI) driven scientific discoveries in fields such as medicine, materials science, climate research, and urban turbulence.

Tokyo Tech is a world-renowned institution in the realm of science and technology. The TSUBAME4.0 supercomputer will empower users to train numerous AI models and execute computational science and analytics applications simultaneously, boosting research efforts and enhancing productivity.

Procured under Japanese government procurement regulations and awarded to HPE Japan, TSUBAME4.0 is set to be fully operational by the spring of 2024. It will be housed in a newly constructed facility on Tokyo Tech’s Suzukakedai campus.

Hewlett Packard Enterprise to build TSUBAME4.0 supercomputer for Tokyo Tech. Photo courtesy of Business Wire.

Justin Hotard — Hewlett Packard Enterprise executive vice president and general manager of AI & Labs said: “National research centers across the globe rely on supercomputing to drive science, engineering, and AI initiatives to understand complex phenomena and accelerate innovation.

“Tokyo Tech is a powerful example of an organization that continues to invest in supercomputing and opens it to a broader community to enable cutting-edge research and new capabilities in AI.

“We are proud to continue our collaboration with Tokyo Tech and NVIDIA to build TSUBAME4.0, which features HPE Cray supercomputing innovation to deliver the massive performance required to augment Tokyo Tech’s ongoing scientific and AI-driven missions.”

TSUBAME4.0 will be built utilizing HPE Cray XD6500 supercomputers, which offer exceptional performance and specialized capabilities for running complex scientific research workloads involving modeling and simulation. These supercomputers are also highly compact and purpose-built to support accelerated compute, optimized for AI, analytics, and image-intensive applications, said Hewlett Packard Enterprise.

With a theoretical peak performance of 66.8 petaflops at 64-bit double precision and an impressive 952 petaflops at 16-bit half-precision, TSUBAME4.0 will deliver 20 times more accelerated compute power than its predecessor, TSUBAME3.0. According to Hewlett Packard Enterprise, this substantial increase in performance will cater to the computational requirements of numerous users, positioning TSUBAME4.0 as a “supercomputer for everyone.”

Professor Yutaka Akiyama from Tokyo Tech School of Computing said: “TSUBAME has been supporting our research on cyclic peptide drug discovery, which is anticipated to become the next-generation medicine.

“TSUBAME has always been our partner in the daring challenges of achieving world’s first. It has been supporting reproduction of biophysical phenomena with hundred-fold larger simulations, and through exhaustive calculation on hundreds of cases has generated quantitative proof of predictive ability.

“With the significantly accelerated TSUBAME4.0, we look forward to its support in realizing intelligent drug discovery through large-scale molecular simulation and fusing it with deep learning technology in generating predictive models.”