RIKEN will add Nvidia GPUs and contract Nvidia to design systems integrating its accelerators into FugakuNEXT. Fujitsu remains contracted to build the successor and provide the MONAKA-X Arm-based CPU. Nvidia's design will explore advanced CPU–GPU connection technologies and consider advanced memory technologies. Specific GPU models, counts, and networking choices have not been disclosed. FugakuNEXT targets to exceed 600 exaFLOPS in FP8 (sparse) and aspires to become the world's first zetta-scale system. RIKEN aims for more than a fivefold hardware performance boost over Fugaku and a hundredfold increase in application performance, with a focus on AI training and GPU-optimized HPC.
Japanese research institution RIKEN has decided it needs GPUs for its next generation "FugakuNEXT" supercomputer and has signed Nvidia to supply them and design the systems needed to get them working. RIKEN is home to Fugaku, a machine that from mid-2020 spent two years atop the TOP500 list of Earth's mightiest supercomputers. The machine is still in seventh place, but RIKEN wants an upgrade and has already awarded a contract to Fujitsu to build its successor and the custom Arm-based CPU called "MONAKA-X"
But whatever ends up inside FugakuNEXT, it will be very fast. RIKEN's announcement of its Nvidia collaboration states it aims for the machine to exceed 600 exaFLOPS (EFLOPS) in FP8 precision (sparse), and expects the machine "to become the world's first 'zetta-scale' system." The research outfit added that involving Nvidia means it's set a target of "more than a fivefold improvement in hardware performance over Fugaku," and it will pursue "a hundredfold increase in application performance" compared to its current supercomputer.
Collection
[
|
...
]