ABCI 3.0: Evolution of the leading AI infrastructure in Japan
This infrastructure aims to accelerate AI research, development, and workforce training, particularly for generative AI, but is incremental as an upgrade to an existing system.
The paper introduces ABCI 3.0, an upgraded AI infrastructure in Japan with 6128 NVIDIA H200 GPUs, achieving 6.22 exaflops peak performance, which is 7 to 13 times faster than its predecessor, and doubling storage capacity and performance.
ABCI 3.0 is the latest version of the ABCI, a large-scale open AI infrastructure that AIST has been operating since August 2018 and will be fully operational in January 2025. ABCI 3.0 consists of computing servers equipped with 6128 of the NVIDIA H200 GPUs and an all-flash storage system. Its peak performance is 6.22 exaflops in half precision and 3.0 exaflops in single precision, which is 7 to 13 times faster than the previous system, ABCI 2.0. It also more than doubles both storage capacity and theoretical read/write performance. ABCI 3.0 is expected to accelerate research and development, evaluation, and workforce development of cutting-edge AI technologies, with a particular focus on generative AI.