The ABCI 3.0 supercomputer will be housed in Kashiwa at a facility run by Japan’s National Institute of Advanced Industrial Science and Technology. Credit: Courtesy of AIST.
Japan’s National Institute of Advanced Industrial Science and Technology (AIST) research organization will integrate thousands of Nvidia H200 Tensor Core GPUs into its HPE-Cray AI Bridging Cloud Infrastructure 3.0 supercomputer (ABCI 3.0).
Nvidia said ABCI, serving as a platform for joint AI R&D with industries, academia and governments, is expected to come online by the end of this year and will be housed in Kashiwa, near Tokyo.
The facility will offer:
- 6 AI exaflops computing capacity
- 410 double-precision petaflops general computing capacity
- Each node is connected via the Quantum-2 InfiniBand platform at 200GB/s of bisectional bandwidth.
Nodes for the HPE Cray XD system will incorporate eight NVLink-connected H200 GPUs with more than 140 gigabytes (GB) of HBM3e memory at 4.8 terabytes per second (TB/s). The capacity and speed of H200’s memory is designed to accelerate generative AI and LLMs, while supporting scientific computing for HPC workloads.
“The integration of advanced Nvidia Quantum-2 InfiniBand with In-Network computing — where networking devices perform computations on data, offloading the work from the CPU — ensures efficient, high-speed, low-latency communication, crucial for handling intensive AI workloads and vast datasets,” Nvidia said.
“In August 2018, we launched ABCI, the world’s first large-scale open AI computing infrastructure,” said AIST Executive Officer Yoshio Tanaka. “Building on our experience over the past several years managing ABCI, we’re now upgrading to ABCI 3.0. In collaboration with NVIDIA and HPE, we aim to develop ABCI 3.0 into a computing infrastructure that will advance further research and development capabilities for generative AI in Japan.”
ABCI 3.0 is constructed and operated by AIST, its business subsidiary, AIST Solutions, and its system integrator, HPE.
“As generative AI prepares to catalyze global change, it’s crucial to rapidly cultivate research and development capabilities within Japan,” said AIST Solutions Co. Producer and Head of ABCI Operations Hirotaka Ogawa. “I’m confident that this major upgrade of ABCI in our collaboration with NVIDIA and HPE will enhance ABCI’s leadership in domestic industry and academia, propelling Japan towards global competitiveness in AI development and serving as the bedrock for future innovation.”
The ABCI 3.0 project follows support from Japan’s Ministry of Economy, Trade and Industry, known as METI, for strengthening its computing resources through the Economic Security Fund and is part of a broader $1 billion initiative by METI that includes both ABCI efforts and investments in cloud AI computing.
Nvidia said it is collaborating with METI on research and education following a visit last year by company founder and CEO, Jensen Huang, who met with political and business leaders, including Japanese Prime Minister Fumio Kishida, to discuss the future of AI. Huang pledged to collaborate on research in generative AI, robotics and quantum computing, to invest in AI startups and provide product support, training and education on AI.
Huang emphasized that “AI factories” — next-generation data centers designed to handle the most computationally intensive AI tasks — are crucial for turning vast amounts of data into intelligence.
“The AI factory will become the bedrock of modern economies across the world,” Huang said during a meeting with the Japanese press in December.
ABCI 3.0 is the latest iteration of Japan’s large-scale Open AI Computing Infrastructure designed to advance AI R&D.
