Softbank plans to build first Nvidia Blackwell-based AI supercomputer using x86 DGX B200 servers
SoftBank's s telecom arm will build an AI supercomputer based on Nvidia's DGX B200 servers, featuring x86 processors and eight B200 GPU modules per server. SoftBank plans to adopt the Grace Blackwell platform, which combines Arm-based Grace CPUs and Blackwell AI GPUs, eventually (it's unclear when).
The Register on MSN2d
Nvidia's MLPerf submission shows B200 offers up to 2.2x training performance of H100Signs point to yes Analysis Nvidia offered the first look at how its upcoming Blackwell accelerators stack up against the ...
TL;DR: Japan's SoftBank is the first to receive NVIDIA's new Blackwell GPU for its AI supercomputer, with plans to use ...
In a move to advance Japan’s AI capabilities, SoftBank is building the country’s most powerful AI supercomputer with Nvidia ...
Elsewhere at Nvidia’s AI Summit Japan, it was revealed that Nvidia and SoftBank have also jointly launched the world’s first ...
NVIDIA's new Blackwell AI GPUs offer 2.2x the performance than Hopper in new MLPerf v4.1 AI training benchmarks released by ...
"This certification in the NVIDIA DGX-Ready Data Center program further extends our leadership, and we are delighted to work with NVIDIA to accelerate the development, design, and deployment of ...
For over 20 years, PNY has been a key player in the professional graphics solutions industry, especially through its ...
At Nvidia's AI Summit in Japan, SoftBank announced its plan to build Japan's most powerful AI supercomputer using Nvidia's ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback