Stand-in literature? NVIDIA will launch chip A800 to China to replace A100

[Gearbest News]NVIDIA must be familiar to everyone. Many OEM manufacturers, graphics card manufacturers, system manufacturers, and consumer electronics companies around the world have chosen NVIDIA's processors as core components of their entertainment and commercial solutions. On November 8, Nvidia stated that it would launch a new chip A800 in China to comply with recent U.S. export control regulations. The spokesperson said that the A800 chip will be put into production in the third quarter as a replacement for the A100 chip, because A100 has been restricted by the U.S. Department of Commerce from exporting to China.

A100 uses NVIDIA Ampere architecture and is the engine of NVIDIA data center platform. A100 delivers up to 20 times better performance than the previous generation and can be divided into seven GPU instances to dynamically adjust to changing needs. The A100 is available in 40GB and 80GB graphics memory versions. The A100 80GB doubles the GPU memory and provides ultra-fast memory bandwidth (more than 2 trillion bytes per second). [TB/s]), can handle extremely large models and datasets.

A100

A100 is part of the entire NVIDIA data center solution, which is composed of hardware, network, software, libraries, and optimized AI models and applications in NGC. A100 Tensor Core uses Tensor floating point operation (TF32) precision to provide 20 times higher performance than NVIDIA Volta without requiring code changes; if you use automatic mixed precision and FP16, the performance can be further improved by 2 times.

magicCubeFunc.write_ad(“dingcai_top_0”);