Tensor Computing Processor BM1682

SOPHON BM1682 is the second-generation tensor processor launched by SOPHGO for deep learning. Its performance has been greatly improved compared with the first generation.

Consultancy

Peak Performance

3TFLOPS FP32

Video Decoding

8 channelsHD hardware decoding

On-chip SRAM Capacity

16MBytes

Arithmetic Unit

2048

Single precision peak performance 3TFLOPS

Integrated video decoding capability

Support Ethernet, PCIe interface

Support TensorFlow, Caffe

Optimized data bandwidth

Wide Application and Scenarios

The edge computing AI chip BM1682 can be used in artificial intelligence, machine vision and high performance computing environments.

Easy-to-use, Convenient and Efficient

BMNNSDK (BITMAIN Neural Network SDK) one-stop toolkit provides a series of software tools including the underlying driver environment, compiler and inference deployment tool. The easy-to-use and convenient toolkit covers the model optimization, efficient runtime support and other capabilities required for neural network inference. It provides easy-to-use and efficient full-stack solutions for the development and deployment of deep learning applications. BMNNSDK minimizes the development cycle and cost of algorithms and software. Users can quickly deploy deep learning algorithms on various AI hardware products of SOPHGO to facilitate intelligent applications.

Support mainstream programming framework

More

Function Block