Tensor Computing Processor BM1684X

SOPHON BM1684X is the fourth-generation tensor processor launched by SOPHGO for deep learning. Its performance has been improved by 2 times compared with the previous generation.

Peak Performance

32 TOPS INT8
16 TFLOPS FP16/BF16
2 TFLOPS FP32

Video Decoding

32 channels HD hardware decoding

Video Encoding

12 channels HD hardware encoding

Energy Efficiency Ratio

2x EER vs previous generation

Support INT8, FP16/BF16 and FP32 precision, greatly improving AI performance

Integrated high-performance ARM core,support secondary development

Integrated video and image decoding and encoding capabilities

Support PCIe, Ethernet interface

Support PyTorch, TensorFlow and other mainstream frameworks

Wide Application and Scenarios

The edge computing AI chip BM1684X 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.

More