Fudan University

Shanghai Cambricon Information Technology Co., Ltd

Di Huang

Yao Zhang

Chang Liu

Shuai Zhang

Jian Shen

Xishan Zhang

Jiaming Guo

Shengyu Zhou

Lifeng Yin

Chunlei Gao

Shiwei Wu

Shaoli Liu

Yu Chen

Xiaofu Meng

Shiyi Zhou

Zeyuan Sun

Guang Jiang

The present disclosure relates to a method, a device, and related products for processing data. In an embodiment of the present disclosure, when processing data related to a neural network, an optimal truncation threshold value for a plurality of pieces of data is determined. The data is truncated through the truncation data threshold, and the plurality of pieces of data is quantized from a high-precision format to a low-precision format. The method in the present disclosure can ensure the precision of data processing as high as possible while reducing the amount of data processing. In addition, the method also helps to significantly reduce the amount of data transmission, thereby greatly accelerating the data exchange among a plurality of computing devices.

Data processing method and apparatus, and related product

The technical solution involves a board card including a storage component, an interface apparatus, a control component, and an artificial intelligence chip. The artificial intelligence chip is connected to the storage component, the control component, and the interface apparatus, respectively; the storage component is used to store data; the interface apparatus is used to implement data transfer between the artificial intelligence chip and an external device; and the control component is used to monitor a state of the artificial intelligence chip. The board card is used to perform an artificial intelligence operation.

Neural network quantization parameter determination method and related products

The present disclosure relates to the technical field of cryogenic cooling. In particular, the present disclosure relates to a mechanical vibration-isolated, liquid helium consumption-free cryogenic cooling device. The system according to some embodiments of the present disclosure comprises: a closed-cycle cryogenic cooling system, a helium heat exchange gas cooling and vibration isolation interface system, a cryogenic throttle valve cooling system, and a temperature feedback control system. The closed-cycle cooling system includes a cold head, a compressor, and a helium pipeline. The cryogenic throttle valve cooling system is thermally coupled to a low-temperature end of the cooling and vibration isolation interface.

Mechanical vibration-isolated, liquid helium consumption-free and extremely low temperature refrigerating system

A scanning probe microscope of the present disclosure includes: a room-temperature bore superconducting magnet including a liquid helium-consumption free closed-cycle cooling system, a superconducting magnet, and a chamber having a room-temperature bore; and a scanning probe microscope including a scanning head, a vacuum chamber, and a vibration isolation platform; and a computer control system. The room-temperature bore superconducting magnet is cooled by the cryogen-free closed-cycle cooling system which eliminates the dependence on liquid helium for high magnetic field operation. There is no physical contact between the scanning probe microscope and the superconducting magnet connected to the closed-cycle cooling system. The scanning probe microscope can achieve atomic-scale spatial resolution. The temperature of the scanning probe microscope is not restricted by the low temperature conditions for operation of the superconducting magnet. The scanning probe microscope and the vacuum chamber can achieve high-temperature baking independent of the superconducting magnet for ultra-high vacuum conditions.

High magnetic field scanning probe microscope employing liquid helium-free room-temperature bore superconducting magnet

Growing community of inventors

Shanghai, China

Di Huang