The Cambricon research project is led by two brothers, CHEN Yunji (陈云霁) and CHEN Tianshi (陈天石), two young full professors at the CAS Institute of Computing Technology. Unlike existing neural networks which require thousands of GPU-based accelerators, Cambricon processors are designed to operate more efficiently and run on much less power. The latest Cambricon-1A chip can handle 16 billion virtual neurons per second and has a peak capacity of two trillion synapses per second. This performance is double that of a conventional GPU but has a power consumption that is lower by one order of magnitude.
CAS news release, April 24, 2017