Google and Wave Computing have working silicon and are conducting customer trials.
* Wave Computing says its 3U deep learning server can train AlexNet in 40 minutes, three times faster than NVIDIA’s P100 DGX-1 server.
* Wave Computing’s claim that its TPU is 1000 times faster.
* NVIDIA has improved the architectural efficiency of its GPUs by roughly 10x over the last few years
Cambricon Technologies aims to have one billion smart devices using its AI processor and own 30% of China’s high-performance AI chip market in three years.
Huawei estimates Cambricon chips are six times faster for deep-learning applications like training algorithms to identify images than a GPU.
The Cambricon-1H8 focuses on lower power consumption visual application, providing up to 2.3 times the performance per watt over its predecessor Cambricon-1A chip. The Cambricon-1H16, has wider application and better performance. While the Cambricon-1M is made for intelligent driving and has 10 times the performance of Cambricon-1A.