发明公开
- 专利标题: COMPUTATION DEVICE AND METHOD
-
申请号: EP19212756.1申请日: 2018-09-03
-
公开(公告)号: EP3651077A1公开(公告)日: 2020-05-13
- 发明人: ZHANG, Yao , WANG, Bingrui
- 申请人: Shanghai Cambricon Information Technology Co., Ltd
- 申请人地址: Floor 6, Block B, No.168 Tonghui Road Pudong New Area Shanghai 201306 CN
- 专利权人: Shanghai Cambricon Information Technology Co., Ltd
- 当前专利权人: Shanghai Cambricon Information Technology Co., Ltd
- 当前专利权人地址: Floor 6, Block B, No.168 Tonghui Road Pudong New Area Shanghai 201306 CN
- 代理机构: Huang, Liwei
- 优先权: CN201810149287 20180213; CN201810207915 20180314
- 主分类号: G06N3/063
- IPC分类号: G06N3/063 ; G06F7/499
摘要:
The present disclosure provides a computation device. The computation device is configured to perform a machine learning computation, and includes an operation unit, a controller unit, and a conversion unit. The storage unit is configured to obtain input data and a computation instruction. The controller unit is configured to extract and parse the computation instruction from the storage unit to obtain one or more operation instructions, and to transmit the one or more operation instructions and the input data to the operation unit. The operation unit is configured to perform operations on the input data according to one or more operation instructions to obtain a computation result of the computation instruction. In the examples of the present disclosure, the input data involved in machine learning computations is represented by fixed-point data, thereby improving the processing speed and processing efficiency of training operations.
公开/授权文献
- EP3651077B1 COMPUTATION DEVICE AND METHOD 公开/授权日:2021-10-27
信息查询