人工智能深度学习芯片调研

2018.6.18 材料（非论文部分）

产生背景：http://www.gyii.cn/baogao/ITtongxin/ruanjian/2017/1016/205999.html

发展概况：http://market.chinabaogao.com/it/121330H012017.html

发展现状及未来前景：http://free.chinabaogao.com/dianzi/201710/10232aa42017.html

寒武纪处理器：http://www.guancha.cn/tieliu/2016_03_16_354051_s.shtml (内含两篇论文)

其他：http://www.360doc.com/content/17/0910/00/42811564_685868180.shtml

新闻：首颗人工智能神经网络芯片标志着人工智能又一次的技术革新http://www.elecfans.com/rengongzhineng/554891.html

AI芯片公司盘点：https://blog.csdn.net/cf2SudS8x8F0v/article/details/78898399

谷歌TPU：In-Datacenter Performance Analysis of a Tensor Processing Unit

AI芯片分类：https://ai.ofweek.com/news/2018-09/ART-201714-8230-30265161.html

https://36kr.com/p/5144249.html

总结性：http://baijiahao.baidu.com/s?id=1600614929244949932&wfr=spider&for=pc

报道信息：

http://36kr.com/p/5088763.html

https://www.taoguba.com.cn/Article/1931680/1

https://www.sohu.com/a/234336647_295206

寒武纪芯片：DianNao、DaDianNao、ShiDianNao、PuDianNao、Cambricon

陈云霁组论文：

Cambricon: An Instruction Set Architecture for Neural Networks

Neuromorphic Accelerators: A Comparison Between Neuroscience and Machine-Learning Approaches

ShiDianNao: Shifting Vision Processing Closer to the Sensor

PuDianNao: A Polyvalent Machine Learning Accelerator

DaDianNao: A Machine-Learning Supercomputer

DianNao: A Small-Footprint High-Throughput Accelerator for Ubiquitous Machine-Learning

转载于:https://www.cnblogs.com/o-din/p/9196688.html