iFPNA: A Flexible and Efficient Deep Learning Processor in 28-nm CMOS Using a Domain-Specific Instruction Set and Reconfigurable Fabric.
Chixiao ChenXindi LiuHuwan PengHongwei DingC.-J. Richard ShiPublished in: IEEE J. Emerg. Sel. Topics Circuits Syst. (2019)
Keyphrases
- instruction set
- deep learning
- domain specific
- general purpose
- low cost
- application specific
- floating point
- computer architecture
- ibm power processor
- embedded systems
- silicon on insulator
- unsupervised learning
- power consumption
- machine learning
- instruction set architecture
- memory subsystem
- parallel processing
- fixed point
- natural images
- computer vision