A 13.7 TFLOPS/W Floating-point DNN Processor using Heterogeneous Computing Architecture with Exponent-Computing-in-Memory.
Juhyoung LeeJihoon KimWooyoung JoSangyeob KimSangjin KimJinsu LeeHoi-Jun YooPublished in: VLSI Circuits (2021)
Keyphrases
- floating point
- heterogeneous computing
- instruction set
- compute intensive
- floating point arithmetic
- computer architecture
- level parallelism
- floating point unit
- memory bandwidth
- fixed point
- memory access
- memory management
- parallel computing
- parallel processors
- grid computing
- parallel computers
- data mining
- computing platform
- computer systems
- management system
- information systems
- wireless sensor networks
- high performance computing
- power consumption
- data access
- main memory