Big-Little Chiplets for In-Memory Acceleration of DNNs: A Scalable Heterogeneous Architecture.
Gokul KrishnanA. Alper GoksoySumit K. MandalZhenyu WangChaitali ChakrabartiJae-sun SeoÜmit Y. OgrasYu CaoPublished in: ICCAD (2022)
Keyphrases
- loosely coupled
- scalable distributed
- multiprocessor architecture
- low memory
- computing power
- real time
- level parallelism
- memory requirements
- heterogeneous environments
- memory space
- memory hierarchy
- highly distributed
- master slave
- limited memory
- memory usage
- associative memory
- management system
- design considerations
- memory access
- big data
- software architecture
- lightweight
- multi agent systems