Details
Presenter(s)
Display Name
Geethan Karunaratne
- Affiliation
-
AffiliationIBM Research - Zurich
- Country
Abstract
Binary Neural Networks enable smart IoT devices, as they significantly reduce the required memory footprint and computational complexity while retaining a high network performance and flexibility. This paper presents ChewBaccaNN, a 0.7 mm2 sized binary CNN accelerator in GlobalFoundries 22nm technology. By exploiting efficient data re-use, data buffering, latch-based memories, and voltage scaling, a throughput of 241 GOPS and a core energy efficiency of 223 TOPS/W is achieved. ChewBaccaNN's flexibility allows to run a much wider range of binary CNNs than other accelerators, drastically improving the accuracy-energy trade-off beyond what can be captured by the TOPS/W metric.