A 2Mbit Digital in-Memory Computing Matrix-Vector Multiplier for DNN Inference supporting flexible bit precision and matrix size achieving 612 binary TOPS/W - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Mohit Gupta, Stefan Cosemans, Peter Debacker, Wim Dehaene. A 2Mbit Digital in-Memory Computing Matrix-Vector Multiplier for DNN Inference supporting flexible bit precision and matrix size achieving 612 binary TOPS/W. In 49th IEEE European Solid State Circuits Conference, ESSCIRC 2023, Lisbon, Portugal, September 11-14, 2023. pages 417-420, IEEE, 2023. [doi]

This author has not been identified. Look up 'Mohit Gupta' in GoogleThis author has not been identified. Look up 'Stefan Cosemans' in GoogleThis author has not been identified. Look up 'Peter Debacker' in GoogleThis author has not been identified. Look up 'Wim Dehaene' in Google

runs on WebDSL