Peer-reviewed paper
tubGEMM: Energy-Efficient and Sparsity-Effective Temporal-Unary-Binary Based Matrix Multiply Unit
tubGEMM combines temporal, unary, and binary arithmetic to build a matrix-multiply unit that is more tolerant of sparsity and low precision. The design studies how hybrid arithmetic can improve energy efficiency without giving up too much flexibility.
Abstract Summary
tubGEMM combines temporal, unary, and binary arithmetic to build a matrix-multiply unit that is more tolerant of sparsity and low precision. The design studies how hybrid arithmetic can improve energy efficiency without giving up too much flexibility.
Research Context
This paper contributes to my research program in tubGEMM, hybrid arithmetic, ISVLSI 2023. It is part of the broader work on efficient ML systems, hardware-software co-design, and deployment-aware computer architecture.