Bit-serial Weight Pools: Compression and Arbitrary Precision Execution of Neural Networks on Resource Constrained Processors

Part of Proceedings of Machine Learning and Systems 4 (MLSys 2022)

Bibtex Paper

Authors

Shurui Li, Puneet Gupta

Abstract

Applications of neural networks on edge systems have proliferated in recent years but the ever increasing model size makes neural networks not able to deploy on resource-constrained microcontrollers efficiently. We propose bit-serial weight pools, an end-to-end framework that includes network compression and acceleration of arbitrary sub-byte precision. The framework can achieve up to 8x compression compared to 8-bit networks by sharing a pool of weights across the entire network. We further propose a bit-serial lookup based software implementation that allows runtime-bitwidth tradeoff and is able to achieve more than 2.8x speedup and 7.5x storage compression compared to 8-bit networks, with less than 1% accuracy drop.