Workload-Balanced Pruning for Sparse Spiking Neural Networks

Authors:
  • RYRuokai Yin
    Ruokai Yin
  • YKYoungeun Kim
    Youngeun Kim
  • YLYuhang Li
    Yuhang Li
  • AMAbhishek Moitra
    Abhishek Moitra
  • NSNitin Satpute
    Nitin Satpute
  • AHAnna Hambitzer
    Anna Hambitzer
  • PPPriyadarshini Panda
    Priyadarshini Panda
Preprint
Publisher website
Google Scholar
Abstract
Pruning for Spiking Neural Networks (SNNs) has emerged as a fundamental methodology for deploying deep SNNs on resource-constrained edge devices. Though the existing pruning methods can provide extremely high weight sparsity for deep SNNs, the high weight sparsity brings a workload imbalance problem. Specifically, the workload imbalance happens when a different number of non-zero weights are assigned to hardware units running in parallel. This results in low hardware utilization and thus imposes longer latency and higher energy costs. In preliminary experiments, we show that sparse SNNs (~98% weight sparsity) can suffer as low as ~59% utilization. To alleviate the workload imbalance problem, we propose u-Ticket, where we monitor and adjust the weight connections of the SNN during Lottery Ticket Hypothesis (LTH) based pruning, thus guaranteeing the final ticket gets optimal utilization when deployed onto the hardware. Experiments indicate that our u-Ticket can guarantee up to 100% hardware utilization, thus reducing up to 76.9% latency and 63.8% energy cost compared to the non-utilization-aware LTH method.

This publication has 31 references indexed in Scilit: