Neural networks span a wide range of applications of industrial and commercial significance. Binary neural networks (BNN) are particularly effective in trading accuracy for performance, energy efficiency or hardware/software complexity. Here, we introduce a spintronic, re-configurable in-memory BNN accelerator, PIMBALL: Processing In Memory BNN AcceL(L)erator, which allows for massively parallel and energy efficient computation. PIMBALL is capable of being used as a standard spintronic memory (STT-MRAM) array and a computational substrate simultaneously. We evaluate PIMBALL using multiple image classifiers and a genomics kernel. Our simulation results show that PIMBALL is more energy efficient than alternative CPU, GPU, and FPGA based implementations while delivering higher throughput.
@article{arxiv.1812.03989,
title = {PIMBALL: Binary Neural Networks in Spintronic Memory},
author = {Salonik Resch and S. Karen Khatamifard and Zamshed Iqbal Chowdhury and Masoud Zabihi and Zhengyang Zhao and Jian-Ping Wang and Sachin S. Sapatnekar and Ulya R. Karpuzcu},
journal= {arXiv preprint arXiv:1812.03989},
year = {2019}
}