ODIN: A Bit-Parallel Stochastic Arithmetic Based Accelerator for In-Situ Neural Network Processing in Phase Change RAM

TL;DR

ODIN is a novel in-memory accelerator using hybrid binary-stochastic arithmetic in phase change RAM, significantly improving speed and energy efficiency for neural network processing compared to prior in-situ accelerators.

Contribution

The paper introduces ODIN, a new processing-in-memory engine employing hybrid binary-stochastic arithmetic inside PCRAM for efficient neural network acceleration.

Findings

ODIN achieves at least 5.8x speedup over prior in-situ accelerators.

ODIN is up to 23.2x more energy-efficient.

ODIN can be up to 90.8x faster and 1554x more energy-efficient in certain benchmarks.

Abstract

Due to the very rapidly growing use of Artificial Neural Networks (ANNs) in real-world applications related to machine learning and Artificial Intelligence (AI), several hardware accelerator de-signs for ANNs have been proposed recently. In this paper, we present a novel processing-in-memory (PIM) engine called ODIN that employs hybrid binary-stochastic bit-parallel arithmetic in-side phase change RAM (PCRAM) to enable a low-overhead in-situ acceleration of all essential ANN functions such as multiply-accumulate (MAC), nonlinear activation, and pooling. We mapped four ANN benchmark applications on ODIN to compare its performance with a conventional processor-centric design and a crossbar-based in-situ ANN accelerator from prior work. The results of our analysis for the considered ANN topologies indicate that our ODIN accelerator can be at least 5.8x faster and 23.2x more energy-efficient, and up to 90.8x faster and 1554x more energy-efficient, compared to the crossbar-based in-situ ANN accelerator from prior work.