STONNE: Enabling Cycle-Level Microarchitectural Simulation for DNN Inference Accelerators

Francisco Munoz-Martinez,Jose L Abellan,Manuel E Acacio,Tushar Krishna

doi:10.1109/lca.2021.3097253

Francisco Munoz-Martinez, Jose L Abellan + Show 2 more

Open Access

https://doi.org/10.1109/lca.2021.3097253

Copy DOI

Abstract

The design of specialized architectures for accelerating the inference procedure of Deep Neural Networks (DNNs) is a booming area of research nowadays. While first-generation rigid accelerator proposals used simple fixed dataflows tailored for dense DNNs, more recent architectures have argued for flexibility to efficiently support a wide variety of layer types, dimensions, and sparsity. As the complexity of these accelerators grows, the analytical models currently being used prove unable to capture execution-time subtleties, thus resulting inexact in many cases. We present STONNE ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Simulation TOol of Neural Network Engines ), a cycle-level microarchitectural simulator for state-of-the-art rigid and flexible DNN inference accelerators that can plug into any high-level DNN framework as an accelerator device, and perform full-model evaluation of both dense and sparse real, unmodified DNN models.

Full Text