HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs

TL;DR

HAWX is a scalable framework that uses multi-level sensitivity scoring and predictive modeling to efficiently explore hardware-aware approximate DNN configurations, significantly accelerating the search process while maintaining accuracy.

Contribution

It introduces a multi-level sensitivity scoring method combined with predictive models for fast, hardware-aware approximation of DNNs, enabling scalable exploration across various architectures.

Findings

Achieves over 23x speedup in layer-level search.

Attains more than 3 million times speedup at filter-level search for LeNet-5.

Demonstrates exponential scalability of efficiency benefits across different DNN benchmarks.

Abstract

This work presents HAWX, a hardware-aware scalable exploration framework that employs multi-level sensitivity scoring at different DNN abstraction levels (operator, filter, layer, and model) to guide selective integration of heterogeneous AxC blocks. Supported by predictive models for accuracy, power, and area, HAWX accelerates the evaluation of candidate configurations, achieving over 23* speedup in a layer-level search with two candidate approximate blocks and more than (3*106)* speedup at the filter-level search only for LeNet-5, while maintaining accuracy comparable to exhaustive search. Experiments across state-of-the-art DNN benchmarks such as VGG-11, ResNet-18, and EfficientNetLite demonstrate that the efficiency benefits of HAWX scale exponentially with network size. The HAWX hardware-aware search algorithm supports both spatial and temporal accelerator architectures, leveraging either off-the-shelf approximate components or customized designs.