ReducedLUT: Table Decomposition with "Don't Care" Conditions

TL;DR

ReducedLUT is a novel method that compresses lookup tables in neural networks by injecting don't care conditions, significantly reducing hardware footprint with minimal impact on accuracy.

Contribution

The paper introduces ReducedLUT, a new LUT compression technique using don't cares, improving efficiency over traditional methods in neural network hardware implementations.

Findings

Up to 1.63x reduction in LUT hardware utilization.

Minimal accuracy degradation of no more than 0.01 points.

Effective exploitation of self-similarities through decomposition techniques.

Abstract

Lookup tables (LUTs) are frequently used to efficiently store arrays of precomputed values for complex mathematical computations. When used in the context of neural networks, these functions exhibit a lack of recognizable patterns which presents an unusual challenge for conventional logic synthesis techniques. Several approaches are known to break down a single large lookup table into multiple smaller ones that can be recombined. Traditional methods, such as plain tabulation, piecewise linear approximation, and multipartite table methods, often yield inefficient hardware solutions when applied to LUT-based NNs. This paper introduces ReducedLUT, a novel method to reduce the footprint of the LUTs by injecting don't cares into the compression process. This additional freedom introduces more self-similarities which can be exploited using known decomposition techniques. We then demonstrate a particular application to machine learning; by replacing unobserved patterns within the training data of neural network models with don't cares, we enable greater compression with minimal model accuracy degradation. In practice, we achieve up to $1.63\times$ reduction in Physical LUT utilization, with a test accuracy drop of no more than $0.01$ accuracy points.