A Configurable Approximate Multiplier for Quantized Convolutional Neural Networks and Its Implementation

Abstract

The invention discloses a configurable approximate multiplier for quantizing a convolutional neural network and an implementation method thereof. The configurable approximate multiplier includes a sign extension module, a sub-multiplier module and an approximate adder; the sign extension module converts the long bit The multiplication of wide signed fixed-point numbers is split into two multiplications of short-width signed fixed-point numbers; the sub-multiplier module includes several sub-multipliers, and each sub-multiplier only receives a signed fixed-point number output from the sign extension module, combined with another One input completes a multiplication of signed fixed-point numbers; the approximate adder combines the output results of the sub-multiplier modules to obtain the final result of multiplication of long-bit-width signed fixed-point numbers. The present invention has obvious speed and energy efficiency improvement for the signed fixed-point multiplication operation of two input bits with unequal lengths; in the quantized convolutional neural network with a large number of multiplication operations, its advantages will be reflected to the greatest extent.

Description

technical field [0001] The invention relates to engineering technical fields such as low power consumption design, approximate calculation, and convolutional neural network, and in particular to a configurable approximate multiplier for quantizing convolutional neural network and an implementation method thereof. Background technique [0002] Deep learning has achieved great success in the past few years due to its accuracy, robustness, and efficiency in various tasks. Deep learning typically employs convolutional neural network (CNN) architectures that can perform millions to billions of multiply and accumulate (MAC) operations per second. Deep learning is much more computationally intensive than traditional machine learning techniques. Therefore, energy efficiency (i.e., energy consumption per operation) has become key to deep learning implementation and deployment, especially for mobile and embedded devices that want to save energy and meet strict power constraints. [...

AI Technical Summary

Problems solved by technology

However, due to their diagonally shaped critical paths, most multiplier hardware circuits (cf. figure 1 in a) and figure 1 almost 75% in b)) are actually ineffective, thus wasting resources and compromising energy efficiency

Such DAS multipliers are even less efficient for quantized CNNs whose weights typically have a smaller bit width than the input, e.g. only 8 bits for 16 or 32 bit inputs

This asymmetry in operands with unequal bit widths makes array-based DAS multipliers not an ideal application

Images