NESTA: Hamming Weight Compression-Based Neural Proc. Engine
This work addresses efficiency bottlenecks in neural network inference for applications like embedded systems, though it appears incremental as it builds on existing compression and approximation techniques.
The paper tackles the problem of accelerating convolution layers in deep convolutional neural networks by introducing NESTA, a specialized neural engine that reformats convolutions into 3x3 batches and uses Hamming weight compressors with residual handling to reduce computational energy and speed up processing.
In this paper, we present NESTA, a specialized Neural engine that significantly accelerates the computation of convolution layers in a deep convolutional neural network, while reducing the computational energy. NESTA reformats Convolutions into $3 \times 3$ batches and uses a hierarchy of Hamming Weight Compressors to process each batch. Besides, when processing the convolution across multiple channels, NESTA, rather than computing the precise result of a convolution per channel, quickly computes an approximation of its partial sum, and a residual value such that if added to the approximate partial sum, generates the accurate output. Then, instead of immediately adding the residual, it uses (consumes) the residual when processing the next batch in the hamming weight compressors with available capacity. This mechanism shortens the critical path by avoiding the need to propagate carry signals during each round of computation and speeds up the convolution of each channel. In the last stage of computation, when the partial sum of the last channel is computed, NESTA terminates by adding the residual bits to the approximate output to generate a correct result.