FEECA: Design Space Exploration for Low-Latency and Energy-Efficient Capsule Network Accelerators

• https://ieeexplore.ieee.org/document/9363276/

capsule neural network, hardware accelerators, design space exploration

In the past few years, Capsule Networks (CapsNets) have taken the spotlight
compared to traditional convolutional neural networks (CNNs) for image
classification. Unlike CNNs, CapsNets have the ability to learn the spatial
relationship between features of the images. However, their complexity grows
because of their heterogeneous capsule structure and the dynamic routing, which
is an iterative algorithm to dynamically learn the coupling coefficients of two
consecutive capsule layers. This necessitates specialized hardware accelerators
for CapsNets. Moreover, a high-performance and energy-efficient design of CapsNet
accelerators requires exploration of different design decisions (such as the size
and configuration of the processing array and the structure of the processing
elements). Toward this, we make the following key contributions: 1) FEECA,
a novel methodology to explore the design space of the (micro)architectural
parameters of a CapsNet hardware accelerator and 2) CapsAcc, the first
specialized RTL-level hardware architecture to perform CapsNets inference with
high performance and high energy efficiency. Our CapsAcc achieves significant
performance improvement, compared to an optimized GPU implementation, due to its
efficient implementation of key activation functions, such as squash and softmax,
and an efficient data reuse for the dynamic routing. The FEECA methodology
employs the Non-dominated Sorting Genetic Algorithm (NSGA-II) to explore the
Pareto-optimal points with respect to area, performance, and energy consumption.
This requires analytical modeling of the number of clock cycles required to
perform each operation of the CapsNet inference and the memory accesses to enable
a fast yet accurate design space exploration. We synthesized the complete
accelerator architecture in a 45-nm CMOS technology using Synopsys design tools
and evaluated it for the MNIST benchmark (as done by the original CapsNet paper
from Google Brain's team) and for a more complex data set, the German Traffic
Sign Recognition Benchmark (GTSRB).