Automated Circuit Approximation Method Driven by Data Distribution
This work addresses the need for efficient circuit approximation in hardware design, particularly for image classification applications, though it appears incremental as it builds on existing genetic programming and error metric techniques.
The authors tackled the problem of automating functional approximation of combinational circuits by developing a data-driven method that translates application-level error metrics to component-level ones, using a weighted mean error distance metric and genetic programming. They demonstrated this approach on approximate MAC units, achieving trade-offs between classification accuracy and power consumption in neural network-based image classifiers.
We propose an application-tailored data-driven fully automated method for functional approximation of combinational circuits. We demonstrate how an application-level error metric such as the classification accuracy can be translated to a component-level error metric needed for an efficient and fast search in the space of approximate low-level components that are used in the application. This is possible by employing a weighted mean error distance (WMED) metric for steering the circuit approximation process which is conducted by means of genetic programming. WMED introduces a set of weights (calculated from the data distribution measured on a selected signal in a given application) determining the importance of each input vector for the approximation process. The method is evaluated using synthetic benchmarks and application-specific approximate MAC (multiply-and-accumulate) units that are designed to provide the best trade-offs between the classification accuracy and power consumption of two image classifiers based on neural networks.