CLAppED: A Design Framework for Implementing Cross-Layer Approximation in FPGA-based Embedded Systems
Hosted in Virtual Platform
Approximate Computing for AI/ML
DescriptionIn recent years, Approximate Computing has emerged as a viable tool for improving performance in FPGA-based systems by utilizing reduced precision data structures and resource-optimized high-performance arithmetic operators. However, most of the related state-of-the-art research has mainly focused on utilizing approximate computing principles individually on different layers of the computing stack. Nonetheless, approximations across different layers of computing stack can substantially enhance the system's performance. To this end, we present a framework for implementing cross-layer approximations in FPGA-based embedded systems. We use 2D convolution operator as a test case and present the results for Gaussian Smoothing of noisy images.