HWTool: Fully Automatic Mapping of an Extensible C++ Image Processing Language to Hardware

TL;DR

HWTool automates the mapping of C++ image processing algorithms to FPGA hardware, significantly reducing manual effort and design time while achieving area efficiency comparable to manual and HLS approaches.

Contribution

The paper introduces HWTool, a system that automatically translates an extensible C++ image processing library into optimized FPGA hardware, streamlining the hardware design process.

Findings

HWTool achieves 11% more FPGA area than manual designs.

HWTool's performance is comparable to HLS-based implementations.

It successfully maps complex image processing applications to FPGA.

Abstract

Implementing image processing algorithms using FPGAs or ASICs can improve energy efficiency by orders of magnitude over optimized CPU, DSP, or GPU code. These efficiency improvements are crucial for enabling new applications on mobile power-constrained devices, such as cell phones or AR/VR headsets. Unfortunately, custom hardware is commonly implemented using a waterfall process with time-intensive manual mapping and optimization phases. Thus, it can take years for a new algorithm to make it all the way from an algorithm design to shipping silicon. Recent improvements in hardware design tools, such as C-to-gates High-Level Synthesis (HLS), can reduce design time, but still require manual tuning from hardware experts. In this paper, we present HWTool, a novel system for automatically mapping image processing and computer vision algorithms to hardware. Our system maps between two domains: HWImg, an extensible C++ image processing library containing common image processing and parallel computing operators, and Rigel2, a library of optimized hardware implementations of HWImg's operators and backend Verilog compiler. We show how to automatically compile HWImg to Rigel2, by solving for interfaces, hardware sizing, and FIFO buffer allocation. Finally, we map full-scale image processing applications like convolution, optical flow, depth from stereo, and feature descriptors to FPGA using our system. On these examples, HWTool requires on average only 11% more FPGA area than hand-optimized designs (with manual FIFO allocation), and 33% more FPGA area than hand-optimized designs with automatic FIFO allocation, and performs similarly to HLS.