Rigel
James Hegarty, Ross Daly, Zachary DeVito et al. · ACM Transactions on Graphics · 2016
Image processing algorithms implemented using custom hardware or FPGAs of can be orders-of-magnitude more energy efficient and performant than software. Unfortunately, converting an algorithm by hand to a hardware description language suitable for compilation on these platforms is frequently too time consuming to be practical. Recent work on hardware synthesis of high-level image processing languages demonstrated that a single-rate pipeline of stencil kernels can be synthesized into hardware with provably minimal buffering. Unfortunately, few advanced image processing or vision algorithms fit into this highly-restricted programming model. In this paper, we present Rigel, which takes pipelines specified in our new multi-rate architecture and lowers them to FPGA implementations. Our flexible multi-rate architecture supports pyramid image processing, sparse computations, and space-time implementation tradeoffs. We demonstrate depth from stereo, Lucas-Kanade, the SIFT descriptor, and a Gaussian pyramid running on two FPGA boards. Our system can synthesize hardware for FPGAs with up to 436 Megapixels/second throughput, and up to 297x faster runtime than a tablet-class ARM CPU.
Cited by 69 works. doi:10.1145/2897824.2925892
Authors
References
- Object recognition from local scale-invariant features
- A Combined Corner and Edge Detector
- An Iterative Image Registration Technique with an Application to Stereo Vision
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
- 2009 International Joint Conference on Artificial Intelligence
- Static Scheduling of Synchronous Data Flow Programs for Digital Signal Processing
- Pyramidal implementation of the Lucas Kanade feature tracker description of the algorithm
- A close examination of performance and power characteristics of 4G LTE networks
- Retiming synchronous circuitry
- Understanding sources of inefficiency in general-purpose chips