Developing high performance embedded vision applications requires balancing run-time performance with energy constraints. Given the mix of hardware accelerators that exist for embedded computer vision (e.g. multi-core CPUs, GPUs, and FPGAs), and their associated vendor optimized vision libraries, it becomes a challenge for developers to navigate this fragmented solution space. To aid with determining which embedded platform is most suitable for their application, we conduct a comprehensive benchmark of the run-time performance and energy efficiency of a wide range of vision kernels. We discuss rationales for why a given underlying hardware architecture innately performs well or poorly based on the characteristics of a range of vision kernel categories. Specifically, our study is performed for three commonly used HW accelerators for embedded vision applications: ARM57 CPU, Jetson TX2 GPU and ZCU102 FPGA, using their vendor optimized vision libraries: OpenCV, VisionWorks and xfOpenCV. Our results show that the GPU achieves an energy/frame reduction ratio of 1.1-3.2× compared to the others for simple kernels. While for more complicated kernels and complete vision pipelines, the FPGA outperforms the others with energy/frame reduction ratios of 1.2-22.3×. It is also observed that the FPGA performs increasingly better as a vision application's pipeline complexity grows.
Field-Programmable Gate Arrays (FPGAs) have lately become a popular target for implementing cryptographic block ciphers, as a well-designed FPGA solution can combine some of the algorithmic flexibility and cost efficiency of an equivalent software implementation with throughputs that are comparable to custom ASIC designs. The recently selected Advanced Encryption Standard (AES) is slowly replacing older ciphers as the building block of choice for secure systems and is well suited to an FPGA implementation. In this paper we explore the design decisions that lead to area/delay tradeoffs in a single-core AES FPGA implementation. This work provides a more thorough description of the defining AES hardware characteristics than is currently available in the research literature, along with implementation results that are pareto optimal in terms of throughput, latency, and area efficiency.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.