paper-with-me

홈 › Papers

Comparing Energy Efficiency of CPU, GPU and FPGA Implementations for Vision Kernels

2019-05-31 · Murad Qasaimeh, Kristof Denolf, Jack Lo, Kees Vissers, Joseph Zambreno, Phillip H. Jones

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 1.1-3.2x 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 1.2-22.3x. It is also observed that the FPGA performs increasingly better as a vision application's pipeline complexity grows.

📄 PDF Abstract BibTeX arXiv:1906.11879

Code (1)

isu-rcl/cvBench 공식 구현

Tasks

CPUGPUNavigate

Similar Papers 제목 키워드 기반

Accelerated Feature Detectors for Visual SLAM: A Comparative Study of FPGA vs GPU

2025-10-15 · Ruiqi Ye, Mikel Luján arxiv

Feature detection is a common yet time-consuming module in Simultaneous Localization and Mapping (SLAM) implementations, which are increasingly deployed on power-constrained platforms, such as drones. Graphics Processing…

To Spike or Not to Spike? A Quantitative Comparison of SNN and CNN FPGA Implementations

2023-06-22 · Patrick Plagwitz, Frank Hannig, Jürgen Teich, Oliver Keszocze

Convolutional Neural Networks (CNNs) are widely employed to solve various problems, e.g., image classification. Due to their compute- and data-intensive nature, CNN accelerators have been developed as ASICs or on FPGAs. …

image-classificationImage Classification

Structured Weight Matrices-Based Hardware Accelerators in Deep Neural Networks: FPGAs and ASICs

2018-03-28 · Caiwen Ding, Ao Ren, Geng Yuan, Xiaolong Ma 외

Both industry and academia have extensively investigated hardware accelerations. In this work, to address the increasing demands in computational capability and memory requirement, we propose structured weight matrices (…

Full-stack Optimization for Accelerating CNNs with FPGA Validation

2019-05-01 · Bradley McDanel, Sai Qian Zhang, H. T. Kung, Xin Dong

We present a full-stack optimization framework for accelerating inference of CNNs (Convolutional Neural Networks) and validate the approach with field-programmable gate arrays (FPGA) implementations. By jointly optimizin…

MajorityNets: BNNs Utilising Approximate Popcount for Improved Efficiency

2020-02-27 · Seyedramin Rasoulinezhad, Sean Fox, Hao Zhou, Lingli Wang 외

Binarized neural networks (BNNs) have shown exciting potential for utilising neural networks in embedded implementations where area, energy and latency constraints are paramount. With BNNs, multiply-accumulate (MAC) oper…