Harnessing FPGAs potential with OpenCL
暂无分享,去创建一个
The work presented deals with the evaluation of F-PGAs resurgence for hardware and software acceleration. We focus our attention on the tools developed by FPGAs manufacturers, in particular the Intel FPGA S-DK for OpenCL, that promises a new level of hardware abstraction from the developer's perspective, allowing a software-like programming of FPGAs. Our first contribution is to propose an accurate memory benchmark, and we follow with an evaluation of different custom OpenCL implementations of one use case : the computed tomogra-phy. With some clues on memory fetching and coalescing, we then further tune designs to improve performance. Finally , a comparison is made with GPU implementations, and a preliminary conclusion is drawn on FPGAs future in the semiconductor realm. This presentation include but is not limited to results presented in [3].
[1] Cyrille Enderli,et al. 3D Tomography parallelization on FPGAs via HLS tools , 2017 .
[2] Michel Desvignes,et al. High Speed 3D Tomography on CPU, GPU, and FPGA , 2008, EURASIP J. Embed. Syst..
[3] M. Wernick,et al. Emission Tomography: The Fundamentals of PET and SPECT , 2004 .