Paper
21 February 2020 Fast calculation by auto-optimized method in CGH video generation using GPU
Hayato Sakai, Yuji Sakamoto
Author Affiliations +
Abstract
Computer-generated hologram (CGH) can generate an ideal 3D video, but the downside is that the calculation time is huge. Recently, it is becoming more common to use a graphics processing unit (GPU) to enable fast calculation for CGH. Therefore, we have created a system that automatically changes various parameters in the CGH calculation by the GPU, searches for optimal parameters, and performs automatic tuning. In this work, we optimized four parameters-loop unrolling, memory structure, point light source sparsity, and allocation of calculation processing units-and found that the calculation time was 1.8 times faster as a result of the optimization.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hayato Sakai and Yuji Sakamoto "Fast calculation by auto-optimized method in CGH video generation using GPU", Proc. SPIE 11306, Practical Holography XXXIV: Displays, Materials, and Applications, 113060S (21 February 2020); https://doi.org/10.1117/12.2545879
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Light sources

Holograms

Computer generated holography

3D image reconstruction

Video

Video acceleration

Light

RELATED CONTENT


Back to Top