基于InfiniBand的并行绘制系统中的数据压缩

Data compression in parallel rendering system based on InfiniBand

为提高并行绘制系统中的帧率,从数据压缩的角度出发,搭建了基于InfiniBand的并行绘制系统。首先对并行绘制系统中数据进行分类,根据当前帧的数据量大小设置临界值,对达到临界值的几何数据进行无损压缩。本文研究并对比了LZ77,LZW,LZO三种数据压缩算法对系统的影响。实验表明,LZ77,LZW和LZO算法均对系统的帧率有所提高,而LZO算法对系统的帧率提高最明显且稳定性最好,使系统帧率提高近60%。无损数据压缩对提高并行绘制系统性能具有很明显的效果。

From the perspective of data compression,parallel rendering system based on InfiniBand is set up in order to improve the frame rate.Data classification in parallel rendering system is performed;and the thresholds are set according to the data of the current frame;the lossless compression is applied to the geometric data which reach up to the critical value.The effects of three types of data compression algorithms,LZ77,Lempel-Ziv-Welch(LZW),Lempel-Ziv-Oberhumer(LZO),are researched and compared.The experiments results show that,LZ77,LZW and LZO algorithms can improve the frame rate of system;LZO algorithm increases the frame rate of system most significantly with the best stability,and the system frame rate is increased by nearly60%.Lossless data compression can improve the performance of parallel rendering system significantly.