图形处理器流水线数据压缩技术研究综述

Survey of data compression techniques for GPU pipeline

提高功耗效率是高端GPU的关键设计目标之一。在3D图形渲染流水线的多个阶段,使用数据压缩技术能够显著减少GPU片外存储器的访问量,从而达到提高图形绘制性能和降低功耗的效果。为了对图形处理器流水线数据压缩技术的应用现状进行总结和分析,立足于GPU图形渲染流水线和存储系统的结构特征,归纳了各种缓冲区对象、纹理数据专用压缩算法的关键特性;分析了图形流水线数据压缩技术的研究现状、不足与挑战;并基于应用需求指明GPU流水线数据压缩技术进一步的研究内容。

One of the most important design aspects for high-end GPU is improving its power efficiency.Data compression can be used in various stages of the GPU 3D rendering pipeline to reduce off-chip memory traffic,yield high performance and low power consumption.In order to summarize the research progress and application status of data compression techniques for GPU pipeline,this paper outlined the key features of data compression specialized for buffer objects and texture based on the structure characteristics of GPU 3D rendering pipeline and memory system.Moreover,it discussed research status,inefficiencies and challenges of data compression in GPU pipeline.In the end,it indicated the further research content for GPU data compression according to application demands.