Many scientific codes and instruments generate large amounts of floating-point data at high rates that must be compressed before they can be stored. Typically, only lossy compression algorithms deliver high-enough compression ratios. However, many of them provide only point-wise error bounds and do not preserve topological aspects of the data such as the relative magnitude of neighboring points. Even topology-preserving compressors tend to merely preserve some critical points and are generally slow. Our Local-Order-Preserving Compressor is the first to preserve the full local order (and thus all critical points), runs orders of magnitude faster than prior topology-preserving compressors, yields higher compression ratios than lossless compressors, and produces bit-for-bit the same output on CPUs and GPUs.
翻译:许多科学代码和仪器以高速率生成大量浮点数据,必须在存储前进行压缩。通常只有有损压缩算法能达到足够高的压缩比。然而,多数算法仅提供逐点误差界,未能保留数据拓扑特性(如相邻数据点的相对大小)。即使是拓扑保持型压缩器,也往往仅保留部分关键点且运行缓慢。本研究的局部顺序保持压缩器是首个完整保留局部顺序(从而保留所有关键点)的压缩器,其运行速度比现有拓扑保持型压缩器快数个数量级,压缩比高于无损压缩器,且在CPU和GPU上生成比特级相同的输出。