.png){kind=icon}
返回
ZFP: A compressed array representation for numerical computations
.png){kind=icon}
PRE
AI
DOI：10.1177/10943420241284023.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
HPC trends favor algorithms and implementations that reduce data motion relative to FLOPS. We investigate the use of lossy compressed data arrays in place of traditional IEEE floating point arrays to store the primary data of calculations. Simulation is fundamentally an exercise in controlled approximation, and error introduced by finite-precision arithmetic (or lossy compression) is just one of several sources of error that need to be managed to ensure sufficient accuracy in a computed result. We describe ZFP, a compressed numerical format designed for in-memory storage of multidimensional arrays, and summarize theoretical results that demonstrate that the error of repeated lossy compression can be bounded and controlled. Furthermore, we establish a relationship between grid resolution and compression-induced errors and show that, contrary to conventional floating point, ZFP reduces finite-difference errors with finer grids. We present example calculations that demonstrate data reduction by 4x or more with negligible impact on solution accuracy. Our results further demonstrate several orders-of-magnitude increase in accuracy using ZFP over IEEE floating point and Posits for the same storage budget.
Keyword:
Lossy compression
reduced precision
number representations
error analysis
partial differential equations
期刊
IF:
2.5
论文数:
1.1K
被引数:
1.3K
机构
引用论文
分享收藏Results of the Pegasus Phase 3 Randomized Trial Demonstrating Superiority of the C3 Inhibitor, Pegcetacoplan, Compared to Eculizumab in Patients with Paroxysmal Nocturnal Hemoglobinuria.png)
Blood
BloodIF0
PREAI
分享收藏Asthma alleviates obesity in males through regulating metabolism and energy expenditure哮喘通过调节代谢和能量消耗减轻男性肥胖
PREAI
分享收藏
查看更多内容