arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.02301cs.MScs.ARcs.NAmath.NA
收藏

Level-Index算术的MATLAB模拟器

MATLAB Simulator of Level-Index Arithmetic

Mantas Mikaitis

AI总结:

本文提出一个MATLAB自定义精度模拟器以重新审视level-index算术,该工具箱能有效探索其在机器学习等窄位宽场景下避免浮点上溢/下溢的性能表现。

摘要:

Level-index算术出现于20世纪80年代。其主要目的之一是消除浮点数中下溢和上溢引起的问题。然而,level-index算术并不扩展数字集合,而是比浮点表示将大数量级的数字间隔得更大,以将无穷大推离零:范围两端数字之间的间隙变得非常大。我们通过在MATLAB中提出一个自定义精度模拟器来重新审视level index。该工具箱对于在研究项目中探索level-index算术的性能非常有用,例如在机器学习算法中使用8位和16位表示,这些算法期望窄位宽,但浮点表示的上溢/下溢会导致困难。

英文摘要:

Level-index arithmetic appeared in the 1980s. One of its principal purposes is to abolish the issues caused by underflows and overflows in floating point. However, level-index arithmetic does not expand the set of numbers but spaces out the numbers of large magnitude even more than floating-point representations to move the infinities further away from zero: gaps between numbers on both ends of the range become very large. We revisit level index by presenting a custom precision simulator in MATLAB. This toolbox is useful for exploring performance of level-index arithmetic in research projects, such as using 8-bit and 16-bit representations in machine learning algorithms where narrow bit-width is desired but overflow/underflow of floating-point representations causes difficulties.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑