期刊文献+

基于申威1621数学库中的非精确结果异常处理

Inexact Exception Handling in Shenwei 1621 Math Library
下载PDF
导出
摘要 由于国产申威基础数学库其功能、接口需要与单机编译器glibc libm库保持一致,将基础数学库集成到glibc中进行功能测试时,检测出有部分函数的INE异常需要消除.针对这种情况,首先研究了glibc数学库的异常检测机制;然后针对基础数学库中数值函数的INE异常进行分析和优化,提出一种测试数据集分段处理的方法,最后消除了这种INE异常.测试表明,测试数据集分段处理的方法能够有效解决数值函数的INE异常,相对于之前的异常处理方法,使用本方法后平均性能加速比达到148%. Since the functions and interfaces of the domestic Shenwei basic math library need to be consistent with the libm library of the stand-alone compiler glibc,the basic math library is integrated into glibc for functional tests.Nevertheless,it is detected that some functions have inexact exception(INE)that needs to be eliminated.In response,this study investigates the exception detection mechanism of the glibc math library,analyzes and optimizes the INE of the numerical functions in the basic math library,and proposes a segmentation processing method for test data sets.In this way,such INE is eliminated.Tests show that the segmentation processing method for test data sets can effectively solve the INE of the numerical functions.Compared with the previous exception processing method,the proposed method improves the average performance speedup to 148%.
作者 张天罡 王磊 ZHANG Tian-Gang;WANG Lei(Frontier Information Technology Research Institute,Zhongyuan University of Technology,Zhengzhou 450007,China)
出处 《计算机系统应用》 2022年第7期113-119,共7页 Computer Systems & Applications
关键词 异常检测 非精确结果异常 数据集分段处理 exception detection inexact exception(INE) data set segmentation processing
  • 相关文献

参考文献3

二级参考文献82

  • 1钱兴隆,臧斌宇,朱传琪.一种SIMD优化中的向量寄存器部分重用方法[J].计算机工程与科学,2007,29(5):141-146. 被引量:3
  • 2Xu JC, Guo SZ, Wang L. Optimization technology in SIMD mathematical functions based on vector register reuse. In: Proc. of the 2012 IEEE 14th Int'l Conf. on High Performance Computing and Communications (HPCC 2012). Liverpoor: IEEE Computer Society, 2012. ! 102-1107. Idol: 10.1109/HPCC.2012.161].
  • 3Daramy C, Defour D, de Dinechin F, Muller JM, Arenaire P. CR-LIBM: A correctly rounded elementary function library. In: Proc. of the Optical Science and Technology, SPIE's 48th Annual Meeting. Int'l Society for Optics and Photonics. 2003. 458-464. [doi: 10.1117/12. 505591].
  • 4Wu XY, Xia JL. New vector forms of elemental functions with Taylor series. Applied Mathematics and Computation, 2003,141(2): 307-312. [doi: 10.1016/S0096-3003(02)00255-2].
  • 5Tang PTP. A Portable Generic Elementary Function Package in Ada and an Accurate Test Suite. Department of Defense, 1990. [doi: 10.1145/123533.123573].
  • 6Manos P, Turner LR. Constrained Chebyshev Approximations to Some Elementary Functions Suitable for Evaluation with Floating Point Arithmetic. NASA, 1972.
  • 7Abramowitz M, Stegun IA. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. Courier Dover Publications, 1964.
  • 8Andraka R. A survey of CORDIC algorithms for FPGA based computers. In: Proc. of the '98 ACM/SIGDA 6th Int'l Symp. on Field Programmable Gate Arrays. ACM Press, 1998. 191-200. [doi: 10.1145/275107.275139].
  • 9Muller JM. Elementary Functions: Algorithms and Implementation. Springer-Verlag, 2006.
  • 10Baboulin M, Buttari A, Dongarra J, Kurzak J, Langou J, Langou J, Luszczek P, Tomov S. Accelerating scientific computations with mixed precision algorithms. Computer Physics Communications, 2009,180(12):2526-2533. [doi: 10.1016/j.cpc.2008.11.005].

共引文献22

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部