扩展双精度浮点并行计算:MPI方法  

Double-Extended Precision Floating-Point Parallel Computing:MPI Implementation

作　　者：杨灿群[1] 杨学军[1] 易会战[1] 

机构地区：[1]国防科学技术大学计算机学院,湖南长沙410073

出　　处：《计算机工程与科学》2010年第12期98-101,共4页Computer Engineering & Science

基　　金：国家自然科学基金重点资助项目(60633050)

摘　　要：双精度浮点并行计算将不能满足高性能计算领域对计算精度的要求,但是目前还没有高性能的超双精度并行计算的解决方法。基于并行编程语言MPI,本文提出了扩展双精度浮点的并行计算实现方法,并且使用精度敏感的圆周率计算BBP算法验证了该方法的正确性和性能。Parallel computing in double-precision floating-point arithmetic will be out of accord with the requirements of the computing precision in high performance computing in the future.However,there is no solution to parallel computing in super double-precision arithmetic with high performance.Based on the wildly used parallel programming language MPI,this paper presents a solution of double-extended precision parallel computing.The correctness and performance of this solution is validated by a precision-sensitive BBP algorithm which is used for the computation of Pi.

关 键 词：扩展双精度 MPI BBP算法 

分 类 号：TP314[自动化与计算机技术—计算机软件与理论]