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.