Accelerated Polynomial Evaluation and Differentiation at Power Series in Multiple Double Precision

Accelerated Polynomial Evaluation and Differentiation at Power Series in Multiple Double Precision
复制标题

多重双精度幂级数的加速多项式计算和微分

DOI:
10.1109/ipdpsw52791.2021.00111
复制
发表时间:
2021
期刊:
2021 IEEE International Parallel and Disributed Processing Symposium Workshops (IPDPSW
影响因子:
--
通讯作者:
Verschelde, Jan
Verschelde, Jan
中科院分区:
--
文献类型:
--
作者:
Verschelde, Jan

文献摘要

参考文献

被引文献

相似文献

问题是用多重双精度算法求一个多元多项式及其按有限次截断的幂序列的梯度。为了弥补多个双精度和幂串联运算的开销,提出了通用图形处理单元的数据并行算法。算法微分的反向模式被组织成许多卷积和截断幂级数的加法的大规模并行计算。实验结果表明,在级数截断阶数为152次的情况下,万亿次浮点运算的性能达到了分贝的双精度。这些算法在提高精度和增加次数方面具有很好的伸缩性。
The problem is to evaluate a polynomial in several variables and its gradient at a power series truncated to some finite degree with multiple double precision arithmetic. To compensate for the cost overhead of multiple double precision and power series arithmetic, data parallel algorithms for general purpose graphics processing units are presented. The reverse mode of algorithmic differentiation is organized into a massively parallel computation of many convolutions and additions of truncated power series. Experimental results demonstrate that teraflop performance is obtained in deca double precision with power series truncated at degree 152. The algorithms scale well for increasing precision and increasing degrees.
并行共享内存计算机上多项式同伦一条路径的鲁棒数值跟踪
DOI: 10.1007/978-3-030-60026-6_33
发表时间: 2021
期刊: vol 12291
影响因子: --
作者:
Telen, Simon;Van Barel, Marc;Verschelde, Jan
通讯作者: Verschelde, Jan
并行软件可抵消更高精度的成本
DOI: 10.1145/3463478.3463483
发表时间: 2021
期刊: ACM SIGAda Ada Letters
影响因子: --
作者:
Verschelde, Jan
通讯作者: Verschelde, Jan
使用 CUMODP 库进行有限域上的密集算术
DOI: --
发表时间: 2014
期刊: International Congress on Mathematical Software
影响因子: --
作者:
S. A. Haque;Xin Li;Farnam Mansouri;M. M. Maza;W. Pan;Ning Xie
通讯作者: Ning Xie
用于机制综合的 GPU 同伦路径跟踪器和最终游戏
DOI: --
发表时间: 2020
期刊: International Journal of Mechanisms and Robotic Systems
影响因子: --
作者:
J. Glabe;J. McCarthy
通讯作者: J. McCarthy
DOI: --
发表时间: 2014
期刊: 2014 IEEE Intl Conf on High Performance Computing and Communications, 2014 IEEE 6th Intl Symp on Cyberspace Safety and Security, 2014 IEEE 11th Intl Conf on Embedded Software and Syst (HPCC,CSS,ICESS)
影响因子: --
作者:
J. Verschelde;Xiangcheng Yu
通讯作者: Xiangcheng Yu