Parallelizing a Micromagnetic Program for Use on Multiprocessor Shared Memory Computers
Parallelizing a Micromagnetic Program for Use on Multiprocessor Shared Memory Computers
复制标题
DOI：
10.1109/tmag.2009.2023866
复制
发表时间：
2009-09
影响因子：
2.1
通讯作者：
M. Donahue
中科院分区：
文献类型：
--
作者：
M. Donahue
研究了共享内存计算机系统上有限差分微磁程序的并行化。人们发现效率受到内存带宽的限制，因此引入了减少内存流量的技术。四个处理器核心的计算速度提高了三倍；在某些系统上，因子可能为五。这对应于小核心数量的 5-10% 的 Karp-Flatt 系列分数。
Parallelization of a finite difference micromagnetic program on shared memory computer systems is studied. Efficiency is found to be limited by memory bandwidth, and techniques are introduced to reduce memory traffic. Computations are sped up by a factor of three with four processor cores; a factor of five is possible on some systems. This corresponds to a Karp-Flatt serial fraction of 5-10% for small core counts.