Multilevel Summation of Electrostatic Potentials Using Graphics Processing Units.

Multilevel Summation of Electrostatic Potentials Using Graphics Processing Units.
复制标题

DOI:
10.1016/j.parco.2008.12.005
复制
发表时间:
2009-03-01
期刊:
影响因子:
1.4
通讯作者:
Schulten K
Schulten K
中科院分区:
计算机科学4区
文献类型:
--
作者:
Hardy DJ;Stone JE;Schulten K

文献摘要

参考文献

被引文献

相似文献

微处理器设计中涉及的物理和工程实用性导致传统单核微处理器的性能增长平平。科学应用程序性能持续提升的迫切需求要求使用众核处理器和加速器,如图形处理单元(GPU)。本文讨论了GPU加速的多级求和方法计算静电势和力的带电原子系统,这是一个问题,在生物分子建模应用中至关重要。我们提出并测试了一种新的GPU算法的长距离的一部分的潜力,计算格点之间的截止对潜在的,基本上卷积一个固定的3-D晶格的“权重”在所有子立方体的一个大得多的晶格。该实现利用GPU上提供的不同内存子系统,通过多处理器流式传输最佳大小的数据集。我们演示了使用单个GPU的完整多级求和计算加速高达26,使用多个GPU的加速高达46,从而能够在12秒内计算150万个原子系统的高分辨率静电势图。
Physical and engineering practicalities involved in microprocessor design have resulted in flat performance growth for traditional single-core microprocessors. The urgent need for continuing increases in the performance of scientific applications requires the use of many-core processors and accelerators such as graphics processing units (GPUs). This paper discusses GPU acceleration of the multilevel summation method for computing electrostatic potentials and forces for a system of charged atoms, which is a problem of paramount importance in biomolecular modeling applications. We present and test a new GPU algorithm for the long-range part of the potentials that computes a cutoff pair potential between lattice points, essentially convolving a fixed 3-D lattice of “weights” over all sub-cubes of a much larger lattice. The implementation exploits the different memory subsystems provided on the GPU to stream optimally sized data sets through the multiprocessors. We demonstrate for the full multilevel summation calculation speedups of up to 26 using a single GPU and 46 using multiple GPUs, enabling the computation of a high-resolution map of the electrostatic potential for a system of 1.5 million atoms in under 12 seconds.
DOI: 10.1006/jcph.1999.6201
发表时间: 1999-05-01
影响因子: 4.1
作者:
Kalé, L;Skeel, R;Schulten, K
通讯作者: Schulten, K
DOI: 10.1002/jcc.10072
发表时间: 2002-04-30
影响因子: 3
作者:
Skeel, RD;Tezcan, I;Hardy, DJ
通讯作者: Hardy, DJ
DOI: 10.1063/1.470117
发表时间: 1995-11-15
影响因子: 4.4
作者:
ESSMANN, U;PERERA, L;PEDERSEN, LG
通讯作者: PEDERSEN, LG
DOI: 10.1016/j.jcp.2008.01.047
发表时间: 2008-05-01
影响因子: 4.1
作者:
Anderson, Joshua A.;Lorenz, Chris D.;Travesset, A.
通讯作者: Travesset, A.
DOI: 10.1016/0263-7855(96)00018-5
发表时间: 1996-02-01
影响因子: 2.9
作者:
Humphrey, W;Dalke, A;Schulten, K
通讯作者: Schulten, K