GreenMD: Energy-efficient Matrix Decomposition on Heterogeneous Multi-GPU Systems

GreenMD: Energy-efficient Matrix Decomposition on Heterogeneous Multi-GPU Systems
复制标题

GreenMD:异构多 GPU 系统上的节能矩阵分解

DOI:
10.1145/3583590
复制
发表时间:
2023
影响因子:
1.6
通讯作者:
Chen, Zizhong
Chen, Zizhong
中科院分区:
--
文献类型:
--
作者:
Zamani, Hadi;Bhuyan, Laxmi;Chen, Jieyang;Chen, Zizhong

文献摘要

参考文献

相似文献

HPC系统当前的性能增长趋势伴随着能耗的大幅增加。在这篇文章中,我们介绍了GreenMD,这是一个用于异构系统的节能框架,用于利用多GPU进行LU分解。LU分解是MAGMA库的一个关键内核,它是高度优化的。我们的目标是通过在CPU和多个GPU上智能地利用松弛来将DVFS应用于此应用程序。为了预测松弛时间,基于算法知识和制造商的规格分别为CPU和GPU开发精确的性能模型。由于DVFS不能降低静态能耗,我们还为CPU和GPU开发了欠电压技术。将电压降低到阈值以下可能会导致错误;因此,我们利用低开销分析阶段提取CPU和GPU的最小安全电压(VsafeMin),并在执行之前应用它们。GreenMD将CPU、GPU和总能耗分别提高了约59%、21%和31%,同时提供了与最先进的线性代数MAGMA库相似的性能。
The current trend of performance growth in HPC systems is accompanied by a massive increase in energy consumption. In this article, we introduce GreenMD, an energy-efficient framework for heterogeneous systems for LU factorization utilizing multi-GPUs. LU factorization is a crucial kernel from the MAGMA library, which is highly optimized. Our aim is to apply DVFS to this application by leveraging slacks intelligently on both CPUs and multiple GPUs. To predict the slack times, accurate performance models are developed separately for both CPUs and GPUs based on the algorithmic knowledge and manufacturer’s specifications. Since DVFS does not reduce static energy consumption, we also develop undervolting techniques for both CPUs and GPUs. Reducing voltage below threshold values may give rise to errors; hence, we extract the minimum safe voltages (VsafeMin) for the CPUs and GPUs utilizing a low overhead profiling phase and apply them before execution. It is shown that GreenMD improves the CPU, GPU, and total energy about 59%, 21%, and 31%, respectively, while delivering similar performance to the state-of-the-art linear algebra MAGMA library.
DOI: --
发表时间: 2009
影响因子: 2.8
作者:
Saumya Chandra;K. Lahiri;A. Raghunathan;S. Dey
通讯作者: S. Dey
百亿亿次计算
DOI: --
发表时间: 2011
期刊: Encyclopedia of Parallel Computing
影响因子: --
作者:
R. Nair
通讯作者: R. Nair
DOI: 10.1109/sc.2018.00071
发表时间: 2018-11
期刊: SC18: International Conference for High Performance Computing, Networking, Storage and Analysis
影响因子: --
作者:
Jieyang Chen;Hongbo Li;Sihuan Li;Xin Liang;Panruo Wu;Dingwen Tao;Kaiming Ouyang;Yuanlai Liu;Kai Zhao;Qiang Guan;Zizhong Chen
通讯作者: Jieyang Chen;Hongbo Li;Sihuan Li;Xin Liang;Panruo Wu;Dingwen Tao;Kaiming Ouyang;Yuanlai Liu;Kai Zhao;Qiang Guan;Zizhong Chen
DOI: --
发表时间: 2016
期刊: ICCD
影响因子: --
作者:
R. Begum;Mark Hempstead;Guru Prasad Srinivasa;Geoffrey Challen
通讯作者: Geoffrey Challen
DOI: 10.1145/1542275.1542340
发表时间: 2009-06
期刊: Proceedings of the 23rd international conference on Supercomputing
影响因子: --
作者:
B. Rountree;D. Lowenthal;B. Supinski;M. Schulz;Vincent W. Freeh;T. Bletsch
通讯作者: B. Rountree;D. Lowenthal;B. Supinski;M. Schulz;Vincent W. Freeh;T. Bletsch