MULTI-GPU DGEMM AND HIGH PERFORMANCE LINPACK ON HIGHLY ENERGY-EFFICIENT CLUSTERS

被引：4

作者：

Rohr, David ^{[1
]}

Bach, Matthias ^{[1
]}

Kretz, Matthias ^{[1
]}

Lindenstruth, Volker ^{[1
]}

机构：

[1] Goethe Univ Frankfurt, Frankfurt Inst Adv Studies, D-60438 Frankfurt, Germany

来源：

IEEE MICRO | 2011年 / 31卷 / 05期

关键词：

DGEMM; double-precision general matrix multiply; GPGPU; Green IT; heterogeneous (hybrid) systems; High Performance Linpack; HPL; multi-GPU; system architecture;

D O I：

10.1109/MM.2011.66

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

High Performance Linpack can maximize requirements throughout a computer system. An efficient multi-GPU double-precision general matrix multiply (DGEMM), together with adjustments to the HPL, is required to utilize a heterogeneous computer to its full extent. The authors present the resulting energy-efficiency measurements and suggest a cluster design that can utilize multiple GPUs. © 2011 IEEE.

引用

页码：18 / 26

页数：9

共 50 条

[31] Exploiting heterogeneity of communication channels for efficient GPU selection on multi-GPU nodes
Faraji, Iman
Mirsadeghi, Seyed H.
Afsahi, Ahmad
PARALLEL COMPUTING, 2017, 68 : 3 - 16
[32] Statistical Power and Energy Modeling of Multi-GPU kernels
Ghosh, Sayan
Chandrasekaran, Sunita
Chapman, Barbara M.
2012 SC COMPANION: HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS (SCC), 2012, : 1516 - 1516
[33] Performance Optimization of Allreduce Operation for Multi-GPU Systems
Nukada, Akira
2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2021, : 3107 - 3112
[34] Two-stage Asynchronous Iterative Solvers for multi-GPU Clusters
Nayak, Pratik
Cojean, Terry
Anzt, Hartwig
PROCEEDINGS OF SCALA 2020: 11TH WORKSHOP ON LATEST ADVANCES IN SCALABLE ALGORITHMS FOR LARGE-SCALE SYSTEMS, 2020, : 9 - 18
[35] High Performance Multi-GPU SpMV for Multi-component PDE-Based Applications
Abdelfattah, Ahmad
Ltaief, Hatem
Keyes, David
EURO-PAR 2015: PARALLEL PROCESSING, 2015, 9233 : 601 - 612
[36] Multi-GPU Efficient Indexing For Maximizing Parallelism of High Dimensional Range Query Services
Kim, Mincheol
Liu, Ling
Choi, Wonik
IEEE TRANSACTIONS ON SERVICES COMPUTING, 2022, 15 (05) : 2910 - 2924
[37] MGPUSim: Enabling Multi-GPU Performance Modeling and Optimization
Sun, Yifan
Baruah, Trinayan
Mojumder, Saiful A.
Dong, Shi
Gong, Xiang
Treadway, Shane
Bao, Yuhui
Hance, Spencer
McCardwell, Carter
Zhao, Vincent
Barclay, Harrison
Ziabari, Amir Kavyan
Chen, Zhongliang
Ubal, Rafael
Abelian, Jose L.
Kim, John
Joshi, Ajay
Kaeli, David
PROCEEDINGS OF THE 2019 46TH INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA '19), 2019, : 197 - 209
[38] An efficient scheme for multi-GPU TTI reverse time migration
Guo-Feng Liu
Xiao-Hong Meng
Zhen-Jiang Yu
Ding-Jin Liu
Applied Geophysics, 2019, 16 : 56 - 63
[39] Towards High-Performance Code Generation for Multi-GPU Clusters Based on a Domain-Specific Language for Algorithmic Skeletons
Fabian Wrede
Herbert Kuchen
International Journal of Parallel Programming, 2020, 48 : 713 - 728
[40] Solving incompressible two-phase flows on multi-GPU clusters
Zaspel, Peter
Griebel, Michael
COMPUTERS & FLUIDS, 2013, 80 : 356 - 364

← 1 2 3 4 5 →