Load Balancing for CPU-GPU Coupling in Computational Fluid Dynamics

被引：2

作者：

Huismann, Immo ^{[1
,3
]}

Lieber, Matthias ^{[2
,3
]}

Stiller, Joerg ^{[1
,3
]}

Froehlich, Jochen ^{[1
,3
]}

机构：

[1] Tech Univ Dresden, Inst Fluid Mech, Dresden, Germany

[2] Tech Univ Dresden, Ctr Informat Serv & High Performance Comp, Dresden, Germany

[3] Ctr Adv Elect Dresden Cfaed, Dresden, Germany

来源：

PARALLEL PROCESSING AND APPLIED MATHEMATICS (PPAM 2017), PT I | 2018年 / 10777卷

关键词：

Parallelization; Heterogeneous computing; GPGPU; Load balancing; CFD; MULTI-GPU; PARALLELIZATION;

D O I：

10.1007/978-3-319-78024-5_30

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

This paper investigates static load balancing models for CPU-GPU coupling from a computational fluid dynamics perspective. While able to generate a benefit, traditional load balancing models are found to be too inaccurate to predict the runtime of a preconditioned conjugate gradient solver. Hence, an expanded model is derived that accounts for the multi-step nature of the solver, i.e. several communication barriers per iteration. It is able to predict the runtime to a margin of 5%, rendering CPU-GPU coupling better predictable so that load balancing can be improved substantially.

引用

页码：337 / 347

页数：11

共 50 条

[21] Denial of Service in CPU-GPU Heterogeneous Architectures
Wen, Hao
Zhang, Wei
2020 IEEE HIGH PERFORMANCE EXTREME COMPUTING CONFERENCE (HPEC), 2020,
[22] A Unified CPU-GPU Protocol for GNN Training
Lin, Yi-Chien
Deng, Gangda
Prasanna, Viktor
PROCEEDINGS OF THE 21ST ACM INTERNATIONAL CONFERENCE ON COMPUTING FRONTIERS 2024, CF 2024, 2024, : 155 - 163
[23] ONLINE SCHEDULING OF MIXED CPU-GPU JOBS
Chen, Lin
Ye, Deshi
Zhang, Guochuang
INTERNATIONAL JOURNAL OF FOUNDATIONS OF COMPUTER SCIENCE, 2014, 25 (06) : 745 - 761
[24] A Efficient Algorithm for Molecular Dynamics Simulation on Hybrid CPU-GPU Computing Platforms
Li, Dapu
Ai, Wei
Ye, Yu
Liang, Jie
2016 12TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (ICNC-FSKD), 2016, : 1357 - 1363
[25] A survey on techniques for cooperative CPU-GPU computing
Raju, K.
Chiplunkar, Niranjan N.
SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS, 2018, 19 : 72 - 85
[26] Parallel Graph Partitioning on a CPU-GPU Architecture
Goodarzi, Bahareh
Burtscher, Martin
Goswami, Dhrubajyoti
2016 IEEE 30TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW), 2016, : 58 - 66
[27] Automatic CPU-GPU Communication Management and Optimization
Jablin, Thomas B.
Prabhu, Prakash
Jablin, James A.
Johnson, Nick P.
Beard, Stephen R.
August, David I.
PLDI 11: PROCEEDINGS OF THE 2011 ACM CONFERENCE ON PROGRAMMING LANGUAGE DESIGN AND IMPLEMENTATION, 2011, : 142 - 151
[28] A Survey on Heterogeneous CPU-GPU Architectures and Simulators
Alaei, Mohammad
Yazdanpanah, Fahimeh
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2025, 37 (01):
[29] A Survey of CPU-GPU Heterogeneous Computing Techniques
Mittal, Sparsh
Vetter, Jeffrey S.
ACM COMPUTING SURVEYS, 2015, 47 (04)
[30] HybridHadoop: CPU-GPU Hybrid Scheduling in Hadoop
Oh, Chanyoung
Jung, Hyeonjin
Yi, Saehanseul
Yoon, Illo
Yi, Youngmin
PROCEEDINGS OF INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING IN ASIA-PACIFIC REGION (HPC ASIA 2021), 2020, : 40 - 49

← 1 2 3 4 5 →