A2Cloud‐RF : A random forest based statistical framework to guide resource selection for high‐performance scientific computing on the cloud

Samuel, David; Khan, Syeduzzaman; Balos, Cody J.; Abuelhaj, Zachariah; Dutoi, Anthony D.; Kari, Chadi; Mueller, David; Pallipuram, Vivek K.

doi:10.1002/cpe.5942

A2Cloud‐RF : A random forest based statistical framework to guide resource selection for high‐performance scientific computing on the cloud

Journal Article · 22 July 2020 · Concurrency and Computation. Practice and Experience

DOI:https://doi.org/10.1002/cpe.5942· OSTI ID:1641843

Samuel, David ^[1]; Khan, Syeduzzaman ^[1]; Balos, Cody J. ^[2]; Abuelhaj, Zachariah ^[1]; Dutoi, Anthony D. ^[3]; Kari, Chadi ^[1]; Mueller, David ^[1]; ^[1]

School of Engineering and Computer Science University of the Pacific Stockton California USA
Lawrence Livermore National Laboratory Stockton California USA
Department of Chemistry, College of the Pacific University of the Pacific Stockton California USA

Summary

This article proposes a random‐forest based A2Cloud framework to match scientific applications with Cloud providers and their instances for high performance. The framework leverages four engines for this task: PERF engine, Cloud trace engine, A2Cloud‐ext engine, and the random forest classifier (RFC) engine. The PERF engine profiles the application to obtain performance characteristics, including the number of single‐precision (SP) floating‐point operations (FLOPs), double‐precision (DP) FLOPs, x87 operations, memory accesses, and disk accesses. The Cloud trace engine obtains the corresponding performance characteristics of the selected Cloud instances including: SP floating point operations per second (FLOPS), DP FLOPS, x87 operations per second, memory bandwidth, and disk bandwidth. The A2Cloud‐ext engine uses the application and Cloud instance characteristics to generate objective scores that represent the application‐to‐Cloud match. The RFC engine uses these objective scores to generate two types of random forests to assist users with rapid analysis: application‐specific random forests (ARF) and application‐class based random forests. The ARF consider only the input application's characteristics to generate a random forest and provide numerical ratings to the selected Cloud instances. To generate the application‐class based random forests, the RFC engine downloads the application profiles and scores of previously tested applications that perform similar to the input application. Using these data, the RFC engine creates a random forest for instance recommendation. We exhaustively test this framework using eight real‐world applications across 12 instances from different Cloud providers. Our tests show significant statistical agreement between the instance ratings given by the framework and the ratings obtained via actual Cloud executions.

View Accepted Manuscript (Publisher)

Sponsoring Organization:: USDOE

Grant/Contract Number:: NONE; AC52-07NA27344

OSTI ID:: 1641843

Journal Information:: Concurrency and Computation. Practice and Experience, Journal Name: Concurrency and Computation. Practice and Experience Journal Issue: 24 Vol. 32; ISSN 1532-0626

Publisher:: Wiley Blackwell (John Wiley & Sons)Copyright Statement

Country of Publication:: United Kingdom

Language:: English

References (42)

Simplified Dynamics of Human and Mammalian Neocortical Neurons Wilson, Hugh R. Journal of Theoretical Biology, Vol. 200, Issue 4 https://doi.org/10.1006/jtbi.1999.1002	journal	October 1999
Fragmentation Methods: A Route to Accurate Calculations on Large Systems Gordon, Mark S.; Fedorov, Dmitri G.; Pruitt, Spencer R. Chemical Reviews, Vol. 112, Issue 1 https://doi.org/10.1021/cr200093j	journal	August 2011
Energy-Based Molecular Fragmentation Methods Collins, Michael A.; Bettens, Ryan P. A. Chemical Reviews, Vol. 115, Issue 12 https://doi.org/10.1021/cr500455b	journal	April 2015
Frozen-Density Embedding Strategy for Multilevel Simulations of Electronic Structure Wesolowski, Tomasz A.; Shedge, Sapana; Zhou, Xiuwen Chemical Reviews, Vol. 115, Issue 12 https://doi.org/10.1021/cr500502v	journal	April 2015
Accurate Composite and Fragment-Based Quantum Chemical Models for Large Molecules Raghavachari, Krishnan; Saha, Arjun Chemical Reviews, Vol. 115, Issue 12 https://doi.org/10.1021/cr500606e	journal	April 2015
The spin–flip approach within time-dependent density functional theory: Theory and applications to diradicals Shao, Yihan; Head-Gordon, Martin; Krylov, Anna I. The Journal of Chemical Physics, Vol. 118, Issue 11 https://doi.org/10.1063/1.1545679	journal	March 2003
A generalized many-body expansion and a unified view of fragment-based methods in electronic structure theory Richard, Ryan M.; Herbert, John M. The Journal of Chemical Physics, Vol. 137, Issue 6 https://doi.org/10.1063/1.4742816	journal	August 2012
Simulation of surface processes Jonsson, H. Proceedings of the National Academy of Sciences, Vol. 108, Issue 3 https://doi.org/10.1073/pnas.1006670108	journal	January 2011
Systematically improvable excitonic Hamiltonians for electronic structure theory Dutoi, Anthony D.; Liu, Yuhong Molecular Physics, Vol. 117, Issue 4 https://doi.org/10.1080/00268976.2018.1522003	journal	September 2018
Excitonically renormalised coupled-cluster theory Liu, Yuhong; Dutoi, Anthony D. Molecular Physics, Vol. 117, Issue 4 https://doi.org/10.1080/00268976.2018.1523481	journal	September 2018
A best-features based digital rotoscope Murphy, Iain; Norlund, Tyler; Pallipuram, Vivek K. 2017 51st Asilomar Conference on Signals, Systems, and Computers https://doi.org/10.1109/ACSSC.2017.8335175	conference	October 2017
Cloud big data decision support system for machine learning on AWS: Analytics of analytics Kaplunovich, Alex; Yesha, Yelena 2017 IEEE International Conference on Big Data (Big Data) https://doi.org/10.1109/BigData.2017.8258340	conference	December 2017
Cloud Service Selection with Fuzzy C-Means Artificial Immune Network Memory Classifier Ha, Weitao 2018 14th International Conference on Computational Intelligence and Security (CIS) https://doi.org/10.1109/CIS2018.2018.00065	conference	November 2018
Efficient Bidding for Virtual Machine Instances in Clouds Zaman, Sharrukh; Grosu, Daniel 2011 IEEE 4th International Conference on Cloud Computing (CLOUD) https://doi.org/10.1109/CLOUD.2011.49	conference	July 2011
Optimal Cloud Resource Selection Method Considering Hard and Soft Constraints and Multiple Conflicting Objectives Powell, Courtney; Miura, Katsunori; Munetomo, Masaharu 2018 IEEE 11th International Conference on Cloud Computing (CLOUD) https://doi.org/10.1109/CLOUD.2018.00115	conference	July 2018
Self-Regulated Multi-criteria Decision Analysis: An Autonomous Brokerage-Based Approach for Service Provider Ranking in the Cloud Wasim, Muhammad Umer; Ibrahim, Abdallah A. Z. A.; Bouvry, Pascal 2017 IEEE International Conference on Cloud Computing Technology and Science (CloudCom) https://doi.org/10.1109/CloudCom.2017.44	conference	December 2017
Performance evaluation of cloud computing providers using fuzzy multiattribute group decision making model Grandhi, Srimannarayana; Wibowo, Santoso 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) https://doi.org/10.1109/FSKD.2015.7381928	conference	August 2015
Decision making on adoption of cloud computing in e-commerce using fuzzy TOPSIS Sohaib, Osama; Naderpour, Mohsen 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) https://doi.org/10.1109/FUZZ-IEEE.2017.8015404	conference	July 2017
A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning Liu, Ning; Li, Zhe; Xu, Jielong 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS) https://doi.org/10.1109/ICDCS.2017.123	conference	June 2017
ML-NA: A Machine Learning Based Node Performance Analyzer Utilizing Straggler Statistics Ouyang, Xue; Wang, Changjian; Yang, Renyu 2017 IEEE 23rd International Conference on Parallel and Distributed Systems (ICPADS) https://doi.org/10.1109/ICPADS.2017.00021	conference	December 2017
A Testing Engine for High-Performance and Cost-Effective Workflow Execution in the Cloud Pallipuram, V. K.; Estrada, T.; Taufer, M. 2015 44th International Conference on Parallel Processing (ICPP) https://doi.org/10.1109/ICPP.2015.94	conference	September 2015
CELIA: Cost-Time Performance of Elastic Applications on Cloud Rathnayake, Sunimal; Loghin, Dumitrel; Teo, Yong Meng 2017 46th International Conference on Parallel Processing (ICPP) https://doi.org/10.1109/ICPP.2017.43	conference	August 2017
Acceleration of spiking neural networks in emerging multi-core and GPU architectures Bhuiyan, Mohammad A.; Pallipuram, Vivek K.; Smith, Melissa C. Distributed Processing, Workshops and Phd Forum (IPDPSW 2010), 2010 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW) https://doi.org/10.1109/IPDPSW.2010.5470899	conference	April 2010
Applying the roofline model Ofenbeck, Georg; Steinmann, Ruedi; Caparros, Victoria 2014 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) https://doi.org/10.1109/ISPASS.2014.6844463	conference	March 2014
Online Algorithms for Cost-Effective Cloud Selection with Multiple Demands Jin, Youngmi; Hayashi, Michiaki; Tagami, Atsushi 2018 30th International Teletraffic Congress (ITC 30) https://doi.org/10.1109/ITC30.2018.00014	conference	September 2018
Cost-Aware Cloud Profiling, Prediction, and Provisioning as a Service Chard, Ryan; Chard, Kyle; Wolski, Rich IEEE Cloud Computing, Vol. 4, Issue 4 https://doi.org/10.1109/MCC.2017.3791025	journal	July 2017
Data migration algorithms in heterogeneous storage systems: A comparative performance evaluation Roberts, Gary; Chen, Sixia; Kari, Chadi 2017 IEEE 16th International Symposium on Network Computing and Applications (NCA) https://doi.org/10.1109/NCA.2017.8171340	conference	October 2017
Daleel: Simplifying cloud instance selection using machine learning Samreen, Faiza; Elkhatib, Yehia; Rowe, Matthew NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium https://doi.org/10.1109/NOMS.2016.7502858	conference	April 2016
HPC Application Performance and Cost Efficiency in the Cloud Roloff, Eduardo; Diener, Matthias; Gaspary, Luciano Paschoal 2017 25th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP) https://doi.org/10.1109/PDP.2017.59	conference	January 2017
Cloud Workload Prediction and Generation Models Wamba, Gilles Madi; Li, Yunbo; Orgerie, Anne-Cecile 2017 29th International Symposium on Computer Architecture and High-Performance Computing (SBAC-PAD), 2017 29th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD) https://doi.org/10.1109/SBAC-PAD.2017.19	conference	October 2017
Understanding the Performance and Potential of Cloud Computing for Scientific Applications Sadooghi, Iman; Martin, Jesus Hernandez; Li, Tonglin IEEE Transactions on Cloud Computing, Vol. 5, Issue 2 https://doi.org/10.1109/TCC.2015.2404821	journal	April 2017
Simple model of spiking neurons Izhikevich, E. M. IEEE Transactions on Neural Networks, Vol. 14, Issue 6 https://doi.org/10.1109/TNN.2003.820440	journal	November 2003
Comprehensive Elastic Resource Management to Ensure Predictable Performance for Scientific Applications on Public IaaS Clouds Kim, In Kee; Steele, Jacob; Qi, Yanjun 2014 IEEE/ACM 7th International Conference on Utility and Cloud Computing (UCC) https://doi.org/10.1109/UCC.2014.45	conference	December 2014
A quantitative description of membrane current and its application to conduction and excitation in nerve Hodgkin, A. L.; Huxley, A. F. The Journal of Physiology, Vol. 117, Issue 4 https://doi.org/10.1113/jphysiol.1952.sp004764	journal	August 1952
Understanding and Improving Computational Science Storage Access through Continuous Characterization Carns, Philip; Harms, Kevin; Allcock, William ACM Transactions on Storage, Vol. 7, Issue 3, p. 1-26 https://doi.org/10.1145/2027066.2027068	journal	October 2011
Heterogeneity and dynamicity of clouds at scale: Google trace analysis Reiss, Charles; Tumanov, Alexey; Ganger, Gregory R. Proceedings of the Third ACM Symposium on Cloud Computing - SoCC '12 https://doi.org/10.1145/2391229.2391236	conference	January 2012
Selecting Efficient Cloud Resources for HPC Workloads Brunetta, Jeferson R.; Borin, Edson UCC '19: IEEE/ACM 12th International Conference on Utility and Cloud Computing, Proceedings of the 12th IEEE/ACM International Conference on Utility and Cloud Computing https://doi.org/10.1145/3344341.3368798	conference	December 2019
Cloud Instance Selection Using Parallel K-Means and AHP Guo, Taiyang; Bahsoon, Rami; Chen, Tao Proceedings of the 12th IEEE/ACM International Conference on Utility and Cloud Computing Companion - UCC '19 Companion https://doi.org/10.1145/3368235.3368845	conference	January 2019
Advances in Correlated Electronic Structure Methods for Solids, Surfaces, and Nanostructures Huang, Patrick; Carter, Emily A. Annual Review of Physical Chemistry, Vol. 59, Issue 1 https://doi.org/10.1146/annurev.physchem.59.032607.093528	journal	May 2008
Modeling of Semiconductor Nanostructures with nextnano ³ Birner, S.; Hackenbuchner, S.; Sabathil, M. Acta Physica Polonica A, Vol. 110, Issue 2 https://doi.org/10.12693/APhysPolA.110.111	journal	August 2006
LULESH Programming Model and Performance Ports Overview Karlin, I. https://doi.org/10.2172/1059462	report	December 2012
Setting Priorities - A Heuristic Approach for Cloud Data Center Selection [Setting Priorities - A Heuristic Approach for Cloud Data Center Selection] Hans, Ronny; Steffen, David; Lampe, Ulrich Proceedings of the 5th International Conference on Cloud Computing and Services Science https://doi.org/10.5220/0005494702210228	conference	May 2015

Similar Records

The implications of working set analysis on supercomputing memory hierarchy design.

Conference · 2005 · OSTI ID:946978

Design Space Exploration of Emerging Memory Technologies for Machine Learning Applications

Conference · 2021 · OSTI ID:1807257

An Empirical Roofline Methodology for Quantitatively Assessing Performance Portability

Conference · 2018 · PROCEEDINGS OF 2018 IEEE/ACM INTERNATIONAL WORKSHOP ON PERFORMANCE, PORTABILITY AND PRODUCTIVITY IN HPC (P3HPC 2018 · OSTI ID:1567493

A2Cloud‐RF : A random forest based statistical framework to guide resource selection for high‐performance scientific computing on the cloud

Citation Formats

References (42)

Similar Records

Related Subjects