Implementation of a multi-threaded framework for large-scale scientific applications

Sexton-Kennedy, E.; Gartung, Patrick; Jones, C. D.; Lange, David

doi:10.1088/1742-6596/608/1/012034

Title: Implementation of a multi-threaded framework for large-scale scientific applications

Full Record
Other Related Research

Abstract

The CMS experiment has recently completed the development of a multi-threaded capable application framework. In this paper, we will discuss the design, implementation and application of this framework to production applications in CMS. For the 2015 LHC run, this functionality is particularly critical for both our online and offline production applications, which depend on faster turn-around times and a reduced memory footprint relative to before. These applications are complex codes, each including a large number of physics-driven algorithms. While the framework is capable of running a mix of thread-safe and 'legacy' modules, algorithms running in our production applications need to be thread-safe for optimal use of this multi-threaded framework at a large scale. Towards this end, we discuss the types of changes, which were necessary for our algorithms to achieve good performance of our multithreaded applications in a full-scale application. Lastly performance numbers for what has been achieved for the 2015 run are presented.

Authors:

Sexton-Kennedy, E. ^[1]; Gartung, Patrick ^[1]; Jones, C. D. ^[1]; Lange, David ^[2]

Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

Publication Date:: Fri May 22 00:00:00 EDT 2015

Research Org.:: Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)

Sponsoring Org.:: USDOE Office of Science (SC), High Energy Physics (HEP)

OSTI Identifier:: 1249525

Report Number(s):: FERMILAB-CONF-15-621-CD
Journal ID: ISSN 1742-6588; 1372982

Grant/Contract Number:: AC02-07CH11359

Resource Type:: Accepted Manuscript

Journal Name:: Journal of Physics. Conference Series

Additional Journal Information:: Journal Volume: 608; Journal Issue: 3; Conference: 16th International workshop on Advanced Computing and Analysis Techniques in physics, Prague (Czech Republic), 1-5 Sep 2014; Journal ID: ISSN 1742-6588

Publisher:: IOP Publishing

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING

Citation Formats


                    Sexton-Kennedy, E., Gartung, Patrick, Jones, C. D., and Lange, David. Implementation of a multi-threaded framework for large-scale scientific applications.  United States: N. p., 2015. 
Web.  doi:10.1088/1742-6596/608/1/012034.

Copy to clipboard


                    Sexton-Kennedy, E., Gartung, Patrick, Jones, C. D., & Lange, David. Implementation of a multi-threaded framework for large-scale scientific applications.  United States.  https://doi.org/10.1088/1742-6596/608/1/012034

Copy to clipboard


                    Sexton-Kennedy, E., Gartung, Patrick, Jones, C. D., and Lange, David. Fri .  
"Implementation of a multi-threaded framework for large-scale scientific applications".  United States.  https://doi.org/10.1088/1742-6596/608/1/012034.  https://www.osti.gov/servlets/purl/1249525.

Copy to clipboard


                    
@article{osti_1249525,

  title        = {Implementation of a multi-threaded framework for large-scale scientific applications},

  author       = {Sexton-Kennedy, E. and Gartung, Patrick and Jones, C. D. and Lange, David},

  abstractNote = {The CMS experiment has recently completed the development of a multi-threaded capable application framework. In this paper, we will discuss the design, implementation and application of this framework to production applications in CMS. For the 2015 LHC run, this functionality is particularly critical for both our online and offline production applications, which depend on faster turn-around times and a reduced memory footprint relative to before. These applications are complex codes, each including a large number of physics-driven algorithms. While the framework is capable of running a mix of thread-safe and 'legacy' modules, algorithms running in our production applications need to be thread-safe for optimal use of this multi-threaded framework at a large scale. Towards this end, we discuss the types of changes, which were necessary for our algorithms to achieve good performance of our multithreaded applications in a full-scale application. Lastly performance numbers for what has been achieved for the 2015 run are presented.},

  doi          = {10.1088/1742-6596/608/1/012034},

  journal      = {Journal of Physics. Conference Series},

  number       = 3,

  volume       = 608,

  place        = {United States},

  year         = {Fri May 22 00:00:00 EDT 2015},

  month        = {Fri May 22 00:00:00 EDT 2015}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1088/1742-6596/608/1/012034

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 3 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

CMSSW Scaling Limits on Many-Core Machines

Conference Jones, Christopher ; Gartung, Patrick

Today the LHC offline computing relies heavily on CPU resources, despite the interest in compute accelerators, such as GPUs, for the longer term future. The number of cores per CPU socket has continued to increase steadily, reaching the levels of 64 cores (128 threads) with recent AMD EPYC processors, and 128 cores on Ampere Altra Max ARM processors. Over the course of the past decade, the CMS data processing framework, CMSSW, has been transformed from a single-threaded framework into a highly concurrent one. The first multithreaded version was brought into production by the start of the LHC Run 2 inmore »« less
Full Text Available
Using the CMS threaded framework in a production environment

Journal Article Jones, C. D. ; Contreras, L. ; Gartung, P. ; ... - Journal of Physics. Conference Series

During 2014, the CMS Offline and Computing Organization completed the necessary changes to use the CMS threaded framework in the full production environment. We will briefly discuss the design of the CMS Threaded Framework, in particular how the design affects scaling performance. We will then cover the effort involved in getting both the CMSSW application software and the workflow management system ready for using multiple threads for production. Finally, we will present metrics on the performance of the application and workflow system as well as the difficulties which were uncovered. As a result, we will end with CMS' plans formore »« less
Cited by 6
https://doi.org/10.1088/1742-6596/664/7/072026

Full Text Available
Fast and Accurate Simulation of the Cray XMT Multithreaded Supercomputer

Journal Article Villa, Oreste ; Tumeo, Antonino ; Secchi, Simone ; ... - IEEE Transactions on Parallel and Distributed Systems, 23(12):2266-2279

Irregular applications, such as data mining and analysis or graph-based computations, show unpredictable memory/network access patterns and control structures. Highly multithreaded architectures with large processor counts, like the Cray MTA-1, MTA-2 and XMT, appear to address their requirements better than commodity clusters. However, the research on highly multithreaded systems is currently limited by the lack of adequate architectural simulation infrastructures due to issues such as size of the machines, memory footprint, simulation speed, accuracy and customization. At the same time, Shared-memory MultiProcessors (SMPs) with multi-core processors have become an attractive platform to simulate large scale machines. In this paper, wemore »« less
https://doi.org/10.1109/TPDS.2012.70
Thread safety in an MPI implementation : requirements and analysis.

Journal Article Gropp, W ; Thakur, R ; Mathematics and Computer Science - Parallel Comput.

The MPI-2 Standard has carefully specified the interaction between MPI and user-created threads. The goal of this specification is to allow users to write multithreaded MPI programs while also allowing MPI implementations to deliver high performance. However, a simple reading of the thread-safety specification does not reveal what its implications are for an implementation and what implementers must be aware (and careful) of. In this paper, we describe and analyze what the MPI Standard says about thread-safety and what it implies for an implementation. We classify the MPI functions based on their thread-safety requirements and discuss several issues to considermore »« less
https://doi.org/10.1016/j.parco.2007.07.002
Thread Group Multithreading: Accelerating the Computation of an Agent-Based Power System Modeling and Simulation Tool -- C GridLAB-D

Conference Jin, Shuangshuang ; Chassin, David P.

GridLAB-DTM is an open source next generation agent-based smart-grid simulator that provides unprecedented capability to model the performance of smart grid technologies. Over the past few years, GridLAB-D has been used to conduct important analyses of smart grid concepts, but it is still quite limited by its computational performance. In order to break through the performance bottleneck to meet the need for large scale power grid simulations, we develop a thread group mechanism to implement highly granular multithreaded computation in GridLAB-D. We achieve close to linear speedups on multithreading version compared against the single-thread version of the same code runningmore »« less
https://doi.org/10.1109/HICSS.2014.318

Similar Records