THE WRENCH FRAMEWORK

Accurate, scalable, and reproducible simulations

WRENCH builds on the open-source SimGrid simulation framework for simulation accuracy (via its validated simulation models), scalability (low ratio of simulation time to simulated time, ability to run large simulations on a single computer with low compute, memory, and energy footprints), and expressivity (ability to simulate arbitrary platform, application, and execution scenarios). WRENCH provides high-level simulation abstractions on top of SimGrid to make it possible to implement simulators of complex scenarios with minimal development effort.

  SIMULATION BUILDING BLOCKS

Prototype implementations of cyberinfrastructure (CI) components and underlying algorithms

  SIMULATION ACCURACY

Captures the behavior of a real-world system with as little bias as possible via validated simulation models

  SCALABILITY

Ability to run large simulations quickly on a single computer with low compute, memory, and energy footprints

  REPRODUCIBLE RESULTS

Reproduction or repetition of published results by a party working independently using the same/different simulation models

  EDUCATION

eduWRENCH provides a set of simulation-driven, self-contained, modules for teaching parallel and distributed computing. These modules span a range of proficiency levels, from college freshmen to graduate students, and for assessing the pedagogic effectiveness of simulation-drive pedagogy

In a nutshell, WRENCH makes it possible to:

  • Develop in-simulation implementations of runtime systems that execute application workloads on distributed hardware platforms managed by various software services commonly known as Cyberinfrastructure (CI) services; and
  • Quickly, scalably, and accurately simulate, on a single computer, arbitrary application and platform scenarios for these runtime system implementation.

RESEARCH PUBLICATIONS

Research Papers, Journal Articles, and Technical Reports

Citing WRENCH

When citing WRENCH, please use the following paper. You should also actually read that paper, as it provides a recent and general overview on the framework.

H. Casanova, R. Ferreira da Silva, R. Tanaka, S. Pandey, G. Jethwani, W. Koch, S. Albrecht, J. Oeth, and F. Suter, "Developing Accurate and Scalable Simulators of Production Workflow Management Systems with WRENCH", Future Generation Computer Systems, vol. 112, p. 162-175, 2020.
@article{wrench,
    title = {Developing Accurate and Scalable Simulators of Production Workflow Management Systems with WRENCH},
    author = {Casanova, Henri and Ferreira da Silva, Rafael and Tanaka, Ryan and Pandey, Suraj and Jethwani, Gautam and Koch, William and Albrecht, Spencer and Oeth, James and Suter, Fr\'{e}d\'{e}ric},
    journal = {Future Generation Computer Systems},
    volume = {112},
    number = {},
    pages = {162--175},
    year = {2020},
    doi = {10.1016/j.future.2020.05.030}
}

On the Feasibility of Simulation-driven Portfolio Scheduling for Cyberinfrastructure Runtime Systems, H. Casanova, Y. C. Wong, L. Pottier, R. Ferreira da Silva, Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP), 2022, doi:

Peachy Parallel Assignments (EduPar 2022), H. M. Bücker, H. Casanova, R. Ferreira da Silva, A. Lasserre, D. Luyen, R. Namyst, J. Schoder, P-A. Wacrenier, D. P. Bunde, 12th NSF/TCPP Workshop on Parallel and Distributed Computing Education (EduPar), 2022, doi:

Teaching Parallel and Distributed Computing Concepts in Simulation with WRENCH, H. Casanova, R. Tanaka, W. Koch, R. Ferreira da Silva, Journal of Parallel and Distributed Computing, 2021, doi: 10.1016/j.jpdc.2021.05.009

GLUME: A Strategy for Reducing Workflow Execution Times on Batch-Scheduled Platforms, E. Hataishi, P.-F. Dutot, R. Ferreira da Silva, H. Casanova, Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP), 2021, doi: 10.1007/978-3-030-88224-2_11

Evaluating energy-aware scheduling algorithms for I/O-intensive scientific workflows, T. Coleman, H. Casanova, T. Gwartney, R. Ferreira da Silva, International Conference on Computational Science (ICCS), 2021, doi: 10.1007/978-3-030-77961-0_16

Peachy Parallel Assignments (EduHPC 2021), H. Casanova, R. Ferreira Da Silva, A. Gonzalez-Escribano, H. Li, Y. Torres, D. P. Bunde, 2021 IEEE/ACM Ninth Workshop on Education for High Performance Computing (EduHPC), doi: 10.1109/EduHPC54835.2021.00012

Emerging Frameworks for Advancing Scientific Workflows Research, Development, and Education, H. Casanova, E. Deelman, S. Gesing, M. Hildreth, S. Hudson, W. Koch, J. Larson, M.A. McDowell, N. Meyers, J.L. Navarro, G. Papadimitriou, R. Tanaka, I. Taylor, D. Thain, S.M. Wild, R. Filgueira, R. Ferreira da Silva, 2021 IEEE Workshop on Workflows in Support of Large-Scale Science (WORKS), doi: 10.1109/WORKS54523.2021

Peachy Parallel Assignments (EduHPC 2020), H. Casanova, R. Ferreira da Silva, A. Gonzalez-Escribano, W. Koch, Y. Torres, D. P. Bunde, 2020 IEEE/ACM Workshop on Education for High-Performance Computing (EduHPC), doi: 10.1109/EduHPC51895.2020.00012

WorkflowHub: Community Framework for Enabling Scientific Workflow Research and Development, R. Ferreira da Silva, L. Pottier, T. Coleman, E. Deelman, H. Casanova, 15th Workshop on Workflows in Support of Large-Scale Science (WORKS’20), 2020, doi: 10.1109/WORKS51914.2020.00012

Modeling the Performance of Scientific Workflow Executions on HPC Platforms with Burst Buffers, L. Pottier, R. Ferreira da Silva, H. Casanova, E. Deelman, IEEE Cluster, 2020, doi: 10.1109/CLUSTER49012.2020.00019

Developing Accurate and Scalable Simulators of Production Workflow Management Systems with WRENCH, H. Casanova, R. Ferreira da Silva, R. Tanaka, S. Pandey, G. Jethwani, W. Koch, S. Albrecht, J. Oeth, F. Suter, Future Generation Computer Systems, 2020, vol. 112, p. 162-175, doi: 10.1016/j.future.2020.05.030

Characterizing, Modeling, and Accurately Simulating Power and Energy Consumption of I/O-intensive Scientific Workflows, R. Ferreira da Silva, H. Casanova, A. Orgerie, R. Tanaka, E. Deelman, F. Suter, Journal of Computational Science, 2020, doi: 10.1016/j.jocs.2020.101157

Teaching Parallel and Distributed Computing Concepts in Simulation with WRENCH, R. Tanaka, R. Ferreira da Silva, H. Casanova, Workshop on Education for High-Performance Computing (EduHPC), 2019, doi: 10.1109/EduHPC49559.2019.00006

Bridging Concepts and Practice in eScience via Simulation-driven Engineering, R. Ferreira da Silva, H. Casanova, R. Tanaka, F. Suter, Workshop on Bridging from Concepts to Data and Computation for eScience (BC2DC’19), 15th International Conference on eScience (eScience), 2019, p. 609-614, doi: 10.1109/eScience.2019.00084

Accurately Simulating Energy Consumption of I/O-intensive Scientific Workflows, R. Ferreira da Silva, A-C. Orgerie, H. Casanova, R. Tanaka, E. Deelman, F. Suter, 2019 International Conference on Computational Science (ICCS), 2019, p. 138-152, doi: 10.1007/978-3-030-22734-0_11

WRENCH: A Framework for Simulating Workflow Management Systems, Casanova, H., Pandey, S. , Oeth, J., Tanaka, R., Suter, F., and Ferreira da Silva, R., 13th Workshop on Workflows in Support of Large-Scale Science (WORKS’18), 2018, p. 74–85, doi: 10.1109/WORKS.2018.00013

THEY USE WRENCH

Research Outcomes Enabled by WRENCH

WRENCH has enabled research in 37 research articles. These articles include research outcomes produced by our own team as well as other researchers from the workflows community.

J. McDonald, M. Horzela, F. Suter, H. Casanova, Automated Calibration of Parallel and Distributed Computing Simulators: A Case Study, 2024

J. McDonald, J. Dobbs, Y. C. Wong, R. Ferreira da Silva, H. Casanova, An exploration of online-simulation-driven portfolio scheduling in workflow management systems, 2024

J. McDonald, J. Dobbs, Y.C. Wong, R. Ferreira da Silva, H. Casanova, An exploration of online-simulation-driven portfolio scheduling in workflow management systems, 2024

Y. C. Wong, F. Suter, K. Mehta, H. Casanova, J. McDonald, Automated Calibration of a Simulator of MPI Application Executions, 2024

J. Monniot, F. Tessier, H. Casanova, G. Antoniu, Simulation of Large-Scale HPC Storage Systems: Challenges and Methodologies, 2024

M. Horzela, H. Casanova, M. Giffels, A. Gottmann, R. Hofsaess, G. Quast, S. Rossi Tisbeni, A. Streit, F. Suter, Modelling Distributed Heterogeneous Computing Infrastructures for HEP Applications, 2023

T. N'Takpé, J. E. Gnimassoun, S. Oumtanaga, F. Suter, Data-aware and simulation-driven planning of scientific workflows on IaaS clouds, 2022

T. Coleman, H. Casanova, L. Pottier, M. Kaushik, E. Deelman, R. Ferreira da Silva, WfCommons: A Framework for Enabling Scientific Workflow Research and Development, 2022

H. M. Bücker, H. Casanova, R. Ferreira da Silva, A. Lasserre, D. Luyen, R. Namyst, J. Schoder, P-A. Wacrenier, D. P. Bunde, Peachy Parallel Assignments (EduPar 2022), 2022

H. Casanova, Y. C. Wong, L. Pottier, R. Ferreira da Silva, On the Feasibility of Simulation-driven Portfolio Scheduling for Cyberinfrastructure Runtime Systems, 2022

T.M.A. Do, L. Pottier, R. Ferreira da Silva, F. Suter, S. Caino-Lores, M. Taufer, E. Deelman, Co-scheduling Ensembles of In Situ Workflows, 2022

A. Losser, J. Witzke, F. Schintke, B. Scheuermann, BottleMod: Modeling Data Flows and Tasks for Fast Bottleneck Analysis, 2022

T. Coleman, H. Casanova, T. Gwartney, R. Ferreira da Silva, Evaluating energy-aware scheduling algorithms for I/O-intensive scientific workflows, 2021

E. Hataishi, P-F. Dutot, R. Ferreira da Silva, H. Casanova, GLUME: A Strategy for Reducing Workflow Execution Times on Batch-Scheduled Platforms, 2021

H. Casanova, R. Tanaka, Koch, William, R. Ferreira da Silva, Teaching Parallel and Distributed Computing Concepts in Simulation with WRENCH, 2021

T. Coleman, H. Casanova, R. Ferreira da Silva, WfChef: Automated Generation of Accurate Scientific Workflow Generators, 2021

H-D. Do, V. Hayot-Sasson, R. Ferreira da Silva, C. Steele, H. Casanova, T. Glatard, Modeling the Linux page cache for accurate simulation of data-intensive applications, 2021

H. Casanova, E. Deelman, S. Gesing, M. Hildreth, S. Hudson, W. Koch, J. Larson, M.A. McDowell, N. Meyers, J-L. Navarro, G. Papadimitriou, R. Tanaka, I. Taylor, D. Thain, S.M. Wild, R. Filgueira, R. Ferreira da Silva, Emerging Frameworks for Advancing Scientific Workflows Research, Development, and Education, 2021

R. Ferreira da Silva, H. Casanova, A-C. Orgerie, R. Tanaka, E. Deelman, F. Suter, Characterizing, Modeling, and Accurately Simulating Power and Energy Consumption of I/O-intensive Scientific Workflows, 2020

J. E. Gnimassoun, T. N'Takpe, G. H. F. Diedie, S. Oumtanaga, A Workflow Scheduling Algorithm for Reducing Data Transfers in Cloud IaaS, 2020

L. Pottier, R. Ferreira da Silva, H. Casanova, E. Deelman, Modeling the Performance of Scientific Workflow Executions on HPC Platforms with Burst Buffers, 2020

R. Ferreira da Silva, L. Pottier, T. Coleman, E. Deelman, H. Casanova, WorkflowHub: Community Framework for Enabling Scientific Workflow Research and Development, 2020

H. Casanova, R. Ferreira da Silva, A. Gonzalez-Escribano, W. Koch, Y. Torres, D. P. Bunde, Peachy Parallel Assignments (EduHPC 2020), 2020

R. Ferreira da Silva, R. Filgueira, E. Deelman, E. Pairo-Castineira, I. M. Overton, M. Atkinson, Using Simple PID-inspired Controllers for Online Resilient Resource Management of Distributed Scientific Workflows, 2019

R. Ferreira da Silva, R. Mayani, Y. Shi, A. R. Kemanian, M. Rynge, E. Deelman, Empowering Agroecosystem Modeling with HTC Scientific Workflows: The Cycles Model Use Case, 2019

R. Ferreira da Silva, A-C. Orgerie, H. Casanova, R. Tanaka, E. Deelman, F. Suter, Accurately Simulating Energy Consumption of I/O-intensive Scientific Workflows, 2019

R. Ferreira da Silva, H. Casanova, R. Tanaka, F. Suter, Bridging Concepts and Practice in eScience via Simulation-driven Engineering, 2019

R. Tanaka, R. Ferreira da Silva, H. Casanova, Teaching Parallel and Distributed Computing Concepts in Simulation with WRENCH, 2019

H. Casanova, A. Legrand, M. Quinson, F. Suter, SMPI Courseware: Teaching Distributed-Memory Computing with MPI in Simulation, 2018

WHO ARE WE?

ABOUT

WRENCH is open-source software distributed under the LGPLV3 license

WRENCH is mainly developed by a collaborative team from the University of Hawai'i at Mãnoa (UHM), the Oak Ridge National Laboratory (ORNL), and the University of Southern California (USC).


Henri Casanova
Professor of Computer Science at the University of Hawai'i at Manoa, and member of the SimGrid team


Rafael Ferreira da Silva
Senior Research Scientist at the Oak Ridge National Laboratory


Frédéric Suter
Senior Research Scientist at the Oak Ridge National Laboratory, and member of the SimGrid team


Jesse McDonald
Computer Science PhD student at the University of Hawaii at Manoa


Loïc Pottier
Research Scientist at the Lawrence Livermore National Laboratory


PREVIOUS CONTRIBUTORS

  Derrick Luyen
Computer Science Masters student at the University of Hawaii at Manoa

  Tainã Coleman
Computer Science PhD student at the University of Southern California

  Jason Feuerstein
Computer Science undergraduate student at University of Southern California

  Gautam Jethwani
Computer Science undergraduate student at University of Southern California

  Evan Hataishi
Computer Science Masters student at University of Hawaii at Manoa

  Ty Gwartney
Computer Science and Maths Undergraduate Student at the University of Hawai`i at Manoa

  William Koch
Computer Science Masters student at University of Hawaii at Manoa

  Ryan Tanaka
Computer Science Masters student at University of Hawaii at Manoa

  Vivian (Tongyu) Zhu
Computer Science undergraduate student at University of Southern California

  Suraj Pandey
Computer Science Masters student at University of Hawaii at Manoa

  Tabitha See Ya Lee
Computer Science undegraduate student at Vanderbilt University

  Samuel He
Computer Science undergraduate student at University of Southern California

  Spencer Albrecht
Computer Science undergraduate student at University of Southern California

  James Oeth
Computer Science undergraduate student at University of Southern California

DEV'S CORNER

Best practices and collaborative insights for developing and enhancing the WRENCH simulation framework

WRENCH's source code is available on GitHub. Our preferred channel to report a bug or request a feature is via WRENCH's Github Issues Track.

You can also reach the WRENCH team via our support email at support@wrench-project.org.

  JOIN US ON SLACK

Connect with the WRENCH community on Slack to collaborate with peers, share your experiences, and get real-time support and updates on the WRENCH simulation framework

The WfCommons project offers a collection of workflow traces and tools for generating synthetic yet realistic workflow instances, seamlessly compatible with simulators developed using the WRENCH framework

Latest Unstable Version

If you want to use the latest unstable version, that will contain brand-new features and can achieve up-to-date performances (but may also contain bugs as the stabilization work is still underway), you may consider retrieving the latest unstable version.

git clone https://github.com/wrench-project/wrench.git