Distributed model validation with Epsilon

TY - JOUR

T1 - Distributed model validation with Epsilon

AU - Madani, Sina

AU - Kolovos, Dimitris

AU - Paige, Richard F.

N1 - Funding Information: The work in this paper was supported by the European Commission via the CROSSMINER H2020 Project (Grant #732223). Publisher Copyright: © 2021, The Author(s).

PY - 2021/3/25

Y1 - 2021/3/25

N2 - Scalable performance is a major challenge with current model management tools. As the size and complexity of models and model management programs increases and the cost of computing falls, one solution for improving performance of model management programs is to perform computations on multiple computers. In this paper, we demonstrate a low-overhead data-parallel approach for distributed model validation in the context of an OCL-like language. Our approach minimises communication costs by exploiting the deterministic structure of programs and can take advantage of multiple cores on each (heterogeneous) machine with highly configurable computational granularity. Our performance evaluation shows that the implementation is extremely low overhead, achieving a speed up of 24.5× with 26 computers over the sequential case, and 122× when utilising all six cores on each computer.

AB - Scalable performance is a major challenge with current model management tools. As the size and complexity of models and model management programs increases and the cost of computing falls, one solution for improving performance of model management programs is to perform computations on multiple computers. In this paper, we demonstrate a low-overhead data-parallel approach for distributed model validation in the context of an OCL-like language. Our approach minimises communication costs by exploiting the deterministic structure of programs and can take advantage of multiple cores on each (heterogeneous) machine with highly configurable computational granularity. Our performance evaluation shows that the implementation is extremely low overhead, achieving a speed up of 24.5× with 26 computers over the sequential case, and 122× when utilising all six cores on each computer.

KW - Distributed computing

KW - Model management

KW - Model validation

KW - Model-driven engineering

KW - Parallelism

UR - http://www.scopus.com/inward/record.url?scp=85103294491&partnerID=8YFLogxK

U2 - 10.1007/s10270-021-00878-x

DO - 10.1007/s10270-021-00878-x

M3 - Article

AN - SCOPUS:85103294491

SN - 1619-1366

VL - 20

SP - 1689

EP - 1712

JO - Software and Systems Modeling

JF - Software and Systems Modeling

IS - 5

ER -