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.
|Number of pages||24|
|Journal||Software and Systems Modeling|
|Publication status||Published - 25 Mar 2021|
Bibliographical noteFunding Information:
The work in this paper was supported by the European Commission via the CROSSMINER H2020 Project (Grant #732223).
© 2021, The Author(s).
- Distributed computing
- Model management
- Model validation
- Model-driven engineering