What is it about?
Hardware is evolving at an unprecedented pace, while programming models cannot cope with their advances. Indeed, it is a challenge for application developers to leverage world-class computer systems without having to manually implement low-level mechanisms such as communication protocols, schedulers, load-balancers, and many others. With this work, we propose an extension to SPar, a new parallel programming model with the main goal to ease the task of developing high-performance applications.
Featured Image
Photo by John Schnobrich on Unsplash
Why is it important?
Our work proves that our parallel programming model is expressive, flexible, and efficient. In fact, through experiments, we showed that it can be used to implement real-world stream processing applications.
Perspectives
Embracing the sequential programming model as the standard in industry and academia shows how far behind we are in terms of programming models. Aiming in this direction, the programming model we introduced in this work has shown to be a good candidate to be considered for the next generation of computer systems. It is non-intrusive, offers good programmability levels, and helps in code maintainability.
Júnior Löff
Pontifical Catholic University of Rio Grande do Sul
Read the Original
This page is a summary of: High-Level Stream and Data Parallelism in C++ for Multi-Cores, September 2021, ACM (Association for Computing Machinery),
DOI: 10.1145/3475061.3475078.
You can read the full text:
Contributors
The following have contributed to this page
