Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Parallel Simulation of a Multi-Span DWDM System Limited by FWM Using OpenMP and Dynamic Parallelism in CUDA

Version 1 : Received: 21 March 2021 / Approved: 23 March 2021 / Online: 23 March 2021 (09:40:25 CET)

How to cite: Sanchez-Lara, R.; Lopez-Martinez, J.L.; Trejo-Sanchez, J.A.; Offerhaus, H.L.; Alvarez-Chavez, J.A. Parallel Simulation of a Multi-Span DWDM System Limited by FWM Using OpenMP and Dynamic Parallelism in CUDA. Preprints 2021, 2021030558 (doi: 10.20944/preprints202103.0558.v1). Sanchez-Lara, R.; Lopez-Martinez, J.L.; Trejo-Sanchez, J.A.; Offerhaus, H.L.; Alvarez-Chavez, J.A. Parallel Simulation of a Multi-Span DWDM System Limited by FWM Using OpenMP and Dynamic Parallelism in CUDA. Preprints 2021, 2021030558 (doi: 10.20944/preprints202103.0558.v1).

Abstract

One of the non-linear phenomena that affect high bandwidth and long reach communication systems is the non-linear phenomenon called four-wave mixing (FWM). Unfortunately, the simulation of such systems aiming to obtain their design parameter limitations require more time as the number of channels increases. In this paper, we propose a new high-performance computational model to obtain optimal design parameters in a multi san Dense Wavelength Division Multiplexing (DWDM) system, limited by FWM and the intrinsic Amplified Spontaneous Emission (ASE) noise of optical amplifiers employed in each segment. The simulation in this work provides a complete optical design characterization and compares the efficiency and speed improvement of the proposed parallelization model versus a previous sequential model. Additionally, an analysis of the computational complexity of parallel model is presented, where two parallel implementations are used. First, Open Multi−Processing (OpenMP), based on the use of a central, multi-core processing unit is used and secondly the Compute Unified Device Arquitecture (CUDA), which is based on the use of graphics processing unit. Results show that parallelism improves to up to 40 times the performance of the simulation when nested parallelization with CUDA is used, over de sequential method and up to 6 times compared with the implementation with OpenMP using 12 processors. Within our parallel implementation, it is possible to simulate with an increased number of channels, that was unpractical in the sequential simulation.

Subject Areas

CUDA; parallel architectures; parallel programming; computer simulation; non-linear fiber optics

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.