Journal ArticleDOI
Simulation of an inelastic dispersive phenomenon: stimulated Brillouin scattering in a single-mode fiber segment through parallelism
TLDR
A novel high-performance computing model intended to analyze the main dispersive effects present in modern fiber communication systems is proposed and results show that parallelism increases the performance of the simulation tenfold.Abstract:
Stimulated Brillouin scattering (SBS) is one of the most important nonlinear phenomena because it limits the maximum transmission power in modern optical communication systems. Unfortunately, the simulation of SBS is time-consuming, since it requires estimating the solutions for a set of complex differential equations that describe this phenomenon. In this paper, a novel high-performance computing model intended to analyze the main dispersive effects present in modern fiber communication systems is proposed. A full optical characterization of the simulation results is included and compared with the efficiency and improved speed of our parallel implementation versus a previous sequential model for SBS. Also, an evaluation of the throughput of our parallel implementation using both central processing unit multi-core and graphics processing unit is presented. Results show that parallelism increases the performance of the simulation tenfold.read more
Citations
More filters
Journal ArticleDOI
Co-Processing Parallel Computation for Distributed Optical Fiber Vibration Sensing
TL;DR: The combination of FPGA, CPU and GPU can largely enhance the capacity of data acquisition and processing, and improve the real-time performance of distributed optical fiber vibration sensing systems.
Posted ContentDOI
Parallel Simulation of a Multi-Span DWDM System Limited by FWM Using OpenMP and Dynamic Parallelism in CUDA
R. Sanchez-Lara,J. L. López-Martínez,Joel Antonio Trejo-Sánchez,Herman L. Offerhaus,Jose Alfredo Alvarez-Chavez +4 more
TL;DR: A new high-performance computational model is proposed to obtain the optimal design parameters in a multi4 span Dense Wavelength Division Multiplexing (DWDM) system, limited by FWM and the intrinsic Amplified Spontaneous Emission noise of optical amplifiers employed in each segment.
References
More filters
Book
Nonlinear Fiber Optics
TL;DR: The field of nonlinear fiber optics has advanced enough that a whole book was devoted to it as discussed by the authors, which has been translated into Chinese, Japanese, and Russian languages, attesting to the worldwide activity in the field.
Book
An introduction to parallel algorithms
TL;DR: This book provides an introduction to the design and analysis of parallel algorithms, with the emphasis on the application of the PRAM model of parallel computation, with all its variants, to algorithm analysis.
Proceedings ArticleDOI
Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU
Victor W. Lee,Changkyu Kim,Jatin Chhugani,Michael E. Deisher,Daehyun Kim,Anthony D. Nguyen,Nadathur Satish,Mikhail Smelyanskiy,Srinivas Chennupaty,Per Hammarlund,Ronak Singhal,Pradeep Dubey +11 more
TL;DR: This paper discusses optimization techniques for both CPU and GPU, analyzes what architecture features contributed to performance differences between the two architectures, and recommends a set of architectural features which provide significant improvement in architectural efficiency for throughput kernels.
Journal ArticleDOI
Large-scale simulation of elastic wave propagation in heterogeneous media on parallel computers
Hesheng Bao,Jacobo Bielak,Omar Ghattas,Loukas F. Kallivokas,David R. O'Hallaron,Jonathan Richard Shewchuk,Jifeng Xu +6 more
TL;DR: A system that helps automate the task of writing efficient portable unstrucmred mesh solvers for distributed memory parallel supercomputers and indicates that, despite the highly irregular structure of the problem, excellent performance and scalability are achieved.
Journal ArticleDOI
Debunking the 100X GPU vs. CPU myth
W LeeVictor,KimChangkyu,ChhuganiJatin,DeisherMichael,KimDaehyun,D NguyenAnthony,SatishNadathur,SmelyanskiyMikhail,ChennupatySrinivas,HammarlundPer,SinghalRonak,DubeyPradeep +11 more
TL;DR: This research presents a novel and scalable approach to throughput computing that combines reinforcement learning, artificial intelligence, and reinforcement learning to solve the challenge of integrating NoSQL data stores to manage massive amounts of data.