.png){kind=icon}
.png){kind=icon}
Return
A data-parallel many-source shortest-path algorithm to accelerate macroscopic transport network assignment
.png){kind=icon}
OA
AI
DOI：10.1016/j.trc.2019.05.020.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The performance and scalability of macroscopic assignment and simulation software limits the quantity, scale and complexity of simulations of transport networks that are used to aid the planning, design and operation of transport systems. Through the application of many-core processing architectures (such as Graphics Processing Units (GPUs)) and data-parallel algorithms, the performance of such software can be dramatically increased. In this paper, a work-efficient, Multiple Source Shortest Path (MSSP) implementation of the Bellman-Ford algorithm is proposed to dramatically increase the performance of shortest path calculations for low-density high-diameter graphs, which are characteristic of transportation networks. This is achieved through the use of an Origin-Vertex Frontier to increase the level of parallelism within the shortest path algorithm for multiple source vertices in low-density graphs, when executed on GPUs. The algorithm is implemented within the SATURN transport simulation software and benchmarked on a range of real-world transportation networks. Our algorithm improves hardware utilisation of massively-parallel GPUs; demonstrating performance improvements of up to 7.8x over a multicore CPU (Central Processing Unit) implementation.
Keywords:
Macroscopic road network simulation
Assignment
Data-parallel
Shortest path
Algorithms
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.9
Papers:
4.7K
Citations:
3.2W
Organization
View more organizations