Tuning block-parallel all-pairs shortest path algorithm for efficient multi-core implementa- tion.
نویسندگان
چکیده
Finding shortest paths in a weighted graph is one of the key problems computer-science, which has numerous practical applications multiple domains. This paper analyzes parallel blocked all-pairs path algorithm at aim evaluating influence multi-core system and its hierarchical cache memory on parameters implementation depending size distance matrix’s block. It proposes technique tuning block-size to given system. The involves profiling tools process allows increase throughput. Computational experiments carried out rack server equipped with two Intel Xeon E5-2620 v4 processors 8 cores 16 hardware threads each have convincingly shown for various sizes that behavior operation don’t depend are determined only by block size. To tune target system, preferable can be found once whose in-memory matrix representation larger than shared among all processor’s cores. Then this blocksize reused graphs bigger efficient solving problem
منابع مشابه
An Efficient Parallel Algorithm for the All Pairs Shortest Path Problem
The all pairs shortest path problem is a class of the algebraic path problem. Many parallel algorithms for the solution of this problem appear in the literature. One of the efficient parallel algorithms on W-RAM model is given by Kucera[17]. Though efficient, algorithms written for the W-RAM model of parallel computation are too idealistic to be implemented on the current hardware. In this repo...
متن کاملAn Optimal Distributed Algorithm for All-pairs Shortest-path
In this paper the network problem of determining all-pairs shortest-path is examined. A distributed algorithm which runs in O(n) time on a network of n nodes is presented. The number of messages of the algorithm is O(e+n log n) where e is the number of communication links of the network. We prove that this algorithm is time optimal.
متن کاملAll-pairs Shortest Path Algorithm based on MPI+CUDA Distributed Parallel Programming Model
In view of the problem that computing shortest paths in a graph is a complex and time-consuming process, and the traditional algorithm that rely on the CPU as computing unit solely can't meet the demand of real-time processing, in this paper, we present an all-pairs shortest paths algorithm using MPI+CUDA hybrid programming model, which can take use of the overwhelming computing power of the GP...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Sistemnyj Analiz i Prikladnaâ Informatika
سال: 2022
ISSN: ['2414-0481', '2309-4923']
DOI: https://doi.org/10.21122/2309-4923-2022-3-57-65