Affiliation:
1. School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA
Abstract
Even distribution of irregular workload to processing units is crucial for efficient parallelization in many applications. In this work, we are concerned with a spatial partitioning called rectilinear partitioning (also known as generalized block distribution). More specifically, we address the problem of symmetric rectilinear partitioning of two dimensional domains, and utilize sparse matrices to model them. By symmetric, we mean both dimensions (i.e., the rows and columns of the matrix) are identically partitioned yielding a tiling where the diagonal tiles (blocks) will be squares. We first show that the optimal solution to this problem is NP-hard, and we propose four heuristics to solve two different variants of this problem. To make the proposed techniques more applicable in real life application scenarios, we further reduce their computational complexities by utilizing effective sparsification strategies together with an efficient sparse prefix-sum data structure. We experimentally show the proposed algorithms are efficient and effective on more than six hundred test matrices/graphs.
Publisher
Association for Computing Machinery (ACM)
Subject
Theoretical Computer Science
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Rectangular partition for n-dimensional images with arbitrarily shaped rectilinear objects;Heliyon;2024-08
2. Accelerating Sparse Data Orchestration via Dynamic Reflexive Tiling;Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3;2023-03-25