Hierarchical Task-Based Programming With StarSs

Author:

Planas Judit1,Badia Rosa M.2,Ayguadé Eduard3,Labarta Jesus3

Affiliation:

1. BARCELONA SUPERCOMPUTING CENTER-CENTRO NACIONAL DE SUPERCOMPUTACIÓN (BSC-CNS), 08034 BARCELONA, SPAIN,

2. BARCELONA SUPERCOMPUTING CENTER-CENTRO NACIONAL DE SUPERCOMPUTACIÓN (BSC-CNS), 08034 BARCELONA, SPAIN, , CONSEJO SUPERIOR DE INVESTIGACIONES CIENTÍFICAS (CSIC), 28006 MADRID, SPAIN

3. BARCELONA SUPERCOMPUTING CENTER-CENTRO NACIONAL DE SUPERCOMPUTACIÓN (BSC-CNS), 08034 BARCELONA, SPAIN, , UNIVERSITAT POLITÈCNICA DE CATALUNYA, 08034 BARCELONA, SPAIN

Abstract

Programming models for multicore and many-core systems are listed as one of the main challenges in the near future for computing research. These programming models should be able to exploit the underlying platform, but also should have good programmability to enable programmer productivity. With respect to the heterogeneity and hierarchy of the underlying platforms, the programming models should take them into account but they should also enable the programmer to be unaware of the complexity of the hardware. In this paper we present an extension of the StarSs syntax to support task hierarchy. A motivation for such a hierarchical approach is presented through experimentation with CellSs. A prototype implementation of such a hierarchical task-based programming model that combines a first task level with SMPSs and a second task level with CellSs is presented. The preliminary results obtained when executing a matrix multiplication and a Cholesky factorization show the viability and potential of the approach and the current issues raised.

Publisher

SAGE Publications

Subject

Hardware and Architecture,Theoretical Computer Science,Software

Cited by 106 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. Combining Asynchronous Task Parallelism and Intel SGX for Secure Deep Learning : (Practical Experience Report);2024 19th European Dependable Computing Conference (EDCC);2024-04-08

2. Hierarchical Management of Extreme-Scale Task-Based Applications;Euro-Par 2023: Parallel Processing;2023

3. Evaluation of Distributed Tasks in Stencil-based Application on GPUs;2021 IEEE/ACM 6th International Workshop on Extreme Scale Programming Models and Middleware (ESPM2);2021-11

4. Understanding Recursive Divide-and-Conquer Dynamic Programs in Fork-Join and Data-Flow Execution Models;2021 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW);2021-06

5. Scheduling on Two Types of Resources;ACM Computing Surveys;2021-05-31

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3