Autotuning of parallel programs using the IBM Watsons Analytics data analysis system

• Published in: PROBLEMS IN PROGRAMMING
• Date: 2018
• Issue: 1
• Pages: 46-54
• ISSN: 1727-4907
• Author Affiliations: А.Yu. Doroshenko — Institute of Software Systems NAS of Ukraine; O.S. Novak — Institute of Software Systems NAS of Ukraine; P.A. Ivanenko — Institute of Software Systems NAS of Ukraine; A.M. Starushyk — NTUU "KPI"
• Keywords: автоматизація оптимізації паралельних програм, автотюнінг програм, оптимізаційне моделювання, оптимізація, автотьюнінг, статистичне моделювання, паралельна програма, автооптимізація, паралельні обчислення, паралельні алгоритми
• Main Authors: Doroshenko, А.Yu., Novak, O.S., Ivanenko, P.A., Starushyk, A.M.
• Format: Article
• Language: Ukrainian
• Published: PROBLEMS IN PROGRAMMING 2018
• Subjects: autotuning; parallel programs; IBM Watsons Analytics; optimization; statistical modeling; UDC 681.3
• Online Access: https://pp.isofts.kiev.ua/index.php/ojs1/article/view/237
• Journal Title: Problems in programming

In this paper an analytical model of the method of automatic adjustment of parallel programs (auto-tuning) is presented. The software implementation of this model is based on the formal transformations of code and using expert data as a foundation of the optimization process and further analysis of...