Profiling and optimization of Python-based social sciences applications on HPC systems by means of task and data parallelism
Authors:
- Lukasz SzustakLSLukasz Szustak
- Marcin LawendaMarcin Lawenda
- Sebastian ArmingSASebastian Arming
- Gregor BankhamerGBGregor Bankhamer
- Christoph SchweimerCSChristoph Schweimer
- Robert ElsässerRERobert Elsässer
Open Access
- 5 July 2023
- journal article
- research article
- Published by Elsevier in Future Generation Computer Systems
- Vol. 148, 623-635
Abstract
No abstract availableKeywords
This publication has 15 references indexed in Scilit:
- Architectural Adaptation and Performance-Energy Optimization for CFD Application on AMD EPYC RomeIEEE Transactions on Parallel and Distributed Systems, 2021
- Effective Exploration of Thread Throttling and Thread/Page Mapping on NUMA Systems2020
- Correlation of Performance Optimizations and Energy Consumption for Stencil-Based Application on Intel Xeon Scalable ProcessorsIEEE Transactions on Parallel and Distributed Systems, 2020
- Reducing Cache Coherence Traffic with a NUMA-Aware Runtime ApproachIEEE Transactions on Parallel and Distributed Systems, 2017
- Efficient estimation of eigenvalue counts in an intervalNumerical Linear Algebra with Applications, 2016
- A Retweet Number Prediction Model Based on Followers' Retweet Intention and Influence2014
- Optimizing spread dynamics on graphs by message passingJournal of Statistical Mechanics: Theory and Experiment, 2013
- Analyzing User Retweet Behavior on Twitter2012
- Data Parallelism for Belief Propagation in Factor Graphs2011
- Want to be Retweeted? Large Scale Analytics on Factors Impacting Retweet in Twitter Network2010