Learning with Analytical Models
Huda Ibeid,Siping Meng,Oliver Dobon,Luke N. Olson,William Gropp +4 more
- pp 778-786
Reads0
Chats0
TLDR
The proposed hybrid model aims to minimize prediction cost while providing reasonable prediction accuracy, and improves the prediction accuracy in comparison to pure machine learning techniques while using small training datasets, thus making it suitable for hardware and workload changes.Abstract:
To understand and predict the performance of scientific applications, several analytical and machine learning approaches have been proposed, each having its advantages and disadvantages. In this paper, we propose and validate a hybrid approach for performance modeling and prediction, which combines analytical and machine learning models. The proposed hybrid model aims to minimize prediction cost while providing reasonable prediction accuracy. Our validation results show that the hybrid model is able to learn and correct the analytical models to better match the actual performance. Furthermore, the proposed hybrid model improves the prediction accuracy in comparison to pure machine learning techniques while using small training datasets, thus making it suitable for hardware and workload changes.read more
Citations
More filters
Journal Article
Optimization and Performance Modeling of Stencil Computations on Modern Microprocessors
TL;DR: In this paper, the cache reuse methodologies across single and multiple stencil sweeps, examining cache-aware algorithms as well as cache-oblivious techniques on the Intel Itanium2, AMD Opteron, and IBM Power5, were compared.
Proceedings ArticleDOI
Indicator-Directed Dynamic Power Management for Iterative Workloads on GPU-Accelerated Systems
TL;DR: This work proposes an online dynamic power-performance (ODPP) management framework that runs on the host and dynamically adjusts GPU DVFS configurations to meet performance and power objectives without any code annotation or modification and targets GPU-accelerated systems and applications.
Proceedings ArticleDOI
Multi-Parameter Performance Modeling Based on Machine Learning with Basic Block Features
TL;DR: A multi-parameter performance modeling and prediction framework called MPerfPred, which utilizes basic block frequencies as features and uses machine learning algorithms to automatically construct multi- Parameter performance models with high generalization ability is proposed.
Multi-Parameter Performance Modeling via Tensor Completion
Edward Hutter,Edgar Solomonik +1 more
TL;DR: In this paper , a low-rank canonical-polyadic (CP) tensor decomposition is proposed for modeling application performance, where application execution times mapped within grid-cells are averaged and represented by tensor elements.
Book ChapterDOI
SMCis: Scientific Applications Monitoring and Prediction for HPC Environments
TL;DR: The SMCis, an application monitoring tool developed with the goal of collecting all aspects of scientific applications in an effective and accurate way, as well as to correlate these data graphically, with the environment of analysis and visualization is proposed.
References
More filters
Journal Article
Scikit-learn: Machine Learning in Python
Fabian Pedregosa,Gaël Varoquaux,Alexandre Gramfort,Vincent Michel,Bertrand Thirion,Olivier Grisel,Mathieu Blondel,Peter Prettenhofer,Ron Weiss,Vincent Dubourg,Jake Vanderplas,Alexandre Passos,David Cournapeau,Matthieu Brucher,Matthieu Perrot,Edouard Duchesnay +15 more
TL;DR: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems, focusing on bringing machine learning to non-specialists using a general-purpose high-level language.
Posted Content
Scikit-learn: Machine Learning in Python
Fabian Pedregosa,Gaël Varoquaux,Alexandre Gramfort,Vincent Michel,Bertrand Thirion,Olivier Grisel,Mathieu Blondel,Andreas Müller,Joel Nothman,Gilles Louppe,Peter Prettenhofer,Ron Weiss,Vincent Dubourg,Jake Vanderplas,Alexandre Passos,David Cournapeau,Matthieu Brucher,Matthieu Perrot,Edouard Duchesnay +18 more
TL;DR: Scikit-learn as mentioned in this paper is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems.
Journal ArticleDOI
Bagging predictors
TL;DR: Tests on real and simulated data sets using classification and regression trees and subset selection in linear regression show that bagging can give substantial gains in accuracy.
Journal ArticleDOI
Original Contribution: Stacked generalization
TL;DR: The conclusion is that for almost any real-world generalization problem one should use some version of stacked generalization to minimize the generalization error rate.
Journal ArticleDOI
A fast algorithm for particle simulations
TL;DR: An algorithm is presented for the rapid evaluation of the potential and force fields in systems involving large numbers of particles whose interactions are Coulombic or gravitational in nature, making it considerably more practical for large-scale problems encountered in plasma physics, fluid dynamics, molecular dynamics, and celestial mechanics.