Predicting GPU Performance from CPU Runs Using Machine Learning
Authors:
- Ioana BaldiniIBIoana Baldini
- Stephen J. FinkSFStephen J. Fink
- Erik AltmanEAErik Altman
- 1 October 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15506533,p. 254-261
Abstract
Graphics processing units (GPUs) can deliver considerable performance gains over general purpose processors. However, GPU performance improvement vary considerably across applications. Porting applications to GPUs by rewriting code with GPU-specific languages requires significant effort. In consequence, it is desirable to predict which applications would benefit most before porting to the GPU. This paper shows that machine learning techniques can build accurate predictive models for GPU acceleration. This study presents an approach which applies supervised learning algorithms to infer predictive models, based on dynamic profile data collected via instrumented runs on general purpose processors. For a set of 18 parallel benchmarks, the results show that a small set of easily-obtainable features can predict the magnitude of GPU speedups on two different high-end GPUs, with accuracies varying between 77% and 90%, depending on the prediction mechanism and scenario. For already-ported applications, similar models can predict the best device to run an application with an effective accuracy of 91%.Keywords
This publication has 21 references indexed in Scilit:
- Mitigating the compiler optimization phase-ordering problem using machine learning2012
- Compiling a high-level language for GPUs2012
- A performance analysis framework for identifying potential benefits in GPGPU applications2012
- The WEKA data mining softwareACM SIGKDD Explorations Newsletter, 2009
- Kernel methods in machine learningThe Annals of Statistics, 2008
- Efficiently exploring architectural design spaces via predictive modeling2006
- Accurate and efficient regression modeling for microarchitectural performance and power prediction2006
- Pin2005
- Support-vector networksMachine Learning, 1995
- Learning Representative Exemplars of Concepts: An Initial Case Study1987