Performance Prediction Model and Analysis for Compute-Intensive Tasks on GPUs

Autor:	John K. Antonio, Amlan Chatterjee, Sridhar Radhakrishnan, Khondker S. Hasan
Rok vydání:	2014
Předmět:	CUDA General purpose Computer science Performance prediction Programming paradigm Context (language use) Parallel computing Graphics Power (physics)
Zdroj:	Advanced Information Systems Engineering ISBN: 9783642387081 NPC
DOI:	10.1007/978-3-662-44917-2_65
Popis:	Using Graphics Processing Units (GPUs) to solve general purpose problems has received significant attention both in academia and industry. Harnessing the power of these devices however requires knowledge of the underlying architecture and the programming model. In this paper, we develop analytical models to predict the performance of GPUs for computationally intensive tasks. Our models are based on varying the relevant parameters - including total number of threads, number of blocks, and number of streaming multi-processors - and predicting the performance of a program for a specified instance of these parameters. The approach can be used in the context of heterogeneous environments where distinct types of GPU devices with different hardware configurations are employed.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::3e542d10133b04eeed3bfe99fe3978e1 https://doi.org/10.1007/978-3-662-44917-2_65 Zobrazit plný text záznamu