Skip to Main content Skip to Navigation
Conference papers

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

Abstract : 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/hal-01403164
Contributor : Hal Ifip <>
Submitted on : Friday, November 25, 2016 - 2:52:03 PM
Last modification on : Thursday, March 5, 2020 - 5:40:13 PM
Long-term archiving on: : Tuesday, March 21, 2017 - 11:55:04 AM

File

978-3-662-44917-2_65_Chapter.p...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Khondker Hasan, Amlan Chatterjee, Sridhar Radhakrishnan, John Antonio. Performance Prediction Model and Analysis for Compute-Intensive Tasks on GPUs. 11th IFIP International Conference on Network and Parallel Computing (NPC), Sep 2014, Ilan, Taiwan. pp.612-617, ⟨10.1007/978-3-662-44917-2_65⟩. ⟨hal-01403164⟩

Share

Metrics

Record views

284

Files downloads

490