User: Guest  Login
Less Searchfields
Simple search
Title:

A Cache-Aware Performance Prediction Framework for GPGPU Computations

Document type:
Konferenzbeitrag
Contribution type:
Textbeitrag / Aufsatz
Author(s):
Pöppl, Alexander; Herz, Alexander
Pages contribution:
749-760
Abstract:
We present a model for the automated prediction of average execution times for OpenCL-based computations on GPUs. The model encompasses the whole execution of the computation, including the transfer to and from the GPU, and the kernel execution itself. In contrast to existing static prediction frameworks, we incorporate the caches available on modern GPUs into our model. Using our benchmark suite, we show that memory access patterns can be grouped into five patterns that exhibit significantly di...     »
Editor:
Hunold, Sascha; Costan, Alexandru; Gimenez, Domingo; Iosup, Alexandru; Ricci, Laura; Gomez Requena, Maria Engracia; Scarano, Vittorio; Varbanescu, Ana Lucia; Scott, Stephen L.; Lankes, Stefan; Weidendorfer, Josef; Alexander, Michael
Book / Congress title:
Euro-Par 2015: Parallel Processing Workshops
Congress (additional information):
Vienna, Austria
Organization:
TU Wien
Date of congress:
25.08.2015-26.08.2015
Publisher:
Springer International Publishing
Publisher address:
Cham
Date of publication:
18.12.2015
Year:
2015
Quarter:
4. Quartal
Year / month:
2015-12
Month:
Dec
Pages:
749-760
Print-ISBN:
978-3-319-27307-5
Bookseries title:
Lecture Notes in Computer Science
Reviewed:
ja
Language:
en
WWW:
https://doi.org/10.1007/978-3-319-27308-2_60
 BibTeX