Detailed Information on Publication Record
2015
OpenCL Kernel Fusion for GPU, Xeon Phi and CPU
FILIPOVIČ, Jiří and Siegfried BENKNERBasic information
Original name
OpenCL Kernel Fusion for GPU, Xeon Phi and CPU
Name in Czech
Fúze OpenCL kernelů pro GPU, Xeon Phi a CPU
Authors
FILIPOVIČ, Jiří (203 Czech Republic, guarantor, belonging to the institution) and Siegfried BENKNER (40 Austria)
Edition
Florianópolis, Proceedings of IEEE International Symposium on Computer Architecture and High Performance Computing, p. 98-105, 8 pp. 2015
Publisher
IEEE
Other information
Language
English
Type of outcome
Stať ve sborníku
Field of Study
10201 Computer sciences, information science, bioinformatics
Country of publisher
Brazil
Confidentiality degree
není předmětem státního či obchodního tajemství
Publication form
storage medium (CD, DVD, flash disk)
RIV identification code
RIV/00216224:14330/15:00083464
Organization unit
Faculty of Informatics
ISSN
UT WoS
000380430500013
Keywords (in Czech)
OpenCL; fúze kernelů; GPU; Xeon Phi; MIC; CPU
Keywords in English
OpenCL; kernel fusion; GPU; Xeon Phi; MIC; CPU
Tags
International impact, Reviewed
Změněno: 27/8/2019 11:57, RNDr. Pavel Šmerk, Ph.D.
Abstract
V originále
Kernel fusion is an optimization method, in which the code from several kernels is composed to create a new, fused kernel. It can push the performance of kernels beyond limits given for their isolated, unfused form. In this paper, we introduce a classification of different types of kernel fusion for both data dependent and data independent kernels. We study kernel fusion on three types of OpenCL devices: GPU, Xeon Phi and CPU. Those hardware platforms have quite different properties, thus, kernel fusion often affects performance in quite different ways. We analyze the impact of kernel fusion on those hardware platforms and show how it can be used to improve performance. Based on our study we also introduce a basic transformation method for generating fused kernels, which has good potential to be automatized.
Links
| EE2.3.30.0037, research and development project |
|