DocumentCode
2037128
Title
Comparative benchmarking: matrix multiplication on a multicore coprocessor and a GPU
Author
Salim, Maryam ; Akkirman, Ali O. ; Hidayetoglu, Mert ; Gurel, Levent
Author_Institution
Electr. & Electron. Eng. Dept., Bilkent Univ., Bilkent, Turkey
fYear
2015
fDate
1-4 July 2015
Firstpage
1
Lastpage
2
Abstract
This paper reports the performances of an Intel Xeon Phi coprocessor and an Nvidia Tesla GPU for multiplication of large matrices. For this purpose, various libraries, such as Intel MKL and MAGMA, are employed with different execution modes of the coprocessor. We compare the performances of the coprocessor and the GPU in terms of running time, memory requirement, and programming difficulty for the special case of matrix-matrix multiplication.
Keywords
coprocessors; graphics processing units; mathematics computing; matrix multiplication; multiprocessing systems; software libraries; GPU; Intel MKL; Intel Xeon Phi coprocessor; MAGMA; Nvidia Tesla GPU; execution modes; matrix-matrix multiplication; memory requirement; multicore coprocessor; programming difficulty; running time; Coprocessors; Graphics processing units; Libraries; Matrices; Memory management; Message systems; Programming;
fLanguage
English
Publisher
ieee
Conference_Titel
Computational Electromagnetics International Workshop (CEM), 2015
Conference_Location
Izmir
Print_ISBN
978-1-4673-9279-2
Type
conf
DOI
10.1109/CEM.2015.7237429
Filename
7237429
Link To Document