Paper Info
Title
Impact of Clock Frequency and Number of Cores on GPU Performance
Abstract
Modern graphics processing units (GPUs) containing massive parallel hardware have become more flexible with unified shader cores which can run diverse graphics operations. Moreover, programmers can run general-purpose applications on GPUs easily, since GPU vendors provide user-friendly application programming interfaces (APIs). Many studies for improving system performance using GPUs have been researched intensively. Study on the GPU architecture is challenging, because the GPU architecture is totally different to the traditional CPU architecture. This paper analyzes the GPU performance according to GPU parameters with various number of cores and clock frequency. According to our simulations, the GPU performance improves by 125.8% and 16.2% on average as the number of cores and clock frequency increase, respectively. However, the performance is saturated when memory system cannot service the data requests efficiently, resulting in memory bottleneck. Consequently, memory bottleneck problem should be considered for efficient GPU architecture design.
Year
DOI
Venue
2014
10.1109/ICITCS.2014.7021776
ICITCS
Keywords
Field
DocType
application program interfaces,clocks,graphics processing units,multiprocessing systems,performance evaluation,api,cpu architecture,gpu architecture design,gpu performance,clock frequency,clock frequency impact,general-purpose applications,graphics operations,parallel hardware,unified shader cores,user friendly application programming interfaces
Graphics,Bottleneck,Fixed-function,Computer science,Parallel computing,Unified shader model,Real-time computer graphics,General-purpose computing on graphics processing units,Application programming interface,Clock rate
Conference
ISSN
Citations 
PageRank 
2473-0122
0
0.34
References 
Authors
6
4
Name
Order
Citations
PageRank
Hong Jun Choi1305.74
Dong Oh Son2214.19
Cheol Hong Kim37324.39
Jong Myron Kim400.34