ACM Transactions on Architecture and Code Optimization, Volume (15), No (4), Year (2019-1) , Pages (68-97)

Title : ( Metric Selection for GPU Kernel Classification )

Authors: SeyedKazem Shekofteh , Hamid Noori , Mahmoud Naghibzadeh , Hadi Sadoghi Yazdi , HOLGER FRONING ,

Access to full-text not allowed by authors

Citation: BibTeX | EndNote


Graphics Processing Units -GPUs- are vastly used for running massively parallel programs. GPU kernels exhibit different behavior at runtime and can usually be classified in a simple form as either “compute-bound” or “memory-bound.” Recent GPUs are capable of concurrently running multiple kernels, which raises the question of how to most appropriately schedule kernels to achieve higher performance. In particular, coscheduling of compute-bound and memory-bound kernels seems promising. However, its benefits as well as drawbacks must be determined along with which kernels should be selected for a concurrent execution. Classifying kernels can be performed online by instrumentation based on performance counters. This work conducts a thorough analysis of the metrics collected from various benchmarks fromRodinia and CUDA SDK. The goal is to find the minimum number of effective metrics that enables online classification of kernels with a low overhead. This study employs a wrapper-based feature selection method based on the Fisher feature selection criterion. The results of experiments show that to classify kernels with a high accuracy, only three and five metrics are sufficient on a Kepler and a Pascal GPU, respectively. The proposed method is then utilized for a runtime scheduler. The results show an average speedup of 1.18× and 1.1× compared with a serial and a random scheduler, respectively.


, Classification, concurrency, feature selection, kernel metrics, resource utilization
برای دانلود از شناسه و رمز عبور پرتال پویا استفاده کنید.

author = {Shekofteh, SeyedKazem and Noori, Hamid and Naghibzadeh, Mahmoud and Sadoghi Yazdi, Hadi and هولگر فرونینگ},
title = {Metric Selection for GPU Kernel Classification},
journal = {ACM Transactions on Architecture and Code Optimization},
year = {2019},
volume = {15},
number = {4},
month = {January},
issn = {1544-3566},
pages = {68--97},
numpages = {29},
keywords = {Classification; concurrency; feature selection; kernel metrics; resource utilization},


%0 Journal Article
%T Metric Selection for GPU Kernel Classification
%A Shekofteh, SeyedKazem
%A Noori, Hamid
%A Naghibzadeh, Mahmoud
%A Sadoghi Yazdi, Hadi
%A هولگر فرونینگ
%J ACM Transactions on Architecture and Code Optimization
%@ 1544-3566
%D 2019