2013 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) 2013
DOI: 10.1109/ispass.2013.6557141
|View full text |Cite
|
Sign up to set email alerts
|

Sampled simulation of multi-threaded applications

Abstract: Abstract-Sampling is a well-known workload reduction technique that allows one to speed up architectural simulation while accurately predicting performance. Previous sampling methods have been shown to accurately predict single-threaded application runtime based on its overall IPC. However, these previous approaches are unsuitable for general multi-threaded applications, for which IPC is not a good proxy for runtime. Additionally, we find that issues such as application periodicity and inter-thread synchroniza… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
71
0

Year Published

2013
2013
2024
2024

Publication Types

Select...
5
4

Relationship

2
7

Authors

Journals

citations
Cited by 51 publications
(71 citation statements)
references
References 26 publications
0
71
0
Order By: Relevance
“…However, the traditional phase classification is based on the clustering using the Basic Block Vector (BBV). Recent studies show that BBV does not behave well in the presence of frequent L2 misses [3,7]. What differentiates our work from the previous contributions is that we perform phase classification analysis for HW/SW co-designed architectures, where the effects of the dynamically execution and the staged compilation cause different application behavior.…”
Section: Related Workmentioning
confidence: 91%
See 1 more Smart Citation
“…However, the traditional phase classification is based on the clustering using the Basic Block Vector (BBV). Recent studies show that BBV does not behave well in the presence of frequent L2 misses [3,7]. What differentiates our work from the previous contributions is that we perform phase classification analysis for HW/SW co-designed architectures, where the effects of the dynamically execution and the staged compilation cause different application behavior.…”
Section: Related Workmentioning
confidence: 91%
“…However, for the cases with a significant number of nondeterministic long latency events (like for example L2 misses) CP I bb varies widely across executions [3,7]. Consequently, BBV phase classification in this case will give inaccurate results.…”
Section: Bbv Phase Classificationmentioning
confidence: 99%
“…In addition, application synchronization timing effects must be taken into account during fast forwarding phases between sampling periods. Otherwise, the accuracy of execution time estimates provided by sampling decreases [17].…”
Section: B Lossy Simulation Techniquesmentioning
confidence: 99%
“…Several solutions have been proposed to address this issue, including workload sampling [Sherwood et al 2002;Wunderlich et al 2003;Ardestani and Renau 2013;Carlson et al 2013Carlson et al , 2014, and simulation acceleration through software optimization [Sanchez and Kozyrakis 2013] and FPGA hardware [Krasnov et al 2007;Chiou et al 2007;Chung et al 2008;Pellauer et al 2011]. …”
Section: Introductionmentioning
confidence: 99%