Predicting MPEG execution times

Andy C. Bavier; A. Brady Montz; Larry L. Peterson

doi:10.1145/277858.277892

Predicting MPEG execution times

Andy C. Bavier, A. Brady Montz, Larry L. Peterson

Research output: Contribution to journal › Article › peer-review

71 Scopus citations

Abstract

This paper reports on a set of experiments that measure the amount of CPU processing needed to decode MPEG-compressed video in software. These experiments were designed to discover indicators that could be used to predict how many cycles are required to decode a given frame. Such predictors can be used to do more accurate CPU scheduling. We found that by considering both frame type and size, it is possible to construct a linear model of MPEG decoding with R² values of 0.97 and higher. Moreover, this model can be used to predict decoding times at both the frame and packet level that are almost always accurate to within 25% of the actual decode times. This is a surprising result given the large variability in MPEG decoding times, and suggests that it is feasible to design systems that make quality of service guarantees for MPEG-encoded video.

Original language	English (US)
Pages (from-to)	131-140
Number of pages	10
Journal	Performance Evaluation Review
Volume	26
Issue number	1
DOIs	https://doi.org/10.1145/277858.277892
State	Published - Jun 1998
Externally published	Yes

ASJC Scopus subject areas

Software
Hardware and Architecture
Computer Networks and Communications

Access to Document

10.1145/277858.277892

Cite this

@article{99629e49776943318611c1bc0c454b0c,

title = "Predicting MPEG execution times",

abstract = "This paper reports on a set of experiments that measure the amount of CPU processing needed to decode MPEG-compressed video in software. These experiments were designed to discover indicators that could be used to predict how many cycles are required to decode a given frame. Such predictors can be used to do more accurate CPU scheduling. We found that by considering both frame type and size, it is possible to construct a linear model of MPEG decoding with R2 values of 0.97 and higher. Moreover, this model can be used to predict decoding times at both the frame and packet level that are almost always accurate to within 25% of the actual decode times. This is a surprising result given the large variability in MPEG decoding times, and suggests that it is feasible to design systems that make quality of service guarantees for MPEG-encoded video.",

author = "Bavier, {Andy C.} and Montz, {A. Brady} and Peterson, {Larry L.}",

year = "1998",

month = jun,

doi = "10.1145/277858.277892",

language = "English (US)",

volume = "26",

pages = "131--140",

journal = "Performance Evaluation Review",

issn = "0163-5999",

publisher = "Association for Computing Machinery (ACM)",

number = "1",

}

TY - JOUR

T1 - Predicting MPEG execution times

AU - Bavier, Andy C.

AU - Montz, A. Brady

AU - Peterson, Larry L.

PY - 1998/6

Y1 - 1998/6

N2 - This paper reports on a set of experiments that measure the amount of CPU processing needed to decode MPEG-compressed video in software. These experiments were designed to discover indicators that could be used to predict how many cycles are required to decode a given frame. Such predictors can be used to do more accurate CPU scheduling. We found that by considering both frame type and size, it is possible to construct a linear model of MPEG decoding with R2 values of 0.97 and higher. Moreover, this model can be used to predict decoding times at both the frame and packet level that are almost always accurate to within 25% of the actual decode times. This is a surprising result given the large variability in MPEG decoding times, and suggests that it is feasible to design systems that make quality of service guarantees for MPEG-encoded video.

AB - This paper reports on a set of experiments that measure the amount of CPU processing needed to decode MPEG-compressed video in software. These experiments were designed to discover indicators that could be used to predict how many cycles are required to decode a given frame. Such predictors can be used to do more accurate CPU scheduling. We found that by considering both frame type and size, it is possible to construct a linear model of MPEG decoding with R2 values of 0.97 and higher. Moreover, this model can be used to predict decoding times at both the frame and packet level that are almost always accurate to within 25% of the actual decode times. This is a surprising result given the large variability in MPEG decoding times, and suggests that it is feasible to design systems that make quality of service guarantees for MPEG-encoded video.

UR - http://www.scopus.com/inward/record.url?scp=0032090154&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032090154&partnerID=8YFLogxK

U2 - 10.1145/277858.277892

DO - 10.1145/277858.277892

M3 - Article

AN - SCOPUS:0032090154

SN - 0163-5999

VL - 26

SP - 131

EP - 140

JO - Performance Evaluation Review

JF - Performance Evaluation Review

IS - 1

ER -

Predicting MPEG execution times

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this