Exploiting program microarchitecture independent characteristics and phase behavior for reduced benchmark suite simulation

Lieven Eeckhout, John Morgan Sampson, Brad Calder

Research output: Chapter in Book/Report/Conference proceedingConference contribution

44 Citations (Scopus)

Abstract

Modern architecture research relies heavily on detailed pipeline simulation. Simulating the full execution of an industry standard benchmark can take weeks to complete. Simulating the full execution of the whole benchmark suite for one architecture configuration can take months. To address this issue researchers have examined using targetted sampling based on phase behavior to significantly reduce the simulation time of each program in the benchmark suite. However, even with this sampling approach, simulating the full benchmark suite across a large range of architecture designs can take days to weeks to complete. The goal of this paper is to further reduce simulation time for architecture design space exploration. We reduce simulation time by finding similarity between benchmarks and program inputs at the level of samples (100M instructions of execution). This allows us to use a representative sample of execution from one benchmark to accurately represent a sample of execution of other benchmarks and inputs. The end result of our analyis is a small number of sample points of execution. These are selected across the whole benchmark suite in order to accurately represent the complete simulation of the whole benchmark suite for design space exploration. We show that this provides approximately the same accuracy as the SimPoint sampling approach while reducing the number of simulated instructions by a factor of 1.5.

Original languageEnglish (US)
Title of host publicationProceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005
Pages2-12
Number of pages11
DOIs
StatePublished - Dec 1 2005
Event2005 IEEE International Symposium on Workload Characterization, IISWC-2005 - Austin, TX, United States
Duration: Oct 6 2005Oct 8 2005

Publication series

NameProceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005
Volume2005

Other

Other2005 IEEE International Symposium on Workload Characterization, IISWC-2005
CountryUnited States
CityAustin, TX
Period10/6/0510/8/05

Fingerprint

Phase behavior
Sampling
Pipelines
Industry

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Eeckhout, L., Sampson, J. M., & Calder, B. (2005). Exploiting program microarchitecture independent characteristics and phase behavior for reduced benchmark suite simulation. In Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005 (pp. 2-12). [1525996] (Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005; Vol. 2005). https://doi.org/10.1109/IISWC.2005.1525996
Eeckhout, Lieven ; Sampson, John Morgan ; Calder, Brad. / Exploiting program microarchitecture independent characteristics and phase behavior for reduced benchmark suite simulation. Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005. 2005. pp. 2-12 (Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005).
@inproceedings{cd35adbff60242aa96d090d639e44709,
title = "Exploiting program microarchitecture independent characteristics and phase behavior for reduced benchmark suite simulation",
abstract = "Modern architecture research relies heavily on detailed pipeline simulation. Simulating the full execution of an industry standard benchmark can take weeks to complete. Simulating the full execution of the whole benchmark suite for one architecture configuration can take months. To address this issue researchers have examined using targetted sampling based on phase behavior to significantly reduce the simulation time of each program in the benchmark suite. However, even with this sampling approach, simulating the full benchmark suite across a large range of architecture designs can take days to weeks to complete. The goal of this paper is to further reduce simulation time for architecture design space exploration. We reduce simulation time by finding similarity between benchmarks and program inputs at the level of samples (100M instructions of execution). This allows us to use a representative sample of execution from one benchmark to accurately represent a sample of execution of other benchmarks and inputs. The end result of our analyis is a small number of sample points of execution. These are selected across the whole benchmark suite in order to accurately represent the complete simulation of the whole benchmark suite for design space exploration. We show that this provides approximately the same accuracy as the SimPoint sampling approach while reducing the number of simulated instructions by a factor of 1.5.",
author = "Lieven Eeckhout and Sampson, {John Morgan} and Brad Calder",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/IISWC.2005.1525996",
language = "English (US)",
isbn = "0780394615",
series = "Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005",
pages = "2--12",
booktitle = "Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005",

}

Eeckhout, L, Sampson, JM & Calder, B 2005, Exploiting program microarchitecture independent characteristics and phase behavior for reduced benchmark suite simulation. in Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005., 1525996, Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005, vol. 2005, pp. 2-12, 2005 IEEE International Symposium on Workload Characterization, IISWC-2005, Austin, TX, United States, 10/6/05. https://doi.org/10.1109/IISWC.2005.1525996

Exploiting program microarchitecture independent characteristics and phase behavior for reduced benchmark suite simulation. / Eeckhout, Lieven; Sampson, John Morgan; Calder, Brad.

Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005. 2005. p. 2-12 1525996 (Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005; Vol. 2005).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Exploiting program microarchitecture independent characteristics and phase behavior for reduced benchmark suite simulation

AU - Eeckhout, Lieven

AU - Sampson, John Morgan

AU - Calder, Brad

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Modern architecture research relies heavily on detailed pipeline simulation. Simulating the full execution of an industry standard benchmark can take weeks to complete. Simulating the full execution of the whole benchmark suite for one architecture configuration can take months. To address this issue researchers have examined using targetted sampling based on phase behavior to significantly reduce the simulation time of each program in the benchmark suite. However, even with this sampling approach, simulating the full benchmark suite across a large range of architecture designs can take days to weeks to complete. The goal of this paper is to further reduce simulation time for architecture design space exploration. We reduce simulation time by finding similarity between benchmarks and program inputs at the level of samples (100M instructions of execution). This allows us to use a representative sample of execution from one benchmark to accurately represent a sample of execution of other benchmarks and inputs. The end result of our analyis is a small number of sample points of execution. These are selected across the whole benchmark suite in order to accurately represent the complete simulation of the whole benchmark suite for design space exploration. We show that this provides approximately the same accuracy as the SimPoint sampling approach while reducing the number of simulated instructions by a factor of 1.5.

AB - Modern architecture research relies heavily on detailed pipeline simulation. Simulating the full execution of an industry standard benchmark can take weeks to complete. Simulating the full execution of the whole benchmark suite for one architecture configuration can take months. To address this issue researchers have examined using targetted sampling based on phase behavior to significantly reduce the simulation time of each program in the benchmark suite. However, even with this sampling approach, simulating the full benchmark suite across a large range of architecture designs can take days to weeks to complete. The goal of this paper is to further reduce simulation time for architecture design space exploration. We reduce simulation time by finding similarity between benchmarks and program inputs at the level of samples (100M instructions of execution). This allows us to use a representative sample of execution from one benchmark to accurately represent a sample of execution of other benchmarks and inputs. The end result of our analyis is a small number of sample points of execution. These are selected across the whole benchmark suite in order to accurately represent the complete simulation of the whole benchmark suite for design space exploration. We show that this provides approximately the same accuracy as the SimPoint sampling approach while reducing the number of simulated instructions by a factor of 1.5.

UR - http://www.scopus.com/inward/record.url?scp=33749073811&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33749073811&partnerID=8YFLogxK

U2 - 10.1109/IISWC.2005.1525996

DO - 10.1109/IISWC.2005.1525996

M3 - Conference contribution

AN - SCOPUS:33749073811

SN - 0780394615

SN - 9780780394612

T3 - Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005

SP - 2

EP - 12

BT - Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005

ER -

Eeckhout L, Sampson JM, Calder B. Exploiting program microarchitecture independent characteristics and phase behavior for reduced benchmark suite simulation. In Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005. 2005. p. 2-12. 1525996. (Proceedings of the 2005 IEEE International Symposium on Workload Characterization, IISWC-2005). https://doi.org/10.1109/IISWC.2005.1525996