Performance predictors for graphics processing units applied to dark-silicon-aware design space exploration

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Standard

Performance predictors for graphics processing units applied to dark-silicon-aware design space exploration. / Sonohata, Rhayssa; Arigoni, Danillo Christi A.; Fernandes, Eraldo Rezende et al.
in: Concurrency and Computation: Practice and Experience, Jahrgang 35, Nr. 17, e6877, 01.08.2023.

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Harvard

APA

Vancouver

Sonohata R, Arigoni DCA, Fernandes ER, Ribeiro dos Santos R, Dessandre Duenha L. Performance predictors for graphics processing units applied to dark-silicon-aware design space exploration. Concurrency and Computation: Practice and Experience. 2023 Aug 1;35(17):e6877. Epub 2022 Mär 4. doi: 10.1002/cpe.6877

Bibtex

@article{d26e304306bd4cd2b493275aecbed0fa,
title = "Performance predictors for graphics processing units applied to dark-silicon-aware design space exploration",
abstract = "The limitations on the scalability of computer systems imposed by the dark-silicon effects are so severe that they support the extensive use of heterogeneity such as the GP-GPU for general purpose processing. Performance simulators of GP-GPU heterogeneous systems aim to provide performance accuracy at the cost of execution time. In this work, we handle time-consuming simulations of design space exploration systems based on GPUs. We have developed performance predictors based on machine learning (ML) algorithms and evaluated them in accuracy and throughput (number of predictions per second). We measure model accuracy through the mean absolute percentage error (MAPE) and the model efficiency through a throughput metric (millions of predictions per second). Our experiments revealed that decision trees predictors are the most promising regarding accuracy and efficiency. We applied the best predictors into the MultiExplorer, a dark silicon-aware design space exploration tool that allows designers to explore the architecture and microarchitecture of multicore/manycore system design.",
keywords = "dark-silicon, design space exploration, GPUs, heterogeneous computing, performance predictors, Business informatics",
author = "Rhayssa Sonohata and Arigoni, {Danillo Christi A.} and Fernandes, {Eraldo Rezende} and {Ribeiro dos Santos}, Ricardo and {Dessandre Duenha}, Liana",
note = "Special Issue: WSCAD 2020. PDCAT 2020/PDCAT‐PAAP 2020 This study was financed in part by FUNDECT and Coordena{\c c}{\~a}o de Aperfei{\c c}oamento de Pessoal de N{\'i}vel Superior ‐ Brasil (CAPES) ‐ Finance Code 001. ",
year = "2023",
month = aug,
day = "1",
doi = "10.1002/cpe.6877",
language = "English",
volume = "35",
journal = "Concurrency and Computation: Practice and Experience",
issn = "1532-0626",
publisher = "John Wiley & Sons Ltd.",
number = "17",

}

RIS

TY - JOUR

T1 - Performance predictors for graphics processing units applied to dark-silicon-aware design space exploration

AU - Sonohata, Rhayssa

AU - Arigoni, Danillo Christi A.

AU - Fernandes, Eraldo Rezende

AU - Ribeiro dos Santos, Ricardo

AU - Dessandre Duenha, Liana

N1 - Special Issue: WSCAD 2020. PDCAT 2020/PDCAT‐PAAP 2020 This study was financed in part by FUNDECT and Coordenação de Aperfeiçoamento de Pessoal de Nível Superior ‐ Brasil (CAPES) ‐ Finance Code 001.

PY - 2023/8/1

Y1 - 2023/8/1

N2 - The limitations on the scalability of computer systems imposed by the dark-silicon effects are so severe that they support the extensive use of heterogeneity such as the GP-GPU for general purpose processing. Performance simulators of GP-GPU heterogeneous systems aim to provide performance accuracy at the cost of execution time. In this work, we handle time-consuming simulations of design space exploration systems based on GPUs. We have developed performance predictors based on machine learning (ML) algorithms and evaluated them in accuracy and throughput (number of predictions per second). We measure model accuracy through the mean absolute percentage error (MAPE) and the model efficiency through a throughput metric (millions of predictions per second). Our experiments revealed that decision trees predictors are the most promising regarding accuracy and efficiency. We applied the best predictors into the MultiExplorer, a dark silicon-aware design space exploration tool that allows designers to explore the architecture and microarchitecture of multicore/manycore system design.

AB - The limitations on the scalability of computer systems imposed by the dark-silicon effects are so severe that they support the extensive use of heterogeneity such as the GP-GPU for general purpose processing. Performance simulators of GP-GPU heterogeneous systems aim to provide performance accuracy at the cost of execution time. In this work, we handle time-consuming simulations of design space exploration systems based on GPUs. We have developed performance predictors based on machine learning (ML) algorithms and evaluated them in accuracy and throughput (number of predictions per second). We measure model accuracy through the mean absolute percentage error (MAPE) and the model efficiency through a throughput metric (millions of predictions per second). Our experiments revealed that decision trees predictors are the most promising regarding accuracy and efficiency. We applied the best predictors into the MultiExplorer, a dark silicon-aware design space exploration tool that allows designers to explore the architecture and microarchitecture of multicore/manycore system design.

KW - dark-silicon

KW - design space exploration

KW - GPUs

KW - heterogeneous computing

KW - performance predictors

KW - Business informatics

UR - http://www.scopus.com/inward/record.url?scp=85125564653&partnerID=8YFLogxK

U2 - 10.1002/cpe.6877

DO - 10.1002/cpe.6877

M3 - Journal articles

AN - SCOPUS:85125564653

VL - 35

JO - Concurrency and Computation: Practice and Experience

JF - Concurrency and Computation: Practice and Experience

SN - 1532-0626

IS - 17

M1 - e6877

ER -

DOI

Zuletzt angesehen

Publikationen

  1. Do abundance distributions and species aggregation correctly predict macroecological biodiversity patterns in tropical forests?
  2. Comparing marginal effects between different models and/or samples
  3. Using measures of reading time regularity (RTR) to quantify eye movement dynamics, and how they are shaped by linguistic information
  4. Crop rotation modelling
  5. Sliding Mode Control for a Vertical Dynamics in the Presence of Nonlinear Friction
  6. Buckling Analysis under Uncertainty
  7. Performance Saga: Interview 01
  8. Modeling of temperature- and strain-driven intermetallic compound evolution in an Al-Mg system via a multiphase-field approach with application to refill friction stir spot welding
  9. Developing a Process for the Analysis of User Journeys and the Prediction of Dropout in Digital Health Interventions:
  10. Learning shortest paths in word graphs
  11. A Two-Stage Sliding-Mode High-Gain Observer to Reduce Uncertainties and Disturbances Effects for Sensorless Control in Automotive Applications
  12. archiDART: an R package for the automated computation of plant root architectural traits
  13. Second-Order Sliding Mode Control with State and Disturbance Estimation for a Permanent Magnet Linear Motor
  14. Deciding between the Covariance Analytical Approach and the Change-Score Approach in Two Wave Panel Data
  15. Encoding the law of State responsibility with courage and resolve
  16. Investigating the Promotional Effect of Green Signals in Sponsored Search Advertising Using Bayesian Parameter Estimation
  17. The effect of structural complexity on large mammal occurrence in revegetation
  18. Telecoupling as a framework to support a more nuanced understanding of causality in land system science
  19. Single-Word Recognition Need Not Depend on Single-Word Features
  20. Playing in the Spaces: Anarchism in the Classroom
  21. Evaluating A Teaching-Learning Sequence (TLS) About Acid-Base Reactions In Upper Secondary School
  22. Anatomy of Chua's System - Nonlinear Dynamic Electronics for Chaos in the Lab
  23. Ontology-based automatic classification for Web pages
  24. Development of Early Spatial Perspective-Taking - Toward a Three-Level Model
  25. A highly transparent method of assessing the contribution of incentives to meet various technical challenges in distributed energy systems
  26. Understanding the error-structure of Time-driven Activity-based Costing
  27. Phase Shift APOD and POD Control Technique in Multi-Level Inverters to Mitigate Total Harmonic Distortion

Presse / Medien

  1. Computersimulation