The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Com a demanda por computação de alto desempenho e eficiência energética, a arquitetura multicore tornou-se mais atraente do que nunca. O agendamento de tarefas multicore é um dos domínios da computação paralela que explora o paralelismo do multicore. Ao contrário do agendamento tradicional, o agendamento de tarefas multicore foi recentemente estudado com base no pressuposto de que as tarefas têm paralelismo inerente e podem ser divididas em múltiplas subtarefas de forma paralela de dados. No entanto, ainda é um desafio determinar adequadamente o grau de paralelismo de tarefas e mapeamento em multicores. Nossas técnicas de escalonamento propostas determinam o grau de paralelismo das tarefas, e as subtarefas decidem quais tipos de núcleos serão atribuídos a multicores heterogêneos. Além disso, são propostas duas abordagens para codesign de hardware/software para sistemas multicore heterogêneos. Os trabalhos otimizam os tipos de núcleos organizados na arquitetura simultaneamente com o escalonamento das tarefas de forma que o consumo geral de energia seja minimizado sob uma restrição de prazo, uma abordagem de partida a quente também é apresentada para resolver efetivamente o problema. Os resultados experimentais mostram que a técnica de programação simultânea e otimização do tipo núcleo reduz notavelmente o consumo de energia.
Hiroki NISHIKAWA
Ritsumeikan University,JSPS Research Fellows
Kana SHIMADA
Ritsumeikan University
Ittetsu TANIGUCHI
Osaka University
Hiroyuki TOMIYAMA
Ritsumeikan University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Hiroki NISHIKAWA, Kana SHIMADA, Ittetsu TANIGUCHI, Hiroyuki TOMIYAMA, "Simultaneous Scheduling and Core-Type Optimization for Moldable Fork-Join Tasks on Heterogeneous Multicores" in IEICE TRANSACTIONS on Fundamentals,
vol. E105-A, no. 3, pp. 540-548, March 2022, doi: 10.1587/transfun.2021VLP0003.
Abstract: With the demand for energy-efficient and high- performance computing, multicore architecture has become more appealing than ever. Multicore task scheduling is one of domains in parallel computing which exploits the parallelism of multicore. Unlike traditional scheduling, multicore task scheduling has recently been studied on the assumption that tasks have inherent parallelism and can be split into multiple sub-tasks in data parallel fashion. However, it is still challenging to properly determine the degree of parallelism of tasks and mapping on multicores. Our proposed scheduling techniques determine the degree of parallelism of tasks, and sub-tasks are decided which type of cores to be assigned to heterogeneous multicores. In addition, two approaches to hardware/software codesign for heterogeneous multicore systems are proposed. The works optimize the types of cores organized in the architecture simultaneously with scheduling of the tasks such that the overall energy consumption is minimized under a deadline constraint, a warm start approach is also presented to effectively solve the problem. The experimental results show the simultaneous scheduling and core-type optimization technique remarkably reduces the energy consumption.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2021VLP0003/_p
Copiar
@ARTICLE{e105-a_3_540,
author={Hiroki NISHIKAWA, Kana SHIMADA, Ittetsu TANIGUCHI, Hiroyuki TOMIYAMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Simultaneous Scheduling and Core-Type Optimization for Moldable Fork-Join Tasks on Heterogeneous Multicores},
year={2022},
volume={E105-A},
number={3},
pages={540-548},
abstract={With the demand for energy-efficient and high- performance computing, multicore architecture has become more appealing than ever. Multicore task scheduling is one of domains in parallel computing which exploits the parallelism of multicore. Unlike traditional scheduling, multicore task scheduling has recently been studied on the assumption that tasks have inherent parallelism and can be split into multiple sub-tasks in data parallel fashion. However, it is still challenging to properly determine the degree of parallelism of tasks and mapping on multicores. Our proposed scheduling techniques determine the degree of parallelism of tasks, and sub-tasks are decided which type of cores to be assigned to heterogeneous multicores. In addition, two approaches to hardware/software codesign for heterogeneous multicore systems are proposed. The works optimize the types of cores organized in the architecture simultaneously with scheduling of the tasks such that the overall energy consumption is minimized under a deadline constraint, a warm start approach is also presented to effectively solve the problem. The experimental results show the simultaneous scheduling and core-type optimization technique remarkably reduces the energy consumption.},
keywords={},
doi={10.1587/transfun.2021VLP0003},
ISSN={1745-1337},
month={March},}
Copiar
TY - JOUR
TI - Simultaneous Scheduling and Core-Type Optimization for Moldable Fork-Join Tasks on Heterogeneous Multicores
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 540
EP - 548
AU - Hiroki NISHIKAWA
AU - Kana SHIMADA
AU - Ittetsu TANIGUCHI
AU - Hiroyuki TOMIYAMA
PY - 2022
DO - 10.1587/transfun.2021VLP0003
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E105-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 2022
AB - With the demand for energy-efficient and high- performance computing, multicore architecture has become more appealing than ever. Multicore task scheduling is one of domains in parallel computing which exploits the parallelism of multicore. Unlike traditional scheduling, multicore task scheduling has recently been studied on the assumption that tasks have inherent parallelism and can be split into multiple sub-tasks in data parallel fashion. However, it is still challenging to properly determine the degree of parallelism of tasks and mapping on multicores. Our proposed scheduling techniques determine the degree of parallelism of tasks, and sub-tasks are decided which type of cores to be assigned to heterogeneous multicores. In addition, two approaches to hardware/software codesign for heterogeneous multicore systems are proposed. The works optimize the types of cores organized in the architecture simultaneously with scheduling of the tasks such that the overall energy consumption is minimized under a deadline constraint, a warm start approach is also presented to effectively solve the problem. The experimental results show the simultaneous scheduling and core-type optimization technique remarkably reduces the energy consumption.
ER -