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
A Teoria da Carga Divisível (DLT) é uma estrutura estabelecida para estudar o Programação de Carga Divisível (DLS). DLT tradicional ignora o fase de coleta de resultadose não especifica nenhuma solução para o caso geral em que a velocidade da rede e a capacidade de computação dos nós são heterogêneas. Neste artigo, o DLS com Coleção Rosult em Sistemas HETerogêmeos (DLSRCHETS) o problema é formulado como um programa linear e analisado. Os artigos até o momento que trataram da coleta de resultados propuseram LIFO (Último a entrar, primeiro a sair) e FIFO (Primeiro a entrar, primeiro a sair) de cronogramas como soluções. As principais contribuições deste artigo são: (a) Uma prova da Condição de precedência de alocação, o que é irrelevante LIFO or FIFO, mas é importante em uma programação geral. (b) Uma prova da Teorema do tempo ocioso, que afirma que independentemente de a carga ser alocada para todos os processadores disponíveis, na solução ótima para o DLSRCHETS problema, no máximo um processador com carga alocada possui tempo ocioso, e que o tempo ocioso existe apenas quando a coleta de resultados começa imediatamente após a conclusão da distribuição da carga.
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
Abhay GHATPANDE, Hidenori NAKAZATO, Olivier BEAUMONT, Hiroshi WATANABE, "Analysis of Divisible Load Scheduling with Result Collection on Heterogeneous Systems" in IEICE TRANSACTIONS on Communications,
vol. E91-B, no. 7, pp. 2234-2243, July 2008, doi: 10.1093/ietcom/e91-b.7.2234.
Abstract: Divisible Load Theory (DLT) is an established framework to study Divisible Load Scheduling (DLS). Traditional DLT ignores the result collection phase, and specifies no solution to the general case where both the network speed and computing capacity of the nodes are heterogeneous. In this paper, the DLS with Rosult Collection on HETerogemeous Systems (DLSRCHETS) problem is formulated as a linear program and analyzed. The papers to date that have dealt with result collection, proposed simplistic LIFO (Last In, First Out) and FIFO (First In, First Out) type of schedules as solutions. The main contributions of this paper are: (a) A proof of the Allocation Precedence Condition, which is inconsequential in LIFO or FIFO, but is important in a general schedule. (b) A proof of the Idle Time Theorem, which states that irrespective of whether load is allocated to all available processors, in the optimal solution to the DLSRCHETS problem, at the most one processor that is allocated load has idle time, and that the idle time exists only when the result collection begins immediately after the completion of load distribution.
URL: https://global.ieice.org/en_transactions/communications/10.1093/ietcom/e91-b.7.2234/_p
Copiar
@ARTICLE{e91-b_7_2234,
author={Abhay GHATPANDE, Hidenori NAKAZATO, Olivier BEAUMONT, Hiroshi WATANABE, },
journal={IEICE TRANSACTIONS on Communications},
title={Analysis of Divisible Load Scheduling with Result Collection on Heterogeneous Systems},
year={2008},
volume={E91-B},
number={7},
pages={2234-2243},
abstract={Divisible Load Theory (DLT) is an established framework to study Divisible Load Scheduling (DLS). Traditional DLT ignores the result collection phase, and specifies no solution to the general case where both the network speed and computing capacity of the nodes are heterogeneous. In this paper, the DLS with Rosult Collection on HETerogemeous Systems (DLSRCHETS) problem is formulated as a linear program and analyzed. The papers to date that have dealt with result collection, proposed simplistic LIFO (Last In, First Out) and FIFO (First In, First Out) type of schedules as solutions. The main contributions of this paper are: (a) A proof of the Allocation Precedence Condition, which is inconsequential in LIFO or FIFO, but is important in a general schedule. (b) A proof of the Idle Time Theorem, which states that irrespective of whether load is allocated to all available processors, in the optimal solution to the DLSRCHETS problem, at the most one processor that is allocated load has idle time, and that the idle time exists only when the result collection begins immediately after the completion of load distribution.},
keywords={},
doi={10.1093/ietcom/e91-b.7.2234},
ISSN={1745-1345},
month={July},}
Copiar
TY - JOUR
TI - Analysis of Divisible Load Scheduling with Result Collection on Heterogeneous Systems
T2 - IEICE TRANSACTIONS on Communications
SP - 2234
EP - 2243
AU - Abhay GHATPANDE
AU - Hidenori NAKAZATO
AU - Olivier BEAUMONT
AU - Hiroshi WATANABE
PY - 2008
DO - 10.1093/ietcom/e91-b.7.2234
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E91-B
IS - 7
JA - IEICE TRANSACTIONS on Communications
Y1 - July 2008
AB - Divisible Load Theory (DLT) is an established framework to study Divisible Load Scheduling (DLS). Traditional DLT ignores the result collection phase, and specifies no solution to the general case where both the network speed and computing capacity of the nodes are heterogeneous. In this paper, the DLS with Rosult Collection on HETerogemeous Systems (DLSRCHETS) problem is formulated as a linear program and analyzed. The papers to date that have dealt with result collection, proposed simplistic LIFO (Last In, First Out) and FIFO (First In, First Out) type of schedules as solutions. The main contributions of this paper are: (a) A proof of the Allocation Precedence Condition, which is inconsequential in LIFO or FIFO, but is important in a general schedule. (b) A proof of the Idle Time Theorem, which states that irrespective of whether load is allocated to all available processors, in the optimal solution to the DLSRCHETS problem, at the most one processor that is allocated load has idle time, and that the idle time exists only when the result collection begins immediately after the completion of load distribution.
ER -