Reducing communication overhead is a key goal of program optimization for current scalable multiprocessors. A well-known approach to achieving this is to map tasks (indivisible units of computation) to processors so that communication and computation overlap as much as possible. In an earlier work, we developed a look-ahead scheduling heuristic for efficiently reducing communication overhead with the aim of decreasing the completion time of a given parallel program. In this paper, we report on an extension of the algorithm, which fills in the idle time slots created by interprocessor communication without increasing the algorithm's time complexity. The results of experiments emphasize the importance of optimally filling idle time slots in processors.
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.
Copy
Dingchao LI, Yuji IWAHORI, Tatsuya HAYASHI, Naohiro ISHII, "Enhanced Look-Ahead Scheduling Technique to Overlap Communication with Computation" in IEICE TRANSACTIONS on Information,
vol. E81-D, no. 11, pp. 1205-1212, November 1998, doi: .
Abstract: Reducing communication overhead is a key goal of program optimization for current scalable multiprocessors. A well-known approach to achieving this is to map tasks (indivisible units of computation) to processors so that communication and computation overlap as much as possible. In an earlier work, we developed a look-ahead scheduling heuristic for efficiently reducing communication overhead with the aim of decreasing the completion time of a given parallel program. In this paper, we report on an extension of the algorithm, which fills in the idle time slots created by interprocessor communication without increasing the algorithm's time complexity. The results of experiments emphasize the importance of optimally filling idle time slots in processors.
URL: https://global.ieice.org/en_transactions/information/10.1587/e81-d_11_1205/_p
Copy
@ARTICLE{e81-d_11_1205,
author={Dingchao LI, Yuji IWAHORI, Tatsuya HAYASHI, Naohiro ISHII, },
journal={IEICE TRANSACTIONS on Information},
title={Enhanced Look-Ahead Scheduling Technique to Overlap Communication with Computation},
year={1998},
volume={E81-D},
number={11},
pages={1205-1212},
abstract={Reducing communication overhead is a key goal of program optimization for current scalable multiprocessors. A well-known approach to achieving this is to map tasks (indivisible units of computation) to processors so that communication and computation overlap as much as possible. In an earlier work, we developed a look-ahead scheduling heuristic for efficiently reducing communication overhead with the aim of decreasing the completion time of a given parallel program. In this paper, we report on an extension of the algorithm, which fills in the idle time slots created by interprocessor communication without increasing the algorithm's time complexity. The results of experiments emphasize the importance of optimally filling idle time slots in processors.},
keywords={},
doi={},
ISSN={},
month={November},}
Copy
TY - JOUR
TI - Enhanced Look-Ahead Scheduling Technique to Overlap Communication with Computation
T2 - IEICE TRANSACTIONS on Information
SP - 1205
EP - 1212
AU - Dingchao LI
AU - Yuji IWAHORI
AU - Tatsuya HAYASHI
AU - Naohiro ISHII
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E81-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 1998
AB - Reducing communication overhead is a key goal of program optimization for current scalable multiprocessors. A well-known approach to achieving this is to map tasks (indivisible units of computation) to processors so that communication and computation overlap as much as possible. In an earlier work, we developed a look-ahead scheduling heuristic for efficiently reducing communication overhead with the aim of decreasing the completion time of a given parallel program. In this paper, we report on an extension of the algorithm, which fills in the idle time slots created by interprocessor communication without increasing the algorithm's time complexity. The results of experiments emphasize the importance of optimally filling idle time slots in processors.
ER -