The Manchester Dataflow Machine (MDFM) works with tasks of size equal to one single instruction. This fine granularity aims at exploring all parallelism at the instruction level. However, this project decision increases the instruction communication cost, which ends up to jam the interconnection network and reduces the system performance. One way to skirt this problem is to adopt variable size tasks instead of working with such small task size. In this paper, in order to study whether or not the usage of such variable size tasks in the MDFM architecture contributes to the improvement of the performance, some simulations by toy programs take place. In the simulation, variable size tasks are realized by packing the sequential instruction stretches into one task. To manage this packing, the Sequential Block (SB) technique is developed. The simulation of those packed and unpacked programs give an outline of advantages and disadvantages of working with variable size tasks, and how the SB technique should be implemented in the system.
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
Paulo LORENZO, Munehiro GOTO, Arthur J. CATTO, "Packing Sequential Stretches in the MDFM" in IEICE TRANSACTIONS on Information,
vol. E78-D, no. 4, pp. 345-354, April 1995, doi: .
Abstract: The Manchester Dataflow Machine (MDFM) works with tasks of size equal to one single instruction. This fine granularity aims at exploring all parallelism at the instruction level. However, this project decision increases the instruction communication cost, which ends up to jam the interconnection network and reduces the system performance. One way to skirt this problem is to adopt variable size tasks instead of working with such small task size. In this paper, in order to study whether or not the usage of such variable size tasks in the MDFM architecture contributes to the improvement of the performance, some simulations by toy programs take place. In the simulation, variable size tasks are realized by packing the sequential instruction stretches into one task. To manage this packing, the Sequential Block (SB) technique is developed. The simulation of those packed and unpacked programs give an outline of advantages and disadvantages of working with variable size tasks, and how the SB technique should be implemented in the system.
URL: https://global.ieice.org/en_transactions/information/10.1587/e78-d_4_345/_p
Copy
@ARTICLE{e78-d_4_345,
author={Paulo LORENZO, Munehiro GOTO, Arthur J. CATTO, },
journal={IEICE TRANSACTIONS on Information},
title={Packing Sequential Stretches in the MDFM},
year={1995},
volume={E78-D},
number={4},
pages={345-354},
abstract={The Manchester Dataflow Machine (MDFM) works with tasks of size equal to one single instruction. This fine granularity aims at exploring all parallelism at the instruction level. However, this project decision increases the instruction communication cost, which ends up to jam the interconnection network and reduces the system performance. One way to skirt this problem is to adopt variable size tasks instead of working with such small task size. In this paper, in order to study whether or not the usage of such variable size tasks in the MDFM architecture contributes to the improvement of the performance, some simulations by toy programs take place. In the simulation, variable size tasks are realized by packing the sequential instruction stretches into one task. To manage this packing, the Sequential Block (SB) technique is developed. The simulation of those packed and unpacked programs give an outline of advantages and disadvantages of working with variable size tasks, and how the SB technique should be implemented in the system.},
keywords={},
doi={},
ISSN={},
month={April},}
Copy
TY - JOUR
TI - Packing Sequential Stretches in the MDFM
T2 - IEICE TRANSACTIONS on Information
SP - 345
EP - 354
AU - Paulo LORENZO
AU - Munehiro GOTO
AU - Arthur J. CATTO
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E78-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 1995
AB - The Manchester Dataflow Machine (MDFM) works with tasks of size equal to one single instruction. This fine granularity aims at exploring all parallelism at the instruction level. However, this project decision increases the instruction communication cost, which ends up to jam the interconnection network and reduces the system performance. One way to skirt this problem is to adopt variable size tasks instead of working with such small task size. In this paper, in order to study whether or not the usage of such variable size tasks in the MDFM architecture contributes to the improvement of the performance, some simulations by toy programs take place. In the simulation, variable size tasks are realized by packing the sequential instruction stretches into one task. To manage this packing, the Sequential Block (SB) technique is developed. The simulation of those packed and unpacked programs give an outline of advantages and disadvantages of working with variable size tasks, and how the SB technique should be implemented in the system.
ER -