Novel technique for parallel computations using associative dataflow processor

Tariq Jamil, R. G. Deshmukh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The prevalent concepts of control-flow and data-flow to build computers have their limitations and weaknesses in exploiting parallelism to the utmost limit. Hence, this paper presents a novel technique to handle parallel computations, called associative dataflow. This approach eliminates the major bottleneck in dataflow architectures concerning the matching of tokens and enhancement of their performance. Preliminary results have indicated faster execution speed and higher ALU utilization for the proposed model compared to conventional dataflow model. These results forecast a promising future for associative dataflow model of computations.

Original languageEnglish
Title of host publicationConference Proceedings - IEEE SOUTHEASTCON
Pages322-328
Number of pages7
Publication statusPublished - 1995
EventProceedings of the IEEE Southeastcon '95 Conference - Raleigh, NC, USA
Duration: Mar 26 1995Mar 29 1995

Other

OtherProceedings of the IEEE Southeastcon '95 Conference
CityRaleigh, NC, USA
Period3/26/953/29/95

Fingerprint

Flow control

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Jamil, T., & Deshmukh, R. G. (1995). Novel technique for parallel computations using associative dataflow processor. In Conference Proceedings - IEEE SOUTHEASTCON (pp. 322-328)

Novel technique for parallel computations using associative dataflow processor. / Jamil, Tariq; Deshmukh, R. G.

Conference Proceedings - IEEE SOUTHEASTCON. 1995. p. 322-328.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Jamil, T & Deshmukh, RG 1995, Novel technique for parallel computations using associative dataflow processor. in Conference Proceedings - IEEE SOUTHEASTCON. pp. 322-328, Proceedings of the IEEE Southeastcon '95 Conference, Raleigh, NC, USA, 3/26/95.
Jamil T, Deshmukh RG. Novel technique for parallel computations using associative dataflow processor. In Conference Proceedings - IEEE SOUTHEASTCON. 1995. p. 322-328
Jamil, Tariq ; Deshmukh, R. G. / Novel technique for parallel computations using associative dataflow processor. Conference Proceedings - IEEE SOUTHEASTCON. 1995. pp. 322-328
@inproceedings{4b05b387fea54c32ba04935953e49df0,
title = "Novel technique for parallel computations using associative dataflow processor",
abstract = "The prevalent concepts of control-flow and data-flow to build computers have their limitations and weaknesses in exploiting parallelism to the utmost limit. Hence, this paper presents a novel technique to handle parallel computations, called associative dataflow. This approach eliminates the major bottleneck in dataflow architectures concerning the matching of tokens and enhancement of their performance. Preliminary results have indicated faster execution speed and higher ALU utilization for the proposed model compared to conventional dataflow model. These results forecast a promising future for associative dataflow model of computations.",
author = "Tariq Jamil and Deshmukh, {R. G.}",
year = "1995",
language = "English",
pages = "322--328",
booktitle = "Conference Proceedings - IEEE SOUTHEASTCON",

}

TY - GEN

T1 - Novel technique for parallel computations using associative dataflow processor

AU - Jamil, Tariq

AU - Deshmukh, R. G.

PY - 1995

Y1 - 1995

N2 - The prevalent concepts of control-flow and data-flow to build computers have their limitations and weaknesses in exploiting parallelism to the utmost limit. Hence, this paper presents a novel technique to handle parallel computations, called associative dataflow. This approach eliminates the major bottleneck in dataflow architectures concerning the matching of tokens and enhancement of their performance. Preliminary results have indicated faster execution speed and higher ALU utilization for the proposed model compared to conventional dataflow model. These results forecast a promising future for associative dataflow model of computations.

AB - The prevalent concepts of control-flow and data-flow to build computers have their limitations and weaknesses in exploiting parallelism to the utmost limit. Hence, this paper presents a novel technique to handle parallel computations, called associative dataflow. This approach eliminates the major bottleneck in dataflow architectures concerning the matching of tokens and enhancement of their performance. Preliminary results have indicated faster execution speed and higher ALU utilization for the proposed model compared to conventional dataflow model. These results forecast a promising future for associative dataflow model of computations.

UR - http://www.scopus.com/inward/record.url?scp=0029239409&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029239409&partnerID=8YFLogxK

M3 - Conference contribution

SP - 322

EP - 328

BT - Conference Proceedings - IEEE SOUTHEASTCON

ER -