This paper proposes an efficient systolic array construction method for optimal planar systolic design of the matrix multiplication. By connection network adjustment among systolic array processing element (PE), the input/output data are jumping in the systolic array for multiplication operation requirements. Various 2-D systolic array topologies, such as square topology and hexagonal topology, have been studied to construct appropriate systolic array configuration and realize high performance matrix multiplication. Based on traditional Kung-Leiserson systolic architecture, the proposed "Jumping Systolic Array (JSA)" algorithm can increase the matrix multiplication speed with less processing elements and few data registers attachment. New systolic arrays, such as square jumping array, redundant dummy latency jumping hexagonal array, and compact parallel flow jumping hexagonal array, are also proposed to improve the concurrent system operation efficiency. Experimental results prove that the JSA algorithm can realize fully concurrent operation and dominate other systolic architectures in the specific systolic array system characteristics, such as band width, matrix complexity, or expansion capability.
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
Yun YANG, Shinji KIMURA, "The Optimal Architecture Design of Two-Dimension Matrix Multiplication Jumping Systolic Array" in IEICE TRANSACTIONS on Fundamentals,
vol. E91-A, no. 4, pp. 1101-1111, April 2008, doi: 10.1093/ietfec/e91-a.4.1101.
Abstract: This paper proposes an efficient systolic array construction method for optimal planar systolic design of the matrix multiplication. By connection network adjustment among systolic array processing element (PE), the input/output data are jumping in the systolic array for multiplication operation requirements. Various 2-D systolic array topologies, such as square topology and hexagonal topology, have been studied to construct appropriate systolic array configuration and realize high performance matrix multiplication. Based on traditional Kung-Leiserson systolic architecture, the proposed "Jumping Systolic Array (JSA)" algorithm can increase the matrix multiplication speed with less processing elements and few data registers attachment. New systolic arrays, such as square jumping array, redundant dummy latency jumping hexagonal array, and compact parallel flow jumping hexagonal array, are also proposed to improve the concurrent system operation efficiency. Experimental results prove that the JSA algorithm can realize fully concurrent operation and dominate other systolic architectures in the specific systolic array system characteristics, such as band width, matrix complexity, or expansion capability.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e91-a.4.1101/_p
Copy
@ARTICLE{e91-a_4_1101,
author={Yun YANG, Shinji KIMURA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={The Optimal Architecture Design of Two-Dimension Matrix Multiplication Jumping Systolic Array},
year={2008},
volume={E91-A},
number={4},
pages={1101-1111},
abstract={This paper proposes an efficient systolic array construction method for optimal planar systolic design of the matrix multiplication. By connection network adjustment among systolic array processing element (PE), the input/output data are jumping in the systolic array for multiplication operation requirements. Various 2-D systolic array topologies, such as square topology and hexagonal topology, have been studied to construct appropriate systolic array configuration and realize high performance matrix multiplication. Based on traditional Kung-Leiserson systolic architecture, the proposed "Jumping Systolic Array (JSA)" algorithm can increase the matrix multiplication speed with less processing elements and few data registers attachment. New systolic arrays, such as square jumping array, redundant dummy latency jumping hexagonal array, and compact parallel flow jumping hexagonal array, are also proposed to improve the concurrent system operation efficiency. Experimental results prove that the JSA algorithm can realize fully concurrent operation and dominate other systolic architectures in the specific systolic array system characteristics, such as band width, matrix complexity, or expansion capability.},
keywords={},
doi={10.1093/ietfec/e91-a.4.1101},
ISSN={1745-1337},
month={April},}
Copy
TY - JOUR
TI - The Optimal Architecture Design of Two-Dimension Matrix Multiplication Jumping Systolic Array
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1101
EP - 1111
AU - Yun YANG
AU - Shinji KIMURA
PY - 2008
DO - 10.1093/ietfec/e91-a.4.1101
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E91-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 2008
AB - This paper proposes an efficient systolic array construction method for optimal planar systolic design of the matrix multiplication. By connection network adjustment among systolic array processing element (PE), the input/output data are jumping in the systolic array for multiplication operation requirements. Various 2-D systolic array topologies, such as square topology and hexagonal topology, have been studied to construct appropriate systolic array configuration and realize high performance matrix multiplication. Based on traditional Kung-Leiserson systolic architecture, the proposed "Jumping Systolic Array (JSA)" algorithm can increase the matrix multiplication speed with less processing elements and few data registers attachment. New systolic arrays, such as square jumping array, redundant dummy latency jumping hexagonal array, and compact parallel flow jumping hexagonal array, are also proposed to improve the concurrent system operation efficiency. Experimental results prove that the JSA algorithm can realize fully concurrent operation and dominate other systolic architectures in the specific systolic array system characteristics, such as band width, matrix complexity, or expansion capability.
ER -