2D (two-dimensional) convolution is a basic operation in image processing and requires intensive computation. Although the SIMD model is considered suitable for 2D convolution, previous 2D convolution algorithms on the SIMD model assume unbounded number of PEs (Processing Elements) available, which we call unbounded case. Unbounded case could not be satisfied on real computers. In this paper, time-optimal data-parallel 2D convolution is studied on mesh-connected SIMD computers with bounded number of PEs. Because the optimal computation complexity is not difficult to achieve, the main concern of this paper is how to achieve optimal communication complexity. Firstly the lower bound computation complexity is analyzed. Then the lower bound communication complexities are analyzed under two typical data-distribution strategies: block-mapping and cyclic-mapping. Based on the analysis result, an optimal algorithm is presented under the block-mapping. The algorithm achieves the lower bound complexity both in computation and in communication.
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
Jian LU, Taiichi YUASA, "Time-Optimal 2D Convolution on Mesh-Connected SIMD Computers with Bounded Number of PEs" in IEICE TRANSACTIONS on Information,
vol. E79-D, no. 8, pp. 1021-1030, August 1996, doi: .
Abstract: 2D (two-dimensional) convolution is a basic operation in image processing and requires intensive computation. Although the SIMD model is considered suitable for 2D convolution, previous 2D convolution algorithms on the SIMD model assume unbounded number of PEs (Processing Elements) available, which we call unbounded case. Unbounded case could not be satisfied on real computers. In this paper, time-optimal data-parallel 2D convolution is studied on mesh-connected SIMD computers with bounded number of PEs. Because the optimal computation complexity is not difficult to achieve, the main concern of this paper is how to achieve optimal communication complexity. Firstly the lower bound computation complexity is analyzed. Then the lower bound communication complexities are analyzed under two typical data-distribution strategies: block-mapping and cyclic-mapping. Based on the analysis result, an optimal algorithm is presented under the block-mapping. The algorithm achieves the lower bound complexity both in computation and in communication.
URL: https://global.ieice.org/en_transactions/information/10.1587/e79-d_8_1021/_p
Copy
@ARTICLE{e79-d_8_1021,
author={Jian LU, Taiichi YUASA, },
journal={IEICE TRANSACTIONS on Information},
title={Time-Optimal 2D Convolution on Mesh-Connected SIMD Computers with Bounded Number of PEs},
year={1996},
volume={E79-D},
number={8},
pages={1021-1030},
abstract={2D (two-dimensional) convolution is a basic operation in image processing and requires intensive computation. Although the SIMD model is considered suitable for 2D convolution, previous 2D convolution algorithms on the SIMD model assume unbounded number of PEs (Processing Elements) available, which we call unbounded case. Unbounded case could not be satisfied on real computers. In this paper, time-optimal data-parallel 2D convolution is studied on mesh-connected SIMD computers with bounded number of PEs. Because the optimal computation complexity is not difficult to achieve, the main concern of this paper is how to achieve optimal communication complexity. Firstly the lower bound computation complexity is analyzed. Then the lower bound communication complexities are analyzed under two typical data-distribution strategies: block-mapping and cyclic-mapping. Based on the analysis result, an optimal algorithm is presented under the block-mapping. The algorithm achieves the lower bound complexity both in computation and in communication.},
keywords={},
doi={},
ISSN={},
month={August},}
Copy
TY - JOUR
TI - Time-Optimal 2D Convolution on Mesh-Connected SIMD Computers with Bounded Number of PEs
T2 - IEICE TRANSACTIONS on Information
SP - 1021
EP - 1030
AU - Jian LU
AU - Taiichi YUASA
PY - 1996
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E79-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 1996
AB - 2D (two-dimensional) convolution is a basic operation in image processing and requires intensive computation. Although the SIMD model is considered suitable for 2D convolution, previous 2D convolution algorithms on the SIMD model assume unbounded number of PEs (Processing Elements) available, which we call unbounded case. Unbounded case could not be satisfied on real computers. In this paper, time-optimal data-parallel 2D convolution is studied on mesh-connected SIMD computers with bounded number of PEs. Because the optimal computation complexity is not difficult to achieve, the main concern of this paper is how to achieve optimal communication complexity. Firstly the lower bound computation complexity is analyzed. Then the lower bound communication complexities are analyzed under two typical data-distribution strategies: block-mapping and cyclic-mapping. Based on the analysis result, an optimal algorithm is presented under the block-mapping. The algorithm achieves the lower bound complexity both in computation and in communication.
ER -