The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Pemproses berbilang teras heterogen tertarik dengan aplikasi pemprosesan media kerana keupayaan mereka melukis kekuatan teras yang berbeza untuk meningkatkan prestasi keseluruhan. Walau bagaimanapun, kesesakan pemindahan data dan pengehadan dalam peruntukan tugas disebabkan oleh operasi tidak serasi pemecut menghalang kami daripada memperoleh potensi penuh pemproses berbilang teras heterogen. Kertas kerja ini membentangkan kaedah pengagihan tugas berdasarkan transformasi algoritma untuk meningkatkan kebebasan pengagihan tugas. Kami menggunakan kaedah penghampiran seperti algoritma CORDIC untuk memetakan operasi tidak serasi pemecut kepada teras pemecut. Mengikut keputusan eksperimen menggunakan pengiraan deskriptor HOG, kaedah peruntukan tugas yang dicadangkan mengurangkan masa pemindahan data sebanyak lebih daripada 82% dan jumlah masa pemprosesan lebih daripada 79% berbanding kaedah peruntukan tugasan konvensional.
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.
Salinan
Hasitha Muthumala WAIDYASOORIYA, Daisuke OKUMURA, Masanori HARIYAMA, Michitaka KAMEYAMA, "Task Allocation with Algorithm Transformation for Reducing Data-Transfer Bottlenecks in Heterogeneous Multi-Core Processors: A Case Study of HOG Descriptor Computation" in IEICE TRANSACTIONS on Fundamentals,
vol. E93-A, no. 12, pp. 2570-2580, December 2010, doi: 10.1587/transfun.E93.A.2570.
Abstract: Heterogeneous multi-core processors are attracted by the media processing applications due to their capability of drawing strengths of different cores to improve the overall performance. However, the data transfer bottlenecks and limitations in the task allocation due to the accelerator-incompatible operations prevents us from gaining full potential of the heterogeneous multi-core processors. This paper presents a task allocation method based on algorithm transformation to increase the freedom of task allocation. We use approximation methods such as CORDIC algorithms to map the accelerator-incompatible operations to accelerator cores. According to the experimental results using HOG descriptor computation, the proposed task allocation method reduces the data transfer time by more than 82% and the total processing time by more than 79% compared to the conventional task allocation method.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E93.A.2570/_p
Salinan
@ARTICLE{e93-a_12_2570,
author={Hasitha Muthumala WAIDYASOORIYA, Daisuke OKUMURA, Masanori HARIYAMA, Michitaka KAMEYAMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Task Allocation with Algorithm Transformation for Reducing Data-Transfer Bottlenecks in Heterogeneous Multi-Core Processors: A Case Study of HOG Descriptor Computation},
year={2010},
volume={E93-A},
number={12},
pages={2570-2580},
abstract={Heterogeneous multi-core processors are attracted by the media processing applications due to their capability of drawing strengths of different cores to improve the overall performance. However, the data transfer bottlenecks and limitations in the task allocation due to the accelerator-incompatible operations prevents us from gaining full potential of the heterogeneous multi-core processors. This paper presents a task allocation method based on algorithm transformation to increase the freedom of task allocation. We use approximation methods such as CORDIC algorithms to map the accelerator-incompatible operations to accelerator cores. According to the experimental results using HOG descriptor computation, the proposed task allocation method reduces the data transfer time by more than 82% and the total processing time by more than 79% compared to the conventional task allocation method.},
keywords={},
doi={10.1587/transfun.E93.A.2570},
ISSN={1745-1337},
month={December},}
Salinan
TY - JOUR
TI - Task Allocation with Algorithm Transformation for Reducing Data-Transfer Bottlenecks in Heterogeneous Multi-Core Processors: A Case Study of HOG Descriptor Computation
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2570
EP - 2580
AU - Hasitha Muthumala WAIDYASOORIYA
AU - Daisuke OKUMURA
AU - Masanori HARIYAMA
AU - Michitaka KAMEYAMA
PY - 2010
DO - 10.1587/transfun.E93.A.2570
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E93-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2010
AB - Heterogeneous multi-core processors are attracted by the media processing applications due to their capability of drawing strengths of different cores to improve the overall performance. However, the data transfer bottlenecks and limitations in the task allocation due to the accelerator-incompatible operations prevents us from gaining full potential of the heterogeneous multi-core processors. This paper presents a task allocation method based on algorithm transformation to increase the freedom of task allocation. We use approximation methods such as CORDIC algorithms to map the accelerator-incompatible operations to accelerator cores. According to the experimental results using HOG descriptor computation, the proposed task allocation method reduces the data transfer time by more than 82% and the total processing time by more than 79% compared to the conventional task allocation method.
ER -