(3.227.235.183) 您好!臺灣時間:2021/04/13 22:44
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:王健宇
研究生(外文):Chien-Yu Wang
論文名稱:針對可重組式多核心架構之異質任務彈性疊加任務配置
論文名稱(外文):Elastic Superposition Mapping for Heterogeneous Tasks in Reconfigurable Multicore Architecture
指導教授:熊博安熊博安引用關係
指導教授(外文):Pao-Ann Hsiung
口試委員:李宗演嚴茂旭陳鵬升
口試委員(外文):Trong-Yen LeeMao-Hsu YenPeng-Sheng Chen
口試日期:2014-06-26
學位類別:碩士
校院名稱:國立中正大學
系所名稱:資訊工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2014
畢業學年度:102
語文別:英文
論文頁數:54
中文關鍵詞:任務配置異質多核心晶片網路可重組式系統
外文關鍵詞:MappingNetwork-on-ChipHeterogeneousReconfigurable
相關次數:
  • 被引用被引用:0
  • 點閱點閱:198
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:5
  • 收藏至我的研究室書目清單書目收藏:0
隨著製程技術的進步,越來越多的應用整合在同一個晶片上。晶片上處理單元可藉由平行運算來加速計算效能;然而,傳統處理單元之間溝通的架構:匯流排將會是一個溝通瓶頸,已不再能夠負荷大量資料傳輸需求。為了支援更有效率的平行溝通,晶片網路被提出當作一個新的處理單元之間溝通的架構。然而,晶片網路也產生新的挑戰:任務配置對於掛載著異質處理單元的可重組式晶片網路是個很重要的議題。

基於區域的任務配置會產生應用程式內部碎裂而基於非區域的任務配置會產生外部碎裂,為了解決這些在目前主流任務配置演算法的問題,在這個研究中,我們提出一個新穎的任務配置演算法,目標是提高每個處理單元可附載任務的數量。透過預留適當數量的處理單元,並在之後利用這些事前預留的處理單元,提供可重組式異質晶片網路擁有充足的配置彈性,使得不同應用程式更容易分享處理單元,並且使應用程式更容易進入到異質晶片網路執行,用以提高每個處理單元可附載任務的數量。

實驗顯示,跟目前主流的任務配置演算法進行比較,在掛載著異質處理單元的晶片網路上可執行的應用程式數量可提高7%到49%;每個處理單元可附載的任務數量可提高5.5%到56%;以及應用程式等待進入晶片網路的時間可降低11%到54%。
With technology improvement, more and more applications are being integrated into a single chip, which requires a large number of processing elements (PE) in a system such that computation can be effectively enhanced through parallel processing. However, the PEs are often inter-connected by a conventional bus that becomes a communication bottleneck. To support more efficient parallel processing, the Network-on-Chip (NoC) is increasing being adopted as a new alternative interconnection architecture. Nevertheless, NoC has presented new challenges, including mapping tasks to the PEs in reconfigurable heterogeneous CPU/GPU multicore architecture, which has become an increasingly important issue.

Region-based allocation of PE results in internal fragmentation, and non-region based allocation results in external fragmentation. To address this issue and to overcome the problems in state-of-the-art task mapping methods, we propose a novel Elastic Superposition Mapping (ESM) that introduces a useful PE reservation heuristic along with dynamic cross-application superposition. ESM can provide a great elasticity for NoC to map more applications. Thus, the task load on PE will increase.

Experiments show that compared with state-of-the-art region-based mapping, 7% to 49% more applications can be executed; the average task load on PE can be increased by 5.5% to 56%; and the application waiting time can be reduced by 11% to 54%.
1 Introduction 1
1.1 Background 2
1.2 Motivation 3
1.3 Thesis Organization 6
2 Related Work 8
2.1 Static Mapping Algorithms 9
2.2 Dynamic Mapping Algorithms 11
2.3 Summary 12
3 Preliminaries 13
3.1 System Models 13
3.1.1 Target NoC Architecture 13
3.1.2 Application 17
3.2 Estimation Model for Task Load on PE 18
3.3 Problem Formulation 19
3.3.1 Task and Application Mapping on NoC 19
3.3.2 Maximizing Average Task Load on PE Problem 19
3.4 Assumptions 20
4 Elastic Superposition Mapping 21
4.1 Elastic Mapping 26
4.2 Superposition 31
5 Experiments 36
5.1 Simulation Framework 36
5.2 Simulation Platform 38
5.3 Comparative Mapping Algorithms 38
5.4 Test Cases 39
5.5 Experiments 41
5.5.1 Average Task Load on PE 41
5.5.2 Application Waiting Time 42
5.5.3 Finished Applications 43
5.5.4 Traffic Congestion 44
5.5.5 Throughput 45
6 Conclusions and Future Work 48
[1] L. Benini and G. De Micheli. Networks on Chips: A new SoC paradigm. Computer, 35(1):70–78, August 2002.
[2] E. Lindholm, J. Nickolls, S. Oberman, and J. Montrym. nVidia Tesla: A unified graphics and computing architecture. IEEE Micro, 28(2):39–55, March 2008.
[3] S. Buljore, H. Harada, S. Filin, P. Houze, K. Tsagkaris, O. Holland, K. Nolte, T. Farnham, and V. Ivanov. Architecture and enablers for optimized radio resource usage in heterogeneous wireless access networks. IEEE Communications, 47(1):122–129, February 2009.
[4] N. E. Jerger and L.-S. Peh. On-chip networks. Synthesis Lectures on Computer Architecture, 4(1):1–141, June 2009.
[5] R. Marculescu, U. Y Ogras, L.-S. Peh, N. E. Jerger, and Y. Hoskote. Outstanding research problems in NoC design: system, microarchitecture, and circuit perspectives. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 28(1):3–21, January 2009.
[6] J. Shao, C. Tian-zhou, and L. Liu. Incremental run-time application mapping for heterogeneous network on chip. In Proceedings of the International Conference on High Performance Computing and Communication, pages 485–492. IEEE, June 2012.
[7] M. Fattah, M. Ramirez, M. Daneshtalab, P. Liljeberg, and J. Plosila. CoNA: Dynamic application mapping for congestion reduction in many-core systems. In Proceedings of the International Conference on Computer Design (ICCD), pages 364–370. IEEE, September 2012.
[8] M. Fattah, M. Daneshtalab, P. Liljeberg, and J. Plosila. Smart hill climbing for agile dynamic mapping in many-core systems. In Proceedings of the 50th Annual Design Automation Conference, page 39. ACM, May 2013.
[9] R. P Dick, D. L Rhodes, and W. Wolf. TGFF: task graphs for free. In Proceedings of the 6th International Workshop on Hardware/software Codesign, pages 97–101. IEEE Computer Society, March 1998.
[10] C.-L. Chou and R. Marculescu. Incremental run-time application mapping for homogeneous NoCs with multiple voltage levels. In Proceedings of the International Conference on Hardware/Software Codesign and System Synthesis (CODES+ ISSS), pages 161–166. IEEE, October 2007.
[11] E. Carvalho, N. Calazans, and F. Moraes. Heuristics for dynamic task mapping in NoC-based heterogeneous MPSoCs. In Proceedings of the International Workshop on Rapid System Prototyping, pages 34–40. IEEE, May 2007.
[12] E. Carvalho and F. Moraes. Congestion-aware task mapping in heterogeneous MPSoCs. In Proceedings of the International Symposium on System-on-Chip, pages 1–4. IEEE, November 2008.
[13] C.-L. Chou, U. Y Ogras, and R. Marculescu. Energy-and performance-aware incremental mapping for networks on chip with multiple voltage levels. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 27(10):1866–1879, October 2008.
[14] A. Raina and V. Muthukumar. Traffic aware scheduling algorithm for network on chip. In Proceedings of the Sixth International Conference on Information Technology: New Generations, pages 877–882. IEEE, April 2009.
[15] F. Moein-Darbari, A. Khademzade, and G. Gharooni-Fard. Cgmap: a new approach to network-on-chip mapping problem. IEICE Electronics Express, 6(1):27–34, January 2009.
[16] E. L. de Souza Carvalho, N. L. V. Calazans, and F. G. Moraes. Dynamic task mapping for MPSoCs. Design & Test of Computers, 27(5):26–35, October 2010.
[17] G. Sun, Y. Li, Y. Zhang, L. Su, D. Jin, and L. Zeng. Energy-aware runtime mapping for homogeneous NoC. In Proceedings of the International Symposium on System on Chip (SoC), pages 8–11. IEEE, September 2010.
[18] A. K. Singh, T. Srikanthan, A. Kumar, and W. Jigang. Communicationaware heuristics for run-time task mapping on NoC-based MPSoC platforms. Journal of Systems Architecture, 56(7):242–255, July 2010.
[19] F. Triviño, J. L Sánchez, F. J Alfaro, and J. Flich. Virtualizing network-on-chip resources in chip-multiprocessors. Microprocessors and Microsystems, 35(2):230–245, October 2011.
[20] E. Khajekarimi and M. R. Hashemi. Communication and congestion aware run-time task mapping on heterogeneous MPSoCs. In CSI International Symposium on Computer Architecture and Digital Systems (CADS), pages 127–132. IEEE, May 2012.
[21] C. J Glass and L. M Ni. The turn model for adaptive routing. In ACM SIGARCH Computer Architecture News, volume 20, pages 278–287. ACM, May 1992.
[22] C. Marcon, N. Calazans, F. Moraes, A. Susin, I. Reis, and F. Hessel. Exploring NoC mapping strategies: an energy and timing aware technique. In Proceedings of the conference on Design, Automation and Test in Europe, pages 502–507. IEEE Computer Society, March 2005.
[23] C. Marcon, A. Borin, A. Susin, L. Carro, and F. Wagner. Time and energy efficient mapping of embedded applications onto NoCs. In Asia and South Pacific Design Automation Conference, volume 1, pages 33–38. IEEE, January 2005.
[24] C.-K. Luk, S. Hong, and H. Kim. Qilin: exploiting parallelism on heterogeneous multiprocessors with adaptive mapping. In IEEE/ACM International Symposium on Microarchitecture, pages 45–55. IEEE, December 2009.
[25] The Noxim website, 2013. http://noxim.sourceforge.net/.
[26] A. K Singh, W. Jigang, A. Prakash, and T. Srikanthan. Mapping algorithms for NoC-based heterogeneous MPSoC platforms. In Euromicro Conference on Digital System Design, Architectures, Methods and Tools, pages 133–140. IEEE, August 2009.
[27] Embedded system synthesis benchmark suite, 2009. http:// ziyang.eecs.umich.edu/ dickrp/e3s/.
[28] J. Howard, S. Dighe, Y. Hoskote, S. Vangal, D. Finan, G. Ruhl, D. Jenkins, H. Wilson, N. Borkar, and G. Schrom. A 48-core IA-32 message-passing processor with DVFS in 45nm CMOS. In Solid-State Circuits Conference Digest of Technical Papers (ISSCC), pages 108–109. IEEE, December 2010.
[29] S. R Vangal, J. Howard, G. Ruhl, S. Dighe, H. Wilson, J. Tschanz, D. Finan, A. Singh, T. Jacob, and S. Jain. An 80-tile sub-100-W teraflops processor in 65-nm CMOS. IEEE Journal of Solid-State Circuits, 43(1):29–41, January 2008.
[30] R. M Henderson and K. B Clark. Architectural innovation: the reconfiguration of existing product technologies and the failure of established firms. Administrative science quarterly, pages 9–30, March 1990.
[31] S.-S. Lu, C.-H. Lu, and P.-A. Hsiung. Congestion-and energy-aware run-time mapping for tile-based network-on-chip architecture. Proceedings of the IET International Conference on Frontier Computing – Theory, Technologies and Applications, pages 300–305, August 2010.
[32] H.-L. Chao, Y.-R. Chen, S.-Y. Tung, P.-A. Hsiung, and S.-J. Chen. Congestion-aware scheduling for NoC-based reconfigurable systems. In Proceedings of the Conference on Design, Automation and Test in Europe, pages 1561–1566. EDA Consortium, March 2012.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊
 
系統版面圖檔 系統版面圖檔