請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/76430
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 盧奕璋(Yi-Chang Lu) | |
dc.contributor.author | Chi-Yun Yang | en |
dc.contributor.author | 楊其昀 | zh_TW |
dc.date.accessioned | 2021-07-09T15:52:14Z | - |
dc.date.available | 2023-03-06 | |
dc.date.copyright | 2018-03-06 | |
dc.date.issued | 2018 | |
dc.date.submitted | 2018-02-27 | |
dc.identifier.citation | [1] Marc Levoy and Pat Hanrahan. Light field rendering. In Proceedings of the 23rd annual conference on Computer graphics and interactive techniques, pages 31–42. ACM, 1996.
[2] Kristin J Dana, Bram Van Ginneken, Shree K Nayar, and Jan J Koenderink. Reflectance and texture of real-world surfaces. ACM Transactions on Graphics (TOG), 18(1):1–34, 1999. [3] Hongcheng Wang, Qing Wu, Lin Shi, Yizhou Yu, and Narendra Ahuja. Out-of-core tensor approximation of multi-dimensional matrices of visual data. ACM Transactions on Graphics (TOG), 24(3):527–535, 2005. [4] M Alex O Vasilescu and Demetri Terzopoulos. Tensortextures: Multilinear image-based rendering. In ACM Transactions on Graphics (TOG), volume 23, pages 336–342. ACM, 2004. [5] Lieven De Lathauwer, Bart De Moor, and Joos Vandewalle. On the best rank-1 and rank-(r 1, r 2,..., rn) approximation of higher-order tensors. SIAM journal on Matrix Analysis and Applications, 21(4):1324–1342, 2000. [6] Yu-Ting Tsai and Zen-Chung Shih. All-frequency precomputed radiance transfer using spherical radial basis functions and clustered tensor approximation. ACM Transactions on Graphics (TOG), 25:967–976, 2006. [7] Yu-Ting Tsai and Zen-Chung Shih. K-clustered tensor approximation: A sparse multilinear model for real-time rendering. ACM Transactions on Graphics (TOG), 31(3):19, 2012. [8] Melissa L Koudelka, Sebastian Magda, Peter N Belhumeur, and David J Kriegman. Acquisition, compression, and synthesis of bidirectional texture functions. In 3rd International Workshop on Texture Analysis and Synthesis (Texture 2003), pages 59–64, 2003. [9] Cobblestones3. https://free3d.com/3d-model/cobblestones-3-86328.html. [10] Xinying Wang and Joseph Zambreno. An fpga implementation of the hestenes-jacobi algorithm for singular value decomposition. In Parallel & Distributed Processing Symposium Workshops (IPDPSW), 2014 IEEE International, pages 220–227. IEEE, 2014. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/76430 | - |
dc.description.abstract | 在電腦視覺與電腦圖學的領域中,常常需要對多維的視覺資料進行分析與處理。隨著使用的的資料量越來越大,用精簡的方式儲存與表示資料也變成一個重要的研究議題。不同於傳統上維度縮減常使用的主成分分析,張量近似可以將資料在維持其原本多維結構的情況下進行維度縮減,更好地利用多維結構中的資料相關性,分別對各個維度進行維度縮減,也提供了在壓縮時的彈性。在需要進行快速影像生成的應用中,資料在經過張量近似壓縮後,重建時的運算量使其無法達到實時生成的需求,因此適用於快速影像生成的張量近似演算法也陸續被提出。
在本篇論文中,我們針對適用於快速影像生成的張量近似演算法進行討論,並且提出了一個硬體加速架構來對其中的分群張量近似演算法進行加速。因為龐大資料量與運算量,張量近似的運算過程相當耗時,利用硬體中平行運算的技巧,可以加快其運算速度。我們使用10 塊靜態隨機存取記憶體,組成高頻寬的記憶體陣列作為內部儲存區域,在資料輸入時得以取出需要的資料進行平行運算。另外也實作了適用於大尺寸長方形矩陣的Hestenes-Jacobi 奇異值分解演算法。我們的硬體架構可以對128x128x128x128x的四維張量進行分群張量近似演算法,使用TSMC 40nmx製程,運行於476 MHzx的時脈頻率,運算速度為軟體實作結果的9.41x倍。完成的晶片面積為3.151 mm²,消耗功率為744.8xmW。 | zh_TW |
dc.description.abstract | In the field of computer vision and computer graphics, processing and analyzing of multidimensional visual data are widely used. As the size of data to be processed increases, how to represent and store data in a compact way becomes an important issue. Unlike traditional dimensionality reduction algorithm, like principal component analysis (PCA), tensor approximation is used to analyzes data while the multidimensional structure is retained, which allows the exploitation of spatial redundancy. Dimensionality reduction along each mode also makes the process more flexible. However, for application which requires rapid image rendering, the computational cost of data reconstruction after applying tensor approximation is very high. As a result, several modified tensor approximation algorithms support fast reconstruction have been proposed.
Because of the enormous size of data and computational cost, tensor approximation suffers from long computation time.In this thesis, we propose a hardware accelerator for one of the modified algorithm, clustered tensor approximation (CTA). With parallel processing techniques in hardware implementation, speed-up can be achieved. We utilize 10 SRAMs to compose a memory array with high bandwidth so that all corresponding data of inputs can be fetched and manipulated simultaneously. We also implement a singular value decomposition (SVD) processor based on Hestenes-Jacobi algorithm which is suitable for decomposition of large rectangular matrices. The architecture we propose can apply clustered tensor approximation to a tensor with a dimension of 128x128x128x128. Using TSMC 40nm technology, the hardware can operate at 476 MHz. The approximation process can be computed 9.41 times faster than the software version. The chip area is 3.151 mm² and the power consumption is 744.8 mW. | en |
dc.description.provenance | Made available in DSpace on 2021-07-09T15:52:14Z (GMT). No. of bitstreams: 1 ntu-107-R03943126-1.pdf: 6538981 bytes, checksum: 1777bc0240290c43ba091501f9d650e2 (MD5) Previous issue date: 2018 | en |
dc.description.tableofcontents | 誌謝 i
摘要 iii Abstract v 1 緒論 1 1.1 多維視覺資料之應用. . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 主成分分析. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.3 論文架構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 2 以張量近似法表示多維視覺資料 3 2.1 張量簡介. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 2.1.1 張量的基本概念. . . . . . . . . . . . . . . . . . . . . . . . . . 3 2.1.2 張量近似. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.2 張量近似應用於多維視覺資料. . . . . . . . . . . . . . . . . . . . . . 6 2.3 交替最小平方法(Alternating Least Squares algorithm) . . . . . . . . . . 8 2.4 適合快速影像生成之張量近似演算法. . . . . . . . . . . . . . . . . . 9 2.4.1 分群張量近似(Clustered Tensor Approximation) . . . . . . . . 10 2.4.2 K 分群張量近似(K-Clustered Tensor Approximation) . . . . . . 11 2.5 實驗結果. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 2.5.1 利用光線追蹤軟體生成測試資料. . . . . . . . . . . . . . . . 15 2.5.2 合成資料組近似結果. . . . . . . . . . . . . . . . . . . . . . . 16 2.5.3 公開資料組近似結果. . . . . . . . . . . . . . . . . . . . . . . 18 3 分群張量近似之硬體架構設計 23 3.1 奇異值分解之硬體實作演算法. . . . . . . . . . . . . . . . . . . . . . 23 3.2 整體架構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 3.3 各電路模組. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 3.3.1 控制器模組. . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 3.3.2 位址計算器模組. . . . . . . . . . . . . . . . . . . . . . . . . . 31 3.3.3 靜態隨機記憶體陣列與緩衝區. . . . . . . . . . . . . . . . . . 33 3.3.4 浮點數運算單元陣列. . . . . . . . . . . . . . . . . . . . . . . 33 3.3.5 張量與矩陣乘法器模組. . . . . . . . . . . . . . . . . . . . . . 34 3.3.6 共變異數矩陣計算模組. . . . . . . . . . . . . . . . . . . . . . 37 3.3.7 Jacobi 旋轉處理器模組. . . . . . . . . . . . . . . . . . . . . . 42 3.4 硬體實驗結果. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48 4 結論與展望 51 4.1 結論. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 4.2 展望. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 參考文獻 53 | |
dc.language.iso | zh-TW | |
dc.title | 利用張量近似法表示多維視覺資料之硬體架構與實現 | zh_TW |
dc.title | Hardware Architecture and Implementation of Tensor Approximation for Multi-Dimensional Visual Data | en |
dc.type | Thesis | |
dc.date.schoolyear | 106-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 江介宏(Jie-Hong Jiang),劉宗德(Tsung-Te Liu),林彥宇(Yen-Yu Lin) | |
dc.subject.keyword | 張量近似,資料壓縮,多維資料,硬體設計, | zh_TW |
dc.subject.keyword | tensor approximation,data compression,multidimensional data,hardware architecture, | en |
dc.relation.page | 54 | |
dc.identifier.doi | 10.6342/NTU201800667 | |
dc.rights.note | 同意授權(全球公開) | |
dc.date.accepted | 2018-02-27 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電子工程學研究所 | zh_TW |
dc.date.embargo-lift | 2023-03-06 | - |
顯示於系所單位: | 電子工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-107-R03943126-1.pdf | 6.39 MB | Adobe PDF | 檢視/開啟 |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。