Abstract
This article investigates the use of many-core systems to execute the disparity estimation algorithm, used in stereo vision applications, as these systems can provide flexibility between performance scaling and power consumption. We present a learning-based runtime management approach that achieves a required performance threshold while minimizing power consumption through dynamic control of frequency and core allocation. Experimental results are obtained from a 61-core Intel Xeon Phi platform for the aforementioned investigation. The same performance can be achieved with an average reduction in power consumption of 27.8% and increased energy efficiency by 30.04% when compared to Dynamic Voltage and Frequency Scaling control alone without runtime management.
- K. Ambrosch and W. Kubinger. 2010. Accurate hardware-based stereo vision. Comput. Vis. Image Underst. 114, 11 (Nov. 2010), 1303--1316. Google Scholar
Digital Library
- N. Baha and S. Larabi. 2012. Accurate real-time neural disparity MAP estimation with FPGA. Pattern Recogn. 45, 3 (Mar. 2012), 1195--1204. Google Scholar
Digital Library
- C. Banz, S. Hesselbarth, H. Flatt, H. Blume, and P. Pirsch. 2010. Real-time stereo vision system using semi-global matching disparity estimation: Architecture and FPGA-implementation. In Proceedings of the 2010 International Conference on Embedded Computer Systems (SAMOS’10). 93--101.Google Scholar
- P. Bellasi, G. Massari, and W. Fornaciari. 2015. Effective runtime resource management using linux control groups with the barbequertrm framework. ACM Trans. Embed. Comput. Syst. 14, 2, Article 39 (Mar. 2015), 17 pages. Google Scholar
Digital Library
- M. Bleyer and C. Rhemann. 2011. PatchMatch stereo—Stereo matching with slanted support windows. In British Machine Vision Conference 2011. 1--11. http://publik.tuwien.ac.at/files/PubDat_201949.pdfGoogle Scholar
- A. Burbano, S. Bouaziz, and M. Vasiliu. 2015. 3D-sensing distributed embedded system for people tracking and counting. In Proceedings of the 2015 International Conference on Computational Science and Computational Intelligence (CSCI’15). 470--475. Google Scholar
Digital Library
- R. Cochran, C. Hankendi, A. K. Coskun, and S. Reda. 2011. Pack 8 cap: Adaptive DVFS and thread packing under power caps. In Proceedings of the 44th Annual IEEE/ACM International Symposium on Microarchitecture. 175--185. Google Scholar
Digital Library
- J. Cohen, P. Cohen, S. G. West, and L. S. Aiken. 2013. Applied Multiple Regression/Correlation Analysis for the Behavioral Sciences. Taylor 8 Francis.Google Scholar
- M. Curtis-Maury, A. Shah, F. Blagojevic, D. S. Nikolopoulos, B. R. de Supinski, and M. Schulz. 2008. Prediction models for multi-dimensional power-performance optimization on many cores. In Proceedings of the 17th International Conference on Parallel Architectures and Compilation Techniques. 250--259. Google Scholar
Digital Library
- B. Cyganek and J. P. Siebert. 2009. Introduction to 3D Computer Vision Techniques and Algorithms. Wiley-Blackwell. Google Scholar
Cross Ref
- J. Ding, J. Liu, W. Zhou, H. Yu, Y. Wang, and X. Gong. 2011. Real-time stereo vision system using adaptive weight cost aggregation approach. EURASIP J. Image Vid. Process. 2011, 1 (2011), 1--19. Google Scholar
Cross Ref
- N. R. Draper and H. Smith. 1998. Applied Regression Analysis (3rd ed.). Wiley-Blackwell. Google Scholar
Cross Ref
- M. Etinski, J. Corbalan, J. Labarta, and M. Valero. 2012. Understanding the future of energy-performance trade-off via DVFS in HPC environments. J. Parallel Distrib. Comput. 72, 4 (Apr. 2012), 579--590. Google Scholar
Digital Library
- X. Fu and X. Wang. 2011. Utilization-controlled task consolidation for power optimization in multi-core real-time systems. In Proceedings of the 2011 IEEE 17th International Conference on Embedded and Real-Time Computing Systems and Applications, Vol. 1. 73--82. Google Scholar
Digital Library
- D. Gadioli, S. Libutti, G. Massari, E. Paone, M. Scandale, P. Bellasi, G. Palermo, V. Zaccaria, G. Agosta, W. Fornaciari, and C. Silvano. 2014. OpenCL application auto-tuning and run-time resource management for multi-core platforms. In Proceedings of the 2014 IEEE International Symposium on Parallel and Distributed Processing with Applications. 127--133. Google Scholar
Digital Library
- S. K. Gehrig, F. Eberli, and T. Meyer. 2009. A Real-Time Low-Power Stereo Vision Engine Using Semi-Global Matching. Springer, Berlin, 134--143. Google Scholar
Digital Library
- K. He, J. Sun, and X. Tang. 2013. Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell. 35, 6 (Jun. 2013), 1397--1409. Google Scholar
Digital Library
- H. Hirschmuller. 2008. Stereo processing by semiglobal matching and mutual information. IEEE Trans. Pattern Anal. Mach. Intell. 30, 2 (Feb. 2008), 328--341. Google Scholar
Digital Library
- A. Hosni, M. Bleyer, C. Rhemann, M. Gelautz, and C. Rother. 2011. REal-time local stereo matching using guided image filtering. In Proceedings of the 2011 IEEE International Conference on Multimedia and Expo. 1--6. Google Scholar
Digital Library
- Y. S. Hwang and K. S. Chung. 2013. Dynamic power management technique for multicore based embedded mobile devices. IEEE Trans. Industr. Inform. 9, 3 (Aug. 2013), 1601--1612. Google Scholar
Cross Ref
- Intel. 2015. Intel Xeon Phi Product Family. https://ark.intel.com/products/80555/Intel-Xeon-Phi-Coprocessor-7120A-16GB-1_238-GHz-61-core.Google Scholar
- M. Jin and T. Maruyama. 2012. A real-time stereo vision system using a tree-structured dynamic programming on FPGA. In Proceedings of the ACM/SIGDA International Symposium on Field Programmable Gate Arrays. 21--24. Google Scholar
Digital Library
- M. Jin and T. Maruyama. 2014. Fast and accurate stereo vision system on FPGA. ACM Trans. Reconfigurable Technol. Syst. 7, 1, Article 3 (Feb. 2014), 24 pages. Google Scholar
Digital Library
- S. Karakaya, G. Kkyildiz, C. Toprak, and H. Ocak. 2014. Development of a human tracking indoor mobile robot platform. In Proceedings of the 16th International Conference on Mechatronics (Mechatronika’14). 683--687. Google Scholar
Cross Ref
- G. C. Sirakoulis L. Nalpantidis and A. Gasteratos. 2008. Review of stereo vision algorithms: From software to hardware. Int. J. Optomechatron. 2, 4 (Jan. 2008), 435--462. Google Scholar
Cross Ref
- B. Lewis and D. J. Berg. 1998. Multithreaded Programming with Pthreads. Prentice-Hall. Google Scholar
Digital Library
- G. Mariani, C. Ykman-Couvreur, K. Zhang, L. Zhang, and G. Lafruit. 2010. An efficient run-time management methodology for stereo matching application. In Proceedings of the 23th International Conference on Architecture of Computing Systems 2010. 1--6. http://ieeexplore.ieee.org/document/5759019/.Google Scholar
- X. Mei, X. Sun, M. Zhou, S. Jiao, H. Wang, and Xiaopeng Zhang. 2011. On building an accurate stereo matching system on graphics hardware. In Proceedings of the 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops’11). 467--474. Google Scholar
Cross Ref
- C. C. T. Mendes and D. F. Wolf. 2013. Real time autonomous navigation and obstacle avoidance using a semi-global stereo method. In Proceedings of the 28th Annual ACM Symposium on Applied Computing. 235--236. Google Scholar
Digital Library
- H. Oleynikova, D. Honegger, and M. Pollefeys. 2015. Reactive avoidance using embedded stereo vision for MAV flight. In Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA’15). 50--56. Google Scholar
Cross Ref
- E. Paone, D. Gadioli, G. Palermo, V. Zaccaria, and C. Silvano. 2014. Evaluating orthogonality between application auto-tuning and run-time resource management for adaptive opencl applications. In Proceedings of the 2014 IEEE 25th International Conference on Application-Specific Systems, Architectures and Processors. 161--168. Google Scholar
Cross Ref
- M. G. Park, J. Park, Y. Shin, E. G. Lim, and K. J. Yoon. 2015. Stereo vision with image-guided structured-light pattern matching. Electron. Lett. 51, 3 (2015), 238--239. Google Scholar
Cross Ref
- S. Perri, P. Corsonello, and G. Cocorullo. 2013. Adaptive census transform: A novel hardware-oriented stereovision algorithm. Comput. Vis. Image Underst. 117, 1 (2013), 29--41. Google Scholar
Digital Library
- A. K. Porterfield, S. L. Olivier, S. Bhalachandra, and J. F. Prins. 2013. Power measurement and concurrency throttling for energy reduction in openmp programs. In Proceedings of the 2013 IEEE 27th International Symposium on Parallel and Distributed Processing Workshops and PhD Forum. 884--891. Google Scholar
Digital Library
- D. Scharstein and R. Szeliski. 2002. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vis. 47, 1–3 (2002), 7--42. Google Scholar
Digital Library
- R. A. Shafik, A. Das, S. Yang, G. Merrett, and B. M. Al-Hashimi. 2015. Adaptive energy minimization of openmp parallel applications on many-core systems. In Proceedings of the 6th Workshop on Parallel Programming and Run-Time Management Techniques for Many-Core Architectures. 19--24. Google Scholar
Digital Library
- Y. Shan, Y. Hao, W. Wang, Y. Wang, X. Chen, H. Yang, and W. Luk. 2014. Hardware acceleration for an accurate stereo vision system using mini-census adaptive support region. ACM Trans. Embed. Comput. Syst. 13, 4s, Article 132 (2014), 24 pages. Google Scholar
Digital Library
- S. Solak and E. D. Bolat. 2015. Distance estimation using stereo vision for indoor mobile robot applications. In Proceedings of the 2015 9th International Conference on Electrical and Electronics Engineering (ELECO’15). 685--688. Google Scholar
Cross Ref
- H. Son, K. Bae, S. Ok, Y. Lee, and B. Moon. 2012. A Rectification Hardware Architecture for an Adaptive Multiple-Baseline Stereo Vision System. Springer, Berlin, 147--155.Google Scholar
- J. Stowers, M. Hayes, and A. Bainbridge-Smith. 2011. Altitude control of a quadrotor helicopter using depth map from microsoft kinect sensor. In Proceedings of the 2011 IEEE International Conference on Mechatronics. 358--362. Google Scholar
Cross Ref
- T. Tahara, R. Kawahara, S. Nobuhara, and T. Matsuyama. 2015. Interference-free epipole-centered structured light pattern for mirror-based multi-view active stereo. In Proceedings of the 2015 International Conference on 3D Vision. 153--161. Google Scholar
Digital Library
- C. Ttofis, C. Kyrkou, and T. Theocharides. 2016. A low-cost real-time embedded stereo vision system for accurate disparity estimation based on guided image filtering. IEEE Trans. Comput. 65, 9 (2016), 2678--2693. Google Scholar
Digital Library
- P. Usachokcharoen, Y. Washizawa, and K. Pasupa. 2015. Sign language recognition with microsoft Kinect’s depth and colour sensors. In Proceedings of the 2015 IEEE International Conference on Signal and Image Processing Applications (ICSIPA’15). 186--190.Google Scholar
- W. Wang, J. Yan, N. Xu, Y. Wang, and F. H. Hsu. 2013. Real-time high-quality stereo vision system in FPGA. In Proceedings of the 2013 International Conference on Field-Programmable Technology (FPT’13). 358--361. Google Scholar
Cross Ref
- S. Yang, R. A. Shafik, G. V. Merrett, E. Stott, J. M. Levine, J. Davis, and B. M. Al-Hashimi. 2015. Adaptive energy minimization of embedded heterogeneous systems using regression-based learning. In Proceedings of the 2015 25th International Workshop on Power and Timing Modeling, Optimisation and Simulation (PATMOS’15). 103--110.Google Scholar
- K. Yoon and In S. Kweon. 2006. Adaptive support-weight approach for correspondence search. IEEE Trans. Pattern Anal. Mach. Intell. 28, 4 (2006), 650--656. Google Scholar
Digital Library
- K. Zhang, J. Lu, and G. Lafruit. 2009. Cross-based local stereo matching using orthogonal integral images. IEEE Trans. Circ. Syst. Video Technol. 19, 7 (2009), 1073--1079. Google Scholar
Digital Library
- L. Zhang, K. Zhang, T. S. Chang, G. Lafruit, G. K. Kuzmanov, and D. Verkest. 2011. Real-time high-definition stereo matching on FPGA. In Proceedings of the 19th ACM/SIGDA International Symposium on Field Programmable Gate Arrays. 55--64. Google Scholar
Digital Library
Index Terms
Runtime Performance and Power Optimization of Parallel Disparity Estimation on Many-Core Platforms
Recommendations
GPU Acceleration for Simulating Massively Parallel Many-Core Platforms
Emerging massively parallel architectures such as a general-purpose processor plus many-core programmable accelerators are creating an increasing demand for novel methods to perform their architectural simulation. Most state-of-the-art simulation ...
Distributed reinforcement learning for power limited many-core system performance optimization
DATE '15: Proceedings of the 2015 Design, Automation & Test in Europe Conference & ExhibitionAs power density emerges as the main constraint for many-core systems, controlling power consumption under the Thermal Design Power (TDP) while maximizing the performance becomes increasingly critical. To dynamically save power, Dynamic Voltage ...
Power optimization for multimedia transcoding on multicore servers
ANCS '10: Proceedings of the 6th ACM/IEEE Symposium on Architectures for Networking and Communications SystemsWe design, implement and evaluate a power-efficient and traffic-aware transcoding system on multicore servers that appropriately adjusts the processor operating level. The system is capable of configuring the number of active cores and core frequency "...






Comments