Rendimiento y análisis energético en formación de haz con GPGPU-Sim
##plugins.themes.bootstrap3.article.sidebar##
ISSN: 1680-8894
E-ISSN: 2219-6714
Sección
Artículos
Artículos
Esta obra está bajo licencia internacional Creative Commons Reconocimiento-NoComercial-SinObrasDerivadas 4.0.
##plugins.themes.bootstrap3.article.main##
Enviado:
Sep 8, 2016
Publicado: Sep 8, 2016
Publicado: Sep 8, 2016
Resumen
Las unidades de procesamiento gráfico (GPU) se utilizan actualmente en una amplia gama de aplicaciones científicas y comerciales. Estos son de las primeras plataformas de energía eficientes y asequibles para el procesamiento de datos en paralelo. En el campo de las imágenes médicas, las GPU son en algunos casos cruciales para hacer uso práctico de algoritmos computacionalmente exigentes. Por esta razón, en esta investigación se explora el área de consumo y eficiencia energética al utilizar GPU como procesadores de señal e imagen primaria para sistemas médicos portátiles futuros de imágenes de ultrasonido. Como metodología de estudio se utilizó la aplicación GPGPU-Sim, un simulador de nivel de ciclo de cargas de trabajo de computación GPU ejecutando código escrito en CUDA, realizando variadas configuraciones a fin de determinar la arquitectura con óptimo rendimiento para nuestra aplicación de formación de haz (beamforming).
Palabras clave
Formación de haz, CUDA, Rendimiento, Consumo energético, GPPGU-Sim, GPUWatchDescargas
La descarga de datos todavía no está disponible.
##plugins.themes.bootstrap3.article.details##
Cómo citar
Vejarano, R. A., & Lee, J.-G. (2016). Rendimiento y análisis energético en formación de haz con GPGPU-Sim. I+D Tecnológico, 12(1), 5-13. Recuperado a partir de https://revistas.utp.ac.pa/index.php/id-tecnologico/article/view/589
Citas
(1) Michel Bénard: "Energy Efficient HPC in Metropolitan Environments," in International Conference on Energy-Aware High Performance Computing, Hamburg , 2010.
(2) David Defour: Arnaud Tisserand, and Sylvain Collange, "Power Consumption of GPUs from a Software Perspective," in ICCS '09 Proceedings of the 9th International Conference on Computational, Berlin, 2009, pp. 914–923.
(3) Reiji Suda and Da Qi Ren: "Power Efficient Large Matrices Multiplication by Load Scheduling on Multi-core and GPU Platform with CUDA," in IEEE CSE'09, 12th IEEE International Conference on Computational Science and Engineering, Vancouver, 2008, pp. 424-429.
(4) S. Huang, S. Xiao, and W. Feng: "On the Energy Efficiency of Graphics Processing Units," in Parallel & Distributed Processing, 2009. IPDPS 2009. IEEE International Symposium on, Rome, 2009, pp. 1-8.
(5) Sunpyo Hong: "Modeling performance and power for energy- efficient GPGPU computing," Georgia Institute of Technology, Tesis Doctoral 2012.
(6) Y. Jiao, H. Lin, P. Balaji, and W. Feng: "Power and Performance Characterization of Computational Kernels on the GPU," in Green Computing and Communications (GreenCom), 2010 IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social Computing (CPSCom), Hangzhou, 2010, pp. 221 - 228.
(7) Y. Abe; H. Sasaki; S. Kato; K. Inou; M. Edahiro; M. Peres: "Power and Performance Characterization and Modeling of GPU-Accelerated Systems," in HotPower'12 Proceedings of the 2012 USENIX conference on Power-Aware Computing and Systems, Berkeley, 2012, p. 10.
(8) Rong Ge, Ryan Vogt, Jahangir Majumder, and Arif Alam: "Effect of Dynamic Voltage and Frequency Scaling on K20 GPU," in Parallel Processing (ICPP), 2013 42nd International Conference on, Lyon, 2013, pp. 826 - 833.
(9) Leng, J.; Hetherington, T.; Tantawy, A E; Gilani, S; Kim, N.; Aamodt, T..; Reddi, V. (2013) GPUWattch Energy Model Manual. http://www.gpgpu-sim.org/gpuwattch/
(10) Wilson W.L. Fung, Tayler H. Hetherington Tor M. Aamodt. (2012) GPGPU-Sim. http://gpgpu-sim.org/manual/index.php/Main_Page
(11) NVIDIA. High Performance Computing. Vertical Industry Solutions. http://www.nvidia.com/object/medical_imaging.htm
(12) James A. Zagzebski: Essentials of Ultrasound Physics, New Edition ed.: Elsevier Health Sciences, 1996.
(13) Thomas L. Szabo: Diagnostic Ultrasound Imaging: Inside Out, 1st ed. London: Elsevier Academic Press, 2004.
(14) Andrew A. Ganse. An Introduction to Beamforming. http://research.ganse.org/physics/beamforming/
(15) PaweáGepner and Michaá F. Kowalik: "Multi-Core Processors: New Way to Achieve High System Performance," in Parallel Computing in Electrical Engineering, 2006. PAR ELEC 2006. International Symposium on, Bialystok, 2006, pp. 9-13.
(16) Ed Grochowski and Murali Annavaram. (2006, Marzo) Energy per Instruction Trends in Intel Microprocessors. http://www.intel.com/pressroom/kits/core2duo/pdf/epi-trends-final2.pdf
(2) David Defour: Arnaud Tisserand, and Sylvain Collange, "Power Consumption of GPUs from a Software Perspective," in ICCS '09 Proceedings of the 9th International Conference on Computational, Berlin, 2009, pp. 914–923.
(3) Reiji Suda and Da Qi Ren: "Power Efficient Large Matrices Multiplication by Load Scheduling on Multi-core and GPU Platform with CUDA," in IEEE CSE'09, 12th IEEE International Conference on Computational Science and Engineering, Vancouver, 2008, pp. 424-429.
(4) S. Huang, S. Xiao, and W. Feng: "On the Energy Efficiency of Graphics Processing Units," in Parallel & Distributed Processing, 2009. IPDPS 2009. IEEE International Symposium on, Rome, 2009, pp. 1-8.
(5) Sunpyo Hong: "Modeling performance and power for energy- efficient GPGPU computing," Georgia Institute of Technology, Tesis Doctoral 2012.
(6) Y. Jiao, H. Lin, P. Balaji, and W. Feng: "Power and Performance Characterization of Computational Kernels on the GPU," in Green Computing and Communications (GreenCom), 2010 IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social Computing (CPSCom), Hangzhou, 2010, pp. 221 - 228.
(7) Y. Abe; H. Sasaki; S. Kato; K. Inou; M. Edahiro; M. Peres: "Power and Performance Characterization and Modeling of GPU-Accelerated Systems," in HotPower'12 Proceedings of the 2012 USENIX conference on Power-Aware Computing and Systems, Berkeley, 2012, p. 10.
(8) Rong Ge, Ryan Vogt, Jahangir Majumder, and Arif Alam: "Effect of Dynamic Voltage and Frequency Scaling on K20 GPU," in Parallel Processing (ICPP), 2013 42nd International Conference on, Lyon, 2013, pp. 826 - 833.
(9) Leng, J.; Hetherington, T.; Tantawy, A E; Gilani, S; Kim, N.; Aamodt, T..; Reddi, V. (2013) GPUWattch Energy Model Manual. http://www.gpgpu-sim.org/gpuwattch/
(10) Wilson W.L. Fung, Tayler H. Hetherington Tor M. Aamodt. (2012) GPGPU-Sim. http://gpgpu-sim.org/manual/index.php/Main_Page
(11) NVIDIA. High Performance Computing. Vertical Industry Solutions. http://www.nvidia.com/object/medical_imaging.htm
(12) James A. Zagzebski: Essentials of Ultrasound Physics, New Edition ed.: Elsevier Health Sciences, 1996.
(13) Thomas L. Szabo: Diagnostic Ultrasound Imaging: Inside Out, 1st ed. London: Elsevier Academic Press, 2004.
(14) Andrew A. Ganse. An Introduction to Beamforming. http://research.ganse.org/physics/beamforming/
(15) PaweáGepner and Michaá F. Kowalik: "Multi-Core Processors: New Way to Achieve High System Performance," in Parallel Computing in Electrical Engineering, 2006. PAR ELEC 2006. International Symposium on, Bialystok, 2006, pp. 9-13.
(16) Ed Grochowski and Murali Annavaram. (2006, Marzo) Energy per Instruction Trends in Intel Microprocessors. http://www.intel.com/pressroom/kits/core2duo/pdf/epi-trends-final2.pdf