3D图形渲染的能耗估计

doi:10.3969/j.issn.1001-2400.2017.04.008

西安电子科技大学学报

3D图形渲染的能耗估计

邢立冬1,2;李涛2;黄虎才2;韩俊刚2

(1. 西安电子科技大学微电子学院，陕西西安 710071；
2. 西安邮电大学电子工程学院，陕西西安 710121)

收稿日期:2016-08-12 出版日期:2017-08-20 发布日期:2017-09-29
基金资助:
国家自然科学基金重点资助项目(61136002)

Energy consumption estimation for 3D graphics rendering

XING Lidong1,2;LI Tao2;HUANG Hucai2;HAN Jungang2

(1. School of Microelectronics, Xidian Univ., Xi'an 710071, China;
2. School of Electronic Engineering, Xi'an Univ. of Posts and Telecommunications, Xi'an 710121, China)

Received:2016-08-12 Online:2017-08-20 Published:2017-09-29
About author:邢立冬(1980-)，男，西安电子科技大学博士研究生，E-mail：zmy_xld@163.com

摘要/Abstract

摘要：

针对硬件设计和图形编程，提出了一种新的三维图形渲染计算阶段的能耗估计模型．针对三维渲染管线中顶点着色器和像素着色器的能耗问题，对影响渲染质量的顶点着色和像素着色的负载进行了分析，得出了像素数与顶点数的比值模型; 同时，对顶点着色阶段和像素着色阶段的能耗进行了建模．用所建立的模型对基准测试程序进行了能耗估计，使用Synopsys VCS(Verilog Compiled Simulator)仿真器和Power Compiler来执行仿真，得到不同测试程序的实际能耗．验证结果表明，该模型预测误差的几何平均值小于3％，达到了较高的估计精度，可用于指导图形硬件和软件的功耗分析和管理．

关键词: 三维图形渲染, 能耗估计模型, 着色器, 预测误差

Abstract:

From the perspective of hardware design and graphics programming, a new energy consumption estimation model of 3D graphics rendering is proposed. Aiming at the energy consumption of the vertex shader and pixel shader in the 3D rendering pipeline, the loads of the vertex shader and the pixel shader which affect the rendering quality are analyzed, and the model of the ratio the number of pixels to the number of vertexes is obtained. At the same time, the energy consumption of vertex shading stages and pixel shading stages are modeled. The model is used to estimate the energy consumption of the benchmark programs, and simulations are performed using the Synopsys VCS simulator and the Power Compiler to obtain the actual energy consumption of these programs. The results show that the geometric mean of the model's prediction error is less than 3％, which can be used to guide the power consumption analysis and management of graphics hardware and software.

Key words: 3D graphics rendering, energy consumption estimation model, shader, prediction error

邢立冬;李涛;黄虎才;韩俊刚. 3D图形渲染的能耗估计[J]. 西安电子科技大学学报, 2017, 44(4): 40-46+74.

XING Lidong;LI Tao;HUANG Hucai;HAN Jungang. Energy consumption estimation for 3D graphics rendering[J]. Journal of Xidian University, 2017, 44(4): 40-46+74.

参考文献

［1］ COLLANGE S, DEFOUR D, TISSERAND A. Power Consumption of GPUs from a Software Perspective［C］//Lecture Notes in Computer Science: 5544. Heidelberg: Springer Verlag, 2009: 914-923.
［2］ SHAIKH M Z, GREGOIRE M, LI W, et al. In Situ Power Analysis of General Purpose Graphical Processing Units［C］//Proceedings of the 19th International Euromicro Conference on Parallel, Distributed and Network. Piscataway: IEEE, 2011: 40-44.
［3］ JOHNSSON B, AKENINE-MLLER T. Measuring Per-frame Energy Consumption of Real-time Graphics Applications［J］. Journal of Computer Graphics Techniques, 2014, 3(1): 60-73.
［4］王海峰, 曹云鹏. GPU集群能耗优化控制模型研究［J］. 电子学报, 2015, 43(10): 1904-1910.
WANG Haifeng, CAO Yunpeng. Power Consumption Optimization Control Model of GPU Clusters［J］. Acta Electronica Sinica, 2015, 43(10): 1904-1910.
［5］ RAKVIC R, BROUSSARD R, NGO H. Energy Efficient Iris Recognition with Graphics Processing Units［J］. IEEE Access, 2016, 4: 2831-2839.
［6］ WU G, GREATHOUSE J L, LYASHEVSKY A, et al. GPGPU Performance and Power Estimation Using Machine Learning［C］//Proceedings of the 2015 IEEE 21st International Symposium on High Performance Computer Architecture. Piscataway: IEEE, 2015: 564-576.
［7］ NAGASAKA H, MARUYAMA N, NUKADA A, et al. Statistical Power Modeling of GPU Kernels Using Performance Counters［C］//Proceedings of the 2010 International Conference on Green Computing. Piscataway: IEEE, 2010: 115-122.
［8］ MA X, DONG M, ZHONG L, et al. Statistical Power Consumption Analysis and Modeling for GPU-based Computing［C］//Proceedings of the Workshop on Power Aware Computing and Systems(HotPower'09). Monlana: ACM, 2009: 1-5.
［9］ WANG H F, CHEN Q K. Power Estimating Model and Analysis of General Programming on GPU［J］. Journal of Software, 2012, 7(5): 1164-1170.
［10］ KASICHAYANULA K, TERPSTRA D, LUSZCZEK P, et al. Power Aware Computing on GPUs［C］//Proceedings of the Symposium on Application Accelerators in High-performance Computing. Washington: IEEE Computer Society, 2012: 64-73.
［11］ ADHINARAYANAN V, SUBRAMANIAM B, FENG W C, et al. Online Power Estimation of Graphics Processing Units［C］//Proceedings of the 2016 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing. Piscataway: IEEE, 2016: 245-254.
［12］ NVIDIA CORPORATION. NVIDIA^ Tegra^ X1 NVIDIA'S New Mobile Superchip ［R］. Santa Clara: NVIDIA, 2015.
［13］ AKENINE-MLLER T, HAINES E, HOFFMAN N. Real-time Rendering［M］. Third Edition. Natick: AK Peters/CRC Press, 2008.

3D图形渲染的能耗估计

Energy consumption estimation for 3D graphics rendering

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 10