An energy model for graphics processing units

We present an energy model for a graphics processing unit (GPU) that is based on the amount and type of work performed in various parts of the unit. By designing and running directed tests on a GPU, we measure the energy consumed when performing different arithmetic and memory operations, allowing us to accurately predict the energy that any arbitrary mix of operations will take. With some knowledge of how data travels through and is transformed by the graphics pipeline, we can predict how many of each operation will occur for a given scene, leading to an estimate of the energy usage. We validate our model against different types of existing graphical applications. With an average difference of 3% from measured energy under typical workloads, our model can be used for various purposes. In this work, we explore and present two use cases: 1) predicting the energy performance of applications on a different architecture, and 2) exploring the energy efficiency of different algorithms to achieve the same graphical effect.

[1]  Hyesoon Kim,et al.  An integrated GPU power and performance model , 2010, ISCA.

[2]  Bruce Jacob,et al.  Accurate and fast system-level power modeling: An XScale-based case study , 2008, TECS.

[3]  Margaret Martonosi,et al.  Wattch: a framework for architectural-level power analysis and optimizations , 2000, Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat. No.RS00201).

[4]  Majid Sarrafzadeh,et al.  Energy-aware high performance computing with graphic processing units , 2008, CLUSTER 2008.

[5]  Li-Shiuan Peh,et al.  High-level power analysis for multi-core chips , 2006, CASES '06.

[6]  K. Ramani,et al.  PowerRed : A Flexible Modeling Framework for Power Efficiency Exploration in GPUs , .

[7]  Li-Shiuan Peh,et al.  High-level power analysis for on-chip networks , 2004, CASES '04.

[8]  Sharad Malik,et al.  Instruction level power analysis and optimization of software , 1996, Proceedings of 9th International Conference on VLSI Design.

[9]  Mary Jane Irwin,et al.  Architecture-level power estimation and design experiments , 2001, TODE.

[10]  Dong Li,et al.  PowerPack: Energy Profiling and Analysis of High-Performance Systems and Applications , 2010, IEEE Transactions on Parallel and Distributed Systems.

[11]  Song Huang,et al.  On the energy efficiency of graphics processing units for scientific computing , 2009, 2009 IEEE International Symposium on Parallel & Distributed Processing.

[12]  Henry Fuchs,et al.  A sorting classification of parallel rendering , 1994, IEEE Computer Graphics and Applications.

[13]  Lance Williams,et al.  Pyramidal parametrics , 1983, SIGGRAPH.

[14]  Jason L. Mitchell,et al.  Shading in valve's source engine , 2006, SIGGRAPH Courses.

[15]  Kevin Skadron,et al.  A flexible simulation framework for graphics architectures , 2004, Graphics Hardware.

[16]  Erik Lindholm,et al.  NVIDIA Tesla: A Unified Graphics and Computing Architecture , 2008, IEEE Micro.

[17]  Yuan Xie,et al.  3D GPU architecture using cache stacking: Performance, cost, power and thermal analysis , 2009, 2009 IEEE International Conference on Computer Design.

[18]  Michael Wimmer,et al.  Coherent Hierarchical Culling: Hardware Occlusion Queries Made Useful , 2004, Comput. Graph. Forum.