Power Aware Computing on GPUs
Authors:
- Kiran KasichayanulaKKKiran Kasichayanula
- Dan TerpstraDTDan Terpstra
- Piotr LuszczekPLPiotr Luszczek
- Stan TomovSTStan Tomov
- Shirley MooreSMShirley Moore
- Gregory D. PetersonGPGregory D. Peterson
- 1 July 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21665133,p. 64-73
Abstract
Energy and power density concerns in modern processors have led to significant computer architecture research efforts in power-aware and temperature-aware computing. With power dissipation becoming an increasingly vexing problem, power analysis of Graphical Processing Unit (GPU) and its components has become crucial for hardware and software system design. Here, we describe our technique for a coordinated measurement approach that combines real total power measurement and per-component power estimation. To identify power consumption accurately, we introduce the Activity-based Model for GPUs (AMG), from which we identify activity factors and power for micro architectures on GPUs that will help in analyzing power tradeoffs of one component versus another using micro benchmarks. The key challenge addressed in this work is real-time power consumption, which can be accurately estimated using NVIDIA's Management Library (NVML). We validated our model using Kill-A-Watt power meter and the results are accurate within 10%. This work also analyses energy consumption of MAGMA (Matrix Algebra on GPU and Multicore Architectures) BLAS2, BLAS3 kernels, and Hessenberg kernels.Keywords
This publication has 9 references indexed in Scilit:
- Statistical GPU power analysis using tree-based methods2011
- Accelerating the reduction to upper Hessenberg, tridiagonal, and bidiagonal forms through hybrid GPU-based computingParallel Computing, 2010
- An Improved Magma Gemm For Fermi Graphics Processing UnitsThe International Journal of High Performance Computing Applications, 2010
- An integrated GPU power and performance modelACM SIGARCH Computer Architecture News, 2010
- Accurate Measurements and Precise Modeling of Power Dissipation of CUDA Kernels toward Power Optimized High Performance CPU-GPU Computing2009
- Standby and Active Leakage Current Control and Minimization in CMOS VLSI CircuitsIEICE Transactions on Electronics, 2005
- Understanding the efficiency of GPU algorithms for matrix-matrix multiplication2004
- Runtime power monitoring in high-end processors: methodology and empirical data2003
- Random ForestsMachine Learning, 2001