Power Modeling for GPU Architectures Using McPAT
Authors:
Open Access
- 23 June 2014
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 19 (3) , 1-24
Abstract
Graphics Processing Units (GPUs) are very popular for both graphics and general-purpose applications. Since GPUs operate many processing units and manage multiple levels of memory hierarchy, they consume a significant amount of power. Although several power models for CPUs are available, the power consumption of GPUs has not been studied much yet. In this article we develop a new power model for GPUs by utilizing McPAT, a CPU power tool. We generate initial power model data from McPAT with a detailed GPU configuration, and then adjust the models by comparing them with empirical data. We use the NVIDIA's Fermi architecture for building the power model, and our model estimates the GPU power consumption with an average error of 7.7% and 12.8% for the microbenchmarks and Merge benchmarks, respectively.Keywords
Funding Information
- Brain Korea 21 Project
- Division of Computer and Network Systems (CCF 1054830, CNS 085511)
- Division of Computing and Communication Foundations (CCF 1054830, CNS 085511)
- Sandia National Laboratories, National Nuclear Security Administration
- Semiconductor Research Corporation
- National Research Foundation of Korea (2012R1A2A2A06047297)
This publication has 28 references indexed in Scilit:
- GPUWattch2013
- A Roofline Model of Energy2013
- Power-performance co-optimization of throughput core architecture using resistive memory2013
- XIOSim2012
- Tree structured analysis on GPU power study2011
- An integrated GPU power and performance model2010
- McPAT2009
- Optimizing NUCA Organizations and Wiring Alternatives for Large Caches with CACTI 6.02007
- Run-time power estimation in high performance microprocessors2001
- Wattch2000