Editing Power management (section)

=={{anchor|DVFS}}In GPUs==
Graphics processing unit ([[GPU]]s) are used together with a [[CPU]] to accelerate [[computing]] in variety of domains revolving around [[scientific]], [[analytics]], [[engineering]], [[consumer]] and [[enterprise applications]].<ref>{{Cite web
|url=http://www.nvidia.com/object/what-is-gpu-computing.html
|title      = What is GPU computing
|publisher  = Nvidia
}}</ref>
All of this comes with some drawbacks, the high computing capability of GPUs comes at the cost of high [[power dissipation]]. Much research has been done over the power dissipation issue of GPUs and many techniques have been proposed to address this issue. [[Dynamic voltage scaling]]/[[dynamic frequency scaling]] (DVFS) and [[clock gating]] are two commonly used techniques for reducing dynamic power in GPUs.

===DVFS techniques===
Experiments show that conventional processor DVFS policy can achieve power reduction of [[Embedded system|embedded]] GPUs with reasonable performance degradation.<ref>"[https://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6329290&tag=1 Dynamic voltage and frequency scaling framework for low-power embedded GPUs]", Daecheol You et al., Electronics Letters  (Volume:48, Issue: 21 ), 2012.</ref> New directions for designing effective DVFS schedulers for heterogeneous systems are also being explored.<ref>"[http://dl.acm.org/citation.cfm?id=2571035 Effects of Dynamic Voltage and Frequency Scaling on a K20 GPU]", Rong Ge et al., 42nd International Conference on Parallel Processing Pages 826-833, 2013.</ref> A heterogeneous CPU-GPU architecture, GreenGPU<ref>"[http://dl.acm.org/citation.cfm?id=2410566 GreenGPU: A Holistic Approach to Energy Efficiency in GPU-CPU Heterogeneous Architectures]", Kai Ma et al., 41st International Conference on Parallel Processing Pages 48-57, 2012.</ref> is presented  which employs DVFS in a synchronized way, both for GPU and CPU. GreenGPU is implemented using the CUDA framework on a real physical testbed with Nvidia GeForce GPUs and AMD Phenom II CPUs. Experimentally it is shown that the GreenGPU achieves 21.04% average [[energy savings]] and outperforms several well-designed baselines.
For the mainstream GPUs which are extensively used in all kinds of commercial and personal applications several DVFS techniques exist and are built into the GPUs alone, [[AMD PowerTune]] and [[AMD ZeroCore Power]] are the two [[dynamic frequency scaling]] technologies for [[AMD]] graphic cards. Practical tests showed that reclocking a [[GeForce]] [[GTX 480]] can achieve a 28% lower power consumption while only decreasing performance by 1% for a given task.<ref>"[http://dl.acm.org/citation.cfm?id=2387879 Power and performance analysis of GPU-accelerated systems]", Yuki Abe et al., USENIX conference on Power-Aware Computing and Systems Pages 10-10, 2012.</ref>

===Power gating techniques===
Much research has been done on the dynamic power reduction with the use of DVFS techniques. However, as technology continues to shrink, leakage power will become a dominant factor.<ref>"[https://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=782564 Design challenges of technology scaling]", Borkar, S., IEEE Micro  (Volume:19,  Issue: 4 ), 1999.</ref> [[Power gating]] is a commonly used circuit technique to remove leakage by turning off the supply voltage of unused circuits. Power gating incurs energy overhead; therefore, unused circuits need to remain idle long enough to compensate this overheads.
A novel micro-architectural technique<ref>"[https://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6176483 Run-time power-gating in caches of GPUs for leakage energy savings]", Yue Wang et al., Design, Automation & Test in Europe Conference & Exhibition (DATE), 2012</ref> for run-time power-gating caches of GPUs saves leakage energy. Based on experiments on 16 different GPU workloads, the average energy savings achieved by the proposed technique is 54%.
Shaders are the most power hungry component of a GPU, a predictive shader shut down power gating technique<ref>"[https://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4758617 A Predictive Shutdown Technique for GPU Shader Processors]", Po-Han Wang et al., Computer Architecture Letters  (Volume: 8,  Issue: 1 ), 2009</ref> achieves up to 46% leakage reduction on shader processors.
The Predictive Shader Shutdown technique exploits workload variation across frames to eliminate leakage in shader clusters. Another technique called Deferred Geometry Pipeline seeks to minimize leakage in [[fixed function units|fixed-function geometry units]] by utilizing an imbalance between geometry and fragment computation across batches which removes up to 57% of the leakage in the fixed-function geometry units. A simple time-out power gating method can be applied to non-shader execution units which eliminates 83.3% of the leakage in non-shader execution units on average.
All the three techniques stated above incur negligible performance degradation, less than 1%.<ref>"[http://dl.acm.org/citation.cfm?id=2019612 Power gating strategies on GPUs]", Po-Han Wang et al., ACM Transactions on Architecture and Code Optimization (TACO) Volume 8 Issue 3, 2011</ref>

===Screen power saving techniques===
On some laptops and smartphones, the screen power saving technique is used. Such technique is dynamatically change the backlight brightness and the LCD offset to decrease screen power. Examples of such technique included Intel Display Power Saving Technology (DPST).<ref>https://ieeexplore.ieee.org/document/4216914</ref>