A Predictive Shutdown Technique for GPU Shader Processors

Authors:
Po-Han Wang;Yen-Ming Chen;Chia-Lin Yang;Yu-Jung Cheng
Affiliations:
National Taiwan Universit, Taipei;National Taiwan Universit, Taipei;National Taiwan University, Taipei;National Taiwan Universit, Taipei
Venue:
IEEE Computer Architecture Letters
Year:
2009

Citing 0
Cited 4

Power gating strategies on GPUs

ACM Transactions on Architecture and Code Optimization (TACO)
Enabling power efficiency through dynamic rerouting on-chip

ACM Transactions on Embedded Computing Systems (TECS) - Special Section on Wireless Health Systems, On-Chip and Off-Chip Network Architectures
Energy-aware code motion for GPU shader processors

ACM Transactions on Embedded Computing Systems (TECS)
Optimizing GPU energy efficiency with 3D die-stacking graphics memory and reconfigurable memory interface

ACM Transactions on Architecture and Code Optimization (TACO)

Quantified Score

Hi-index	0.00

Visualization

Abstract

As technology continues to shrink, reducing leakage is critical to achieve energy efficiency. Previous works on low-power GPU (Graphics Processing Unit) focus on techniques for dynamic power reduction, such as DVFS (Dynamic Voltage/Frequency Scaling) and clock gating. In this paper, we explore the potential of adopting architecturelevel power gating techniques for leakage reduction on GPU. In particular, we focus on the most power-hungry components, shader processors. We observe that, due to different scene complexity, the required shader resources to satisfy the target frame rate actually vary across frames. Therefore, we propose the Predictive Shader Shutdown technique to exploit workload variation across frames for leakage reduction on shader processors. The experimental results show that Predictive Shader Shutdown achieves up to 46% leakage reduction on shader processors with negligible performance degradation.