IEEE Computer Architecture Letters · 2009 · 20 citations · 18 references
Hardware SecurityPower-aware ComputingGpu ArchitectureEngineeringEnergy EfficiencyLeakage ReductionComputer EngineeringComputer ArchitectureParallel ProgrammingComputer ScienceParallel ComputingGpu Shader ProcessorsGpu ClusterWorkload VariationGpu ComputingPower Management
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 architecture-level 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.
18
Design challenges of technology scaling
Shekhar Borkar · IEEE Micro · 1999 · 1.1K citations
Krisztián Flautner, Nam Sung Kim, Steve Martin et al. · ACM SIGARCH Computer Architecture News · 2002 · 737 citations
Electrical Engineering, Power-aware Computing, Engineering +12
Michael D. Powell, Se-Hyun Yang, Babak Falsafi et al. · 2000 · 666 citations · Full text
Hardware Security, Electrical Engineering, Deep-submicron Cmos Designs +10
Stefanos Kaxiras, Zhigang Hu, Margaret Martonosi · 2001 · 613 citations
Hardware Security, Electrical Engineering, Power-aware Computing +13