high performance computing on graphics processing units: hgpu.org

Graphics processing units (GPUs) provide significant improvements in performance and performance-perwatt as compared to traditional multicore CPUs. This energy-efficiency of GPUs has facilitated the use of GPUs in many application domains. Albeit energy efficient, GPUs consume non-trivial power independently of CPUs. Therefore, we need to analyze the power and performance characteristic of GPUs and their causal relation with CPUs in order to reduce the total energy consumption of the system while sustaining high performance. In this paper, we provide a power and performance analysis of GPU-accelerated systems for better understandings of these implications. Our analysis on a real system discloses that system energy can be reduced by 28% retaining a decrease in performance within 1% by controlling the voltage and frequency levels of GPUs. We show that energy savings can be achieved when GPU core and memory clock frequencies are appropriately scaled considering the workload characteristics. Another interesting finding is that voltage and frequency scaling of CPUs is trivial for total system energy reduction, and even should not be applied in state-of-the-art GPU-accelerated systems. We believe that these findings are useful to develop dynamic voltage and frequency scaling (DVFS) algorithms for GPU-accelerated systems.