2020/02/18 by Yehia Arafa, Ammar ElWazir, Abdelrahman ElKanishy +6 · 1 voice · 2 citations
Computer Science · Engineering · #Advanced Data Storage Technologies #Green IT and Sustainability #Parallel Computing and Optimization Techniques #cs.DC #cs.PF
paper · pdf · doi:10.1145/3387902.3392613
arxiv published 2020/02/18 · openalex created_date 2020/02/24 · openalex publication_date 2020/05/11 · arxiv updated 2020/06/02 · openalex updated_date 2026/07/29
GPUs are prevalent in modern computing systems at all scales. They consume a significant fraction of the energy in these systems. However, vendors do not publish the actual cost of the power/energy overhead of their internal microarchitecture. In this paper, we accurately measure the energy consumption of various PTX instructions found in modern NVIDIA GPUs. We provide an exhaustive comparison of more than 40 instructions for four high-end NVIDIA GPUs from four different generations (Maxwell, Pascal, Volta, and Turing). Furthermore, we show the effect of the CUDA compiler optimizations on the energy consumption of each instruction. We use three different software techniques to read the GPU on-chip power sensors, which use NVIDIA's NVML API and provide an in-depth comparison between these techniques. Additionally, we verified the software measurement techniques against a custom-designed hardware power measurement. The results show that Volta GPUs have the best energy efficiency of all the other generations for the different categories of the instructions. This work should aid in understanding NVIDIA GPUs' microarchitecture. It should also make energy measurements of any GPU kernel both efficient and accurate.