arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.05472cs.LGcs.AI
收藏

深度学习推理中的计算和能耗趋势

Compute and Energy Consumption Trends in Deep Learning Inference

European Commission, Joint Research Centre(欧盟委员会联合研究中心)

Radosvet Desislavov, Fernando Martínez-Plumed, José Hernández-Orallo

摘要:

一些人工智能范例的进展,如深度学习,据说与参数数量的指数增长有关。有许多研究证实了这些趋势,但这是否会转化为能源消耗的指数增长?为了回答这个问题,我们关注的是推理成本而不是训练成本,因为前者占了大部分计算工作量,这仅仅是因为乘法因素。此外,除了算法创新之外,我们还考虑了更具体和更强大的硬件(导致更高的FLOPS),这些硬件通常伴随着重要的能效优化。我们还将重点从突破性论文的首次实现转移到一两年后的技术整合版本。在这种独特而全面的视角下,我们研究了计算机视觉和自然语言处理领域的相关模型:为了持续提高性能,我们看到能耗的增长比之前预期的要温和得多。唯一需要注意的是,随着未来人工智能的渗透率增加,并且变得更加普遍,倍增因素再次出现。

英文摘要:

The progress of some AI paradigms such as deep learning is said to be linked to an exponential growth in the number of parameters. There are many studies corroborating these trends, but does this translate into an exponential increase in energy consumption? In order to answer this question we focus on inference costs rather than training costs, as the former account for most of the computing effort, solely because of the multiplicative factors. Also, apart from algorithmic innovations, we account for more specific and powerful hardware (leading to higher FLOPS) that is usually accompanied with important energy efficiency optimisations. We also move the focus from the first implementation of a breakthrough paper towards the consolidated version of the techniques one or two year later. Under this distinctive and comprehensive perspective, we study relevant models in the areas of computer vision and natural language processing: for a sustained increase in performance we see a much softer growth in energy consumption than previously anticipated. The only caveat is, yet again, the multiplicative factor, as future AI increases penetration and becomes more pervasive.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑