arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.17331cs.ARcs.CY
收藏

人工智能/机器学习加速器、超级计算机和计算密集型应用中计算的能源估计趋势

Trends in Energy Estimates for Computing in AI/Machine Learning Accelerators, Supercomputers, and Compute-Intensive Applications

Sadasivan Shankar, Albert Reuther

摘要:

我们研究了由几何缩放定律驱动的不同系统的计算能量需求,以及在过去十年中越来越多地使用人工智能或机器学习(AI-ML)。随着更多基于数据驱动发现的科学技术应用,机器学习方法,特别是深度神经网络得到了广泛的应用。为了实现这些应用,硬件加速器和先进的AI-ML方法都导致了新架构、系统设计、算法和软件的引入。我们对能源趋势的分析表明了三个重要的观察结果:1)由于几何缩放而导致的能源效率正在放缓; 2)对于各种系统,特别是对于大规模AI-ML加速器或超级计算机,比特级的能源效率并没有转化为并行级或系统级的效率; 3)在应用层面,通用AI-ML方法可能是计算能量密集型的,抵消了几何缩放和专用加速器带来的能量增益。此外,我们的分析提供了具体的指标,将能源效率与性能分析相结合,以实现未来的高性能和可持续计算。

英文摘要:

We examine the computational energy requirements of different systems driven by the geometrical scaling law, and increasing use of Artificial Intelligence or Machine Learning (AI-ML) over the last decade. With more scientific and technology applications based on data-driven discovery, machine learning methods, especially deep neural networks, have become widely used. In order to enable such applications, both hardware accelerators and advanced AI-ML methods have led to the introduction of new architectures, system designs, algorithms, and software. Our analysis of energy trends indicates three important observations: 1) Energy efficiency due to geometrical scaling is slowing down; 2) The energy efficiency at the bit-level does not translate into efficiency at the instruction-level, or at the system-level for a variety of systems, especially for large-scale AI-ML accelerators or supercomputers; 3) At the application level, general-purpose AI-ML methods can be computationally energy intensive, off-setting the gains in energy from geometrical scaling and special purpose accelerators. Further, our analysis provides specific pointers for integrating energy efficiency with performance analysis for enabling high-performance and sustainable computing in the future.

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。

↑