Facebook 数据中心的深度学习推理：特征刻画、性能优化与硬件启示
机器学习
2018-11-30 v2 机器学习
摘要
深度学习技术的应用使机器学习模型取得了显著改进。本文详细刻画了 Facebook 社交网络服务中使用的深度学习模型。我们给出了模型的算力特征，描述了面向现有系统的高性能优化，指出了其局限性，并对未来的通用/加速推理硬件提出建议。此外，我们强调需要更好地协同设计算法、数值计算与计算平台，以应对数据中心中常见工作负载的挑战。
引用
@article{arxiv.1811.09886,
title = {Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications},
author = {Jongsoo Park and Maxim Naumov and Protonu Basu and Summer Deng and Aravind Kalaiah and Daya Khudia and James Law and Parth Malani and Andrey Malevich and Satish Nadathur and Juan Pino and Martin Schatz and Alexander Sidorov and Viswanath Sivakumar and Andrew Tulloch and Xiaodong Wang and Yiming Wu and Hector Yuen and Utku Diril and Dmytro Dzhulgakov and Kim Hazelwood and Bill Jia and Yangqing Jia and Lin Qiao and Vijay Rao and Nadav Rotem and Sungjoo Yoo and Mikhail Smelyanskiy},
journal= {arXiv preprint arXiv:1811.09886},
year = {2018}
}