Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications

11/24/2018
by   Jongsoo Park, et al.
0

The application of deep learning techniques resulted in remarkable improvement of machine learning models. In this paper provides detailed characterizations of deep learning models used in many Facebook social network services. We present computational characteristics of our models, describe high performance optimizations targeting existing systems, point out their limitations and make suggestions for the future general-purpose/accelerated inference hardware. Also, we highlight the need for better co-design of algorithms, numerics and computing platforms to address the challenges of workloads often run in data centers.

READ FULL TEXT
research
03/20/2020

Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems

Large-scale training is important to ensure high performance and accurac...
research
05/06/2021

Challenges and Obstacles Towards Deploying Deep Learning Models on Mobile Devices

From computer vision and speech recognition to forecasting trajectories ...
research
07/08/2021

First-Generation Inference Accelerator Deployment at Facebook

In this paper, we provide a deep dive into the deployment of inference a...
research
01/17/2022

VELTAIR: Towards High-Performance Multi-tenant Deep Learning Services via Adaptive Compilation and Scheduling

Deep learning (DL) models have achieved great success in many applicatio...
research
12/30/2021

Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques

Deep learning is pervasive in our daily life, including self-driving car...
research
04/06/2017

ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models

While deep learning models have achieved state-of-the-art accuracies for...
research
05/28/2021

Bridge Data Center AI Systems with Edge Computing for Actionable Information Retrieval

Extremely high data rates at modern synchrotron and X-ray free-electron ...

Please sign up or login with your details

Forgot password? Click here to reset