Towards Accelerating Generic Machine Learning Prediction Pipelines

Machine Learning models are often composed by sequences of transformations. While this design makes easy to decompose and accelerate single model components at training time, predictions requires low latency and high performance predictability whereby end-to-end runtime optimizations and acceleratio...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE International Conference on Computer Design (ICCD) pp. 431 - 434
Main Authors Scolari, Alberto, Yunseong Lee, Weimer, Markus, Interlandi, Matteo
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2017
Subjects
Acceleration
Computational modeling
Data models
Field programmable gate arrays
FPGA
Machine Learning
Model Scoring
Pipelines
Prediction Pipelines
Predictive models
Training
Online AccessGet full text

Cover

More Information
Summary:Machine Learning models are often composed by sequences of transformations. While this design makes easy to decompose and accelerate single model components at training time, predictions requires low latency and high performance predictability whereby end-to-end runtime optimizations and acceleration is needed to meet such goals. This paper shed some light on the problem by using a production-like model, and showing how by redesigning model pipelines for efficient execution over CPUs and FPGAs performance improvements of several folds can be achieved.
ISSN:1063-6404
2576-6996
DOI:10.1109/ICCD.2017.76