Towards Accelerating Generic Machine Learning Prediction Pipelines.
ICCD, pp. 431-434, 2017.
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 pap...More
Full Text (Upload PDF)
PPT (Upload PPT)