End-to-end Optimization of Machine Learning Prediction Queries

no code implementations • 31 May 2022 • Kwanghyun Park, Karla Saur, Dalitso Banda, Rathijit Sen, Matteo Interlandi, Konstantinos Karanasos

First, it employs logical optimizations that pass information between the data part (and the properties of the underlying data) and the ML part to optimize each other.

BIG-bench Machine Learning

Query Processing on Tensor Computation Runtimes

no code implementations • 3 Mar 2022 • Dong He, Supun Nakandala, Dalitso Banda, Rathijit Sen, Karla Saur, Kwanghyun Park, Carlo Curino, Jesús Camacho-Rodríguez, Konstantinos Karanasos, Matteo Interlandi

Finally, TQP can accelerate queries mixing ML predictions and SQL end-to-end, and deliver up to 9$\times$ speedup over CPU baselines.

Management

Extending Relational Query Processing with ML Inference

no code implementations • 1 Nov 2019 • Konstantinos Karanasos, Matteo Interlandi, Doris Xin, Fotis Psallidas, Rathijit Sen, Kwanghyun Park, Ivan Popivanov, Supun Nakandal, Subru Krishnan, Markus Weimer, Yuan Yu, Raghu Ramakrishnan, Carlo Curino

The broadening adoption of machine learning in the enterprise is increasing the pressure for strict governance and cost-effective performance, in particular for the common and consequential steps of model storage and inference.

Cloudy with high chance of DBMS: A 10-year prediction for Enterprise-Grade ML

no code implementations • 30 Aug 2019 • Ashvin Agrawal, Rony Chatterjee, Carlo Curino, Avrilia Floratou, Neha Gowdal, Matteo Interlandi, Alekh Jindal, Kostantinos Karanasos, Subru Krishnan, Brian Kroth, Jyoti Leeka, Kwanghyun Park, Hiren Patel, Olga Poppe, Fotis Psallidas, Raghu Ramakrishnan, Abhishek Roy, Karla Saur, Rathijit Sen, Markus Weimer, Travis Wright, Yiwen Zhu

Consequently, rigorous data management has emerged as a key requirement in enterprise settings.

Management