公开(公告)号：US20210089532A1

公开(公告)日：2021-03-25

申请号：US16581905

申请日：2019-09-25

Applicant: Microsoft Technology Licensing, LLC

Inventor： Hiren S. PATEL ,  Rathijit SEN ,  Zhicheng YIN ,  Shi QIAO ,  Abhishek ROY ,  Alekh JINDAL ,  Subramaniam Venkatraman KRISHNAN ,  Carlo Aldo CURINO

IPC: G06F16/2453

Abstract: The cloud-based query workload optimization system disclosed herein the cloud-based query workloads optimization system receives query logs from various query engines to a cloud data service, extracts various query entities from the query logs, parses query entities to generate a set of common workload features, generates intermediate representations of the query workloads, wherein the intermediate representations are agnostic to the language of the plurality of the queries, identifies a plurality of workload patterns based on the intermediate representations of the query workloads, categorizes the workloads in one or more workload type categories based on the workload patterns and the workload features, and selects an optimization scheme based on the category of workload pattern.

公开(公告)号：US20230342359A1

公开(公告)日：2023-10-26

申请号：US18345789

申请日：2023-06-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Irene Rogan SHAFFER ,  Remmelt Herbert Lieve AMMERLAAN ,  Gilbert ANTONIUS ,  Marc T. FRIEDMAN ,  Abhishek ROY ,  Lucas ROSENBLATT ,  Vijay Kumar RAMANI ,  Shi QIAO ,  Alekh JINDAL ,  Peter ORENBERG ,  H M Sajjad Hossain ,  Soundararajan Srinivasan ,  Hiren Shantilal PATEL ,  Markus WEIMER

IPC: G06F16/2453 ,  G06N20/00 ,  G06F11/34 ,  G06F16/901

CPC classification number: G06F16/24542 ,  G06N20/00 ,  G06F11/3466 ,  G06F16/9024

Abstract: Methods of machine learning for system deployments without performance regressions are performed by systems and devices. A performance safeguard system is used to design pre-production experiments for determining the production readiness of learned models based on a pre-production budget by leveraging big data processing infrastructure and deploying a large set of learned or optimized models for its query optimizer. A pipeline for learning and training differentiates the impact of query plans with and without the learned or optimized models, selects plan differences that are likely to lead to most dramatic performance difference, runs a constrained set of pre-production experiments to empirically observe the runtime performance, and finally picks the models that are expected to lead to consistently improved performance for deployment. The performance safeguard system enables safe deployment not just for learned or optimized models but also for additional of other ML-for-Systems features.