公开(公告)号：US20210124739A1

公开(公告)日：2021-04-29

申请号：US16990506

申请日：2020-08-11

Applicant: Microsoft Technology Licensing, LLC

Inventor： Konstantinos KARANASOS ,  Matteo INTERLANDI ,  Fotios PSALLIDAS ,  Rathijit SEN ,  Kwanghyun PARK ,  Ivan POPIVANOV ,  Subramaniam VENKATRAMAN KRISHNAN ,  Markus WEIMER ,  Yuan YU ,  Raghunath RAMAKRISHNAN ,  Carlo Aldo CURINO ,  Doris Suiyi XIN ,  Karla Jean SAUR

IPC: G06F16/2458 ,  G06N5/04 ,  G06N20/00 ,  G06F16/28

Abstract: The description relates to executing an inference query relative to a database management system, such as a relational database management system. In one example a trained machine learning model can be stored within the database management system. An inference query can be received that applies the trained machine learning model on data local to the database management system. Analysis can be performed on the inference query and the trained machine learning model to generate a unified intermediate representation of the inference query and the trained model. Cross optimization can be performed on the unified intermediate representation. Based upon the cross-optimization, a first portion of the unified intermediate representation to be executed by a database engine of the database management system can be determined, and, a second portion of the unified intermediate representation to be executed by a machine learning runtime can be determined.

公开(公告)号：US20240231927A1

公开(公告)日：2024-07-11

申请号：US18152391

申请日：2023-01-10

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yiwen ZHU ,  Alex YEO ,  Harsha Nihanth NAGULAPALLI ,  Sumeet KHUSHALANI ,  Arijit TARAFDAR ,  Subramaniam VENKATRAMAN KRISHNAN ,  Deepak RAVIKUMAR ,  Andrew Francis FOGARTY ,  Steve D. SUH ,  Yoonjae PARK ,  Niharika DUTTA ,  Santhosh Kumar RAVINDRAN

IPC: G06F9/50 ,  G06F9/48 ,  G06N3/08

CPC classification number: G06F9/5038 ,  G06F9/4843 ,  G06N3/08

Abstract: The present application relates to a network, apparatus, and method for allocating clusters of computing nodes for programming jobs. A network includes a plurality of datacenters including computing resources configurable to instantiate nodes for executing programming jobs on a cluster. The computing resources at one of the datacenters are configured to: provision a live pool including a number of clusters, each cluster in the live pool including a plurality of nodes imaged with a configuration for executing the programming jobs in parallel on the cluster; receive a request from a user to execute a programming job; allocate a cluster from the live pool to the user for the programming job when the cluster is available; evict the cluster from the live pool; and provision a new cluster within the live pool to meet the number of clusters. The number of clusters may be optimized based on linear programming and machine-learning.

公开(公告)号：US20250156430A1

公开(公告)日：2025-05-15

申请号：US19022565

申请日：2025-01-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Konstantinos KARANASOS ,  Matteo INTERLANDI ,  Fotios PSALLIDAS ,  Rathijit SEN ,  Kwanghyun PARK ,  Ivan POPIVANOV ,  Subramaniam VENKATRAMAN KRISHNAN ,  Markus WEIMER ,  Yuan YU ,  Raghunath RAMAKRISHNAN ,  Carlo Aldo CURINO ,  Doris Suiyi XIN ,  Karla Jean SAUR

IPC: G06F16/2458 ,  G06F16/28 ,  G06N5/04 ,  G06N20/00

Abstract: The description relates to executing an inference query relative to a database management system, such as a relational database management system. In one example a trained machine learning model can be stored within the database management system. An inference query can be received that applies the trained machine learning model on data local to the database management system. Analysis can be performed on the inference query and the trained machine learning model to generate a unified intermediate representation of the inference query and the trained model. Cross optimization can be performed on the unified intermediate representation. Based upon the cross-optimization, a first portion of the unified intermediate representation to be executed by a database engine of the database management system can be determined, and, a second portion of the unified intermediate representation to be executed by a machine learning runtime can be determined.