ML-based indexing ("The Case for Learned Index Structures", a paperfrom Google) - Mailing list pgsql-hackers

From Nikolay Samokhvalov
Subject ML-based indexing ("The Case for Learned Index Structures", a paperfrom Google)
Date
Msg-id CANNMO+J1KeTSx5q5SYuwHf1v-gPRLrOZw1s7qOpqWx=3UMMvtg@mail.gmail.com
Whole thread Raw
Responses Re: ML-based indexing ("The Case for Learned Index Structures", apaper from Google)  (Oleg Bartunov <obartunov@gmail.com>)
List pgsql-hackers
Very interesting read: https://arxiv.org/abs/1712.01208


Some of the comments (from Twitter https://twitter.com/schrockn/status/940037656494317568): "Jeff Dean and co at GOOG just released a paper showing how machine-learned indexes can replace B-Trees, Hash Indexes, and Bloom Filters. Execute 3x faster than B-Trees, 10-100x less space. Executes on GPU, which are getting faster unlike CPU. Amazing."

Can those ideas be applied to Postgres in its current state? Or it's not really down-to-earth?

pgsql-hackers by date:

Previous
From: Tom Lane
Date:
Subject: Re: plpgsql test layout
Next
From: Robert Haas
Date:
Subject: Re: [HACKERS] Moving relation extension locks out of heavyweight lock manager