hawq-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Hongxu Ma (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HAWQ-1450) New HAWQ executor with vectorization & possible code generation
Date Wed, 20 Jun 2018 05:18:00 GMT

    [ https://issues.apache.org/jira/browse/HAWQ-1450?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16517807#comment-16517807

Hongxu Ma commented on HAWQ-1450:

All work finished, thanks! [~weinan003] [~zhangshujie]

Form Weinan's mail in hawq-dev:
"At present, it supports 7 types of data trigger the vectorized function and reach two to
eight times 
acceleration comparing with regular execution in different performance test queries. Furthermore,
it has an extended friendly framework, you can patch other types into as your need.

> New HAWQ executor with vectorization & possible code generation
> ---------------------------------------------------------------
>                 Key: HAWQ-1450
>                 URL: https://issues.apache.org/jira/browse/HAWQ-1450
>             Project: Apache HAWQ
>          Issue Type: New Feature
>          Components: Query Execution
>            Reporter: Lei Chang
>            Assignee: Hongxu Ma
>            Priority: Major
>             Fix For: backlog
>         Attachments: hawq_vectorized_execution_design_v0.1.pdf
> Most HAWQ executor code is inherited from postgres & gpdb. Let's discuss how to build
a new hawq executor with vectorization and possibly code generation. These optimization may
potentially improve the query performance a lot.

This message was sent by Atlassian JIRA

View raw message