You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@lucene.apache.org by "Ignacio Vera (Jira)" <ji...@apache.org> on 2020/05/11 05:48:00 UTC
[jira] [Updated] (LUCENE-9368) SIMD-based decoding of BKD docIds
[ https://issues.apache.org/jira/browse/LUCENE-9368?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Ignacio Vera updated LUCENE-9368:
---------------------------------
Description:
In LUCENE-9087 we changed the way how we constructed Kd trees to always have full leaves. This open the possibility to use more efficient decoding techniques for docIds, similar to what we do in postings.
This issue explores adding SIMD-based techniques when encoding docIds in the BKD tree.
> SIMD-based decoding of BKD docIds
> ---------------------------------
>
> Key: LUCENE-9368
> URL: https://issues.apache.org/jira/browse/LUCENE-9368
> Project: Lucene - Core
> Issue Type: Improvement
> Reporter: Ignacio Vera
> Priority: Minor
>
> In LUCENE-9087 we changed the way how we constructed Kd trees to always have full leaves. This open the possibility to use more efficient decoding techniques for docIds, similar to what we do in postings.
>
> This issue explores adding SIMD-based techniques when encoding docIds in the BKD tree.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@lucene.apache.org
For additional commands, e-mail: issues-help@lucene.apache.org