[
https://issues.apache.org/jira/browse/LUCENE-10150?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17427388#comment-17427388
]
ASF subversion and git services commented on LUCENE-10150:
----------------------------------------------------------
Commit 61c15c8c10fe97c7bee8102f2304613d8a2a4877 in lucene's branch
refs/heads/hnsw from Robert Muir
[ https://gitbox.apache.org/repos/asf?p=lucene.git;h=61c15c8 ]
LUCENE-10150: override readLongs() in ByteBuffersDataInput (#363)
Implement the bulk readLongs() with view buffers, consistent with how
readFloats() is implemented today.
This method is important for traversing the postings lists (PFOR
decompression), and is also used for block metadata in the stored fields
decompression.
> ByteBuffersDataInput should override readLongs?
> -----------------------------------------------
>
> Key: LUCENE-10150
> URL: https://issues.apache.org/jira/browse/LUCENE-10150
> Project: Lucene - Core
> Issue Type: Task
> Reporter: Robert Muir
> Priority: Major
> Fix For: main (9.0)
>
> Time Spent: 0.5h
> Remaining Estimate: 0h
>
> This DataInput optimizes readFloats() with a FloatBuffer view, but does
> nothing for readLongs().
> Currently readLongs() will read the entire array one-byte-at-a-time.
> With LUCENE-10149, it will go eight-bytes-at-a-time.
> But we could override this method and optimize it further, to reduce bounds
> checks and speed up postings.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org
For additional commands, e-mail: issues-h...@lucene.apache.org
