[
https://issues.apache.org/jira/browse/HIVE-15743?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15847333#comment-15847333
]
Sergey Shelukhin edited comment on HIVE-15743 at 1/31/17 7:09 PM:
------------------------------------------------------------------
does there have to be a string, as well as toCharArray? The original code has
bytes as input. String creation is actually more than half of the cost of going
from byte[] to double (see picture).
Also, I am not sure how important the precision issue is; however, one thing to
suggest, if it's rare and easy to detect, is to handle the 99% cases fast, and
fall back to Double.parse(new String) in exotic/rare cases.
was (Author: sershe):
does there have to be a string, as well as toCharArray? The original code has
bytes as input. String creation is actually more than half of the cost of going
from byte[] to double (see picture).
> vectorized text parsing: speed up double parse
> ----------------------------------------------
>
> Key: HIVE-15743
> URL: https://issues.apache.org/jira/browse/HIVE-15743
> Project: Hive
> Issue Type: Bug
> Reporter: Sergey Shelukhin
> Assignee: Teddy Choi
> Attachments: HIVE-15743.1.patch, HIVE-15743.2.patch, tpch-without.png
>
>
> {noformat}
> Double.parseDouble(
> new String(bytes, fieldStart, fieldLength,
> StandardCharsets.UTF_8));{noformat}
> This takes ~25% of the query time in some cases.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
