hadoop-pig-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Dmitriy V. Ryaboy (JIRA)" <j...@apache.org>
Subject [jira] Commented: (PIG-688) PERFORMANCE: Vectorize operators
Date Mon, 30 Nov 2009 16:11:20 GMT

    [ https://issues.apache.org/jira/browse/PIG-688?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12783720#action_12783720
] 

Dmitriy V. Ryaboy commented on PIG-688:
---------------------------------------

I am not sure what you mean by processing remaining tuples in the close() method.

My understanding is more like this: in the first next() call on the leaf operator, a next()
call cascades down the tree, and a bag of tuples gets processed as it comes back up the tree.
The next b calls get a pre-computed result from the buffer. Once the buffer is empty, the
operation is repeated, until all tuples at the bottom of the tree have been fetched.  The
close method is unaffected. 

> PERFORMANCE: Vectorize operators
> --------------------------------
>
>                 Key: PIG-688
>                 URL: https://issues.apache.org/jira/browse/PIG-688
>             Project: Pig
>          Issue Type: Improvement
>            Reporter: Thejas M Nair
>
> By Vectorization, I mean passing multiple (/vector of) records at a time between operators
(and potentially other functions like udfs)
> Vectorization of pig operators can improve performance by 
> 1. improving locality and cache utilization
> 2. Reducing number of function calls. Many functions calls are likely to be dynamically
resolved. There may be some checks in each function that we might be able to do once for several
recs.
> 3. Potentially benefit from cpu pipeline architecture. ( But I don't know how good java
VM is at that ..)
> To do vectorization in map stage, we need to use MapRunner - see PIG-687.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message