[ 
https://issues.apache.org/jira/browse/AVRO-354?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12804510#action_12804510
 ] 

Thiruvalluvan M. G. commented on AVRO-354:
------------------------------------------

I too saw an improvement of over 10% for the nested record case and no 
improvement in readInt(). But, curiously, if you do both the tests together, 
(Perf -N -i), I see about 10% improvement  for nested record and about 20% for 
readInt(). As would have expected performing readInt() before nested record 
test (-i -N) shows improvement only in nested record test.

My machine is an HP laptop Compaq 6910p and my tests are with JDK 1.6.0_17.

I'd vote for slipping in this optimization because it improves performance in 
certain cases and does not degrade any.

> Performance improvement to BinaryDecoder.readInt()
> --------------------------------------------------
>
>                 Key: AVRO-354
>                 URL: https://issues.apache.org/jira/browse/AVRO-354
>             Project: Avro
>          Issue Type: Improvement
>          Components: java
>    Affects Versions: 1.3.0
>         Environment: koli...@koliver-ws4:~$ uname -a
> Linux koliver-ws4 2.6.24-26-generic #1 SMP Tue Dec 1 17:55:03 UTC 2009 x86_64 
> GNU/Linux
>            Reporter: Kevin Oliver
>            Priority: Minor
>         Attachments: AVRO-354-results.csv, AVRO-354.patch
>
>
> Able to get a 3-7% improvement on Perf -i by creating a specialized version 
> of BinaryDecoder.readInt() that uses the same code as readLong() but uses 
> ints instead of long for all its math and bit arithmetic.
> The performance improvement is larger on a 32-bit VM (around 7%) than on a 
> 64-bit VM (around 3%). 

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

Reply via email to