[ 
https://issues.apache.org/jira/browse/HADOOP-11505?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16191316#comment-16191316
 ] 

Anup Halarnkar commented on HADOOP-11505:
-----------------------------------------

Thanks for the response Steve.
I had already tried the latest "08" patch. But, it did not work for me.
I am not really sure about intricacies or dependencies involved for "bswap" as 
the ver 08 patch is too big.

Honestly, I used only the GCC builtin macros (__builtin_bswap32(), etc. These 
are already ported to output assembly code for power). And I made the 
modification is just one file "primitives.h". Also, I made sure that other 
architectures would not be disturbed with this change as I used PPC specific 
arch macros.

So, I was trying to get more information from community about my patch ( Info 
related to portability, dependencies, arch specific info, etc)

I am thankful for your response and will look to explore the ver 08 patch given 
here as well as try to get results from other power specific communities.

Thanks,
Anup Halarnkar

> Various native parts use bswap incorrectly and unportably
> ---------------------------------------------------------
>
>                 Key: HADOOP-11505
>                 URL: https://issues.apache.org/jira/browse/HADOOP-11505
>             Project: Hadoop Common
>          Issue Type: Bug
>    Affects Versions: 3.0.0-alpha1
>            Reporter: Colin P. McCabe
>            Assignee: Alan Burlison
>         Attachments: HADOOP-11505.001.patch, HADOOP-11505.003.patch, 
> HADOOP-11505.004.patch, HADOOP-11505.005.patch, HADOOP-11505.006.patch, 
> HADOOP-11505.007.patch, HADOOP-11505.008.patch
>
>
> hadoop-mapreduce-client-nativetask fails to use x86 optimizations in some 
> cases.  Also, on some alternate, non-x86, non-ARM architectures the generated 
> code is incorrect.  Thanks to Steve Loughran and Edward Nevill for finding 
> this.



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to