incubator-hama-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Edward J. Yoon (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HAMA-83) 2D sqaure blocking for dense matrix multiplication
Date Wed, 12 Nov 2008 06:47:44 GMT

    [ https://issues.apache.org/jira/browse/HAMA-83?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12646816#action_12646816
] 

Edward J. Yoon commented on HAMA-83:
------------------------------------

This is my plan.

1. Generate formula
2. To avoid a lot of full scan, collect the data to new structure
3. Calculate them on map/reduce
4. Put result to table

> 2D sqaure blocking for dense matrix multiplication
> --------------------------------------------------
>
>                 Key: HAMA-83
>                 URL: https://issues.apache.org/jira/browse/HAMA-83
>             Project: Hama
>          Issue Type: New Feature
>          Components: implementation
>    Affects Versions: 0.1.0
>            Reporter: Edward J. Yoon
>            Assignee: Edward J. Yoon
>             Fix For: 0.1.0
>
>
> The matrix multiplication of the original arrays can be transformed into matrix multiplication
of blocks. For example,
> C_block(1,1)=A_block(1,1)*B_block(1,1) + A_block(1,2)*B_block(2,1)
> emit  <blockKey, subMatrix> pairs instead of current <Int, Vector> input
formatter, and have a reducer sum up the sub matrices as describe below.
> {code}
>  Mapper<BlockKey, subMatrix> {
>     sub-matrix multiplication of block
>  }
>  Reducer<BlockKey, subMatrix> {
>     summation all sub-matrices
>  }
> {code}

-- 
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