Dear Wiki user, You have subscribed to a wiki page or wiki category on "Hama Wiki" for change notification.
The "SpMV" page has been changed by Mikalai Parafeniuk: http://wiki.apache.org/hama/SpMV?action=diff&rev1=13&rev2=14 In setup stage every peer reads input dense vector from file. After that, framework will partition matrix rows by the algorithm provided in custom partitioner automatically. After that local computation is performed. We gain some cells of result vector in bsp procedure, and they are written to output file. Output file is reread to construct instance of dense vector for further computation. === Implementation === - Implementation can be found in my GitHub repository [[https://github.com/ParafeniukMikalaj/spmv]] and patch can be found in [[https://issues.apache.org/jira/browse/HAMA-524|Apache JIRA]] as soon as JIRA will become available. GitHub repository contains only classes related to SpMV. I considered two possible use cases of SpMV: + Implementation can be found in my GitHub repository [[https://github.com/ParafeniukMikalaj/spmv]] and patch can be found in [[https://issues.apache.org/jira/browse/HAMA-524|Apache JIRA]] as soon as JIRA will become available. GitHub repository contains only classes related to SpMV. Before you start with SpMV make sure that you have followed [[http://wiki.apache.org/hama/GettingStarted|this]] guide and set up environment variables and so on. I considered two possible use cases of SpMV: 1. Usage in pair with `RandomMatrixGenerator`. 2. Usage with arbitrary text files. - In this section you will see how to use SpMV in this two cases. NOTE: currently SpMV is buggy, so output can be not correct. I propose the following directory structure for the following examples + In this section you will see how to use SpMV in this two cases. I propose the following directory structure for the following examples {{{ /user/hduser/spmv/matrix-seq /user/hduser/spmv/matrix-txt @@ -39, +39 @@ /user/hduser/spmv/vector-txt }}} Suffix `seq` denotes that directory contains sequence files. Suffix `txt` denotes that directory contains human-readable text files. <<BR>> - Also I defined some shell variables in .bashrc file of hadoop user to simplify following scripts. + Also I defined some shell variables in .bashrc file of hadoop user to simplify following code snippets. {{{ export HAMA_EXAMPLES=$HAMA_HOME/hama-examples*.jar export SPMV=/user/hduser/spmv
