You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hama.apache.org by ed...@apache.org on 2012/02/01 01:35:08 UTC
svn commit: r1238880 - in /incubator/hama/trunk: CHANGES.txt
src/site/xdoc/index.xml
Author: edwardyoon
Date: Wed Feb 1 00:35:07 2012
New Revision: 1238880
URL: http://svn.apache.org/viewvc?rev=1238880&view=rev
Log:
Website Improvements
Modified:
incubator/hama/trunk/CHANGES.txt
incubator/hama/trunk/src/site/xdoc/index.xml
Modified: incubator/hama/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/incubator/hama/trunk/CHANGES.txt?rev=1238880&r1=1238879&r2=1238880&view=diff
==============================================================================
--- incubator/hama/trunk/CHANGES.txt (original)
+++ incubator/hama/trunk/CHANGES.txt Wed Feb 1 00:35:07 2012
@@ -34,6 +34,7 @@ Release 0.4 - Unreleased
IMPROVEMENTS
+ HAMA-460: Website Improvements (Suraj Menon via edwardyoon)
HAMA-470: The web UI should display the version of running Hama cluster. (Suraj Menon via edwardyoon)
HAMA-475: Add unit test for SSSP example (edwardyoon)
HAMA-481: Add reopen to peer (tjungblut)
Modified: incubator/hama/trunk/src/site/xdoc/index.xml
URL: http://svn.apache.org/viewvc/incubator/hama/trunk/src/site/xdoc/index.xml?rev=1238880&r1=1238879&r2=1238880&view=diff
==============================================================================
--- incubator/hama/trunk/src/site/xdoc/index.xml (original)
+++ incubator/hama/trunk/src/site/xdoc/index.xml Wed Feb 1 00:35:07 2012
@@ -25,16 +25,16 @@ xsi:schemaLocation="http://maven.apache.
<section name="Apache Hama"></section>
<img src="images/hama_art_arthur_300x220.png" align="right" style="margin-top:-20px;margin-left:20px;margin-right:20px;" />
<p>
- <strong>Apache Hama</strong> is a Pure BSP computing framework on top of Hadoop HDFS for massive scientific computations
- e.g., matrix, graph and network algorithms. Currently, it has follow features:
+ <strong>Apache Hama</strong> is a pure BSP(Bulk Synchronous Parallel) computing framework on top of HDFS (Hadoop Distributed File System) for massive scientific computations
+ such as matrix, graph and network algorithms. Currently, it has the following features:
</p>
<ul>
<li>Job submission and management interface.</li>
<li>Multiple tasks per node.</li>
<li>Input/Output Formatter.</li>
<li>Checkpoint recovery.</li>
- <li>Supports to run in the Clouds using <a href="hama_on_clouds.html">Apache Whirr</a>.</li>
- <li>Supports to run with Hadoop YARN.</li>
+ <li>Support to run in the Cloud using <a href="hama_on_clouds.html">Apache Whirr</a>.</li>
+ <li>Support to run with Hadoop YARN.</li>
</ul>
<br/>
<table class="green" width="100%" cellspacing="0" cellpadding="5" border="1">
@@ -48,8 +48,7 @@ xsi:schemaLocation="http://maven.apache.
</ul>
</td></tr></table>
<subsection name="Why Hama and BSP?"></subsection>
- <p>Today, many practical data processing applications requires a good scalability, a flexible model, a high compatibility with existing data systems e.g., HDFS, HBase, and especially a communication capability which allows to exchange information using message-passing paradigm beyond MapReduce.
- Here, Bulk Synchronous Parallel (BSP) model fills the bill nicely and besides, it has several main advantages over MapReduce and MPI:</p>
+ <p>Today, many practical data processing applications require a more flexible programming abstraction model that is compatible to run on highly scalable and massive data systems (e.g., HDFS, HBase, etc). A message passing paradigm beyond Map-Reduce framework would increase its flexibility in its communication capability. Bulk Synchronous Parallel (BSP) model fills the bill appropriately. Some of its significant advantages over MapReduce and MPI are:</p>
<ul>
<li>Supports message passing paradigm style of application development</li>
<li>Provides a flexible, simple, and easy-to-use small APIs</li>