<?xml version="1.0" encoding="UTF-8"?>











<rss version="2.0" xmlns:jf="http://www.jivesoftware.com/xmlns/jiveforums/rss">



<channel>
    <title>Support Forums: Message List - Article: Distributed Computing Economics</title>
    <link>http://www.theserverside.com</link>
    <description>Most recent forum messages</description>
    <language>en</language>
    
        <generator>Jive Forums Silver 5.5.30 (www.jivesoftware.com)</generator>
    
    <pubDate>Thu, 23 May 2013 17:19:42 -0400</pubDate>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[Um, your arguments are rather all over the map on this one.  You're arguing about excessive copying and homegenous shared memory clusters and layouts of primitives.  It's a dizzying array of very different concepts!...]]></description>
        

        <pubDate>Tue, 08 Jul 2003 19:15:08 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 19:15:08 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 19:15:08 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Mike Spille</jf:author>
        <jf:replyCount>0</jf:replyCount>
    </item>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[I think some of these ideas need to be challenged a little. With objects, is page sharing (mapping pages in and out of various servers' physical address spaces using a &quot;shared memory over the network&quot; approach) the right approach? It was hard...]]></description>
        

        <pubDate>Tue, 08 Jul 2003 19:09:35 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 19:09:35 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 19:09:35 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Cameron Purdy</jf:author>
        <jf:replyCount>0</jf:replyCount>
    </item>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[<i>No, C/C++ cannot readily map objects into memory.  Yes, you can cast to a struct - and break when you upgrade compilers, change compiler switches, or try to interchange with another compiler or OS.</i>...]]></description>
        

        <pubDate>Tue, 08 Jul 2003 17:59:46 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 17:59:46 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 17:59:46 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Brian Miller</jf:author>
        <jf:replyCount>2</jf:replyCount>
    </item>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[&lt;mike&gt;
<br>Is this compared to plain old Serializable objects, or Externalizable objects? 
<br>&lt;/mike&gt;
<br>Serialization that is. 
<br>
<br>Regards,
<br>Nikita Ivanov.
<br><a href="http://www.fitechlabs.com" target="_blank">Fitech Labs.</a>]]></description>
        

        <pubDate>Tue, 08 Jul 2003 17:35:15 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 17:35:15 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 17:35:15 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Nikita Ivanov</jf:author>
        <jf:replyCount>0</jf:replyCount>
    </item>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[\Nikita Ivanov\...]]></description>
        

        <pubDate>Tue, 08 Jul 2003 17:20:00 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 17:20:00 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 17:20:00 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Mike Spille</jf:author>
        <jf:replyCount>1</jf:replyCount>
    </item>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[\Brian Miller\...]]></description>
        

        <pubDate>Tue, 08 Jul 2003 17:19:10 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 17:19:10 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 17:19:10 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Mike Spille</jf:author>
        <jf:replyCount>3</jf:replyCount>
    </item>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[&lt;cameron&gt;...]]></description>
        

        <pubDate>Tue, 08 Jul 2003 16:19:37 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 16:19:37 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 16:19:37 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Nikita Ivanov</jf:author>
        <jf:replyCount>2</jf:replyCount>
    </item>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[<i>Certainly writing out bytes yourself is usually faster, since you're hard coding the read/write code for a fixed format.</i>...]]></description>
        

        <pubDate>Tue, 08 Jul 2003 12:38:48 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 12:38:48 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 12:38:48 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Brian Miller</jf:author>
        <jf:replyCount>4</jf:replyCount>
    </item>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[Part of it is the cost of reflection on Serializable, part of it is the need to constantly flush the internal cache of written objects.  If you ensure all your objects implement Externalizable and hand code the serialization, things can be sped up by...]]></description>
        

        <pubDate>Tue, 08 Jul 2003 12:00:46 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 12:00:46 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 12:00:46 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Mike Spille</jf:author>
        <jf:replyCount>5</jf:replyCount>
    </item>


    <item>

        <title>very interesting</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[<i> FWIW - we see the most demand in financial applications, that gobble unbelievable amounts of memory and CPU power ... and have problems sets that theoretically will scale well into the thousands of CPUs in a grid. I'm talking about existing C/C++...]]></description>
        

        <pubDate>Tue, 08 Jul 2003 10:10:12 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 10:10:12 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 10:10:12 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Mark N</jf:author>
        <jf:replyCount>0</jf:replyCount>
    </item>


    <item>

        <title>ProActive</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[For this area check out:...]]></description>
        

        <pubDate>Tue, 08 Jul 2003 03:22:43 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 03:22:43 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 03:22:43 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Lofi Dewanto</jf:author>
        <jf:replyCount>0</jf:replyCount>
    </item>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[The real problem is object input and output streams. They're dogs. Like very slow dogs with bad hearts and clogged veins with their fur covered with frozen molasses. You know it's bad when you profile Java on the network and the serialization times are...]]></description>
        

        <pubDate>Tue, 08 Jul 2003 01:03:22 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 01:03:22 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 01:03:22 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Cameron Purdy</jf:author>
        <jf:replyCount>9</jf:replyCount>
    </item>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[<i>The difference is that you have to &quot;emulate&quot; shared memory with a cluster...</i>...]]></description>
        

        <pubDate>Tue, 08 Jul 2003 00:01:52 -0400</pubDate>

        

        <jf:creationDate>Tue, 08 Jul 2003 00:01:52 -0400</jf:creationDate>
        <jf:modificationDate>Tue, 08 Jul 2003 00:01:52 -0400</jf:modificationDate>
        <jf:date>Jul 8, 2003</jf:date>
        <jf:author>Brian Miller</jf:author>
        <jf:replyCount>11</jf:replyCount>
    </item>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[Several of our customers use various grid management packages, such as Platform Computing (I think that's the name?!?!) and obviously they use Tangosol Coherence for the state management / event flow etc....]]></description>
        

        <pubDate>Mon, 07 Jul 2003 20:25:11 -0400</pubDate>

        

        <jf:creationDate>Mon, 07 Jul 2003 20:25:11 -0400</jf:creationDate>
        <jf:modificationDate>Mon, 07 Jul 2003 20:25:11 -0400</jf:modificationDate>
        <jf:date>Jul 7, 2003</jf:date>
        <jf:author>Cameron Purdy</jf:author>
        <jf:replyCount>12</jf:replyCount>
    </item>


    <item>

        <title>ka-ching</title>
        <link>http://www.theserverside.com/discussions/thread.tss?thread_id=20162</link>

        

        
            <description><![CDATA[<i>FWIW - we see the most demand in financial applications, that gobble unbelievable amounts of memory and CPU power and have problems sets that theoretically will scale well into the thousands of CPUs in a grid.</i>...]]></description>
        

        <pubDate>Mon, 07 Jul 2003 18:11:44 -0400</pubDate>

        

        <jf:creationDate>Mon, 07 Jul 2003 18:11:44 -0400</jf:creationDate>
        <jf:modificationDate>Mon, 07 Jul 2003 18:11:44 -0400</jf:modificationDate>
        <jf:date>Jul 7, 2003</jf:date>
        <jf:author>Brian Miller</jf:author>
        <jf:replyCount>13</jf:replyCount>
    </item>



</channel>
</rss>

