<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic File I/O performance - memory alignment in Intel® Integrated Performance Primitives</title>
    <link>https://community.intel.com/t5/Intel-Integrated-Performance/File-I-O-performance-memory-alignment/m-p/893538#M11802</link>
    <description>&lt;P&gt;I am testing my system performance by buffered and unbuffered sequential file reading.&lt;BR /&gt;In theory unbuffered should be faster for large files. But it should be memory aligned.&lt;BR /&gt;After reading it I want to perform IPP SplitC on the file read. The file is a comma delimited &lt;BR /&gt;text file.&lt;BR /&gt;&lt;BR /&gt;I am coding in C# and need a quick example how to do that with IPP.&lt;/P&gt;
&lt;P&gt;The reason I do that is I want get the maximum performance processing large comma &lt;BR /&gt;delimited files. There are severals choices to be made. I prefer to code in C# because it is higher&lt;BR /&gt;level than C and the project can be done faster. Also I believe .NET has many advantages wich&lt;BR /&gt;work underground. From other side I need to perform a lot of string processing after reading the file.&lt;BR /&gt;I have to compare the string processing performance of C# with IPP to decide which one is better.&lt;/P&gt;
&lt;P&gt;So as a summary I have to decide what is better performance wise:&lt;BR /&gt;1) Buffered vs Unbuffered read of large comma delimited files.&lt;BR /&gt;2) IPP SplitC vs nativeSplit C&lt;BR /&gt;3) C# vs C.&lt;/P&gt;
&lt;P&gt;Thanks in advance,&lt;BR /&gt;Constantine&lt;/P&gt;</description>
    <pubDate>Fri, 28 Nov 2008 23:25:02 GMT</pubDate>
    <dc:creator>constantine-vassilev</dc:creator>
    <dc:date>2008-11-28T23:25:02Z</dc:date>
    <item>
      <title>File I/O performance - memory alignment</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/File-I-O-performance-memory-alignment/m-p/893538#M11802</link>
      <description>&lt;P&gt;I am testing my system performance by buffered and unbuffered sequential file reading.&lt;BR /&gt;In theory unbuffered should be faster for large files. But it should be memory aligned.&lt;BR /&gt;After reading it I want to perform IPP SplitC on the file read. The file is a comma delimited &lt;BR /&gt;text file.&lt;BR /&gt;&lt;BR /&gt;I am coding in C# and need a quick example how to do that with IPP.&lt;/P&gt;
&lt;P&gt;The reason I do that is I want get the maximum performance processing large comma &lt;BR /&gt;delimited files. There are severals choices to be made. I prefer to code in C# because it is higher&lt;BR /&gt;level than C and the project can be done faster. Also I believe .NET has many advantages wich&lt;BR /&gt;work underground. From other side I need to perform a lot of string processing after reading the file.&lt;BR /&gt;I have to compare the string processing performance of C# with IPP to decide which one is better.&lt;/P&gt;
&lt;P&gt;So as a summary I have to decide what is better performance wise:&lt;BR /&gt;1) Buffered vs Unbuffered read of large comma delimited files.&lt;BR /&gt;2) IPP SplitC vs nativeSplit C&lt;BR /&gt;3) C# vs C.&lt;/P&gt;
&lt;P&gt;Thanks in advance,&lt;BR /&gt;Constantine&lt;/P&gt;</description>
      <pubDate>Fri, 28 Nov 2008 23:25:02 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/File-I-O-performance-memory-alignment/m-p/893538#M11802</guid>
      <dc:creator>constantine-vassilev</dc:creator>
      <dc:date>2008-11-28T23:25:02Z</dc:date>
    </item>
  </channel>
</rss>

