URL
https://opencores.org/ocsvn/openrisc_2011-10-31/openrisc_2011-10-31/trunk
Subversion Repositories openrisc_2011-10-31
[/] [openrisc/] [trunk/] [rtos/] [ecos-2.0/] [doc/] [html/] [ref/] [profile-functions.html] - Rev 314
Go to most recent revision | Compare with Previous | Blame | View Log
<!-- Copyright (C) 2003 Red Hat, Inc. --> <!-- This material may be distributed only subject to the terms --> <!-- and conditions set forth in the Open Publication License, v1.0 --> <!-- or later (the latest version is presently available at --> <!-- http://www.opencontent.org/openpub/). --> <!-- Distribution of the work or derivative of the work in any --> <!-- standard (paper) book form is prohibited unless prior --> <!-- permission is obtained from the copyright holder. --> <HTML ><HEAD ><TITLE >Profiling functions</TITLE ><meta name="MSSmartTagsPreventParsing" content="TRUE"> <META NAME="GENERATOR" CONTENT="Modular DocBook HTML Stylesheet Version 1.76b+ "><LINK REL="HOME" TITLE="eCos Reference Manual" HREF="ecos-ref.html"><LINK REL="UP" TITLE="Application profiling" HREF="services-profile-gprof.html"><LINK REL="PREVIOUS" TITLE="Application profiling" HREF="services-profile-gprof.html"><LINK REL="NEXT" TITLE="eCos Power Management Support" HREF="services-power.html"></HEAD ><BODY CLASS="CHAPTER" BGCOLOR="#FFFFFF" TEXT="#000000" LINK="#0000FF" VLINK="#840084" ALINK="#0000FF" ><DIV CLASS="NAVHEADER" ><TABLE SUMMARY="Header navigation table" WIDTH="100%" BORDER="0" CELLPADDING="0" CELLSPACING="0" ><TR ><TH COLSPAN="3" ALIGN="center" >eCos Reference Manual</TH ></TR ><TR ><TD WIDTH="10%" ALIGN="left" VALIGN="bottom" ><A HREF="services-profile-gprof.html" ACCESSKEY="P" >Prev</A ></TD ><TD WIDTH="80%" ALIGN="center" VALIGN="bottom" ></TD ><TD WIDTH="10%" ALIGN="right" VALIGN="bottom" ><A HREF="services-power.html" ACCESSKEY="N" >Next</A ></TD ></TR ></TABLE ><HR ALIGN="LEFT" WIDTH="100%"></DIV ><DIV CLASS="CHAPTER" ><H1 ><A NAME="PROFILE-FUNCTIONS">Chapter 52. Profiling functions</H1 ><DIV CLASS="SECT1" ><H1 CLASS="SECT1" ><A NAME="SERVICES-PROFILE-API">API</H1 ><P >In order for profile data to be gathered for an application, the program has to initiate the process. Once started, execution histogram data will be collected in a dynamic memory buffer. This data can be uploaded to a host using <SPAN CLASS="emphasis" ><I CLASS="EMPHASIS" >TFTP</I ></SPAN >. A side effect of the upload of the data is that the histogram is reset. This is useful, especially for high resolution histograms, since the histogram data are collected as 16-bit counters which can be quickly saturated. For example, if the histogram is being collected at a rate of 10,000 samples per second, a hot spot in the program could saturate after only 6.5 seconds.</P ><P > The API for the application profiling functions can be found in the file <TT CLASS="FILENAME" ><cyg/profile/profile.h></TT >.</P ><DIV CLASS="SECT2" ><H2 CLASS="SECT2" ><A NAME="SERVICES-PROFILE-API-PROFILE-ON">profile_on</H2 ><P >This function is used to initiate the gathering of the runtime execution histogram data.</P ><TABLE BORDER="5" BGCOLOR="#E0E0F0" WIDTH="70%" ><TR ><TD ><PRE CLASS="PROGRAMLISTING" >void profile_on(void *start, void *end, int bucket_size, int resolution);</PRE ></TD ></TR ></TABLE ><P >Calling this function will initiate execution profiling. An execution histogram is collected at the rate of <TT CLASS="PARAMETER" ><I >resolution</I ></TT > times per second. The area between <TT CLASS="PARAMETER" ><I >start</I ></TT > and <TT CLASS="PARAMETER" ><I >end</I ></TT > will be divided up into a number of buckets, each representing <TT CLASS="PARAMETER" ><I >bucket_size</I ></TT > program bytes in length. Using statistical sampling (via a high speed timer), when the program counter is found to be within the range <TT CLASS="PARAMETER" ><I >start</I ></TT >..<TT CLASS="PARAMETER" ><I >end</I ></TT >, the appropriate bucket (histogram entry) will be incremented.</P ><P >The choice of <TT CLASS="PARAMETER" ><I >resolution</I ></TT > and <TT CLASS="PARAMETER" ><I >bucket_size</I ></TT > control how large the data gathered will be, as well as how much overhead is encumbered for gathering the histogram. Smaller values for <TT CLASS="PARAMETER" ><I >bucket_size</I ></TT > will garner better results (<TT CLASS="FUNCTION" >gprof</TT > can more closely align the data with actual function names) at the expense of a larger data buffer.</P ><DIV CLASS="NOTE" ><BLOCKQUOTE CLASS="NOTE" ><P ><B >NOTE: </B >The value of <TT CLASS="PARAMETER" ><I >bucket_size</I ></TT > will be rounded up to a power of two.</P ></BLOCKQUOTE ></DIV ></DIV ></DIV ></DIV ><DIV CLASS="NAVFOOTER" ><HR ALIGN="LEFT" WIDTH="100%"><TABLE SUMMARY="Footer navigation table" WIDTH="100%" BORDER="0" CELLPADDING="0" CELLSPACING="0" ><TR ><TD WIDTH="33%" ALIGN="left" VALIGN="top" ><A HREF="services-profile-gprof.html" ACCESSKEY="P" >Prev</A ></TD ><TD WIDTH="34%" ALIGN="center" VALIGN="top" ><A HREF="ecos-ref.html" ACCESSKEY="H" >Home</A ></TD ><TD WIDTH="33%" ALIGN="right" VALIGN="top" ><A HREF="services-power.html" ACCESSKEY="N" >Next</A ></TD ></TR ><TR ><TD WIDTH="33%" ALIGN="left" VALIGN="top" >Application profiling</TD ><TD WIDTH="34%" ALIGN="center" VALIGN="top" ><A HREF="services-profile-gprof.html" ACCESSKEY="U" >Up</A ></TD ><TD WIDTH="33%" ALIGN="right" VALIGN="top" >eCos Power Management Support</TD ></TR ></TABLE ></DIV ></BODY ></HTML >
Go to most recent revision | Compare with Previous | Blame | View Log