<?xml version="1.0" encoding="UTF-8" standalone="yes" ?>
<!DOCTYPE bugzilla SYSTEM "https://bugs.webkit.org/page.cgi?id=bugzilla.dtd">

<bugzilla version="5.0.4.1"
          urlbase="https://bugs.webkit.org/"
          
          maintainer="admin@webkit.org"
>

    <bug>
          <bug_id>20812</bug_id>
          
          <creation_ts>2008-09-12 15:11:24 -0700</creation_ts>
          <short_desc>MASTER: Function call overhead is taking a lot of time on v8&apos;s benchmarks</short_desc>
          <delta_ts>2012-03-07 00:02:14 -0800</delta_ts>
          <reporter_accessible>1</reporter_accessible>
          <cclist_accessible>1</cclist_accessible>
          <classification_id>1</classification_id>
          <classification>Unclassified</classification>
          <product>WebKit</product>
          <component>JavaScriptCore</component>
          <version>528+ (Nightly build)</version>
          <rep_platform>Mac</rep_platform>
          <op_sys>OS X 10.5</op_sys>
          <bug_status>RESOLVED</bug_status>
          <resolution>FIXED</resolution>
          
          
          <bug_file_loc></bug_file_loc>
          <status_whiteboard></status_whiteboard>
          <keywords></keywords>
          <priority>P2</priority>
          <bug_severity>Normal</bug_severity>
          <target_milestone>---</target_milestone>
          <dependson>21295</dependson>
    
    <dependson>21296</dependson>
    
    <dependson>21317</dependson>
    
    <dependson>21319</dependson>
    
    <dependson>21364</dependson>
    
    <dependson>21396</dependson>
    
    <dependson>21541</dependson>
    
    <dependson>21583</dependson>
    
    <dependson>21584</dependson>
          <blocked>20813</blocked>
          <everconfirmed>1</everconfirmed>
          <reporter name="Maciej Stachowiak">mjs</reporter>
          <assigned_to name="Geoffrey Garen">ggaren</assigned_to>
          <cc>barraclough</cc>
    
    <cc>zwarich</cc>
          

      

      

      

          <comment_sort_order>oldest_to_newest</comment_sort_order>  
          <long_desc isprivate="0" >
    <commentid>90972</commentid>
    <comment_count>0</comment_count>
    <who name="Maciej Stachowiak">mjs</who>
    <bug_when>2008-09-12 15:11:24 -0700</bug_when>
    <thetext>Many of v8&apos;s individual benchmark tests spend a lot of time in function call overhead, including cti_op_call_JSFunction, cti_op_ret, and getCallData. It is the top issue on the Richards, DeltaBlue, and EarleyBoyer test cases.There is also some effect on Crypto and Raytrace. Shark profiles to come.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>90983</commentid>
    <comment_count>1</comment_count>
    <who name="Maciej Stachowiak">mjs</who>
    <bug_when>2008-09-12 15:55:46 -0700</bug_when>
    <thetext>See bug 20813 for Shark profiles of individual v8 tests.

Note: this should probably be broken down into separate bugs for separate tasks.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>93672</commentid>
    <comment_count>2</comment_count>
    <who name="Cameron Zwarich (cpst)">zwarich</who>
    <bug_when>2008-10-01 23:11:35 -0700</bug_when>
    <thetext>Replacing ExecState with a call frame Register pointer is bug 21295.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>93674</commentid>
    <comment_count>3</comment_count>
    <who name="Cameron Zwarich (cpst)">zwarich</who>
    <bug_when>2008-10-01 23:18:43 -0700</bug_when>
    <thetext>Removing profiling hooks when not profiling is bug 21296.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>93678</commentid>
    <comment_count>4</comment_count>
    <who name="Cameron Zwarich (cpst)">zwarich</who>
    <bug_when>2008-10-01 23:36:41 -0700</bug_when>
    <thetext>Moving toThisObject() conversion to the callee is bug 21297.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>93801</commentid>
    <comment_count>5</comment_count>
    <who name="Cameron Zwarich (cpst)">zwarich</who>
    <bug_when>2008-10-02 14:53:48 -0700</bug_when>
    <thetext>Replacing the RegisterFile size and capacity information with Register pointers is bug 21317.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>93813</commentid>
    <comment_count>6</comment_count>
    <who name="Cameron Zwarich (cpst)">zwarich</who>
    <bug_when>2008-10-02 16:05:47 -0700</bug_when>
    <thetext>Avoiding restoring the caller&apos;s &apos;r&apos; value in op_ret is bug 21319.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>94061</commentid>
    <comment_count>7</comment_count>
    <who name="Cameron Zwarich (cpst)">zwarich</who>
    <bug_when>2008-10-04 00:37:09 -0700</bug_when>
    <thetext>Removing the branch in op_ret for OptionalCalleeActivation and OptionalCalleeArguments is bug 21364.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>94208</commentid>
    <comment_count>8</comment_count>
    <who name="Cameron Zwarich (cpst)">zwarich</who>
    <bug_when>2008-10-05 22:45:54 -0700</bug_when>
    <thetext>Removing the OptionalCalleeActivation call frame slot is bug 21396.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>95236</commentid>
    <comment_count>9</comment_count>
    <who name="Cameron Zwarich (cpst)">zwarich</who>
    <bug_when>2008-10-13 17:51:11 -0700</bug_when>
    <thetext>Removing the branches for CodeBlock and CTI code in function call logic is bug 21583.</thetext>
  </long_desc><long_desc isprivate="0" >
    <commentid>572615</commentid>
    <comment_count>10</comment_count>
    <who name="Gavin Barraclough">barraclough</who>
    <bug_when>2012-03-07 00:02:14 -0800</bug_when>
    <thetext>All dependencies closed, making fixed.</thetext>
  </long_desc>
      
      

    </bug>

</bugzilla>