1<html> 2<head> 3<title>V8 Benchmark Suite Revisions</title> 4<link type="text/css" rel="stylesheet" href="style.css" /> 5</head> 6<body> 7<div> 8 <div class="title"><h1>V8 Benchmark Suite Revisions</h1></div> 9 <table> 10 <tr> 11 <td class="contents"> 12 13<p> 14 15The V8 benchmark suite is changed from time to time as we fix bugs or 16expand the scope of the benchmarks. Here is a list of revisions, with 17a description of the changes made. Note that benchmark results are 18not comparable unless both results are run with the same revision of 19the benchmark suite. 20 21</p> 22 23<div class="subtitle"><h3>Version 6 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v6/run.html">link</a>)</h3></div> 24 25<p>Removed dead code from the RayTrace benchmark and fixed a couple of 26typos in the DeltaBlue implementation. Changed the Splay benchmark to 27avoid converting the same numeric key to a string over and over again 28and to avoid inserting and removing the same element repeatedly thus 29increasing pressure on the memory subsystem. Changed the RegExp 30benchmark to exercise the regular expression engine on different input 31strings.</p> 32 33<p>Furthermore, the benchmark runner was changed to run the benchmarks 34for at least a few times to stabilize the reported numbers on slower 35machines.</p> 36 37<div class="subtitle"><h3>Version 5 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v5/run.html">link</a>)</h3></div> 38 39<p>Removed duplicate line in random seed code, and changed the name of 40the Object.prototype.inherits function in the DeltaBlue benchmark to 41inheritsFrom to avoid name clashes when running in Chromium with 42extensions enabled. 43</p> 44 45<div class="subtitle"><h3>Version 4 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v4/run.html">link</a>)</h3></div> 46 47<p>The <i>Splay</i> benchmark is a newcomer in version 4. It 48manipulates a splay tree by adding and removing data nodes, thus 49exercising the memory management subsystem of the JavaScript engine. 50</p> 51 52<p> 53Furthermore, all the unused parts of the Prototype library were 54removed from the RayTrace benchmark. This does not affect the running 55of the benchmark. 56</p> 57 58 59<div class="subtitle"><h3>Version 3 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v3/run.html">link</a>)</h3></div> 60 61<p>Version 3 adds a new benchmark, <i>RegExp</i>. The RegExp 62benchmark is generated by loading 50 of the most popular pages on the 63web and logging all regexp operations performed. Each operation is 64given a weight that is calculated from an estimate of the popularity 65of the pages where it occurs and the number of times it is executed 66while loading each page. Finally the literal letters in the data are 67encoded using ROT13 in a way that does not affect how the regexps 68match their input. 69</p> 70 71 72<div class="subtitle"><h3>Version 2 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v2/run.html">link</a>)</h3></div> 73 74<p>For version 2 the Crypto benchmark was fixed. Previously, the 75decryption stage was given plaintext as input, which resulted in an 76error. Now, the decryption stage is given the output of the 77encryption stage as input. The result is checked against the original 78plaintext. For this to give the correct results the crypto objects 79are reset for each iteration of the benchmark. In addition, the size 80of the plain text has been increased a little and the use of 81Math.random() and new Date() to build an RNG pool has been 82removed. </p> 83 84<p>Other benchmarks were fixed to do elementary verification of the 85results of their calculations. This is to avoid accidentally 86obtaining scores that are the result of an incorrect JavaScript engine 87optimization.</p> 88 89 90<div class="subtitle"><h3>Version 1 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v1/run.html">link</a>)</h3></div> 91 92<p>Initial release.</p> 93 94</td><td style="text-align: center"> 95</td></tr></table> 96 97</div> 98 99</body> 100</html> 101