Home | History | Annotate | Download | only in benchmarks 
      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 
     15 The V8 benchmark suite is changed from time to time as we fix bugs or
     16 expand the scope of the benchmarks.  Here is a list of revisions, with
     17 a description of the changes made.  Note that benchmark results are
     18 not comparable unless both results are run with the same revision of
     19 the benchmark suite.
     20 
     21 </p>
     22 <div class="subtitle"><h3>Version 7 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v7/run.html">link</a>)</h3></div>
     23 
     24 <p>This version includes the new Navier-Stokes benchmark, a 2D differential
     25  equation solver that stresses arithmetic computations on double arrays.</p>
     26 
     27 <div class="subtitle"><h3>Version 6 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v6/run.html">link</a>)</h3></div>
     28 
     29 <p>Removed dead code from the RayTrace benchmark and fixed a couple of
     30 typos in the DeltaBlue implementation. Changed the Splay benchmark to
     31 avoid converting the same numeric key to a string over and over again
     32 and to avoid inserting and removing the same element repeatedly thus
     33 increasing pressure on the memory subsystem. Changed the RegExp
     34 benchmark to exercise the regular expression engine on different input
     35 strings.</p>
     36 
     37 <p>Furthermore, the benchmark runner was changed to run the benchmarks
     38 for at least a few times to stabilize the reported numbers on slower
     39 machines.</p>
     40 
     41 <div class="subtitle"><h3>Version 5 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v5/run.html">link</a>)</h3></div>
     42 
     43 <p>Removed duplicate line in random seed code, and changed the name of
     44 the Object.prototype.inherits function in the DeltaBlue benchmark to
     45 inheritsFrom to avoid name clashes when running in Chromium with
     46 extensions enabled.
     47 </p>
     48 
     49 <div class="subtitle"><h3>Version 4 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v4/run.html">link</a>)</h3></div>
     50 
     51 <p>The <i>Splay</i> benchmark is a newcomer in version 4.  It
     52 manipulates a splay tree by adding and removing data nodes, thus
     53 exercising the memory management subsystem of the JavaScript engine.
     54 </p>
     55 
     56 <p>
     57 Furthermore, all the unused parts of the Prototype library were
     58 removed from the RayTrace benchmark. This does not affect the running
     59 of the benchmark.
     60 </p>
     61 
     62 
     63 <div class="subtitle"><h3>Version 3 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v3/run.html">link</a>)</h3></div>
     64 
     65 <p>Version 3 adds a new benchmark, <i>RegExp</i>.  The RegExp
     66 benchmark is generated by loading 50 of the most popular pages on the
     67 web and logging all regexp operations performed.  Each operation is
     68 given a weight that is calculated from an estimate of the popularity
     69 of the pages where it occurs and the number of times it is executed
     70 while loading each page.  Finally the literal letters in the data are
     71 encoded using ROT13 in a way that does not affect how the regexps
     72 match their input.
     73 </p>
     74 
     75 
     76 <div class="subtitle"><h3>Version 2 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v2/run.html">link</a>)</h3></div>
     77 
     78 <p>For version 2 the Crypto benchmark was fixed.  Previously, the
     79 decryption stage was given plaintext as input, which resulted in an
     80 error.  Now, the decryption stage is given the output of the
     81 encryption stage as input.  The result is checked against the original
     82 plaintext.  For this to give the correct results the crypto objects
     83 are reset for each iteration of the benchmark.  In addition, the size
     84 of the plain text has been increased a little and the use of
     85 Math.random() and new Date() to build an RNG pool has been
     86 removed. </p>
     87 
     88 <p>Other benchmarks were fixed to do elementary verification of the
     89 results of their calculations.  This is to avoid accidentally
     90 obtaining scores that are the result of an incorrect JavaScript engine
     91 optimization.</p>
     92 
     93 
     94 <div class="subtitle"><h3>Version 1 (<a href="http://v8.googlecode.com/svn/data/benchmarks/v1/run.html">link</a>)</h3></div>
     95 
     96 <p>Initial release.</p>
     97 
     98 </td><td style="text-align: center">
     99 </td></tr></table>
    100 
    101 </div>
    102 
    103 </body>
    104 </html>
    105