<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html; charset=ISO-8859-9"
http-equiv="Content-Type">
</head>
<body bgcolor="#ffffff" text="#000000">
On 2010-07-17 10:37, Florian Klämpfl wrote:
<blockquote cite="mid:4C415DD0.2030000@freepascal.org" type="cite">
<pre wrap="">Adem schrieb:
</pre>
<blockquote type="cite">
<pre wrap="">Windows 7, x64.
Delphi: 32-bit.
FPC: 64-bit.
</pre>
</blockquote>
<pre wrap="">So one of the most useless benchmarks I ever saw.
</pre>
</blockquote>
Focus of that 'test' was to see how TopMM compares with FastMM (both
Delphi only), which turned out that FastMM is 50% faster than
TopMemory.<br>
<br>
Which, to me at least, significantly reduces TopMM's desirability
until I find a massively threaded application to test it with.<br>
<br>
About that 64bit/32bit issue..<br>
<br>
I don't really see what all that fuss was about.<br>
<br>
Here are the timings:<br>
<br>
FPC_x64: 489.4<br>
FPC_x86: 632.7<br>
TopMM: 425.4<br>
Delphi: 304.0<br>
FastMM: 282.6<br>
<br>
And, these are the ratios:<br>
<br>
FPC_x86/FPC_x64 = 1.29<br>
FPC_x86/TopMM: 1.49<br>
FPC_x86/Delphi: 2.08<br>
FPC_x86/FastMM: 2.24<br>
<br>
Delphi/FastMM = 1.08<br>
FPC/Delphi = 1.61<br>
FPC/FastMM = 1.73<br>
FPC/TopMM = 1.15<br>
TopMM/Delphi = 1.40<br>
TopMM/FastMM = 1.51<br>
<br>
On Windows7_x64, <b>64bit binary</b> compiled with FPC runs about <b>30%
faster</b> than 32bit binary.<br>
<br>
I don't have an identical native x86 computer with Windows7_x86 to
test, sorry.<br>
<br>
<br>
<br>
</body>
</html>