Author: Vincent Diepeveen
Date: 06:19:19 02/29/04
Go up one level in this thread
On February 29, 2004 at 07:38:34, Bo Persson wrote: >On February 28, 2004 at 10:57:28, Slater Wold wrote: > >>On February 28, 2004 at 10:51:13, Gian-Carlo Pascutto wrote: >> >>>On February 28, 2004 at 10:48:28, Slater Wold wrote: >>> >>>>Both compilers came from the DDK, and are, per MS, exactly the same. They just >>>>use different libraries. >>>> >>>>It wasn't poor testing. You just misinterpeted it. >>> >>>Microsoft (R) C/C++ Optimizing Compiler Version 14.00.2207 for AMD64 >>>Copyright (C) Microsoft Corporation 1984-2002. All rights reserved. >>> >>>Microsoft (R) 32-bit C/C++ Optimizing Compiler Version 12.00.8804 for 80x86 >>>Copyright (C) Microsoft Corp 1984-1998. All rights reserved. >>> >>>I think you're the one who misinterpreted something. >>> >>>In any case a comparison between unoptimized compiles is IMHO worthless. >>> >>>-- >>>GCP >> >>Like I said, both came with the Windows 2003 Server DDK...using the WNET >>libraries... > > >But the 12.00 compiler is what comes with the VC6.0 release. If you want maximum >speed, you would use ver 13.10 from VS .NET 2003. > >That would most likely give you the 20-25 % speedup Vincent refers to. No i'm not referring to 20-25% speedup but 250% speedup when compared to his original compile. 32 bits PGO'ed executable from crafty using intel c++ at a 2.2Ghz A64/Opteron will be getting quite a bit more than 600k nps. He compares it with a very optimized executable using AMD64 visual c++ which does not have PGO yet (version 8 hopefully will). So a) he's using -O instead of -O3 b) he's using outdated compiler c) he's using no PGO That all for a 32 bits executable. That gets compared with an optimal compiled 64 bits executable. >Bo Persson
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.