delorie.com/archives/browse.cgi | search |
From: | "Elias Pschernig" <f DOT x DOT gruber-museum-arnsdorf AT magnet DOT at> |
Newsgroups: | comp.os.msdos.djgpp |
Subject: | Re: Allegro : MMX or not MMX ??? |
Date: | Tue, 23 Feb 1999 18:14:46 +0100 |
Organization: | magnet Gesellschaft für digitale Kommunikation m.b.H |
Lines: | 20 |
Message-ID: | <7aunpe$p0q$1@orudios.magnet.at> |
References: | <36D01C7B DOT B72C38E3 AT club-internet DOT fr> |
NNTP-Posting-Host: | 195.3.67.112 |
X-Newsreader: | Microsoft Outlook Express 4.71.1712.3 |
X-MimeOLE: | Produced By Microsoft MimeOLE V4.71.1712.3 |
To: | djgpp AT delorie DOT com |
DJ-Gateway: | from newsgroup comp.os.msdos.djgpp |
Reply-To: | djgpp AT delorie DOT com |
>Hello everybody, > When I run allegro\tests\test.exe , the 'Profile 3D' option finds >out that the 3D routines display the same number of polygons per second >whether the 'MMX option' is enabled or not. In some cases (RGB Gouraud >Shading with 8bpp depth colors), it finds out that the MMX routines are >slower than the 'no MMX' ones. Is it normal ? > > I have a PentiumII 300MHz and when I make the Allegro library, it >confirms that my assembler supports MMX instructions ! I have enabled >the Pentium optimisations by setting PGCC to 1 in the makefile. Is there >anything else to do ? > When i enable MMX, some polygon functions are A BIT faster. (on Pentium 200 Mhz)
webmaster | delorie software privacy |
Copyright © 2019 by DJ Delorie | Updated Jul 2019 |