From: Ludvig Larsson <ludvig AT club-internet DOT fr>
Newsgroups: comp.os.msdos.djgpp
Subject: Re: Banked vesa And another Question(as we already are here)
Date: Thu, 29 Oct 1998 05:37:33 +0100
Organization: Faas-Goldhart
Lines: 20
Message-ID: <3637F10D.6613@club-internet.fr>
References: <8D53104ECD0CD211AF4000A0C9D60AE32300CD AT probe-2 DOT Acclaim-Euro DOT net>
NNTP-Posting-Host: toulouse-camichel9-114.club-internet.fr
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Trace: front1.grolier.fr 909637507 7761 195.36.147.114 (29 Oct 1998 05:05:07 GMT)
NNTP-Posting-Date: 29 Oct 1998 05:05:07 GMT
X-Mailer: Mozilla 3.01C-CLUB  (Win95; I)
To: djgpp AT delorie DOT com
DJ-Gateway: from newsgroup comp.os.msdos.djgpp
Reply-To: djgpp AT delorie DOT com

I have read a lot of questions about bankswitching
and lineframebuffers, and everyone is either saying
that bankswitching is Sloow or won't say anything:)

I downloaded a vbe.zip example and got my lfb running,
but first, in my 640x480x16bit mode, with doublebuffer,
actually, the bankswitches doesn't eat about any time
(well, sure they do, but the time it takes to perform
these 9-10 switches is really non-performance related)
Well, the lfb then, is super slow...

I have an old Matrox Millennium(well, two years old pci etc)
and, sure, maybe I have made some stupidities in the lfb
code, but what can one expect as time to make a bankswitch
on a "normal" card?

Hope someone can help me with a figure or two(I'v read some time
ago that a bankswitch eats a houndred or so processor cycles?).

Ludvig Larsson