www.delorie.com/archives/browse.cgi   search  
Mail Archives: djgpp/1998/10/18/13:04:12

Message-ID: <362A2D79.FC9223A8@mcis.de>
Date: Sun, 18 Oct 1998 19:03:37 +0100
From: Gero Timann <geti AT mcis DOT de>
Organization: MediaCompany Goe
X-Mailer: Mozilla 4.05 [de]C-NECCK (Win95; I)
MIME-Version: 1.0
Newsgroups: comp.os.msdos.djgpp
To: djgpp AT delorie DOT com
Subject: Re: UDMA <-> getting physical address of an array ?
References: <Pine DOT SUN DOT 3 DOT 91 DOT 981018134316 DOT 2705c-100000 AT is>
Reply-To: djgpp AT delorie DOT com

Hi,Hi !

I only read FAQ201 at this time, no such point found ... Oh, its in the
new FAQ211. Ok, i promise to read your newest FAQ (is 211 your newest ?)
before asking such silly questions above.

Nevertheless, many thanks for your hints. Now i have to proof, whether
i should reprogram my project in BC5 using WDOSX or not...arghh, the
windows-development-enviroment is horrible..



Regards,
Gero


Eli Zaretskii schrieb:

> On Sat, 17 Oct 1998, Gero Timann wrote:
>
> > Another point is, that there is no time to use dosmemget. Takes about
> > 100mikroseconds only for the skelett.  This is already the time i can
> > use between two samples ! No more operations possible !
> > Last night i've experimented with the farpoke-family (i've learned this
> > from a DJGPP vbe-programing-example-program). These seams the real
> > answer to my question.
>
> Unless the buffers you need to move are very small, your conclusions
> are wrong: dosmemget/put is *faster* than _farptr functions, because
> it uses REP MOVSD after some initial setup.
>
> Section 18.4 of the DJGPP FAQ list includes a detailed description of
> the different methods to move data to and from conventional memory,
> and discusses the relative merits of each method; I suggest you read
> it.
>
> > But if i know the real physical adress from an array, let a[], i
> > can fill this direct by DMA. Looks much simpler. Is this cs:<a>?
>
> No.  If anything, it should be DS, not CS.  But the only way to get
> the physical address is via the VDS API, or by using a buffer in
> conventional memory where all addresses are mapped 1:1, and so
> physical and virtual addresses are the same.
>
> > Sorry about my silly questions. But, i'm a DJGPP- and DPMI-newbe.
> > Therefore all these things looks not as simple for me as for you.
> > Let me know better ways, please.
>
> A better way is to search the FAQ.  It has DMA in the index.



--
___________________________________________________________________

Dipl.Phys.Gero Timann
Schülerstieg 20
37081 Göttingen
Germany

Tel./Fax: Germany-0551-96782
EMail:
   geti AT mcis DOT deREMOVE_THIS
   geti AT spock DOT physik3 DOT gwdg DOT deREMOVE_THIS
   geti AT online DOT deREMOVE_THIS
____________________________________________________________________

- Raw text -


  webmaster     delorie software   privacy  
  Copyright © 2019   by DJ Delorie     Updated Jul 2019