Date: Sun, 4 Oct 1998 12:45:47 +0300 (IDT)
From: Eli Zaretskii <eliz AT is DOT elta DOT co DOT il>
X-Sender: eliz AT is
To: "Miles F. Bintz Ii" <bintzimf AT clarkson DOT edu>
cc: djgpp AT delorie DOT com
Subject: Re: Access phys. mem above 1 meg
In-Reply-To: <Pine.A41.3.96.981001180512.88950A-100000@polaris.clarkson.edu>
Message-ID: <Pine.SUN.3.91.981004124525.1863T-100000@is>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII


On Thu, 1 Oct 1998, Miles F. Bintz Ii wrote:

> And in fact, the FAQ says this method is slow... but then later goes on to
> say that 'experience says.... its not that bad'.

It says that it is a little bit slower than nearptr, and on many
machines the difference is negligible.

> But recommends using nearptr hack if I need that additional speed.

It's the other way around: it tells you to NOT use nearptr, *unless*
you absolutely cannot make your program work without those last
tidbits of speed.

> For my "performance sensitive"
> reads/writes I will probably use a section of memory in DS and use the
> movedata function to get it out to the correct memspace.  Do you know any
> of the details on movedata?

You have free access to the sources, so you can find it out as well.

> Does this use DMA?

No.

> How is the performance of this function when moving large blocks of
> data?

Very good; it is as fast as it gets.  It moves with REP MOVSD.