X-Authentication-Warning:	delorie.com: mail set sender to djgpp-bounces using -f
Date:	Thu, 07 Sep 2006 09:03:52 -0700
From:	Ivor Bowden <ivorlist AT peritek DOT com>
User-Agent:	Thunderbird 1.5.0.5 (Windows/20060719)
MIME-Version:	1.0
Newsgroups:	comp.os.msdos.djgpp
Subject:	Re: 64 bit access under DOS?
References:	<44ff387a$0$19628$88260bb3 AT free DOT teranews DOT com> <edolud$a5q$1 AT main DOT corriga DOT net>
In-Reply-To:	<edolud$a5q$1@main.corriga.net>
Lines:	57
Message-ID:	<450035cf$0$19664$88260bb3@free.teranews.com>
NNTP-Posting-Date:	07 Sep 2006 15:07:59 GMT
X-Complaints-To:	abuse AT teranews DOT com
To:	djgpp AT delorie DOT com
DJ-Gateway:	from newsgroup comp.os.msdos.djgpp
Reply-To:	djgpp AT delorie DOT com

on 9/7/2006 1:38 AM PDT Rod Pemberton wrote:
> <snip>
> My understanding is that you are wanting a single 64-bit read or write on
> the actual hardware data lines, which is/should be a 64-bit data bus.

Yes, that's it exactly.

> If so, then you'll need to write your own routines using AMD64 (or
> equivalent Intel instructions depending on the CPU).

I think Intel implemented the AMD64 instruction set, so hopefully I 
won't need code conditional on the processor, except to test the 
instructions are valid.

> You'll also have to
> figure out how to use those instructions either (1) in 32-bit mode (possibly
> using instruction overrides?)

That would be best.

> or (2) by switching into and out of 64-bit
> mode without affecting executing 32-bit code such as the DPMI host or
> Windows.

That sounds difficult.

> Also, it should be possible effectively test a 64-bit read/write on a 64-bit
> bus by using two 32-bit reads/writes (_farpeekl/_farpokel) to consecutive
> addresses.  Of course, either (1) half the data lines should be activated
> for each read/write and you'd need to monitor two memory/port accesses
> instead of one

What happens is the data always takes the low path. The 32 bit address 
determines the destination. I need to test the physical high path.

> or (2) the hardware may combine both accesses into a single
> 64-bit access (bonus!).

That is what I was originally hoping for, but it doesn't happen on my 
test machine. I'd like to find a solution that has a high probability of 
working on any given machine.

> This is specific knowledge you or the manufacturer
> should have or you may be able to determine with your test equipment.
> 
> I really can't help much further.  You'll probably need to post to a few
> assembly language groups (AMD64 instructions) and a few electrical
> engineering groups (test hardware/logic analyzer) for more accurate
> answers...  For assembly, I'd try alt.lang.asm and comp.lang.asm.x86, but I
> haven't seen too many who seem to have much AMD64 knowledge.  I don't have
> any suggestions for EE groups.

Thank you for your advice!

> Rod Pemberton

Ivor Bowden

-- 
Posted via a free Usenet account from http://www.teranews.com

- Raw text -