[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
PCI I/O space on DEC Alpha machines
- To: Mailing List Recipients <pci-sig-request@znyx.com>
- Subject: PCI I/O space on DEC Alpha machines
- From: Mitch Norcross <mitch@sunsvr.Pixera.com>
- Date: Mon, 26 Aug 1996 19:02:54 -0700
- Cc: mitch@sunsvr.Pixera.com
- Organization: Pixera Corporation
- Resent-Date: Mon, 26 Aug 1996 19:02:54 -0700
- Resent-From: pci-sig-request@znyx.com
- Resent-Message-Id: <"sOf4d2.0.s77.Wcb8o"@dart>
- Resent-Sender: pci-sig-request@znyx.com
> On 23 Aug 1996, 11:32:48, Mike wrote:
> > Stephen -- Could you explain once again *why* you want
> > to put any new PCI device into IO space? I'm having
> > trouble following the thread related to your initial
> > question. If you are not a legacy device, I argue
> > that no compelling reason exists. Also what if your
> > PWB ends up in an Alpha, Power PC, etc. These *real*
> > computers don't have IO space and everything ends up
> > in memory space anyways.
I have a comment on the above, based on my experience with the
Alpha 21064/71/72 chipsets.
Alpha machines do have I/O space (PCI I/O space, that is),
they just don't have I/O instructions.
Access to PCI I/O space is provided through the core logic
chipsets by accessing certain address regions using
load/store instructions.
So, Alpha's lack of I/O instructions is not a reason
to avoid implementing I/O BARs. These machines do provide
access to PCI I/O space.
References:
http://ftp.digital.com/pub/Digital/info/semiconductor/literature/210712ds.pdf
http://www.digital.com:80/.i/info/DTJE04/DTJE04SC.TXT
/Mitch Norcross
Pixera Corporation
mitch@pixera.com
http://www.pixera.com
… ð