[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: PCI Trend
- To: Mailing List Recipients <pci-sig-request@znyx.com>
- Subject: Re: PCI Trend
- From: John R Pierce <pierce@hogranch.com>
- Date: Tue, 21 Jan 1997 17:54:43 -0800
- Resent-Date: Tue, 21 Jan 1997 17:54:43 -0800
- Resent-From: pci-sig-request@znyx.com
- Resent-Message-Id: <"iKnrG2.0.m-.fGNvo"@dart>
- Resent-Sender: pci-sig-request@znyx.com
At 03:34 PM 1/21/97 -0800, Benson Cheung wrote:
Note. All answers are MY OWN PERSONAL OPINION, from the viewpoint of a
software engineer who specializes in device drivers for graphics
accelerators on mainstream PC's.
>1) Support for 64-bit PCI bus.
> (We know DEC makes 64-bit PCI-PCI
> bridge today.)
Limited primarily to non-mass market high end workstations for the
forseeable future. Perhaps some time after Merced ships (see answer to 4)
64 bit addressing will increase in importance.
>2) 66 MHz PCI bus.
> (Any 66 MHz PCI bus available now or in the future?)
The only forseeable 66MHz bus in the mass market will be the single slot AGP
bus dedicated for graphics.
>3) Is 5V-compliant important for
> a chip designed for 3V signaling
> environment?
I'm a software guy.
>4) Support for 64-bit addressing.
Intel's "Merced" P7 project is due around about then (mid 98), this will be
a true 64 bit chip supposedly. I can't see mainstream systems needing more
than 4000 Megabytes of physical memory for a few more years.
-jrp
|
j