Thank you David for your email.
> > I have been told that using gcc will reduce
> > the efficiency of the embedded system (these comments have come from
> > compiler developers).
>
> AFAIK, this depends on the target architecture. gcc was designed for real
> CPUs with lots of generic (=usable!) registers, while the x86 architecture
> is severely crippled with it's 8 halfway generic regs, especially from the
> compiler POV. It's not all that bad really, and you can help the compiler a
> little by avoiding constructs that need more temporary variables than there
> are regs (ie x86 C source optimization), but there are compilers that
> generate faster code for the x86.
The reason that I consider x86 is to get something working as quickly as
possible and as cheaply as possible. I figure that using an x86 would be one
of the cheapest solutions. I may be wrong, especially if I then require extra
chips for interrupt handling.
> > The idea of having everything on one board is to reduce latency and the
> > complexity of ISA or PCI buses. Also I aim to reduce the delay getting
> > data from the A/Ds normally experienced. A ROM will be used to boot the
> > system.
>
> Are you going to use some kind of local bus construct for the stuff that's
> normally on the ISA, or is the ISA going to run out of spec? The latter
> seems easier as standard chipset parts can be used, but it's asking for
> trouble if the "turbo-ISA" is exposed on some bus where people can connect
> standard stuff. I've had trouble with some old ISA boards and the modern PCs
> that overclock the ISA by default (to speed up the on-board ISA stuff, I
> guess), so this problem seems rather real to me...
It's still early days so I haven't figured out the details.
One of the main delays I want to avoid is getting data from the A/Ds.
currently I'm using a couple of C40s, and I have to slow down the bus speed
(currently using 5 wait states) to get the data from the analogue or digital
I/O boards. With a 10kHz sample rate I don't get much time to move data over
the backplane so I figure that I could do it faster with the chips closer
i.e. on the main board. Again, I'm not sure of the details.
--
Andrew Tuckey
Postdoctoral Research Scientist
Eindhoven University of Technology
EE Dept., Group EMV, Room EL 1.13
PO Box 513 Phone: +31 - 40 2 47 3895
5600 MB EINDHOVEN Fax: +31 - 40 2 43 4364
The Netherlands Email: [EMAIL PROTECTED]
-- [rtl] ---
To unsubscribe:
echo "unsubscribe rtl" | mail [EMAIL PROTECTED] OR
echo "unsubscribe rtl <Your_email>" | mail [EMAIL PROTECTED]
---
For more information on Real-Time Linux see:
http://www.rtlinux.org/rtlinux/
