my next "spare time" project....
Wallace White
wallace at stanfordalumni.org
Mon May 14 08:32:12 EDT 2001
"Mark L. Chang" wrote:
>
> A little looking around and it seems that some tests have shown kernel
> blocking times for interrupts (ie. when the kernel can't service any
> interrupts) on the order of 150us if things are done smartly. This goes
> down to around 100us or so for RAM-based filesystems.
100 us? File systems? Get rid of the operating system, guys, and you can
do this job properly, with latencies of less than 10 us.
You really don't need a PC to run a car. You need an embedded
microcontroller, like the Hitachi unit in our 5kcstq's. Take a look at
www.microchip.com and you'll find a PIC with enough A/D lines and
general I/O. I'd be happy to help you find one that fits, if you'd like.
And you set up only the interrupts you want, if any.
You'd still need to do a lot of testing before you could feel safe
running a car off our own code, but you'd never have to reboot it.
- Wallace
'87 5kcstq 173k
More information about the quattro
mailing list