Re: [OT] high precision hardware (was Re: [PATCH] i386: SelectableFrequency of the Timer Interrupt)

[Christoph Lameter]

On Fri, 15 Jul 2005, Paul Jakma wrote:

> On Thu, 14 Jul 2005, Christoph Lameter wrote:
> 
> > Linux can already provide a response time within < 3 usecs from user space
> > using f.e. the Altix RTC driver which can generate an interrupt that then
> > sends a signal to an application. The Altix RTC clock is supported via POSIX
> > timer syscalls and can be accessed using CLOCK_SGI_CYCLE. This has been
> > available in Linux since last fall and events can be specified with 50
> > nanoseconds accurary.
> 
> Out of curiosity, are there any cheap and 'embeddable' linux supported
> architectures which support such response times (User or kernel space)?

Well, just implement the proper hooks for the HPET so that you can use
CLOCK_HPET from user space.

> Input comes in at anywhere from 6kHz to 100kHz (variable), (T0 say),
> requirement is to assert an output line Ta seconds after each T0, Ta needs to
> be accurate to about 6us in the extreme case (how long the output is held has
> similar accuracy requirement).

Well the interrupt latency depends on many things in the linux kernel. 
Worst case is much greater than 6us. You probably need the RT patches as 
well.
 
> What kind of hardware is capable of this? Even in microcontroller space it's
> difficult to do (eg looked at some ARM microcontrollers, which still have
> several usec of interrupt latency - even with no OS, still likely cant use
> timers and interrupts.).

Try HPET which is pretty standard these days.


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/