From: fachat (afachat_at_gmx.de)
Date: 2005-04-27 19:48:13
On Wed, Apr 27, 2005 at 06:56:48AM -0500, Jim Brain wrote:
> fachat wrote:
> >On Tue, Apr 26, 2005 at 11:17:53PM -0500, Jim Brain wrote:
> >>The only thing I think of doing is to stretch the cycle during a page
> >>fault to the maximum allowed and use another processor to do something
> >
> >Yes, I think this is the only way. Only for the 6502 you have to queue
> >the write accesses as they cannot be stretched, right?
> >
> Hmm, I was not aware writes could not be stretched, but others may have
These "unstretchable" writes are the reason why the C64 has three wait cycles
before a bad line where the CPU is haltet because the VICII must read the
character data for the line. The CPU does at most three writes in a line
(IRQ handling IIRC), so those writes are done and then the CPU is guaranteed
to have stopped, so the VICII can take over the bus only then.
Andre
Message was sent through the cbm-hackers mailing list
Archive generated by hypermail pre-2.1.8.