Re: MISC-d Digest V97 #46

[jfox@xxxxxxxx (Jeff Fox)]

>Could someone offer an explanation of why a JUMP in the video coprocessor
>takes "zero time"?  Some sort of smart prefetch?
>
>Thanks.
>
>-Dave

Dear MISC readers:

The "zero time" description is a little misleading.  It takes zero time
in the sense that jumps force the video coprocessor to fetch and
execute two instructions on the same coprocecessor clock input.  So
a video jump and the next instruction that follow it both execute
at the speed of a normal single video coprocessor instruction.  It
doesn't take zero time in the real world, but what happens is that
the video jump happens in between the timed pixel instructions.  In
that sense it takes zero time since the pixel instructions appear
to happen at the regular timing sequence and the jump is forced
to happen between them.

It does take up memory bandwidth and time on the bus.   But from the
viewpoint of the timing of pixels a video jump takes zero time.  This
is why a video jump must not to another video jump.

Jeff Fox              jfox@dnai.com    
Ultra Technology Inc. http://www.dnai.com/~jfox/