Re[3]: Arbitration question (GNT#->FRAME# latency)

["Johnson, Ralph" <ralphj@bit3.com>]

Robert,

>     Are you sure the arbiter is not changing the GNT to a different device 
>     while a cycle is still pending.  I have seen chipsets that will give a 
>     GNT to a device while a cycle is still pending and then pull that GNT 
>     away and give the bus to the HOST-PCI bridge instead.

No, the bus was not active.  The situation I described would occur if the 
host-PCI bridge was requesting to move data across the PCI bus concurrent with 
my add-in board requesting to do the same. 

>      This is completely legal as long as the GNT is removed while another     
>      cycle is going on.

I agree.  GNT# can change state during an active bus cycle. The point I wish to 
make is that during concurrent host initiated PCI bus accesses, a PCI bus master
may encounter a one cycle GNT#.

Ralph Johnson
ralphj@bit3.com 
QTC