Re: [Qemu-devel] [PATCH] 64 bit I/O support v7

[Edgar E. Iglesias]

On Tue, May 05, 2009 at 02:59:28AM +0100, Jamie Lokier wrote:
> Blue Swirl wrote:
> > - Small writes cause a read-modify-write cycle, but I think that may
> > happen with real devices too. Another solution is to write zero in
> > other byte lanes without reading.
> 
> On PCI and I think most buses, there are separate byte-enable pins for
> writing each byte lane and the hardware can decide to ignore the
> unenabled bytes or not.

>From my experience it is not uncommon for peripheral busses to
don't have the byte strobes. In fact, most (if not all) of the
embedded ones I've worked with are purely 32bit.

Cheers