Re: Tuple and changes for m68k with -malign-int
On Wed, 21 May 2025, I wrote:
>
> On Wed, 21 May 2025, John Klos wrote:
>
> > Likewise, do you really think that the overhead of unaligned access is
> > outweighed by the fact that more stuff fits in the cache? Seriously?
> >
>
> Yes, some of my 68030 systems have 16-bit data busses.
>
For the record, the user manuals say the entries in the 68020 and 68030
caches are long-words. So a 16-bit data bus would be a liability for
accesses involving the caches, and John's probably right about overhead.
Reply to: