[Ffmpeg-devel] Re: [PATCH] Fix compilation when using --disable-opts

[Måns Rullgård]

Derek E. Lewis said:
> On Sun, 1 Apr 2007, M?ns Rullg?rd wrote:
>
>> I figured that's what you meant, although with a 64-bit address space
>> even truly globally unique addresses would be theoretically possible.
>> In practice there would of course be the problem of coordination.
>> Besides, no current CPUs have a full 64-bit address space.
>
> Greetings,
>
> No, this is very wrong. All MMUs on sun4u systems, since the
> UltraSPARC-III, have supported full, 64-bit address spaces. Prior to
> UltraSPARC-III (say UltraSPARC-II, which is very, very old), the address
> space had a hole, and thus only a 48-bit address space. All recent POWER
> systems that I've worked with (POWER3, POWER4, and POWER5) have full
> 64-bit address spaces, too.
>
> Just beause AMD64 doesn't have a full, 64-bit address space doesn't mean
> real hardware doesn't. :-)

I stand corrected.  I was however talking about more than x86_64.  I have used
Alpha, MIPS64, PPC and x86_64 with less than 64 bits virtual address space.

-- 
M?ns Rullg?rd
mans at mansr.com