1 |
Billy Holmes posted <4396F711.9050708@××××××.net>, excerpted below, on |
2 |
Wed, 07 Dec 2005 09:52:01 -0500: |
3 |
|
4 |
> Conway S. Smith wrote: |
5 |
>> assumption on this list, then you automatically get support for well |
6 |
>> over 4GiB of memory (I can't remember exactly how much is supported, but |
7 |
> |
8 |
> If we low ball it and just assume 48-bits are used to address memory, then |
9 |
> that's |
10 |
> |
11 |
> 256 Terabytes of RAM :) |
12 |
> |
13 |
> I think we're safe for the time being. |
14 |
|
15 |
The current AMD spec says the CPUs offer 40-bit physical memory |
16 |
addressing, 48-bit virtual memory addressing. So, 256 TB virtual memory, |
17 |
but only a terabyte physical memory, in a flat-address configuration. |
18 |
However, given that terabyte disks are only now becoming feasible, and |
19 |
thinking back to where memory was when gigabyte disks were at that stage, |
20 |
we still have several year's worth of progress before a typical |
21 |
configuration has to start worrying about that. I'm sure AMD and Intel |
22 |
will both have long addressed the problem by the time it appears, |
23 |
increasing usable physical address bitcount to 48 or higher. It's not |
24 |
like there's another barrier of similar significance to 32-bit, out until |
25 |
64-bit, which is far enough beyond current technology that it's no use |
26 |
planning beyond that, because we don't know what the rest of technology |
27 |
will look like by then, so we can't predict what the solution once that |
28 |
point is reached, might be. |
29 |
|
30 |
In the mean time, even a single TB of physical memory will be enough for |
31 |
most uses, for several years yet. In the extremes where it's not, the |
32 |
techniques for non-flat memory are well developed from 32-bit land, and |
33 |
can be used where needed. |
34 |
|
35 |
-- |
36 |
Duncan - List replies preferred. No HTML msgs. |
37 |
"Every nonfree program has a lord, a master -- |
38 |
and if you use the program, he is your master." Richard Stallman in |
39 |
http://www.linuxdevcenter.com/pub/a/linux/2004/12/22/rms_interview.html |
40 |
|
41 |
|
42 |
-- |
43 |
gentoo-amd64@g.o mailing list |