Menu
Search

Forums

Forum Index

Thread overview
allocated object address as high as 46th bit (i.e in the 131072 GB range)
Oct 09, 2023
mw
Oct 09, 2023
mw
Oct 11, 2023
Jerry
October 09, 2023
Gravatar of mwPosted by mwReply
mw
Gravatar of mw


Reply

https://dlang.org/library/core/bitop/bsr.html

I'm trying to find out allocated object's address' space:

import std.stdio;
import core.bitop;

void main() {
  const size_t ONE_G = 1 << 30;
  char[][128] ptrs;
  foreach (i, ref ptr; ptrs) {
    ptr = new char[ONE_G];
    if (ptr is null) {
      break;
    }
    writeln(i, ": ", bsr(cast(size_t)ptr.ptr));
  }
}

I tried on a few 64-bit machines (all of them have less than 128GB memory), and the result are about all the same:

$ uname -m
x86_64

$ ./bit_op
0: 46
1: 46
2: 46
3: 46
4: 46
5: 46
6: 46
7: 46
8: 46
9: 46
10: 46
Killed

What puzzled me is that the highest set bit of the allocated address are all 46! i.e in the in the 2^47 ~= 131072 GB range!

I know this could be an OS thing, but just wonder if anyone can give me some explanation?

Thanks.

October 09, 2023
Gravatar of Richard (Rikki) Andrew CattermolePosted by Richard (Rikki) Andrew Cattermole
in reply to mw		Reply
Richard (Rikki) Andrew Cattermole
Gravatar of Richard (Rikki) Andrew Cattermole
Posted in reply to mw


Reply
As far as I'm aware, no cpu that you can get ahold of support more than 48bit of address space at the hardware level.

There is simply no reason at this time to support more, due to the fact that nobody has implemented anywhere near that maximum.

Also worth noting, the address a block of memory is, has no relation to the hardware. A kernel will instruct the cpu to map it wherever it pleases per process.
October 09, 2023
Gravatar of mwPosted by mw
in reply to Richard (Rikki) Andrew Cattermole		Reply
mw
Gravatar of mw
Posted in reply to Richard (Rikki) Andrew Cattermole


Reply
On Monday, 9 October 2023 at 05:57:47 UTC, Richard (Rikki) Andrew Cattermole wrote:
> As far as I'm aware, no cpu that you can get ahold of support more than 48bit of address space at the hardware level.
>
> There is simply no reason at this time to support more, due to the fact that nobody has implemented anywhere near that maximum.
>
> Also worth noting, the address a block of memory is, has no relation to the hardware. A kernel will instruct the cpu to map it wherever it pleases per process.

Thanks for the info. I'm surprised that kernel set virtual space that high.
October 11, 2023
Gravatar of JerryPosted by Jerry
in reply to mw		Reply
Jerry
Gravatar of Jerry
Posted in reply to mw


Reply
The reason high bits are often set is because an address layout is actually 4 indicies into the page table and a page byte offset. So all the way to bit 48 there is index info the cpu uses.