• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

How the heck does a 32-bit CPU use 6GB of memory?

her209

No Lifer
Or am I mistaken to assume that the P4 Xeons have more than 32-bits for addressing?

2^32 = 4GB...
 
I don't know if this is done here also, but i had a microprocessor tutorial, with a cpu that could generate a 18bit address, although it had only a 16bit address bus. This was done with some extra flags.
 
They have 2 ^ 36 address since the early pentium days. I learned that last week from my CS teacher after he told us it was 2 ^ 32 the week before and then looked up some diagrams.
 
It has 36 bit virtual addressing. You can access the first 32-bit block and then have the OS switch to the next block.
 


A 32-bit processor implies 32-bit data, not 32 bit address. While the 8085 was 8-bit, addressing was 16 bit.

While 8086 was 16-bit addressing was 20-bit.


 
Originally posted by: intelbugger
A 32-bit processor implies 32-bit data, not 32 bit address. While the 8085 was 8-bit, addressing was 16 bit.

While 8086 was 16-bit addressing was 20-bit.

I just assumed that the CPU was 32-bit address because it is 32-bit data. I just think its weird to have more address lines than data lines, i.e., why make the address space longer and taking more clocks to read the same amount of data versus having a wider address space and reading more data.

I guess I stand corrected about both points.
 
Back
Top