Harvard vs Von Neumann architecture
There are at least two different types of CPU's in terms of how they are laid out from a physical or architecture standpoint. One is referred to as the Harvard architecture and the other one is referred to as the Von Newmann or Princeton architecture. Depending on the processor, microprocessor or CPU, it is possible to have either. I'm not presently able to lecture anyone on the differences but I'm pointing out that they exist and here are the links that give further information. It is important to note that how a processor is made does change how things get done and should change the way we write programs because it is hardware specific.
http://en.wikipedia.org/wiki/Harvard_architecture
http://en.wikipedia.org/wiki/Von_Neumann_architecture
Harvard vs Von Neumann architecture
Moderators: Chuckt, Garth, bitfogav
- brad
- Site Admin
- Posts: 2578
- Joined: Fri Mar 26, 2010 10:30 pm [phpBB Debug] PHP Warning: in file [ROOT]/vendor/twig/twig/lib/Twig/Extension/Core.php on line 1266: count(): Parameter must be an array or an object that implements Countable
Re: Harvard vs Von Neumann architecture
I read up on harvard a while ago which is what (from memory) PIC microcontrollers use.
Up until I read that I just thought all cpu's worked basically the same!
Up until I read that I just thought all cpu's worked basically the same!
-
- I practically live here!
- Posts: 1127
- Joined: Sun Mar 28, 2010 1:36 pm [phpBB Debug] PHP Warning: in file [ROOT]/vendor/twig/twig/lib/Twig/Extension/Core.php on line 1266: count(): Parameter must be an array or an object that implements Countable
Re: Harvard vs Von Neumann architecture
I think all processors use Von Newman because all instructions are executed sequentially.
In terms of caches, the X86 seems to copy things from the Harvard architecture because it has two (instructions and data). I'm guessing that the Harvard architecture uses a merged address space where it was calculated (theoretical).
In terms of caches, the X86 seems to copy things from the Harvard architecture because it has two (instructions and data). I'm guessing that the Harvard architecture uses a merged address space where it was calculated (theoretical).
Who is online
Users browsing this forum: No registered users and 5 guests