Welcome, Guest. Please login or register.

Author Topic: Coldfire status  (Read 8520 times)

Description:

0 Members and 1 Guest are viewing this topic.

Offline Karlos

  • Sockologist
  • Global Moderator
  • Hero Member
  • *****
  • Join Date: Nov 2002
  • Posts: 16882
  • Country: gb
  • Thanked: 6 times
    • Show all replies
Re: Coldfire status
« on: May 13, 2006, 11:55:40 AM »
Just to add my random thoughts....

Coldfire _in theory_ might possibly run a pretty fast 68K JIT. If you look up HP's Dynamo technology, you'll see what I mean.

Of course JIT has overheads too, transcription times being one of them, and a pretty big one for slower CPUs at that. This, however, is where the coldfire could do well in that transcription for a lot of instructions (basically all the implemented ones) wouldn't really involve much more than copying them.

This all hinges, of course, on someone having the time and skill to develop it. Oh, and it being feasable to do in the first place, which I freely admit might prove a little bit tricky :-)
int p; // A
 

Offline Karlos

  • Sockologist
  • Global Moderator
  • Hero Member
  • *****
  • Join Date: Nov 2002
  • Posts: 16882
  • Country: gb
  • Thanked: 6 times
    • Show all replies
Re: Coldfire status
« Reply #1 on: May 13, 2006, 11:59:56 AM »
Quote

Piru wrote:

Elbox also has some nice habit of using theoretical values out of context in their marketing material. For example the "266MB/s transfer speed" of the Mediator (PCI vs PCI speed is irrelevant with mediator, as the bus between the system and the pci-subsystem is ridiculously slow, and surprisingly this more important speed is not mentioned anywhere...).


Whaddaya mean? 8MB/s CPU driven transfer from system to PCI ought to be enough for anybody!

:lol: ;-)
int p; // A