Welcome, Guest. Please login or register.

Author Topic: natami  (Read 22679 times)

Description:

0 Members and 1 Guest are viewing this topic.

Offline minator

  • Hero Member
  • *****
  • Join Date: Jan 2003
  • Posts: 592
    • Show all replies
    • http://www.blachford.info
Re: natami
« on: May 20, 2012, 06:40:59 PM »
Quote from: matthey;692732
Hi Mike. First, I am not an official spokesman for the Apollo project. Gunnar has talked about releasing the Apollo core source to specific customers under a strict license (and for a hefty fee).


Does the Apollo project have licenses for all the patents it's going to be using?

Building an open source CPU is one thing, selling it is something else altogether.  If they make any money they can expect to be contacted by lawyers demanding money.

OTOH this is probably the least of their worries...

Quote
The Apollo core will have some go fast features that will take a lot of work to duplicate like pipelining, Superscaler, instruction combining, new powerful instructions and addressing modes, sophisticated instruction and data caches (including snooping), loop optimizations, branch cache and prediction, etc.


It usually takes big teams of experienced engineers years to build something like this.  I don't ever like to say never but I'm going to break that tradition by saying I predict the Apollo project will never finish a design of this complexity.


Even if they could do it - what possible reason is there for anyone to pay for it?
This thing is going to require a big, hot and expensive FPGA.  All so you run stuff slower than a $1 ARM.

It's interesting as a technical project I'm sure, but the rest strikes me as wishful thinking.
 

Offline minator

  • Hero Member
  • *****
  • Join Date: Jan 2003
  • Posts: 592
    • Show all replies
    • http://www.blachford.info
Re: natami
« Reply #1 on: May 20, 2012, 06:55:27 PM »
Quote from: AmigaClassicRule

No one told me Natami is an emulator. I thought it was real. Good thing I have an A1200 then. Paying a fortune for an emulator my seem a put off for me.


It's not an emulator in any normal sense of that word.

A traditional emulator runs 68K code by converting it into e.g. x86 code and running it on the CPU.  The hardware doesn't exist so it also has to be recreated as software and executed on the CPU.  The conversion takes time as you'd imagine so emulators that work like this tend to be slow.

In the case of Natami (or Minimig or FPGA arcade) the original 68K and custom chips have been recreated as a "description".  This description configures the FPGA to act as the 68K and custom chips.  When you run you amiga app the FPGA hardware is doing the same job as the Amiga hardware.  The FPGA executes the 68K instructions - there is no software conversion involved.