Yep, wonderfull!
I really need to take the time to do my logic sim (realtime on CUDA), and try to simulate that one!

Wow, that's a huge job you made org.
I really need to learn to "read" those schematics so that I can (someday) simulate those NES chips.
(would do it at logic level, with basic gates like OR/AND/NOR/NAND/NOT ...)

I have 3 procs actually (from '84 Apple //e + '88 //e Platinum + a '86 //e Enhanced motherboard).

One is on a '86 Apple //e Enhanced motherboard: the chip is marked "Rockwell 6503 Mexico".
And I'm just discovering there have been a 6503 variation. ;)
(I suppose it's a 65C02 variation since I found ...

Yep interesting. Obviously I'm not the first that had that idea: found that first page on google --> logic.ly
Anyway, I'll do mine. I started the web site & writing a bit of computing history to start.

And I'll need someone with a good english grammar to correct the web site.
That's about computer history (and MOS & apple), so that's mainly american, so it will be in english.

Yep but I need an editor to start building the cpu, and to prepare the web site (with screenshots from it ; with working animated logics in javascript later).

The core of the simulator itself would be the easiest part I think: that would be something like 3-4 pages of C code and 2 pages of CUDA ...

I was more on the idea of redoing the 6502: reinventing it from a white page, step by step. And using basic logics (and adding a 1 pass flip-flop component) it could be optimized so it's stabilized in 14 pass (nicely fiting the 14 MHz clock). Of course I would be 99% inspired by the real thing, but ...

With some optimization of CUDA PTX ISA code, I think it could run even faster.

AND|OR|XOR|NAND|NOR gates (2 by 2)

.global .b32 pointers[2000]; # (4000 pointers pairs grouped by 2)
.global .b8 old[4000];
.global .b32 new[2000]; # (4000 values grouped by 2)

ld.global.b64 %r, pointers[index]
mov ...

Great!! Thanks!
So it's like half the gates I'll have to simulate.
Meaning even my GTX 570 could do it, with some margin.
(I could simulate a bit more chips on the motherboards then)
And I hope the reduced logic will allow the chip to stabilize in <14 pass.
(else I'll have to cheat with accelerated ...

Hi everyone. I'm new here, first post. :mrgreen:

I've just made the math quickly, and on paper, it fits!
It shall be possible to emulate the 6502 (at circuit level @ 14 MHz signaling), in realtime, using the last GeForce GTX 680 graphic card.

Image no longer available: http://www.chaunier.com ...