First to implement AAA chipset?

[freqmax]

Seems the AAA chipset is the only unreleased one with documentation. Ranger and Hombre seems to lack any documentation. So who will be first to implement AAA in hardware?

The Nyx prototype went for 2525.25 USD in april 2011..

[freqmax]

Another question.. is there even an operating system that would run on Nyx ?

[freqmax]

Guess I'm slightly curious how it "would been"
Anyway all building blocks of a core can be replaced. Just because there's AAA graphics core, doesn't hinder it's replacement with a plain "compile". Ie you can in essence select your cpu-gfx-sound combo at will.

For pure performance and compabiltity maybe it's better to plainly extend OCS/ECS/AGA modes with higher capabilities? HAM64? or planar/chunky-24, more sprites etc.

[freqmax]

SAGA but be nice, but unless the spec is released. It doesn't exist in practice for the majority.

As to what capabilities to implement. The things that ease the burden of the CPU most is the ones that should be given priority. And consideration has to be taken such that feature additions and changes won't be locked out by current API.

[freqmax]

I talk about hardware API specification, that is registers etc.. and what they do. Actual implementation is another story.

[freqmax]

Yeah, software support beyond OCS/ECS/AGA is likely almost nonexistent

[freqmax]

I doubt we will see much that bangs the hardware in the old fashioned sense, we are probably a decade to late for that to be much of a success. But I do expect SAGA to get a lot of easily converted opensource ports from linux and windows, blender, browsers, various emulators etc.

The Windows and Unix environment lacks the low latency architecture of AmigaOS because they for one thing operate in protected mode and uses kernel APIs.

Software doing the assembler pook & peek will still run circles around other other programming methods. It's rather different than "too late". If you want to put the effort in to code is another story

I think RTG might be a way around software compatibility.

What do you think of AROS 68k ?

I have the sneaking suspicion that NatAmi is going to be very expensive though.

I think it will be late to the party and expensive. And liable to any whims from Altera.

[freqmax]

There already is a bootable AROS 68k version since many months ago.

For 3D.. try OpenGL

[freqmax]

Computers for the masses (deja vu)

[freqmax]

Famicon is not an Amiga system.

[freqmax]

Adding Coldfire instructions would allow libraries of Coldfire software (often more modern than 68k code for things like audio or video processing) to be used on the Amiga. Some developers may be attracted to cheap development platforms for Coldfire or even use the whole board for small production imbedded systems or kiosks.

Makes sense!

I agree, but this is not so bad. There are some pretty powerful gfx cards that are 10 years old and the AmigaOS doesn't have much overhead when using them. I want gfx support that is well documented and easy to program which I am willing to trade for some speed.

Less is more, and a slim design might be a value on its own. Especially if one makes a laptop version. Think 10 hour laptop, because the Amiga uses less power than a PC.

One could also ask, what do we really need?, when OCS/ECS/AGA is covered, 99% of the software should work too.

I'm glad we've moved from the 68000 to the 68020. It's much more powerful and easier to program. It would be better yet with Coldfire instructions .

As a bonus the FPGA 68020 isn't limited to 68020 speed. Some previous benchmark shows FPGA-Arcade will beat a A4000T setup.

[freqmax]

Makes sense ??  By that argument add and ARM, PPC and X64 support as well

It makes sense to increase the number of instructions with ~5% from a overall compatible processor for the benefit of being able to use all the software for an additional architectecture ISA.

ARM, PPC, X64 all requires 100% instruction and design change. Coldfire is likely to not being even near.