One unified OS for the future?

[biggun]

Why decide between ARM and X86 at all?

Why pick one?

Linux runs on everything, UAE runs on everything.
Why would one need to focus just on one chip - makes no sense to me.


Now if you compare x86 and ARM both have their very own advantages.

1) x86 has the stronger chips
2) x86 has the more advanced company behind the,
3) arm has a compelling selling model which makes arm chips attractive for mobile devices.

ARM is not in anyway cleaner or technically better than x86.
People complaining about 16bit modes  have lost the focus for what is important.
Don't get fooled by these silly points.

What is important for a today CPU is performance per cycle and the evolution of the cache technology.
Intel is certainly very advanced here .

[biggun]

ARM can run bigendian, like m68k and like PowerPC, which simplifies things when you have an OS that is also supposed to run an integrated m68k emulator.

And the x86 has similar instructions and similar address modes as the 68K.
This will also simplify things if you want to emulate 68k.

[biggun]

I thought this discussion was about the (impossibility) possibility of a single OS that could unify the Amiga community,

There are three groups of OS developers right now.
AROS, MOS, OS4.

If you say one OS would this imply that the three groups merge their effort?
Or would this imply that one takes over the lead and the other two would die out?

[biggun]

A cross platform (and endianess) program can access memory with either big endian or little endian but only a byte at a time without byte order swapping. Without hardware byte swapping, cross platform (and endianess) programs can run significantly slower than endian specific programs that work with 4 bytes at a time using a 32 bit CPU.

Since ages (since the 486) the x86 support single instruction 32bit byte swapping to process Big Endian data.

[biggun]

If you want to take the Amiga legacy seriously - and this is the second path - then PPC, ARM and x64 are all equally unsuitable in first place. You would then need a hardware emulation(!) of the 68K and the custom chips, and probably carefully extend that with some emulation of expansion boards (like P96 for graphics). This was the idea with Natami, and the FPGA emulation. It is also an option, but goes into a different direction, namely the retro market.

Strangely enough, none of these options have been picked up by the big players.

With todays low cost FPGA you can instantiate a compatible chipset able to display FullHD
and you can instantiate an 68K core faster than 68060,  
speed wise in the range of lower PPC systems.

Maybe people want more speed than a FPGA-68K equal low end PPC would provide?

[biggun]

With money would wouldn't matter because it is perfectly possible to produce low cost / powerfull hardware with PPC cpu. It would require at least 10 000 - 15 000 mobos minium .

Well if you produce that many than there would be the funds
to also produce 68k cores which can compete with PPC systems.
Including real AMIGA chipsets again.

Right now we can with FPGA technology build 68k system
in the performance range of PowerpC Efika systems.

If you would produce around 15,000 - 20,000 systems as you describe
then you could "bake" real 68Ks including AMIGA chipset as SOC.

These systems would have the real chipset and performance
wise would be able to play in the same league as PowerPC AMIGA XE systems.

[biggun]

My perfect OS

* does not need to have 64bit pointers.

* does not need to have memory protection

* does not need to support many cores.


I actually think that AMIGA OS as it was and is -
actually is quite what I'm looking for. :-)

[biggun]

Wow Biggun, I don't know if you're trolling or just plain delusional:

Not only does AmigaOS fit that criteria, but so does CP/M, TOS and DOS. I don't see why you'd want to renounce memory protection, I mean I'd hate to have a stop error, guru meditation or what have you constantly interrupt my work and corrupt my data. Its used because often enough programmes simply aren't perfect and will happily corrupt your OS.

If your texteditor crashes then you loose your work anyhow.
Whether this is on AMIGA-OS or on UNIX it does not matter.
And memory protection does not help here.

SMP, and also threading and multiplexing are very important, simply because a single CPU can't do more than one task at a time. Multiprocessing allows for load balancing, increased CPU efficiency and less time spent switching tasks.

First of all - AMIGA OS supports threads.

Your argument is very "simple" but OK lets follow it.
Just say stop when you think you have enough CPU power

2 Cores have theoretically more power than 1
4 Cores have theoretically more power than 2
8 Cores have theoretically more power than 4
16 Cores have theoretically more power than 8
32 Cores have theoretically more power than 16
64 Cores have theoretically more power than 32
128 Cores have theoretically more power than 64
256 Cores have theoretically more power than 128
512 Cores have theoretically more power than 256
1024 Cores have theoretically more power than 512
2048 Cores have theoretically more power than 1024

Not happy yet?
Still need more?
What bloated Software do you want to run?

64-bit addressing and pointers are also important, because 4GB RAM no longer cuts it.

For all I want to do with my computer - 4 GB is enough.

[biggun]

maybe after all of that has happened, we can get a Kickstarter project started to provide the funding needed to "Bake" some new ASIC chips and increase the speed and performance of these FPGA accelerators and stand alone clones by another factor of 2x to 4x, or more.
.

The FPGA get faster every other year.
If you assume that "maybe after all of that has happened" will take a year or two.
Then simple using the new FPGA models will us a 2x performance factor.
No big fund will be needed for this.

[biggun]

That is true.  Maybe it will never be cost effective to "bake" new ASIC chips for an updated Amiga clone.

It will depend on your goal.

If you want to bring out something like "CD32-2015 edition"  which you want to sell to halve a million people then baking chips is the best way forward.

If you want to produce some 68K Amiga clones and you are satisfied with
a calculated performance of an A500 running @ 1 Giagaherz then FPGA are the easiest way for this.

[biggun]

As I said, I love people pretending their poor computing needs should be just enough for everyone.

Mind to te-read my post.

I clearly said that FOR ME PERSONALLY for my home usage.
I'm absolutely happy with 32bit pointers.

As work I use an SMT POWER8 system with 640 threads and 2 Terrabyte of main memory.
This system is nice for its purpose.

But I do not think that people need such systems at home.
And me personally surely does not need this.

What I like to do at home is:

- read emails
- listen to some mp3
- buy stuff on amazon or ebay
- chat in irc
- view some videos
- write some stuff in my favority editor = vi

For all these task more than 4GB is not needed.
If the main CPU is fast enough to decoder the video I like to watch then I also have no need for SMT.
With more cores I could not listen faster to MP3, nor faster read my emails.

These are MY personal demands. I only speak for myself and not for you.

[biggun]

This thinking is flawed. When your text editor crashes you indeed lose your work on that text editor. But your other text editors are still running and you can save your work.

No its not,

When I do stuff in parallel on AMIGA then I listen to an MP3 in the background and write some stuff in an editor.

If the MP3 player and the text editor is stable enough - then you do not need memory protection for this.

Even without memory protection my texteditor did not crash on me for years.
So I'm not missing anything here.

[biggun]

@biggun

There's a first time for everything. Perhaps one day, while writing a long document or doing your taxes, your MP3 player crashes and takes everything else with it.
Memory protection does make a huge difference.

The discussion is like talking about "seat belts".
Yes seat belts can save lives.

But I like to drive my motor bike and used to scate board when I was young.

I look at AMIGA OS as "fun" OS.
Like I look at a scate board or a motor bike.

Its fun to dirt race on the bike. And when I fall then I will fall.
Its that simple.

What I like abotu AMIGA os is that is elegant and "free" in its way to use stuff.
I can quickly hack a program together which snoops system calls.
Or which monitors the disk IO.
This is how AMIGA OS is and  I just like the way it is.

[biggun]

I talked about the choice of 32 bit 68k for the low end and 64 bit PPC for a high end Amiga with one unified API. Let's let the consumers choose:

1) 68k laptop Amiga for $1000
 o CPU speed of a Raspberry Pi or better
 o 1GB of memory
 o 40GB SSD
 o SAGA gfx with chunky
 o supports most 68k Amiga software
 o battery life of 16 hours

or

2) PPC laptop Amiga $7000
 o CPU speed of an i3 or better, 64 bit, 2-4 cores, virtualization support
 o 8GB of memory
 o 1TB hard drive
 o integrated modern gfx card
 o 68k software is sandboxed, PPC AmigaOS support is possible, no virtualization software
 o battery life of 4 hours

To be honest I find both way to expensive...

I would rather target something like this:


* 68K CPU with enhanced feature set and instruction providing multimedia acceleration
* 1 GB of fast main memory
   My design target would here by to reach 1.5 to 3.0 GB/sec memory copy speed.
   This means this 68K system would be about 10 times more powerful in memory than a PowerPC G4 Amiga.
* USB, Network and HDMI connectors
* Amiga Chipset with P96 und truecolor
* Video resolution up to full HD
* SDCard storage

We have the know-how to produce the above today.
The whole could be sold for $300-ish

[biggun]

A 68k laptop is my dream but it is quite a bit more work to make with quality and it really needs high enough production numbers to make it worthwhile. A small tower board makes more sense although it may be possible to make it in a shape that would fit in an existing laptop shell. My point with the laptops in general was to show how much more difficult and costly it would be to make a modern competitive laptop compared to a fun but still useful 68k netbook/laptop.



I think Gunnars estimates may be a little low but not that far off by looking at the Mist and fpga Arcade. I wish these boards would put more memory on board.

$300 for the system is not low.


Very similar FPGA systems as I did describe
* 1 GB memory
* video out,
*  SDCard,
and an FPGA actually twice as big
and twice as expensive as we need.

= the complete systems were sold for a retail price of $99.

This means is absolutely possible to produce such a system for less than $100.