NatAmi 68070 design draft

[Plaz]

@bloodline

like just how suited the Coldfire actually is to running 68k code

You're correct, it isn't. That's why you put in the JIT.

You are suggesting a symmetric design, which is expensive for this...

Not so sure. Not in CPU's anyway. 166/V2's about $20US each. 200/V4e's About $32US each. 68060 if you can find new stock....$500US. Coding bios an glue logic for a card is where the time would be spent though.

Plaz

[bloodline]

HenryCase wrote:

bloodline wrote:
NATAMI is anything but elegant... the Amiga was an elegant solution to the computing problems of the mid 80's... Take any generic mainstream PC/Mac/whatever and it will be far more elegant a solution to the modern computing environment than an weird Amiga like kludge...

You and I have different interpretations of the word 'elegant' it seems. I am looking from the perspective of less bottlenecks in the system, which the PC/Mac/whatever have. What's the point of all that CPU power if you can't use it to its full potential? Why use the CPU for everything when co-processors can do a better job? As I said PC architecture is moving in the co-processor direction (and has been for a while now) but it's not quite where I'd like it to be yet.

There are more "Co-Processors" in even a 10 year old PC than there ever was in the Amiga...

I would love for you to list these "bottlenecks", that PC's have... I can think of plenty present in the AGA chipset, off the top of my head...

bloodline wrote:
A5000 is a bit of a meaningless idea, But I do understand that it would have been nice to see what could have been... but as the great Dave Haynie has pointed out, The future of Amiga development would have moved to off the shelf parts... AAA was OK, in 93... but nothing but a joke by 97...

AAA != SuperAGA, but I see where you're going by mentioning it.

Personally I have no issue with the PARISC strategy that was planned for the new Amiga CPU, as at least the 68k functions could have been built in to the new CPU core.

That was NYX, that was not Amiga compatible, it was a totally new architecture... I was meant to replace the Amiga, though Chris Ludwig did mention that AmigaOS would have been ported to it, the main OS would have been WinNT... Had commodore started on NYX earlier and got it going, then it might have push Commodore ahead again like the Amiga did al those years before...

 However, if Commodore were planning on going with all off the shelf parts then I'm glad they fell on their arse when they did because they clearly didn't see the unique benefits of the Amiga architecture.

Moving to off the shelf parts would have been a lazy attempt to renovate the platform to make up for the years they wasted by not investing highly in R&D.

Yes, that's right... and it was the only realistic solution after they failed to capitalise on the Amiga technology....We should have been phasing the AGA chipset out by 1990... perhaps with something like AAA filling the gap until something like NYX could be brought to market by 1992...

Using your same Dave Haynie AAA reference 'it would have been revolutionary if released in 1990'. Commodore had 5 years to get from OCS to AAA, which is plenty of time IF they properly invested in R&D.

Yes, that's sad. But that's what happened and the rest of the world moved on!

[HenryCase]

bloodline wrote:
Have you noticed that we have gone from lots of different CPU architectures, to basically just 2... the x86 and the ARM... Yes, the PPC is clinging on too... I think you would be hard push to justify why you didn't use either the x86 or the ARM in a new design... And I think you would, probably kiss your job as a chip/system designer goodbye if you choose something other than x86, ARM or PPC in your system...

There simply isn't the investment in software to justify building a system built around the 68k...

There are plenty of different CPU architectures out there. Whilst I concur that the biggest players in the consumer CPU architecture market are x86/x64 and ARM, that doesn't stop companies using other architectures where appropriate.

bloodline wrote:
Why would any company be interested in a weird, slow, incompatible and expensive design... where is the value in that? How can you sell that to anyone?

Aah, I'm starting to see where you're getting confused now...

bloodline wrote:
By which time, your Average PC will be 20 times more powerful!

I have nothing against NATAMI, but you need to be realistic in what can be achieved!

I'm trying to be realistic in what the Natami can achieve, believe me there are people much more fanatical about the Natami in the Amiga community than me.

I think the reason we're not seeing eye to eye on this is because you think I expect the Natami to compete in the modern PC market. I do not. I do not expect to see it on the shelves of shops (at least not unless an outside company takes a liking to the N68070/SuperAGA chip, for mobile phones for instance). I expect it to be a successful product in the Amiga market, maybe drawing back a few old Amiga users and a few developers interested in retro hardware (demoscene coders for example) but not reviving the commercial viability of the platform.

The Natami is an ambitious hobby project and we have nothing to lose by giving the Natami developers our support. If the N68070 never sees the light of day at least we should have the Natami60 to play around with.

[bloodline]

Plaz wrote:
@bloodline

like just how suited the Coldfire actually is to running 68k code

You're correct, it isn't. That's why you put in the JIT.

No, I mean running a sequence of coldfire instructions that perform the same function as the missing 68k instruction... it's not a simple 1 to 1 mapping... The 68k Addressing modes can require a huge amount of additional logic and arithmetic code to emulate and we haven't even covered Flag calculation... The 68k is horrible to Emulate... that's why you need something big and powerful like the x86 :-)

You are suggesting a symmetric design, which is expensive for this...

Not so sure. Not in CPU's anyway. 166/V2's about $20US each. 200/V4e's About $32US each. 68060 if you can find new stock....$500US. Coding bios an glue logic for a card is where the time would be spent though.

But two coldfires emulating a single 68k, at a speed, perhaps as fast as a 40Mhz 68040... really why bother at this point? Just buy a cheap PC (£250 including everything including a monitor!) and run WinUAE...

[HenryCase]

bloodline wrote:

Using your same Dave Haynie AAA reference 'it would have been revolutionary if released in 1990'. Commodore had 5 years to get from OCS to AAA, which is plenty of time IF they properly invested in R&D.

Yes, that's sad. But that's what happened and the rest of the world moved on!

Not all of us, evidently. ;-)

[sdyates]

AmiBoy wrote:
For anyone who is interested in the NatAmi (like me) Gunnar has released an early draft on the 68070 processor they are hoping to implement in the model after the 060 equipmed Dev Board.

I dont really undrerstand any of it but I thought some of the more technical minded people on here might want to take a look!

http://www.natami.net/knowledge.php?b=4¬e=642

I don't get it either: i just prefer the executive summary

I thought they were making an entire machine...

[bloodline]

HenryCase wrote:

bloodline wrote:
Have you noticed that we have gone from lots of different CPU architectures, to basically just 2... the x86 and the ARM... Yes, the PPC is clinging on too... I think you would be hard push to justify why you didn't use either the x86 or the ARM in a new design... And I think you would, probably kiss your job as a chip/system designer goodbye if you choose something other than x86, ARM or PPC in your system...

There simply isn't the investment in software to justify building a system built around the 68k...

There are plenty of different CPU architectures out there. Whilst I concur that the biggest players in the consumer CPU architecture market are x86/x64 and ARM, that doesn't stop companies using other architectures where appropriate.

I'm talking about general purpose CPU architectures... i.e. the market that the 68k was designed for...

There is basically either an x86 or an ARM that fits into any market and price point now, that needs a general purpose CPU... And you are talking to a MIPS fan here...

bloodline wrote:
Why would any company be interested in a weird, slow, incompatible and expensive design... where is the value in that? How can you sell that to anyone?

Aah, I'm starting to see where you're getting confused now...

bloodline wrote:
By which time, your Average PC will be 20 times more powerful!

I have nothing against NATAMI, but you need to be realistic in what can be achieved!

I'm trying to be realistic in what the Natami can achieve, believe me there are people much more fanatical about the Natami in the Amiga community than me.

But I doubt they are able to see the flaws in their thinking....

I think the reason we're not seeing eye to eye on this is because you think I expect the Natami to compete in the modern PC market. I do not. I do not expect to see it on the shelves of shops

Woah!!! Hang on there!!!! One step at a time... We've not got that far yet! We still have to sell this idea to an investor before we can manufacture it...

(at least not unless an outside company takes a liking to the N68070/SuperAGA chip, for mobile phones for instance).

Ok, give me one thing that N68070/SuperAGA has over an StrongARM/PowerVR chip (i.e. the chipset in the iPhone)?

 I expect it to be a successful product in the Amiga market, maybe drawing back a few old Amiga users and a few developers interested in retro hardware (demoscene coders for example) but not reviving the commercial viability of the platform.

The MiniMig was good in the Amiga Market, it was a cheap, simple design and generally compatible with most existing software.

The NATAMI is looking to be expensive and incompatible with features that are not required by the amiga software base.... How do you sell this to an investor?

The Natami is an ambitious hobby project and we have nothing to lose by giving the Natami developers our support. If the N68070 never sees the light of day at least we should have the Natami60 to play around with.

The NATAMI is a fun hobby project, really good... but I really can't be much more... the N68070 is totally pie-in-the-sky, I would suggest the originators of the idea do a lot of reading...

[Plaz]

The 68k Addressing modes can require a huge amount of additional logic and arithmetic code to emulate and we haven't even covered Flag calculation

There's only about 12 instructions to deal with. You just never know when their going to hit the CPU though. The coldfire is a 68K core and about 99.2% compatible with 68x00. The trouble comes when one of thes dozen instructions does a diffent task on the CF than it does on the cold fire. Supervisor mode can capture and redirect invalid instructins to a lib where software takes care of it. However, these few instructions are not invalid and can't be trapped that way. You have to intercept them some how. If you have to intercept a few, you're just as well off intercepting them all with a fast JIT. IO is another problem. V2 is very pin compatible, but slow. V4 is much faster, but not IO compatible. So... to be more specific on my idea. V4 to do JIT to handle invalid instructions, and "feed" the V2 to handle buss IO and execute program code.

All good conversation, but obviouly going nowhere unless I win the lottery this week :-P

Just buy a cheap PC (£250 including everything including a monitor!) and run WinUAE

Not any cheaper than a new card if some one can come up with one. PC emulation is a perfect idea for some things, but I can't run all my hardware. For video and music studio work I might as well just stick with my XP and all the USB hardware. As long as emulation is just amiga "running in a vacuum" it's not useful to me. It all comes back to... no hardware. Ok I'm depressed now. Time to go work on the toaster/flyer box.

Plaz

[HenryCase]

I'm talking about general purpose CPU architectures... i.e. the market that the 68k was designed for...

There is basically either an x86 or an ARM that fits into any market and price point now, that needs a general purpose CPU... And you are talking to a MIPS fan here...

But 68k does fit in the Amiga market. The Natami is not aiming to be some PC killer, but rather a supercharged classic Amiga.

But I doubt they are able to see the flaws in their thinking....

I don't know if that was meant to be a sly dig at me or not but I personally I think I'm fairly willing to admit when I've got something wrong.

Ok, give me one thing that N68070/SuperAGA has over an StrongARM/PowerVR chip (i.e. the chipset in the iPhone)?

It will have me coding for it. ;-)
In all seriousness, it's clear that software is the thing that drives computer sales. From a technical perspective I think the N68070/SuperAGA chip would work well in a mobile phone. The software is another matter. The direction of the commercial Natami will largely be determined by the Natami60 software developers.

The NATAMI is looking to be expensive and incompatible with features that are not required by the amiga software base.... How do you sell this to an investor?

With a library of Natami60 apps and games. I personally don't see any investors coming from outside the Amiga community, but who knows.

bloodline wrote:
The NATAMI is a fun hobby project, really good... but I really can't be much more... the N68070 is totally pie-in-the-sky, I would suggest the originators of the idea do a lot of reading...

As I've said, the N68070 is a fairly new idea. I'm glad you approve of the Natami as a fun hobby project. The best way we have to ensure we see this hobby project succeed is to give our advice and support to the Natami team, so what would you add/change in the current N68070 design brief?

[Crumb]

Something as complex as a 68k CPU is never going to get even 20Hmz real speed on an FPGA... I'd be surprised if that to be honest...

Tobiflex m68k core is faster than a 20Mhz 68000 with a DE-1 board.

[HenryCase]

Crumb wrote:

Something as complex as a 68k CPU is never going to get even 20Hmz real speed on an FPGA... I'd be surprised if that to be honest...

Tobiflex m68k core is faster than a 20Mhz 68000 with a DE-1 board.

I'm pretty sure 20Mhz is a typo, it should say 200MHz, though thanks for the information about Tobiflex's 68k core.

[bloodline]

Plaz wrote:

The 68k Addressing modes can require a huge amount of additional logic and arithmetic code to emulate and we haven't even covered Flag calculation

There's only about 12 instructions to deal with. You just never know when their going to hit the CPU though. The coldfire is a 68K core and about 99.2% compatible with 68x00. The trouble comes when one of thes dozen instructions does a diffent task on the CF than it does on the cold fire. Supervisor mode can capture and redirect invalid instructins to a lib where software takes care of it. However, these few instructions are not invalid and can't be trapped that way. You have to intercept them some how. If you have to intercept a few, you're just as well off intercepting them all with a fast JIT. IO is another problem. V2 is very pin compatible, but slow. V4 is much faster, but not IO compatible. So... to be more specific on my idea. V4 to do JIT to handle invalid instructions, and "feed" the V2 to handle buss IO and execute program code.

All good conversation, but obviouly going nowhere unless I win the lottery this week :-P

Well lets hope you win that lottery... but in the mean time...

I've spent a fair bit of time reading the tech docs for the Coldfire and it is missing quite a bit, instructions are one thing, but addressing modes are the bane of RISC designs and expunged.

Yes, a JIT is the best way to run 68k code on the Coldfire... but the Coldfire is not a instruction munching monster... it derives it's performance from not having to execute the CISC baggage of the 68k... once the 68k code has con through the JIT all that baggage is added back in...

The supervisor mode of the Coldfire is totally different to the 68k... this means no AmigaOS... your best bet then is to use AROS...

Just buy a cheap PC (£250 including everything including a monitor!) and run WinUAE

Not any cheaper than a new card if some one can come up with one. PC emulation is a perfect idea for some things, but I can't run all my hardware. For video and music studio work I might as well just stick with my XP and all the USB hardware. As long as emulation is just amiga "running in a vacuum" it's not useful to me. It all comes back to... no hardware. Ok I'm depressed now. Time to go work on the toaster/flyer box.

Plaz

I was in a similar situation about 10 years ago... when I needed to keep up with the Music technology curve and the Amiga just wasn't cutting it... My Amiga has been relegated to old synth/effect module status... rather than the centrepiece it once was.

[bloodline]

HenryCase wrote:

I'm talking about general purpose CPU architectures... i.e. the market that the 68k was designed for...

There is basically either an x86 or an ARM that fits into any market and price point now, that needs a general purpose CPU... And you are talking to a MIPS fan here...

But 68k does fit in the Amiga market. The Natami is not aiming to be some PC killer, but rather a supercharged classic Amiga.

This isn't really an Amiga market anymore... there a retro/hobbyist market, and they aren't interested in something a bit compatible with the Amiga... They want to run their old Amiga software, they don't need or want a 9Ghz 68k...

But I doubt they are able to see the flaws in their thinking....

I don't know if that was meant to be a sly dig at me or not but I personally I think I'm fairly willing to admit when I've got something wrong.

I'm not bothering with sly digs tonight! :-)

Ok, give me one thing that N68070/SuperAGA has over an StrongARM/PowerVR chip (i.e. the chipset in the iPhone)?

It will have me coding for it. ;-)

Have you downloaded the iPhone SDK... it's pretty cool... I bet you'd love it even more than Amiga :-o

In all seriousness, it's clear that software is the thing that drives computer sales.

There is nothing else that drives computer sales... Take the iPhone for example, the hardware was pretty unimpressive... but the software was totally innovative...

From a technical perspective I think the N68070/SuperAGA chip would work well in a mobile phone.

That is delusional... it would be expensive, use too much power, get too hot, offer hardly any features of competing hardware and no way could anyone ever afford to have it fabbed at a process small enough to make it fit in a mobile.

The software is another matter. The direction of the commercial Natami will largely be determined by the Natami60 software developers.

:-?

The NATAMI is looking to be expensive and incompatible with features that are not required by the amiga software base.... How do you sell this to an investor?

With a library of Natami60 apps and games.

Your business model is technically "The Underpants Gnomes Model"

 I personally don't see any investors coming from outside the Amiga community, but who knows.

Well, go on... sell it to me...

bloodline wrote:
The NATAMI is a fun hobby project, really good... but I really can't be much more... the N68070 is totally pie-in-the-sky, I would suggest the originators of the idea do a lot of reading...

As I've said, the N68070 is a fairly new idea. I'm glad you approve of the Natami as a fun hobby project.

Well.. I am an Amiga guy... just a realistic one...

The best way we have to ensure we see this hobby project succeed is to give our advice and support to the Natami team, so what would you add/change in the current N68070 design brief?

Everything... :-(

[bloodline]

Crumb wrote:

Something as complex as a 68k CPU is never going to get even 20Hmz real speed on an FPGA... I'd be surprised if that to be honest...

Tobiflex m68k core is faster than a 20Mhz 68000 with a DE-1 board.

Yeah, and really how fast does it actually run?

[Pyromania]

I still think the NatAmi should have one Zorro slot and a video slot so the Video Toaster 4000 & Flyer card can work in it. Maybe the next version?

[amigadave]

bloodline wrote:

Crumb wrote:

Something as complex as a 68k CPU is never going to get even 20Hmz real speed on an FPGA... I'd be surprised if that to be honest...

Tobiflex m68k core is faster than a 20Mhz 68000 with a DE-1 board.

Yeah, and really how fast does it actually run?

Well with all that positive energy, it is sure to do well!

I am hoping that the NatAmi team does not give up when they come across a few tough obstacles and is able to prove the "Nay Sayer's" all wrong and come out with an improved Amiga 68k design that does indeed run faster than any existing Classic Amiga.

Why spend so much energy telling people that their plans are impossible when such a project would be a benefit to the Amiga community?  

And, for the person who wrote that no one in the Amiga community wants a super 68k and super AGA, WRONG!  That is exactly what I would like to have.  A 200-400mHz 68040/68060 with Super AGA or AAA that is fully backward compatible with AGA and ECS, OCS software.

You can have your PPC AmigaOne and OS4.0, I would rather spend my time working on and with OS3.x and what might be possible with the NatAmi.

As a commercial project, it may not succeed as there are not enough people that will purchase it, or enough developers that will write programs for it.

I'm too tired to rant any further.