MiniMig with AGA

[MskoDestny]

Um, y'all do know that the v3 and higher coldfire chips are faster and cheaper than all of those 68Ks, and can translate whichever core you want to use just by changing out the library you use in the boot ROM, right?

It's been a long time since I last looked at this, but the v3 isn't fully compatible even with the emulation library for missing instructions (for instance, I believe it only has a single stack pointer whereas the 68K has separate stack pointers for system and user mode). v4e + the emulation traps is probably close enough for most things though.

That said,  emulating instructions via traps is expensive, especially on moderned pipelined architectures like ColdFire. I haven't seen any solid numbers on what the performance hit is, but from the impressions I get it's substantial enough to wipe out most if not all of the performance gains over a 68060 and maybe even less powerful members of the 68K family. If AROS had a working Amiga 68K port, it might make more sense. Then at least the OS and libraries could all be compiled for native Coldfire and only legacy apps would end up triggering the traps. The Atari folks are working on some hardware that would be suitable for a ColdFire based Amiga clone: http://acp.atari.org/ It looks like it has a fairly large FPGA so I imagine it should have plenty of room for an AGA implementation, TG68 core for a compatibility mode and whatever extra features one might like to add.

Of course, if I understand some screenshots made by Tobias from the thread linked earlier, it seems that TG68 can beat out an 030 just by virtue of being clocked so much higher. It would seem that with a more modern design (TG68 is designed to be cycle accurate to a 68000 for most byte and word width instructions from what I understand) smoking a 68060 in a reasonably attainable FPGA should be quite possible.

[kolla]

Um, y'all do know that the v3 and higher coldfire chips are faster and cheaper than all of those 68Ks

Not quite true, the cheapest coldfires are still twice the price of the typical 68000s.

[Dr_Righteous]

@kolla - No, the original purpose of the minimig was an A4000 clone, but Dennis had to start somewhere. Besides I was responding to the 020 and 030 posts. A MCF5407CAI220 is about US$26, vs $40-65 for the 020 or 030.

@MskoDestny - ...and at 220MHz I seriously doubt those traps would slow it down enough to even notice. The remainder of the coldfire's core is still 68K instruction compatable. The benefit I see is being able to select the CPU you want to emulate for maximum compatability and performance. Hell, make it a menu in the boot ROM. Before you load the library, select the CPU for this session.

[kolla]

Who am I to argue with Dr Righteous  :rolleyes:

[countzero]

@kolla - No, the original purpose of the minimig was an A4000 clone, but Dennis had to start somewhere.

you're making this up. MiniMig was intended to be a A500 clone, nothing more, nothing less.

http://www.techtravels.org/amiga/minimig/weeren001/minimig.html

@MskoDestny - ...and at 220MHz I seriously doubt those traps would slow it down enough to even notice. The remainder of the coldfire's core is still 68K instruction compatable. The benefit I see is being able to select the CPU you want to emulate for maximum compatability and performance. Hell, make it a menu in the boot ROM. Before you load the library, select the CPU for this session.

Coldfire route had been taken before, and it ended in disaster. Not much sense in discovering the wheel again. But of course you're free to make your own coldfire based board and put the world to shame :afro:

[MskoDestny]

@MskoDestny - ...and at 220MHz I seriously doubt those traps would slow it down enough to even notice. The remainder of the coldfire's core is still 68K instruction compatable.

I think you greatly underestimate the cost of all those traps. There are a number of commonly used 68K instructions and addressing modes that ColdFire doesn't support even in the v4e version. Something as simple as add.w would need to be emulated with a trap (ColdFire only supports the 32-bit add.l natively). It will take several cycles to just branch to the trap and then you'll need several instructions to emulate the unimplemented instruction.

When you compile natively for Coldfire, a 220MHz v4e will handily beat even the fastest 68060, but code compiled for the 68K family will run substantially slower. Again, I don't have actual numbers, but at least one person said the performance was similar to a fast 030 or maybe an 040 when running typical Amiga software: http://bbrv.blogspot.com/2008/03/coldfire-developer-program-begins.html (see the second comment or so).

The benefit I see is being able to select the CPU you want to emulate for maximum compatability and performance. Hell, make it a menu in the boot ROM. Before you load the library, select the CPU for this session.

This isn't really a big deal. These libraries implement the missing instructions, but they don't deal with other sources of incompatibility (cache, 24-bit vs 32-bit addressing, etc.). If a piece of software won't run on a 68040 or 68060 equipped Amiga it won't run on ColdFire either. The only reason there are multiple versions of the emulation is that there is no point taking up ROM space to implement instructions your software is never going to use. Beyond that, there is no benefit not implementing some of the 68K family instructions.

[desiv]

you're making this up. MiniMig was intended to be a A500 clone, nothing more, nothing less.
http://www.techtravels.org/amiga/minimig/weeren001/minimig.html

That article doesn't mention his "original intentions", just that he first built the minimig as an A500 clone.  He still "could" have intended it to be a 4000, but changed his mind early in development when he considered the complexity...  
BUT...  I wasn't satisfied with "could"..  So I knew the Interwebs would help me..  and they did!  This quote agrees with countzero (great name btw..):

This pretty much means that I've completed my initial goal, recreate a console-like A500 to play games on my TV.

From here:  http://eab.abime.net/archive/index.php/t-27708.html

Yes, this is a mostly useless post, but I'm delaying some bash scripting work a few minutes and needed a distraction.. :-)

desiv

[bloodline]

Denis stated very clearly on these very forums that MiniMig was never intended to be anything more than an Amiga500 clone. That is the Amiga he had and wanted to emulate using an FPGA. A quick look at the hardware shows that the design had always intended 12bit gfx and a 68000, both unable to support AGA.

[Dr_Righteous]

Well that may or may not have been his original intentions. I'll conceed that point. But I DO clearly remember it was most people's intentions to take the concept well beyond A500.

Be it a v4 Coldfire or TG68 in a rubber burnin' FPGA, AGA is coming and we'll need more power than that 68000 in the v1.1.

[ChaosLord]

Um, y'all do know that the v3 and higher coldfire chips are faster and cheaper than all of those 68Ks, and can translate whichever core you want to use just by changing out the library you use in the boot ROM, right?

Wrong.  They are completely incompatible.  This has been covered.

[trekiej]

Isn't the V4 or V5 that was supposed to be 68K compatible?

[Linde]

Sign me up for one as well as long as it was under $300AUD (around $280US), if possible.

Last I heard, Mike was aiming for "(much) less" than €200, so your price requirement gives some room for miscalculations.

[Belial6]

Not to mimic the "Forget hardware, just run UAE" crowd, but why would we want to use a hard wired processor when we can use an FPGA?

[Linde]

Not to mimic the "Forget hardware, just run UAE" crowd, but why would we want to use a hard wired processor when we can use an FPGA?

My sentiments exactly. Fast, reliable, future proof; all things good minus all things bad. As far as I understand, the 030 core will be able to maintain a high clock speed (faster than any 030 accelerator).

[mikej]

Ah, so Yaqube has let his secret out
This explains why my mailbox is now full. Sorry if you have mailed me and I have not replied, I'll try and get around to everybody.

I'm in China at the moment and working hard to finish the RevB layout. There are about 30 connections left to make, but it's pretty much done.

This has a few fixes over the RevA board. The main difference is the connectors are all moved to one side (not the rs232 debug) and it includes composite/svhs option on the main board.

It should go to manufacture Monday, and I hope they can make them in time before I leave...
MikeJ

[NovaCoder]

Go MikeJ