MiSTer FPGA Forum

Fularu wrote: ↑Tue Mar 23, 2021 8:59 pm This has been discussed here and you can find his posts on the subject.

Please point to them, I find only 6 posts here by Mike and 106 over at atari-forum, but nothing that really covers what you write... I just see his tg68 spin-off that he calls m68k which he has put on github already, which is more like a 020... nothing about 040/060.

I see kolla's here to mention how pointless such an endeavor is as usual

If you read more carefully, I you may notice that I am not saying anything about such an endavour being pointless - I am saying that wishing for it and explaining to everyone over and over how cool it would be to have a faster core... is rather pointless. Of course it would be cool and awesome, that is obvious, and people with the skill and knowledge already knows this and is "on it" as best they can already.

kolla wrote: ↑Thu Mar 25, 2021 10:08 pm

Fularu wrote: ↑Tue Mar 23, 2021 8:59 pm This has been discussed here and you can find his posts on the subject.

Please point to them, I find only 6 posts here by Mike and 106 over at atari-forum, but nothing that really covers what you write... I just see his tg68 spin-off that he calls m68k which he has put on github already, which is more like a 020... nothing about 040/060.

I see kolla's here to mention how pointless such an endeavor is as usual

If you read more carefully, I you may notice that I am not saying anything about such an endavour being pointless - I am saying that wishing for it and explaining to everyone over and over how cool it would be to have a faster core... is rather pointless. Of course it would be cool and awesome, that is obvious, and people with the skill and knowledge already knows this and is "on it" as best they can already.

You're right it was an exchange we had on the Commodore Amiga facebook group. And since Facebook'S search function is atrocious I have issues pointing to it.

But hey, @mikej can come in and chime himself if he has the time for it.

Well the Mister minimig core could use some speed, having now (for fun and to compare apples to apples as best as I can) I setup Coffin R58 on both the V4SA and the Mister I find the mister painfully slow for a great number of things like SMB shares, web stuff (this is not surprising since these things are demanding and the minimig is only a speedy 020-ish cpu at best) but I can see why some people are asking for more "umph" if they are using this core for their "daily amiga driver" and if you are doing RTG and all that having a beefier cpu is going to help a great deal, if you are however just playing Turrican, Lemmings or Cannon Fodder not so much ..

Fularu wrote: ↑Fri Mar 26, 2021 2:04 am
But hey, @mikej can come in and chime himself if he has the time for it.

Yea I would be curious where he is in all that.. I honestly dont bug him since hes a very busy guy doing important stuff.. and honestly id rather have him working on THAT stuff then getting down into the mud to setting a disagreement on semantics ..

try software emulator the ARM first, I dare you, I double dare you

Eh, if you know who I am (congratulations, I have had the same nick for 30 years) then you already know that I do regular rebuilds of Amibian, both for ARM native and JS (presently doing a WASM port). Emulation is not an issue. The whole point here was that if we have this kick-ass FPGA to play with, why not make that as awesome as possible. So dare accepted and date pushed back by a few years, because building for ARM is pretty common.

most people "demanding" faster CPU claim they cannot do it themselves because they are "software people", so again I challenge you to try software 68k emulation on the ARM!

Again, done and dusted. And utterly beside the point. I even made a custom intermediate assembler that implements support for variables (stack mapped) and Rust like memory handling. The same bytecodes can be post processed and emitted to multiple processors and high-level languages (see link below).
http://quartexhq.myasustor.com/amibian01.jpg

Sorgelig doesn’t care that much about Amiga aside from playing games, so don’t expect much

That is sad to hear, but if he would be interested in a patreon project for doing a new Amiga core, or refactoring the existing Mist core, then im fairly confident the Amiga community would be interested. Presentation is everything, and the Amiga community is very supportive of such projects. Who knows, he might change his mind, it doesn't hurt to ask.

if you want faster CPU core, you most likely must do it yourselves.

Perhaps. But there are plenty of options out there. You can soon pick up the Buffee which chews 68k opcodes at insane 3.2 GHz, where a relatively humble ARM CPU has been tailored to purely act as a CPU (https://amitopia.com/new-buffee-amiga-a ... 1000-mips/). With the groundwork done, there is nothing stopping Rene' from stuffing a high-end ARM cpu in the next model, something like a SnapDragon 880 series CPU delivers Intel i5 performance. So as always the community have found solutions for the particular problem of speed.

The question really is, wouldn't this be much better to move to FPGA?
If you take the Buffee work that Rene has done, then look at the architecture of the Mister, you cant help thinking that it has a massive advantage over the Vampire. The CPU can be moved to the ARM side. Memory sharing is already solved, and FPGA space can be reserved for the chipset. In such an approach you can free up the gate-blocks allocated for the cpu. This could be refactored as chipset advancements.

that exlains all the revisionism regarding "the vampire situation" and all the rest

In what possible way is cheering on the Mister synonymous with being a Vampire V4 fan? I'm actually quite unbiased on the subject. It became a "thing" because the group I run on FB was created purely for emulation and FPGA, yet some members were utterly incapable of following the rules. The point of the group was to have a space where people could calmly debate emulation, various SBCs, FPGA and next-gen Amiga machines without being hounded by some of the people that, at the time, were ripping through the Commodore Amiga group.

At the moment we have several standards fighting over who is the next best Amiga. You have PPC/OS4, Aros, Vampire, classics, Morphos -- and they are all running with their own ideas, different hardware, different software.

If the Mister could tap in to say the 080/AMMX functionality, it would make life much easier for software developers. Having to cross compile to the extent we do now is pretty tedious, and with the massive differences in speed, hardware capabilities etc. -- new software gravitate towards the lowest end of the spectrum. This could be solved more elegantly by pushing the low-end standard to something akin of a PS2.

But do feel free to elaborate.

QuartexNOR wrote: ↑Tue Mar 30, 2021 3:10 am
If the Mister could tap in to say the 080/AMMX functionality, it would make life much easier for software developers.

I am just going to throw this out there and guess that you wont even likely see AMMX/080 make its way to the Mister and et-all till you see it first hit WinUAE/FS-UAE ... and the winds that blow in those parts don't look favorable to that happening anytime soon based on the various things that I have seen (as much as I too would love to see it added everywhere).

Yeah I think you might be right. In my mind it doesn't have to be AMMX/SAGA. RTG is cool and already there, so getting the cpu over to ARM would kick ass. It would also finally enable me to build the HTML5 browser code I have prepared without so much hassle.

Part of the reason I'm on about this, is because we need standards. In a perfect world SDL would be able to auto-scale the graphics and sound so it would fit whatever hardware you have, but the classics don't stand a chance in that department. And Webkit is written with a GPU in mind, so you still need to implement a subset of the traditional GPU operations that the chipset lacks. CPU powered scrolling in 2021 on 35 year old hardware is not going to be a nice experience.

It was worth asking, but I'm not holding my breath.
Sadly I don't see how we can ever get the platform back on track with so many different views on what constitutes an Amiga, or where it should evolve next. We have finally reached the point where off-the-shelves parts can replace old patents and copyright material. We have finally arrived where we can leave the ever squabbling owners behind.

For some reason, the people that have the hardware skills seem hell bent on keeping it cult and stuck in the 80s, which means the Amiga inevitably dies with our generation. The Mister has the potential to be an affordable, future proof Amiga that could scale (i.e move to a better FPGA / ARM solution once the market was built), but without a clear vision and a desire to establish standards, I don't see that happening.

The more I see of the players on the field, the more convinced I become that my initial idea was the right one.
Once I'm done with the new compiler/IDE, I should be able to finish QTX in six months.
If people like it, then we re-implement it as a native desktop.

I just wish someone else would do this. I shouldn't have to become involved.

ericgus09 wrote: ↑Tue Mar 30, 2021 3:43 am

QuartexNOR wrote: ↑Tue Mar 30, 2021 3:10 am
If the Mister could tap in to say the 080/AMMX functionality, it would make life much easier for software developers.

I am just going to throw this out there and guess that you wont even likely see AMMX/080 make its way to the Mister and et-all till you see it first hit WinUAE/FS-UAE ... and the winds that blow in those parts don't look favorable to that happening anytime soon based on the various things that I have seen (as much as I too would love to see it added everywhere).

Not even going that far .. Im still waiting for Amibian/Amiberry x86 ... there are oceans of commodity off the shelf PCs just headed for the skip that would make kickass amigas.. for free.. wont cost you anything but your time to go fish it out of the trashbin.

views on what constitutes an Amiga,

It's nothing more than a nostalgic 90s gaming machine, and nothing else. Anyone treating the Amiga as a "serious" machine in 2021 is in cloud-cuckoo-land. A modern PC, MAC, Laptop, Tablet, Raspberry Pi, Mobile Phone, all make any of the Amiga range look like a ZX81.
I owned a A500, A1200, A4000. One of the best things I ever did was selling the lot - with the A4000 making me enough money to build a complete gaming PC.

Classic Amiga was more than gaming. The film producers of titles like Titanic and the propeller heads at NASA made very good use of the 2500 and 4000 lines, and not for gaming on their lunch break. Preserving that legacy is just as valuable as conserving the bustling demo scene culture and the groundbreaking games of the era. Yet somehow admitting that Amiga was ever more than a toy is apparently quite a challenge for some.. Those looking towards the platform for daily productivity in 2021 face an uphill battle, but that is their free choice to make. I've done productive work on a C64 on this side of the 21st century so cloud-cuckoo-land is in a different place for many people.

Then stick to the REAL thing. The Mister is NOT an Amiga-only FPGA device, so stop treating it like it is.
And what can an ageing Amiga do that a modern PC can't do ? Answer = Nothing.

The real thing (big box Amiga) is A) hideously expensive these days and B) so ancient that it crumbles to bits, requiring electronics maintenance skills most non-engineers won't possess. The real thing these days actually belongs in a competent museum.

A modern PC by the way does not boot into the Kickstart ROM, let alone as fast as MiSTer does. But that's just picking nits.

Why keep pushing back against a wish for a bigger Amiga on the MiSTer platform? Just because software emulation or other alternatives already exist and it's a heck of a lot of work? If that were in any way valid, MiSTer itself would have had exactly zero birthright. And yet here we are, and that's a good thing in my book.

Sure the bigger Amigas muddy the waters of what exactly could be a good target system. But the addition of FPU and MMU (the latter to a much lesser extent) do not seem all that unreasonable *and* they'd be useful to other cores as well. Like a bigger Mac or Atari Falcon, maybe even NextComputer.. it's really not just about Amiga here.

I can’t see anyone saying “this is a bad idea”, but I can see people pointing out that this isn’t trivial: either implementing a high performance processor core, or offloading processor duties to the arm for emulation, is hard.

There is a fantastic 68k processor core, it’s been designed and implemented by the vampire team. It’s not available it seems. The arm is already providing io and support to the core so the architectural designs will be interesting...

I’d love to see the vampire 68080 in the mister fpga - I have a vampire v2+ and it’s really quite wonderful - but the vampire team seem to have a very clear vision on where they’re going and this doesn’t seem part of it.

Gunnar did apparently offer the 080 core giving 060 level performance: has that definitely been taken off the table? That does seem like the simplest way forward.

MiSTer_Kirk wrote: ↑Tue Mar 30, 2021 6:44 pm Then stick to the REAL thing. The Mister is NOT an Amiga-only FPGA device, so stop treating it like it is.
And what can an ageing Amiga do that a modern PC can't do ? Answer = Nothing.

Eh, have you looked at the code for the OS? It's not gaming im interested in, its moving the OS forward together with the hardware.
My interest IS the amiga core, you are free to enjoy whatever core you like.

As for aging Amiga vs. PC, what does that have to do with anything? A Playstation 4 is absurdly underpowered compared to my i9 work PC, but its still an interesting device.

The amiga sauce is in the OS and it's architecture. But either way -- the more that supports a subset of a hardware standard, the more software can be ported. And yes, there are new games and new applications written for Amiga OS every year. You might not care about that - but a lot of people do. Stick the cores you enjoy, and i will stick to mine.

MiSTer_Kirk wrote: ↑Wed Mar 31, 2021 10:30 am

As for aging Amiga vs. PC, what does that have to do with anything? A Playstation 4 is absurdly underpowered compared to my i9 work PC, but its still an interesting device.

You play GAMES on the PS4, not use it for serious work. Just like the Amiga, why fuck around with old crap software when you can just use a modern computer ? It's just sad. The Amiga is a dead platform, Commodore are long gone and good riddance.

Why fuck around with MiSTer at all when you can play games on modern devices?

Your gate-keeping of what qualifies as a valid interest/use-case is frankly disgusting and really doesn't belong here IMO.

It's just a really weird position to take when it really doesn't affect him in the slightest.

MiSTer_Kirk wrote: ↑Wed Mar 31, 2021 10:30 am You play GAMES on the PS4, not use it for serious work. Just like the Amiga, why fuck around with old crap software when you can just use a modern computer ? It's just sad. The Amiga is a dead platform, Commodore are long gone and good riddance.

One part of using older/obscure hardware/software could very well be security.
Hell just by using a 5 1/4" floppy or even better 8" floppy will mean a pretty high security in it self since not many working drives still exists.

And could not agree more with chanunnaki!
Why are you then even on this forum that is for old ass systems with crappy software?
And the ps4 is almost dead too!
Use a ps5 if you want too play games.

*shrugs* Advancing Amiga at a hardware level is frankly ridiculous, and even luminaries like Dave Haynie have chimed in on that very point in the exact same manner. It's dead. folks. Not even Zorro III was interesting *at the time* compared to open alternatives, certainly not now.

A true path forward (whatever that means, for a system that still to this day lacks basic memory protection) is AROS, which allows you to enjoy whatever hardware is _actually_ modern and available (without having to make it up yourself!) generally through a simple recompile, and is infinitely extendible if desired because source code is available.

Let's be honest, seriously - Vampire is interesting as a five-minute tech demo. Nobody - and I mean *nobody* - is or will be using Amiga tech as their daily driver for anything 'real', ever again. Once you get up to use cases like the Video Toaster (which I'd argue might be one of the few reasons you'd still want to do so), you're so far beyond the bounds of FPGA it's not funny. Short of that - no, office document editing or web browsing will simply never be a thing anyone seriously does on Amiga. Fancy losing all your work due to a tiny software bug in a different app or commodity? Yeah, me either.

I honestly cant believe how closed minded people are here - gunnar would very much disagree about the Vampire being a "Tech Demo" and I agree! at the same time the Amiga isnt really suited to daily driver tasks I get that but its fun pushing its limits way beyond.. just seems none of you guys seem to think so.

We have a fun video game project going on here that's still in the early stages and most of us don't want to see any of it's limited resources being devoted to a giant niche waste of time like this. You guys are more than welcome to find our own resources and work one whatever you want but just don't be surprised that no one here gets excited about it.

I understand everyone has an opinion and is very much entitled to share this with others, a healthy discussion is fine. However personal attacks and insults to other users is unacceptable behaviour on this forum.

As such I have deleted a number of posts from this thread, those users involved have been warned.

However personal attacks and insults to other users is unacceptable behaviour on this forum.

Understood, and apologies.

No worries, understood.

Xbytez wrote: ↑Wed Mar 31, 2021 9:34 pm I understand everyone has an opinion and is very much entitled to share this with others, a healthy discussion is fine. However personal attacks and insults to other users is unacceptable behaviour on this forum.

As such I have deleted a number of posts from this thread, those users involved have been warned.

Just to underline my point (and thank you to the admin for cleaning up the thread, it got a bit heated there).

The vampire is fun, but the price point is quite steep. With shipping and taxes the sub total is in the $800 range for me up here in Norway.
It is here that the Mister makes for a wonderful alternative. I also feel the Mister deserves more representation, it really is one of the best, if not the best, FPGA implementation out there - and combined with the Linux layer that the DE-10 Nano provides, you have some brilliant avenues of technology that can be explored.

There is a lot of life in the Amiga community still. Thriving shops that provides new motherboards, keyboards, spare parts and amazingly enough, brand new hardware. There is likewise a good community on social media where new software and technology is constantly presented and sold. As well as software development groups covering assembly, C/C++, E-lang, Java, BlitzBasic and Amos basic. It might come as a surprise but Amos basic just got a major overhaul 20 years down the line, adding support for chunky modes, RTG display modes, modern file-formats and quite a bit of fixes and speed improvements.

The Amiga has this exploring spirit over it, where developers and users like to push the limits of what is possible. It's not really about the latest and greatest, but pushing boundaries and doing much with little.

My primary interest is not so much the hardware as it is Amiga OS. You have features in that little thing that Apple only added to OS X in 2015. And it's small size and extremely low memory requirements makes it a perfect candidate for embedded work (if modernized naturally).

Aros, which is a reverse-engineered variation of Amiga OS runs on x86, and it's presently being ported to ARM. It retains the use of 68k instructions by treating the instruction-set as bytecodes, much like Java or .Net operates with. This is converted to ARM code in realtime (PJIT) so that people can target the system using the classical toolchains. Which is pretty amazing, especially since you can pick up an SBC with 4-8 gigabytes of ram for less than $100 these days (Raspberry PI 4, ODroid N2, NVidia - plenty of options).

What I would like to see is some work to make it easier to cross compile, which means a faster cpu implementation first of all. This way its possible to use libraries such as SDL to abstract away some of the underlying differences.
Both GCC and Freepascal have up to date compilers for Amiga (some 10 million object pascal developers in the world, so FPC is a great tool to cover both Classics, Vampire, Morphos and Aros). The bottleneck is with the classics, in that some modules are best tested on real hardware, emulation struggles with clock-cycle distribution (e.g cpu takes all the cpu power, causing issues with chipset emulation).

There is also embedded to consider. A system like Aros is perfect for single application systems, typically used in medical and kiosk devices. Even linux has gained some weight over the years, and its now ancient ring system makes relatively simple tasks overly complicated. A simple, reliable and minimalistic OS is very attractive in such settings.

So there are avenues and potential in this work that might not be immediately apparent.

If you're really looking for a future amiga platform.... wouldn't you be better off with AROS?

68k is 25-35-45 years ago. 68080 is still way, way slower than modern hardware. AROS has integrated 68k emulation but otherwise runs on your native hardware at native speeds. It is supposedly source compatible with AmigaOS.

Port your software to AROS, run old software via built in UAE, be happy with FAR, FAR better performance than you'll get out of any FPGA based 68k family processor?

Rather than continually re-inventing hardware that is like 20 years behind the curve.... run a platform that is x86 (OR ARM) native and evolves with whatever new hardware comes out for the mass market? Effort is IMHO better thrown behind that direction?

throAU wrote: ↑Sun Apr 18, 2021 1:44 pm If you're really looking for a future amiga platform.... wouldn't you be better off with AROS?

68k is 25-35-45 years ago. 68080 is still way, way slower than modern hardware. AROS has integrated 68k emulation but otherwise runs on your native hardware at native speeds. It is supposedly source compatible with AmigaOS.

Port your software to AROS, run old software via built in UAE, be happy with FAR, FAR better performance than you'll get out of any FPGA based 68k family processor?

Rather than continually re-inventing hardware that is like 20 years behind the curve.... run a platform that is x86 (OR ARM) native and evolves with whatever new hardware comes out for the mass market? Effort is IMHO better thrown behind that direction?

ha ha the only version of Aros I like is ApolloOS that runs on 68k hardware... silly man!

Just watching this great interview with Jim Keller. One good quote is that 80% of the execution is ~6 instructions:load, store, add, subtract, compare and branch.

Perhaps we can clock TG68K and the cache say 4x faster then add a 4 cycle pipeline for all the other instructions.

https://www.youtube.com/watch?v=AFVDZeg4RVY

foft wrote: ↑Fri Jun 25, 2021 12:03 pm Just watching this great interview with Jim Keller. One good quote is that 80% of the execution is ~6 instructions:load, store, add, subtract, compare and branch.

Unfortunately load and store aren't separate operations on 68k, but are folded into most of the other instructions in the form of all those fancy addressing modes which make the 68k such a joy to code for (and such a pain to code compiler backends for!)

Oh well, then back to plan A
* increase clock
* pipeline failing paths
* repeat!

Guess that quote was more suitable for a https://en.wikipedia.org/wiki/Load–store_architecture. Though it is still a good interview.

foft wrote: ↑Fri Jun 25, 2021 2:46 pmGuess that quote was more suitable for a https://en.wikipedia.org/wiki/Load–store_architecture. Though it is still a good interview.

It is indeed (I just watched it, or at least the first half until a mid-roll annoyed me enough to quit the YouTube session).

I daresay the observation applies to 68k as much as it to other architectures (in fact you're probably well-placed to test it - can either Musashi or qemu produce a histogram of executed instructions?) - it's just difficult to make effective use of that information thanks to the addressing modes.