Jump to content
Sign in to follow this  
HYDRAGON

new 99 dollar 500mhz 68020?

Recommended Posts

Amiga accelerators based on FPGAs already exist. MHz is meaningless; the speeds are anywhere around to twice the speed of a 50 MHz m68060:

 

http://www.majsta.com/modules.php?name=News&file=categories&op=newindex&catid=1

 

Work is already underway to make the CPU core more complete (MMU, FPU support, too), and some work has been done on an Amiga 500 version which would be compatible with certain Macs if the m68000 is socketed since it just uses the CPU socket.

 

The current core would be faster, but not significantly faster than m68060 CPUs, but later FPGA cores could really speed things up tremendously. There's been talk about one which would be electrically compatible with m68040 sockets, which would probably interest everyone here...

Share this post


Link to post
Share on other sites

Guys excuse me,It is indeed the apollo core,is full 68020 compatible,it is as fast as a 500mhz 020 cause it is superscalar,has two execution units,fast fpu and many other improvements,it runs this fast on common Cyclone 5 Altera,nothing too exotic,there are Xilinx Zync 7010 boards for 99 dollar now,Zync 7010 contains fast Artix 7 fpga logic and is big enough for a very fast 68k mac,it has 1 gig ram,HDMI,usb,ethernet,all this on a credit card sized board.

Maybe we could do a kickstarter campaign to hire in some developers?

Share this post


Link to post
Share on other sites

The core Majesta uses is a crippled version with one execution unit,the full core has two of them so much faster,it is blazing fast,there wouldnt even be a need for an Mac,it could run on the FPGA alone.

Share this post


Link to post
Share on other sites

They've made more progress than I was expecting the last time I checked on them.

But they're testing on Amigas, not Macs.

Share this post


Link to post
Share on other sites

Same lot as that NatAmi thing, isn't it? If so I'd expect them to get it done.

 

But not open, no, so Mac people can't extend it and it'll only support the boards they decide. Feels a bit backwards to me, but I suppose anyone still involved with Amigas must secretly love getting left high and dry.

Share this post


Link to post
Share on other sites

The developer,Gunnar,is very openminded,but he does all the hard work on his own,if we could support him it would accelerate the proces enourmously.We could have a cheap FPGA board with a very fast 68k MAC,AMIGA,ATARI,the hardware is here,only needs some good FPGA developers to write the code.

Share this post


Link to post
Share on other sites

On one hand you're talking about an FPGA-based accelerator, then in the same thread you mention:

 

The core Majesta uses is a crippled version with one execution unit,the full core has two of them so much faster,it is blazing fast,there wouldnt even be a need for an Mac,it could run on the FPGA alone.

 

So you want to skip the Mac hardware altogether and just use an FPGA board? Why not just get a really fast Core i7 and emulate a Mac in that case?

Share this post


Link to post
Share on other sites

John,software emulation and fpga are not the same isn't it?,can you buy a real fast i7 for 99 euro/dollar?,but I am not here to argue,some very talented man puts alot of energy in preserving and upgrading a processor wich we all love I hope,the only way we not so talented could support him is with our money,if we bundle our forces instead of argue maybe one day we can have new 68k computers,be it APPLE MAC,AMIGA or ATARI

Share this post


Link to post
Share on other sites

Well especially if you can get the 68K fast enough, you may be able to finally write a decent web rendering engine for the 68K mac and it actually be usable. 

 

BUT... there is a HUGE BUT... the processor can be 5Ghz, your still stuck at the 16 to 33Mhz system bus using the real hardware, this includes the RAM so its going to be slower than balls still. 

 

Sure the CPU can crunch the numbers as fast as lightning, but if you cant "get" it to there, then it wont run any faster. 

 

itll help if the L2 cache and of course the main system RAM is modern and running as fast as the processor. But again, the interrupts and all that jaz are ASIC/VIA controlled, and again, your stuck. 

Edited by techknight

Share this post


Link to post
Share on other sites

No, software emulation and FPGA emulation are not the same, but they're also not all that different. I'm interested in an FPGA accelerator because it can be used with real hardware from decades ago. Remove all the hardware and emulate it (in the case of a complete FPGA system), and it's less interesting to me.

 

The completeness of the current m68k FPGA accelerator for the Amiga 600 is a good sign. But how practical is it to do something like that for Macs? As far as I know, the only Macs that have a surface mount m68000 are the Classic and the Portable. How many 128K / 512K / SE Macs have socketed m68000s?

 

Considering the space and power limitations of the Amiga 600, the FPGA accelerator is damned impressive. But the next step, and a better one for people who care about performance, would be an FPGA accelerator for m68040 sockets. m68040 machines have more of a power budget for the CPU, have much faster access to motherboard memory and more expandability, along with a more physically robust socket. I'm looking forward to those!

Share this post


Link to post
Share on other sites

Having hunted around the appropriate websites for a bit, it looks to me like the current state of play is this:

• It looks like they have transparent 68EC020 emulation working at ~200MHz
• They're using a software shim to handle exceptions, but I'm not sure if that is only for the 060 emulation, or for both modes.

 

nb: these are beta releases that are still being debugged.

Both of those imply that it's not Mac-ready. The EC020 was never used in a Mac
.  And the "software shim for exceptions" is the same reason we can't use existing Amiga 060 accelerators on Macs.

The surface mount vs DIP40 issue with the 68000 is "only" a matter of altering the PCB layout to suit.

To my thinking, the ultimate scenario for Macs would be:

• Fully transparent 68000 emulation at speed, and
• Fully transparent 68040 emulation at speed.

Either of those would allow the use of the accelerator with existing Mac system software, ie, not requiring the patching that Amiga folks have already done to the various Amiga OSes to use 060s etc.

But as I have at present no way of contributing to the work, this is all wild speculation on my part.

Share this post


Link to post
Share on other sites

Well especially if you can get the 68K fast enough, you may be able to finally write a decent web rendering engine for the 68K mac and it actually be usable. 

 

BUT... there is a HUGE BUT... the processor can be 5Ghz, your still stuck at the 16 to 33Mhz system bus using the real hardware, this includes the RAM so its going to be slower than balls still. 

 

Sure the CPU can crunch the numbers as fast as lightning, but if you cant "get" it to there, then it wont run any faster. 

 

itll help if the L2 cache and of course the main system RAM is modern and running as fast as the processor. But again, the interrupts and all that jaz are ASIC/VIA controlled, and again, your stuck. 

That's exactly the problem I see with this kind of accelerators.

I'm not really an expert, but if I recall correctly most (if not all) 68k Macs derive all their clock signals from a single oscillator that controls the CPU, the bus speed and possibly the video signal refresh rate. You can't just expect to speed everything up, because replacing that oscillator would create all kinds of troubles with the system architecture. 

I think you could completely bypass the main oscillator by having the CPU run with its own clock, but that would have very little effect - you would still be limited by the bus and RAM speeds, so the performance gain would be negligible if present at all. 

I don't really know how accelerator cards worked back then, but if you could design an accelerator that's got its own CPU *and* RAM to bypass the stock ones, you may achieve something interesting. But that's far from being a drop-in replacement.

Edited by Sherry Haibara

Share this post


Link to post
Share on other sites

^ This.

 

Initially I thought the idea was to build an entirely new model of Macintosh, which I would imagine happening one of two ways:

  • New fast CPU in an FPGA, with memory controller, ASICS, I/O, sound, graphics, etc. implemented externally in hardware. This would be the closest thing to a "real" Mac, and would be very cool, but probably a tremendous amount of work. 
  • The entire thing implemented in an FPGA, with connections for a VGA or HDMI display and USB peripherals. Probably an easier approach (though still very challenging), but as johnklos said, the difference between that and an emulator is subtle. It's totally different at the bottom level, but the end result looks nearly identical. Put Mini vMac on a fast ARM CPU board inside a custom enclosure, and ask people to tell the difference between that and an FPGA solution.

 

Talking about an accelerator card for an existing Mac sounds more promising to me. The big issue there, as Sherry and techknight and others said, is RAM. To see much benefit from a 500 MHz CPU in a computer designed for ~20 MHz, you'd need to replace all the RAM, the memory controller, and the caches. And even then, anything on the Nubus like a graphics card would still run at the same old speed. Disk I/O would be just as slow too. But it would be pretty nifty! It could be tons faster for computation-heavy work.

Edited by bigmessowires

Share this post


Link to post
Share on other sites

The Amiga 600 accelerator has 64 megs of local, really really fast memory. Macs could use system memory to boot and add the really fast memory during boot. But even though the interface to the motherboard is 7.16 MHz, 16 bit, it still makes the old school Amiga ECS chipset shine.

Share this post


Link to post
Share on other sites

Well the accelerator could bypass the decoding of the RAM addressing for the system board, entirely. And replace it with the local RAM. 

 

The only downside is you need to handle the Overlay function. Basically ROM/RAM swap during RESET vector. 

Share this post


Link to post
Share on other sites

Would it be faster to do everything on the FPGA, or would it be faster to take an existing 68k compatible CPU like a Coldfire, then add the instructions needed to be compatible with a Mac?

 

I guess all the hard work has been done already on the Amiga side.  Probably faster for everything on FPGA.

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
Sign in to follow this  

×