New type of accelerator design?

[amigadave]

...............I  plan on thinning the herd here soon -have 15 or 20 Amigas and rarely use ANY of them anymore.Maybe I can raise enough funds for a SAM.

Warning!!! OFF TOPIC: To recidivist, or any other Amiga collector that has many Amiga computers that are not being used, please consider attempting to get your un-used Amiga computers into the hands of a new Amiga enthusiast.  It is not an easy task to get anyone interested in such a old and limited computer system, but there are a few exceptional people still out there that will find the Amiga an interesting diversion.  If we can find just one person who will continue their interest and become a programmer who writes code for AmigaOS3.x, AmigaOS4.x, MorphOS2.x, or AROS, then the effort we expend to give, auction, or sell our un-used Amiga computer systems to those special individuals will be well rewarded and a benefit to all of the Amiga community.

[amigadave]

I would not bother emulating he 68k CPUs when they are available still (even if they are second hand). My plan is to use CPLD or FPGA to create the bridging device which is between the A1200 and the 68040/60 CPU. Towards the 68040/60 it is a bus arbiter while towards the A1200 motherboard it emulates a 68020 CPU's bus cycles. Beleive it or not the  A1200's Channel Z port is not a magical unknown area. You can find useful information on it if you read docs carefully.

For me the Amiga is the 68k architecture and not the PPCs. I don't want graphic card or any other CPU that is not 68k compatible. All I want is faster calculation and RAM. I don't want to make money out of this, I am just interested in FPGAs and digital circuits and this seems to be an interesting project to have fun.

I would like to see a softcore 680x0 CPU accelerator in FPGA made someday that can exceed the speed of the fastest 68060.  Is it possible to create a 68000 softcore (which is already available) that can run at 200MHz to 400MHz, or would  a 75MHz to 100MHz 68060 still be faster?

If a 68020 softcore is ever finished and could run at the same 200MHz to 400MHz or faster, would that be the logical direction for future Classic Amiga accelerators to look into?  I think this is what the Natami team is researching and trying to accomplish, or perhaps they are still looking at creating a more advanced 680x0 softcore design.


Hopefully when Jens completes his Clone-A project, there will be the possibility to create a new Amiga Clone computer completely from one or many FPGA chips that can operate many times faster than any Classic Amiga ever could.  Keeping the timing compatible with older Amiga programs and games, while at the same time increasing the speed of all of the Amiga custom chips that Clone-A has moved into FPGA chips will be a challenge that must be considered.

[amigadave]

A 68020 compatible core (possibly with a few 040 user mode extensions such as move16) implemented in an FPGA would seem the best bet to me. I don't know how feasible that is, but if it could be done would be an ideal accelerator base maybe. If it could be implemented, along with a basic memory controller that allows generic DDR memory (simply based on availability) that'd be nice.

Something like that would certainly have me interested

Me too!  I think it can be done, and will very likely be completed by someone, or some group in the near future (1 to 3 years).  The longer it takes to be invented, the less people will still be around here and interested in paying for it, as the Amiga community continues to splinter and disintegrate.