First Amiga 600 FPGA Accelerator - Vampire 600

[majsta]

Work in progress...

[ Show youtube player ]

[kriz]

Interesting!!

[Magno Boots]

Interesting.. I hope something comes of this.

Many of us have previously lost out investing in an A600 ram expansion, which came to nothing.

I would happily invest in something that came to fruition

[rkauer]

Really interesting!

How far is the project?

[alexh]

Originally Posted by Magno Boots

Many of us have previously lost out investing in an A600 ram expansion, which came to nothing.

Everyone got their money back didn't they?

Originally Posted by Magno Boots

I would happily invest in something that came to fruition

I wonder if it will come in at a price below the ACA630?

It has to be significantly lower than a MiniMig v1.1 PCB else what's the point? (Other than for fun)

[moijk]

Originally Posted by majsta

Work in progress...

[ Show youtube player ]

Kudos for the appropriate mid 90s dj bobo / love is all around soundtrack.

[DonAmiga]

Great Stuff

[majsta]

@rkauer Project needs 2 days to finish schematics and final pcb, all is done. Next week sending it for prototype production. Goal is to make 2 types of board. One dev board so anyone who know something about vhdl can work with accelerator and make it faster. One board for users with 1 gb of ddr ram and about 80mhz. All we needed for this years is something that we can work with. Some dev board for testing, upgrating and speeding up performance... I know that there are few people who can make softcore faster only if they had hardware. That is my goal to create something that people can work with.

[cosmicfrog]

1 gb of ddr ram and about 80mhz

[Loedown]

Originally Posted by Magno Boots

Many of us have previously lost out investing in an A600 ram expansion, which came to nothing.

This doesn't seem very pleasant considering that Zetr0 offered to refund people, if you said it was ok before and changed your stance now I think you should damned well apologize.

[Cosmos]

Very good

[TjLaZer]

Specs of card? CPU?

[b0lt-thrower]

This is actually kind of awesome. Once the soft CPU is programmed in the FPGA can it be "upgraded"? e.g., if someone writes a faster core (or a different gen m68k - like say you're aiming at 020 and someone releases a soft 060 core) can it be flashed with this hypothetical new core?

[Magno Boots]

I am deeply sorry and ashamed for making the statement that I did.

I am positive that all funds have been refunded and am verry sorry that I suggested that this did not occur.

Zert0.. please accept my public apology, as I know you are an honest man and had the community at heart when taking the project on.

I personally won't be able to forgive myself for this this.

Bye

[alexh]

I don't believe that any FPGA (at what we would consider a reasonable price) is going to be able to run a fast 68060 at 80MHz together with a DDR core etc. I think what we'll get is a version of T68 (68000) + DDR core running at 80MHz. The price of the FPGA + boards will almost certainly be as high as existing turbo cards.

So don't all throw away your 060 turbo boards. Even the most expensive FPGA's of today will struggle to replicate a compatible 680x0 close to the real computational speed of a 68060 at 50MHz

But as Jens' has shown, improvements in the memory controller can have amazing speed boosts compared to the original Amiga Turbo cards.

Add to that FPGA's could be programmed (if they were big enough and fast enough) to make all 680x0 opcode instructions single cycle. This would be a huge boost over the original CPU's.

The problem comes in that the original chips (especially the 060) had many many complex speed boosts themselves. Their caching, branch prediction and super scaler architectures are all advanced techniques not yet fully reverse engineered.

Tobias' great work on T68 and Jakub's work on adding 020 instructions and stack frames etc. is in it's infancy compared to these features.

They will come, in time.

[moijk]

Originally Posted by alexh

I don't believe that any FPGA (at what we would consider a reasonable price) is going to be able to run a fast 68060 at 80MHz together with a DDR core etc.

The NatAmi team have persuaded that goal with their softcore 050 and plans for a 070. I believe they will succeed with it, seeing the talented people working on it. They are also boosting nice numbers with legacy processors - currently they are running a real 060 stable at speeds of 120mhz.

I have to admire peoples will to do projects like this. Even if they fail or doesn't reach their goals - it is still supporting the Amiga. Which by any regular sense would be a page in the history of computers - much less a platform with life left.

[Loedown]

Originally Posted by Magno Boots

I am deeply sorry and ashamed for making the statement that I did.

I am positive that all funds have been refunded and am verry sorry that I suggested that this did not occur.

Zert0.. please accept my public apology, as I know you are an honest man and had the community at heart when taking the project on.

I personally won't be able to forgive myself for this this.

Bye

No one asked you to fall on your own sword, I just felt an apology was in order.

[alexh]

Originally Posted by moijk

The NatAmi team have persuaded that goal with their softcore 050 and plans for a 070. I believe they will succeed with it, seeing the talented people working on it.

Thomas Hirsch has proved he is a good engineer (if a little quiet). Gunnar... not so much but in his favour he's certainly enthusiastic. They cannot however defeat the laws of physics or economics with good code alone. Cheap FPGA's (at this moment in time) are in my experience either too small or too slow for such capabilities. If they are getting good numbers then they are using an expensive FPGA (expensive = much more than €60 which is the cost of an 060)

Has any true information about their 680x0 clone been shared with anyone (i.e. the price of the FPGA containing the CPU on their board, the source code for their CPU, the FPGA synthesis and mapping reports and system speed numbers?)

All I've seen are snippets of specs, techniques and ideas which anyone reasearching the subject could put together in a few days. No hard evidence / substantial work/prices related questions.

But then I've not been looking.

Originally Posted by moijk

They are also boosting nice numbers with legacy processors - currently they are running a real 060 stable at speeds of 120mhz.

Nice, but not ground breaking. This has been accomplished many times in the past. CT060 about 5-6 years ago and most recently with the Apollo boards now the problem with stability has been traced not to the speed of the memory controller (or memory) but to the voltage regulator. Once bypassed, speed can be increased considerably and stability maintained. Look at the work of RATTE

[moijk]

Originally Posted by alexh

If they are getting good numbers then they are using an expensive FPGA (expensive = much more than €60 which is the cost of an 060)

The 050 core apparently needs a bit of work before prime time, right now they seem to be focusing on getting the best benchmarks out of the 060 daughterboard.

The point with the natami is not only duplicate a 4000/060, but using modern memory and putting the coprocessors on stereoids get the most out of the arcitecture as possible. I have no idea about final price though.

Originally Posted by alexh

Has any true information about their 680x0 clone been shared with anyone (i.e. the price of the FPGA containing the CPU on their board, the source code for their CPU, the FPGA synthesis and mapping reports and system speed numbers?)

The price can be sourced by anyone familiar with fpga. I can't recall the exact fpga used, but they have at least mentioned the brand name if not exact model somewhere. Source is closed source.

Originally Posted by alexh

All I've seen are snippets of specs, techniques and ideas which anyone reasearching the subject could put together in a few days. No hard evidence / substantial work/prices related questions.

If your questioning if they actually have made progress in any way, I would say that is quite disrespectful.

I'd have to say I congratulate everyone spending their time with the Amiga or related technology. If someone actually gets something new to the markedplace that is better than escom and gateway ever did.

[alexh]

Originally Posted by moijk

If your questioning if they actually have made progress in any way, I would say that is quite disrespectful.

Respect is earned. When they have something, they'll shout about it. And I'll listen and congratulate them. But Gunnar blows hot and cold too often to believe they have a next gen 680x0 CPU core waiting in the wings.

But at least they are doing "something" which is more than most people, including myself.