Does the Apollo project have licenses for all the patents it's going to be using?
Building an open source CPU is one thing, selling it is something else altogether. If they make any money they can expect to be contacted by lawyers demanding money.
OTOH this is probably the least of their worries...
"It is only a nice story when Gunnar tells that we had a conversation with the ColdFire/M68k Division Manager of freescale. That we asked him if a custom made MC68060 with higher speed than the classic ones could be available. When he declined we got on asking if we could at least get/license some source HDL code to use in an FPGA. He told us that the MC68060 is built in some kind of HDL source. He regrets but it is absolutely not possible to get/see/license this code for anybody in any form. The only thing he could do is to provide us contacts to companies who sell 68k IP cores. Freescale itself doesn't do this, it is not their business. Then Gunnar asked him what might happen if we wrote our own IP. He said that Freescale will not have a problem with that and that, in his opinion, we do not need any permission from Freescale even if we are about to sell it. But we can not expect any technical help or support from Freescale when we decide to do so.
This is just a story which happened some time ago. We do not need prove or evidence of that. This only (sadly) shows that this is the end of the road for the 68k. The business of this division of Freescale is to sell competitive embedded ColdFire chips, not software. These chips *must* not compete with faster PowerPC which is a different division at Freescale. As said, in the real world they would only sue us for money, not for fun. It would be money if we decide to sell 68k compatible chips running at 600MHz at a price of 1,5$ per piece. Then the discussion here might be justified. But it is not because we won't because we can't.
I just wonder why AMD is still selling x86 compatible CPUs. Ah, right, I forgot. They use a completely different opcode than intel.
Meaning that it might be worth continuing this discussion. Since we AND Freescale are not really involved because both do not have a problem with this topic I would emphasize to discuss whether an opcode is copyrightable or patentable in talk, not as an NatAmi question. For now Freescale does not have any interest in high-speed 68k. The moment this changes we are the first to get a 2GHz 68k dual core and just drop the softcore '50 (sorry Gunnar/Jens) and get the chip mounted onto a SyncZorro card. But immediately." -Thomas Hirsch
It usually takes big teams of experienced engineers years to build something like this. I don't ever like to say never but I'm going to break that tradition by saying I predict the Apollo project will never finish a design of this complexity.
Gunnar and Jens are "experienced engineers" that work for IBM as their day jobs. Most of the programming of the pipelined superscaler integer CPU, caches and memory controller is done. A FPU and simple SIMD unit are probable at some point. It can always be updated as it's fpga. It's not that far beyond the core used in the fpgaArcade which already performs better than many of the fpga cores on the market.
Even if they could do it - what possible reason is there for anyone to pay for it?
This thing is going to require a big, hot and expensive FPGA. All so you run stuff slower than a $1 ARM.
It's interesting as a technical project I'm sure, but the rest strikes me as wishful thinking.
A large fpga does not run hot. The main disadvantage of the fpga over a real "chip" is speed, and limited shifting and multiplying ability. The advantages of the fpga are cheaper in low quantities and the ability to customize and update what's in them. Some fpga customers find the advantages outweigh the disadvantages. It's simplest and cheapest to put everything in 1 fpga with their custom logic. Some customers may go ASIC later and want a full featured CPU while others want the minimal CPU for the smallest possible fpga, memory and price. The 68k/Apollo has the advantage of being easy to program (many embedded systems do not use an OS) and very good code density (better than ARM with Thumb 2). ARM also relies on shifting a lot (improves code density) so is not well suited for an fpga. The 68k/Apollo relies on sign extending (for code density improvement) which is easier for an fpga. The Apollo core has outperformed the NIOS and PowerPC 440 in most of IBM's tests. IBM could burn or use their own processor "chips" but even they have a use for fpga processors.
