Hi all.
As I said in topic title I want to clone ARM Cortex-A57 (ISA ARMv8) as my final university project.
I want to know if anybody would like to help me do this! Of course this is very hard, but also not impossible!
Thank you.
P.S : We can start with simple cores like Cortex-A7 or something like this.

@Manili:

Really? You want to clone the Cortex-A57 from the ARMv8 ISA? And this is your final year project?

>"P.S : We can start with simple cores like Cortex-A7 or something like this. "

Sure. Let's start with something simple like that. Maybe include the big.LITTLE cluster interconnect as a weekend project.
Since this is your final year project, you have some 40 weeks in totum.
Say, you plan to clone the simpler A7 in, like, 16 weeks, and then go for the bolder 64bits cousin in the remaining 24 weeks, right?

Please keep us posted.

- Jonny

Really? I guess times have changed... Where I went to school, seeking outside help on your Senior Project meant risking your BSEE... (saw it happen... Watched four poor fools get themselves permanently bounced...) Perhaps you'd be best off choosing a project that is less ambitious, but representative of YOUR OWN BLOODY WORK... Which University do you attend, BTW? ;-)

I suggest you try to work out a simple processor with few instructions and multicycle.

Consider something which is achievable for a university project. I am not discouraging anyone but doing something reasonably achievable is always encouraging.

I doubt SoC division in my company works that fast to implement ARM CPU from scratch in 40 weeks. Maybe something like 6502 drop-in clone would be better.

1. When I say final project I mean something about 100 weeks or more (40 * 2.5)!
2. I don't want to fully clone ARM for the project (Only main features not all patents!)?
3. Just think about Linus Torvalds vs. Microsoft Empire! Want to explain more?
4. Anyway I'm not here to struggle with anyone. And also I know that you just want to warn me against what I'm going to do, so thanks a lot dear friend.

P.S. : I learnt a lot from your comment.

Thanks a lot for your replay.
That was a really great point. I'll keep that in my mind for future.

Which processor do you suggest? Of course MIPS is not possible because sources are available.
Thanks for replay.



What's your suggestion my friend?
Thank you very much.



Well, if I wanted to clone 6502 it would be better to clone MIPS or at least MANO processor. Remember it's not C.A. class project!
Anyway thank you very much for your suggestion.






Everybody thanks for your answers. I learnt a lot from comments.
Finally as @aikijw said I think it would be better to be MY OWN BLOODY WORK !

Anytime... Glad I could help, although I'm not sure you actually got my point, but I'm not in a class with you, and it seems unlikely you'll ever work for me, so... Which university allows two years (100 weeks?) for a "final project"? That's something I've not encountered before... BTW... The 6502 is an excellent suggestion for a host of reasons... It bears consideration and would make a very good final project... Especially if you build a well documented design... Regards, /jw

@aikijw
Dear jw
Is my uni project the problem?! So imagine I'm going to clone ARM for fun :-D ! I mean forget about uni or final project ;-)!
BTW, why do you suggest 6502?! It's easy to implement this processor with LISA. And also if still my uni is the problem, I think they won't accept this project. Because sources are available, and finally I have to choose completely different project which is too bad :-(( !
What do you exactly mean by "well documented design"?
Again thank you very much for your advices.
Looking forward to your answer ...

I don't have to "imagine" anything... You clearly stated that this was for your "final university project". That cat is, effectively, out of the bag. I'm sure your University has an honor code. Sorry... As a practicing Electrical Engineer speaking to someone trying to enter MY chosen Profession, I simply can't ignore that. Cloning the ARM "for fun" is a bit ridiculous. Licensing considerations alone make this both risky and pointless. ARM is rightfully protective of their IP. Waiving an Open Source flag at the ARM architecture reveals a bit of a misunderstanding of the "Open Source" movement. The comparison that you make, between "Linus Torvalds" and the "Microsoft Empire" on this basis, is specious. I don't speak for Linus, but my guess is that he would disagree. He didn't clone "Windows", nor did he clone "Unix". Using your analogy, you should be coming up with your own processor design. A design that significantly improves on the ARM architecture... Not "cloning" things... If you did succeed in successfully cloning any ARM core that is considered protected IP, I'd suggest that you'd find yourself infected with lawyers in a very short period of time...

I didn't originally suggest the 6502 as a target. Another poster did. I agree with the suggestion, however. The 6502, beyond it's historical significance, represents a processor that you could, in fact, perhaps manage to get your hands around in a semester, followed by a semester of implementation. There are available emulators for you to test against, and overall, you could make a great little project out of something like this. The 6502 is still in relatively wide use today (as is the Z80, for example). IMHO, even this is an aggressive project.

Your argument that a project is unacceptable because "source code is available", tends to indicate that you don't really have a full understanding of how much cake you're trying to stuff in your mouth with the proposed ARM project. (There is also source code available for various ARM clones, BTW, so...) While there is source code available for various 6502 implementations, the design artifacts proving that you actually DID design a specific instantiation, would more than prove that you were responsible for the work. Those artifacts, in general, are NOT available... That's what I mean by "well documented design". On the basis of just turning in source code, I would certainly consider that an unacceptable project.

That's a really long graduation project. I'd say it seems unreasonable effort for a final year project. Something of this magnitude (2 years worth of work) looks more like a masters degree.



So, just some of the patents, then? You are aware of the complications of cloning a fully patented work, aren't you?
Let's say you write a processor from scratch that executes the ARMv8 ISA. Well, it is a violation of licensed IP. You will never be allowed to share your work, publish it, or even make it available here at OpenCores, for example. You'd need to keep it to your personal amusement.



Yes, looks like you need someone to explain it more to you. Linus never stole a single line of code from Microsoft Empire.
Linux is written from scratch, using solid licensing to back it up. The entire work of the Linux Foundation is protected under Copyright Law, and is licensed under a GPL license.

If Linus did something like you propose (copy an IP that is protected and violating its licensing terms), Linux would never be, and Linus Torvalds would never be able to topple Microsoft, because he would be sued to his bones and be forced to withdraw every bit of the work from public reach.

You can only share something that is YOURS in the first place, i.e., something that nobody can claim property but you. Then you may decide to license it with a GPL, or even a BSD license, and give it to the world.



I do not want to warn you against anything. This is a Forum, and you invited all passers by to talk. I am just pointing out the inconsistencies in your plan.

Copying *ANY* processor core with the complexity of an ARMv8 class processor is a gargantuan task, that would be daunting to a team of very experienced processor designers, and requires an army of backend and verification engineers, just to check if the design works. Doing it from scratch, from the ISA and specs, just compounds that difficulty. Companies like Texas Instruments, Marvell, Apple and Samsung pay licenses of hundreds of million dollars to acquire rights to design their own cores based on ARM's ISA, and they have entire buildings packed with the best paid processor engineers in the world. These teams may find 100 weeks dismally short to do that.

You referred to the ARM Cortex-A7 as a "simple" core, to be done with as a stage during the project. That sounds preposterous. I really cannot make any judgement on your abilities as a processor designer, and you can be a gifted hardware talent, but the fact that you are at least 2 years from graduation, and the fact that you refer to cloning a Cortex-A7 as an ultra simple task, do not talk well on your behalf.

So, please keep us posted when you do it.

- Jonny

@Jonny
So Jonny would you please do me a favor and write your suggestion for me?