@Massi

[boccaccia mia statte zittaaaaa....]

[incazzato]
Am getting tired of this things, are we in a linux forum that we are throwing most of the TM trademarks including Paid[by-dont-know-who]$hill and so on? Ever thought that cdimauro simply strongly disagrees with the course of action taken by Hyperion and the others and feel that ISO a healthy reality check is needed?

Or is like disturbing in the church for you? mean you CANNOT disagree is the os4/PPC real DOGMA!!!

[/incazzato]

[calmo]
Btw i disagree too with the lines, but because i would prefer a much different approach and a different business ethics rather than the 'make us milk you and shut up' that seems to go on.
I would prefer that the Amiga and like technology has no more an owner or an aggressive protectionism of its now mostly obsolete technology; wish that was left to the community itself the power to do what they like with, keeping the essentials open, making it migrate in all architectures they like and evolve the way they like without nobody telling that i cannot do things due to copyrights, patent, business tactics and so on.
That is why i by heart endorse AROS, and that is also why I asked cdimauro if the tina project that is involved with will have the FPGA cores open: because am tired of all this fighting, the ego clash and the artificial barriers that affect this technology and keep it at stake letting the community members fight their own little feuds; and because IMO Amiga/mos/AROS should just be a way for us to enjoy what we do first of all, if can make some money out of it even better, like what happens in other retro communities that have much less 'drama'.

I endorse what Paolone said in a much more diplomatic way than me
[/calmo]

Last edited by saimon69 on 24-Jan-2013 at 06:20 PM.
Last edited by saimon69 on 24-Jan-2013 at 06:18 PM.
Last edited by saimon69 on 24-Jan-2013 at 06:09 PM.
Last edited by saimon69 on 24-Jan-2013 at 06:04 PM.
Last edited by saimon69 on 24-Jan-2013 at 05:59 PM.
Last edited by saimon69 on 24-Jan-2013 at 05:56 PM.

_________________
Scarabocchi Binari - Italian AROS Blog
Binary Doodles - English language AROS Blog

@Crumb

No one has been producing desktop MIPS, PPC or ARM computers for a long time, that's why there are no high performance desktops with those chips. + the fact that there really is no high performance (remotely desktop suitable) ARM yet in the wild)

Latest x86 desktop that became available runs at 1Ghz. That's very interesting development!!

_________________
- KimmoK
// For freedom, for honor, for AMIGA
//
// Thing that I should find more time for: CC64 - 64bit Community Computer?

@KimmoK

If you're referring to AMD Temash @ 1 GHz, that's a mobile chip for tablets.

_________________

@NutsAboutAmiga

Quote:

Stick to the full name or else we don't know wtf your taking about.

you mean like "operating system four"? most people on this site and beyond (or at least enough of them) use "os4" like i use it, and everybody understands what we are talking about, right? do you know a dediacted german site called "os4welt.de". wanna complain with them too? am i allowed to use "mos" as referrence to morphos, or will you stand up?

@KimmoK

Quote:

KimmoK wrote: @Crumb No one has been producing desktop MIPS [..] for a long time

Ignorance is so bold

http://lemote.com/en/
http://mattst88.com/blog/2010/11/12/The_Loongson_3A_%28Godson_3A%29_looks_nice!/

_________________
No PowerPC, No Fun
Make Amiga Great Again

Quote:

KimmoK wrote: @cdimauro "I was talking about x86 or x64, not i5 specifically." I just spotted someone putting i5 together with "cheap" and to me that does not currently match. (after quick look I found 2.5Ghz AMD APU chip for 39eur and 1Ghz PPC for 30eur)

Yes, and there's Via too with its interesting x86 family.

x86 is both cheap & power-efficient nowadays. Something that nobody bet a penny a dozen years ago.
Quote:

But as gone through, CPU & SoC markets are changing. x86 is shrinking, but reaching towards embedded and mobile market (intell will die unless they manage) and ARM is growing at fastest speed, reaching towards 64bit etc... In a few years things should look pretty different, all architectures should have new generations on the market (all multicore with pretty low Ghz rating)..

x86 is moving to tablet and, more generally, mobile market. Also, Sony and Microsoft chose AMD x86 for their next generation console.

So, yes, PC may probably shrinking market share in the future, but the same could not apply to x86, which is attacking new markets.

ARM is trying to attack x86 market with its ARM64, but x86 has, and will have, A LOT to say about pure performance. I don't think that RISCs are able to fill the gap.

Quote:

wawa wrote: @cdimauro Quote: Frankly speaking, I don't see the value for such a thing. fine, but i actually do, even though it may sound pretty radical. the obvious reason is speed. but also reducing the amount of work to be done, problem which was still able to kill projects like natami on a comperatively advanced stage. and beyond that that it might be quite complicated to get full 68k 32 bit emu including fpu and mmu.

But if you are using an x86, it has enough power to emulate a complete Amiga machine, not only a CPU, at very good speed and beyond original machines.

That's why I don't see a value in using it just for a bit of the puzzle.
Quote:

mmu is frequently considered not necessary, still it is useful for debugging and may be helpful for improving the system in therms of stability and the like.

MMU is also a mess on 68K: every CPU (coprocessor for the 68020) has a different implementation.

I hadn't an MMU on my Amigas (2000 and 1200), so I don't remember details on how and what kind of usage make of it tools such as Enforcer.

With FPGAs, I think that a "basic" MMU implementation can be done, just to make them work. May be "faking" it working, but just enabling zero page and/or non-existent page accesses.

However it's quite premature to think about it. It'll be one of the last things to do, IMO.
Quote:

but im not trying to convince you, just explaining, its just one of alternatives and im interested in and supportive for a pure fpga approach too. the thing is i believe the approach has to be open and modularized.

From what I have understood, it seems that Alberto, the head of the project, wants to realize an open platform, but the project will be closed in the development stage. Obviously guys that want to help are welcome.

Regarding the modularization, I think that it's very difficult. We are not working on an "exact replica" of the old chips. Right now there are 3 FPGAs, which basically will be used to synthesize CPU, graphic processor, and audio & I/O, but you don't have to think at them like the "canonical" counterparts. In my idea, the 3 chips will include some "chipset" functionalities, such as memory and local buses arbitration / priority.
There'll be a very fast local bus, that will take 1 or 2 clocks to quickly access a 16 or 32 bits register from one FPGA to any other; think about the CPU trying to access $DFF180 : it may take 1 clock (not sure now; it's my hope) to write the 16 bit value, leaving the memory bus free for other purposes. If the Copper will be put into the audio / I/O FPGA (it depends strictly on how the resources will be distributed into the FPGAs) it can write values to the graphic chip registers very fast using this bus.
So, in this scenery, you cannot take a single module/FPGA and use it seamlessly in another project, since it's part of a system.

Why 3 chips and not a single, bigger, FPGA? That wasn't because we don't know the original Amiga architecture . We know it, and we know that there were 4 chips (68000, Agnus, Paula, and Denise, for the OCS machines, for example); so we are "missing" one, sorry.
The head of project wanted to have separate FPGAs to make it simple to work on specific parts of the project, without synthesize every time everything (which takes time: about 10 minutes for every run). It'll be costly at the beginning, since we have to split functionalities and implement an interface between the 3 FPGAs, but once done it'll be easier to work on it, adding new features. Also, we have plenty of I/O pins, which are needed to implement features such as DVI, which takes a lot of them.
Another reason is that this way we can have more room for future, big, enhancements: 3 fatter FPGAs are better than one fatter FPGA.

Finally, we can think about using all the FPGA resources to take out the best of the chip.
With 30K LE for the CPU, we can make a more complex, complete, and fast CPU; with 70KB of memory we can implement 32KB code + 32KB data cache, and may be something like Branch Target Buffer and Branch prediction bits, or MMU TLBs.
With 70KB of memory for the graphic chip we can buffer / cache entire display rasterlines in FullHD, and sprites data too, using 32 bit colors, maximizing the DRAM memory bandwidth usage. Scan-doubling can be easily implemented, as well as multiple color palettes.
With 70KB of memory for the audio I/O chip we can buffer / cache all the Blitter channels, again maximizing the DRAM memory bandwidth usage; we can also fully buffer an entire bitplane used as a mask, without loading it every time that a canonical bitplane operation must be executed (repeated for each bitplane used by the screen).

Anyway, they are just ideas: I don't know if all or any of them will be implemented. Right now the first goal is to make the first working board. Enhancements will come as they'll be completed. I prefer to do small releases,often, so that people can take his hands on them ASAP and enjoy.

Just one last thing: there aren't only 2 people working at this project. Alberto has a company with some engineers that will be involved. His idea is to use the idle time (which is a lot right now in Italy; it's not a good period, unfortunately) to release this project, and acquire a big know-how that they can sell to their customers. Except for BGA soldering, the company has laboratories where every single aspect of the project can be handled.

That's all. I wanted to make some clarifications because I read too many things about it. I don't want to talk again here, since we have an open forum were anyone can subscribe and make questions and/or contribute (as we hope).

@Fransexy

mate, theyre kinda cool.... great for mips enthusiasts.

_________________
Never underestimate the bandwidth of a station wagon full of tapes hurtling down the highway.

I serve King Jesus.
What/who do you serve?

Quote:

pavlor wrote: @cdimauro Quote: You know that Hyperion has no right to use the Amiga brand. Only AmigaOne, Amiga One, AmigaOS and Amiga OS are usable. Amiga One is Amiga brand created by Amiga.Inc in 2000 with aim to restart "Amiga desktop platform". Only Hyperion can use both Amiga One and Amiga OS names and of course has access to original OS source codes. That is enough for my definition of "Amiga". Licence of Commodore USA is probably valid for all name combinations with small limitation: OS similar to Amiga OS can´t be pre-installed on these computers.

Yes, I know. But if you talk about licenses, even a lighter with a sticker applied can be legitimately called "Amiga".
Quote:

Quote: I don't care about users, but about history, and history says that the last Amiga (branded) machine by Commodore had a custom hardware, on top of which ran an had hoc operating system. Users and operating system, that is all what left of Amiga platform.

Right, but the Amiga platform itself died. Now we talk about the operating system, but not about a complete machine, which is what Amiga was in the past.

IMHO

Quote:

simplex wrote: @anyone who actually knows what he's talking about When I read the quote by the PPC guy, I notice that he's talking in the context of microcontrollers. Maybe I'm wrong (probably -- I'm not a hardware guy) but I don't believe that covers the entire range of Freescale PPC products. Could he simply be saying that R&D on microcontrollers is nearly entirely ARM? That wouldn't exclude the continuation of R&D on other PPC products.

Sorry guy, but I don't see any desktop or server PowerPC which is produced or planned by Freescale. Embedded/microcontroller is the Freescale reference market, and now it's moving to ARM. So, take your conclusions.

Quote:

AmigaBlitter wrote: @thread meanwhile, Freescale released SDK to help who wants to migrate to multicore PPC, with sdk, tools and other instruments. Maybe our Kernel guy can have a look at this if can help. http://www.freescale.com/webapp/sps/site/overview.jsp?code=QORIQ_SW_DEV

It's at a lower, CPU, level.

What you need now is a proper kernel that can handle multiple cores without breaking things. Which is very diffucult on a so "open" operating system, such as Amiga o.s. / like.

Quote:

Barana wrote: @cdimauro you sound very much like that fella that started up merlancia (same undeniable charm and wit) in the day of coldfire amiga stb's are you related to him?

You look like an integralist whose somebody touched his holy totem.

Relax guy: we are talking about just some piece of hardware or software. Nothing so much important to declare a fatwa to the apostate.

Quote:

Massi wrote: @cdimauro As Italian and AmigaOS 4.x developer and user, I usually read all your Amiga related articles on www.appuntidigitali.it and let me say I don' t really like the fact that you always throw mud on everything regarding the modern Amiga both hardware and software sides.

I report facts, that you may like or not, I don't care: I cannot satisfy everybody. I do my job, and I think I do it well, but I prefer to leave judgements to people.

My articles are open to comments and critics too. You are Italian and a developer, so you are in the best position to throw stones if you see something wrong.
Quote:

It seems to me you have a special interest to do this, perhaps you get paid for the purpose, do you?

Gotcha! He's Steve Ballmer that payed me to spread manure to post-Amiga things. Even after many years from Commodore bankrupt, Microsoft is scared about that, you know.

It's simply freedom of speech, Massi(mo?): you have to accept it, the same I do with all the guys that don't agree with me and write their complains... on a technical basis, as usual.

"Religion", taste, emotionality should be left out.

@cdimauro

we are doing little talking, you're the one who's hijacked ='talking', ur just filling the thread with mostly semi agressive opinionated babble and tripe. this thread is lame. im outta here.go home.

_________________
Never underestimate the bandwidth of a station wagon full of tapes hurtling down the highway.

I serve King Jesus.
What/who do you serve?

Quote:

Barana wrote: @cdimauro we are doing little talking, you're the one who's hijacked ='talking', ur just filling the thread with mostly semi agressive opinionated babble and tripe. this thread is lame. im outta here.go home.

I haven't started it, guy, and many posts are talking about me and my article, in not so much polite way.

And you are one of them, which gave zero contribute to the thread, and used it only to make fun of me...

So it's silly to read your complaints now.

Quote:

Fransexy wrote: @KimmoK Quote: KimmoK wrote: @Crumb No one has been producing desktop MIPS [..] for a long time Ignorance is so bold http://lemote.com/en/ http://mattst88.com/blog/2010/11/12/The_Loongson_3A_%28Godson_3A%29_looks_nice!/

Hu. A RISC with 200 instructions added too.. more easily emulate an x86 CPU. Not exactly what the "R" stays for in "RISC".

Do you have any benchmark which can show its desktop performance? Thanks.

@cdimauro

thanks for explanations. ill observe the project even though i still wonder how its going to be financed. i mean the employees want to be paid even if they are working on a chiefs pahntasy. but lets assume it has been thought of.

Quote:

I hadn't an MMU on my Amigas (2000 and 1200), so I don't remember details on how and what kind of usage make of it tools such as Enforcer.

what concerns mmu it is actually very useful with muforce imho. it has had some application in higher end amigas even what concerns system functionality afair, but im not sure what it was. if there is actually a way to implement this in an easier way, im all for it.

now:
Quote:

But if you are using an x86, it has enough power to emulate a complete Amiga machine, not only a CPU, at very good speed and beyond original machines.

first of all even on x86 there is considerable amount of power lost on chipset emulation that can be spared if you have it available in hardware as on genuine amigas.

of course, the amiga chipset philosophy could be explored and induced into its possible alternative patch of development as it was attempted and talked about with natami. however what would come out of it? 24 bit hdres planar screens? strange obscure pixel formats? an alternative attempt at 3d acceleration not compatible with anything else developed while last 15 years? lets face it, at the end of the day every aspect of the implementation available by means of contemporary gfx and sound card wold beat it by performance, software portability and any other factor i can think of. therefore i think the amiga chipset can very well be left as is for legacy reasons. it isnt even necessary to reproduce it, as genuine hardware it is still available in quantities that likely may cover the demand of the scene. it is unlikely to produce any custom hardware in comparable numbers.

therefore i think it is most sane to take your amiga and use what remains usable of it, which is kickstart, keyboard, power supply, legacy interfaces, legacy chipset, floppy drive, and the genuine (labelled) housing (!) and extend it with whatever tech can be introduced to it. be it an x86 board with sata, pci and usb, if it behaves like an ultra fast 68k accelerator, then what makes it inferior to, say, a cyberstorm.

from your point of view, one could argue an accelerator extended with pci board, gfx and sound card doesnt actually need amiga underneath, yet such extensions have been succesfully built, people bought them, are proud of their frankenstein configs and the demand is still high. thats why i think an x86/arm accelerator board might not only be sane but perhaps even be a commercial success, feasible with least design effort, in shortest time and with least investments.

Last edited by wawa on 24-Jan-2013 at 11:27 PM.

@cdimauro

Quote:

Sorry guy, but I don't see any desktop or server PowerPC which is produced or planned by Freescale.

Really? Navigate to www.freescale.com. Hover mouse over "Products". Drop-down menu has several choices. One is Microcontrollers, another is Processors (e.g., PowerQUICC, Power Architecture). Freescale's website, at least, acts as if these are different.

The guy quoted in your article (Lees) is the director of microcontroller technology: Quote:

Geoff Lees, Freescale's new general manager for microcontroller products...

His statement can be read to say that R&D in microcontrollers will be nearly 100% ARM, not R&D in all products.

Hence my question. I don't have a dog in this fight; I just want to know if anyone who actually knows something about Freescale can clarify. Cherry-picking ambiguous press interviews doesn't clarify.

_________________
I've decided to follow an awful lot of people I respect and leave AmigaWorld. If for some reason you want to talk to me, it shouldn't take much effort to find me.

@olegil

Thanks for the reply, but I don't think you answered my question, which was whether the head of microcontroller division was referring to R&D for the entire company or for his division only.

As I told cdimauro, I don't have a dog in this fight, but I find it hard to believe that the head of the microcontroller division can speak for the R&D in other divisions, such as Processors, which Freescale's web pages suggest is a different division. I've found news releases from the past six or seven months that say Freescale will continue to design and produce its own PowerPC, so I'm not convinced.Quote:

ARM will not replace Power cores for Freescale, at least in the foreseeable future. The company said it has long-term plans to continue designing and supporting Power cores.

_________________
I've decided to follow an awful lot of people I respect and leave AmigaWorld. If for some reason you want to talk to me, it shouldn't take much effort to find me.

@cdimauro
Hi Caesar,

I am Matt Hey from the Natami Forum. Remember discussing 68k enhancements where we both argued for the block memory copy/clearing instructions and EA update addressing modes? We certainly had similar ideas about what the 68k needs. I created some documentation for a new open 68k ISA standard. It's all preliminary and needs some work but it has some good ideas. Since you seem to be helping with this Italian fpga Amiga project, maybe we could work together to help refine it and for possible use in your project. It can be found here:

http://www.amigacoding.de/index.php?topic=273.0
http://www.natami.net/knowledge.php?b=3¬e=47318

I also have an older version of the N050 fpga CPU if you want to have a look. Jens is ok with it and will be releasing the VHDL source anyway when he gets it cleaned up. It's pipelined and looks well designed and coded to me but it's incomplete. The TG68k is no doubt more mature but simpler. What fpga CPU were you looking at using? Is anyone working on the CPU currently?

Quote:

cdimauro wrote to wawa: That's all. I wanted to make some clarifications because I read too many things about it. I don't want to talk again here, since we have an open forum where anyone can subscribe and make questions and/or contribute (as we hope).

What is the name and website for information on your project?