If ... just if ...

[darule]

If I had the money, like for example Richard Branson, I would buy all companies, assets and rights related to the Amiga. I would kick out everyone and start all over with innovative people like Haynie. I would make Haynie CEO by the way.

Next Amiga on the market: The A5000.

PPC powered @3GHz
4Gb RAM
onboard 2.5" HDD 500Gb
AAA-like chipset featuring Dale(video),Glenn(audio),Dave(DMA chip).
VideoMem would be 1Gb
PCMCIA-port
SDRAM/MMC/CF ports

Need more? The A5000T.
Extra:
5x PCI-bus for more hardware
3x ZORRO IV, backward compatible with all others ZORRO ports.

Oh well, one can have dreams...

[ami_junki]

mate that is exactly what I was thinking, what a beautiful dream ... if only ...  :-(

[AeroMan]

darule wrote:

...Dale(video),Glenn(audio),Dave(DMA chip).

Can't we keep using ladies names  :-P

[Trev]

@da9000

Decomposition. Yes. Although I'd move that into software, probably the compiler. Now it's separate from the hardware, and the compiled code can scale appropriately depending on the target.

Everyone take note: without a major engineering breakthrough, processors are not going to get faster than they are today. It's all about rethinking how we solve problems.

@darule

That sounds like a great machine for continuing the classic legacy (although I'd ditch PCI and use PCIe and probably drop Zorro altogether); however, it's not going to move things forward.

Here's an excellent example of innovation using existing technology:

1. Ageia releases the PhysX SDK and companion hardware for accelerating physics calculations in games and other software.
2. nVidia buys Ageia, ports the PhysX middleware to its existing GPUs, and ends up with a solution that runs PhysX software an order of magnitude faster than the original companion hardware.

Here's my point: you don't need special purpose hardware. You just need a configuration flexible enough to allow your developers to make the best use of existing hardware. (Yes, "GPUs" are now general purpose processors.) That's what makes Cell, Tesla, and other low-cost, high-performance processor subsystems so attractive.

[paolone]

the sooner the world ditches x86 and moves on, the better. its about time for a revolution rather than an evolution. and when you bring something to market, it has to be a top to bottom range.

Oh my god! This foolish argument another time! You're late, my friend: the world has already ditched x86 and is moving to x64 and, anyway, the x86 has progressively improved over the years adding instructions, multiple cores, 64 bit computation and now it's the most powerful and costless architecture. No need to use something else for our everyday computing.

I'd like PPC advocates to bring to this discussion any REAL argument, because goin' on hating x86 just for the spirit of hating it is really really stupid.

[darule]

paolone wrote:
I'd like PPC advocates to bring to this discussion any REAL argument, because goin' on hating x86 just for the spirit of hating it is really really stupid.

I don't like CISC because I think it is an inefficient CPU. More instructions equals more transistors equals more heat etc. The RISC always used to be faster, at the same frequency, and still is to my knowledge.

I like to think that the CISC processor is where it today  because Microsoft is using that architecture.

Which brings me to hell called Windows. An operating system which requires insane amounts of RAM, CPU and clock speeds just to be....slow.

I work with Windows every day, because I have to, not because I really really like it. This is not meant as a rant against Microsoft, I just don't find the operating system efficient at all.

Hm, I got carried away....
Anyway, I don't believe adding more computing power is the way to get a fast operating system. I still firmly believe in a ROM-based operating system. But hey, perhaps I should be beamed back to the 90s.  :-D

[Sparky]

darule wrote:

I don't like CISC because I think it is an inefficient CPU. More instructions equals more transistors equals more heat etc. The RISC always used to be faster, at the same frequency, and still is to my knowledge.

I like to think that the CISC processor is where it today  because Microsoft is using that architecture.

Which brings me to hell called Windows. An operating system which requires insane amounts of RAM, CPU and clock speeds just to be....slow.

I work with Windows every day, because I have to, not because I really really like it. This is not meant as a rant against Microsoft, I just don't find the operating system efficient at all.

Hm, I got carried away....
Anyway, I don't believe adding more computing power is the way to get a fast operating system. I still firmly believe in a ROM-based operating system. But hey, perhaps I should be beamed back to the 90s.  :-D

Wow .. I'm amazed that in this day and age of Wikipedia and Google people still don't know very much about computer architecture.

Though I will agree with your statement about adding more cpu power is not the way to go ... elegant code is the way to performance, rather than the just compile it approach people have these days :-)

regards

Mark

[darule]

Well, I wasn't talking all bull poopoo:
:-D

RISC Vs. CISC
The argument over which concept is better has been repeated over the past few years. Macintosh owners have elevated the argument to a pseudo religious level in support of their RISC-based God (the PowerPC sits next to the Steve Jobs statue on every Mac altar). Both positions have been blurred by the argument that we have entered a Post-RISC stage.

    RISC: For and Against
    RISC supporters argue that it the way of the future, producing faster and cheaper processors - an Apple Mac G3 offers a significant performance advantage over its Intel equivalent. Instructions are executed over 4x faster providing a significant performance boost! However, RISC chips require more lines of code to produce the same results and are increasingly complex. This will increase the size of the application and the amount of overhead required. RISC developers have also failed to remain in competition with CISC alternatives. The Macintosh market has been damaged by several problems that have affected the availability of 500MHz+ PowerPC chips. In contrast, the PC compatible market has stormed ahead and has broken the 1GHz barrier. Despite the speed advantages of the RISC processor, it cannot compete with a CISC CPU that boasts twice the number of clock cycles.

    CISC: For and Against
    As discussed above, CISC microprocessors are more expensive to make than their RISC cousins. However, the average Macintosh is more expensive than the WIntel PC. This is caused by one factor that the RISC manufacturers have no influence over - market factors. In particular, the WIntel market has become the definition of personal computing, creating a demand from people who have not used a computer previous. The x86 market has been opened by the development of several competing processors, from the likes of AMD, Cyrix, and Intel. This has continually reduced the price of a CPU of many months. In contrast, the PowerPC Macintosh market is dictated by Apple. This reduces the cost of x86 - based microprocessors, while the PowerPC market remains stagnant.

[JC]

well i think if just if we had a version of Amiga os for the ps3 then that would be a pretty sweet amiga

[Trev]

@darule

Microsoft wouldn't be the only developer that preferred CISC to RISC. Regardless, today's RISC processors are more like CISC processors than they are like the first generation RISC processors--lots of high level instructions that could have been implemented by the software developer as a series of low-level instructions. But really, that sums up any modern processor, doesn't it? Instructions are microcode that translate into primitives implemented in hardware. It keeps the hardware smaller, regardless of the core architecture.

[persia]

NVidia has a market cap of 4.1 billion US Dollars, it spends hundreds of millions of US Dollars in research, what's a paltry 100 million quid gonna do?  Best to built a house on the beach in tropical north queensland, actually the Sunshine Coast would be ok.  Buy the Amiga name and start a Portuguese/Spanish dating service, no I mean give it to the community, give out the OS source and leave it to the community to develop, the Amiga is a hobby computer, let it's future be in the hands of the hobbyists.

[darule]

persia wrote: Buy the Amiga name and start a Portuguese/Spanish dating service, no I mean give it to the community, give out the OS source and leave it to the community to develop, the Amiga is a hobby computer, let it's future be in the hands of the hobbyists.

Hehe "Hablamos Español", but making it open source would be a great idea.

[darksun9210]

Oh my god! This foolish argument another time! You're late, my friend: the world has already ditched x86 and is moving to x64 and, anyway, the x86 has progressively improved over the years adding instructions, multiple cores, 64 bit computation and now it's the most powerful and costless architecture. No need to use something else for our everyday computing.

no, look, you've missed my point. my point is to start from fresh. "given the money to do what ever you liked, what would you do?"
this isn't an argument about risc vs cisc, or x86 vs ppc vs mips vs sparc. this is about having the money and giving Amiga a fresh start. which i think i covered in my last post.

i am not impressed however, by persons who tell me i am stupid and use that as the founding basis for their ideas as to why i am stupid, and in doing so display a total lack of understanding of either the intention of my post, or the topic thread.

to quote the famous philosipher 'Cartmanious',:-
"jesus f*cking christ dude."

:lol:

[paolone]

I don't like CISC because I think it is an inefficient CPU. More instructions equals more transistors equals more heat etc. The RISC always used to be faster, at the same frequency, and still is to my knowledge.

Darule, you statements about RISC and CISC are incredibly outdated. Even the words you later reported are painflully old (the Mac "ruling the RISC market"? this used to happen many years ago). Modern x86 processors are mixed CISC/RISC architectures, and they are frankly more powerful and efficient than PowerPC processors still alive are.

Anyway, Motorola 68K were CISC microprocessors and this helped a lot in developing a tiny operating system and simple applications. RISC is the absolute negation of all this, and the necessity to write longer routines to get the same results obviosuly doesn't help so much: it's better having less transistors continuously working and consuming power, or more transtistors which can be but down to a consume-less Cn state when they aren't needed?

I think all this love for RISC architectures is the natural son of the hate for Microsoft and Intel.

Anyway, if I had so much money to spend (but there would need more to accomplish the mission) I would buy all Amiga IPs, open source anything related to AmigaOS 3.1 and move to a new platform and operating system, trying to keep all the look'n'feel of AmigaOS, but focusing on stream multiprocessing and use of GPUs general purpose features. My favourite platform for now would be a X64 mainboard coupled with a RV770 GPU from AMD. With a total cost of no more than € 249, we would get a powerful and energy-saving computer with cpu, GPU, northbridge, southbridge, audio and ethernet link.

[darule]

paolone wrote:
Darule, you statements about RISC and CISC are incredibly outdated.

I feel outdated myself after that statement.  :lol:

[darksun9210]

 :lol:  :headwall:  :lol: