> AMD did lead the move to 64 bit.

...12 years and 7 8 ISAs after the first one ;-)

https://morph.zone/modules/newbb_plus/viewtopic.php?forum=3&topic_id=7675&start=17

[ Edited by Andreas_Wolf 10.03.2022 - 12:10 ]

Quote:

Personally, it still looks like the evolution of one ISA to me.
There is a much greater degree of backward compatibility here then say differing Power families.
But I am sure you will contest that. ;)

> it still looks like the evolution of one ISA to me. There is a much greater degree
> of backward compatibility here then say differing Power families. But I am sure
> you will contest that. ;)

Absolutely ;-) PPC64 and PPC32 are much more alike than x86-64 and x86(-32) or AArch64 and AArch32. The reason for the good backward compatibility in the latter cases is the fact that these 64-bit processors separately implement the 32-bit ISA in addition.

Quote:

Good answer.
A fine line, but valid.

Update:

>>> in terms of 64-bit ARMv8 (AArch64) cores, there is announced so far:
>>> - Cortex-A53, Cortex-A57 and Cortex A-72 from ARM Ltd.
>>> - Denver from nVidia
>>> - X-Gene from Applied Micro
>>> - Thunder from Cavium
>>> - Cyclone and Typhoon from Apple

>> - Vulcan from Broadcom
>> - K12 from AMD

> - Kryo from Qualcomm

- Xiaomi from Phytium

http://www.theplatform.net/2015/08/25/inside-chinas-homegrown-64-core-arm-big-iron-chip/
http://www.eetimes.com/document.asp?doc_id=1327526

For me i am absolutly sure that Morphos will be ported to AMD64 arch, i don't know the target machine but it's not the problem. All powerpc software could be ported on AMD64 well...but it's just a problem for 68k apps, for me i don't use any 68k app for now...i prefer using e-uae whith jit. On AMD64 E-UAE will be dramatically faster ....just like a bullet.
If the switch occur it could be the time to add memory protection and smp and lot of things, backward compatibility is not the way .... it will be better to recompile lot of sdl and application for the new morphos.
I am sure that people who are saying AMD or INTEL sucks today will change their mind when they will see a new morphos without amigaos limitations but whith all the spirit of amigaos. It will be transparent for end user, just better and easier for programmers.
It's the time to change the rules......whithout many work AMD 64 could launch Owb whith Javascript jit...Many emulators whith jit; many games which have endianess issues.....
More devellopers we have more software we have.....
To help for hardware support we can imagine that morphos could be hosted by an another kernel like quark on powerpc machines.
A bit like amithlon....

[ Edited by acepeg 27.08.2015 - 21:48 ]

Intel, Amd, and the other X86 vendors used to suck.
From the '386 onward things have steadily improved.
Once AMD introduced the Athlon, I really started to be impressed, and the move that AMD started to X64 really solidifies the ISA.

So, I'm pretty much over my anti Intel bias.
Although I DO think RISC processors are a better solution (but then we don't really want to get down to what is really running at the core of some "X86" cpus).

Quote:

You mean how they are all RISC under the hood?

Not that it matters one bit. It was a long time that thing stopped to matter. A PPC CPU saying "RISC processors are a better solution" to a current Intel Core i3/i5/i7 CPU, is like an A500 saying "Only Amiga makes it possible" to a PS4.

Quote:
Yep, not many people realize that processors no longer directly execute their opcodes.
I think the last hard coded cpu may have been the 6809.

As to the rest, its really a pointless argument these days isn't it?
And we don't need that much horsepower.
Today's PPC and X64 cpus are more powerful then we need.

Not that we can't always use more power.

I do not like it either. I want a MIPS port. It would be a perfect for MorphOS to have MIPS, to retain uniqueness. As an alternative, I would enjoy seeing MorphOS ported to a Pi device.

But neither will attract sufficient new developers apparently.

I do hope that they will consider AMD instead of Intel, and if successful (attracting at minimum 100,000 new users and a 100 more developers) then ports to all the other architectures and other Hardware including fully support of Power Mac G5, and Minimig might be possible in perhaps 25 years.

[ Edited by In_Correct 28.08.2015 - 10:39 ]

> I think the last hard coded cpu may have been the 6809.

Interestingly, the 68060 is completely hard-wired while the 68040 and prior use microcode.

Quote:

We don't?

And please don't put an equal sign on PPC and x64, not only do they not play in the same league, they are in different dimensions today.

Heavy graphics editing/processing (á la Photoshop), 3D rendering, applications for video editing (á la After Effects on PC/Mac) and encoding, music creation (with lots of stacked SW synth's/VST plugs like on PC/Mac), etc, all historical "Amiga" strengths (a in a different time of course, using different methods than today of course, and Amiga of course never saw these kind of programs, but anyway ), they will all happily swallow all CPU power you throw at it. Especially if you want to view results (or at least previews) in real-time, which really is something that benefits any creative process.

Of course I know that there are no such programs for Amiga, and if possible it will be even less for the new MorphOS once it gets here. And I'm not claiming there will ever be any either. But without the CPU power of modern Intel's, there is also no point in writing such applications. You've got to start somewhere!

And when speaking of writing SW, it deserves to mention that SW development/compiling large projects require a lot of CPU power. Ask Fab what machine he uses to compile Odyssey for example. I would be surprised if the very MorphOS releases we use today isn't built on x86 machines as well.

Heck, even everyday stuff like web browsing (especially heavy, media-centric sites) and media playback of various kinds could use a lot more CPU power than we can get from our PPC machines...

And 4k is about to break through, stuff like augmented reality, VR, etc. Not saying that we will ever have such applications, I'm not naive, but without the processing ower, the chances are 0%.

Quote:

I don't, that wouldn't make sense IMHO.

Quote:


There's a simple IT rule: You cannot have too much computing power!

Quote:

From one µnice to another µniche? Well, some ppl actually like to bang their head against th ewall all day long....

No ....AMD64 is the best way for many reasons...AMD graphics card whith pci express will be also supported (os4 support partially such cards)
I prefer also ISA like arm or mips or powerpc e6500 but i fact there is no desktop machine mass producted with those ISA... and the power stay behind AMD64. Arm cortex A15 is a lot faster than Intel Atom; but versus a core I3 or any AMD FX it's not the same.
Processor power is a need for descent browsing speed,for html5 games like angry birds for exemple....

Amd64 ISA offert more power for lower prices.....it's not a joke...it's real.
Powerpc is dead for desktop, Mips is only for super computers, no mainstream manufacturer use it. And Arm is growing fast, it's interesting but only chromebook use it for now.

[ Edited by acepeg 28.08.2015 - 22:35 ]

@acepeg

I don't mean to insult you, but I think it's a bit difficult to decide if you are trolling here or if your arguments are honestly meant? Anyway, I'll bite: MorphOS has supported Radeon's since forever, and I see nothing that suggests that this is about to change, rather the opposite, the latest MorphOS releases suggests future Radeon HD support quite far up in model generations, and there is IMHO no reason to think that this will stop. No nVidia in sight, as far as I can see! ISA doesn't really matter to anyone (not to very many at least) besides compiler developers, right? And AMD64 is the same ISA as "Intel 64" (X64, X86-64 etc) anyway. And I don't really think the reason to migrate to another CPU architecture is to be "low spec" like Atom, PPC is already low spec.

I agree that ARM is a very interesting and rapidly developing platform (hence this thread ), and that it's indeed being developed into new market segments. But it's not yet a "general" architecture per se, at least not from a desktop OS's perspective, so it would ideally require some kind of wealthy HW partner "in for the long run" for MorphOS to build a future proof existence there. X86 (Intel of course! ) on the other hand is a widely available, very powerful, and a very cost effective platform. It's definitely the most future proof, powerful, bang/buck platform there is!

Maybe some time in the future there will be an ARMv8 version of the Raspberry Pi, maybe a "Raspberry Pi 3"? Or maybe someone else will build an open and mass produced ARMv8 board suitable for desktop usage? And preferably more than one? And maybe the MorphOS Team has made (will make) the future MorphOS as HW independent that a port to ARM will be painless?

> Mips is only for super computers

It's also used for datacenter (Broadcom, Cavium), networking (Qualcomm, MediaTek) and portable applications (Ingenic).

> no mainstream manufacturer use it.

MIPS cores are used in mainstream networking equipment.

Quote:

I don't believe this to be true of any 68k processor, but we can check.

@takemehomegrandma

You are on quite a roll tonight.
I hope we continue to support discrete Radon video cards too, but AMD APUs offer similar gpus in an integrated package.
It wouldn't bother me in the least if we supported those.
And I have never favored supporting only the largest player in the industry, as lack of competition defeats innovation.
Plus, when Intel made the mistake of betting on the Pentium 4, AMD products were kicking their ass.
I don't anticipate Intel failing this way in the future, but without competition they WILL try to feed us similar crap.
As to the comparable power of PPCs vs. X64 processors, they are not nearly as far apart as you seem to think. Even ARM is approaching a competitive stance with X64.
And, as you have pointed out, its all microcode based anyway.

Quote:

+1 Thanks.

Quote:

You can't be serious?! You don't see the difference between a proper Radeon R9 GFX card (or R7 or most other current Radeon GFX cards) on a proper Intel Broadwell Core i5 platform with decent performance Intel chipset, and some integrated AMD APU crap? There was a point in time where you could say about AMD CPU's that "well hey, at least it's cheap". But that was a looong time ago, IMHO AMD lost its relevance on desktop computing somewhere back when PPC became obsolete.

Quote:

I bet it wouldn't, after all you are advocating a "future" based on PPC...

Quote:

Yeah, let us make the purpose of next generation MorphOS to even out the x86 market shares out of some ideological "fairness" reason, and MorphOS betting its life on the notorious number two will really make a difference and change the x86 market in this regard.

Quote:

Pentium 4?!?? Really...?

Quote:

Yes, because feeding the world crap is how Intel became the single relevant player on the Desktop market...

Quote:

Yes they are. Not even in the same dimension.

Quote:

No, not really, not in a desktop context.

Quote:

Oh my god...

>> the 68060 is completely hard-wired while the 68040 and prior use microcode.

> I don't believe this to be true of any 68k processor, but we can check.

"MC68060 [...] is all hardwired - there is no microcode in it."
http://www.faqs.org/faqs/motorola/68k-chips-faq/

From the Freescale/NXP website:
"The Motorola 68K family consists of a wide range of members from the micro-coded MC68000 to the super-scalar, hard-wired MC68060."
https://www.nxp.com/docs/en/supporting-information/MC680X0OPTAPP.txt

From Motorola's Jim Reinhart:
"the 060 execution units are fully logic driven (i.e. no microcode)"
http://www.verycomputer.com/154_1d1b5950dff465d3_1.htm#p4

From Thomas 'thor' Richter:
"In 1982, CISC CPUs where mostly controlled by microcode, hence slow. A 68K required multiple cycles for a single instruction [...]. 68060 was hardwired again, and could run many instructions in one cycle [...]. [...] the 68K is microcoded. The 68060 is not [...]."
http://forum.amiga.org/index.php?topic=71284.msg812454#msg812454
http://forum.amiga.org/index.php?topic=71284.msg812522#msg812522


Edit: added another quote
Edit2: corrected some obsolete links

[ Edited by Andreas_Wolf 06.01.2020 - 14:08 ]

> There was a point in time where you could say about AMD CPU's that "well hey,
> at least it's cheap".

There was a point in time when AMD CPUs were faster than Intel CPUs. Jim is correct here.

Quote:

Thanks Andreas,
That really confirms what I've heard over the years (that there conflicting views on this).
My information came directly from Motorola engineering in the early '90s.
So, as we were using the 68000, getting ready to use the '020, and the '030 was on the horizon (but the '060 was long off), I'd be willing to say the 68K family is entirely microcoded.

BUT...here is the problem, there is no way to confirm anything.
The structure of these chips is totally "black box".
We have diagrams showing us the logical parts and we have the instruction set, programming modes, and other useful info but no real info on the actual logic.