»

[takemehomegrandma]

@Iggy

(A break-out from the X1000 dnetc benchmark thread)

Originally Posted by Iggy

You like long winded posts, but you never offer any proof for your statements.

I'd really like to see a benchmark on the second one since it seems implausible.

"A Cortex-A8 (Efika MX) beats a Sam440"

PPC440EP: 2.0 DMIPS/MHz, meaning 1,334 DMIPS @ 667MHz of a Sam440ep
Cortex-A8: 2.0 DMIPS/MHz, meaning 1,600 DMIPS @ 800MHz of an Efika MX

NBench pictures the Efika MX as generally faster, even after upscaling the Sam results to 800MHz. In addition to this, the CPU used in the Efika MX has several HW accellerators that will offload and speed up many multi-media tasks from the CPU, like audio/video encoding/decoding, OpenVG, it has a SIMD (like Altivec, but not as powerful) called Neon, etc. None of this is present in the PPC440EP, which doesn't even have a L2 cache (the Efika MX CPU has 256KB). For example, the Efika MX can decode and display 720p HD video streams (it can actually decode 1080p streams, but not display it at 1080p resolution, due to some bottle necks that was removed in the i.MX53 version). The Efika is the winner.

Oh, and for the sake of comparison:

Efika MX: $129, giving you a complete, fully working system for most uses (but yes, rather limited and not expandable)
Sam440: ~$600, giving you a *motherboard only*, system components of choice *on top* of this, plus the mandatory OS4, all in all "north of" $1,000.
VAT not included.


"A Cortex-A9 beats a G4"

MPC7447A: 2.3 DMIPS/MHz:
This should mean about 3,266 DMIPS @ 1,420 MHz (a *fast* G4, used for example in a Common Mac Mini)

Cortex-A9: 2.5 DMIPS/MHz (*per core*, can have 1-4 cores):

A *generic* Cortex-A9 from ARM (used in Apple A5 and Tegra 2 for instance) delivers 2,500 DMIPS per core @ 1,000 MHz, meaning 5,000 DMIPS per CPU in dual core configuration.

Then there is the upcoming (summer 2012?) Qualcomm Krait, that isn't simply just using the generic core, but optimized and tuned to improve the per-core performance to 3.3 DMIPS/MHz (built using 28nm process), resulting in a staggering 9,900 DMIPS @ 1,500 MHz.

The Tegra 3 is a *quad-core* Cortex-A9, running up to 1.300 MHz (times 2.5 DMIPS/MHz, times 4 cores). It's "up to 3 times faster than Tegra 2 (measured with GLBenchmark 2.0 Egypt)", still being Cortex-A9, still being built in a 40nm process. Actually, the Tegra 3 is a "five core" CPU: "The Tegra 3 is the world's first variable symmetric multiprocessing processor (vSMP). Variable SMP is the brain that makes the 4 main + 1 companion core setup tick. Basically, it smartly distributes the workload so the platform uses four cores humming at up to 1.3GHz when needed (think games), but switches to two for lower loads (think browsing with Flash), and goes down to one for casual activities (browsing, no Flash). Finally, it can also use only the companion core running from 0 to 500MHz for active stand-by, video and music." (Link: An Interesting Article on the Tegra 3)

The scaled NBench numbers (measuring *one* of the cores on an "old" OMAP4 based 1GHz PandaBoard) suggests that the Cortex-A9 is about on par with the G4, but again, much has happened to the Cortex-A9 CPU's since that one was made, and since most Cortex-A9 based CPU's come in dual core configuration (or quad), I actually feel my statement that Cortex-A9 beats a G4 is water proof. In addition to this, the Cortex-A9 processors (like most other ARM processors) also come with various HW accelleartors on the chip, freeing the core CPU from the most common heavy multi-media tasks, vector graphics/GUI/Flash, hardware Java/JIT acelleration, etc, things that the G4 simply don't have.


And while we are at it: Some speculations about Cortex-A15 and G5

While not being a 64-bit CPU (although it will at least be able to address up to 1TB of memory thanks to the 40-bit Large Physical Address Extensions (LPAE) addressing), the Cortex-A15 will probably be giving the old G5 a match, with its 3.5 DMIPS/MHz in configurations suitable both for mobile, high-end home entertainment, or low-power servers, up to quad core running at 2.5GHz (or for servers for example, octo-core or larger configurations through multiple coherent SMP processor clusters through "AMBA 4").

For example the announced dual core: "ST-Ericsson Nova A9600 (Dual Core @ 2.5 GHz Over 20K DMIPS)"

Iggy, this is a quote from a post you made here on amiga.org back in 2010:

e300: 1.9
PPC440: 2.0
PPC460: 2.0
Titan: 2.0 (presumably PPC450 based (http://www.morphzone.org/modules/new...start=20#74317))
PA6T: 2.2
PPC750: 2.3
e600: 2.3
PPC470: 2.3 or 2.5 (varying with information source)
e500mc: 2.5
PPC970: 2.9
e5500: 3.0

As a reference to year 2012 ARM (some in quad core with clock frequencies up to 2.0-2.5GHz):

ARM Cortex-A7: 1.9
ARM Cortex-A8: 2.0
Qualcomm Scorpion: 2.1
Marvell Sheeva PJ4: 2.4
ARM Cortex-A9: 2.5
Marvell Sheeva PJ4B: 2.6
Qualcomm Krait: 3.3
ARM Cortex-A15: 3.5

This is current or immidiate future (like this year), not even mentioning the not-too-far-away 64-bit "x86-killers" from nVidia and others, based on ARMv8.

[commodorejohn]

Be interesting to see how newer PPC processors stack up - certainly there's more memory bandwidth to go around than with the G4s, which never got past 166MHz (not even DDR-capable.)

[Duce]

Interesting numbers, a good read, Takemehomegrandma. Cheers for posting it.

As for why things haven't migrated to a more modern platform, God only knows. Niche market, no financial reward for the amount of work, who knows.

Some people say if they wanted a x86 or other modern chipped Amiga, AROS is there. A valid point. I've often griped about HW issues with AROS, but the truth is it runs very well on supported HW and that HW list is getting bigger day by day.

The MOS camp have the luxury of the OS running on extremely cheap, readily available PPC Mac's. This has served them very well, and the OS is great, the old PPC Mac's are still easy to find. It won't be that way forever, though - and I imagine they are looking towards more modern platforms for future releases.

AmigaOS? God only knows why they have stuck with it (PPC). My only guess is because PPC is what OS4 runs on now, and perhaps there's simply no manpower or financial rewards to port the whole OS over to ARM or something for them. Then again, the first thing I'd do with OS4 is make it run on PPC Mac's if I ran the show there atm. It's a niche market, and OS4 limited to expensive PPC embedded boards is a true shame.

[takemehomegrandma]

@takemehomegrandma

And now to the *actual point* of my initial post:

No, I'm not necessarily advocating ARM as *the* path to glory for *miga OS's. While ARM without doubt have its significant benefits, and this architecture indeed has a lot of focus from the whole industry, there are some issues as well. Mainly (IMHO): "Consumer Electronic Devices", i.e. not having a broad base for general, open "desktop" systems is probably the main one. Genesi and Pandaboard are two, are there more? Maybe it will be? Genesi is now working on producing a Cortex-A9 design based on the Freescale i.MX61 though, and may very well continue developing new systems whenever Freescale releases a new CPU...

But I wouldn't object to a x86 MorphOS system either! No, no! That's not the point I'm trying to make!

Some people say that one of the most important things of the X1000 is that it is dual core, and thanks to this, SMP can be incorporated in the *miga OS from Hyperion. (The PowerMac G4 has dual CPU configurations as well BTW)

But here is the point:

Judging from what people have requested over the last decade, and also judging from what seems to be the ambition from some OS developers, "Moving Forward" may at some point mean the incorporation of some of the "modern" OS features, like true SMP, true MP, 64-bit, etc. And since this *will* require a clean-slate break from the Amiga legacy anyway (it must happen if you decide to go there), with a clearly defined border line marking the "before" and "after", the seemless "Amiga compatibility" scrapped post that line, starting anew, I must ask the question:

At that point, why continue the PPC path?

If you are to break the "Amiga" anyway, why not do it on some other architecture. My point is that even ARM seems to beat PPC. Performance wise, and from a desktop Point of View, x86 is even more attractive.

Isn't a platform migration the natural thing to do at that point? There is no "Power" in PowerPC, not in the year 2012 and beyond! ARM and/or x86, but not PPC!

Right?

[takemehomegrandma]

Originally Posted by commodorejohn

Be interesting to see how newer PPC processors stack up - certainly there's more memory bandwidth to go around than with the G4s, which never got past 166MHz (not even DDR-capable.)

AFAIK, the MPC8610 (the last of the "G4"?) from Freescale had an on-chip DDR/DDR2 SDRAM memory cotroller @ 533 MHz (1066 DDR)...?

[commodorejohn]

Originally Posted by takemehomegrandma

AFAIK, the MPC8610 (the last of the "G4"?) from Freescale had an on-chip DDR/DDR2 SDRAM memory cotroller @ 533 MHz (1066 DDR)...?

You might be right, though either way it never saw use in Mac or Amiga-like systems...

[takemehomegrandma]

Originally Posted by commodorejohn

You might be right, though either way it never saw use in Mac or Amiga-like systems...

Exactly like...

"Be interesting to see how newer PPC processors stack up"

...then?

[zylesea]

THGM

While ppc is not the saviour of us all it has the benefit that MorphOS/AOS4 runs on it already. That is the *only* benefit of ppc over other architectures that holds some significance.
Hence the real question is not "ppc or ARM?", but "ppc or not ppc?". And in case of not ppc - why on earth should you choose ARM over x86 which is _for GP computers (aka PC)_ factors more widespread and very powerful and will not vanish in the foreseeable future.
ARM holds _zero_ significance fo Amiga today. There are virtually no powerful general purpose computers based on ARM available, but a gazillion of x86 pcs.

[takemehomegrandma]

Originally Posted by zylesea

THGM

While ppc is not the saviour of us all it has the benefit that MorphOS/AOS4 runs on it already. That is the *only* benefit of ppc over other architectures that holds some significance.
Hence the real question is not "ppc or ARM?", but "ppc or not ppc?". And in case of not ppc - why on earth should you choose ARM over x86 which is _for GP computers (aka PC)_ factors more widespread and very powerful and will not vanish in the foreseeable future.
ARM holds _zero_ significance fo Amiga today. There are virtually no powerful general purpose computers based on ARM available, but a gazillion of x86 pcs.

Please zylesea! I guess you didn't read post #4?

Again, I wasn't really trying to promote ARM in front of x86! I would actually prefer a x86 port myself! The initial post was merely a "prelude"!

Rather it was a question to those who (with the advent of X1000 etc) begin to look for features like SMP, MP, 64-bit, etc, and the question I was trying to rise was: "Since that would require a break from the past, why continue with PPC at all? Why not bring the new platform onto a modern architecture?"

For example, if MorphOS developers would want to start exploring 64-bit support for the future (as suggested by Fab in his presentation of MorphOS future), why would they do that on a *dead* G5 platform (or PA6T for that matter)? I mean, if the legacy is to be broken anyway, why not migrate to greener pastures while you are at it?

And indeed, there are many reasons to choose x86 over ARM...

[TheBilgeRat]

I would think ARM is attractive in the sense that it is getting tiny and very efficient compared to x86. I am not too sure what modern PPC platforms or chips you are referring to. Is there a link somewhere to cheap modern PPC chips?

[SamuraiCrow]

Since getting PPC performance up to snuff requires compilers with cache hints and other tricks, I see no reason to continue the PPC path. It was a temporary kludge.

ARM is the cuts a lot of cruft out of other instruction sets including the x86. Though the AMD64 has better developed software that Amiga cannot use, ARM looks more promising.

Going back to 68k is more promising, for that matter. Since the N68050 is slated to contain some of the same features as modern ARM processors, it just is a matter of finishing it up and getting it on the market so we can work out more bugs and get it mass-produced someday. If the N68070 cannot beat the performance of a 68060 per clock cycle, it might make sense to switch to AROS for ARM.

I look forward to the Raspberry Pi, even if it doesn't run much Amiga software.

[freqmax]

If ARM is the CPU to go around, then use it? The original Amiga idea was to use the best available technology for a given (low) price. That in turn makes it possible to grab a huge market section, which is why there is still Amiga fans around. The other is just that "the best" choice you can make for hardware within a given budget. Which will attract persons that appreciate sound technology choices.

Next objective, which graphics chip will give the best bang for the buck?

And will this translate into the best low price multimedia platform, which seems to been the nische for Amiga ..?

[Digiman]

I have 2 question,

1 is ARM better price/mips than the cheapest i7?
2 is there an ARM CPU for sale today as powerful as the fastest i7

If the answer is not yes to both then OS4 needs to go x86 and be optimised for i7 multiple cores and hyperthreading IMO.

My $0.02 worth.

[Iggy]

Very good arguments, takemehomegrandma.
I don't really disagree that ARM is an attractive option.
I'd just like to see MorphOS on a G5 before the transition to ARM or X86 begins.

Moving to another ISA will take a considerable amount of time and effort.

A G5 port would be much easier/quicker and would give us some more powerful equipment (available at a low cost).

Oh, and the DMIPS figures are from Andreas Wolf.

[haywirepc]

You answered your own question I think as to why AMIGAOS4.x will never be ported to x86 OR ARM.

The amiga grave robbers LIKE robbing you for hardware that has specs my 50$ phone beats. Why would they want to port it to something inexpensive when people are paying ridiculous prices for hardware thats so ****ty?

They will NEVER port it to an inexpensive platform while people are paying such high prices for such old spec junk.

Steven