>> http://http.distributed.net/pub/dcti/current-client/dnetc-morphos-ppc.lha
>> http://www.219.dic.at/data/projects/native/AmigaMARK/AmigaMARK-morphos.lha
>> http://amigadev.free.fr/powerpc/nbench_mos.lha
>> http://aminet.net/package/util/moni/stream_mos

> All these benchmarks and apps are optimized for a G4.

How do you know? Which compiler options were used for each of the executables? dnetc uses AltiVec for some algorithms but these were excluded from the comparison for obvious reasons.

> If the compiler isn't optimized for a specific core, then the developer has to
> optimize the code.

In high-level languages you don't have the low-level control regarding machine code the code generator of a compiler has.

> If the code is optimized, then:
> 7448 vs. 7447 = slightly faster [...]
> 750GX vs. 7448 = on par (without AltiVec), clock by clock [...]
> PA6T vs. 7448 = on par (clock by clock) [...]
> 970 vs, 7448 = 1.2:1 (clock by clock) [...]
> P5 vs. T4 = 1:1.1 (without AltiVec) (clock by clock) [...]
> 970 vs. P5 = 1:1 (without AltiVec) (clock by clock) [...]

These specific ratios are only true for a specific benchmark, like Dhrystone, and can't be generalized for everything. An "actual speed of the cpu" does really only exist in terms of a specific task with fixed parameters.

https://morph.zone/modules/newbb_plus/viewtopic.php?topic_id=7553&forum=9&start=1

> NXP nor IBM is selling these CPUs for home computer

They are selling them for whatever purpose you want to use them for, on condition that minimum purchase quantity is met. Of course they had certain target markets in mind during development, but this doesn't mean you can't buy these CPUs if you are not in these markets. A-Eon's AmigaOne X5000/CyrusPlus is proof of that.

> buy a x86 box for 400$ and start morphOS on an emulator

Which emulator would that be than can run current MorphOS?

Andreas,

yes you are right, everything is task specific
If the code is heavy on FP-code or bandwidth use a G5, if it is AltiVec use a T4. If you have pseudo-random access tasks use a CPU with an integrated memory controller and don't use a G5.

I have only tried to put the CPUs in relation to each other ...
How do I know that the code is G4 optimized? Because for a long time it was the only CPU in Amiga land available

And yes, of course you could use every CPU for desktop use. You could also use a T4 as a curler
But that isn't the point. The question is, what's the target market?
IBM could build a really sweet desktop CPU for sure, BUT who will buy such a CPU?
If IBM tomorrow presents a CPU twice as good as everything Intel is able to offer on the desktop, how cares? If Amigaians use this CPU, how cares? Sadly, nobody.

It doesn't matter what outside the WinTel or MacTel world is going on. Nobody cares about "die hard" PowerPC or Amiga fans. Its just irrelevant.

If 2000€ is too much money for a "Amiga" computer, then maybe every morphOS or AmigaOS user should spend 2000€ for a x86 port of the OS.

Edit: It surprises me, that everyone is surprised about the performance of the NXP offerings ... who in hell has really thought, that a T4 is as fast as the latest Intel offerings? And holy ***, the X5000 does costs money ... What would be a good price of the X5000? 1000$? 500$? What production quantity? 5000pcs? 50000pcs?

[ Editiert durch AltiVeced 26.01.2016 - 20:08 ]

Quote:

It is your choice to buy an X5000 when it is available for purchase, or to continue using cheaper and faster used Mac hardware. Most people are going to agree with you and will not buy an X5000, but I don't berate anyone who decides they want to buy one, and I also don't blame A-Eon for making new PPC computers to run AmigaOS4.1FE (and now MorphOS3.10). I am sure Trevor (and Matthew) are trying to make the best decisions they can given the information available to them, and the advice they receive from their manufacturing partners, as well as the developers at Hyperion. We and many other people may not agree with many of those decisions, or the advice that led to those decisions, but I don't get all worked up, angry, or disrespectful toward the people who are attempting to do something to help the greater Amiga community.

I dislike the amount and/or severity of some of the criticism I see on forum sites, specially when it is coming from people who don't have all the facts and history that have influenced the decisions. When I do criticize any of the decisions that A-Eon managers have made, I try very hard to remain objective, and I have the advantage of knowing the people making some of those decisions a little better than most other users who have no contact directly with Trevor and Matthew. I have had the pleasure of talking with both and feel that I have a good understanding of what they are trying to accomplish, or at the very least, I think I know for certain that their intentions are good for the community, even when some people within the community feel that some or all of the choices management of A-Eon have made over the last several years, in some of the users minds, are actually bad for the community (a view that I don't agree with).

More than anything else, I respect Trevor and Matthew for their commitment and courage to invest so much of their own money and time, trying to achieve their goals, regardless if you agree or disagree with their goals, or the choices and methods used to try to achieve them. Also, I greatly dislike the way in which some of the criticism has been presented, and have found that some times, by some people (not saying this is you), have often spread information and opinions that are blatantly false, usually with great emotion and few or zero facts.

From my perspective, I blame Hyperion for most bad choices, and I firmly believe that all AmigaOS4.x users and programmers would be much better off if AmigaOS4.x had followed the example of MorphOS2.0, by porting AmigaOS4.x to G4 & G5 Mac computers (but I probably shouldn't even mention that any more, as it is ancient history, and we can't go back to change those mistakes).

One advantage the AmigaOS4.x community has over the MorphOS community is that they have far less users who waste time bashing other systems, other users, and other developers, or company choices, and they have the appearance of a more positive and active community of users and 3rd party developers. They are more vocal in a positive way and spread positive news better and more wide spread than the MorphOS users appear to be able to do, and the only explanation most MorphOS users seem to have is that they would rather have less quantity, but better quality, which is okay, but the perspective that many (most) people outside the MorphOS community have of us, is a negative one, which in my opinion has hurt our ability to gain as many new users from the remaining 68k Amiga community as we should have, or could have, but that loss is impossible to gauge or measure, so it is usually dismissed, specially by those who may have done the most harm to the MorphOS community with their hateful, or negative comments on forums like this one.

After all, we can probably count on one hand the number of new users who come to any Amiga inspired OS from outside the former Commodore Amiga 68k community each year, so not offending those former 68k Commodore Amiga users and programmers, or NOT giving them such a negative perspective is very important to our ability to gain more new users and programmers from the community where are most likely to get new users and programmers from.

Quote:

That's where I greatly disagree. If you want to benchmark use real code, not some laboratory ware.
The question for Joe Average is not what does the cpu theoretically, but which computer replays hd video best, which one provides me the most fluent browsing experience. And there will be no subarchitecture optimizes binaries for this and that. Hence, try it with ordinary code and no specially tailored one. That would be misleading.

You are kidding, right?
To not use all features/ capacities of CPU is a wise idea?
To keep it simple ... It's like building a highway with 4 lanes and only use 1 ...

For everyday use a 68k CPU should be enough ...
Give Trevor a call and tell him to use a 750 G3. It's cheap and all you need

Sorry, it's unbelievable ...

Tell the x86 guys to not use the SIMD unit of a i7. It will be fun for sure
I wonder, what do you want in fact?

> If the code is heavy on FP-code or bandwidth use a G5, if it is
> AltiVec use a T4.

AltiVec on a 2.7 GHz PPC970 may be faster than on a 1.8 GHz e6500. And are you sure that bandwidth of PPC970 is better than e6500?

> I have only tried to put the CPUs in relation to each other ...

Already done long ago:
https://morph.zone/modules/newbb_plus/viewtopic.php?forum=3&topic_id=7001&start=743

> How do I know that the code is G4 optimized? Because for a long time
> it was the only CPU in Amiga land available ;-)

For an even longer time, G2 and G3 have been used in "Amiga land". So it may as well be optimized for one of them.

> It surprises me, that everyone is surprised about the performance
> of the NXP offerings ... who in hell has really thought, that a T4
> is as fast as the latest Intel offerings?

The comparison was with a decade-old Motorola/Freescale offering, not with any latest Intel offering. That's worlds apart.

Quote:

No, I am not kidding. I am pretty serious.
Of course an optimized code for every processor would speed things up. But it messes things up, too. Look, today we have quite some differerent cpus for MorphOS already (603e, 604, 5200B, 750CXe, 7447ies, some other G4s, 970ies). But binaries don't care about that issue. They are identical for all these processors. The only exception is Altivec. Nobody wants special binaries for a particular processor, what an ugly mess that would be... If that were the case arguments against the Tabor board would be void, too. The thing is about usability in real life: One architecture/ISA - one binary. But no sub ISA binaries.

All in all it's definitely not a G3 that is good for all, but the processor that executes generic code fastest is choice #1. In MorphOS ppc land that is ibm 970. Unfortunately the 970 bysed systems have their downsides (bulky, noisy, leaky, energy-hungry).

The other thing is to realize when a horse that gets ridden is actually dead. And the ppc horse is a dead for desktop usage since a while. Put you saddle on the back of a new horse if you want to ride on.

[ Editiert durch Zylesea 27.01.2016 - 00:12 ]

> today we have quite some differerent cpus for MorphOS already
> (603e, 604, 5200B, 750CXe, 7447ies, some other G4s, 970ies).

...and 460 with 440 core :-)

> binaries [...] are identical for all these processors. The only exception
> is Altivec. Nobody wants special binaries for a particular processor,
> what an ugly mess that would be...

We already have that with special E-UAE binary for 970, and we had it on m68k :-)

Quote:

And with four times the threads, the e6500 is likely to have an advantage anyway.

BTW - Andreas, did Freescale get around to enhancing AltiVec on the e6500?

>>> If the code is heavy on FP-code or bandwidth use a G5, if it is
>>> AltiVec use a T4.

>> AltiVec on a 2.7 GHz PPC970 may be faster than on a 1.8 GHz e6500.
>> And are you sure that bandwidth of PPC970 is better than e6500?

> with four times the threads, the e6500 is likely to have an advantage anyway.

It'd be even more with the T4240 instead of the T4160 (four times the threads of 2x PPC970MP) or T4080 (four times the threads of 1x PPC970MP or 2x PPC970FX).

> Andreas, did Freescale get around to enhancing AltiVec on the e6500?

Yes, as reported 3½ years ago:

https://morph.zone/modules/newbb_plus/viewtopic.php?forum=3&topic_id=7183&start=805

"AltiVec technology for the e6500 core is essentially the same as AltiVec technology from the e600 core, except for the following:
- Adds new instructions for computing absolute differences [...] These speed up in the inner loop of motion estimation video processing
- Adds new instructions for dealing with misaligned vectors more easily [...]
- Adds new instructions for dealing with elements of vectors [...] These allow loading/storing of arbitrary elements to arbitrary addresses
- Instructions for moving data from GPRn to vector register [...]"

Doesn't look like too much.
It is hard to tell how much of a performance increase this will provide, but then, it beats not having AltiVec at all.

> It is hard to tell how much of a performance increase this will provide

None, unless the new instructions are being used. And using the new instructions means the code won't run on CPUs with "old" AltiVec, I guess. I wonder what ramifications the fact that data stream (dst) instructions are no-oped on the new AltiVec will entail, if any.

The OS4 Kommunity seems to run on a different clock than the rest of the world. Where is the X5000? Where is everything else promised? The X5000 was announced on Jan 8, 2014. I hope this boat anchor isn't holding back further proper MorphOS development.

1523804_741436842533370_1201160379_o.jpg

> The X5000 was announced on Jan 8, 2014.

Yes, this was when the "AmigaOne X5000" name was decided upon. The Cyrus mainboard itself was announced even half a year earlier:

https://morph.zone/modules/newbb_plus/viewtopic.php?forum=3&topic_id=7001&start=780
http://www.amiga-news.de/en/news/AN-2013-07-00015-EN.html

> I hope this boat anchor isn't holding back further proper MorphOS development.

At least the delay of the X5000 won't hold back MorphOS development ;-)

Quote:

Good point, this is really snail pace.

Quote:

Maybe not if the machine actually gets released to end users. If A-Eonkit goes belly up and the X5000 never gets released, then it seems to me an awful lot of development time has been wasted that could have gone into the ISA switch.

I doubt they will go bankrupt. Trevor doesn't do it for the money. It seems that he don't mind losing the money invested either. I bet he want as much of it back as possible, but if nothing comes out of it except for a little fun I think he is satisfied.

>>> I hope this boat anchor isn't holding back further proper MorphOS development.

>> At least the delay of the X5000 won't hold back MorphOS development ;-)

> Maybe not if the machine actually gets released to end users. If A-Eonkit goes
> belly up and the X5000 never gets released, then it seems to me an awful lot of
> development time has been wasted that could have gone into the ISA switch.

From the point of view of someone who calls the X5000 a 'boat anchor', imminent release, further delay or even entire cancellation won't make a difference as development time will have been wasted for porting either way.

Quote:


A-Eon is a registered Limited company. Granted that probably means different than I am used to in the US, but it is not something that Trevor is simply going to throw money at forever.

According to the latest filing, A-Eon has £86,381 in the bank and £673,447 in short term debt which is coming due in the coming couple months. I strongly doubt sales of 3D drivers and a few games on AmiStore will be enough to service that debt. A-Eon's hands may be tied by HYPErion, they don't seem to want to release the hardware until OS4.1 is done and development appears from the outside to be halted.

Quote:

I call it a boat anchor because it seems to have acted exactly as such. Development of OS4.X has come to a screeching halt, just like a boat tossing an anchor into the ocean. On the MorphOS side we hear that support of further PowerMac G5 models (PCIe) isn't proceeding due to focus elsewhere, which is likely X5000 work. Just speculating but makes sense. If the X5000 ends up being canceled, the work put into it sure has acted like a boat anchor IMO.

@redrumla

Trevor is rich and somewhat eccentric. I think he can keep his company floating until he can release the X5000. Heck, it's even possible that he will release it anyway with only MorphOS on it if the AOS 4 port takes too long. With a promise of an upcoming 4.1 I bet a lot of fanboys are going to buy the board anyway, even if they are just gonna look at it or run PPC Ubuntu on it (I doubt many of them will even touch MorphOS). Don't forget that the boards are already made. I seriously doubt Trevor would prefer throwing those away than letting them be runned on a non AOS 4 system.

MorphOS Team is not just working on the X5000 port, but also on drivers for Radeon HD cards which will also benefit SAM 460 users and a possible G5 PCI-x port. And then we have all the internals that is being worked on too. The Team isn't focusing on the X5000 alone.

>>>>> I hope this boat anchor isn't holding back further proper MorphOS development.

>>>> At least the delay of the X5000 won't hold back MorphOS development ;-)

>>> Maybe not if the machine actually gets released to end users. If A-Eonkit goes
>>> belly up and the X5000 never gets released, then it seems to me an awful lot of
>>> development time has been wasted that could have gone into the ISA switch.

>> From the point of view of someone who calls the X5000 a 'boat anchor', imminent
>> release, further delay or even entire cancellation won't make a difference as
>> development time will have been wasted for porting either way.

> If the X5000 ends up being canceled, the work put into it sure has acted like a
> boat anchor IMO.

And if it will get released, porting MorphOS to it won't have held back "further proper MorphOS development", acting like a 'boat anchor'?

> a possible G5 PCI-x port

PCIe or PCI-E :-)

Quote:

I think this is a myth, carefully cultivated for some reason, probably to raise goodwill or some kind of saint status around the AeonKit business sphere. A marketing twist. Like they "saved" those community forums they bought, like they "saved" those old pieces of SW they bought, like they "saved" the developers by funneling them through their "app store". You don't sell €3,000 machines as "charity" or to lose money on purpose. That's my firm opinion.

They have a huge gamble in the X5000, it's long overdue, and it has turned out that it won't be offering any significant performance gain over current PPC machines (a platform that is hopelessly behind anyway). And if the rumors about a thosand Tabor motherboards (with that uncompatible FPU) already built and paid for is true, then a huge loss is a fact. A lot of money. A lot. For nothing. Excentric or not, nobody likes flushing huge amounts of money down the toilet. That wouldn't be excentric, that would be insane.

If the X5000 fails, and if the Tabor fails, don't expect him to keep pumping in huge amounts of money in sequel gambles. Especially not given the obvious hopeless OS4 situation, that must be really frustrating for them.

"AeonKit aren't doing it for the money" - Well, I call that bluff...

well, at least morphos 3.10 release is not depended on X5000 release.

no. it's just postponed because of this (because of OS4 is not ready yet).

Quote:

I don't see any reason the X5000 would fail.
Tabor, while not a good solution, is still likely to be purchased by the OS4 fanboys that want a low cost system.