dnetc benchmarks

[zylesea]

The poor performance of the PA6T could shed new light on the whole ISA shift affair by Apple. I mean, the PA6T was (inofficially) the scheduled successor of the 744x in Apple's laptops. But it performs rather worse. Not well suited for a 7447A successor laptop. ibm hat no fitting offerings for Apple and Freescale's 86xx were also not the huge step forward. No wonder why Apple looked elsewhere eventually.
But okay, Apple would have had one huge advantage over AOS4 and the X1000, tOS X has SMP support, so a Powerbook PA6T would have benefited quite a lot from the 2nd core.

Anyway, from those historical what-if games I would like to see an benchmark between a PA6T and 8641D based system. It seems to me as if Freescale's chip would have been the better choice eventually. A shame it was not used in a GP computer back when it was current.

[zylesea]

Is it possible to buy G4 processors new from anywhere these days?

Not talking about old mac's or whatever, but are there sources where factory new chips for a new computer design could be sourced, or is that a completely closed off option?

Freescale still sells 744x processors, e.g 7447A:
http://www.freescale.com/webapp/sps/site/prod_summary.jsp?code=MPC7447A&tab=Buy_Parametric_Tab&nodeId=018rH38653&pspll=1&fromSearch=false

or 7448

http://www.freescale.com/webapp/sps/site/prod_summary.jsp?code=MPC7448&tab=Buy_Parametric_Tab&nodeId=018rH38653&pspll=1&fromSearch=false

Prices are high, but not completely nuts.

But G4 series rather shifted to the 86xx chip line - which unfortunately never made it into a GP computer..

[zylesea]

The 8640 would definitely had been an option. It is a rather expensive ship, but still way cheaper than teh PA6T according to some AEon information which was about 500 US$ for each PA6T.
Plus Freescale is really helpful, they are still intersted to get their products out to the wild (genesi had and have a good support by them), other than PA Semi which is a company swallowed by Apple.

The 8640 has one or two e600 cores (aka g4) as known from the 7447A (Mac mini) or 7448 (some 3rd party cpu cards for Powermac G4). But it has a fast bus. Well, not as fast as the PA6T bus, but still quite fast, RAM interface is 600MHz DDR2, FSB is 200MHz (PA6T RAM interface is 1066MHz DDR, FSB is 233MHz).
But the difference of system performance between a PA6T and 8640D systen is probably only little. 8640D has the big advanatge of a proven and known core and a company behind it supporting it still actively. I was always in favor of the 86xx chips.

[zylesea]

Iggy:

We are agreeing on these issues pretty much anyway. The 86xx would have been nice a few years ago. While I still think the 8610 would still be acceptable for a very compact and cost sensitive system (I suggested it as better alternative to Acubes choices in several threads for some years already), the 8640 is no longer a vialble path to follow, since the T50x0 is soon to arrive and will leave the 8640 ways beyond.

[zylesea]

Pegasos I and II.
Perhaps you mean there is no new MorphOS specific machine available

Plus Efika5200B. A shame it came with too little RAM and such a slow ide. But still a nice tiny board for little money ($99) a few years ago.

[zylesea]

Can you provide a link to that information? $500 for a CPU (particularly one designed for embedded systems) is farkin' ridiculous, that's what P3s cost new in 1999. Hope they didn't pay that kind of cash for all the parts...

I quote from the exclusive interview with Trevor Dickinson from http://amigatronics.wordpress.com/2011/04/08/exclusive-to-amigatronics-28-questions-and-28-answers-with-trevor-dickinson-a-eon/

12.
What do you think is the solution for a market so little as Amiga? In my opinion, the price of AmigaOneX1000 could be reduced and that could help Amiga to grow faster again. Don´t you think so?

Unfortunately no.  The AmigaOne X1000 is based on the PA Semi CPU.  This component alone costs $500 and when you add in development costs and factor in the high cost of low volume manufacturing there is no way to reduce the sales price for the Amiga market. Also see my answer to question 11.

$500 for a PA6T.

[zylesea]

at the end of the day who the hell cares?

All those ppl who want to have the fastest Amiga ever. While I am not a big fan of OS4 myself even I would have considered an X1000 if it were really fast and giving me a big computing power benefit over what  have already. Well, it doesn't. I think that's highly interesting and valuable information. Saves me $3000 at the end of the day.

[zylesea]

I know that the soon to be released Netbook will fill the low price OS4 problem with hardware.

Do you really believe that netbook will come soon? I have my concerns on this. No public demonstration, nothing except the talk at Amiwest. And confronted with the question whether it will be a THTF/MTC 5121 based design or not only silence. It will. And hence it will come with all the 5121 weaknesses.
SSolie not even sure about the screen size is telling how serious that whole thing is. It is just a placeholder for "oh yes, we have a laptop, too", telling the crowd between the lines not to buy an "old crappy Powerbook" to run MorphOS on it.

[zylesea]

Has anyone did any benchmarks yet with Linux running on both cores?

It would be interesting to see the possible future Potential with SMP support for OS4x.

Well for a perfectly symmetrically balanced system you mag gain a speed increase of the factor lim 2. In evryday usage it depends quite a lot. Take that lame test. alme itself is nt multithreaded, but a nice frontend can just launch several instances of lame. On a system more or less idle execpt doing the lame encoding this could really yield to a speed increase of nearly the factor of 2. Thing is, you need an SMP system to benefit from the 2 cores in a balanced way, or an AMP system with quite some apps written to use the 2nd core if available.
SMP is out of question for OS4 as long as a high backward compability will not get discarded, AMP is rather easy possible, but requires Applications to support that (also possible, but they don't com efrom above like the Manna). I *highly doubt* AmigaOS 4.x will benefit seriously from the 2nd core before 2014.

[zylesea]

So you are really saying that because the X1000 looks like it "might" be slightly slower than a mac you won't be buying it? Also again this makes no sense as you'll only be using it to run OS4 so at this precise moment it's the fastest OS4 machine, if you want the fastest MOS machine you get a mac.

No. It's the other way around. Because the X1000 is not significantly faster than what I have already it it totally pointless and uninteresting for me.
If it were significantly faster I might have considered one machine. But with those results - no way!

[zylesea]

What have you got?

Among other hardware there is a Mac mini G4 1500, a Powerbook 1.67 is on the shopping list. And to avoid your next respond "but this s not Amiga". Indeed it is not called Amiga and OS4 doesn't run on it. But MorphOS. Well and if you refuse to see why MorphOS s amigaish as OS4 except the tademark and some antique code snippets I give you a link to my statemet what MorphOS is: http://via.i-networx.de/wim.htm

[zylesea]

Good question, and given all the PPC suppliers are switching to ARM, one they are going to have to answer fairly soon.

Quite a bold statement about *all* ppc suppliers. Freescale isn't switching to ARM - they are supporting both, ppc & ARM since ages. And I don't see ibm going ARM in favor of ppc.
ARM has clearly most of the buzz and very probably a brighter future than ppc, but it's not a world revolution and ppc going >nil:

[zylesea]

But everybody says PPC is dead! If it's repeated so much, it must be true, right?

well in fact everybody says ppc is dead on the *desktop* - and this is de facto true. Albeit there are a few processors upcoming whih could be nicely used with desktops. In embedded/telco/supercomputing/automotive ppc is still pretty alive.

[zylesea]

And I don't see IBM going PPC in favor over POWER...

Power = ppc. There's no difference anymore since Power ISA 2.03 and ppc is the outdated name. I prefer to use it out of tradition. Nitpickingly you are right, ppc is dead. But power isn't. Neither at ibm, nor at Freescale. Freescale are using both name schemes, PowerPC and Power. I think they do it because of tradition like I am doing it.


Quote from wikipedia:

The PowerPC specification is now handled by Power.org where IBM, Freescale, and AMCC are members. PowerPC, Cell and POWER processors are now jointly marketed as the Power Architecture. Power.org released a unified ISA, combining POWER and PowerPC ISAs into the new Power ISA v.2.03 specification and a new reference platform for servers called PAPR (Power Architecture Platform Reference).

[zylesea]

Seems unlikely as Hyperion (not Acube) controls OS4. Also, Acuibe would hardly profit by a port to Mac hardware.

Acube is a distributor of OS4, hence they would have profited from OS4 for Mac sales. Anyway, it didn't happen.