To answer my own questions:

> 1. Does PacketPro have an FPU?
> [...]
> 6. What is Applied Micro's "APM86XXX" "32-bit Commercial Processor" that is
> listed in Power.org's latest Power Architecture roadmap version? Is it PacketPro?

The answer is "yes" to both questions.

"AppliedMicro's Mamba APM86190 single-core devices and APM86290 dual-core processors feature up to two 1.5GHz PowerPC 465 processing cores with floating point units, 32 KB I- and 32KB D-cache, 256 KB L2 cache per processor, hardware cache coherency, 1600 Mbps DDR3 memory controller with optional ECC. High-speed interfaces consist of two GE ports with classification and TCP/IP offload, one x4 PCI-Express(R) Gen2, two x1 PCI-e Gen 2 ports, two USB 2.0 hosts with integrated PHYs, one USB 2.0 OTG with integrated PHY and two SATA 2.0 ports. [...] Sample quantities of AppliedMicro's Mamba APM86190 single-core and APM86290 dual-core SoCs are available now and production quantities are expected in the second quarter of 2011."
http://investor.appliedmicro.com/phoenix.zhtml?c=78121&p=irol-newsArticle&ID=1506830

"Dual-Core Power 465 processors each with a Floating Point Unit"
http://www.appliedmicro.com/products/process.html#EmbeddedProcessors

"At the heart of the APM86290 are two 1.5-GHz 465 processor cores based on Power Architecture with full SMP support and individual Floating Point processors. [...] The APM86290 incorporates two high performance 465 processors. Each 465 has [...] an IEEE floating point unit (FPU)."
http://www.appliedmicro.com/products/APM86290_PB_20101011.pdf

I guess that both USB 3.0 and 10GbE, which were announced for PacketPro back in September, are supposed to be implemented only in future, yet to be announced PacketPro processors.

Edit:
http://www.apm.com/products/embedded/multicore460/apm86190/
http://www.apm.com/products/embedded/multicore460/apm86290/

[ Edited by Andreas_Wolf on 2011/1/6 22:48 ]

Andreas, that "mamba" chip looks the nicest PowerPC offer in ages (sans AltiVec, pity). As AMC is already sampling, could a development board already exist?

> that "mamba" chip looks the nicest PowerPC offer in ages

At least the best Applied Micro has to offer after they scrapped the Titan core and accompanied APM83290/Gemini processor (which also sampled and had an evaluation board, btw).

> sans AltiVec, pity

Indeed. That's why I'm looking forward to news from Freescale. They still have 2.5 weeks left ;-)

https://morph.zone/modules/newbb_plus/viewtopic.php?topic_id=7001&forum=3&post_id=76983#76983

> could a development board already exist?

I very much guess so. From the press release linked before:

"The company's Serengeti evaluation platform incorporates a dual core APM86290 running up to 1.5GHz and exposes all interfaces available on the SoC."

Great! Let's make our own computer then!

> Let's make our own computer then!

You mean using the eval board as is? While technically possible I'm afraid that could easily result in a system as expensive as the X1000 ;-)

As requested by Andreas_Wolf in another thread: dnetc -bench results for my Powermac G4 Quicksilver 2002 with 7448 @ 2GHz installed.

dnetc v2.9105-511-CTR-09050816 for MorphOS (MorphOS 2.7).
Please provide the *entire* version descriptor when submitting bug reports.
The distributed.net bug report pages are at http://bugs.distributed.net/

[Dec 21 18:27:45 UTC] Automatic processor type detection found
a PowerPC 7448 (G4) processor.
[Dec 21 18:27:45 UTC] OGR-NG: using core #0 (KOGE 3.1 Scalar).
[Dec 21 18:28:04 UTC] OGR-NG: Benchmark for core #0 (KOGE 3.1 Scalar)
0.00:00:16.71 [19,916,193 nodes/sec]
[Dec 21 18:28:04 UTC] OGR-NG: using core #1 (KOGE 3.1 Hybrid).
[Dec 21 18:28:23 UTC] OGR-NG: Benchmark for core #1 (KOGE 3.1 Hybrid)
0.00:00:16.31 [41,269,521 nodes/sec]
[Dec 21 18:28:23 UTC] OGR-NG benchmark summary :
Default core : #1 (KOGE 3.1 Hybrid)
Fastest core : #1 (KOGE 3.1 Hybrid)
[Dec 21 18:28:23 UTC] RC5-72: using core #0 (MH 2-pipe).
[Dec 21 18:28:43 UTC] RC5-72: Benchmark for core #0 (MH 2-pipe)
0.00:00:17.00 [7,746,782 keys/sec]
[Dec 21 18:28:43 UTC] RC5-72: using core #1 (KKS 2-pipe).
[Dec 21 18:29:02 UTC] RC5-72: Benchmark for core #1 (KKS 2-pipe)
0.00:00:16.08 [7,643,136 keys/sec]
[Dec 21 18:29:02 UTC] RC5-72: using core #2 (KKS 604e).
[Dec 21 18:29:21 UTC] RC5-72: Benchmark for core #2 (KKS 604e)
0.00:00:16.94 [7,790,965 keys/sec]
[Dec 21 18:29:21 UTC] RC5-72: using core #3 (KKS 7400).
[Dec 21 18:29:40 UTC] RC5-72: Benchmark for core #3 (KKS 7400)
0.00:00:16.11 [18,096,530 keys/sec]
[Dec 21 18:29:40 UTC] RC5-72: using core #4 (KKS 7450).
[Dec 21 18:29:59 UTC] RC5-72: Benchmark for core #4 (KKS 7450)
0.00:00:16.67 [21,062,902 keys/sec]
[Dec 21 18:29:59 UTC] RC5-72: using core #5 (MH 1-pipe).
[Dec 21 18:30:17 UTC] RC5-72: Benchmark for core #5 (MH 1-pipe)
0.00:00:16.60 [7,074,547 keys/sec]
[Dec 21 18:30:17 UTC] RC5-72: using core #6 (MH 1-pipe 604e).
[Dec 21 18:30:36 UTC] RC5-72: Benchmark for core #6 (MH 1-pipe 604e)
0.00:00:16.78 [6,999,792 keys/sec]
[Dec 21 18:30:36 UTC] RC5-72 benchmark summary :
Default core : #4 (KKS 7450)
Fastest core : #4 (KKS 7450)

[ Edited by Ruud on 2010/12/21 18:36 ]

[ Edited by Ruud on 2010/12/21 18:38 ]

[ Edited by Ruud on 2010/12/21 19:08 ]

> As requested by Andreas_Wolf in another thread: dnetc -bench results for my
> Powermac G4 Quicksilver 2002 with 7448 @ 2GHz installed.

Thanks. Just in case you wonder: the purpose of asking you for these benchmark results is that I want to compare the 7448 to the 7447A/B on a clock per clock basis to see how much faster the 7448 is in dnetc, if at all.

> dnetc v2.9105-511-CTR-09050816 for MorphOS

That's not the most recent version for MorphOS (I used v2.9106-514) but I think it doesn't matter.

Comparison:

KOGE 3.1 Scalar: 7448 is 0.4% faster.
KOGE 3.1 Hybrid: 7447A/B is 1.0% faster.
MH 2-pipe: 7448 is 0.8% faster.
KKS 2-pipe: 7448 is 1.5% faster.
KKS 604e: 7448 is 1.2% faster.
KKS 7400: 7448 is 1.1% faster
KKS 7450: 7448 is 0.6% faster.
MH 1-pipe: 7448 is 0.8% faster.
MH 1-pipe 604e: 7448 is 1.0% faster.

All in all I conclude that regarding dnetc there's no significant clock per clock difference between 7447A/B and 7448.

Addendum:

> "AltiVec SIMD has long been recognized for its performance in the
> PowerQUICC processor line"
> http://www.freescale.com/webapp/sps/site/homepage.jsp?code=QORIQ_HOME
>
> AltiVec in PowerQUICC? Huh? While it's true that they present QorIQ P1 to P3
> as PowerQUICC replacements and QorIQ P4 and P5 as MPC86xx replacements
> that surely doesn't make MPC86xx a PowerQUICC, does it? Are they now trying
> to retroactively subsume MPC86xx (or even MPC74xx) as PowerQUICC?

Just discovered that Freescale indeed lists the MPC8610 as PowerQUICC III (while MPC864x is listed as "Host Processor") there:

http://www.freescale.com/webapp/sps/site/overview.jsp?code=PRDCT_LONGEVITY_HM

Furthermore, MPC74xx and MPC86xx are listed in Freescale's 'PowerQUICC and QorIQ Processor Selector Guide':

http://www.freescale.com/files/32bit/doc/brochure/PWRARCHQIQSG.pdf

Explanation that adds up, anybody?

Quote:

Oh no! Andreas, what do you think?
If someone want to step up and pitch in ten grand or so, we can start slogging through the manufacturers datasheet and compile the massive amount of detailed info need just to start.

But, I'm not playing that game with MY money. How about yours?

>> Let's make our own computer then!

> Andreas, what do you think?

See my answer to jcmarcos' suggestion.

> If someone want to step up and pitch in ten grand or so, we can start slogging
> through the manufacturers datasheet and compile the massive amount of
> detailed info need just to start.

I don't think jcmarcos referred to designing a new board but rather to using existing eval boards in order to build new Power Architecture based computer systems.

Quote:

Oh! I get it now. He's never priced a PPC evaluation board.
Remember the $4000 I was quoted for the FreescaleHPCN-MPC8641D (Matt said he got his during the period they were 'discounted' to the oh so affordable price of $2000)..

Why aren't PPC evaluation board commonly used to build practical systems?
I'll avoid posting this in the caps I want to use, because they're too damned expensive!.
The odd thing is I got the impression (after a lot of work) that if I was serious about producing something with their product, Freescale would have given me the layout files and design info.

That's kind of why I was curious about jcmarco's comment about building a computer.
Semiconductor manufacturers don't want to sell you motherboards (those are design examples - proof of concept). They want to sell you the components to populate motherboards.

This is where we need someone as foolhardy (in a kind of admirable way) like Treavor who is willing to take a potential loss on a vanity project.

I really DID think he meant "build a computer". Believe it or not I've been around long enough for that to really mean to me "design, finance, build and sell" a computer. I've been part of that kind of operation before and you can take a royal shellacking on it.

I think you were right when you first mentioned that we'd end up with something as expensive as the X1000 (which I like, but will never buy).

This is where ARM starts to look seductive. Remember the last ARM evaluation board I mentioned to you? $200!
Find me a $200 PPC board (let alone a manufacturers evaluation board).

[ Edited by Jim on 2010/12/30 2:37 ]

[ Edited by Jim on 2010/12/30 2:38 ]

[ Edited by Jim on 2010/12/30 2:39 ]

I like my arm 800ghz coby kyros which l just got for under 150US$. I say later with the old stuff but we may have missed porting to mobile devices. As for X1000...it's a hugh move but hey it's something. AOne had it's run at long awaited supporters too. Right now whatever hobby works for whoever.
can't complain till I'm more of a contributer.

Oh common man. Of course you can complain. You come from the State I live in, You know our country men. Americans have refined complaint to an art form.
You can complain, but who'll listen?

That's where you have to respect the contributors (which now that I think about it - I can't consider this post to be a part of)..
Sorry.

The ARM system sounds interesting. <$150! Neat.

[ Edited by Jim on 2010/12/30 4:33 ]

Quote:

Oh yes I did! I wanted also to point out my frustration about how much easier is to make you own computer with other CPU architectures... It's a pity PowerPC is so expensive and hard to source. Maybe every PowerPC provider sucks?

Quote:

Well, that's how the Pegasos started. You buy a single eval board, and blatantly copy it for you new computer. In the process, you will be tempted to add some bits you want, and remove others you don't.

(I can feel the audience's boredom at rading this - OK! )

Quote:

Sure, but I know these toys are expensive. BUt why on earth do I have to stand that a Beagleboard costs just a hundred bucks? It actually IS an evaluation board, for god's sake. Why can't we PowerPC lovers have the same treatment? And yet again, how the hell does LimePC do what they do?

Quote:

Many people would devote those four grands to anything else but hardware you are not going to see in the market. By the way, you mentioned ten grand, are you saying that's enough to make a new computer out of nothing (plus an eval board to copy, of course)?

Quote:

I was hoping for someone to stand up with those ten grand. It's Christmas after all, the time for miracles. Oh boy, I've just realized the world is in crisis.

Quote:

And most of them, if you ask for less than a zillion units, just don't hear you. Legitimate, but hurting, don't you think? Then, a different provider treats you better, and you end up building a different computer. You also wave goodbye forever to the first provider, giving them your "best" wishes.

Quote:

Oh, fantastic: Has he (or better say, the people he has convinced) some ten grand left for us? By the way, you weren't around back ni the age when Genesi WAS MorphOS, were you.

Quote:

Nope, there's chips out there for something cheaper. Remember the original Efika. Only, this time, with the MPC8610, or something similar. But then, some crook asks you four grand for a single unit. Can you keep any desire left to build a computer around that CPU? Go figure. Jeez, freescale should be giving away eval boards for their products!

Quote:

Want a surprise? That's exactly what freescale thought: Instead of making PowerPC (your key market) accesible for developers, you switch to ARM. Of course people who've been there for years like Samsung and Texas instruments are sissies you can easily defeat.

quote]Remember the last ARM evaluation board I mentioned to you? $200![(quote]

Would you pleas stop torturing me already?

Quote:

The MPC 5125 eval board is 119 US$ ( http://www.freescale.com/webapp/sps/site/prod_summary.jsp?code=TWR-MPC5125-KIT&fsrch=1&sr=3 ), but is intended for usage with the Freescale Tower system. While the 5125 is probbaly not what you had in mind, I still rate it one of the most interesting ppcs out there. Sure, it is very low end, but has a very competetive price tag and MorphOS on a e300/400 runs okay.
But situation is, nobody comes around willing to invest making a 50 US$ low end board happen and the MorphOS-Team would probably be not too euphoric about an e300 again. But if you wanted to do a actually sellable ppc system the 5125 would be pretty high on my list. The 86xx ship unfortunately has more or less sailed, next chance for a modest powerful ppc system will be with the Altivec enabled QorIQs, but it will take a litle time until they arrive.

[ Editiert durch Zylesea an 2010/12/30 12:17 ]

No Zylesea, theMPC 5125 eval board wasn't even close to what I was thinking off, but you've got a point. There are a few low cost evaluation boards, they just don't include the kind of processor I like to use.

OK! jcmarcos! You did mean what I thought you meant. That's cool.
I'll let you in on something that's not really a secret, several of us have repeatedly examined this idea.
Well, not just examined, really more like established contacts with company reps, obtained price quotess, did at least some preliminary design work.
Andreas is more familiar with this than I am. I spent time on inquiries with I BM and Freescale and went so far as to start the design of an MPC8640 based system (with an ATI SB600 Southbridge).
One of the few people I quizzed for feedback was Andreas (which is why I threw the question at him in this thread).
Another MorphOS contributor (who can talk to you himself or Andreas can reference) still has regrets about not following through with an 8610 based design.
I myself still think it might be a good idea (a new PPC motherboard) and I can see two possible sources for the processor (Freescale and Applied Micro), but there are some qualifiers.
Price is the biggest one. I gave up my design when G4 Mac support was announced. An MPC8640 design would have some advantages, but the ultimate clock speed would be lower than the G4s. And how are you going to compete with the price of Macs that are practically being given away? Ultimately, once you crunch the numbers, you realize that the price of the X1000 and Acube's products aren't as overpriced as everyone complains.
Low scale production of custom boards like this is expensive.
The other qualifier (and I'm sure there are more) is performance. While a few PPC processor are now being introduced that again have started pushing performance up, its still hard to beat the performance of the G5 (and again these systems are dirt cheap).

Think carefully about this,. It would be great to have a new system and the new options that would offer us (like PCI-e 2.0), but in practical terms- does it make good economic sense to invest a fairly large amount of money to produce something that will cost several times what an older platform (that would competently perform about as well) would? What is your market? Is it larger enough that you're not going to take a bath (financially)?

Genesi and Acube have pursued other markets than just the MorphOS market when developing new hardware. Can you do that? Are there the resources and time necessary to pull this off?

And its going to be a lot of work. Are you willing to commit that much of your life to this as it will obviously take?
All thoughts that have gone through my mind and still I find the idea tempting.

Anyone elses input on this would be gladly accepted. I don't know what the answer is. It would be nice, but how to do it, where to find the financial resources and how to organize it are all questions that still vex me.

Anyone?

[ Edited by Jim on 2010/12/30 15:28 ]

Quote:

Of course not. I've taken out the rest of your valuable comments, because I've assimilated them easily. In fact, nothing of what you say is a surprise.

In the end, when something doesn't get done, it has to be because of something.

So sure, my comment about "making our own computer" can be reduced to an act of sarcasm.

Final note: This is a cold, ungrateful world...

Final note 2: The Team's idea to use Mac hardware might have been the best idea in amigaland in decades.

>> I don't think jcmarcos referred to designing a new board

> Oh yes I did!

Then it seems I misread your response to my answer to your question if there's already a development board for Applied Micro's Mamba processor :-)

> yet again, how the hell does LimePC do what they do?

What do you mean specifically?

>> we'd end up with something as expensive as the X1000

> Nope, there's chips out there for something cheaper.

This statement was made under the (improper) premise that you were referring to using existing eval boards :-)

> freescale should be giving away eval boards for their products!

At least they're giving the CPUs away for free for evaluation purposes ;-)

https://morph.zone/modules/newbb_plus/viewtopic.php?topic_id=7001&forum=3&post_id=74509#74509

> Matt said he got his during the period they were 'discounted' to
> the oh so affordable price of $2000

I think it was $1500.

http://www.newsletterarchive.org/2008/07/18/397039-Freescale
http://moobunny.dreamhosters.com/cgi/mbmessage.pl/amiga/158082.shtml

> Remember the last ARM evaluation board I mentioned to you? $200!

It's $174 now:

http://search.digikey.com/scripts/DkSearch/dksus.dll?keywords=UEVM4430F-01-00-00-ND

Quote:

I'd call your last post a fine exaple of why you were one of the few people I ask advice from. Scary, now that you mention it, it probanly was $1500 (still about 33% higher than it ought to be, but I would have paid that).

You see jcmarcos, here's is THE man on the post with total recall, who has done a lot of research on topics related to our market. And no, I don't think you were being sacastic. I feel that way every time I see a new promising introduction. Then all the economics courses I took in the past kick in, and I reach the same (somewhat depressing solution) - not practical. For now the MOS development has the right idea.

BTW - Andreas, thanks for throwing the Digikey reference back at me, I may have to buy one of those just to play with it (if they're available).

[ Edited by Jim on 2010/12/31 2:37 ]

[ Edited by Jim on 2010/12/31 2:44 ]

> 800ghz coby kyros

Had those specs been written by Max Seybold by chance? ;-)

https://morph.zone/modules/newbb_plus/viewtopic.php?topic_id=6726&forum=11&post_id=77311#77311

looks familiar though can't get over opensuite, which reads all my m$ stuff! c'mon mannn!
with editing...been only b!tching for something similar on morph now for like ever!

> The MPC 5125 eval board is 119 US$

That development board by THTF/LimePC for the Freescale Tower System is not *the* MPC5125 eval board, which is rather the ADS5125 by STx (2000 USD). The same as with the MPC5121e: There's the ADS5121 ("Hellrosa") eval board by STx for 2000 USD (or 500 USD for an older revision) and there's the much cheaper MPC5121e development board by THTF/LimePC for the Freescale Tower System.

> The 86xx ship unfortunately has more or less sailed

Freescale at least say they'll ensure its availability until 2018 ;-)

> established contacts with company reps, obtained price quotess,
> did at least some preliminary design work.
> Andreas is more familiar with this than I am. I spent time on inquiries
> with I BM and Freescale and went so far as to start the design of an
> MPC8640 based system

I don't quite understand. What is it that you think I'm more familiar with than you?

> I can see two possible sources for the processor (Freescale and Applied Micro)

I'd add LSI to that:

https://morph.zone/modules/newbb_plus/viewtopic.php?topic_id=7001&forum=3&post_id=77307#77307

> Acube have pursued other markets than just the MorphOS
> market when developing new hardware.

I'd even go as far as saying that the MorphOS market has never been in ACube's mind ;-)

Quote:

Mass manufacturing and selling (!) of lovely little PowerPC computers. They even make the best (read: non crazy expensive) evaluation boards for freescale! Funnily, that was the space I once though Genesi was in - perhaps that THTF betrayal went much further than I thought...