> Pity you missed the point. Again.

I think I got the point, which is: You're full of double standards.

>> the PowerXCell 32 isn't supposed to have anything to do with PS4
>> and never was. This alleged connection exists only within your
>> twisted mind.

> now you're talking BS.

I don't think so. There has *never* been any statement neither by IBM nor Toshiba nor Sony that the PowerXCell 32 would be a candidate for the PS4. The only people assuming such connection were some rabid PS fans and random clueless analysts. You can convince me of your claim being true by presenting just *one single* official statement that goes along your view. Until then, you're the BS talker here.
Btw, the PowerXCell 8i wasn't supposed to power the PS4 either, yet it got R&D'd. Care to explain?

> A company like IBM won't spend *hundreds of millions* of USD on R&D
> for a CPU if it only ends up in a couple of their supercomputers
> and a few thousand boards sold here and there.

Maybe they had plans for their Cells that never came to fruition, who knows. Fact is, you (and me) know nothing about IBM's internal plans for the coming PowerXCell 32. At least, there's not one single document out there proving that R&D of PowerXCell 32 has anything to do with PS4. So you're obviously talking out of your behind again.

> They have never done that. Even the [...] 450 used in BlueGene
> systems are widely sold as embedded CPUs (perhaps slightly modified).

No, the 450 is not sold on the free market. It's only used within BlueGene systems. So, they indeed have done that before already in an even stricter way. The PowerXCell 8i is not only used in their RoadRunner but also on server blades and PCIe boards for the free market. Why shouldn't they do the same thing they already did with the PowerXCell 8i and (in an even stricter way) the 450 with the PowerXCell 32 as well?

> the PowerXCell 32 *initial* purpose was to go in the PS4.

Your claim is worth nothing without proof. Why has the PowerXCell 8i been R&D'd then?

> Just as the PowerXCell 8i is a bigger/better version of the Cell BE
> (which came *after* the Cell BE)

Yes, of course. That's been my point the whole time.

> so the 32-SPU Cell would find its way to the PS4.

From the PowerXCell 8i being a better version of the Cell B.E. you conclude that the PowerXCell 32 was intented for the PS4? What's that kind of logic called?

> At least that would make perfect sense

Really? The PowerXCell 8i didn't end up in a Sony's gaming device, yet it got R&D'd and gets produced and is sold on the free market as part of certain IBM systems today. Care to explain?

> Go and do some reading first

URLs please. You're telling me over and over to do some reading, yet you keep failing to provide me with even *one single* URL to do so.

> before you post tons of links, where you probably just skim the
> title and post the URL, I'm tired of this.

You're tired of me posting tons of links? Let me recommend you to get some sleep helping your tired and confused mind then. Else your delusions might reach a dangerous state.

> unlike the QorIQ they're not powerful enough.

You know the power of future 460s and future e500s other than QorIQ? Please tell.

> I know that QorIQ was even considered by Genesi as basis of a
> ppc-based system.

Genesi's considerations remind me of the caprices of a menstruating woman ;-)
Seriously: I expressed my feelings towards the QorIQ regarding desktop use (especially running MorphOS as this is MorphZone after all) already on page 2 of this very thread.

> After all this discussion, you still miserably fail to see the
> obvious. The PowerPC line is withering and limiting itself to just
> a few models/markets, whereas the competition has a plethora of
> choices for whatever need.

How do you conclude that I'm failing to see this? I'm quite *with you* on this observation! It's just that I didn't address this in any way, as I told you already. You simply *cannot* conclude any position of mine regarding a certain issue from me *not* addressing that issue!
Obviously, you're assuming too much. Please stick to the things I actually write, not to some strange fantasy assumptions in your head.

> You try to justify your reasoning with comments like "hey, you
> forgot the Titan and the IBM 472

It's the 476.

> and the A2 and all the -unrelated to the topic- embedded CPUs!"

Indeed, I justify my reasoning that you forget these CPU lines with comments like this. Any objections?
As for the unrelatedness of embedded CPUs: Why is the QorIQ related, but other future e500s and future 460s are not?

> Considering the netbook target, the only *new* CPU fit for the job
> would be the QorIQ actually (being multi-core and able to reach
> high frequencies), which is why I mentioned it.

And other future e500s and future 460s certainly won't fit netbooks?

> I also mentioned Power7 because it's the most important line
> currently

Most important regarding which aspects exactly?

> and the only one that is able to beat Intel/AMD offerings

Regarding performance, yes. Yet it's offtopic in any discussion about desktop use for the reasons you're going to name:

>> the POWER7 is not suited for desktop applications either

> there you're wrong. [...] If only one could afford it; and the
> electricity bill.

Thanks for presenting the reasons for the POWER7 not being suited for desktop applications. So, thanks for proving my point.

To sum it up: You claimed the QorIQ and POWER7 to be the only future Power Architecture CPUs and now justify your denial of the other lines with something like thread context, which is ridiculous especially regarding your mentioning of POWER7. You could as well have mentioned the e200 line instead for it's probably the most used Power Architecture CPU line of all. That would have been as much within this thread's context as POWER7. Your justification is composed of inconsistent reasons you now come up with to conceal your claim being false.

Btw, you still keep failing to back up your claim that Sony "first [...] started with a Cell 3 design" for the PS4.

Quote:

Well, sure, PowerXCell 8i has 5-8 times *more* double precision floating point math performance (actually that's the theoritical limit, usually it's more like ~4x faster), and allows up to 16GB of RAM. It's *targetted* for scientific simulations, where floating point is almost useless, and lots of RAM is of vital importance. The plain Cell is fine for games (32-bit floats are fine for a game, but they just don't cut it when it comes to scientific calculations, they're almost useless there). But I guess you never had to do that so you wouldn't know.

Quote:

Well, sure, let's see. Amidst the insults, I see a challenge. So, if we have an 8-SPU Cell used in PS3 good at 32-bit fp math and shortly after a HPC-targetted PowerXCell 8i, still 8-core but ~4x faster at 64-bit fp math, used in huge clusters and supercomputers, and we have an announcement of a 32-SPU Cell successor (2 versions, 32-SPUs each, 2/4 PPEs resp.). Now, why does that sound familiar? Oh wait, it might be because one model, one possible explanation might be that the 2-PPE one would be strong only on 32-bit fp and the 4-PPE strong on 64-bit fp as well, just like the Cell and PowerXcell 8i. Of course that's just a guess, because not much specs are available on either CPU model, in fact, it's only a rumour that there are two versions. Of course you wrote it as a fact, falling in the same trap you accuse me of.

Quote:

Oh, now you have inside info of the IBM CPU sales? Fantastic. However, I think this is funny:

http://www-03.ibm.com/press/us/en/pressrelease/7433.wss

check the part where it says "A third synthesizable processor core, the IBM PowerPC 450, targeted for the networking and communications segments, is expected to be available in 2006."

Availability for what? demos only? And you would know this, how exactly?

Quote:

Because the 450 is cheaper to R&D and produce and sell than the PowerXCell 32 by a big factor? Especially, when Sony or someone else is not interested in funding the R&D? What I mean is, if Sony is not sharing R&D costs, of what benefit would it be to IBM to take it up on itself to develop a 32-SPU Cell, only to put in a few super computers and sell a few thousand blades/boards? If you add up the costs, it doesn't make financial sense.

Quote:

Please read above.

Quote:

Please read above.

Quote:

Thank you that was a nice advice, I can see more clearly now that my tired and confused mind wasn't playing tricks on me. You firmly established my opinion of you.

Quote:

Sure, when they're here, they might, "future" being the key word here. QorIQ at least has already been shown and demoed, and available in mid-2009 -or so they say anyway. Same argument used as for the Titan, let's see it first, even as a demo and then we can talk all day about the merits of each CPU.

Quote:

Brand recognition. Most people know Power6/7 and its -allegedly insane- performance, but very few know names and specs or even existence of the other models. I guess you don't disagree there.

Quote:

You know, I've never met anyone so obsessed with proving the other one wrong. You remind me of http://xkcd.com/386/. SO WHAT if I neglected a few unrelated CPU models? I mentioned real and existing CPUs, which are the main focus points of the two biggest PowerPC companies, and you mentioned future ones. And you call me inconsistent? Let's wait first ok?

Quote:

http://www.businessinsider.com/2009/1/rumor-sony-ps4-plans-leaked-and-it-targets-casual-gamers-sne
http://www.gossipgamers.com/leaked-ps4-details-flatly-denied-by-sony/

These are ...

Bah, I just felt an strong earthquake now and I realized just how much I'm wasting my time replying to you. Last message on thread, enjoy your meaningless triumph.

[ Edited by feanor on 2009/4/12 2:59 ]

[ Edited by feanor on 2009/4/12 19:42 ]

Quote:

Just to add.
ST-Microelectronics STn8820
http://www.beyond3d.com/content/news/586

@feanor

Like Ageia?s PhysX PPU, Toshiba is attempting to add their SpursEngine (quad SPE only) as a part of the X86 PC ecosystem e.g. on selected Toshiba laptops and WinFast (Foxconn) PxVC1100 PCI-E add-on card.

It would be nice if SpursEngine is available as an ExpressCard.

Quote:
~50 percent of PCs sold in 2008 includes ATI CAL or NV CUDA** hardware.

**SIMT(single instruction multiple thread) model. It?s like SIMD but with multi-thread data dispach.

Attention all, please:

IBM decided to realize its version of processors for netbook computers!

Infacts IBM associated to Chartered Semiconductor, GlobalFoundries, Infineon, Samsung, STMicro and Toshiba creating a society named Joint Development Alliance.

New CPU will feature 28nm technology and will be 40% more powerful than Intel Atom consuming 20% less than Atom processors...

http://www.vnunet.com/vnunet/news/2240525/ibm-moves-28nm-chip-fabrication

[ Edited by Raf_MegaByte on 2009/4/20 12:00 ]

Quote:

...but this is a yet another ARM initiative. Doh.

If even IBM has lost interest in POWER architecture, who will make our favourite chips? We look more and more into a dead end.

The Amiga curse!

Quote:

We have two solutions:

1) Learn how to program ARM processors and migrate from PPC to ARM...

At least these processors are pure RISC and it not be should far more different from PPC RISC architecture...

[Question:

Are arm Big Endian or Low Endian??? IF ARM are LOW Endian then the porting should take a little (?) more...

...But we Amigans have a great skill in patience and waiting...

End of Question]


2) Continuing using PPC that are still manifactured from AMCC as those used in SAm440...

[ Edited by Raf_MegaByte on 2009/4/20 15:21 ]

@Raf_MegaByte

No.

Quote:

As Pilatus said in Jesus Christ Superstar famous Musical:

- What do you mean by that? This is not an answer!


1) "No" is intended to my question LOW or BIG Endian?

2) Better "No" to passing to Arm?

3) Better "No" to using still PPCs manufactured by AMCC?

@Raf_MegaByte

See my previous post.

|||




[ Edited by Velcro_SP 19.04.2011 - 16:19 ]

Just a little update in the whole CherryPal scam..

3643040463_a7fdddb535.jpg

@ ironfist

Yeah, I read the documents BBRV talks about in their latest blog:

http://bbrv.blogspot.com/2009/06/warningto-all-interested-parties.html

Very interesting...

|||

[ Edited by Velcro_SP 19.04.2011 - 16:12 ]

Quote:

So, at least one amigan has a Cherypal? I didn't notice about it, and would find very valuable your opinions, if you haven't posted them already. Please tell us, is it as bad as some people say?
Haev you started hacking it yet? Is it remotely possible?

|||

[ Edited by Velcro_SP 28.05.2011 - 06:29 ]

@Velcro_SP

OK, you don't like what I say, but am I wrong?

|||

[ Edited by Velcro_SP 27.04.2011 - 06:58 ]

Velcro, I agree with all your comments here. Even those "against" takemehomegrandma. Count me also in that category, as I usually do the same praising towards Genesi from time to time. Somehow, I feel in debt with them, perhaps some more people here feel like that (but wouldn't admit it in public).

I've red your blog entry about the Cherrypal ("LimePC" from now), and recall doing so in the past. Sorry for fooling myself, as I obviously red (and commented!) your MorphZone thread also, but had forgotten about it.

Your idea of "picking up LimePC" makes sense, at least for an ignorant like me. but it's hard to tell how difficult it would be. Being such a little compuiter, it should be VERY easy to do, or it wouldn't be viable, we're talking low cost computing.

In the past, I thought of an initiative consisting in buying a bunch of LimePCs and give them to the MorphOS Team, for them to check the possibility of a port. Hell, they are cheap! It's not like buying a bunch of PowerMacs G5! (yeah, right, as I'm dumb and can't do it myself, I pass that task to tme Team, as if they weren't busy enough).

The MacMini port is a good thing. Mostly because it's the ONLY possible thing. Doh.

But it's a pity the LimePC can't enjoy a decent operating system (and community!). Because LimePC and MorphOS deserve each other. Knowing that the original plan was about MorphOS only hurts more.

So, if we had the guarantee (yeah, right) that freescale would be manufacturing the MPC5121e for five more years, and THTF would do so with the motherboard... But those are, precisely, two companies known for NOT delivering on their announcements. Anyone here in China willing to reach THTF's offices for an agrement over LimePC? Wait, Genesi did so, and were screwed...

It's just a shame that the LimePC, indeed, does exist, and that "being born" for MorphOS, we can't do anything about it.

Or "yes we can" (TM)?

@Velcro_SP

It was not a comment to a single blog post, it was an aggregated conclusion based on *all* of what has been said, and *all* observations I have made during the last year. And with "dead" I didn't mean that your device didn't power up anymore. That's the same tiresome "logic" that rigid die hard Amigans use when they say "The Amiga isn't dead, my LED is still lit" when you say it's "dead" in the sense that the platform has no clear commercial purpose, no focus, no role to play in a greater scheme, and has been lagging behind in most areas every year for a decade and a half (at least if you consider it to be what most "amigans" consider it to be - a full blown desktop OS that is here to rule the world and kick Windows out of the picture).

"It's dead for all purposes of interest to us", i.e. if the chip is still sold (of which I am sure it is, though I doubt the platform will be further developed, at least not in a way that would be remotely interesting to *us*), then you will find it hidden in cars etc, not in the consumer electronic devices and netbooks you are looking for.

The similarity with MAI/Articia and AmigaOne is striking IMHO. Both chips had a great deal of bugs and came in lots of new revisions (to the actual market!) before the problems started to get ironed out. Yet the lack of a working cache coherency functionality came as a total surprise to the third party developers. Some (Genesi and most other) consider this to be a deal breaker and jumped ship to another chip, while some few (Eyetech and Cherrypal) pushed ahead, they made a few sales before they went belly up, and left some users that happily testify online that "I have never had any problems with my AmigaOne/Cherrypal whatsoever" (which probably is totally true but not really relevant). Yet the Articia had at least two follow up models on the road map, and the MobileGT platform had the 5123, 5125, and the 5130 in the pipe line. I bet that there still is a few people over at amigans.net that still are waiting for the Articia P (it will never come), and explains the outage of the MAI website as some simple site maintenance. The 5123 was *originally* supposed to be here at Q1 2008 (Genesi was supposed to handle the development of a MPC5123 system reference design), and the 5125/5130 in Q2 2009. According to posts by BBRV, there has been some vast reorganization at Freescale though, a complete refocus. At one point in time, Genesi had the hopes of the 5121e/5123 to be suitable for netbook like devices, but it turned out it wasn't (it's completely focused on embedded markets). Neither the 5125 nor the 5130 will even have an MBX or AXE core (if they ever get here), so they are out of the picture as well. Conclusion: The 5121e/5123 won't suffice, and the follow up chips won't correct this. *THIS* is what I mean with "dead"; I'm *not* disputing that the LED on your Cherrypal is stil lit, because I'm sure it is. But the fact is that Freescale's consumer focus is around the i.Mx family now (ARM). And this is where Genesi is as well.

@jcmarcos

Quote:

No. It makes no sense whatsoever.

Genesi developed the LimePC/Cherrypal, and they have already left it. For this:

3630491475_0301f70970.jpg

This chip has at least twice as good performance and much better specifications than the 5121e. It has lots of support controllers and accelerators. It has a SIMD unit (think Altivec). And it has momentum. It can do the things you want a netbook to do, the 5121e is *much* more limited in its specs and performance.

YouTube Video


Quote:

I'll quote a reply that BBRV already made to Velcro_SP in an old thread:

"We tried to explain a number of times here and on PowerDeveloper why the 5121e is a waste of time for use with an OS like MorphOS. Please don't waste you time and money on this proposed bounty. If a MorphOS-Team developer wants one of these systems we would be happy to send one to them. This is not the issue."

"Porting MorphOS to the 5121e is a waste of time. It is too bad things worked out like they did. We had high hopes for this chip."

|||

[ Edited by Velcro_SP 27.04.2011 - 06:56 ]

TMHG:

Well, this ARM chip may be nice, and I am prett ysure it will power some nice netboks, but what does this chip has to do with MorphOS?
You know even this non super-duper 5121 chip has one significant serious adantage over any ARM, x86, MIPS and the likes. It is a PowerPC. And that is - at least up to now - the only architecture supported by MorphOS.

After the Mini release it will be time to make a new decision which way to proseed. But b4 that release isn't out and information about acceptance, demand, or the lack of it, is gained all discussion about future plans is IMHO rather void.

@Velcro_SP wrote:

Quote:

I think that if you really ask them, you would get a similar response.

Quote:

Genesi hasn't asked for a MorphOS port to ARM (LINK), but they would support it if the will from the MorphOS team was there. But I think they are perfectly aware of the time and effort required to accomplish something like that. It took the MorphOS team almost 2 years to deliver MorphOS for the Efika. Two years is a man age in computer years, complete technology shifts can happen in that much time, and the whole Efika/LimePC window was closed before MorphOS was even ready. And that was for a PPC platform, *not* a migration to a different architecture.

Quote:

I'm sure the 5121e is an excellent chip, when used for its purpose. For MorphOS though, the 5121e is broken by design. It lacks HW cache coherency. This turned out to be a design move (Click Here and read the post from henri234), and I agree that it makes sense for the context in which the chip is supposed to be used, i.e. embedded applications only. Genesi though, had counted on cache coherency being there. The whole point with the Efika->5121e program, and the whole idea with LimePC/Cherrypal/Whatever, relied on that.

Look Velcro, I didn't mean to take away the fun for you to have a Cherrypal thing. I have been toying with the thought of getting one myself, as some kind of collectors item if for no other reasons. Lots of AmigaOne owners are perfectly happy with their machines as well. Happiness is a good thing. But when you suggest that Genesi should continue with the 5121e design instead of the ARM design that not only is superior in every single way of measurement, and also cheaper, then it just becomes ridiculous. As for the MorphOS team - I'm sure they have their hands full to achieve the Mac Mini PPC port, and I'm sure *it will* happen. Any year now. The 5121e is a waste of time.