> What's the fastest T1?

The only one announced so far:

https://morph.zone/modules/newbb_plus/viewtopic.php?forum=3&topic_id=7001&start=736

> What core is to used in T2-T4?

"e6500 core running up to 2.5 GHz (T2-T5 families)"
http://www.freescale.com/webapp/sps/site/overview.jsp?code=QORIQ_AMP_SERIES

Update:

> There's also another error in there, as it reads "P3080" where it should read "P3060"

P3060 cancelled:

https://lists.ozlabs.org/pipermail/linuxppc-dev/2012-July/099047.html
http://lists.denx.de/pipermail/u-boot/2012-July/127806.html

Update:

>>> Just for the purpose of overview I compiled a list of the DMIPS/MHz per core
>>> figures for various PPCs in ascending order (AltiVec capability is generally
>>> ignored, obviously):
>>> [...]
>>> e5500: 3.0

>> The table on page #2 of the QorIQ AMP fact sheet PDF indicates that
>> the e6500 core didn't improve in that regard (comparing e6500's per-thread
>> performance to e5500's per-core performance).

> The QorIQ AMP T4240/T4160 fact sheet claims "6.0 DMIPS/MHz per core"
> and at the same time for dual threads "1.7 times the performance of a single thread".
> To me this sounds strange as I think it should be [...] about 5 DMIPS per MHz and core
> at best in case of dual-threaded execution.

According to page 11 of

http://www.freescale.com/files/training_pdf/FTF/2012/americas/WBNR_FTF12_NET_F0027.pdf
http://www.freescale.co.jp/event/ftfj/2012/technicalsession/pdf/FTF12_NET_F0027_Don_rev2-180.pdf
http://www.freescale.com/files/training/doc/dwf/DWF13_AMF_NET_T0027_Ottawa.pdf
http://www.power.org/wp-content/uploads/2013/11/QorIQ-T4xxx-Slides.pdf

it's indeed 6.0 (or 5.4, or 7?) DMIPS/MHz per e6500 core, but 3.3 instead of 3.0 (or 2.7?) DMIPS/MHz per thread, which amounts to a factor of 1.8 (or 1.6, or 2.1?) instead of 1.7.
Taking these new information into account, this is the revised list of the DMIPS/MHz per core figures for various PPCs:

e300: 1.9...2.0 (depending on version)
PPC440: 2.0
PPC460: 2.0
PA6T: 2.2
PPC750: 2.3
e600: 2.3
e500mc: 2.5 (or 2.7?)
PPC470: 2.7
PPC970: 2.9
e5500: 3.0 (or 3.3 (32-bit) and 3.4 (64-bit)?)
e6500 (1 thread): 3.3 (or 3.4 (32-bit) and 3.5 (64-bit)?)
e6500 (2 threads): 6.0 (or 5.4, or 7?)


Edit: added another PDF link
Edit2: added alternative value for e6500 (2 threads)
Edit3: added alternative values for e500mc, e5500 and e6500 (1 thread) from https://www.nxp.com/files-static/training/doc/ftf/2014/FTF-NET-F0139.pdf (page 3/4)
Edit4: another source for alternative value for e6500 (1 thread)
Edit5: added alternative value for e6500 (2 threads)
Edit6: https://www.nxp.com/docs/en/supporting-information/DN-Digital%20Networking%20solution-2017.pdf (page 17) confirms "3.4 (64-bit)" value for e5500

[ Edited by Andreas_Wolf 17.05.2023 - 14:34 ]

>> bPlan are very close to finishing Aura development on the EfikaMX, thus providing
>> an high level abstraction to the devices/drivers of the device in an OS-agnostic way.
>> Of course, an appropriate Linux kernel is also developed at the same time.

> Thanks for the clarification Konstantinos. So, what Genesi/bPlan/Pegatron are doing
> is making a new computer and custom operating system. Well, almost... But in many
> regards, it is. Once done, it's all a matter of convincing the world to write kernels for Aura.

According to Genesi's statement from June 2011, they are more successful than IBM in this regard at least:

"Genesi also possess the proprietary technology, "Aura." Competitors like IBM have worked diligently and spent substantial amounts of time and capital to replicate Aura. However, until this date, they have not been able to succeed in that endeavor."
http://www.genesi-tech.com/cache/baylor/China.pdf (page 20)

Does anybody have any information about IBM's alleged unsuccessful endeavour to "replicate Aura"?

Update:

>> when I discussed PPC based systems with the owner of Varisys
>> (the designers of the X1000 motherboard) I got this response:
>> "In terms of PPC we are thinking QorIQ here for higher end designs."

> Apparently, they've started to follow suit:
> "XMC/PMC [...] VM400 (XMC) QorIQ Pxxxx"
> "COM Express [...] VPX1 QorIQ P1022"
> "PC104 [...] MC104PRQ QorIQ P2022"
> http://www.varisys.co.uk/products.html

The VM400 has now been revealed as:

"XMC/PMC VM400 (XMC) QorlQ P3041/5020"
https://www.box.com/index.php?rm=box_download_shared_file&file_id=f_3209347735&shared_name=si8iwtiq2ag3oyykkqvb (page 9)

PDF file seems to be 4 months old but was apparently publicly released only now.

Update:

> T1022 seems to be next (maybe it has a DIU like the P1022)

T1020 and T1022 announced:

http://media.freescale.com/phoenix.zhtml?c=196520&p=irol-newsArticle&ID=1743554
http://www.freescale.com/webapp/sps/site/prod_summary.jsp?code=T1020

And indeed they seem to come with a DIU (just like the also newly announced T1040 and the previously announced T1042 do):

http://www.freescale.com/files/graphic/block_diagram/T1020_T1022_BD_IMG.jpg
http://www.freescale.com/files/32bit/doc/fact_sheet/T1FAMILYFS.pdf
http://www.freescale.co.jp/event/ftfj/2012/technicalsession/pdf/FTF12_NET_F0635_Matt_rev2-180.pdf (pages 10 to 14)
http://www.youtube.com/watch?v=hyU3VUT2Vpc


Edit: T1023 mentioned with block diagram and specs in http://www.freescale.com/files/training/doc/dwf/DWF13_APF_NET_T0809.pdf (page 12)

[ Edited by Andreas_Wolf 26.11.2013 - 22:41 ]

Update:

> "e6500 core running up to 2.5 GHz (T2-T5 families)"
> http://www.freescale.com/webapp/sps/site/overview.jsp?code=QORIQ_AMP_SERIES

...has been changed (somewhen between October 4th and today*) to:

"e6500 core running up to 1.8 GHz (T2-T4 families)"

No mention of T5 anymore. What gives?


* Edit:
The Wayback Machine link now shows the site on October 7th already having been without mention of the T5. Thus, the removal of the T5 must have happened somewhen between October 4th and October 7th.

[ Edited by Andreas_Wolf 28.10.2012 - 21:29 ]

Andreas_Wolf,
Quote:

Bitterly disappointing.
With a clear lead, it appears that PPC manufacturers could eventually see their products outperformed by ARM Socs.

The T4 is neat, but its got too many cores and too low a clock speed.

[ Edited by Jim 16.10.2012 - 00:50 ]

>> No mention of T5 anymore. What gives?

> Bitterly disappointing.

Let's not jump to conclusions here. I didn't mean to imply that the T5 was cancelled. I guess we'll have to see if Freescale will follow through with their announcement or if the QorIQ T5 will suffer the same fate as the MPC75xx and MPC87xx.

> With a clear lead, it appears that PPC manufacturers could
> eventually see their products outperformed by ARM Socs.

...from their very own production (Freescale's QorIQ LS1, Applied Micro's X-Gene, LSI's ARM-based Axxia), that is.

Update:

> Seems it's being worked on for Sam460ex as well:
> http://gitorious.org/aros/aros/commits/sam460
> http://aros-exec.org/modules/newbb/viewtopic.php?post_id=72012#forumpost72012
> http://aros-exec.org/modules/newbb/viewtopic.php?post_id=72034#forumpost72034

AmiWest 2012 news:

"We will be demonstrating AROS v1 on the Sam460 (native)"
http://www.amiga.org/forums/showpost.php?p=711924

Andreas_Wolf,
Quote:

Where this could prove interesting is in 3D support on newer Nvidia video cards.
I'll have to contact AmigaDave and see if Samuel Crow really does demo this.

Its not MorphOS and the Sam460 has a pretty weak CPU, but newer, more powerful video cards with OpenGL support?
Gotta find out more.

From AmigaDave at Amiwest, today:

"Not sure why there would be so excited about anything running on the SAM460ex, since it is still over priced and under powered, but Jason McMullan has confirmed that he does have AROS running on his SAM460ex and will be showing it tomorrow during the show. He will be leaving after his presentation on Sunday morning to go home."

So, I guess, more news tomorrow...

> I guess, more news tomorrow...

Indeed:

http://www.acube-systems.biz/index.php?page=news&id=108

Andreas_Wolf,
Quote:

Well, we have an official announcement.
No word from David as to how to demo went, but I think his initial assessment is probably correct.
Acube hardware is underpowered.
Why would you run AROS on an expensive Acube board, only to have it seriously outperformed by cheaper X86 hardware?

> Why would you run AROS on an expensive Acube board, only to have it
> seriously outperformed by cheaper X86 hardware?

I have no idea :-)

Jim wrote:,
Quote:

Jason ended up giving his AROS presentation on the SAM460ex on Saturday, instead of Sunday, so he did not even set up his computers on Sunday, and he left to go to the airport around 10:30am on Sunday. I over slept on Sunday, after initially waking up at around 6:30am I fell back to sleep and did not wake up until 5 minutes until 10am, so I almost missed even saying goodbye to Jason McMullan on Sunday morning.

To be honest, I was so busy with people interested in MorphOS3.1, winning raffle prizes (I think I won 4, or 5 out of the possible 8 to 10 raffle prizes during both days by giving the SACC club a $20.00 donation to support their work in putting on the AmiWest Show each year), and trying to look around at all of the different display tables and buying a couple of things from Matthew & AmigaKit (I hate to see Matthew pack up much gear that he had shipped over to sell during the show), as I never want Matthew to bring Amiga gear over with him and have me not buy something from him before he returns to Wales and has to ship his remaining stock that did not sell during the AmiWest Show.

I only had a quick look at AROS running native on the SAM460ex, and the only thing I noticed was that Jason McMullan had not yet completed work on the video driver so that the resolution he was running at was not optimal for the monitor he had borrowed from one of the other people attending the 2012 AmiWest Show. I did not realize that Jason was not going to set up his display at all on Sunday, because his original plan was to do his presentation on Sunday and then leave for the airport to catch his flight home. I wish I had taken a closer look at the demonstration of AROS native on the SAM460ex, so I could answer some of your questions regarding it.

I don't want to offend all of the people who have purchased a SAM460ex with my comment that Jim quoted from my email to Jim, after he had indicated that many posters on the MorphZone.org forum were interested in the Native AROS demonstration that was rumored that Jason was going to do during some part of the 2012 AmiWest Show (Jim, that is twice now that you have copy and pasted part of a private comment between me and yourself into a public forum).

Although I stand by what I wrote to you, I don't want people taking it out of the context of my perception that not many people who post on the forums of MorphZone.org would own a SAM460ex, as it does not run any version of MorphOS, so only AmigaOS4.x users would use a SAM460ex, and there are not many people who run AmigaOS4.x exclusively posting comments on a MorphOS Centric public forum. I can easily understand why people who already own a SAM460ex (which by the way has adequate power to run AmigaOS4.1.5 at an acceptable speed, or maybe even at a fast speed, but it woud depend on what you are comparing it to, as there are only a limited number of computers that can run AmigaOS4.1.5 and the SAM460ex is perhaps the 2nd fastest new computer you can purchase, or the 3rd fastest available computer over all if you consider all current and past computer designs that can run AmigaOS4.1.5 on today.

Comparing computers that can run AmigaOS4.1.5 with other computers which are not capable of running AmigaOS4.1.5, makes no sense. It is like comparing a Ferrari with a pick-up truck. Only the truck is capable of carrying over 1,000 pounds of cement bags down a dirt road to a construction site without damaging itself, so it serves it's specific purpose well. Running AROS on the SAM460ex does not make any sense, UNLESS the person already owns a SAM460ex to run AmigaOS4.1.5 and he just wants to explore what running AROS is like, just like many X1000 owners are curious about how well their X1000 can run Linux, so a few smart guys with X1000's have taken the time and expended the effort to write, or modify existing Linux kernels, so they can boot many different versions of Linux on their X1000 computers, but I doubt that any Amiga users have purchased their X1000 computers only for running Linux on them, just as I strongly doubt that any MorphOS3.1 users will purchase a SAM460ex so they can run AROS native, instead of buying an x86 PC to run AROS Natively at many times the speed of a SAM460ex.

Jason McMullan already owned a SAM460ex and his programming skill set is ideal for writing AROS drivers, from what I can tell, after spending just a short time with him on Friday evening and a little time while we were setting up his AROS demonstration and I was setting up the many computers I use each year to demonstrate MorphOS, with the addition of my X1000 this year, that was sharing my table space with all the MorphOS3.1 computers.

Sorry for the long explanation, but I did not want my quoted comment about the SAM460ex to be misunderstood, without the context I was using to base my comment on fully explained. When you discuss AROS running native on the SAM460ex, you naturally must consider other platforms that can also run AROS. The same discussion is very different when you are talking about computers that are capable of running AmigaOS4.1.5. Since I own, use, and promote all flavors of the Amiga experience, including all of the Classic Amiga computer models, so I never want any of my comments used out of context, which is why I have written such a long explanation here.

Perhaps Jim also misunderstood my comment, as I did not write it out clearly within my email to him, which was short and did not include any long explanation, but I thought he would understand, since I believe it was this forum he was referring to, when he made the initial comment about people being very interested in the rumor of Jason McMullan demonstrating AROS Native on the SAM460ex.

[ Edited by amigadave 24.10.2012 - 04:50 ]

Addendum:

>> he instead announced that he is moving forward with more new computers
>> from A-Eon with Varisys as his partner and AmigaKit was also joining him
>> as a partner to produce new AmigaOne computers.

> True, he specifically said that they contracted Varisys to develop three new products,
> one of which will be an XCore processor card. I guess the remaining two will be
> standalone PPC boards for running OS4.

"we learned a bunch of things this year, including news on two systems coming from A-EON"
http://amigaworld.net/modules/newbb/viewtopic.php?topic_id=35667&forum=16&start=380#685510

Not sure why David would feel compelled to make such a long explanation.
Frankly, I'm baffled at the idea of running AROS on an expensive PPC when there is already a more mature, faster X86 version.
Sure the SAMs don't run MorphOS, but since they do run OS4.1 I'm not sure why Jason would want to expend this much energy on this.

Mind you, this is solely MY opinion, but as AROS is freeware designed to run on relatively low cost hardware, focusing on X86 and ARM makes more sense to me.

Since MorphOS and OS4 are commercial products, I can justify spending slightly more on the hardware needed to run them.

Andreas_Wolf,
Quote:

Curious.
Trevor mentioned months ago that he and Paul Gentle's firm were working on at least a couple projects.
But I don't think he's revealed too many of the details yet.
Considering that Paul mentioned an interest in Qorlq processor to me about two years ago, and considering the remarkable developments within those product lines, one can only wonder what those fellows are up to.

> Curious.

Why? 2 new systems plus 1 new XCore card amounts to 3 new products. So I'd say that this year's statement is very much coherent with last year's statement.

> Trevor mentioned months ago that he and Paul Gentle's firm were working
> on at least a couple projects.

True, and 3 is a couple, isn't it?

> Considering that Paul mentioned an interest in Qorlq processor to me about
> two years ago, and considering the remarkable developments within those
> product lines, one can only wonder what those fellows are up to.

...and not to forget considering this:

https://morph.zone/modules/newbb_plus/viewtopic.php?forum=3&topic_id=7001&start=745

I can imagine that Varisys base the Nemo successor(s) on their VM400 product, which would mean that the 2 new A-Eon systems could be a cheaper lower end system with P3041 chip running at, say, 1.2 GHz, and a more expensive higher end system with P5020 chip at 2.2 GHz, all using the same basic board design thanks to the pin compatibility of the chips. And if they want to avoid the awkward situation where the lower end board has a higher core count than the higher end board, they can very well use the pin-compatible 4-core P5040 chip running at up to 2.4 GHz instead of the P5020.

>Why? 2 new systems plus 1 new XCore card amounts to 3 new products. So I'd say that this year's statement is very much coherent with last year's statement.

true, but what's the Xcore board for? An Acube add on?

>True, and 3 is a couple, isn't it?

Actually, what Trev said was at least a couple. Apparently they may have been exploring more then the three they settled on.

>...not to forget considering this:

>No, don't want to forget that. But I'm still more interested in what A-eon pays to develop.
Paul's stuff can be pretty pricey. Although he did have a really neat Xcore design early in the life cycle of that product.

I am very impressed with Varisys and can't think of any other company designing PPC boards with a better record of bringing announced projects to market.
And Paul Gentle has been a good source for advice.

> what's the Xcore board for? An Acube add on?

There's a short note about that there:

http://amigaworld.net/modules/newbb/viewtopic.php?topic_id=35667&forum=16&start=400#685542

According to this, there should be more info on the XCore board in that video (which I haven't watched yet):

http://blip.tv/bios/hazelwood-on-xena-and-xorro-6432644 (direct link)

According to a note from Lyle Hazelwood during Trevor's AmiWest 2012 presentation (direct link, Youtube), the XCore board has been specifically designed for the X1000's Xorro slot and thus won't work in anything else.

>> 3 is a couple, isn't it?

> Actually, what Trev said was at least a couple.

Even just 2 would be "at least a couple" to my understanding. So 3 is even 50% more than the minimum required to comply with that statement :-)

> Apparently they may have been exploring more then the three they settled on.

I'd be surprised if it's really more than the XCore board and the two new systems. That's not to mean that Varisys couldn't handle more, but rather that A-Eon can't pay for development of more at a time.

> I [...] can't think of any other company designing PPC boards with a better
> record of bringing announced projects to market.

There are dozens of companies designing PPC boards out there but I've yet to conduct a survey examining the announcement-release ratio of those companies to come to any such conclusion like you have ;-)


Edit: Added link to the AmiWest video.

[ Edited by Andreas_Wolf 20.11.2012 - 23:26 ]

Andreas_Wolf,
Quote:

I'm astounded that they can pay for what they are developing now.
No, what I meant was that they may have considered other options.
Not that they actively poured money into development.

Its obvious they are thinking low end, high end, and Xcore add on.

And while I like Xcore, and have explored it, I'm no more into that then the Parallax Propeller or the multitude of ARM based MCUs.
I hope A-eon doesn't focus too much on Xcore.
Its a rather limited technology that may be less powerful then a FPGA.

I wish there was something better then OS4.1 to run on A-eon boards (or Ubuntu as I can run that on an X86 or ARM).
Maybe I've been a little hasty about AROS.

> what I meant was that they may have considered other options.
> Not that they actively poured money into development.

For instance? The netbook form factor is supposed to come from Hyperion. What would that leave for A-Eon? A tablet?

> I hope A-eon doesn't focus too much on Xcore.

That's my hope too. I think XCore is of no real use in the market A-Eon resides in with the X1000 and possible future successors.

> I wish there was something better then OS4.1 to run on A-eon boards
> (or Ubuntu as I can run that on an X86 or ARM).

No OS4 and no OS that can also run on x86 or ARM leaves only MorphOS, right? :-)

> Maybe I've been a little hasty about AROS.

You mean AROS/PPC running hosted on Linux/PPC on an A-Eon PPC board? But then, AROS also runs natively on x86 and thus wouldn't meet your premise of an OS you'd wish to run on any A-Eon PPC board.
Btw, about native AROS/PPC on the X1000:

"AROS is now running on PPC SAMs & Sam Crow has said he would see about getting it going on the A1 & X1000, something I asked about at Amiwest."
http://amigaworld.net/modules/newbb/viewtopic.php?topic_id=36695&forum=16&start=120#686212

>> what I meant was that they may have considered other options.
>> Not that they actively poured money into development.

>For instance? The netbook form factor is supposed to come from >Hyperion. What would that leave for A-Eon? A tablet?

Well, as total speculation, even simpler boards like a micro-itx, a PCIe plug-in board, tablets like you mentioned, other processors (outside of the likely Qorlq components). Since they're pretty close mouthed its hard to say.

However, in all likelihood, pretty much what we've been speculating about (although the e6500 looks less likely now with the lowered clock speeds).