There's Still No Sign Of AMD's Low-Cost ARM Development Boards

[ddriver]

So 600$ for an arm board is "low cost"? Here is the list of the people "missing it":

list ends here.

[starshipeleven]

So 600$ for an arm board is "low cost"? Here is the list of the people "missing it":

list ends here.

You know shit of devboards right?
Pricing of 1.5k or even more is normal.

We aren't talking of crappy trash SoCs like tablet stuff.

[jrch2k8]

Instead of a board that's recycling old ARM cores and that apparently isn't on sale anyway, may I suggest an alternative that's truly an SoC with strong power efficiency: http://www.anandtech.com/show/10574/...f-atom-iot-kit

Bonus points for having a GPU architecture with open-source in-kernel drivers and being made by Intel, who is the #1 organizational contributor to the Linux kernel.

Sadly Intel sucks extremely hard on embedded and to buy joule is basically burn $360 for the fun of it, plus Joule is implicitly EoL already since Intel kinda emo rage quitted the embedded mass market and instead will rent their fabs to ARM.

This boards at best are for some cool factor demos on Windows IoT but for nothing else, is too expensive and the power figures are not impressive by any standard and from what i could gather the GPU is nothing to be proud either since at this price tag nVidia Maxwell/Pascal systems will tear it a new one and actually support Cuda, OpenCL, OpenGL, OpenGLes, Vulkan, etc.

The actual novelty of the AMD boards was the fact they were made by AMD, imagine the efficiency of AArch64 with AMD GCN architecture but half the price of Tegra but well the dream is off for now.

[schmidtbag]

Perhaps AMD realized Zen was better than expected. I originally got the impression that AMD made this ARM Opteron as a sort of last-ditch effort to keep themselves relevant as a CPU manufacturer. I doubt AMD ditched their ARM designs entirely though. They're probably just holding them off, focusing all their engineers on Zen for the time being.

[Min1123]

Since I ordered the Lemaker Cello, I have received a few emails from them.

June 28 I got this:

Thanks for your support for LeMaker Cello. We announced the prototype of LeMaker Cello at Linaro Connect BKK16 in March 2016, and we planned to start shipment from this month. In past three months, AMD, Linaro and LeMaker have been working on completing the design validation and getting Cello supported in Linaro Reference Software Platform. 



Currently we are running a small pre-production batch which is expected to be completed by fisrt week of July. As soon as this new batch of boards pass the tests, we will be confident enough to kick off the production of 200PCS early-bird engineering board for you all. Please accept our apologies of the delay, we will keep you posted in the meantime. Please grant us more patients and we'll ensure you a new well Cello. Thank you again.



As it is declared on lenovator.com, the fist batch of LeMaker Cello for public will be early-bird version, the FCC and CE cerstification is not released yet. You'll receive the shipping package with a mark of "engineering board". But don't worry, LeMaker guarantees the technical support and after-sale service for all the customers. If you had quality issue or met problems when using LeMaker Cello, we will provide helps, repairs or replacements. We expect that you’re an experienced engineer or a company if you bought the early-bird engineering board, we do not suggest the newbie to buy it at current. 



Last but not the least, if you want to order the heat sink with fan and SODIMM ECC DDR3 memory module, please reply this email so that we can prepare it for you. The heat sink and memory module will also be available at lenovator.com for purchasing as soon as the coming up of the first 200PCS LeMaker Cello.  Alternatively, you could also source these two components by yourself since it might be cheaper to buy it locally.

And then some info about the particulars of the heat sinks.

On August 19 I received this:

Dear Friends,

Appologize to delay the Cello board again. We produced 10PCS samples on sencond-stage in July and sent to Linaro and AMD to debug. Still the problem is on the PCIE connector. The PCIE power rails, clock, reset signal and tx lane are all work, but only the rx lane can not get the signals. All other functions on Cello are now working well. 
We already have all the components stocked in our warehouse and waite the PCIE problem to be solved, then we can begin mass production.

We also have prepared 50PCS free heat sink with fans for  the first 50 orders.
Thanks for your support again.

So the boards are moving ahead, but AMD didn't actually launch the production A1100 run chips until January, so even without getting FCC certs this is probably pretty fast.

[c117152]

I've looked it up as well and from what I can tell all the ARM server class +\- dev boards SoCs got delayed or outright canceled when the Amlogic S912, the RockChip RK3399, MediaTek Helio P30 and etc... were announced with 8+cores clocked at 2+Ghz.

At this point, the Chinese fabs are a decision away from throwing in ECC memory and a PCI-E bus to a SATA controller for competing against AMD and Intel in the server market. So, Intel is giving up and starting to fab ARMs again. While AMD is exploring their options while pushing back their release.

If you need conformation, just look at what Google is cooking. They've canceled running ChromeOS apps on other platforms while starting to build windowing support into Android. If that's not an obvious move from a company who knows what hardware is coming next, I don't know what is.

[ddriver]

You know shit of devboards right?
Pricing of 1.5k or even more is normal.

We aren't talking of crappy trash SoCs like tablet stuff.

This board is nothing special - quad core A57, and it doesn't even come with ram. It is NOT a "special" cpu, it is about the same stuff you see in every decent tablet or phone. That price is laughable, even at 300$. I know enough to know how much it is worth, now if you are willing to pay 1.5k for it - my condolences. Quadruple the cores, and I will get a few at 300$, then it will be a good deal.

[hajj_3]

the amd arm chips sucks as cortex a57 sucks. cortex a72 has been in phones for many months and cortex a73 out in a few months. K12 however is a much more interested cpu core which hopefully will be ready next year.

[bridgman]

Perhaps AMD realized Zen was better than expected. I originally got the impression that AMD made this ARM Opteron as a sort of last-ditch effort to keep themselves relevant as a CPU manufacturer. I doubt AMD ditched their ARM designs entirely though. They're probably just holding them off, focusing all their engineers on Zen for the time being.

AFAIK the A1100 was to make sure there there were enough server-class parts out there to finish the ARM server SW ecosystem before K12 shipped, and to give us a seat at the table in case the ARM server market took off as quickly as many were forecasting. We had to do something similar to get SW ready for AMD64, but there we had to do a lot of the early dev work with ISA simulators.

[torsionbar28]

While that is true it is also long term, AMD is much more likely to sell more x86 processors than ARM SoCs in the near term, and if they don't sell anything in the near term there will be no long term at all.

x2, I'd be willing to bet it's "all hands on deck" at AMD for the Zen product line. They absolutely have to get Zen right, and ASAP. Their survival depends on it.

ARM is indeed promising, but it's a niche market still. You won't see any significant ARM in the datacenter until you get enterprise OS support. That means RHEL and SLES. I'm sure that's in the works, but as of today, it's nonexistent outside of developer previews. Probably because the AArch64 hardware selection is so slim, is anyone selling an ARM commodity server besides HP right now?