Qualcomm Snapdragon, DragonBoard 410c Fire Up at World Maker Faire | Hacker News Reader

Qualcomm Snapdragon, DragonBoard 410c Fire Up at World Maker Faire

makezine.com

49 pointswootboards39 comments

I have one of these, and so far it's a mixed bag. First off, the wifi is badly broken in ubuntu because NO multicast ethernet packets are received by Linux; they are apparently being filtered in the ethernet card by the binary blob. No solution exists at this time, and the shipped Ubuntu kernel doesn't support any USB network adapters I have.

On the other hand, it did work well enough for me to make a basic port of LinuxCNC to it, though without a working PREEMPT-RT kernel it cannot be used to control hardware.

Of the ARM SBCs I own, this board is way below ODROID U3 and RPi2 -- it's buggy, it's not particularly high spec (other than being aarch64), and it doesn't have the world of accessories that RPi has. (Pick ODROID for performance, RPi for accessories)

But if you want to port an app to aarch64, or just say that you own a 64-bit arm system, and your hardware budget is under $200, DragonBoard and hikey are basically the two games in town.

https://bugs.96boards.org/show_bug.cgi?id=66 "Ubuntu can't ssh in"

What is the power draw like at idle and load?

I only have a kill-a-watt for measuring power consumption. I am using a brandless Universal AC Adapter at 15V and I do not know its efficiency. I'm not aware of any ability to monitor power consumption directly on the dragonboard.

    Idle, text  1W 5VA
    Idle, X     2W 5VA 
    1CPU, X     3W 7VA
    2CPU, X     4W 9VA
    4CPU, X     4W 11VA

(CPU load generated by dieharder statistical randomness test on AES_OFB CRNG, dieharder -a -g 205)

Incidentally, Dieharder's AES_OFB CRNG (which I don't think uses the AES instruction set on intel) runs at 5e6 randoms per second per thread on dragonboard, compared to 2.5e7 randoms per second per thread on my 3yo 2-core/4-thread i5 laptop at 2.6GHz, to make just one simplistic comparison of CPU speed.

(edited to try to fix formatting)

The board should be prepared for current measurement instrumentation. Details can be found in the schematics, that finally got published after they were sitting around on them for a few months.

Not publishing the schematics and a couple of other things are actually violating the grand LINARO 96boards compliance spec, but nobody there seems to really give a f...art.

Thank you! That does put an upper ceiling on power draw. (When I measure, I either use a bench PSU or splice a DMM in line.)

I researched the 410c schematic as suggested by tbr. I can measure the input voltage at J1 and measure the input current as a voltage across the .1Ohm resistor r77 or pads 1 and 2 of j10 (both on the bottom side of the board).

    Idle, text  15.2v   115mA  1.75W
    Idle, X     15.2v   124mA  1.89W
    1CPU, X     15.2v  ~180mA  2.74W
    2CPU, X     15.2v  ~240mA  3.65W
    4CPU, X     15.2v  ~260mA  3.95W

All of my CPU loading scenarios had much more variable current readings, I tried to record the highest value I saw on a multimeter with a ~.5s update time over 10+ seconds.

[Slightly offtopic] Since you seem to have lots of experience (and numerous ARM boards), I'm curious if you've had a chance to try Applied Micro's 64-bit ARM SOC[0]? I realize it's $1500, but that's probably to reduce support costs and qualify potential customers. Anyway, it would be nice to know from a first-hand source.

[0]https://www.apm.com/products/data-center/x-gene-family/x-c1-...

We've been using these at Red Hat for 18 months+ and after an initial rough start, they are now our workhorse machines for aarch64 development (I've got one under my desk). They are 8 core (plus 1 x 32 bit management core), come with 8, 16 or 32 GB of RAM, UEFI firmware, ACPI and other enterprise features. They're nice and fast for development work.

Largely, the hardware and firmware bugs have now all been resolved or worked around.

Downsides: No wake-on-LAN. No IPMI. (Both rumoured to exist in the management core, but I've not worked out how to enable either). The 10 Gb ethernet doesn't work for me. I don't have a monitor plugged into mine, but that's OK since I only care about serial access for ARM server hardware. Mine is noisy because of the numerous, loud fans. I disabled all the case fans, but haven't had the balls to disable the processor fan which still makes a racket.

For virt development, OpenStack and that kind of thing, they're the only [aarch64] game in town.

In summary, they work well.

Thanks for the run-down, esp. the mention of the CPU fan, as I had noticed it in one of the photos. I'd be interested in reducing clock speed in the hope that I could get rid of all the fans (maybe use a heatsink?). The available RAM and lack of GPU are major benefits, and I hope we see more products with those features. Cavium seem like they could offer something similar, but I don't think their sales model fits with widespread availability of dev kits.

Edit: Their site and sales sheet have a discrepancy about power supply. Does the dev kit come with one, and what are the specs? Thanks again!

There's a photo of mine on this page (on the left): https://rwmj.wordpress.com/2014/09/08/raise-the-itanic/

The machine is physically a standard 19" 1U rack case, half depth (or less?). It comes with an 80W PSU and a single SATA HDD. I fitted mine with a second SDD (I believe there are 4 SATA ports on the motherboard, but not enough room in the case for 4 hard drives).

The motherboard inside is pretty tiny, about 7"x7".

Red Hat have some Caviums and Seattles as well, but I've not used those.

Edit: I forgot an important point: The upstream kernel works out of the box. (For x86 users, this will sound like a strange thing to point out, but it's BIG news in the ARM world).

Have you retried with a more recent image? After I kicked them about the USB Ethernet situation Ndec enabled a few more drivers for the kernel in the Ubuntu images. Both my ancient Pegasus USB1.1 and a newer USB3 GBit card then worked out of the box.

The WiFi situation is indeed annoying and I've complained about it, they seem to be since looking into it, but as the driver is open source, someone else could check too and send patches. There even is a debug tool to intercept the proprietary QC driver commands (used in Android images). It should just be reconfiguring the filters away from their broken default state.

Yeah, I had a similar situation on the Hikey 96board. I ended up downloading their kernel source and building a bunch of additional modules so I could get USB Ethernet, as the wifi was basically useless there too.

Yeah, luckily that was very straight forward. Did that too before they released the new images.

Though the Dragon Board looks great, the specs on the HiKey board are even more impressive [1, 2], but I haven't found anyone selling them yet. There is a variation of the HiKey board made by LeMaker that has more RAM [3]. The 96boards "Enterprise Edition" boards are just stunning [4, 5] and have two DDR3 SO-DIMM sockets, but again, they aren't shipping yet.

[1] https://www.96boards.org/products/ce/hikey/

[2] http://www.em.avnet.com/en-us/design/drc/Pages/HiKey-board.a...

[3] http://www.cnx-software.com/2015/09/23/lemaker-hikey-96board...

[4] http://www.cnx-software.com/2015/06/28/amd-announces-96board...

[5] https://community.amd.com/community/amd-business/blog/2015/0...

I got mine from Arrow(US) in July. They suspended shipping at some point after that due to missing FCC tests, but you could still get the board if you signed a waiver.

The HiKey board has different pros and cons. Pro: It's received a lot more engineering time, as it was the first 96board. Actual open source first stage bootloader, from what I can tell. Con: WiLink8 WiFi; Initially unobtainium as "produced" by Circuitco in homeopathic doses; HiSilicon also needs quite some proprietary blobs for things.

So far ALL 96borads have their problems and surprisingly all of them seem to violate the LINARO/96boards spec in multiple ways.

I think there were hardware bugs on a lot of the Hikey wifi boards too. Mine always failed in the driver and I ended up using USB Ethernet after rebuilding the kernel.

The onboard eMMC is also extremely slow, luckily it's easy to switch it to boot off a microSD instead.

The kernel forked at 3.17 and hasn't been updated since.

So far I'm pretty disappointed, both hardware and software wise. I find it surprising Linaro would put their name on this, I really hope this isn't the "reference" for quality.

Pros:

* cheapest 64 bit ARM

* 8GB flash

* onboard GPS

Cons:

* relatively slow cores

* 1GB ram

* no usb3

* no ethernet (100 or 1000)

* no sata

For lightweight desktop/server use, this is a horrible board. The XU4 blows it away on all counts. However, the inclusion of onboard GPS shows more what it was meant for: things that move. Likely battery powered things that move.

The utility of the board comes down to the max and idle power draw. The XU4 is the board to compare the DragonBoard against; it does 2.5W idle and 8W-12W peak. If Qualcomm can beat those by a factor of four or so, then I could see a place for the DragonBoard.

Would be interesting to see a comparison/benchmark similar to: http://www.davidhunt.ie/raspberry-pi-2-benchmarked/

Why not choose an Intel ecosystem board, something like:

http://www.minnowboard.org/meet-minnowboard-max/

Traditionally they have been behind on development boards like this but things have been improving. Unless you must have lowest power I'm thinking that you are in many ways better off:

    64-bits? No problem.
    Performance? Intel has a matching Atom for every Arm.
    Compatibility? Run desktop Ubuntu.. heck, run Windows
    Drivers? They are all open source and work.

There are a bunch of extremely cheap Z3735F based systems available also, for example: http://www.geekbuying.com/Search/?keyword=windows+mini+pc ("pc stick" and "mini pc").

(I do like ARM, but at the Cortex-M0 level as a PIC replacement).

Minnowboard Max has the same unobtainium problem like the HiKey. That said, it's about to change.

Luckily also there a second manufacturer stepped in and the 'Turbot' version was recently announced. Same as the LeMaker version of Hikey, should have less of the usual Circuitco Unobtainium problems.

Off topic, I didn't know the spelling "faire", and didn't come across having lived almost a decade in the US. My dictionary just says "obsolete spelling of fair". Does it carry a slightly different meaning? Why this obsolete choice?

It's just their branding, I think: https://en.wikipedia.org/wiki/Maker_Faire.

Perhaps it allows them to trademark the name?

Renaissance faires use the renaissance spelling. Maker faire is perhaps trying to evoke those.

Interesting to see a board with built in GPS for mobile apps, as well as wifi/bluetooth.

Nice to see Cortex-A53 for a bit more CPU performance (compared to raspberry-pi), but anyone know how GFX driver support compares to the r-pi?

Note that GPS so far only works under Android with the QC propriatary binary mumbojumbo. Not sure about the graphics drivers, would need to check.

I would imagine that there will never be a fully open source gps, as this would allow anyone to bypass the "am I a missle?" test.

Ndec claimed that there is interest from QC to have as much as possible implemented as open source.

We will see how far this goes.

There are already many open source implementations of GPS using SDR.

In addition, most consumer GPSes just have firmware that does the SDR bit and output NMEA strings. There's literally no reason for the driver receiving NMEA strings to be proprietary.

Then what is preventing an open source implementation from exceeding the 60,000 ft and 999mph limits imposed by the US DoD?

Nothing.

Looks interesting, but seems a little pricey. It looks like the ODROID XU4 (http://www.hardkernel.com/main/products/prdt_info.php) but with the ODROID you at least get 2GB of RAM. Either way, it's good to have competition.

I've had one of these on order for about six weeks (from https://www.96boards.org/products/ce/dragonboard410c/). Are they shipping now?

No gig-e? :(

What would you do if it had gigabit Ethernet that you can't do now?

Use it as an HTPC/Streaming PC? A lightweight desktop replacement? Digital signage? Home automation? Home server? Built in b/g/n is a nice touch but most prefer the ease of installation, reliability, and goodput of ethernet over wifi for anything important.

I suppose you could use a USB ethernet adapter, but now you're just sacrificing a USB port to have a less capable XU4. I'm not sure what market they're targeting here. I suppose you're just supposed to build mobile devices around this.

Yeah, ethernet is nice for a bit of reliability but it's not that important.

But I was focusing more on the 'gigabit' part, and what you listed generally doesn't need it.

If you are looking for GigE. https://developer.nvidia.com/jetson-tk1

Reply on news.ycombinator.com