[fedora-arm] 1ghz ARM Laptop (12in 1280x800 LCD)

[Gordan Bobic]

Matt Sealey wrote:
>> Thank you for the proposal and none the less interesting discussion. It's people like you who actually "get us there" at end, and it's good to know that possible ways are being searched for.
>>
>> Unfortunately, I'm not a hardware hacker. But, as a consumer, I'd say that a "1gb NAND Flash" is quite a bit below the level. I also wouldn't care much about a 1280x720 screen if the hardware wouldn't be capable of playing the video flawlessly. Or, if there was an HDMI port to connect to TV, which is, in my taste, better suited for watching.
> 
> The Efika MX desktop has 8GB and the Efika MX Smartbook has 16GB of
> NAND flash connected to the PATA port. Plenty of space.

That may have been OK by standards of 2-3 years ago. And kudos for 
including an extra uSD port for extra storage. But performance of _ALL_ 
SD cards on the market today is appalling. The best ones are ~100x 
slower than a decent SSD and cost 3x more per GB. As I said before, the 
only usable SD cards for running the OS from are the SanDisk and Lexar 
ones, and those are those are about £110 for 32GB vs. £60 for a 40GB 
Intel X25-V which will annihilate them in performance and is ~20% 
bigger. With uSD the situation is even worse, the cards are even slower 
and even more expensive.

The way forward here would be a SATA port. Anything else doesn't cut it 
in terms of performance, and even on something as low on CPU as an 
800MHz A8 still suffers significant slow-down when working off SD cards. 
This has a massive effect on perceived performance, especially with only 
512MB of RAM for caching to cover up the deficiency.

Annoyingly, I've not yet seen a production ARM based netbook with a SATA 
port.

> I agree
> wholeheartedly (see above..) with the video playback thing. A laptop
> *only* good as a compiler box won't sell.

Perhaps you can tell us, then, when the Efika MX will have accelerated 
drivers available? The video poing keeps coming up, but Xorg on my Efika 
MX is running off raw fbdev on mine and none of the standard 
acceleration APIs work (e.g. XV).

>> The gorgeously-looking Efika MX would fit me almost perfectly if not
>> the soon-deprecating A8 CPU and the plans for a dual-core solution
>> with faster RAM. Plus, taking in mind the early stage of software on
>> ARM and its stability issues and rather a development taste of the
>> hardware, 350 bucks seems above the decent price when you see a 299
>> competitor on Atom which is, yes, only a 2-hours-on-battery runner
>> that heats like a stove, but hell, it has 1 gig of RAM, a 160 gigs
>> hard drive and takes $my_favorite_distro on-board.
> 
> The Cortex-A8 is absolutely NOT being deprecated.

Maybe not deprecated in the "out of production sense", but in fairness 
an 1GHz Tegra 2 blows it away by so much it's not even funny. I think it 
would be foolish to bother bringing out a new product based on the A8 if 
it is intended for non-embedded use (i.e. generic laptop/desktop use). I 
can see that it is overspecified for tablets, phones, and other devices 
with 800x480 screen that will never need to start up OpenOffice or full 
fat Firefox, but it doesn't have that much margin for error when it 
comes to staying on the right side of borderline for a laptop.

But that's just my opinion having extensively used both in the past 
month or two...

>> As for the "early
> stage of software on ARM", we've been running and shipping a full
> Linux desktop (GNOME, for all it's worth) for well over a year. I'm
> not sure what you guys think the state of ARM actually is, if you're
> basing it on the availability of Fedora.. well, that is Fedora's
> problem. Other Linux distros (Debian for example) have had no problem
> running on ARM for almost a decade, using the EABI for nearly 5.

Indeed, I think a lot of us are painfully aware of just how far behind 
Fedora is at the moment.

> The reason we chose Freescale's i.MX515 is because it had the most
> mature Cortex-A8 implementation on the market and by far the best
> integration and featureset. Compared to the other A8 chips at the time
> - from Samsung or TI - it was head and shoulders above on featureset
> and performance. As an owner of several varying revisions of
> Beagleboard, I would say OMAP3 was not the greatest chip to be working
> with in the world. I like my Beagles but based on experience, I have
> some doubts that being there first is better than having a mature
> implementation.

One of the big problems with ARM SoCs is that a mature implementation 
(to me at least) means having good, stable drivers that are well 
supported and updatable for the rest of the OS stack (i.e. you want to 
make sure that there is a suitable Xorg driver when the distro moves to 
a new version of Xorg with a new ABI.

By that measure there is no such thing as a mature ARM SoC 
implementation, and there will not be until there is an OSS driver for 
PowerVR. Given it has taken the best part of a decade to get stable 
accelerated ATI and Nvidia drivers (which are still, BTW, nowhere nearly 
as accelerated as you might think), unless there is suddenly a big drive 
for raising millions for funding development of an OSS PowerVR driver, I 
wouldn't put much stock in seeing such a thing available before the end 
of this decade.

> Freescale's roadmap is based on waiting until the
> platform is at a point where it won't cause significant problems to
> the rollout of the chip - less errata to deal with, ideally less
> chance of a major automotive customer having cars sold where the
> dashboard stops working. They'll hit Cortex-A9 at a fairly decent
> revision, with a very tight integration and an optimized core on an
> optimized process. TI is trying to be ahead of it's competitors which
> will result, yet again, in a chip which is going to take 2 years to
> actually get anywhere in the market.

And they'll still be a year before everyone else. Companies like Nvidia 
are talking about shipping A15 based SoCs in 2012.

> This is not the Intel/AMD Windows market where every 3 months you need
> to release something faster, and faster, and faster. To give a very
> recent and very relevant example, Intel just screwed up their
> southbridge for the second generation Core i7. It's cost them over
> half a billion dollars to try and be the latest and greatest and rush
> chips out. We have had that with chips in the past, trying to be there
> too fast, and it costs money, and causes strife for customers.

Sure, but that happens once a decade or so, and the figures you mention 
are for the volume shipments are measured in hundreds of thousands. Then 
again, I do recognize the point that a smaller company can afford such a 
failure far less than Intel.

> I'll say it again, if you want 2GHz, dual core, 16GB dual-channel DDR3
> RAM, 800MHz memory controllers, go buy a PC. You're in the wrong
> market. Neither ARM nor Freescale or even TI are designing chips for
> power users;

We're not talking about power use here. We're talking about "good enough".

> the expected panel resolution is 1024x600. It's very
> common.

Oh come on. 1024x600 isn't really adequate. It only ever took off 
because of the initial rush to the market was driven by products that 
were as cheap as possible. It was a novelty to have a tiny laptop, even 
if it was no good. 1024x600 is barely adequate for something that is 
just too painful on an 800x480 phone. And since 10in screens running 
1366x768 are easily available, it's hardly justifiable from the 
usability point of view. In the x86 world there are no doubt thousands 
of those who don't know better and will buy such things because they're 
cheap. But given the price tag on ARM based smartbooks is no lower and 
the only people likely to buy them are the select elite, there is a lot 
to be said for building a product that the only likely audience would 
want. And in this case they will most certainly want something better 
than 1024x600, even if it costs them an extra $20.

> Go look at the Blackberry PlayBook, AI TouchBook, etc. - this
> is the desired form factor, this is what the vendors want, it is what
> the target users are looking for (and the targets are kids, people who
> don't do well with computers and are a little bit frightened by a
> wailing, 17" hulk on their desk just to do word processing and go to
> Facebook) and the market they are trying to capture is not People Who
> Compile Software A Lot And Need Tons Of Memory and Enough Processing
> Power to Make You Dizzy.

I can't help but think that the market they are trying to capture isn't 
going to be very responsive. How many non-geeks have bought ARM based 
netbooks? They are going to be the select elite from among those who 
might run Linux on their x86 netbooks. I don't think it's sane to be 
speccing up a low-end system targeting the unclued-up users using 
unfamiliar software, and trying to compete with x86 on price. For the 
life of me I cannot see that being a successful business strategy.

Toshiba tried to side-step the issue by shipping the AC100 with Android, 
and that was a massive fiasco resulting from seemingly nobody checking 
the usability of Android on a non-touchscreen device. Great as a Linux 
laptop (if only accelerated Xorg drivers worked), but using Android 
without a touchscreen is at best an alien and difficult experience.

Having said all that - the one thing that applies to both the consumer 
and geek markets is usability. Toshiba failed it due to shipping Android 
on the AC100. My Efika MX's usability got salvaged from the jaws of 
defeat by some software hacking to re-map keyboard keys to replace the 
completely unusable mouse buttons integrated into the glide-pad.

> I call them the Numbers Brigade because the
> actual usefulness of the device as a holistic computing solution is
> not relevant to them, it's the bullet points on the processor
> datasheet compared to another one, and the prospect of a new one
> coming out soon that will outclass it based entirely on the
> theoretical math of seeing which number is bigger without taking into
> account the way the components interact. They are the kind of people
> who live in a constant state of early adoption and infinite buyer's
> remorse. While you might think they make up a significant percentage
> of PC sales through their rampant purchasing of new technology at high
> prices and low turnaround times, they simply don't.

Except we aren't talking about PC sales here. If anybody is likely to 
have buyer's remorse when acquiring ARM based netbooks it's exactly the 
average users you describe. They are the ones that are going to be least 
able to deal with Android without a touchscreen, lack of working flash 
(no youtube), lack of video acceleration, and lack of reliably and 
unobtrusively functioning mouse buttons. The geeks will likely get 
together and hack up a solution that makes the situation bearable. The 
rest will either send the product back as unfit for purpose, ebay it, or 
shelve it and never look at it again while spreading bad word about the 
product.

> Maybe when the Cortex-A15 is out and we have ARM servers floating
> around,

ARM servers are already floating around. ZT systems have released such a 
thing. It's not cheap, but if you are up against the wall on data centre 
power consumption and cooling it is well within the realm of plausible 
when it comes to value for money. It has dual core A9s in it (8 of them):

http://www.ztsystems.com/Default.aspx?tabid=1483

> the dream of a Power User ARM Smartbook with a huge screen, a
> ton of RAM and processing power enough to spook a horse will be
> fulfilled. Good luck waiting for 2015 for that one, in the meantime I
> guarantee the first usable Cortex-A15 unit on the market will be dual
> core, less than 1.5GHz, and have an 11" 720p screen on it.

You may be right about an A15, but a large-screened A9 should be more 
than plausible today. The AC100 has a HDMI output and can (supposedly - 
haven't tested it myself yet) handle outputting a 1080 signal. I tried 
fitting a 720p panel into it, but Toshiba did some firmware "sabotaging" 
that makes higher res panels not work, but I don't have any reason to 
think this is for reasons for any hardware limitations, it's almost 
certainly a firmware issue. And if it can output a 1080p HDMI signal, I 
don't see why there would be a reason why you couldn't output that 1080p 
via LVDS to a TFT panel.

Gordan