Toshiba AC100 Smartbook – Underdog to Winner in 5 Months

I have had the Toshiba AC100 for as long as I have had the Genesi Efika MX, but on top of suffering some of the same frustrating limitations, the stability of the drivers for it in the Linux kernel just wasn’t quite up to the task until recently, and few sane people would consider using Android on a device without a touchscreen, as Toshiba appear to have envisaged.

Since Efika MX‘s major problems – the painfully low screen resolution (a problem it shares with the AC100) and the completely unusable touchpad – turned out to be easily fixable, the AC100 went on the shelf for a while. This was a shame since the AC100 had about three times the CPU power of the Efika MX (dual core Cortex A9 1GHz vs Efika’s single core Cortex A8 800MHz), but having a fully working, usable system was more important.

All that changed recently. ChromeOS 2.6.38.3 kernel brought with it more support for Tegra2 based devices, including the development board that the AC100 is based on, and shortly afterwards thanks to the awesome people in the AC100 community, a lot of things fell into place, including stable NVEC support (what keyboard/mouse/LEDs are connected to on the AC100) and sound support. But most importantly for me, the recent kernel also came with the kernel level display panel setup. No longer entirely at the mercy of what the boot loader configures, it became possible to use a higher resolution screen!

So, I carried out the upgrade to 1280×720 using the same TFT panel that I used to upgrade the Efika. All that was required was a small kernel patch. Without a change to the boot loader data the machine still starts up in 1024×600, and the kernel boot-up output is corrupted until the console font is re-set, but since setfont is called very early during the Fedora boot-up sequence, it is a problem that isn’t hard to live with. From there on, everything works absolutely fine in 1280×720. An article on the details of the upgrade procedure and the required kernel patch will follow shortly.

The nvidia binary driver works OK-ish – most of the time, but it isn’t particularly stable – every once in a while you will do something that causes the screen output to get partially corrupted. This is not related to the higher resolution, all the problems occur at 1024×600, too. Unfortunately, it doesn’t look like nvidia are showing that much interest in improving this quickly, and since their approachability and interest in helping their user community is as non-existent as ever, I wouldn’t expect driver improvements any time soon. Still, for normal use the standard unaccelerated frame buffer driver is rock solid, and the acceleration in the nvidia driver does work well enough if you want to play videos at full screen resolution, and there is even a Tegra accelerated version of flash available so YouTube works, too. All of this is a considerable improvement on the Efika MX.

Power management is also completely functional on the AC100 now, so it’s battery life is virtually identical to the Efika MX.

It is amazing how much difference 5 months can make. AC100 went from being the underdog to being an outright winner. It now matches the Efika on battery life and screen resolution, and soundly beats it by a large margin on the touchpad (the touchpad on the AC100 is actually extremely good), performance and features (no YouTube without Flash).

Best of all, it is no more expensive than the Efika MX. Here in UK – new ones can be had for as little as £170, which is less than you’ll pay for an Efika with a non-US keyboard.

In fact, the price/performance in terms of CPU power is actually better on the AC100 than it is on the SheevaPlug, and that’s before the added convenience of also having a screen/keyboard attached for troubleshooting. Because of this, AC100s are now used for extending my ARM compile farm.