Slashdot Mirror
CEO of Centaur Discusses x86 Strategy and Linux
An anonymous reader writes "This fascinating interview with Glenn Henry, founder of VIA processor subsidiary Centaur Technology, discusses the founding of Centaur, its strategy and products, and why Linux is fundamental to his company's success. Additional topics covered include: how to produce an x86 clone with a few million dollars and a few dozen engineers; the embedded x86 market, and how it compares to the traditional ARM and MIPS based embedded market; why Centaur doesn't compete with AMD and Intel so much as enable x86 to reach new markets; how Linux is enabling greater hardware functionality; the urgent need for pervasive security -- and much more!"
If you want that, get a Soekris box. I run a few of them and they're very nice.
Whether it's the best "textbook" architecture or not, it's entrenched itself in the computer world so deeply that x86 will be around forever.
It works, engineers and coders are familiar with it.. The embedded world is still largely about ASM routines and tight little loops that dont leave the cache, etc, etc.. You can write and test your fancy-shamcy hand-assembled routine at your leisure on your desktop computer.... There are plenty of upsides, and the only downside is the "other stuff looks better on paper" argument.
It's a newcomer to the embedded world, but will no doubt take a strong hold.
I don't need no instructions to know how to rock!!!!
In the embedded (business/use)-case, the Centaur CEO is talking about, Linux is crucial, because it is cheaper. Windows adds a lot to the sale price. Linux doesn't, so it has a competitive advantage.
Actually, the architecture I would recommend (and the one I use) for really small footprints is the ETRAX 100MCM from Axis.
The new version (it's not on the web yet, but they are shipping in limited quantities) includes on chip: 4 Mbyte Flash, 16 Mbyte SDRAM, an Ethernet transceiver, Reset circuitry, and dozens of passives (resistors and capacitors), and all the usual: 4 Serial UARTS, a parallel port, SPI bus, etc.
So if you wanted to build a credit-card sized Linux machine with Ethernet, BOA webserver, SSH, FTP, vi, sqlite, LUA scripting language, etc., you could (and you would still have at least 1.5 MB left over).
This is what I use for my embedded designs, and it's astonishingly easy using the cross-compiling toolchain (basically, just gcc and a change in the makefile for target) that they provide. They also have a mailing list for questions if you don't want to call.
Oh, and their architecture is now supported in the main fork of the 2.6 kernel.
It's throw-away lock-in. Same thing that happened to Televisions and VCRs 20 years ago. Standardizing the parts and interfaces won't help - the labor required is simply too time conssuming.
Laptops are amazingly upgradable, and even those are less and less apt to be worth the time required. You mention driver circuits, but really - there are somewhere around 80 different driver circuits in current use for laptop displays. Yet, there are some 500 laptop models out there. And without the the driver circuit, the Liquid Crystal display is far cheaper than an integrated unit would be. So, I think that part of your argument is counter-productive. LCD + accompanying driver costs a lot more money, yes. However, the video card hardware can be configured to talk to most of the driver circuits (they are close to standarized at the interface level). Again - it's just a lot of work.
When you don't have the 90% air that most PC chasis hold, you can't have big bulky large finger capable standard connectors between every part. Sometimes, you have to route your signals through flat cables or custom bundles.
Really that pain-in-the-ass to price point is even hitting PCs. Once a computer is more than 3 years out of date, it actually becomes cheaper to simply buy a package deal. If you really liked your case, swap it, the case was free with the bundle - along with yet another floppy and CD-ROM. As prices drop, the three years will turn to 6 months. Or about the same period between major CPU/architecture performance boosts.
Kinetic stupidity has a new brand leader: Allen Zadr.
Check out Ministry Mobile's device. Vaporware?
Thinking of starting a business in Minnesota? Me too! mnsmall.biz
Cirrus Logic EP9301 eval kit.
It immediately occured to me that this guy is very good at thinking out of the box. A processor company is not an easy thing to create, especially with a startup budget as low as 15 million US.
Now they have been through 5 major product revisions and are currently shipping 1GHz PIII compatible processors that don't need a fan.
Technically, I'm not laughing. Personally, I'm wondering if I should send him my re'sume'.
Kinetic stupidity has a new brand leader: Allen Zadr.
Not really. There isn't much assembly necessary on a modern embedded platform.
Ditto. I have only really used asm in two or three places in embedded projects. One is in the initial bootloader. The second is in instances where the compiler won't do what I want. The third is to access special instructions that the compiler doesn't know about (eg, eieio on the PPC). The second and third instances can't mostly be dealt with inline asm and cpp macros, and gcc make this a lot easier if you have access to it.
(S(SKK)(SKK))(S(SKK)(SKK))
Since then they've come out with the C3 "Nehemiah" which has a full speed FPU and has a 266MHz bus. They've gotten somewhat faster; although, I don't have any benchmarks for you.