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!"
I think it is a sound idea to go into the niche markets so to speak instead of just jumping into the fray with AMD/Intel. Everyone has had enough of the SSE2 vs 3dnow! extended vs the new kitchen sink it comes with. Those types of things have no real bearing on markets where companies are looking for solutions that are cheap, easy to deploy and know the company is designing the hardware for their problem. Not the company having to make their systems go on the vendors limited products.
The more competition the better we the consumers are at getting the best products.
Push harder towards Open Media/Content
Every other day, it seems, someone is shouting about how their company is finding linux is crucial to their success/business plan/what have you.
I wonder if it's a case of corporate "me too!" or if all the small firms were simply waiting for some large firm (IBM for example) to thumb their corporate nose at Microsoft, before they decided it was safe to do so.
Don't get me wrong, I'm all for firms being able to decide who to attach their sail to, I was just wondering why it was taking until now...
So rise up, all ye lost ones, as one, we'll claw the clouds.
You're either being _Very_ sarcastic, or have no idea about hardware.
Look up the stats on the GBA, It runs at less than 20 MHz.
-Jesse, unhappy at both hardware and software bloat, returning to the "good ole' days".
Nothing says "unprofessional job" like wrinkles in your duct tape.
I don't know if anyone else noticed, but they apparantly started on April Fools Day:
"We started officially on Apr. 1, 1995, the day the check came in the mail, an auspicious date."
I don't know why, but I found that amusing...
Give PPC a try. I love my LinuxPPC machines, they're wonderful. I honestly fell in love with the PPC in college, first in real world x86 emulation (VirtualPC) and then in Computer Architecture and Computer Hardware Design. It's a lovely architecture, and you can see its low power uses in the iBook. I've read that the 750 in the iBook used less power than the southbridge, but I don't have references to back that up. Suffice it to say, the PPCs have been traditionally pretty low power, and have pretty good desktop acceptance as far as non-x86 processors go on desktop machines.
After you get through the base packages of a useful distro, like Debian or a multitude of others, you'll start to find x86 only packages-- retail packages usually don't even acknowledge that Linux runs on non-x86 hardware! Is x86 compatible really the architecture to target for Linux acceptance? If I didn't love PPC and have a source of cheap old Macs, I'd rather be running a VIA / Cyrix derivative because of how cool they run. Since the Pentium class, x86 hasn't been about the native instruction set, it's been about the state machine that re-orders, re-names and actually issues native instructions on a pretty nice, flexible RISC inside anyway. So, Centaur's problem is basically updating their RISC core and keeping their x86 runtime emulator tuned. That way you don't have to bend anybody's mindset to make packages for some off the wall architecture, or beat another architecture at their own game.
Thumbs up for ARM (pun not intended). Plus you can take a synthetic ARM core and dump it to silicon together with the peripherals of your choice, and get a system-on-chip with very little effort. Try to do that with a x86 - not!
I hadn't known there were so many idiots in the world until I started using the Internet -Stanislaw Lem
``There are plenty of upsides, and the only downside is the "other stuff looks better on paper" argument.''
It doesn't just look better on paper. A cleaner architecture results in a simpler chip, meaning lower power consumption, cost, heat production, and smaller die size. Those things matter to embedded devices, and thus MIPS or ARM would be a better fit than x86.
What x86 has going for it is that it is much more abundant. The chips are produced in higher volume, making them easier and cheaper to get, it's easier (and thus cheaper) to find programmers who can code for them. It's really all about Worse is Better.
Please correct me if I got my facts wrong.
While system costs are higher for the consumer assembling a system, I don't think that a product for the masses will encounter the same problems. Manufacturers enjoy economies of scale that we don't; otherwise the low price providers (Dell/HP/etc.) would still be selling generic beige boxes instead of snappy looking cases.
Thinking of starting a business in Minnesota? Me too! mnsmall.biz
The VIA processors have high market penetration because they ship with all of the low-cost VIA systems. You probably just don't recognize the name because you wouldn't associate it with a standalone processor product like you would with Intel or AMD.
These guys certainly have an advantage over Transmeta in that they are tied to VIA and as such have chipset and motherboard support. Transmeta fell on it's face in part because they just did the processor and not the associated chipsets. But processors without motherboards are just inefficient paperweights.
Michael
we have the cheap desktops now, like the walmart 200 buck boxes, but does anyone make a *new* laptop that uses this guys chips and a via mobo, and is it under 500 clams brand new? what he says is true, and I'm in that 90% range that what passes for a mid range speed is MORE than enough for my purposes. I don't do gaming or weather modeling, etc. That's the breakthrough and the sweetspot general pricing range I am waiting for, the linux laptop,comes complete and works outta-the-box, including wireless, under 500$, and *upgradeable*. Is this possible now? Say it is, I mean, 3-4 years from now I could replace the whole mobo with whatever is cool then, along those lines, yet alone just swapping in a new cpu, etc. And a REAL battery (or batteries even better, in some sort of standardized arrangement, with 12 volt DC input being standard) in it, I'll tote a couple extra lbs, I don't need a laptop to weigh sub-3 lbs, 6-7 is still quite acceptable, it's the same as the ones I have now. His chip at 7 watts sounds great, and 1 ghz is perfectly acceptable. Heck, even if it had a switch to toggle it back and forth between 3 watts and 7 watts would be nice, as in clocked/not clocked.
Desktops are a different story, you can always swap around parts and do a little drilling and cutting, etc to make anything fit, but laptops are teh sucks for upgrading and working on, more or less, and they are too expensive as they are sold now to change out very often (for me I mean, but bet a lot of other folks feel the same way). I'd get one and use it for my main desktop most of the time then with an external keyboard and my regular mouse and monitor, scrap energy hog desktops, but retain the option of true portability.
Well, even so, it's still would be better than what I am using now, a PP200. I know all sorts of people still using older systems because they paid a lot of money for them and they still work well enough. So, you are right on what is top end now or midrange, but the centaur guys observations that his chips are good enough for 90% of what most people use a computer for are most likely still valid. Here on slashdot you have a much higher ratio of people who have brand new or pretty new systems than you do in the "general" population, and uber geeks tend to hang out more with other uber geeks, so perhaps they don't see it as much. I know most corporate bosses make so much money and live such a different lifestyle it's hard for them to relate to joe working stiff, that's why you see so many weird business changes-marketing and the bosses can't relate to most people, they lose track of anything outside their little niche worlds of much better off financially people than any sort of median-norm. I know there's no company out there that I have seen is offering any sort of new laptop that even possibly could be in my price range, so I hang on to the older ones, and I bought them used. Same with my desktops.
There's different niches out there, and there's a huge niche where "cheap and good enough" is still king, and it was refreshing to see an article on slashdot where that is covered, usually it's some new thing that is the fastest/best and most expensive, and most energy hog as well, and seeing as how I am into alternative energy, I always look at that angle. I don't want an electrical sub station needed to power me and my house and stuff, I think that is beyoind ridiculous and getting into the generational greedy range. that's ME, others can think different, but it is how I think...
This guy at centaur gets it on where his market is, and I'm exactly the sort of person he is thinking of, that's why I wondered if any company had an upgradeable cheap laptop based on his cpu/mobo stuff yet. Like my desktop, when I get ready I'll put a new board and CPU in it, but for now, this is "good enough" for me, just never seen a laptop I can do the same thing with, and I want low power, good battery life, and upgradeable by switching a few cables and slapping in a new board for cheap a few years hence.
Just a-wondering is all, no biggee. If I really wanted or needed a liquid cooled monster like we see all the time here, I guess I would get one, but it would be overkill for my needs, and definetly suck way too much juice and throw too much heat. don't need it really, like I said, don't do games or modeling or whatever. Folks who do got tons of choices, folks who don't got almost squat for choices it appears, and I despise the forced upgrade business solutions we keep seeing.. There's plenty of choices out there in that expensive/faster/ mo powah direction, but very few choices the other way.
This discussion is perhaps more suited to ArsTechnica, as the issue at hand is whether or not x86 is the best instruction set for a low power budget chip maker to pursue. I hope you don't hold that Alpha would be a more suitable instruction set for that -- I don't even want to think of what packages aren't available for Alpha, let alone ask a vendor for a program ported to my "Alpha-Compatible". Academically speaking, however, I will reply to your PowerPC attacks. Regretfully, all my college textbooks are 300 miles away, and I have not looked through my senior textbooks in 5 years, so my rebuttal cannot cite specific Alpha shortfalls beyond anecdotal recollection.
4 precise detractors against the PPC ommitted, I concede that these are 4 of very many
ReferenceMake no mistake, I make no claims about the Alpha deserving the fate that we all foresaw when DEC made the deal with the Devil. Alpha had its share of problems (remember the quick race to 500MHz, then the hard stop for a long time while they straightened out their unbuffered cross chip clock signal?). The RISC/CISC debate ended long ago when Intel effectively merged them. Since then, the two different schools have borrowed from each other so much that we expect chips to have some cruft to reflect their original intents. For this reason, we'll see all Itanium derivatives reflecting that they were made for pre-defined behavior where a compiler can make predictions of the instruction ordering, and likely this will continue to be in intensely predictable math operations. At this time, anyone who insists that modern PPC, x86, Alpha or Sparc chips are exclusively RISC or CISC hasn't taken the time to realize that there is a very blurry line between the RISC and CISC lately. Many have argued that this line is effectively erased and that the definitions have only had meaning in college courses for the past decade.
The Alpha may be your ultimately pure holy processor, but I will continue to find PPC to be a great balance between theory and real world needs and heritage. If nothing else, x86 has taught us that we can have incredibly high performance architectures based on 1970s vintage processors like the 4004.