Slashdot Mirror
National Semiconductor unveils their PC-on-a-chip
KevinRemhof writes "National Semiconductor unveiled their Geode family of chips. The SC1400 chip has video and PC functions built in. The memory and other features require separate chips. The target audience is set-top boxes. Expect to see the first ones by next summer. This is a bold move shortly after selling off Cyrix to Via Technologies. " As other articles point out, they are trying to save themselves by moving into a less-competitive area of the market.
Already there. Try ftp.kernel.org.
Seriously, it's just an enhanced MediaGX chip( (read: x86 clone). There might not be a driver for the MPEG decoder or the TV stuff yet, but the rest should work like any other Intel/AMD/Cyrix/etc chip.
Anyone else notice the date on the ZDnet article that was linked as 'other articles'? Look close and check it out:
;-)
National Semiconductor unveils 'PC on a Chip'
April 6, 1998 9:20 AM PDT
Interesting.
Topher
Space versus Time.
Optimization versus Portability.
Integrated chips:
1. Take more time to develop and make.
2. Are suited specifically to the task at hand.
3. Are not easily upgradeable.
4. Are not as powerful as they could be due to the limits imposed by small size and close proximity.
Distributed solutions (within the same chipset OR clustering solutions)
1. Take less time to make.
2. Are more flexible.
3. Are less optimized.
4. Have communications overhead between components. (Backpropagation? Crosspropagation? Whuzzat?)
5. Generally are more powerful.
6. Take up more space.
Trends have moved between integrating (wow, less overhead than those wacky multi-piece solutions!) and multi-piece solutions (wow, more powerful than that weak and non-upgradeable integrated solutions!) So the fanfare here won't last long I promise.
Although a beowulf of these things would have the best of both worlds... right?
Three Step Plan:
1. Take over the world.
2. Get a lot of cookies.
3. Eat the cookies.
I'm all for technology, but I'm buggered if I'm going to use a PC on a chip. The built-in monitor -- even if it's built into the heat sink -- can't possibly have a resolution greater than about 30x30. That's not even enough to play tetris.
I have been brutally exposed to the "real world" recently (I like using quotation "marks" arbitrarily), and I doubt the average user will ever own two desktop systems. Aside from costs from moniters and other nonsharable peripherals, the average user can't set up a LAN, unless someone, and I'm thinking of a hypothetical God here, could make Plug 'n' Pray live up to its expectations. As for your wired house, I think that when that sort of thing becomes affordable, it will be on a USB-like I/O port. I just pray that we don't end up with proprietary toast protocols, and suchlike.
As for VCR's, the most I am willing to grant them, excepting Stevie Wonder, is that they might be marginally more bright than hamster.
Microsoft's traditional area of strength is software, not hardware (whether this is through programming skill, marketing savvy or hairy men named Guido is irrelevant for this particular point). AT&T's traditional strength is voice communications, not digital content (and their recent purchase of TCI really hasn't added much to this).
While Microsoft/AT&T may be in a situation to sell desktop boxes, someone has to MAKE them. National Semi will be in a position to sell TO the Microsoft/AT&T partnership. National Semi isn't competing with Microsoft/AT&T, because the product in question is a chipset, not a content-delivery network. And since the Geode is based on the MediaGX core (which is an x86 chip), porting WinCE to the Geode will be a snap. I'd bet Microsoft LIKES this.
It's just another platform. Sure, it will run WinCE shortly. And just as sure, someone's going to get a flavor of Linux running on it. The only exciting thing about the Geode is the fact that it's single-chip, meaning that the barrier to entry into 'information appliances' design just got a lot lower.
It is now within the realm of possibility that a talented hardware geek, operating not as a Big Expensive Company but as a hobbyist, could create a Palm-like device that runs x86/PC software with a bare minimum of porting.
Now, THAT'S interesting.