Messages in this thread | | | Date | Sun, 13 Feb 2000 15:45:22 +0100 | From | "J.D. Bakker" <> | Subject | Re: Scheduled Transfer Protocol on Linux |
| |
>I believe it's possible, but I think Larry's estimates of 50% extra cost >($200 -> $300) are off the wall. The Itsy shows you can make Linux boxes >small enough, but the pricetag (several thousand $) also shows that it's >economically impractical.
Excuse me ?
Where does it say that an Itsy costs several thousand $ ? The LART (see .sig) is very similar to the Itsy, and its prototypes didn't cost more than US$600 each. Even in small volume (qty100) this drops down to $250. And that's for a machine that's heavily overqualified to do the tasks that Larry was talking about.
My estimate is that adding a minimal StrongARM+100BT to a disk drive adds $40-$50 maximum to the BOM cost at volumes >10k; less if you go for higher quantities and stuff an SA-1 (or other fast core) and integrated 100[0]BT into an ASIC.
JDB. [who would be surprised if the Ethernet transformer wouldn't be the dominating factor in the PCB area calculation]
-- LART. 250 MIPS under one Watt. http://www-ict.its.tudelft.nl/~erik/open-source/LART/
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |