[J-core] Pondering j-core kickstarter ideas.
rob at landley.net
Sun Apr 24 14:50:09 EDT 2016
So way back when (our linuxcon japan presentation) we worked out that if
you're adding a j2 processor to an existing device at ~45 nanometers,
it's something like an extra 3 cents of silicon real estate per chip,
and would run around 450 mhz. But that assumes you're _already_ making a
chip with a reasonably current process. And it also sort of assumes
you're using a "system in ROM/NOR-flash plus 256k of SRAM" style tricks
like the ones described in this presentation at last year's ELC:
More recently we worked out that if you wanted to run your own batch of
chips through a much older/cheaper 150 nanometer process (vintage
year-2000 technology according to the table at
https://en.wikipedia.org/wiki/Die_shrink#Half-shrink) at a fab like
TSMC, your kickstarter would need to raise around $60k so that (after
Kickstarter's cut) you'd have enough to order 6 wafers off ebay, have
the fab make a mask, burn the wafers, test the chips, dice the wafers,
package the good chips, and mail them to you, and with expected yields
the result would be around 36,000 chips running around 250 mhz.
This means you can make SOC's for a little under $2/chip, but what we
DIDN'T work out is what you'd do with those next.
This is a tiny little chip (a couple milimeters on each side), which you
could stick on the end of a USB or Ethernet connector, anything that
provides both data and power. The question is, what would it take to
wire the pins on the thing to the pins on say an ethernet connector,
properly buffered so that passing insects don't fry your circuits? And
what other stuff do you need to add (similarly tiny DRAM chips that our
DRAM controller can talk to, etc).
What would it take to make an actual, minimal hobbyist _device_?
More information about the J-core