Slashdot Mirror

← Back to Stories (view on slashdot.org)

Stretch Announces Chip That Rewires Itself On The Fly

Posted by simoniker on from the self-reconfiguring-articles-next dept.

tigre writes "CNET News reports on a chip startup call Stretch which produces the S5000, a RISC processor with electronically programmable hardware so that it can add to its instruction set as it deems necessary. Thus it can re-configure itself to behave like a DSP, or a (digital) ASIC, and perform the equivalent of hundreds of instructions in one cycle. Great way to bridge the gap between general-purpose computing and ASICs."

6 of 311 comments (clear)

  1. That reminds me of... by ajiva · · Score: 4, Interesting

    I remember a project where hardware engineers setup a cpu to modify itself until it learned to do a task by itself. It got to the point where the hardware was doing the right thing, but not because the hardware was reconfigured properly, but because the software was using minute naunances in the electricity flowing through to get the job done. Even the hardware designers had no idea how it could possible be working

    1. Re:That reminds me of... by itp · · Score: 4, Interesting

      It was an FPGA, and it wasn't the CPU modifying itself, it was a genetic algorithm designing a circuit that would perform a specific task (differentiate between two different ranges of input signals, IIRC).

      The interesting result was that the circuit designed by the GA didn't use conventional structures, but instead, according to traditional circuit design theory, should not have functioned at all -- dead loops, etc. The behavior and result was tied to the physical FPGA being used to test and give feedback to the GA -- the minute nuances, as you referred to them -- and was not portable to even another instance of the exact same FPGA.

    2. Re:That reminds me of... by bigbigbison · · Score: 4, Interesting

      I remember reading about this in either Popular Science of Discover magazine. I seem to remember that the head researcher took the chips to another building or room to show them off and they didn't work. Then took them back to the room they came from and they worked again. They finally determined that the rooms had slightly different temperature and the chips were so specific to that environment thta changing the temperature even a tiny bit stopped them from working.
      Crazy stuff.

      --
      http://www.popularculturegaming.com -- my blog about the culture of videogame players
  2. Re:virus hitting the hardware by NanoGator · · Score: 4, Interesting

    "Can you imagine the virus you could write if you could change the instruction set of the cpu?"

    Forgive my ignorance, but why would this be any different than the virus you can write with the general purpose CPUs we have today? You could make the machine unreliable, but that wouldn't make for an effective virus distributing machine.

    --
    "Derp de derp."
  3. Re:New application-speed records to be set... by Stripe7 · · Score: 4, Interesting

    This looks interesting, at this generation it looks to be dedicated applications. You code for your particular application and use their compiler which restructures the CPU to optimize for that application. What it does not say is if the hardware changes are read/write. If you release a maintenance patch to your application, do you have to swap in a new CPU for optimal performance? If the area is read/write just how many times can you change the CPU instruction set? Can you change the CPU instruction set with something else other than using their compiler? That is using a microcode release that rewrites the CPU. I would not want to load a compiler onto every one of my products.

  4. Re:Insightful?! by CedgeS · · Score: 4, Interesting
    Easy - Say, the extra instructions are supposed perform a matrix convolution. Call extra instruction 1 with some random matrix. If it doesn't calculate the same thing as a slow version run in the regular RISC part you know extra instruction 1 has in some way failed and needs to be reprogrammed. Your virus software and OS etc should never have special instructions and are always run in the regular RISC part.

    I highly doubt anyone is planning on making PCs with these. They are designed for being a processor in something like a data logging / control system, surveillance video compression, etc. Your system will probably have no need for virus detection any more specific than other more general regression and test suites it will need during operation.