The Propeller Modular Computer

2»

Comments

  • So, curious, the I/O pins on the P1 are logic gated together between cogs to determine the final output. Is there any real speed difference between the pins going through more or less gates? If so, which pins would be optimal to use between props?
    That's not an explosion! That's an unscheduled rapid disassembly!

    Looking for a way to have a silicon chip made.
  • There has been said to be some difference, but I personally haven't run into any issues, even with 20 MHz SPI. Some couple nanoseconds (a single CPU cycle @ 80Mhz is 12.5 ns!)

    I think(!) that pins 0-15 are closest to cog 0 and pins 16-32 are closest to cog 7. Maybe the other way round. I'm sure there's a thread on here about it, but I can't find it right now.
  • Smaller opcodes for small constants versus referencing bigger values via "fake constants" in memory may be a thing there too. Code addressing lower pin numbers may be slightly faster.

    Perhaps this has more impact than the distance from cog to pin...
    ◁ propeller-wiki ▷ ◁ FastSpin ▷ ◁ DK-E ▷ ◁ :-D ▷ ◁ Stay OmmmmmmPtimistic! ▷ ◁ No Source – No Go! ▷ ◁ Help Spin at RosettaCode.org ▷ ◁ Why Asimov's Laws of Robotics Don't Work ▷ ◁ DNA is a four letter word. ▷
  • @yeti
    That could make a difference in Spin only. PASM timing is the same regardless of whether the source is immediate.

    However, pins 0-7 have the advantage of not needing to be shifted down to be WRBYTE'd...
  • Thank you! I will have another look at my pin assignments(finally just made a .txt file to keep track of them all) and set up the data lines.
    That's not an explosion! That's an unscheduled rapid disassembly!

    Looking for a way to have a silicon chip made.
Sign In or Register to comment.