mark2222
mark2222
97 / 4
24th Mar 2017
14th Jul 2018
Absurdly small and fast subframe multiplication for ALUs/GPUs using an entirely new algorithm. Now with a flashy demo. Use freely.
multiply calculator digital subframe 60hz electronic electronics multiplication multiplier

Comments

  • danieldan0
    danieldan0
    25th Mar 2017
    What if there was simple decimal input?
  • danieldan0
    danieldan0
    25th Mar 2017
    Sometimes SWCH in display is blinking. Like in old displays...
  • danieldan0
    danieldan0
    25th Mar 2017
    hmmmm..... why FILT ctype is signed integer? why FILT doesn't use all 32 bits?
  • mark2222
    mark2222
    25th Mar 2017
    @Schmolendevice As for the colour code, I suppose the best would be to make a Lua script that automatically assigns deco colour, but I have better things to do. It would be very cumbersome for me to adopt a colour code during development itself as the design keeps changing until it finishes, and by then I wouldn't need a colour code any more. I doubt a colour code would really help others to understand it either...
  • mark2222
    mark2222
    25th Mar 2017
    @Schmolendevice No, you can't extract an adder out of this. What it does is to convert an addition of 3 numbers into an addition of 2 numbers in O(1) time (the 2 numbers being A^B^C and A&B | B&C | C&A). This technique is actually used in real-life multiplication circuits. My mod only helps by displaying stacked particles, so you can tell if there's a DTEC underneath an ARAY.
  • Schmolendevice
    Schmolendevice
    25th Mar 2017
    I am also wondering if you might be interested in adopting a colour code. I personally find that it makes subframe assemblies and layering use much easier to discern. I might send you a .txt of the scheme I am currently using. I personally couldn't do without it as I would feel encumbered by having to hover my mouse over each pixel or have to memorize what was under a particular ARAY. I don't know if your mod covers this in some way.
  • Schmolendevice
    Schmolendevice
    25th Mar 2017
    I see you have done quite well to forward "subframe education" to the community. Meanwhile, my highly outdated Word doc languishes in my USB. :( SCHM Corps. has lost its hold on the business as it has moved its interests temporarily towards machining. Someday I'll get to seeing how you implemented this highly compact addition system. Is it akin to achieving an addition and carry propagation with one line of FILT operations? Could you extract a single, high capacity adder from this?
  • munche
    munche
    24th Mar 2017
    Holy Mary this is the coolest thing I've ever seen on tpt
  • QuanTech
    QuanTech
    24th Mar 2017
    @handicraftsman lol too used to the irc "/me"
  • danieldan0
    danieldan0
    24th Mar 2017
    awesome! +1