Additional device for Espruino to support 8 pins in parallel (for discussion)

I tested with latest direct_io branch, see my code
First checked speed, which is really fast, came down to 18msec/scan :-)
Up to this everything was fine

var led;
connect2 = function(R1,R2,B1,B2,G1,G2,A,B,C,D,Latch,Clock,Enable) {
  var sfnc = shiftOut.bind(null,[R1,G1,B1,R2,G2,B2],{clk:Clock});
  var dfnc = digitalWrite.bind(null,[Enable,Latch,Latch,D,C,B,A,Enable]);

  var en = Enable;
  var g = Graphics.createArrayBuffer(64,32,4);
  var buf = g.buffer;
  var ledBuf = new Uint8Array(64 * 32 / 2);//converted graphics.buffer to data for LED
  var arr = [];
  g.prep = function() {
    var bufpnt1,bufpnt2,ledpnt;
    bufpnt1 = 0; bufpnt2 = 512; ledpnt = 0;
    var pane = false,i,j;
    for(i = 0; i < 16; i++){
      for(j = 0; j < 64;j +=2){
        ledBuf[ledpnt] = (buf[bufpnt2] & 7) + ((buf[bufpnt1] & 7)<<3);
        ledpnt++;
        ledBuf[ledpnt] = ((buf[bufpnt2] & 0xf0) >>4) + ((buf[bufpnt1] & 0xf0)>>1);
        ledpnt++;
        bufpnt1++;
        bufpnt2++;
      }
    }
    arr = [];
    for(var y=0; y < 16;y++){
      arr.push(new Uint8Array(ledBuf.buffer,y*64,64));
      arr.push({callback:dfnc.bind(null,33|y<<1)});
    }
  };
  g.scan = function() {
    en.reset();
    sfnc(arr);
    en.set();
  };
  g.setBgColor(1);
  g.clear();
  g.setColor(2);
  g.fillRect(5,12,50,25);
  g.setColor(4);
  g.fillRect(10,14,40,20);
  g.fillRect(10,0,40,0);
  return g;
};
function tst(){
  led = connect2(D2,D16,D4,D17,D15,D27, D5,D18,D19,D21, D26,D22,D25);
  if(led.prep) led.prep();
  var t=getTime();
  led.scan();
  print((getTime()-t) * 1000);
}

Next tried to work with graphics and whatever I did, panel displays something different. :-(
During testing I added some printf's here and there
First confusing was how often jswrap_io_shiftOutCallbackFast was called. My expectation was 1024, but the counter I added returns 8704
Counter was added like this

int xx = 0;
void jswrap_io_shiftOutCallbackFast(int val, void *data) {
xx++;
  jswrap_io_shiftOutData *d = (jswrap_io_shiftOutData*)data;
  int n, i;
  for (i=0;i<d->repeat;i++) {
.....
void jswrap_io_shiftOut(JsVar *pins, JsVar *options, JsVar *data) {
xx = 0;
  jswrap_io_shiftOutData d;
  d.cnt = 0;
  d.clk = PIN_UNDEFINED;
.......
  // Now run through the data, pushing it out
  jsvIterateCallback(data, allFast ? jswrap_io_shiftOutCallbackFast : jswrap_io_shiftOutCallback, &d);
printf("xx:%d\n",xx);
}

Checking jsvIterateCallback was next step, some more printf like this in
BTW, this is the short version of a long story, ....

  // Handle the data being an array buffer
  else if (jsvIsArrayBuffer(data)) {
jsWarn("ArrayBuffer:%j\n",data);
    JsvArrayBufferIterator it;
    jsvArrayBufferIteratorNew(&it, data, 0);
jsWarn("byteLength:%d\n",it.byteLength);
    if (JSV_ARRAYBUFFER_GET_SIZE(it.type) == 1 && !JSV_ARRAYBUFFER_IS_SIGNED(it.type)) {
      JsvStringIterator *sit = &it.it;

See log, Sum of all byteLength gives exactly 8704, which is the number how often callbackFast is called.
Here we reach the point where the story is beyond my knowledge. Hope you can help.

tst()
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 36, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:64
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:128
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:192
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:256
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:320
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:384
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:448
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:512
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:576
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:640
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:704
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:768
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:832
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:896
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 17, 17, 17, 17, 17, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:960
WARNING: ArrayBuffer:new Uint8Array([9, 9, 9, 9, 9, 17, 17, 17, 17, 17, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9])
WARNING: byteLength:1024
xx:8704