How can I optimize this image copy function for the embedded system

The function below reads the image on the page using read_page (pageIter, pageArr, PAGESIZE) and outputs the data to the DOUT and CCLK pins.

I was told that this is inefficient, but I can’t find a way to do it faster. This is basically a pipe running on a 64-pin uProcessor, between two memory spaces. One holds the image, and the other receives the image.

I used the register keyword, removed the indexing of the array and replaced it with arithemetic, but it should be faster.

Thank!

/*
Port C Pin Out
*/
#define     BIT0        0x01    // CCLK
#define     BIT1        0x02    // CS_B
#define     BIT2        0x04    // INIT_B
#define     BIT3        0x08    // PROG_B
#define     BIT4        0x10    // RDRW_B
#define     BIT5        0x20    // BUSY_OUT
#define     BIT6        0x40    // DONE
#define     BIT7        0x80    // DOUT (DIN)

/*
PAGE
*/

#define     PAGESIZE    1024    // Example

void copyImage(ulong startAddress, ulong endAddress)
  {
  ulong pageIter;
  uchar *eByte, *byteIter, pageArr[PAGESIZE];
  register uchar bitIter, portCvar;
  portCvar = PORTC;
  /* Loops through pages in an image using ulong type*/
  for(pageIter = startAddress ;  pageIter <= endAddress ; pageIter += PAGESIZE)
    {
    read_page(pageIter, pageArr, PAGESIZE);
    eByte = pageArr+PAGESIZE;
    /* Loops through bytes in a page using pointer to uchar (pointer to a byte)*/
    for(byteIter = pageArr; byteIter <= eByte; byteIter++)
      {
      /* Loops through bits in byte and writes to PORTC - DIN ANC CCLK  */
      for(bitIter = 0x01; bitIter != 0x00; bitIter = bitIter << 1)
        {
        PORTC = portCvar | BIT0;
        (bitIter & *byteIter) ? (PORTC = portCvar & ~BIT7) : (PORTC = portCvar | BIT7);
        PORTC = portCvar & ~BIT0;
        }
      }
    }
  }