djmips

mul1 * mul2 + A/2 -> A:mul1 (mul2 is unchanged)

; inner loop credit Supercat

MUL:
     dec mul2	;5  ; decrement mul2 because we will be adding with carry set for speed (an extra one)
     ror mul1	;5      \
     bcc b1	  ;2/3     \  Best case 8 Worst case 10
     adc mul2	;3       /
b1: ror		    ;2       \

djmips

; DASM assembler

processor  6502

	seg.u   zpage
	ORG $0080


theta   ds 2
x	   ds 2

djmips

// Assume there is a currX and currY global state which is the current x,y position
// Assume that currBuffer points to a valid properly sized buffer in RAM for DMA
//
// Buffer size can be calculated as n * 4 bytes where n is max(xdelta, ydelta) 
// where xdelta and ydelta are the extents of the line to be drawn
//
// xd and yd is the destination point
//
// The output DACs are 12 bit but for speed this outputs in steps of 4 to cut the point generation by 4 times
// Effective resolution is 1024 points in X and Y