6502 multiply

;;
; Multiplies two 8-bit factors to produce a 16-bit product
; in about 153 cycles.
; @param A one factor
; @param Y another factor
; @return high 8 bits in A; low 8 bits in $0000
;         Y and $0001 are trashed; X is untouched
.proc mul8
factor2 = TempVal+1
prodlo = TempVal

  ; Factor 1 is stored in the lower bits of prodlo; the low byte of
  ; the product is stored in the upper bits.
  lsr a  ; prime the carry bit for the loop
  sta prodlo
  sty factor2
  lda #0
  ldy #8
loop:
  ; At the start of the loop, one bit of prodlo has already been
  ; shifted out into the carry.
  bcc noadd
  clc
  adc factor2
noadd:
  ror a
  ror prodlo  ; pull another bit out for the next iteration
  dey         ; inc/dec don't modify carry; only shifts and adds do
  bne loop
  ldy TempVal
  rts
.endproc