/* Calculate the factorial of the number held in variable A.
 * The number in variable A must be greater than 0 and less than or 
 * equal to 8! = 40,320
 * Store factorial of A into 16 bit variable C. Byte ordering is little endian.
 * C = A!
 * Tip: Copy and paste subroutine muls16x8_24 into your assembly file.
 */

.INCLUDE <m328pdef.inc> 

.DSEG
A:     .BYTE 1
C:     .BYTE 2

.CSEG

Fact1_8:
	lds  r22, A        ; calculate r26!
	clr  r25
	clr  r24
	inc  r24           ; r25:r24 = 0x0001
fact1_8a:
    rcall muls16x8_24  ; r4:r3:r2 = r25:r24 x r26
    movw  r25:r24, r3:r2

    dec  r22
	brne fact1_8a
	sts  C, r0    ; least significant byte (little end)
	sts  C+1, r1  ; most  significant byte (big end)
	rjmp Fact1_8

/* Multiply a 16-bit unsigned number in the r25:r24 register pair by 
 * an 8-bit number in r22. Return the answer in r4:r3:r2
 */ 
muls16x8_24:
    push r15         ; save contents of registers modified by this subroutine
	in   r15, SREG
    push r24
	push r1
	push r0

    clr  r4
    mul  r24,r22     ; multiply LSB
	movw r3:r2,r1:r0 ; copy result to result register
	mul  r25,r22     ; multiply MSB
	add  r3,r0
    adc  r4,r1

	pop  r0
	pop  r1
	pop  r24
	out  SREG, r15
	pop  r15
	ret