/* Calculate A^2 where A is an 8-bit unsigned variable.
 * The result is placed into 16-bit variable C. 
 * The 24-bit result is saved using little endian byte ordering.
 * C = A^2           
 */

 .INCLUDE <m328pdef.inc> 

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

.CSEG

A_Squared:
    lds  r26,A    ; load
	mul  r26,r26
	sts  C,r0     ; store least significant byte (little end)
	sts  C+1,r1   ; store most  significant byte (big end)

	rjmp A_Squared