Kinda Intersting

;;;;;;;;;;;;;;Average One Variable;;;;;;;;;;;;;;
;mov r0, #0
;vsub.f32 s0, s0, s0
;ldr r1, ptArrayLinearX
;ldr r2, ptArrayLinearY
;ldr r3, dimArrayLinear
;No caso de querermos fazer a media de x: ->
		;mov r4, r1
;No caso de querermos fazer a media de y: ->
		;mov r4, r2
sumAvg1_for:
		cmp r0, r3							;if we reach the array dimension ->
		beq sumAvg1_for_end					;jump to sumAvg1_for_end
		vldr s1, [r4]						;load byte and update address.
		add r4, #4							;add 4 to r4
		vadd.f32 s0, s0, s1					;s0 = s0 + s1
		add r0, #1       					;add 1 to r0
		b sumAvg1_for						;branch sumAvg1_for
sumAvg1_for_end:
		vmov s3, r3							;s3 = r3
		vcvt.f32.s32 s3, s3					;makes sure it is converted int to float
		vdiv.f32 s0, s0, s3					;s0 = s0/s3
		bx LR								;branch and exchange

;;;;;;;;;;;;;;Average Two Variables;;;;;;;;;;;;;;
sumAvg2_for:
		cmp r0, r3							;if we reach the array dimension ->
		beq sumAvg2_for_end					;jump to sumAvg2_for_end
		vldr s1, [r4]						;load byte and update address
		vldr s2, [r5]						;load byte and update address
		add r4, #4							;add 4 bytes to r4
		add r5, #4							;add 4 bytes to r5
		vmla.f32 s0, s1, s2					;s0 = s0 + (s1 * s2)
		add r0, #1       					;add 1 to r0
		b sumAvg2_for						;branch sumAvg2_for
sumAvg2_for_end:
		vmov s3, r3							;s3 = r3
		vcvt.f32.s32 s3, s3					;makes sure it is converted int to float
		vdiv.f32 s0, s0, s3					;s0 = s0/s3
		bx LR								;branch and exchange

;;;;;;;;;;;;;;Average Three Variables;;;;;;;;;;;;;;
sumAvg3_for:
		cmp r0, r3							;if we reach the array dimension ->
		beq sumAvg3_for_end					;jump to sumAvg3_for_end
		vldr s1, [r4]						;load byte and update address
		vldr s2, [r5]						;load byte and update address
		vldr s3, [r6]						;load byte and update address
		add r4, #4							;add 4 bytes to r4
		add r5, #4							;add 4 bytes to r5
		add r6, #4							;add 4 bytes to r6
		vmul.f32 s4, s1, s2					;s4 = s1 * s2
		vmla.f32 s0, s4, s3					;s0 = s0 + (s4 * s3)
		add r0, #1       					;add 1 to r0
		b sumAvg3_for						;branch sumAvg3_for
sumAvg3_for_end:
		vmov s3, r3							;s3 = r3
		vcvt.f32.s32 s3, s3					;makes sure it is converted int to float
		vdiv.f32 s0, s0, s3					;s0 = s0/s3
		bx LR								;branch and exchange

;;;;;;;;;;;;;;Average Four Variables;;;;;;;;;;;;;;
sumAvg4_for:
		cmp r0, r3							;if we reach the array dimension ->
		beq sumAvg4_for_end					;jump to sumAvg4_for_end
		vldr s1, [r4]						;load byte and update address
		vldr s2, [r5]						;load byte and update address
		vldr s3, [r6]						;load byte and update address
		vldr s4, [r7]						;load byte and update address
		add r4, #4							;add 4 bytes to r4
		add r5, #4							;add 4 bytes to r5
		add r6, #4							;add 4 bytes to r6
		add r7, #4							;add 4 bytes to r7
		vmul.f32 s5, s1, s2					;s5 = s1 * s2
		vmul.f32 s5, s5, s3					;s5 = s5 * s3
		vmla.f32 s0, s5, s4					;s0 = s0 + (s5 * s4)
		add r0, #1       					;add 1 to r0
		b sumAvg4_for						;branch sumAvg4_for
sumAvg4_for_end:
		vmov s3, r3							;s3 = r3
		vcvt.f32.s32 s3, s3					;makes sure it is converted int to float
		vdiv.f32 s0, s0, s3					;s0 = s0/s3
		bx LR								;branch and exchange