diff --git a/modules/arm_neon/amplify.S b/modules/arm_neon/amplify.S
index 9e655afe16..59c945445b 100644
--- a/modules/arm_neon/amplify.S
+++ b/modules/arm_neon/amplify.S
@@ -21,7 +21,6 @@
 #include "asm.S"
 
 	.syntax	unified
-	.arm
 #if HAVE_AS_FPU_DIRECTIVE
 	.fpu	neon
 #endif
@@ -33,6 +32,7 @@
 	.align 2
 function amplify_float_arm_neon
 	cmp		SIZE,	#0
+	it		eq
 	bxeq		lr
 #ifdef __ARM_PCS
 	vmov		s0,	r3	@ softfp
diff --git a/modules/arm_neon/deinterleave_chroma.S b/modules/arm_neon/deinterleave_chroma.S
index 9cd01c7aed..7c0723e2f6 100644
--- a/modules/arm_neon/deinterleave_chroma.S
+++ b/modules/arm_neon/deinterleave_chroma.S
@@ -52,6 +52,7 @@ function deinterleave_chroma_neon
 	sub		IPAD,	IPITCH,	WIDTH, lsl #1
 	sub		OPAD,	OPITCH,	WIDTH
 1:
+	ite		gt
 	movsgt		COUNT,	WIDTH
 	pople		{r4-r6,pc}
 2:
diff --git a/modules/arm_neon/i420_rgb.S b/modules/arm_neon/i420_rgb.S
index 54fb38746e..6624c4e604 100644
--- a/modules/arm_neon/i420_rgb.S
+++ b/modules/arm_neon/i420_rgb.S
@@ -95,6 +95,7 @@ function i420_rgb_neon
 	/* round the width to be a multiple of 16 */
 	ands		OPAD, WIDTH, #15
 	sub			WIDTH, WIDTH, OPAD
+	it		ne
 	addne		WIDTH, WIDTH, #16
 
 	/* init constants (scale value by 64) */
@@ -115,10 +116,12 @@ function i420_rgb_neon
 	sub			YPAD,	YPITCH,	WIDTH
 
 loop_row:
+	it	gt
 	movsgt	COUNT,	WIDTH
 	add		O2,	O1,	OPITCH
 	add		Y2,	Y1,	YPITCH
 	/* exit if all rows have been processed */
+	itt	le
 	vpople	{q4-q7}
 	pople	{r4-r8,r10-r11,pc}
 
diff --git a/modules/arm_neon/i420_rv16.S b/modules/arm_neon/i420_rv16.S
index 15d1e7b7bd..a3bbae2ed1 100644
--- a/modules/arm_neon/i420_rv16.S
+++ b/modules/arm_neon/i420_rv16.S
@@ -98,6 +98,7 @@ function i420_rv16_neon
 	/* round the width to be a multiple of 16 */
 	ands		OPAD, WIDTH, #15
 	sub			WIDTH, WIDTH, OPAD
+	it		ne
 	addne		WIDTH, WIDTH, #16
 
 	/* init constants (scale value by 64) */
@@ -117,10 +118,12 @@ function i420_rv16_neon
 	sub			YPAD,	YPITCH,	WIDTH
 
 loop_row:
+	it	gt
 	movsgt	COUNT,	WIDTH
 	add		O2,	O1,	OPITCH
 	add		Y2,	Y1,	YPITCH
 	/* exit if all rows have been processed */
+	itt	le
 	vpople	{q4-q7}
 	pople	{r4-r8,r10-r11,pc}
 
diff --git a/modules/arm_neon/i420_yuyv.S b/modules/arm_neon/i420_yuyv.S
index 29668e438e..22355e0b61 100644
--- a/modules/arm_neon/i420_yuyv.S
+++ b/modules/arm_neon/i420_yuyv.S
@@ -49,9 +49,11 @@ function i420_yuyv_neon
 	sub		OPAD,	OPITCH,	WIDTH,	lsl #1
 	sub		YPAD,	YPITCH,	WIDTH
 1:
+	it		gt
 	movsgt		COUNT,	WIDTH
 	add		O2,	O1,	OPITCH
 	add		Y2,	Y1,	YPITCH
+	it		le
 	pople		{r4-r8,r10-r11,pc}
 2:
 	pld		[U, #64]
@@ -86,9 +88,11 @@ function i420_uyvy_neon
 	sub		OPAD,	OPITCH,	WIDTH,	lsl #1
 	sub		YPAD,	YPITCH,	WIDTH
 1:
+	it		gt
 	movsgt		COUNT,	WIDTH
 	add		O2,	O1,	OPITCH
 	add		Y2,	Y1,	YPITCH
+	it		le
 	pople		{r4-r8,r10-r11,pc}
 2:
 	pld		[U, #64]
diff --git a/modules/arm_neon/i422_yuyv.S b/modules/arm_neon/i422_yuyv.S
index 9119839ea5..9a5b8fc4b8 100644
--- a/modules/arm_neon/i422_yuyv.S
+++ b/modules/arm_neon/i422_yuyv.S
@@ -45,6 +45,7 @@ function i422_yuyv_neon
 	sub		OPAD,	OPAD,	WIDTH,	lsl #1
 	sub		YPAD,	YPAD,	WIDTH
 1:
+	ite		gt
 	movsgt		COUNT,	WIDTH
 	pople		{r4-r6,pc}
 2:
@@ -76,6 +77,7 @@ function i422_uyvy_neon
 	sub		OPAD,	OPAD,	WIDTH,	lsl #1
 	sub		YPAD,	YPAD,	WIDTH
 1:
+	ite		gt
 	movsgt		COUNT,	WIDTH
 	pople		{r4-r6,pc}
 2:
diff --git a/modules/arm_neon/nv12_rgb.S b/modules/arm_neon/nv12_rgb.S
index 1bb924fc2b..ceef76cbef 100644
--- a/modules/arm_neon/nv12_rgb.S
+++ b/modules/arm_neon/nv12_rgb.S
@@ -91,6 +91,7 @@ function nv12_rgb_neon
 	/* round the width to be a multiple of 16 */
 	ands		OPAD, WIDTH, #15
 	sub			WIDTH, WIDTH, OPAD
+	it		ne
 	addne		WIDTH, WIDTH, #16
 
 	/* init constants (scale value by 64) */
@@ -111,10 +112,12 @@ function nv12_rgb_neon
 	sub			YPAD,	YPITCH,	WIDTH
 
 loop_row:
+	it	gt
 	movsgt	COUNT,	WIDTH
 	add		O2,	O1,	OPITCH
 	add		Y2,	Y1,	YPITCH
 	/* exit if all rows have been processed */
+	itt	le
 	vpople	{q4-q7}
 	pople	{r4-r8,r10-r11,pc}
 
diff --git a/modules/arm_neon/nv21_rgb.S b/modules/arm_neon/nv21_rgb.S
index f775b5a6ac..0d75b9f7f9 100644
--- a/modules/arm_neon/nv21_rgb.S
+++ b/modules/arm_neon/nv21_rgb.S
@@ -91,6 +91,7 @@ function nv21_rgb_neon
 	/* round the width to be a multiple of 16 */
 	ands		OPAD, WIDTH, #15
 	sub			WIDTH, WIDTH, OPAD
+	it		ne
 	addne		WIDTH, WIDTH, #16
 
 	/* init constants (scale value by 64) */
@@ -111,10 +112,12 @@ function nv21_rgb_neon
 	sub			YPAD,	YPITCH,	WIDTH
 
 loop_row:
+	it	gt
 	movsgt	COUNT,	WIDTH
 	add		O2,	O1,	OPITCH
 	add		Y2,	Y1,	YPITCH
 	/* exit if all rows have been processed */
+	itt	le
 	vpople	{q4-q7}
 	pople	{r4-r8,r10-r11,pc}
 
diff --git a/modules/arm_neon/yuyv_i422.S b/modules/arm_neon/yuyv_i422.S
index 637effe9bc..62d826c838 100644
--- a/modules/arm_neon/yuyv_i422.S
+++ b/modules/arm_neon/yuyv_i422.S
@@ -45,6 +45,7 @@ function yuyv_i422_neon
 	sub		YPAD,	YPAD,	WIDTH
 	sub		IPAD,	IPAD,	WIDTH,	lsl #1
 1:
+	ite		gt
 	movsgt		COUNT,	WIDTH
 	pople		{r4-r6,pc}
 2:
@@ -74,6 +75,7 @@ function uyvy_i422_neon
 	sub		YPAD,	YPAD,	WIDTH
 	sub		IPAD,	IPAD,	WIDTH,	lsl #1
 1:
+	ite		gt
 	movsgt		COUNT,	WIDTH
 	pople		{r4-r6,pc}
 2:
diff --git a/modules/video_filter/deinterlace/merge_arm.S b/modules/video_filter/deinterlace/merge_arm.S
index d3f32c5ca6..4b211aeb31 100644
--- a/modules/video_filter/deinterlace/merge_arm.S
+++ b/modules/video_filter/deinterlace/merge_arm.S
@@ -21,7 +21,6 @@
 #include "../arm_neon/asm.S"
 
 	.syntax	unified
-	.arm
 #if HAVE_AS_ARCH_DIRECTIVE
 	.arch	armv6
 #endif
@@ -67,6 +66,7 @@ function merge8_arm_neon
 	vst1.u8		{q0-q1},	[DEST,:128]!
 3:
 	cmp		SIZE,	#16
+	it		lo
 	bxlo		lr
 	vld1.u8		{q0},		[SRC1,:128]!
 	sub		SIZE,	SIZE,	#16
@@ -106,6 +106,7 @@ function merge16_arm_neon
 	vst1.u16	{q0-q1},	[DEST,:128]!
 3:
 	cmp		SIZE,	#16
+	it		lo
 	bxlo		lr
 	vld1.u16	{q0},		[SRC1,:128]!
 	sub		SIZE,	SIZE,	#16
@@ -131,6 +132,7 @@ function merge8_armv6
 	stm		DEST!,	{r4-r5}
 	uhadd8		r7,	r7,	lr
 	stm		DEST!,	{r6-r7}
+	it		eq
 	popeq		{r4-r9,pc}
 	b		1b
 
@@ -151,5 +153,6 @@ function merge16_armv6
 	stm		DEST!,	{r4-r5}
 	uhadd16		r7,	r7,	lr
 	stm		DEST!,	{r6-r7}
+	it		eq
 	popeq		{r4-r9,pc}
 	b		1b