vpx_scale: sync from master

Update vpx_scale from current code in master, run style transform, fix
lint warnings.

Change-Id: I47eadeb5b6881d448ea3728537f9b8a5b5aac78e

5 files changed, 142 insertions, 515 deletions

diff --git a/vpx_scale/arm/neon/vp8_vpxyv12_copy_y_neon.asm b/vpx_scale/arm/neon/vp8_vpxyv12_copy_y_neon.asm
new file mode 100644
index 000000000..9189641b1
--- /dev/null
+++ b/vpx_scale/arm/neon/vp8_vpxyv12_copy_y_neon.asm
@@ -0,0 +1,122 @@
+;
+;  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
+;
+;  Use of this source code is governed by a BSD-style license
+;  that can be found in the LICENSE file in the root of the source
+;  tree. An additional intellectual property rights grant can be found
+;  in the file PATENTS.  All contributing project authors may
+;  be found in the AUTHORS file in the root of the source tree.
+;
+
+
+    EXPORT  |vp8_yv12_copy_y_neon|
+
+    ARM
+    REQUIRE8
+    PRESERVE8
+
+    INCLUDE asm_com_offsets.asm
+
+    AREA ||.text||, CODE, READONLY, ALIGN=2
+
+;void vpxyv12_copy_y_neon(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc)
+|vp8_yv12_copy_y_neon| PROC
+    push            {r4 - r11, lr}
+    vpush           {d8-d15}
+
+    ldr             r4, [r0, #yv12_buffer_config_y_height]
+    ldr             r5, [r0, #yv12_buffer_config_y_width]
+    ldr             r6, [r0, #yv12_buffer_config_y_stride]
+    ldr             r7, [r1, #yv12_buffer_config_y_stride]
+    ldr             r2, [r0, #yv12_buffer_config_y_buffer]       ;srcptr1
+    ldr             r3, [r1, #yv12_buffer_config_y_buffer]       ;dstptr1
+
+    ; copy two rows at one time
+    mov             lr, r4, lsr #1
+
+cp_src_to_dst_height_loop1
+    mov             r8, r2
+    mov             r9, r3
+    add             r10, r2, r6
+    add             r11, r3, r7
+    movs            r12, r5, lsr #7
+    ble             extra_copy_needed   ; y_width < 128
+
+cp_src_to_dst_width_loop1
+    vld1.8          {q0, q1}, [r8]!
+    vld1.8          {q8, q9}, [r10]!
+    vld1.8          {q2, q3}, [r8]!
+    vld1.8          {q10, q11}, [r10]!
+    vld1.8          {q4, q5}, [r8]!
+    vld1.8          {q12, q13}, [r10]!
+    vld1.8          {q6, q7}, [r8]!
+    vld1.8          {q14, q15}, [r10]!
+
+    subs            r12, r12, #1
+
+    vst1.8          {q0, q1}, [r9]!
+    vst1.8          {q8, q9}, [r11]!
+    vst1.8          {q2, q3}, [r9]!
+    vst1.8          {q10, q11}, [r11]!
+    vst1.8          {q4, q5}, [r9]!
+    vst1.8          {q12, q13}, [r11]!
+    vst1.8          {q6, q7}, [r9]!
+    vst1.8          {q14, q15}, [r11]!
+
+    bne             cp_src_to_dst_width_loop1
+
+    subs            lr, lr, #1
+    add             r2, r2, r6, lsl #1
+    add             r3, r3, r7, lsl #1
+
+    bne             cp_src_to_dst_height_loop1
+
+extra_copy_needed
+    ands            r10, r5, #0x7f                  ;check to see if extra copy is needed
+    sub             r11, r5, r10
+    ldr             r2, [r0, #yv12_buffer_config_y_buffer]       ;srcptr1
+    ldr             r3, [r1, #yv12_buffer_config_y_buffer]       ;dstptr1
+    bne             extra_cp_src_to_dst_width1
+end_of_cp_src_to_dst1
+
+    vpop            {d8 - d15}
+    pop             {r4-r11, pc}
+
+;=============================
+extra_cp_src_to_dst_width1
+    add             r2, r2, r11
+    add             r3, r3, r11
+    add             r0, r8, r6
+    add             r11, r9, r7
+
+    mov             lr, r4, lsr #1
+extra_cp_src_to_dst_height_loop1
+    mov             r8, r2
+    mov             r9, r3
+    add             r0, r8, r6
+    add             r11, r9, r7
+
+    mov             r12, r10
+
+extra_cp_src_to_dst_width_loop1
+    vld1.8          {q0}, [r8]!
+    vld1.8          {q1}, [r0]!
+
+    subs            r12, r12, #16
+
+    vst1.8          {q0}, [r9]!
+    vst1.8          {q1}, [r11]!
+    bne             extra_cp_src_to_dst_width_loop1
+
+    subs            lr, lr, #1
+
+    add             r2, r2, r6, lsl #1
+    add             r3, r3, r7, lsl #1
+
+    bne             extra_cp_src_to_dst_height_loop1
+
+    b               end_of_cp_src_to_dst1
+
+    ENDP
+
+    END
diff --git a/vpx_scale/arm/neon/vp8_vpxyv12_copyframe_func_neon.asm b/vpx_scale/arm/neon/vp8_vpxyv12_copyframe_func_neon.asm
index e6bb486c8..e55d076d9 100644
--- a/vpx_scale/arm/neon/vp8_vpxyv12_copyframe_func_neon.asm
+++ b/vpx_scale/arm/neon/vp8_vpxyv12_copyframe_func_neon.asm
@@ -18,7 +18,8 @@
 
     AREA ||.text||, CODE, READONLY, ALIGN=2
 
-;void vp8_yv12_copy_frame_func_neon(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
+;void vp8_yv12_copy_frame_func_neon(YV12_BUFFER_CONFIG *src_ybc,
+;                                   YV12_BUFFER_CONFIG *dst_ybc);
 
 |vp8_yv12_copy_frame_func_neon| PROC
     push            {r4 - r11, lr}
@@ -52,7 +53,8 @@ cp_src_to_dst_height_loop
     mov             r9, r3
     add             r10, r2, r6
     add             r11, r3, r7
-    mov             r12, r5, lsr #7
+    movs            r12, r5, lsr #7
+    ble             extra_cp_needed   ; y_width < 128
 
 cp_src_to_dst_width_loop
     vld1.8          {q0, q1}, [r8]!
@@ -83,6 +85,7 @@ cp_src_to_dst_width_loop
 
     bne             cp_src_to_dst_height_loop
 
+extra_cp_needed
     ands            r10, r5, #0x7f                  ;check to see if extra copy is needed
     sub             r11, r5, r10
     ldr             r2, [r0, #yv12_buffer_config_y_buffer]       ;srcptr1
@@ -110,7 +113,8 @@ cp_src_to_dst_height_uv_loop
     mov             r9, r3
     add             r10, r2, r6
     add             r11, r3, r7
-    mov             r12, r5, lsr #6
+    movs            r12, r5, lsr #6
+    ble             extra_uv_cp_needed
 
 cp_src_to_dst_width_uv_loop
     vld1.8          {q0, q1}, [r8]!
@@ -133,6 +137,7 @@ cp_src_to_dst_width_uv_loop
 
     bne             cp_src_to_dst_height_uv_loop
 
+extra_uv_cp_needed
     ands            r10, r5, #0x3f                  ;check to see if extra copy is needed
     sub             r11, r5, r10
     ldr             r2, [sp]        ;srcptr1
diff --git a/vpx_scale/arm/neon/vp8_vpxyv12_copyframeyonly_neon.asm b/vpx_scale/arm/neon/vp8_vpxyv12_copyframeyonly_neon.asm
deleted file mode 100644
index febccc2d8..000000000
--- a/vpx_scale/arm/neon/vp8_vpxyv12_copyframeyonly_neon.asm
+++ /dev/null
@@ -1,500 +0,0 @@
-;
-;  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
-;
-;  Use of this source code is governed by a BSD-style license
-;  that can be found in the LICENSE file in the root of the source
-;  tree. An additional intellectual property rights grant can be found
-;  in the file PATENTS.  All contributing project authors may
-;  be found in the AUTHORS file in the root of the source tree.
-;
-
-
-    EXPORT  |vp8_yv12_copy_frame_yonly_neon|
-    EXPORT  |vp8_yv12_copy_frame_yonly_no_extend_frame_borders_neon|
-
-    ARM
-    REQUIRE8
-    PRESERVE8
-
-    INCLUDE asm_com_offsets.asm
-
-    AREA ||.text||, CODE, READONLY, ALIGN=2
-;void vpxyv12_copy_frame_yonly(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-; Note: this is VP8 function, which has border=32 and 16. Internal y_width and y_height
-; are always multiples of 16.
-
-|vp8_yv12_copy_frame_yonly_neon| PROC
-    push            {r4 - r11, lr}
-    vpush           {d8 - d15}
-
-    ldr             r4, [r0, #yv12_buffer_config_y_height]
-    ldr             r5, [r0, #yv12_buffer_config_y_width]
-    ldr             r6, [r0, #yv12_buffer_config_y_stride]
-    ldr             r7, [r1, #yv12_buffer_config_y_stride]
-    ldr             r2, [r0, #yv12_buffer_config_y_buffer]       ;srcptr1
-    ldr             r3, [r1, #yv12_buffer_config_y_buffer]       ;dstptr1
-
-    ; copy two rows at one time
-    mov             lr, r4, lsr #1
-
-cp_src_to_dst_height_loop
-    mov             r8, r2
-    mov             r9, r3
-    add             r10, r2, r6
-    add             r11, r3, r7
-    mov             r12, r5, lsr #7
-
-cp_src_to_dst_width_loop
-    vld1.8          {q0, q1}, [r8]!
-    vld1.8          {q8, q9}, [r10]!
-    vld1.8          {q2, q3}, [r8]!
-    vld1.8          {q10, q11}, [r10]!
-    vld1.8          {q4, q5}, [r8]!
-    vld1.8          {q12, q13}, [r10]!
-    vld1.8          {q6, q7}, [r8]!
-    vld1.8          {q14, q15}, [r10]!
-
-    subs            r12, r12, #1
-
-    vst1.8          {q0, q1}, [r9]!
-    vst1.8          {q8, q9}, [r11]!
-    vst1.8          {q2, q3}, [r9]!
-    vst1.8          {q10, q11}, [r11]!
-    vst1.8          {q4, q5}, [r9]!
-    vst1.8          {q12, q13}, [r11]!
-    vst1.8          {q6, q7}, [r9]!
-    vst1.8          {q14, q15}, [r11]!
-
-    bne             cp_src_to_dst_width_loop
-
-    subs            lr, lr, #1
-    add             r2, r2, r6, lsl #1
-    add             r3, r3, r7, lsl #1
-
-    bne             cp_src_to_dst_height_loop
-
-    ands            r10, r5, #0x7f                  ;check to see if extra copy is needed
-    sub             r11, r5, r10
-    ldr             r2, [r0, #yv12_buffer_config_y_buffer]       ;srcptr1
-    ldr             r3, [r1, #yv12_buffer_config_y_buffer]       ;dstptr1
-    bne             extra_cp_src_to_dst_width
-end_of_cp_src_to_dst
-
-
-    ;vpxyv12_extend_frame_borders_yonly
-    mov             r0, r1
-    ;Not need to load y_width, since: y_width = y_stride - 2*border
-    ldr             r3, [r0, #yv12_buffer_config_border]
-    ldr             r1, [r0, #yv12_buffer_config_y_buffer]       ;srcptr1
-    ldr             r4, [r0, #yv12_buffer_config_y_height]
-    ldr             lr, [r0, #yv12_buffer_config_y_stride]
-
-    cmp             r3, #16
-    beq             b16_extend_frame_borders
-
-;=======================
-b32_extend_frame_borders
-;border = 32
-;=======================
-;Border copy for Y plane
-;copy the left and right most columns out
-    sub             r5, r1, r3              ;destptr1
-    add             r6, r1, lr
-    sub             r6, r6, r3, lsl #1      ;destptr2
-    sub             r2, r6, #1              ;srcptr2
-
-    ;Do four rows at one time
-    mov             r12, r4, lsr #2
-
-copy_left_right_y
-    vld1.8          {d0[], d1[]}, [r1], lr
-    vld1.8          {d4[], d5[]}, [r2], lr
-    vld1.8          {d8[], d9[]}, [r1], lr
-    vld1.8          {d12[], d13[]}, [r2], lr
-    vld1.8          {d16[], d17[]},  [r1], lr
-    vld1.8          {d20[], d21[]}, [r2], lr
-    vld1.8          {d24[], d25[]}, [r1], lr
-    vld1.8          {d28[], d29[]}, [r2], lr
-
-    vmov            q1, q0
-    vmov            q3, q2
-    vmov            q5, q4
-    vmov            q7, q6
-    vmov            q9, q8
-    vmov            q11, q10
-    vmov            q13, q12
-    vmov            q15, q14
-
-    subs            r12, r12, #1
-
-    vst1.8          {q0, q1}, [r5], lr
-    vst1.8          {q2, q3}, [r6], lr
-    vst1.8          {q4, q5}, [r5], lr
-    vst1.8          {q6, q7}, [r6], lr
-    vst1.8          {q8, q9}, [r5], lr
-    vst1.8          {q10, q11}, [r6], lr
-    vst1.8          {q12, q13}, [r5], lr
-    vst1.8          {q14, q15}, [r6], lr
-
-    bne             copy_left_right_y
-
-;Now copy the top and bottom source lines into each line of the respective borders
-    ldr             r7, [r0, #yv12_buffer_config_y_buffer]       ;srcptr1
-    mul             r8, r3, lr
-
-    mov             r12, lr, lsr #7
-
-    sub             r6, r1, r3              ;destptr2
-    sub             r2, r6, lr              ;srcptr2
-    sub             r1, r7, r3              ;srcptr1
-    sub             r5, r1, r8              ;destptr1
-
-copy_top_bottom_y
-    vld1.8          {q0, q1}, [r1]!
-    vld1.8          {q8, q9}, [r2]!
-    vld1.8          {q2, q3}, [r1]!
-    vld1.8          {q10, q11}, [r2]!
-    vld1.8          {q4, q5}, [r1]!
-    vld1.8          {q12, q13}, [r2]!
-    vld1.8          {q6, q7}, [r1]!
-    vld1.8          {q14, q15}, [r2]!
-
-    mov             r7, r3
-
-top_bottom_32
-    subs            r7, r7, #1
-
-    vst1.8          {q0, q1}, [r5]!
-    vst1.8          {q8, q9}, [r6]!
-    vst1.8          {q2, q3}, [r5]!
-    vst1.8          {q10, q11}, [r6]!
-    vst1.8          {q4, q5}, [r5]!
-    vst1.8          {q12, q13}, [r6]!
-    vst1.8          {q6, q7}, [r5]!
-    vst1.8          {q14, q15}, [r6]!
-
-    add             r5, r5, lr
-    sub             r5, r5, #128
-    add             r6, r6, lr
-    sub             r6, r6, #128
-
-    bne             top_bottom_32
-
-    sub             r5, r1, r8
-    add             r6, r2, lr
-
-    subs            r12, r12, #1
-    bne             copy_top_bottom_y
-
-    mov             r7, lr, lsr #4              ;check to see if extra copy is needed
-    ands            r7, r7, #0x7
-    bne             extra_top_bottom_y
-end_of_border_copy_y
-
-    vpop            {d8 - d15}
-    pop             {r4 - r11, pc}
-
-;=====================
-;extra copy part for Y
-extra_top_bottom_y
-    vld1.8          {q0}, [r1]!
-    vld1.8          {q2}, [r2]!
-
-    mov             r9, r3, lsr #3
-
-extra_top_bottom_32
-    subs            r9, r9, #1
-
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    bne             extra_top_bottom_32
-
-    sub             r5, r1, r8
-    add             r6, r2, lr
-    subs            r7, r7, #1
-    bne             extra_top_bottom_y
-
-    b               end_of_border_copy_y
-
-
-;=======================
-b16_extend_frame_borders
-;border = 16
-;=======================
-;Border copy for Y plane
-;copy the left and right most columns out
-    sub             r5, r1, r3              ;destptr1
-    add             r6, r1, lr
-    sub             r6, r6, r3, lsl #1      ;destptr2
-    sub             r2, r6, #1              ;srcptr2
-
-    ;Do four rows at one time
-    mov             r12, r4, lsr #2
-
-copy_left_right_y_b16
-    vld1.8          {d0[], d1[]}, [r1], lr
-    vld1.8          {d4[], d5[]}, [r2], lr
-    vld1.8          {d8[], d9[]}, [r1], lr
-    vld1.8          {d12[], d13[]}, [r2], lr
-    vld1.8          {d16[], d17[]},  [r1], lr
-    vld1.8          {d20[], d21[]}, [r2], lr
-    vld1.8          {d24[], d25[]}, [r1], lr
-    vld1.8          {d28[], d29[]}, [r2], lr
-
-    subs            r12, r12, #1
-
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q4}, [r5], lr
-    vst1.8          {q6}, [r6], lr
-    vst1.8          {q8}, [r5], lr
-    vst1.8          {q10}, [r6], lr
-    vst1.8          {q12}, [r5], lr
-    vst1.8          {q14}, [r6], lr
-
-    bne             copy_left_right_y_b16
-
-;Now copy the top and bottom source lines into each line of the respective borders
-    ldr             r7, [r0, #yv12_buffer_config_y_buffer]       ;srcptr1
-    mul             r8, r3, lr
-
-    mov             r12, lr, lsr #7
-
-    sub             r6, r1, r3              ;destptr2
-    sub             r2, r6, lr              ;srcptr2
-    sub             r1, r7, r3              ;srcptr1
-    sub             r5, r1, r8              ;destptr1
-
-copy_top_bottom_y_b16
-    vld1.8          {q0, q1}, [r1]!
-    vld1.8          {q8, q9}, [r2]!
-    vld1.8          {q2, q3}, [r1]!
-    vld1.8          {q10, q11}, [r2]!
-    vld1.8          {q4, q5}, [r1]!
-    vld1.8          {q12, q13}, [r2]!
-    vld1.8          {q6, q7}, [r1]!
-    vld1.8          {q14, q15}, [r2]!
-
-    mov             r7, r3
-
-top_bottom_16_b16
-    subs            r7, r7, #1
-
-    vst1.8          {q0, q1}, [r5]!
-    vst1.8          {q8, q9}, [r6]!
-    vst1.8          {q2, q3}, [r5]!
-    vst1.8          {q10, q11}, [r6]!
-    vst1.8          {q4, q5}, [r5]!
-    vst1.8          {q12, q13}, [r6]!
-    vst1.8          {q6, q7}, [r5]!
-    vst1.8          {q14, q15}, [r6]!
-
-    add             r5, r5, lr
-    sub             r5, r5, #128
-    add             r6, r6, lr
-    sub             r6, r6, #128
-
-    bne             top_bottom_16_b16
-
-    sub             r5, r1, r8
-    add             r6, r2, lr
-
-    subs            r12, r12, #1
-    bne             copy_top_bottom_y_b16
-
-    mov             r7, lr, lsr #4              ;check to see if extra copy is needed
-    ands            r7, r7, #0x7
-    bne             extra_top_bottom_y_b16
-end_of_border_copy_y_b16
-
-    vpop            {d8 - d15}
-    pop             {r4 - r11, pc}
-
-;=====================
-;extra copy part for Y
-extra_top_bottom_y_b16
-    vld1.8          {q0}, [r1]!
-    vld1.8          {q2}, [r2]!
-
-    mov             r9, r3, lsr #3
-
-extra_top_bottom_16_b16
-    subs            r9, r9, #1
-
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    vst1.8          {q0}, [r5], lr
-    vst1.8          {q2}, [r6], lr
-    bne             extra_top_bottom_16_b16
-
-    sub             r5, r1, r8
-    add             r6, r2, lr
-    subs            r7, r7, #1
-    bne             extra_top_bottom_y_b16
-
-    b               end_of_border_copy_y_b16
-
-;=============================
-extra_cp_src_to_dst_width
-    add             r2, r2, r11
-    add             r3, r3, r11
-    add             r0, r8, r6
-    add             r11, r9, r7
-
-    mov             lr, r4, lsr #1
-extra_cp_src_to_dst_height_loop
-    mov             r8, r2
-    mov             r9, r3
-    add             r0, r8, r6
-    add             r11, r9, r7
-
-    mov             r12, r10
-
-extra_cp_src_to_dst_width_loop
-    vld1.8          {q0}, [r8]!
-    vld1.8          {q1}, [r0]!
-
-    subs            r12, r12, #16
-
-    vst1.8          {q0}, [r9]!
-    vst1.8          {q1}, [r11]!
-    bne             extra_cp_src_to_dst_width_loop
-
-    subs            lr, lr, #1
-
-    add             r2, r2, r6, lsl #1
-    add             r3, r3, r7, lsl #1
-
-    bne             extra_cp_src_to_dst_height_loop
-
-    b               end_of_cp_src_to_dst
-
-    ENDP
-
-;===========================================================
-;In vp8cx_pick_filter_level(), call vp8_yv12_copy_frame_yonly
-;without extend_frame_borders.
-|vp8_yv12_copy_frame_yonly_no_extend_frame_borders_neon| PROC
-    push            {r4 - r11, lr}
-    vpush           {d8-d15}
-
-    ldr             r4, [r0, #yv12_buffer_config_y_height]
-    ldr             r5, [r0, #yv12_buffer_config_y_width]
-    ldr             r6, [r0, #yv12_buffer_config_y_stride]
-    ldr             r7, [r1, #yv12_buffer_config_y_stride]
-    ldr             r2, [r0, #yv12_buffer_config_y_buffer]       ;srcptr1
-    ldr             r3, [r1, #yv12_buffer_config_y_buffer]       ;dstptr1
-
-    ; copy two rows at one time
-    mov             lr, r4, lsr #1
-
-cp_src_to_dst_height_loop1
-    mov             r8, r2
-    mov             r9, r3
-    add             r10, r2, r6
-    add             r11, r3, r7
-    mov             r12, r5, lsr #7
-
-cp_src_to_dst_width_loop1
-    vld1.8          {q0, q1}, [r8]!
-    vld1.8          {q8, q9}, [r10]!
-    vld1.8          {q2, q3}, [r8]!
-    vld1.8          {q10, q11}, [r10]!
-    vld1.8          {q4, q5}, [r8]!
-    vld1.8          {q12, q13}, [r10]!
-    vld1.8          {q6, q7}, [r8]!
-    vld1.8          {q14, q15}, [r10]!
-
-    subs            r12, r12, #1
-
-    vst1.8          {q0, q1}, [r9]!
-    vst1.8          {q8, q9}, [r11]!
-    vst1.8          {q2, q3}, [r9]!
-    vst1.8          {q10, q11}, [r11]!
-    vst1.8          {q4, q5}, [r9]!
-    vst1.8          {q12, q13}, [r11]!
-    vst1.8          {q6, q7}, [r9]!
-    vst1.8          {q14, q15}, [r11]!
-
-    bne             cp_src_to_dst_width_loop1
-
-    subs            lr, lr, #1
-    add             r2, r2, r6, lsl #1
-    add             r3, r3, r7, lsl #1
-
-    bne             cp_src_to_dst_height_loop1
-
-    ands            r10, r5, #0x7f                  ;check to see if extra copy is needed
-    sub             r11, r5, r10
-    ldr             r2, [r0, #yv12_buffer_config_y_buffer]       ;srcptr1
-    ldr             r3, [r1, #yv12_buffer_config_y_buffer]       ;dstptr1
-    bne             extra_cp_src_to_dst_width1
-end_of_cp_src_to_dst1
-
-    vpop            {d8 - d15}
-    pop             {r4-r11, pc}
-
-;=============================
-extra_cp_src_to_dst_width1
-    add             r2, r2, r11
-    add             r3, r3, r11
-    add             r0, r8, r6
-    add             r11, r9, r7
-
-    mov             lr, r4, lsr #1
-extra_cp_src_to_dst_height_loop1
-    mov             r8, r2
-    mov             r9, r3
-    add             r0, r8, r6
-    add             r11, r9, r7
-
-    mov             r12, r10
-
-extra_cp_src_to_dst_width_loop1
-    vld1.8          {q0}, [r8]!
-    vld1.8          {q1}, [r0]!
-
-    subs            r12, r12, #16
-
-    vst1.8          {q0}, [r9]!
-    vst1.8          {q1}, [r11]!
-    bne             extra_cp_src_to_dst_width_loop1
-
-    subs            lr, lr, #1
-
-    add             r2, r2, r6, lsl #1
-    add             r3, r3, r7, lsl #1
-
-    bne             extra_cp_src_to_dst_height_loop1
-
-    b               end_of_cp_src_to_dst1
-
-    ENDP
-
-    END
diff --git a/vpx_scale/arm/neon/vp8_vpxyv12_extendframeborders_neon.asm b/vpx_scale/arm/neon/vp8_vpxyv12_extendframeborders_neon.asm
index 8444b8e03..ebc4242b2 100644
--- a/vpx_scale/arm/neon/vp8_vpxyv12_extendframeborders_neon.asm
+++ b/vpx_scale/arm/neon/vp8_vpxyv12_extendframeborders_neon.asm
@@ -75,12 +75,13 @@ copy_left_right_y
     mul             r8, r4, lr              ; plane_height * plane_stride
 
     ; copy width is plane_stride
-    mov             r12, lr, lsr #7         ; plane_stride / 128
+    movs            r12, lr, lsr #7         ; plane_stride / 128
 
     sub             r1, r1, #32             ; src_ptr1 = y_buffer - Border
     add             r6, r1, r8              ; dest_ptr2 = src_ptr2 - plane_stride (src_ptr1 + (plane_height * plane_stride))
     sub             r2, r6, lr              ; src_ptr2 = src_ptr1 + (plane_height * plane_stride) - plane_stride
     sub             r5, r1, lr, asl #5      ; dest_ptr1 = src_ptr1 - (Border * plane_stride)
+    ble             extra_y_copy_needed     ; plane stride < 128
 
 copy_top_bottom_y
     vld1.8          {q0, q1}, [r1]!
@@ -119,6 +120,7 @@ top_bottom_32
     subs            r12, r12, #1
     bne             copy_top_bottom_y
 
+extra_y_copy_needed
     mov             r7, lr, lsr #4          ; check to see if extra copy is needed
     ands            r7, r7, #0x7
     bne             extra_top_bottom_y
@@ -184,12 +186,13 @@ copy_left_right_uv
 ;Now copy the top and bottom source lines into each line of the respective borders
     mov             r1, r7
     mul             r8, r4, lr              ; plane_height * plane_stride
-    mov             r12, lr, lsr #6         ; plane_stride / 64
+    movs            r12, lr, lsr #6         ; plane_stride / 64
 
     sub             r1, r1, #16             ; src_ptr1 = u_buffer - Border
     add             r6, r1, r8              ; dest_ptr2 = src_ptr2 + plane_stride (src_ptr1 + (plane_height * plane_stride)
     sub             r2, r6, lr              ; src_ptr2 = src_ptr1 + (plane_height * plane_stride) - plane_stride
     sub             r5, r1, lr, asl #4      ; dest_ptr1 = src_ptr1 - (Border * plane_stride)
+    ble             extra_uv_copy_needed    ; plane_stride < 64
 
 copy_top_bottom_uv
     vld1.8          {q0, q1}, [r1]!
@@ -219,7 +222,7 @@ top_bottom_16
 
     subs            r12, r12, #1
     bne             copy_top_bottom_uv
-
+extra_uv_copy_needed
     mov             r7, lr, lsr #3          ; check to see if extra copy is needed
     ands            r7, r7, #0x7
     bne             extra_top_bottom_uv
diff --git a/vpx_scale/arm/neon/yv12extend_arm.c b/vpx_scale/arm/neon/yv12extend_arm.c
index 94f499cf7..eabd4951a 100644
--- a/vpx_scale/arm/neon/yv12extend_arm.c
+++ b/vpx_scale/arm/neon/yv12extend_arm.c
@@ -8,17 +8,14 @@
  *  be found in the AUTHORS file in the root of the source tree.
  */
 
+#include "./vpx_rtcd.h"
 
-#include "vpx_scale/yv12config.h"
-#include "vpx_mem/vpx_mem.h"
-#include "vpx_scale/vpxscale.h"
+extern void vp8_yv12_copy_frame_func_neon(struct yv12_buffer_config *src_ybc,
+                                          struct yv12_buffer_config *dst_ybc);
 
-void vp8_yv12_copy_frame_func_neon(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-
-void
-vp8_yv12_copy_frame_neon(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc) {
+void vp8_yv12_copy_frame_neon(struct yv12_buffer_config *src_ybc,
+                              struct yv12_buffer_config *dst_ybc) {
   vp8_yv12_copy_frame_func_neon(src_ybc, dst_ybc);
-  // printf("Border:%d; plane_stride:%d; plane_height:%d; plane_width:%d\n",dst_ybc->border,dst_ybc->y_stride,dst_ybc->y_height,dst_ybc->y_width);
 
-  vp8_yv12_extend_frame_borders_ptr(dst_ybc);
+  vp8_yv12_extend_frame_borders_neon(dst_ybc);
 }