vpx_scale: sync from master

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

Change-Id: I47eadeb5b6881d448ea3728537f9b8a5b5aac78e

37 files changed, 414 insertions, 2016 deletions

diff --git a/vp9/common/alloccommon.c b/vp9/common/alloccommon.c
index 5f363267c..33d322099 100644
--- a/vp9/common/alloccommon.c
+++ b/vp9/common/alloccommon.c
@@ -81,7 +81,8 @@ int vp9_alloc_frame_buffers(VP9_COMMON *oci, int width, int height) {
   for (i = 0; i < NUM_YV12_BUFFERS; i++) {
     oci->fb_idx_ref_cnt[i] = 0;
     oci->yv12_fb[i].flags = 0;
-    if (vp8_yv12_alloc_frame_buffer(&oci->yv12_fb[i], width, height, VP8BORDERINPIXELS) < 0) {
+    if (vp8_yv12_alloc_frame_buffer(&oci->yv12_fb[i], width, height,
+                                    VP9BORDERINPIXELS) < 0) {
       vp9_de_alloc_frame_buffers(oci);
       return 1;
     }
@@ -97,12 +98,14 @@ int vp9_alloc_frame_buffers(VP9_COMMON *oci, int width, int height) {
   oci->fb_idx_ref_cnt[2] = 1;
   oci->fb_idx_ref_cnt[3] = 1;
 
-  if (vp8_yv12_alloc_frame_buffer(&oci->temp_scale_frame,   width, 16, VP8BORDERINPIXELS) < 0) {
+  if (vp8_yv12_alloc_frame_buffer(&oci->temp_scale_frame, width, 16,
+                                  VP9BORDERINPIXELS) < 0) {
     vp9_de_alloc_frame_buffers(oci);
     return 1;
   }
 
-  if (vp8_yv12_alloc_frame_buffer(&oci->post_proc_buffer, width, height, VP8BORDERINPIXELS) < 0) {
+  if (vp8_yv12_alloc_frame_buffer(&oci->post_proc_buffer, width, height,
+                                  VP9BORDERINPIXELS) < 0) {
     vp9_de_alloc_frame_buffers(oci);
     return 1;
   }
diff --git a/vp9/common/asm_com_offsets.c b/vp9/common/asm_com_offsets.c
index e135a4d78..07d3e333a 100644
--- a/vp9/common/asm_com_offsets.c
+++ b/vp9/common/asm_com_offsets.c
@@ -27,7 +27,7 @@ DEFINE(yv12_buffer_config_y_buffer,             offsetof(YV12_BUFFER_CONFIG, y_b
 DEFINE(yv12_buffer_config_u_buffer,             offsetof(YV12_BUFFER_CONFIG, u_buffer));
 DEFINE(yv12_buffer_config_v_buffer,             offsetof(YV12_BUFFER_CONFIG, v_buffer));
 DEFINE(yv12_buffer_config_border,               offsetof(YV12_BUFFER_CONFIG, border));
-DEFINE(VP8BORDERINPIXELS_VAL,                   VP8BORDERINPIXELS);
+DEFINE(VP9BORDERINPIXELS_VAL,                   VP9BORDERINPIXELS);
 
 END
 
@@ -36,5 +36,5 @@ END
 
 #if HAVE_ARMV7
 /* vp8_yv12_extend_frame_borders_neon makes several assumptions based on this */
-ct_assert(VP8BORDERINPIXELS_VAL, VP8BORDERINPIXELS == 32)
+ct_assert(VP9BORDERINPIXELS_VAL, VP9BORDERINPIXELS == 32)
 #endif
diff --git a/vp9/common/postproc.c b/vp9/common/postproc.c
index a05ed1236..b947938e3 100644
--- a/vp9/common/postproc.c
+++ b/vp9/common/postproc.c
@@ -12,7 +12,6 @@
 #include "vpx_ports/config.h"
 #include "vpx_scale/yv12config.h"
 #include "postproc.h"
-#include "vpx_scale/yv12extend.h"
 #include "vpx_scale/vpxscale.h"
 #include "systemdependent.h"
 
@@ -667,7 +666,7 @@ int vp9_post_proc_frame(VP9_COMMON *oci, YV12_BUFFER_CONFIG *dest,
     vp9_deblock(oci->frame_to_show, &oci->post_proc_buffer,
                 q, 1, 0, RTCD_VTABLE(oci));
   } else {
-    vp8_yv12_copy_frame_ptr(oci->frame_to_show, &oci->post_proc_buffer);
+    vp8_yv12_copy_frame(oci->frame_to_show, &oci->post_proc_buffer);
   }
 
   if (flags & VP9D_ADDNOISE) {
diff --git a/vp9/common/reconinter.c b/vp9/common/reconinter.c
index 252485fe0..536b28753 100644
--- a/vp9/common/reconinter.c
+++ b/vp9/common/reconinter.c
@@ -576,27 +576,29 @@ static void clamp_mv_to_umv_border(MV *mv, const MACROBLOCKD *xd) {
    * filtering. The bottom and right edges use 16 pixels plus 2 pixels
    * left of the central pixel when filtering.
    */
-  if (mv->col < (xd->mb_to_left_edge - ((16 + INTERP_EXTEND) << 3)))
+  if (mv->col < (xd->mb_to_left_edge - ((16 + VP9_INTERP_EXTEND) << 3)))
     mv->col = xd->mb_to_left_edge - (16 << 3);
-  else if (mv->col > xd->mb_to_right_edge + ((15 + INTERP_EXTEND) << 3))
+  else if (mv->col > xd->mb_to_right_edge + ((15 + VP9_INTERP_EXTEND) << 3))
     mv->col = xd->mb_to_right_edge + (16 << 3);
 
-  if (mv->row < (xd->mb_to_top_edge - ((16 + INTERP_EXTEND) << 3)))
+  if (mv->row < (xd->mb_to_top_edge - ((16 + VP9_INTERP_EXTEND) << 3)))
     mv->row = xd->mb_to_top_edge - (16 << 3);
-  else if (mv->row > xd->mb_to_bottom_edge + ((15 + INTERP_EXTEND) << 3))
+  else if (mv->row > xd->mb_to_bottom_edge + ((15 + VP9_INTERP_EXTEND) << 3))
     mv->row = xd->mb_to_bottom_edge + (16 << 3);
 }
 
 /* A version of the above function for chroma block MVs.*/
 static void clamp_uvmv_to_umv_border(MV *mv, const MACROBLOCKD *xd) {
-  mv->col = (2 * mv->col < (xd->mb_to_left_edge - ((16 + INTERP_EXTEND) << 3))) ?
+  const int extend = VP9_INTERP_EXTEND;
+
+  mv->col = (2 * mv->col < (xd->mb_to_left_edge - ((16 + extend) << 3))) ?
             (xd->mb_to_left_edge - (16 << 3)) >> 1 : mv->col;
-  mv->col = (2 * mv->col > xd->mb_to_right_edge + ((15 + INTERP_EXTEND) << 3)) ?
+  mv->col = (2 * mv->col > xd->mb_to_right_edge + ((15 + extend) << 3)) ?
             (xd->mb_to_right_edge + (16 << 3)) >> 1 : mv->col;
 
-  mv->row = (2 * mv->row < (xd->mb_to_top_edge - ((16 + INTERP_EXTEND) << 3))) ?
+  mv->row = (2 * mv->row < (xd->mb_to_top_edge - ((16 + extend) << 3))) ?
             (xd->mb_to_top_edge - (16 << 3)) >> 1 : mv->row;
-  mv->row = (2 * mv->row > xd->mb_to_bottom_edge + ((15 + INTERP_EXTEND) << 3)) ?
+  mv->row = (2 * mv->row > xd->mb_to_bottom_edge + ((15 + extend) << 3)) ?
             (xd->mb_to_bottom_edge + (16 << 3)) >> 1 : mv->row;
 }
 
@@ -621,12 +623,12 @@ void vp9_build_1st_inter16x16_predictors_mby(MACROBLOCKD *xd,
   if (xd->mode_info_context->mbmi.pred_filter_enabled) {
     if ((ymv.as_mv.row | ymv.as_mv.col) & 7) {
       // Sub-pel filter needs extended input
-      int len = 15 + (INTERP_EXTEND << 1);
+      int len = 15 + (VP9_INTERP_EXTEND << 1);
       unsigned char Temp[32 * 32]; // Data required by sub-pel filter
-      unsigned char *pTemp = Temp + (INTERP_EXTEND - 1) * (len + 1);
+      unsigned char *pTemp = Temp + (VP9_INTERP_EXTEND - 1) * (len + 1);
 
       // Copy extended MB into Temp array, applying the spatial filter
-      filter_mb(ptr - (INTERP_EXTEND - 1) * (pre_stride + 1), pre_stride,
+      filter_mb(ptr - (VP9_INTERP_EXTEND - 1) * (pre_stride + 1), pre_stride,
                 Temp, len, len, len);
 
       // Sub-pel interpolation
@@ -693,15 +695,15 @@ void vp9_build_1st_inter16x16_predictors_mbuv(MACROBLOCKD *xd,
     int i;
     unsigned char *pSrc = uptr;
     unsigned char *pDst = dst_u;
-    int len = 7 + (INTERP_EXTEND << 1);
+    int len = 7 + (VP9_INTERP_EXTEND << 1);
     unsigned char Temp[32 * 32]; // Data required by the sub-pel filter
-    unsigned char *pTemp = Temp + (INTERP_EXTEND - 1) * (len + 1);
+    unsigned char *pTemp = Temp + (VP9_INTERP_EXTEND - 1) * (len + 1);
 
     // U & V
     for (i = 0; i < 2; i++) {
       if (_o16x16mv.as_int & 0x000f000f) {
         // Copy extended MB into Temp array, applying the spatial filter
-        filter_mb(pSrc - (INTERP_EXTEND - 1) * (pre_stride + 1), pre_stride,
+        filter_mb(pSrc - (VP9_INTERP_EXTEND - 1) * (pre_stride + 1), pre_stride,
                   Temp, len, len, len);
 
         // Sub-pel filter
@@ -831,12 +833,12 @@ void vp9_build_2nd_inter16x16_predictors_mby(MACROBLOCKD *xd,
   if (xd->mode_info_context->mbmi.pred_filter_enabled) {
     if ((mv_row | mv_col) & 7) {
       // Sub-pel filter needs extended input
-      int len = 15 + (INTERP_EXTEND << 1);
+      int len = 15 + (VP9_INTERP_EXTEND << 1);
       unsigned char Temp[32 * 32]; // Data required by sub-pel filter
-      unsigned char *pTemp = Temp + (INTERP_EXTEND - 1) * (len + 1);
+      unsigned char *pTemp = Temp + (VP9_INTERP_EXTEND - 1) * (len + 1);
 
       // Copy extended MB into Temp array, applying the spatial filter
-      filter_mb(ptr - (INTERP_EXTEND - 1) * (pre_stride + 1), pre_stride,
+      filter_mb(ptr - (VP9_INTERP_EXTEND - 1) * (pre_stride + 1), pre_stride,
                 Temp, len, len, len);
 
       // Sub-pel filter
@@ -898,9 +900,9 @@ void vp9_build_2nd_inter16x16_predictors_mbuv(MACROBLOCKD *xd,
 #if CONFIG_PRED_FILTER
   if (xd->mode_info_context->mbmi.pred_filter_enabled) {
     int i;
-    int len = 7 + (INTERP_EXTEND << 1);
+    int len = 7 + (VP9_INTERP_EXTEND << 1);
     unsigned char Temp[32 * 32]; // Data required by sub-pel filter
-    unsigned char *pTemp = Temp + (INTERP_EXTEND - 1) * (len + 1);
+    unsigned char *pTemp = Temp + (VP9_INTERP_EXTEND - 1) * (len + 1);
     unsigned char *pSrc = uptr;
     unsigned char *pDst = dst_u;
 
@@ -908,7 +910,7 @@ void vp9_build_2nd_inter16x16_predictors_mbuv(MACROBLOCKD *xd,
     for (i = 0; i < 2; i++) {
       if ((omv_row | omv_col) & 15) {
         // Copy extended MB into Temp array, applying the spatial filter
-        filter_mb(pSrc - (INTERP_EXTEND - 1) * (pre_stride + 1), pre_stride,
+        filter_mb(pSrc - (VP9_INTERP_EXTEND - 1) * (pre_stride + 1), pre_stride,
                   Temp, len, len, len);
 
         // Sub-pel filter
diff --git a/vp9/common/rtcd_defs.sh b/vp9/common/rtcd_defs.sh
index ec68f50d0..f909c1898 100644
--- a/vp9/common/rtcd_defs.sh
+++ b/vp9/common/rtcd_defs.sh
@@ -480,3 +480,39 @@ specialize vp9_short_walsh8x4_x8
 
 fi
 # end encoder functions
+
+# Scaler functions
+if [ "CONFIG_SPATIAL_RESAMPLING" != "yes" ]; then
+    prototype void vp8_horizontal_line_4_5_scale "const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width"
+    prototype void vp8_vertical_band_4_5_scale "unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_last_vertical_band_4_5_scale "unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_horizontal_line_2_3_scale "const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width"
+    prototype void vp8_vertical_band_2_3_scale "unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_last_vertical_band_2_3_scale "unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_horizontal_line_3_5_scale "const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width"
+    prototype void vp8_vertical_band_3_5_scale "unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_last_vertical_band_3_5_scale "unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_horizontal_line_3_4_scale "const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width"
+    prototype void vp8_vertical_band_3_4_scale "unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_last_vertical_band_3_4_scale "unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_horizontal_line_1_2_scale "const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width"
+    prototype void vp8_vertical_band_1_2_scale "unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_last_vertical_band_1_2_scale "unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_horizontal_line_5_4_scale "const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width"
+    prototype void vp8_vertical_band_5_4_scale "unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_horizontal_line_5_3_scale "const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width"
+    prototype void vp8_vertical_band_5_3_scale "unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_horizontal_line_2_1_scale "const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width"
+    prototype void vp8_vertical_band_2_1_scale "unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+    prototype void vp8_vertical_band_2_1_scale_i "unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width"
+fi
+
+prototype void vp8_yv12_extend_frame_borders "struct yv12_buffer_config *ybf"
+specialize vp8_yv12_extend_frame_borders neon
+
+prototype void vp8_yv12_copy_frame "struct yv12_buffer_config *src_ybc, struct yv12_buffer_config *dst_ybc"
+specialize vp8_yv12_copy_frame neon
+
+prototype void vp8_yv12_copy_y "struct yv12_buffer_config *src_ybc, struct yv12_buffer_config *dst_ybc"
+specialize vp8_yv12_copy_y neon
+
diff --git a/vp9/decoder/decodframe.c b/vp9/decoder/decodframe.c
index 0499eeb9d..dd1d5ab0b 100644
--- a/vp9/decoder/decodframe.c
+++ b/vp9/decoder/decodframe.c
@@ -20,7 +20,6 @@
 #include "vp9/common/entropymode.h"
 #include "vp9/common/quant_common.h"
 #include "vpx_scale/vpxscale.h"
-#include "vpx_scale/yv12extend.h"
 #include "vp9/common/setupintrarecon.h"
 
 #include "decodemv.h"
diff --git a/vp9/decoder/onyxd_if.c b/vp9/decoder/onyxd_if.c
index 3364856a6..2654985b8 100644
--- a/vp9/decoder/onyxd_if.c
+++ b/vp9/decoder/onyxd_if.c
@@ -17,7 +17,6 @@
 #include "onyxd_int.h"
 #include "vpx_mem/vpx_mem.h"
 #include "vp9/common/alloccommon.h"
-#include "vpx_scale/yv12extend.h"
 #include "vp9/common/loopfilter.h"
 #include "vp9/common/swapyv12buffer.h"
 #include <stdio.h>
@@ -108,7 +107,6 @@ void vp9_initialize_dec(void) {
   if (!init_done) {
     vp9_initialize_common();
     vp9_init_quant_tables();
-    vp8_scale_machine_specific_config();
     init_done = 1;
   }
 }
@@ -191,7 +189,7 @@ vpx_codec_err_t vp9_get_reference_dec(VP9D_PTR ptr, VP9_REFFRAME ref_frame_flag,
     vpx_internal_error(&pbi->common.error, VPX_CODEC_ERROR,
                        "Incorrect buffer dimensions");
   } else
-    vp8_yv12_copy_frame_ptr(&cm->yv12_fb[ref_fb_idx], sd);
+    vp8_yv12_copy_frame(&cm->yv12_fb[ref_fb_idx], sd);
 
   return pbi->common.error.error_code;
 }
@@ -231,7 +229,7 @@ vpx_codec_err_t vp9_set_reference_dec(VP9D_PTR ptr, VP9_REFFRAME ref_frame_flag,
 
     /* Manage the reference counters and copy image. */
     ref_cnt_fb(cm->fb_idx_ref_cnt, ref_fb_ptr, free_fb);
-    vp8_yv12_copy_frame_ptr(sd, &cm->yv12_fb[*ref_fb_ptr]);
+    vp8_yv12_copy_frame(sd, &cm->yv12_fb[*ref_fb_ptr]);
   }
 
   return pbi->common.error.error_code;
@@ -428,7 +426,7 @@ int vp9_receive_compressed_data(VP9D_PTR ptr, unsigned long size,
       /* Apply the loop filter if appropriate. */
       vp9_loop_filter_frame(cm, &pbi->mb);
     }
-    vp8_yv12_extend_frame_borders_ptr(cm->frame_to_show);
+    vp8_yv12_extend_frame_borders(cm->frame_to_show);
   }
 
 #if CONFIG_DEBUG
diff --git a/vp9/encoder/arm/neon/picklpf_arm.c b/vp9/encoder/arm/neon/picklpf_arm.c
index f16dadc62..9357769fe 100644
--- a/vp9/encoder/arm/neon/picklpf_arm.c
+++ b/vp9/encoder/arm/neon/picklpf_arm.c
@@ -13,7 +13,6 @@
 #include "vp9/encoder/onyx_int.h"
 #include "vp9/encoder/quantize.h"
 #include "vpx_mem/vpx_mem.h"
-#include "vpx_scale/yv12extend.h"
 #include "vpx_scale/vpxscale.h"
 #include "vp9/common/alloccommon.h"
 
diff --git a/vp9/encoder/encodeframe.c b/vp9/encoder/encodeframe.c
index a4be21fea..47f7c3749 100644
--- a/vp9/encoder/encodeframe.c
+++ b/vp9/encoder/encodeframe.c
@@ -574,12 +574,12 @@ static void pick_mb_modes(VP9_COMP *cpi,
 
     // Set up limit values for MV components to prevent them from
     // extending beyond the UMV borders assuming 16x16 block size
-    x->mv_row_min = -((mb_row * 16) + VP8BORDERINPIXELS - INTERP_EXTEND);
-    x->mv_col_min = -((mb_col * 16) + VP8BORDERINPIXELS - INTERP_EXTEND);
+    x->mv_row_min = -((mb_row * 16) + VP9BORDERINPIXELS - VP9_INTERP_EXTEND);
+    x->mv_col_min = -((mb_col * 16) + VP9BORDERINPIXELS - VP9_INTERP_EXTEND);
     x->mv_row_max = ((cm->mb_rows - mb_row) * 16 +
-                     (VP8BORDERINPIXELS - 16 - INTERP_EXTEND));
+                     (VP9BORDERINPIXELS - 16 - VP9_INTERP_EXTEND));
     x->mv_col_max = ((cm->mb_cols - mb_col) * 16 +
-                     (VP8BORDERINPIXELS - 16 - INTERP_EXTEND));
+                     (VP9BORDERINPIXELS - 16 - VP9_INTERP_EXTEND));
 
     xd->up_available   = (mb_row != 0);
     xd->left_available = (mb_col != 0);
@@ -759,12 +759,12 @@ static void pick_sb_modes (VP9_COMP *cpi,
 
   /* Set up limit values for MV components to prevent them from
    * extending beyond the UMV borders assuming 16x16 block size */
-  x->mv_row_min = -((mb_row * 16) + VP8BORDERINPIXELS - INTERP_EXTEND);
-  x->mv_col_min = -((mb_col * 16) + VP8BORDERINPIXELS - INTERP_EXTEND);
+  x->mv_row_min = -((mb_row * 16) + VP9BORDERINPIXELS - VP9_INTERP_EXTEND);
+  x->mv_col_min = -((mb_col * 16) + VP9BORDERINPIXELS - VP9_INTERP_EXTEND);
   x->mv_row_max = ((cm->mb_rows - mb_row) * 16 +
-                   (VP8BORDERINPIXELS - 32 - INTERP_EXTEND));
+                   (VP9BORDERINPIXELS - 32 - VP9_INTERP_EXTEND));
   x->mv_col_max = ((cm->mb_cols - mb_col) * 16 +
-                   (VP8BORDERINPIXELS - 32 - INTERP_EXTEND));
+                   (VP9BORDERINPIXELS - 32 - VP9_INTERP_EXTEND));
 
   xd->up_available   = (mb_row != 0);
   xd->left_available = (mb_col != 0);
@@ -939,22 +939,22 @@ static void encode_sb(VP9_COMP *cpi,
     if (xd->mode_info_context->mbmi.encoded_as_sb) {
       // Set up limit values for MV components to prevent them from
       // extending beyond the UMV borders assuming 32x32 block size
-      x->mv_row_min = -((mb_row * 16) + VP8BORDERINPIXELS - INTERP_EXTEND);
-      x->mv_col_min = -((mb_col * 16) + VP8BORDERINPIXELS - INTERP_EXTEND);
+      x->mv_row_min = -((mb_row * 16) + VP9BORDERINPIXELS - VP9_INTERP_EXTEND);
+      x->mv_col_min = -((mb_col * 16) + VP9BORDERINPIXELS - VP9_INTERP_EXTEND);
       x->mv_row_max = ((cm->mb_rows - mb_row) * 16 +
-                       (VP8BORDERINPIXELS - 32 - INTERP_EXTEND));
+                       (VP9BORDERINPIXELS - 32 - VP9_INTERP_EXTEND));
       x->mv_col_max = ((cm->mb_cols - mb_col) * 16 +
-                       (VP8BORDERINPIXELS - 32 - INTERP_EXTEND));
+                       (VP9BORDERINPIXELS - 32 - VP9_INTERP_EXTEND));
     } else {
 #endif
       // Set up limit values for MV components to prevent them from
       // extending beyond the UMV borders assuming 16x16 block size
-      x->mv_row_min = -((mb_row * 16) + VP8BORDERINPIXELS - INTERP_EXTEND);
-      x->mv_col_min = -((mb_col * 16) + VP8BORDERINPIXELS - INTERP_EXTEND);
+      x->mv_row_min = -((mb_row * 16) + VP9BORDERINPIXELS - VP9_INTERP_EXTEND);
+      x->mv_col_min = -((mb_col * 16) + VP9BORDERINPIXELS - VP9_INTERP_EXTEND);
       x->mv_row_max = ((cm->mb_rows - mb_row) * 16 +
-                       (VP8BORDERINPIXELS - 16 - INTERP_EXTEND));
+                       (VP9BORDERINPIXELS - 16 - VP9_INTERP_EXTEND));
       x->mv_col_max = ((cm->mb_cols - mb_col) * 16 +
-                       (VP8BORDERINPIXELS - 16 - INTERP_EXTEND));
+                       (VP9BORDERINPIXELS - 16 - VP9_INTERP_EXTEND));
 #if CONFIG_SUPERBLOCKS
     }
 #endif
diff --git a/vp9/encoder/firstpass.c b/vp9/encoder/firstpass.c
index 4ca190334..b9a3ac4c9 100644
--- a/vp9/encoder/firstpass.c
+++ b/vp9/encoder/firstpass.c
@@ -21,7 +21,6 @@
 #include "encodemb.h"
 #include "vp9/common/extend.h"
 #include "vp9/common/systemdependent.h"
-#include "vpx_scale/yv12extend.h"
 #include "vpx_mem/vpx_mem.h"
 #include "vp9/common/swapyv12buffer.h"
 #include <stdio.h>
@@ -513,8 +512,9 @@ void vp9_first_pass(VP9_COMP *cpi) {
     recon_uvoffset = (mb_row * recon_uv_stride * 8);
 
     // Set up limit values for motion vectors to prevent them extending outside the UMV borders
-    x->mv_row_min = -((mb_row * 16) + (VP8BORDERINPIXELS - 16));
-    x->mv_row_max = ((cm->mb_rows - 1 - mb_row) * 16) + (VP8BORDERINPIXELS - 16);
+    x->mv_row_min = -((mb_row * 16) + (VP9BORDERINPIXELS - 16));
+    x->mv_row_max = ((cm->mb_rows - 1 - mb_row) * 16)
+                    + (VP9BORDERINPIXELS - 16);
 
 
     // for each macroblock col in image
@@ -544,8 +544,9 @@ void vp9_first_pass(VP9_COMP *cpi) {
       intra_error += (int64_t)this_error;
 
       // Set up limit values for motion vectors to prevent them extending outside the UMV borders
-      x->mv_col_min = -((mb_col * 16) + (VP8BORDERINPIXELS - 16));
-      x->mv_col_max = ((cm->mb_cols - 1 - mb_col) * 16) + (VP8BORDERINPIXELS - 16);
+      x->mv_col_min = -((mb_col * 16) + (VP9BORDERINPIXELS - 16));
+      x->mv_col_max = ((cm->mb_cols - 1 - mb_col) * 16)
+                      + (VP9BORDERINPIXELS - 16);
 
       // Other than for the first frame do a motion search
       if (cm->current_video_frame > 0) {
@@ -764,7 +765,7 @@ void vp9_first_pass(VP9_COMP *cpi) {
        (cpi->twopass.this_frame_stats->pcnt_inter > 0.20) &&
        ((cpi->twopass.this_frame_stats->intra_error /
          cpi->twopass.this_frame_stats->coded_error) > 2.0))) {
-    vp8_yv12_copy_frame_ptr(lst_yv12, gld_yv12);
+    vp8_yv12_copy_frame(lst_yv12, gld_yv12);
     cpi->twopass.sr_update_lag = 1;
   } else
     cpi->twopass.sr_update_lag++;
@@ -775,7 +776,7 @@ void vp9_first_pass(VP9_COMP *cpi) {
 
   // Special case for the first frame. Copy into the GF buffer as a second reference.
   if (cm->current_video_frame == 0) {
-    vp8_yv12_copy_frame_ptr(lst_yv12, gld_yv12);
+    vp8_yv12_copy_frame(lst_yv12, gld_yv12);
   }
 
 
diff --git a/vp9/encoder/lookahead.c b/vp9/encoder/lookahead.c
index 25fa06921..ca0b4cdf4 100644
--- a/vp9/encoder/lookahead.c
+++ b/vp9/encoder/lookahead.c
@@ -80,7 +80,7 @@ vp9_lookahead_init(unsigned int width,
       goto bail;
     for (i = 0; i < depth; i++)
       if (vp8_yv12_alloc_frame_buffer(&ctx->buf[i].img,
-                                      width, height, VP8BORDERINPIXELS))
+                                      width, height, VP9BORDERINPIXELS))
         goto bail;
   }
   return ctx;
diff --git a/vp9/encoder/mbgraph.c b/vp9/encoder/mbgraph.c
index 975cfe5dd..301826e50 100644
--- a/vp9/encoder/mbgraph.c
+++ b/vp9/encoder/mbgraph.c
@@ -303,8 +303,9 @@ static void update_mbgraph_frame_stats
   // Set up limit values for motion vectors to prevent them extending outside the UMV borders
   arf_top_mv.as_int = 0;
   gld_top_mv.as_int = 0;
-  x->mv_row_min     = -(VP8BORDERINPIXELS - 16 - INTERP_EXTEND);
-  x->mv_row_max     = (cm->mb_rows - 1) * 16 + VP8BORDERINPIXELS - 16 - INTERP_EXTEND;
+  x->mv_row_min     = -(VP9BORDERINPIXELS - 16 - VP9_INTERP_EXTEND);
+  x->mv_row_max     = (cm->mb_rows - 1) * 16 + VP9BORDERINPIXELS
+                      - 16 - VP9_INTERP_EXTEND;
   xd->up_available  = 0;
   xd->dst.y_stride  = buf->y_stride;
   xd->pre.y_stride  = buf->y_stride;
@@ -320,8 +321,9 @@ static void update_mbgraph_frame_stats
     // Set up limit values for motion vectors to prevent them extending outside the UMV borders
     arf_left_mv.as_int = arf_top_mv.as_int;
     gld_left_mv.as_int = gld_top_mv.as_int;
-    x->mv_col_min      = -(VP8BORDERINPIXELS - 16 - INTERP_EXTEND);
-    x->mv_col_max      = (cm->mb_cols - 1) * 16 + VP8BORDERINPIXELS - 16 - INTERP_EXTEND;
+    x->mv_col_min      = -(VP9BORDERINPIXELS - 16 - VP9_INTERP_EXTEND);
+    x->mv_col_max      = (cm->mb_cols - 1) * 16 + VP9BORDERINPIXELS
+                         - 16 - VP9_INTERP_EXTEND;
     xd->left_available = 0;
 
     for (mb_col = 0; mb_col < cm->mb_cols; mb_col++) {
diff --git a/vp9/encoder/mcomp.c b/vp9/encoder/mcomp.c
index 29d0a1e05..60ec49c95 100644
--- a/vp9/encoder/mcomp.c
+++ b/vp9/encoder/mcomp.c
@@ -275,14 +275,14 @@ int vp9_find_best_sub_pixel_step_iteratively(MACROBLOCK *x, BLOCK *b, BLOCKD *d,
   int buf_r1, buf_r2, buf_c1, buf_c2;
 
   // Clamping to avoid out-of-range data access
-  buf_r1 = ((bestmv->as_mv.row - INTERP_EXTEND) < x->mv_row_min) ?
-      (bestmv->as_mv.row - x->mv_row_min) : INTERP_EXTEND - 1;
-  buf_r2 = ((bestmv->as_mv.row + INTERP_EXTEND) > x->mv_row_max) ?
-      (x->mv_row_max - bestmv->as_mv.row) : INTERP_EXTEND - 1;
-  buf_c1 = ((bestmv->as_mv.col - INTERP_EXTEND) < x->mv_col_min) ?
-      (bestmv->as_mv.col - x->mv_col_min) : INTERP_EXTEND - 1;
-  buf_c2 = ((bestmv->as_mv.col + INTERP_EXTEND) > x->mv_col_max) ?
-      (x->mv_col_max - bestmv->as_mv.col) : INTERP_EXTEND - 1;
+  buf_r1 = ((bestmv->as_mv.row - VP9_INTERP_EXTEND) < x->mv_row_min) ?
+      (bestmv->as_mv.row - x->mv_row_min) : VP9_INTERP_EXTEND - 1;
+  buf_r2 = ((bestmv->as_mv.row + VP9_INTERP_EXTEND) > x->mv_row_max) ?
+      (x->mv_row_max - bestmv->as_mv.row) : VP9_INTERP_EXTEND - 1;
+  buf_c1 = ((bestmv->as_mv.col - VP9_INTERP_EXTEND) < x->mv_col_min) ?
+      (bestmv->as_mv.col - x->mv_col_min) : VP9_INTERP_EXTEND - 1;
+  buf_c2 = ((bestmv->as_mv.col + VP9_INTERP_EXTEND) > x->mv_col_max) ?
+      (x->mv_col_max - bestmv->as_mv.col) : VP9_INTERP_EXTEND - 1;
   y_stride = 32;
 
   /* Copy to intermediate buffer before searching. */
diff --git a/vp9/encoder/onyx_if.c b/vp9/encoder/onyx_if.c
index d89e055dc..3534c39f1 100644
--- a/vp9/encoder/onyx_if.c
+++ b/vp9/encoder/onyx_if.c
@@ -23,7 +23,6 @@
 #include "ratectrl.h"
 #include "vp9/common/quant_common.h"
 #include "segmentation.h"
-#include "vpx_scale/yv12extend.h"
 #if CONFIG_POSTPROC
 #include "vp9/common/postproc.h"
 #endif
@@ -309,7 +308,6 @@ void vp9_initialize_enc() {
   static int init_done = 0;
 
   if (!init_done) {
-    vp8_scale_machine_specific_config();
     vp9_initialize_common();
     vp9_tokenize_initialize();
     vp9_init_quant_tables();
@@ -1239,7 +1237,7 @@ static void alloc_raw_frame_buffers(VP9_COMP *cpi) {
 #if VP9_TEMPORAL_ALT_REF
 
   if (vp8_yv12_alloc_frame_buffer(&cpi->alt_ref_buffer,
-                                  width, height, VP8BORDERINPIXELS))
+                                  width, height, VP9BORDERINPIXELS))
     vpx_internal_error(&cpi->common.error, VPX_CODEC_MEM_ERROR,
                        "Failed to allocate altref buffer");
 
@@ -1283,12 +1281,12 @@ void vp9_alloc_compressor_data(VP9_COMP *cpi) {
 
 
   if (vp8_yv12_alloc_frame_buffer(&cpi->last_frame_uf,
-                                  width, height, VP8BORDERINPIXELS))
+                                  width, height, VP9BORDERINPIXELS))
     vpx_internal_error(&cpi->common.error, VPX_CODEC_MEM_ERROR,
                        "Failed to allocate last frame buffer");
 
   if (vp8_yv12_alloc_frame_buffer(&cpi->scaled_source,
-                                  width, height, VP8BORDERINPIXELS))
+                                  width, height, VP9BORDERINPIXELS))
     vpx_internal_error(&cpi->common.error, VPX_CODEC_MEM_ERROR,
                        "Failed to allocate scaled source buffer");
 
@@ -2405,7 +2403,7 @@ int vp9_get_reference_enc(VP9_PTR ptr, VP9_REFFRAME ref_frame_flag,
   else
     return -1;
 
-  vp8_yv12_copy_frame_ptr(&cm->yv12_fb[ref_fb_idx], sd);
+  vp8_yv12_copy_frame(&cm->yv12_fb[ref_fb_idx], sd);
 
   return 0;
 }
@@ -2426,7 +2424,7 @@ int vp9_set_reference_enc(VP9_PTR ptr, VP9_REFFRAME ref_frame_flag,
   else
     return -1;
 
-  vp8_yv12_copy_frame_ptr(sd, &cm->yv12_fb[ref_fb_idx]);
+  vp8_yv12_copy_frame(sd, &cm->yv12_fb[ref_fb_idx]);
 
   return 0;
 }
@@ -2806,7 +2804,7 @@ static void loopfilter_frame(VP9_COMP *cpi, VP9_COMMON *cm) {
     vp9_loop_filter_frame(cm, &cpi->mb.e_mbd);
   }
 
-  vp8_yv12_extend_frame_borders_ptr(cm->frame_to_show);
+  vp8_yv12_extend_frame_borders(cm->frame_to_show);
 
 }
 
diff --git a/vp9/encoder/picklpf.c b/vp9/encoder/picklpf.c
index 9363bccca..71c0fb1f1 100644
--- a/vp9/encoder/picklpf.c
+++ b/vp9/encoder/picklpf.c
@@ -13,7 +13,6 @@
 #include "onyx_int.h"
 #include "quantize.h"
 #include "vpx_mem/vpx_mem.h"
-#include "vpx_scale/yv12extend.h"
 #include "vpx_scale/vpxscale.h"
 #include "vp9/common/alloccommon.h"
 #include "vp9/common/loopfilter.h"
@@ -279,7 +278,7 @@ void vp9_pick_filter_level(YV12_BUFFER_CONFIG *sd, VP9_COMP *cpi) {
 #endif
 #if !HAVE_ARMV7 || CONFIG_RUNTIME_CPU_DETECT
   {
-    vp8_yv12_copy_frame_ptr(cm->frame_to_show, &cpi->last_frame_uf);
+    vp8_yv12_copy_frame(cm->frame_to_show, &cpi->last_frame_uf);
   }
 #endif
 
@@ -320,7 +319,7 @@ void vp9_pick_filter_level(YV12_BUFFER_CONFIG *sd, VP9_COMP *cpi) {
 #endif
 #if !HAVE_ARMV7 || CONFIG_RUNTIME_CPU_DETECT
   {
-    vp8_yv12_copy_frame_yonly_ptr(&cpi->last_frame_uf, cm->frame_to_show);
+    vp8_yv12_copy_y(&cpi->last_frame_uf, cm->frame_to_show);
   }
 #endif
 
@@ -359,7 +358,7 @@ void vp9_pick_filter_level(YV12_BUFFER_CONFIG *sd, VP9_COMP *cpi) {
 #endif
 #if !HAVE_ARMV7 || CONFIG_RUNTIME_CPU_DETECT
       {
-        vp8_yv12_copy_frame_yonly_ptr(&cpi->last_frame_uf, cm->frame_to_show);
+        vp8_yv12_copy_y(&cpi->last_frame_uf, cm->frame_to_show);
       }
 #endif
 
@@ -394,7 +393,7 @@ void vp9_pick_filter_level(YV12_BUFFER_CONFIG *sd, VP9_COMP *cpi) {
 #endif
 #if !HAVE_ARMV7 || CONFIG_RUNTIME_CPU_DETECT
       {
-        vp8_yv12_copy_frame_yonly_ptr(&cpi->last_frame_uf, cm->frame_to_show);
+        vp8_yv12_copy_y(&cpi->last_frame_uf, cm->frame_to_show);
       }
 #endif
 
diff --git a/vp9/encoder/temporal_filter.c b/vp9/encoder/temporal_filter.c
index db8b36138..c2657e97e 100644
--- a/vp9/encoder/temporal_filter.c
+++ b/vp9/encoder/temporal_filter.c
@@ -22,7 +22,6 @@
 #include "ratectrl.h"
 #include "vp9/common/quant_common.h"
 #include "segmentation.h"
-#include "vpx_scale/yv12extend.h"
 #include "vpx_mem/vpx_mem.h"
 #include "vp9/common/swapyv12buffer.h"
 #include "vpx_ports/vpx_timer.h"
@@ -247,18 +246,19 @@ static void temporal_filter_iterate_c
   for (mb_row = 0; mb_row < mb_rows; mb_row++) {
 #if ALT_REF_MC_ENABLED
     // Source frames are extended to 16 pixels.  This is different than
-    //  L/A/G reference frames that have a border of 32 (VP8BORDERINPIXELS)
+    //  L/A/G reference frames that have a border of 32 (VP9BORDERINPIXELS)
     // A 6/8 tap filter is used for motion search.  This requires 2 pixels
     //  before and 3 pixels after.  So the largest Y mv on a border would
-    //  then be 16 - INTERP_EXTEND. The UV blocks are half the size of the Y and
-    //  therefore only extended by 8.  The largest mv that a UV block
-    //  can support is 8 - INTERP_EXTEND.  A UV mv is half of a Y mv.
-    //  (16 - INTERP_EXTEND) >> 1 which is greater than 8 - INTERP_EXTEND.
+    //  then be 16 - VP9_INTERP_EXTEND. The UV blocks are half the size of the
+    //  Y and therefore only extended by 8.  The largest mv that a UV block
+    //  can support is 8 - VP9_INTERP_EXTEND.  A UV mv is half of a Y mv.
+    //  (16 - VP9_INTERP_EXTEND) >> 1 which is greater than
+    //  8 - VP9_INTERP_EXTEND.
     // To keep the mv in play for both Y and UV planes the max that it
-    //  can be on a border is therefore 16 - (2*INTERP_EXTEND+1).
-    cpi->mb.mv_row_min = -((mb_row * 16) + (17 - 2 * INTERP_EXTEND));
+    //  can be on a border is therefore 16 - (2*VP9_INTERP_EXTEND+1).
+    cpi->mb.mv_row_min = -((mb_row * 16) + (17 - 2 * VP9_INTERP_EXTEND));
     cpi->mb.mv_row_max = ((cpi->common.mb_rows - 1 - mb_row) * 16)
-                         + (17 - 2 * INTERP_EXTEND);
+                         + (17 - 2 * VP9_INTERP_EXTEND);
 #endif
 
     for (mb_col = 0; mb_col < mb_cols; mb_col++) {
@@ -269,9 +269,9 @@ static void temporal_filter_iterate_c
       vpx_memset(count, 0, 384 * sizeof(unsigned short));
 
 #if ALT_REF_MC_ENABLED
-      cpi->mb.mv_col_min = -((mb_col * 16) + (17 - 2 * INTERP_EXTEND));
+      cpi->mb.mv_col_min = -((mb_col * 16) + (17 - 2 * VP9_INTERP_EXTEND));
       cpi->mb.mv_col_max = ((cpi->common.mb_cols - 1 - mb_col) * 16)
-                           + (17 - 2 * INTERP_EXTEND);
+                           + (17 - 2 * VP9_INTERP_EXTEND);
 #endif
 
       for (frame = 0; frame < frame_count; frame++) {
diff --git a/vp9/vp9_cx_iface.c b/vp9/vp9_cx_iface.c
index 1d8d950e0..1572920f1 100644
--- a/vp9/vp9_cx_iface.c
+++ b/vp9/vp9_cx_iface.c
@@ -829,12 +829,12 @@ static vpx_image_t *vp8e_get_preview(vpx_codec_alg_priv_t *ctx) {
 
     /*
     vpx_img_wrap(&ctx->preview_img, VPX_IMG_FMT_YV12,
-        sd.y_width + 2*VP8BORDERINPIXELS,
-        sd.y_height + 2*VP8BORDERINPIXELS,
+        sd.y_width + 2*VP9BORDERINPIXELS,
+        sd.y_height + 2*VP9BORDERINPIXELS,
         1,
         sd.buffer_alloc);
     vpx_img_set_rect(&ctx->preview_img,
-        VP8BORDERINPIXELS, VP8BORDERINPIXELS,
+        VP9BORDERINPIXELS, VP9BORDERINPIXELS,
         sd.y_width, sd.y_height);
         */
 
diff --git a/vp9/vp9_dx_iface.c b/vp9/vp9_dx_iface.c
index f93c6efa2..7116d5f9e 100644
--- a/vp9/vp9_dx_iface.c
+++ b/vp9/vp9_dx_iface.c
@@ -282,7 +282,7 @@ static void yuvconfig2image(vpx_image_t               *img,
   img->fmt = yv12->clrtype == REG_YUV ?
              VPX_IMG_FMT_I420 : VPX_IMG_FMT_VPXI420;
   img->w = yv12->y_stride;
-  img->h = (yv12->y_height + 2 * VP8BORDERINPIXELS + 15) & ~15;
+  img->h = (yv12->y_height + 2 * VP9BORDERINPIXELS + 15) & ~15;
   img->d_w = yv12->y_width;
   img->d_h = yv12->y_height;
   img->x_chroma_shift = 1;
diff --git a/vpx_scale/arm/armv4/gen_scalers_armv4.asm b/vpx_scale/arm/armv4/gen_scalers_armv4.asm
deleted file mode 100644
index e495184e7..000000000
--- a/vpx_scale/arm/armv4/gen_scalers_armv4.asm
+++ /dev/null
@@ -1,774 +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  |horizontal_line_4_5_scale_armv4|
-    EXPORT  |vertical_band_4_5_scale_armv4|
-    EXPORT  |horizontal_line_2_3_scale_armv4|
-    EXPORT  |vertical_band_2_3_scale_armv4|
-    EXPORT  |horizontal_line_3_5_scale_armv4|
-    EXPORT  |vertical_band_3_5_scale_armv4|
-    EXPORT  |horizontal_line_3_4_scale_armv4|
-    EXPORT  |vertical_band_3_4_scale_armv4|
-    EXPORT  |horizontal_line_1_2_scale_armv4|
-    EXPORT  |vertical_band_1_2_scale_armv4|
-
-    AREA    |.text|, CODE, READONLY  ; name this block of code
-
-src         RN  r0
-srcw        RN  r1
-dest        RN  r2
-mask        RN  r12
-c51_205     RN  r10
-c102_154    RN  r11
-;/****************************************************************************
-; *
-; *  ROUTINE       : horizontal_line_4_5_scale_armv4
-; *
-; *  INPUTS        : const unsigned char *source : Pointer to source data.
-; *                  unsigned int source_width    : Stride of source.
-; *                  unsigned char *dest         : Pointer to destination data.
-; *                  unsigned int dest_width      : Stride of destination (NOT USED).
-; *
-; *  OUTPUTS       : None.
-; *
-; *  RETURNS       : void
-; *
-; *  FUNCTION      : Copies horizontal line of pixels from source to
-; *                  destination scaling up by 4 to 5.
-; *
-; *  SPECIAL NOTES : None.
-; *
-; ****************************************************************************/
-;void horizontal_line_4_5_scale_armv4
-;(
-;   r0 = UINT8 *source
-;   r1 = UINT32 source_width
-;   r2 = UINT8 *dest
-;   r3 = UINT32 dest_width
-;)
-|horizontal_line_4_5_scale_armv4| PROC
-    stmdb   sp!, {r4 - r11, lr}
-
-    mov     mask, #255              ; mask for selection
-    ldr     c51_205, =0x3300cd
-    ldr     c102_154, =0x66009a
-
-    ldr     r3, [src], #4
-
-hl45_loop
-
-    and     r4, r3, mask            ; a = src[0]
-    and     r5, mask, r3, lsr #8    ; b = src[1]
-    strb    r4, [dest], #1
-
-    orr     r6, r4, r5, lsl #16     ; b | a
-    and     r7, mask, r3, lsr #16   ; c = src[2]
-    mul     r6, c51_205, r6         ; a * 51 + 205 * b
-
-    orr     r5, r5, r7, lsl #16     ; c | b
-    mul     r5, c102_154, r5        ; b * 102 + 154 * c
-    add     r6, r6, #0x8000
-    and     r8, mask, r3, lsr #24   ; d = src[3]
-    mov     r6, r6, lsr #24
-    strb    r6, [dest], #1
-
-    orr     r7, r8, r7, lsl #16     ; c | d
-    mul     r7, c102_154, r7        ; c * 154 + 102 * d
-    add     r5, r5, #0x8000
-    ldr     r3, [src], #4
-    mov     r5, r5, lsr #24
-    strb    r5, [dest], #1
-
-    add     r7, r7, #0x8000
-    and     r9, mask, r3            ; e = src[4]
-    orr     r9, r9, r8, lsl #16     ; d | e
-    mul     r9, c51_205, r9         ; d * 205 + 51 * e
-    mov     r7, r7, lsr #24
-    strb    r7, [dest], #1
-
-    add     r9, r9, #0x8000
-    subs    srcw, srcw, #4
-    mov     r9, r9, lsr #24
-    strb    r9, [dest], #1
-
-    bne     hl45_loop
-
-    and     r4, r3, mask
-    and     r5, mask, r3, lsl #8
-    strb    r4, [dest], #1
-
-    orr     r6, r4, r5, lsl #16     ; b | a
-    mul     r6, c51_205, r6
-
-    and     r7, mask, r3, lsl #16
-    orr     r5, r5, r7, lsl #16     ; c | b
-    mul     r5, c102_154, r5
-    add     r6, r6, #0x8000
-    and     r8, mask, r3, lsl #24
-    mov     r6, r6, lsr #24
-    strb    r6, [dest], #1
-
-    orr     r7, r8, r7, lsl #16     ; c | d
-    mul     r7, c102_154, r7
-    add     r5, r5, #0x8000
-    mov     r5, r5, lsr #24
-    strb    r5, [dest], #1
-
-    add     r7, r7, #0x8000
-    mov     r7, r7, lsr #24
-    strb    r7, [dest], #1
-
-    ldrb    r3, [src]
-    strb    r3, [dest], #1
-
-    ldmia   sp!, {r4 - r11, pc}
-    ENDP    ;|vp8cx_horizontal_line_4_5_scale_c|
-
-;/****************************************************************************
-; *
-; *  ROUTINE       : vertical_band_4_5_scale_armv4
-; *
-; *  INPUTS        : unsigned char *dest    : Pointer to destination data.
-; *                  unsigned int dest_pitch : Stride of destination data.
-; *                  unsigned int dest_width : Width of destination data.
-; *
-; *  OUTPUTS       : None.
-; *
-; *  RETURNS       : void
-; *
-; *  FUNCTION      : Scales vertical band of pixels by scale 4 to 5. The
-; *                  height of the band scaled is 4-pixels.
-; *
-; *  SPECIAL NOTES : The routine uses the first line of the band below
-; *                  the current band.
-; *
-; ****************************************************************************/
-;void vertical_band_4_5_scale_armv4
-;(
-;   r0 = UINT8 *dest
-;   r1 = UINT32 dest_pitch
-;   r2 = UINT32 dest_width
-;)
-|vertical_band_4_5_scale_armv4| PROC
-    stmdb   sp!, {r4 - r11, lr}
-
-    ldr     c51_205, =0x3300cd
-    ldr     c102_154, =0x66009a
-
-vl45_loop
-    mov     r3, src
-    ldrb    r4, [r3], r1            ; a = des [0]
-    ldrb    r5, [r3], r1            ; b = des [dest_pitch]
-    ldrb    r7, [r3], r1            ; c = des[dest_pitch*2]
-    add     lr, src, r1
-
-    orr     r6, r4, r5, lsl #16     ; b | a
-    mul     r6, c51_205, r6         ; a * 51 + 205 * b
-
-    ldrb    r8, [r3], r1            ; d = des[dest_pitch*3]
-    orr     r5, r5, r7, lsl #16     ; c | b
-    mul     r5, c102_154, r5        ; b * 102 + 154 * c
-    add     r6, r6, #0x8000
-    orr     r7, r8, r7, lsl #16     ; c | d
-    mov     r6, r6, lsr #24
-    strb    r6, [lr], r1
-
-    ldrb    r9, [r3, r1]            ; e = des [dest_pitch * 5]
-    mul     r7, c102_154, r7        ; c * 154 + 102 * d
-    add     r5, r5, #0x8000
-    orr     r9, r9, r8, lsl #16     ; d | e
-    mov     r5, r5, lsr #24
-    strb    r5, [lr], r1
-
-    mul     r9, c51_205, r9         ; d * 205 + 51 * e
-    add     r7, r7, #0x8000
-    add     src, src, #1
-    mov     r7, r7, lsr #24
-    strb    r7, [lr], r1
-
-    add     r9, r9, #0x8000
-    subs    r2, r2, #1
-    mov     r9, r9, lsr #24
-    strb    r9, [lr], r1
-
-    bne     vl45_loop
-
-    ldmia   sp!, {r4 - r11, pc}
-    ENDP    ;|vertical_band_4_5_scale_armv4|
-
-;/****************************************************************************
-; *
-; *  ROUTINE       : horizontal_line_2_3_scale_armv4
-; *
-; *  INPUTS        : const unsigned char *source : Pointer to source data.
-; *                  unsigned int source_width    : Stride of source.
-; *                  unsigned char *dest         : Pointer to destination data.
-; *                  unsigned int dest_width      : Stride of destination (NOT USED).
-; *
-; *  OUTPUTS       : None.
-; *
-; *  RETURNS       : void
-; *
-; *  FUNCTION      : Copies horizontal line of pixels from source to
-; *                  destination scaling up by 2 to 3.
-; *
-; *  SPECIAL NOTES : None.
-; *
-; *
-; ****************************************************************************/
-;void horizontal_line_2_3_scale_armv4
-;(
-;   const unsigned char *source,
-;   unsigned int source_width,
-;   unsigned char *dest,
-;   unsigned int dest_width
-;)
-|horizontal_line_2_3_scale_armv4| PROC
-    stmdb   sp!, {r4 - r11, lr}
-    ldr     lr,  =85
-    ldr     r12, =171
-
-hl23_loop
-
-    ldrb    r3, [src], #1           ; a
-    ldrb    r4, [src], #1           ; b
-    ldrb    r5, [src]               ; c
-
-    strb    r3, [dest], #1
-    mul     r4, r12, r4             ; b * 171
-    mla     r6, lr, r3, r4          ; a * 85
-    mla     r7, lr, r5, r4          ; c * 85
-
-    add     r6, r6, #128
-    mov     r6, r6, lsr #8
-    strb    r6, [dest], #1
-
-    add     r7, r7, #128
-    mov     r7, r7, lsr #8
-    strb    r7, [dest], #1
-
-    subs    srcw, srcw, #2
-    bne     hl23_loop
-
-    ldrb    r4, [src, #1]           ; b
-    strb    r5, [dest], #1
-    strb    r4, [dest, #1]
-
-    mul     r4, r12, r4             ; b * 171
-    mla     r6, lr, r5, r4          ; a * 85 + b *171
-
-    add     r6, r6, #128
-    mov     r6, r6, lsr #8
-    strb    r6, [dest]
-
-    ldmia   sp!, {r4 - r11, pc}
-    ENDP    ;|horizontal_line_2_3_scale_armv4|
-
-;/****************************************************************************
-; *
-; *  ROUTINE       : vertical_band_2_3_scale_armv4
-; *
-; *  INPUTS        : unsigned char *dest    : Pointer to destination data.
-; *                  unsigned int dest_pitch : Stride of destination data.
-; *                  unsigned int dest_width : Width of destination data.
-; *
-; *  OUTPUTS       : None.
-; *
-; *  RETURNS       : void
-; *
-; *  FUNCTION      : Scales vertical band of pixels by scale 2 to 3. The
-; *                  height of the band scaled is 2-pixels.
-; *
-; *  SPECIAL NOTES : The routine uses the first line of the band below
-; *                  the current band.
-; *
-; ****************************************************************************/
-;void vertical_band_2_3_scale_armv4
-;(
-;   r0 = UINT8 *dest
-;   r1 = UINT32 dest_pitch
-;   r2 = UINT32 dest_width
-;)
-|vertical_band_2_3_scale_armv4| PROC
-    stmdb   sp!, {r4 - r8, lr}
-    ldr     lr,  =85
-    ldr     r12, =171
-    add     r3, r1, r1, lsl #1      ; 3 * dest_pitch
-
-vl23_loop
-    ldrb    r4, [src]               ; a = des [0]
-    ldrb    r5, [src, r1]           ; b = des [dest_pitch]
-    ldrb    r7, [src, r3]           ; c = des [dest_pitch*3]
-    subs    r2, r2, #1
-
-    mul     r5, r12, r5             ; b * 171
-    mla     r6, lr, r4, r5          ; a * 85
-    mla     r8, lr, r7, r5          ; c * 85
-
-    add     r6, r6, #128
-    mov     r6, r6, lsr #8
-    strb    r6, [src, r1]
-
-    add     r8, r8, #128
-    mov     r8, r8, lsr #8
-    strb    r8, [src, r1, lsl #1]
-
-    add     src, src, #1
-
-    bne     vl23_loop
-
-    ldmia   sp!, {r4 - r8, pc}
-    ENDP    ;|vertical_band_2_3_scale_armv4|
-
-;/****************************************************************************
-; *
-; *  ROUTINE       : vp8cx_horizontal_line_3_5_scale_c
-; *
-; *  INPUTS        : const unsigned char *source : Pointer to source data.
-; *                  unsigned int source_width    : Stride of source.
-; *                  unsigned char *dest         : Pointer to destination data.
-; *                  unsigned int dest_width      : Stride of destination (NOT USED).
-; *
-; *  OUTPUTS       : None.
-; *
-; *  RETURNS       : void
-; *
-; *  FUNCTION      : Copies horizontal line of pixels from source to
-; *                  destination scaling up by 3 to 5.
-; *
-; *  SPECIAL NOTES : None.
-; *
-; *
-; ****************************************************************************/
-;void vp8cx_horizontal_line_3_5_scale_c
-;(
-;   const unsigned char *source,
-;   unsigned int source_width,
-;   unsigned char *dest,
-;   unsigned int dest_width
-;)
-|horizontal_line_3_5_scale_armv4| PROC
-    stmdb   sp!, {r4 - r11, lr}
-
-    ldr     c51_205, =0x3300cd
-    ldr     c102_154, =0x66009a
-
-    ldrb    r4, [src], #1           ; a = src[0]
-
-hl35_loop
-
-    ldrb    r8, [src], #1           ; b = src[1]
-    strb    r4, [dest], #1
-
-    orr     r6, r4, r8, lsl #16     ; b | a
-    ldrb    r9, [src], #1           ; c = src[2]
-    mul     r6, c102_154, r6        ; a * 102 + 154 * b
-
-    orr     r5, r9, r8, lsl #16     ; b | c
-    mul     r5, c51_205, r5         ; b * 205 + 51 * c
-    add     r6, r6, #0x8000
-    ldrb    r4, [src], #1           ; d = src[3]
-    mov     r6, r6, lsr #24
-    strb    r6, [dest], #1
-
-    orr     r7, r8, r9, lsl #16     ; c | b
-    mul     r7, c51_205, r7         ; c * 205 + 154 * b
-    add     r5, r5, #0x8000
-    mov     r5, r5, lsr #24
-    strb    r5, [dest], #1
-
-    orr     r9, r4, r9, lsl #16     ; c | d
-    mul     r9, c102_154, r9        ; c * 154 + 102 * d
-    add     r7, r7, #0x8000
-    mov     r7, r7, lsr #24
-    strb    r7, [dest], #1
-
-    add     r9, r9, #0x8000
-    subs    srcw, srcw, #3
-    mov     r9, r9, lsr #24
-    strb    r9, [dest], #1
-
-    bpl     hl35_loop
-
-    ldrb    r5, [src], #1           ; b = src[1]
-    strb    r4, [dest], #1
-
-    orr     r6, r4, r8, lsl #16     ; b | a
-    ldrb    r9, [src], #1           ; c = src[2]
-    mul     r6, c102_154, r6        ; a * 102 + 154 * b
-
-    orr     r5, r9, r8, lsl #16     ; b | c
-    mul     r5, c51_205, r5         ; b * 205 + 51 * c
-    add     r6, r6, #0x8000
-    mov     r6, r6, lsr #24
-    strb    r6, [dest], #1
-
-    orr     r7, r8, r9, lsl #16     ; c | b
-    mul     r7, c51_205, r7         ; c * 205 + 154 * b
-    add     r5, r5, #0x8000
-    mov     r5, r5, lsr #24
-    strb    r5, [dest], #1
-
-    add     r7, r7, #0x8000
-    mov     r7, r7, lsr #24
-    strb    r7, [dest], #1
-    strb    r9, [dest], #1
-
-    ldmia   sp!, {r4 - r11, pc}
-    ENDP    ;|vp8cx_horizontal_line_3_5_scale_c|
-
-
-;/****************************************************************************
-; *
-; *  ROUTINE       : vp8cx_vertical_band_3_5_scale_c
-; *
-; *  INPUTS        : unsigned char *dest    : Pointer to destination data.
-; *                  unsigned int dest_pitch : Stride of destination data.
-; *                  unsigned int dest_width : Width of destination data.
-; *
-; *  OUTPUTS       : None.
-; *
-; *  RETURNS       : void
-; *
-; *  FUNCTION      : Scales vertical band of pixels by scale 3 to 5. The
-; *                  height of the band scaled is 3-pixels.
-; *
-; *  SPECIAL NOTES : The routine uses the first line of the band below
-; *                  the current band.
-; *
-; ****************************************************************************/
-;void vertical_band_4_5_scale_armv4
-;(
-;   r0 = UINT8 *dest
-;   r1 = UINT32 dest_pitch
-;   r2 = UINT32 dest_width
-;)
-|vertical_band_3_5_scale_armv4| PROC
-    stmdb   sp!, {r4 - r11, lr}
-
-    ldr     c51_205, =0x3300cd
-    ldr     c102_154, =0x66009a
-
-vl35_loop
-    mov     r3, src
-    ldrb    r4, [r3], r1            ; a = des [0]
-    ldrb    r5, [r3], r1            ; b = des [dest_pitch]
-    ldrb    r7, [r3], r1            ; c = des[dest_pitch*2]
-    add     lr, src, r1
-
-    orr     r8, r4, r5, lsl #16     ; b | a
-    mul     r6, c102_154, r8        ; a * 102 + 154 * b
-
-    ldrb    r8, [r3, r1, lsl #1]    ; d = des[dest_pitch*5]
-    orr     r3, r7, r5, lsl #16     ; b | c
-    mul     r9, c51_205, r3         ; b * 205 + 51 * c
-    add     r6, r6, #0x8000
-    orr     r3, r5, r7, lsl #16     ; c | b
-    mov     r6, r6, lsr #24
-    strb    r6, [lr], r1
-
-    mul     r5, c51_205, r3         ; c * 205 + 154 * b
-    add     r9, r9, #0x8000
-    orr     r3, r8, r7, lsl #16     ; c | d
-    mov     r9, r9, lsr #24
-    strb    r9, [lr], r1
-
-    mul     r7, c102_154, r3        ; c * 154 + 102 * d
-    add     r5, r5, #0x8000
-    add     src, src, #1
-    mov     r5, r5, lsr #24
-    strb    r5, [lr], r1
-
-    add     r7, r7, #0x8000
-    subs    r2, r2, #1
-    mov     r7, r7, lsr #24
-    strb    r7, [lr], r1
-
-
-    bne     vl35_loop
-
-    ldmia   sp!, {r4 - r11, pc}
-    ENDP    ;|vertical_band_3_5_scale_armv4|
-
-;/****************************************************************************
-; *
-; *  ROUTINE       : horizontal_line_3_4_scale_armv4
-; *
-; *  INPUTS        : const unsigned char *source : Pointer to source data.
-; *                  unsigned int source_width    : Stride of source.
-; *                  unsigned char *dest         : Pointer to destination data.
-; *                  unsigned int dest_width      : Stride of destination (NOT USED).
-; *
-; *  OUTPUTS       : None.
-; *
-; *  RETURNS       : void
-; *
-; *  FUNCTION      : Copies horizontal line of pixels from source to
-; *                  destination scaling up by 3 to 4.
-; *
-; *  SPECIAL NOTES : None.
-; *
-; *
-; ****************************************************************************/
-;void horizontal_line_3_4_scale_armv4
-;(
-;   const unsigned char *source,
-;   unsigned int source_width,
-;   unsigned char *dest,
-;   unsigned int dest_width
-;)
-|horizontal_line_3_4_scale_armv4| PROC
-    stmdb   sp!, {r4 - r11, lr}
-
-    ldr     r10, =64
-    ldr     r11, =192
-    mov     r9, #128
-
-    ldrb    r4, [src], #1           ; a = src[0]
-
-hl34_loop
-
-    ldrb    r8, [src], #1           ; b = src[1]
-    ldrb    r7, [src], #1           ; c = src[2]
-    strb    r4, [dest], #1
-
-    mla     r4, r10, r4, r9         ; a*64 + 128
-    mla     r4, r11, r8, r4         ; a*64 + b*192 + 1
-
-    add     r8, r8, #1              ; b + 1
-    add     r8, r8, r7              ; b + c + 1
-    mov     r8, r8, asr #1          ; (b + c + 1) >> 1
-
-    mov     r4, r4, asr #8          ; (a*64 + b*192 + 1) >> 8
-    strb    r4, [dest], #1
-
-    strb    r8, [dest], #1
-
-    ldrb    r4, [src], #1           ; [a+1]
-
-    mla     r7, r11, r7, r9         ; c*192 + 128
-    mla     r7, r4, r10, r7         ; a*64 + b*192 + 128
-
-    subs    srcw, srcw, #3
-
-    mov     r7, r7, asr #8          ; (a*64 + b*192 + 128) >> 8
-    strb    r7, [dest], #1
-
-    bpl     hl34_loop
-
-    ldrb    r8, [src], #1           ; b = src[1]
-    ldrb    r7, [src], #1           ; c = src[2]
-    strb    r4, [dest], #1
-
-    mla     r4, r10, r4, r9         ; a*64 + 128
-    mla     r4, r11, r8, r4         ; a*64 + b*192 + 1
-    mov     r4, r4, asr #8          ; (a*64 + b*192 + 1) >> 8
-    strb    r4, [dest], #1
-
-    add     r8, r8, #1              ; b + 1
-    add     r8, r8, r7              ; b + c + 1
-    mov     r8, r8, asr #1          ; (b + c + 1) >> 1
-    strb    r8, [dest], #1
-    strb    r7, [dest], #1
-
-    ldmia   sp!, {r4 - r11, pc}
-    ENDP    ;|vp8cx_horizontal_line_3_4_scale_c|
-
-
-;/****************************************************************************
-; *
-; *  ROUTINE       : vertical_band_3_4_scale_armv4
-; *
-; *  INPUTS        : unsigned char *dest    : Pointer to destination data.
-; *                  unsigned int dest_pitch : Stride of destination data.
-; *                  unsigned int dest_width : Width of destination data.
-; *
-; *  OUTPUTS       : None.
-; *
-; *  RETURNS       : void
-; *
-; *  FUNCTION      : Scales vertical band of pixels by scale 3 to 4. The
-; *                  height of the band scaled is 3-pixels.
-; *
-; *  SPECIAL NOTES : The routine uses the first line of the band below
-; *                  the current band.
-; *
-; ****************************************************************************/
-;void vertical_band_3_4_scale_armv4
-;(
-;   r0 = UINT8 *dest
-;   r1 = UINT32 dest_pitch
-;   r2 = UINT32 dest_width
-;)
-|vertical_band_3_4_scale_armv4| PROC
-    stmdb   sp!, {r4 - r11, lr}
-
-    ldr     r10, =64
-    ldr     r11, =192
-    mov     r9, #128
-
-;   ldr     r1,[r1]
-vl34_loop
-    mov     r3, src
-    ldrb    r4, [r3], r1            ; a = des [0]
-    ldrb    r5, [r3], r1            ; b = des [dest_pitch]
-    ldrb    r7, [r3], r1            ; c = des [dest_pitch*2]
-    add     lr, src, r1
-
-    mla     r4, r10, r4, r9         ; a*64 + 128
-    mla     r4, r11, r5, r4         ; a*64 + b*192 + 1
-
-    add     r5, r5, #1              ; b + 1
-    add     r5, r5, r7              ; b + c + 1
-    mov     r5, r5, asr #1          ; (b + c + 1) >> 1
-
-    mov     r4, r4, asr #8          ; (a*64 + b*192 + 1) >> 8
-    strb    r4, [lr], r1
-
-    ldrb    r4, [r3, r1]            ; a = des [dest_pitch*4]
-
-    strb    r5, [lr], r1
-
-    mla     r7, r11, r7, r9         ; c*192 + 128
-    mla     r7, r4, r10, r7         ; a*64 + b*192 + 128
-    mov     r7, r7, asr #8          ; (a*64 + b*192 + 128) >> 8
-
-    add     src, src, #1
-    subs    r2, r2, #1
-
-    strb    r7, [lr]
-
-    bne     vl34_loop
-
-    ldmia   sp!, {r4 - r11, pc}
-    ENDP    ;|vertical_band_3_4_scale_armv4|
-
-;/****************************************************************************
-; *
-; *  ROUTINE       : vp8cx_horizontal_line_1_2_scale_c
-; *
-; *  INPUTS        : const unsigned char *source : Pointer to source data.
-; *                  unsigned int source_width    : Stride of source.
-; *                  unsigned char *dest         : Pointer to destination data.
-; *                  unsigned int dest_width      : Stride of destination (NOT USED).
-; *
-; *  OUTPUTS       : None.
-; *
-; *  RETURNS       : void
-; *
-; *  FUNCTION      : Copies horizontal line of pixels from source to
-; *                  destination scaling up by 1 to 2.
-; *
-; *  SPECIAL NOTES : None.
-; *
-; ****************************************************************************/
-;void vp8cx_horizontal_line_1_2_scale_c
-;(
-;   const unsigned char *source,
-;   unsigned int source_width,
-;   unsigned char *dest,
-;   unsigned int dest_width
-;)
-|horizontal_line_1_2_scale_armv4| PROC
-    stmdb   sp!, {r4 - r5, lr}
-
-    sub     srcw, srcw, #1
-
-    ldrb    r3, [src], #1
-    ldrb    r4, [src], #1
-hl12_loop
-    subs    srcw, srcw, #1
-
-    add     r5, r3, r4
-    add     r5, r5, #1
-    mov     r5, r5, lsr #1
-
-    orr     r5, r3, r5, lsl #8
-    strh    r5, [dest], #2
-
-    mov     r3, r4
-
-    ldrneb  r4, [src], #1
-    bne     hl12_loop
-
-    orr     r5, r4, r4, lsl #8
-    strh    r5, [dest]
-
-    ldmia   sp!, {r4 - r5, pc}
-    ENDP    ;|vertical_band_3_5_scale_armv4|
-
-;/****************************************************************************
-; *
-; *  ROUTINE       : vp8cx_vertical_band_1_2_scale_c
-; *
-; *  INPUTS        : unsigned char *dest    : Pointer to destination data.
-; *                  unsigned int dest_pitch : Stride of destination data.
-; *                  unsigned int dest_width : Width of destination data.
-; *
-; *  OUTPUTS       : None.
-; *
-; *  RETURNS       : void
-; *
-; *  FUNCTION      : Scales vertical band of pixels by scale 1 to 2. The
-; *                  height of the band scaled is 1-pixel.
-; *
-; *  SPECIAL NOTES : The routine uses the first line of the band below
-; *                  the current band.
-; *
-; ****************************************************************************/
-;void vp8cx_vertical_band_1_2_scale_c
-;(
-;   r0 = UINT8 *dest
-;   r1 = UINT32 dest_pitch
-;   r2 = UINT32 dest_width
-;)
-|vertical_band_1_2_scale_armv4| PROC
-    stmdb   sp!, {r4 - r7, lr}
-
-    ldr     mask, =0xff00ff             ; mask for selection
-    ldr     lr, = 0x010001
-
-vl12_loop
-    mov     r3, src
-    ldr     r4, [r3], r1
-    ldr     r5, [r3, r1]
-
-    add     src, src, #4
-    subs    r2, r2, #4
-
-    and     r6, r4, mask
-    and     r7, r5, mask
-
-    add     r6, r7, r6
-    add     r6, r6, lr
-
-    and     r4, mask, r4, lsr #8
-    and     r5, mask, r5, lsr #8
-
-    mov     r6, r6, lsr #1
-    and     r6, r6, mask
-
-    add     r4, r5, r4
-    add     r4, r4, lr
-
-    mov     r4, r4, lsr #1
-    and     r4, r4, mask
-
-    orr     r5, r6, r4, lsl #8
-
-    str     r5, [r3]
-
-    bpl     vl12_loop
-
-    ldmia   sp!, {r4 - r7, pc}
-    ENDP    ;|vertical_band_3_5_scale_armv4|
-
-    END
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);
 }
diff --git a/vpx_scale/arm/scalesystemdependent.c b/vpx_scale/arm/scalesystemdependent.c
deleted file mode 100644
index d168d0510..000000000
--- a/vpx_scale/arm/scalesystemdependent.c
+++ /dev/null
@@ -1,97 +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.
- */
-
-
-#include "vpx_ports/config.h"
-#include "vpx_ports/arm.h"
-#include "vpx_scale/vpxscale.h"
-
-
-void (*vp8_yv12_extend_frame_borders_ptr)(YV12_BUFFER_CONFIG *ybf);
-extern void vp8_yv12_extend_frame_borders(YV12_BUFFER_CONFIG *ybf);
-extern void vp8_yv12_extend_frame_borders_neon(YV12_BUFFER_CONFIG *ybf);
-
-void (*vp8_yv12_copy_frame_yonly_ptr)(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-extern void vp8_yv12_copy_frame_yonly(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-extern void vp8_yv12_copy_frame_yonly_neon(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-
-void (*vp8_yv12_copy_frame_ptr)(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-extern void vp8_yv12_copy_frame(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-extern void vp8_yv12_copy_frame_neon(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-
-/****************************************************************************
-*  Imports
-*****************************************************************************/
-
-/****************************************************************************
- *
- *  ROUTINE       : vp8_scale_machine_specific_config
- *
- *  INPUTS        : UINT32 Version : Codec version number.
- *
- *  OUTPUTS       : None.
- *
- *  RETURNS       : void
- *
- *  FUNCTION      : Checks for machine specifc features such as MMX support
- *                  sets appropriate flags and function pointers.
- *
- *  SPECIAL NOTES : None.
- *
- ****************************************************************************/
-void vp8_scale_machine_specific_config() {
-#if HAVE_ARMV7 && CONFIG_RUNTIME_CPU_DETECT
-  int flags;
-#endif
-  /*
-  vp8_horizontal_line_1_2_scale        = horizontal_line_1_2_scale_armv4;
-  vp8_vertical_band_1_2_scale          = vertical_band_1_2_scale_armv4;
-  vp8_last_vertical_band_1_2_scale      = vp8cx_last_vertical_band_1_2_scale_c;
-  vp8_horizontal_line_3_5_scale        = horizontal_line_3_5_scale_armv4;
-  vp8_vertical_band_3_5_scale          = vertical_band_3_5_scale_armv4;
-  vp8_last_vertical_band_3_5_scale      = vp8cx_last_vertical_band_3_5_scale_c;
-  vp8_horizontal_line_3_4_scale        = horizontal_line_3_4_scale_armv4;
-  vp8_vertical_band_3_4_scale          = vertical_band_3_4_scale_armv4;
-  vp8_last_vertical_band_3_4_scale      = vp8cx_last_vertical_band_3_4_scale_c;
-  vp8_horizontal_line_2_3_scale        = horizontal_line_2_3_scale_armv4;
-  vp8_vertical_band_2_3_scale          = vertical_band_2_3_scale_armv4;
-  vp8_last_vertical_band_2_3_scale      = vp8cx_last_vertical_band_2_3_scale_c;
-  vp8_horizontal_line_4_5_scale        = horizontal_line_4_5_scale_armv4;
-  vp8_vertical_band_4_5_scale          = vertical_band_4_5_scale_armv4;
-  vp8_last_vertical_band_4_5_scale      = vp8cx_last_vertical_band_4_5_scale_c;
-
-  vp8_vertical_band_5_4_scale           = vp8cx_vertical_band_5_4_scale_c;
-  vp8_vertical_band_5_3_scale           = vp8cx_vertical_band_5_3_scale_c;
-  vp8_vertical_band_2_1_scale           = vp8cx_vertical_band_2_1_scale_c;
-  vp8_vertical_band_2_1_scale_i         = vp8cx_vertical_band_2_1_scale_i_c;
-  vp8_horizontal_line_2_1_scale         = vp8cx_horizontal_line_2_1_scale_c;
-  vp8_horizontal_line_5_3_scale         = vp8cx_horizontal_line_5_3_scale_c;
-  vp8_horizontal_line_5_4_scale         = vp8cx_horizontal_line_5_4_scale_c;
-  */
-
-#if !HAVE_ARMV7 || CONFIG_RUNTIME_CPU_DETECT
-  vp8_yv12_extend_frame_borders_ptr      = vp8_yv12_extend_frame_borders;
-  vp8_yv12_copy_frame_yonly_ptr          = vp8_yv12_copy_frame_yonly;
-  vp8_yv12_copy_frame_ptr           = vp8_yv12_copy_frame;
-#endif
-#if HAVE_ARMV7
-#if CONFIG_RUNTIME_CPU_DETECT
-  flags = arm_cpu_caps();
-  if (flags & HAS_NEON)
-#endif
-  {
-#if VP8BORDERINPIXELS == 32
-    vp8_yv12_extend_frame_borders_ptr = vp8_yv12_extend_frame_borders_neon;
-    vp8_yv12_copy_frame_yonly_ptr     = vp8_yv12_copy_frame_yonly_neon;
-    vp8_yv12_copy_frame_ptr           = vp8_yv12_copy_frame_neon;
-#endif
-  }
-#endif
-}
diff --git a/vpx_scale/generic/gen_scalers.c b/vpx_scale/generic/gen_scalers.c
index bb1178669..60c21fb3a 100644
--- a/vpx_scale/generic/gen_scalers.c
+++ b/vpx_scale/generic/gen_scalers.c
@@ -17,7 +17,7 @@
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_horizontal_line_4_5_scale_c
+ *  ROUTINE       : vp8_horizontal_line_4_5_scale_c
  *
  *  INPUTS        : const unsigned char *source : Pointer to source data.
  *                  unsigned int source_width    : Stride of source.
@@ -34,13 +34,10 @@
  *  SPECIAL NOTES : None.
  *
  ****************************************************************************/
-void vp8cx_horizontal_line_4_5_scale_c
-(
-  const unsigned char *source,
-  unsigned int source_width,
-  unsigned char *dest,
-  unsigned int dest_width
-) {
+void vp8_horizontal_line_4_5_scale_c(const unsigned char *source,
+                                     unsigned int source_width,
+                                     unsigned char *dest,
+                                     unsigned int dest_width) {
   unsigned i;
   unsigned int a, b, c;
   unsigned char *des = dest;
@@ -78,7 +75,7 @@ void vp8cx_horizontal_line_4_5_scale_c
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_vertical_band_4_5_scale_c
+ *  ROUTINE       : vp8_vertical_band_4_5_scale_c
  *
  *  INPUTS        : unsigned char *dest    : Pointer to destination data.
  *                  unsigned int dest_pitch : Stride of destination data.
@@ -95,7 +92,9 @@ void vp8cx_horizontal_line_4_5_scale_c
  *                  the current band.
  *
  ****************************************************************************/
-void vp8cx_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_vertical_band_4_5_scale_c(unsigned char *dest,
+                                   unsigned int dest_pitch,
+                                   unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c, d;
   unsigned char *des = dest;
@@ -122,7 +121,7 @@ void vp8cx_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest_pitc
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_last_vertical_band_4_5_scale_c
+ *  ROUTINE       : vp8_last_vertical_band_4_5_scale_c
  *
  *  INPUTS        : unsigned char *dest    : Pointer to destination data.
  *                  unsigned int dest_pitch : Stride of destination data.
@@ -140,7 +139,9 @@ void vp8cx_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest_pitc
  *                  last band.
  *
  ****************************************************************************/
-void vp8cx_last_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_last_vertical_band_4_5_scale_c(unsigned char *dest,
+                                        unsigned int dest_pitch,
+                                        unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c, d;
   unsigned char *des = dest;
@@ -166,7 +167,7 @@ void vp8cx_last_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_horizontal_line_2_3_scale_c
+ *  ROUTINE       : vp8_horizontal_line_2_3_scale_c
  *
  *  INPUTS        : const unsigned char *source : Pointer to source data.
  *                  unsigned int source_width    : Stride of source.
@@ -184,13 +185,10 @@ void vp8cx_last_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest
  *
  *
  ****************************************************************************/
-void vp8cx_horizontal_line_2_3_scale_c
-(
-  const unsigned char *source,
-  unsigned int source_width,
-  unsigned char *dest,
-  unsigned int dest_width
-) {
+void vp8_horizontal_line_2_3_scale_c(const unsigned char *source,
+                                     unsigned int source_width,
+                                     unsigned char *dest,
+                                     unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c;
   unsigned char *des = dest;
@@ -221,7 +219,7 @@ void vp8cx_horizontal_line_2_3_scale_c
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_vertical_band_2_3_scale_c
+ *  ROUTINE       : vp8_vertical_band_2_3_scale_c
  *
  *  INPUTS        : unsigned char *dest    : Pointer to destination data.
  *                  unsigned int dest_pitch : Stride of destination data.
@@ -238,7 +236,9 @@ void vp8cx_horizontal_line_2_3_scale_c
  *                  the current band.
  *
  ****************************************************************************/
-void vp8cx_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_vertical_band_2_3_scale_c(unsigned char *dest,
+                                   unsigned int dest_pitch,
+                                   unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c;
   unsigned char *des = dest;
@@ -256,7 +256,7 @@ void vp8cx_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest_pitc
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_last_vertical_band_2_3_scale_c
+ *  ROUTINE       : vp8_last_vertical_band_2_3_scale_c
  *
  *  INPUTS        : unsigned char *dest    : Pointer to destination data.
  *                  unsigned int dest_pitch : Stride of destination data.
@@ -274,7 +274,9 @@ void vp8cx_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest_pitc
  *                  last band.
  *
  ****************************************************************************/
-void vp8cx_last_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_last_vertical_band_2_3_scale_c(unsigned char *dest,
+                                        unsigned int dest_pitch,
+                                        unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b;
   unsigned char *des = dest;
@@ -291,7 +293,7 @@ void vp8cx_last_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_horizontal_line_3_5_scale_c
+ *  ROUTINE       : vp8_horizontal_line_3_5_scale_c
  *
  *  INPUTS        : const unsigned char *source : Pointer to source data.
  *                  unsigned int source_width    : Stride of source.
@@ -309,13 +311,10 @@ void vp8cx_last_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest
  *
  *
  ****************************************************************************/
-void vp8cx_horizontal_line_3_5_scale_c
-(
-  const unsigned char *source,
-  unsigned int source_width,
-  unsigned char *dest,
-  unsigned int dest_width
-) {
+void vp8_horizontal_line_3_5_scale_c(const unsigned char *source,
+                                     unsigned int source_width,
+                                     unsigned char *dest,
+                                     unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c;
   unsigned char *des = dest;
@@ -354,7 +353,7 @@ void vp8cx_horizontal_line_3_5_scale_c
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_vertical_band_3_5_scale_c
+ *  ROUTINE       : vp8_vertical_band_3_5_scale_c
  *
  *  INPUTS        : unsigned char *dest    : Pointer to destination data.
  *                  unsigned int dest_pitch : Stride of destination data.
@@ -371,7 +370,9 @@ void vp8cx_horizontal_line_3_5_scale_c
  *                  the current band.
  *
  ****************************************************************************/
-void vp8cx_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_vertical_band_3_5_scale_c(unsigned char *dest,
+                                   unsigned int dest_pitch,
+                                   unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c;
   unsigned char *des = dest;
@@ -395,7 +396,7 @@ void vp8cx_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest_pitc
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_last_vertical_band_3_5_scale_c
+ *  ROUTINE       : vp8_last_vertical_band_3_5_scale_c
  *
  *  INPUTS        : unsigned char *dest    : Pointer to destination data.
  *                  unsigned int dest_pitch : Stride of destination data.
@@ -413,7 +414,9 @@ void vp8cx_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest_pitc
  *                  last band.
  *
  ****************************************************************************/
-void vp8cx_last_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_last_vertical_band_3_5_scale_c(unsigned char *dest,
+                                        unsigned int dest_pitch,
+                                        unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c;
   unsigned char *des = dest;
@@ -437,7 +440,7 @@ void vp8cx_last_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_horizontal_line_3_4_scale_c
+ *  ROUTINE       : vp8_horizontal_line_3_4_scale_c
  *
  *  INPUTS        : const unsigned char *source : Pointer to source data.
  *                  unsigned int source_width    : Stride of source.
@@ -455,13 +458,10 @@ void vp8cx_last_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest
  *
  *
  ****************************************************************************/
-void vp8cx_horizontal_line_3_4_scale_c
-(
-  const unsigned char *source,
-  unsigned int source_width,
-  unsigned char *dest,
-  unsigned int dest_width
-) {
+void vp8_horizontal_line_3_4_scale_c(const unsigned char *source,
+                                     unsigned int source_width,
+                                     unsigned char *dest,
+                                     unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c;
   unsigned char *des = dest;
@@ -497,7 +497,7 @@ void vp8cx_horizontal_line_3_4_scale_c
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_vertical_band_3_4_scale_c
+ *  ROUTINE       : vp8_vertical_band_3_4_scale_c
  *
  *  INPUTS        : unsigned char *dest    : Pointer to destination data.
  *                  unsigned int dest_pitch : Stride of destination data.
@@ -514,7 +514,9 @@ void vp8cx_horizontal_line_3_4_scale_c
  *                  the current band.
  *
  ****************************************************************************/
-void vp8cx_vertical_band_3_4_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_vertical_band_3_4_scale_c(unsigned char *dest,
+                                   unsigned int dest_pitch,
+                                   unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c;
   unsigned char *des = dest;
@@ -537,7 +539,7 @@ void vp8cx_vertical_band_3_4_scale_c(unsigned char *dest, unsigned int dest_pitc
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_last_vertical_band_3_4_scale_c
+ *  ROUTINE       : vp8_last_vertical_band_3_4_scale_c
  *
  *  INPUTS        : unsigned char *dest    : Pointer to destination data.
  *                  unsigned int dest_pitch : Stride of destination data.
@@ -555,7 +557,9 @@ void vp8cx_vertical_band_3_4_scale_c(unsigned char *dest, unsigned int dest_pitc
  *                  last band.
  *
  ****************************************************************************/
-void vp8cx_last_vertical_band_3_4_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_last_vertical_band_3_4_scale_c(unsigned char *dest,
+                                        unsigned int dest_pitch,
+                                        unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c;
   unsigned char *des = dest;
@@ -578,7 +582,7 @@ void vp8cx_last_vertical_band_3_4_scale_c(unsigned char *dest, unsigned int dest
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_horizontal_line_1_2_scale_c
+ *  ROUTINE       : vp8_horizontal_line_1_2_scale_c
  *
  *  INPUTS        : const unsigned char *source : Pointer to source data.
  *                  unsigned int source_width    : Stride of source.
@@ -595,13 +599,10 @@ void vp8cx_last_vertical_band_3_4_scale_c(unsigned char *dest, unsigned int dest
  *  SPECIAL NOTES : None.
  *
  ****************************************************************************/
-void vp8cx_horizontal_line_1_2_scale_c
-(
-  const unsigned char *source,
-  unsigned int source_width,
-  unsigned char *dest,
-  unsigned int dest_width
-) {
+void vp8_horizontal_line_1_2_scale_c(const unsigned char *source,
+                                     unsigned int source_width,
+                                     unsigned char *dest,
+                                     unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b;
   unsigned char *des = dest;
@@ -625,7 +626,7 @@ void vp8cx_horizontal_line_1_2_scale_c
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_vertical_band_1_2_scale_c
+ *  ROUTINE       : vp8_vertical_band_1_2_scale_c
  *
  *  INPUTS        : unsigned char *dest    : Pointer to destination data.
  *                  unsigned int dest_pitch : Stride of destination data.
@@ -642,7 +643,9 @@ void vp8cx_horizontal_line_1_2_scale_c
  *                  the current band.
  *
  ****************************************************************************/
-void vp8cx_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_vertical_band_1_2_scale_c(unsigned char *dest,
+                                   unsigned int dest_pitch,
+                                   unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b;
   unsigned char *des = dest;
@@ -659,7 +662,7 @@ void vp8cx_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest_pitc
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_last_vertical_band_1_2_scale_c
+ *  ROUTINE       : vp8_last_vertical_band_1_2_scale_c
  *
  *  INPUTS        : unsigned char *dest    : Pointer to destination data.
  *                  unsigned int dest_pitch : Stride of destination data.
@@ -677,7 +680,9 @@ void vp8cx_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest_pitc
  *                  last band.
  *
  ****************************************************************************/
-void vp8cx_last_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_last_vertical_band_1_2_scale_c(unsigned char *dest,
+                                        unsigned int dest_pitch,
+                                        unsigned int dest_width) {
   unsigned int i;
   unsigned char *des = dest;
 
@@ -693,7 +698,7 @@ void vp8cx_last_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_horizontal_line_4_5_scale_c
+ *  ROUTINE       : vp8_horizontal_line_4_5_scale_c
  *
  *  INPUTS        : const unsigned char *source : Pointer to source data.
  *                  unsigned int source_width    : Stride of source.
@@ -710,13 +715,10 @@ void vp8cx_last_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest
  *  SPECIAL NOTES : None.
  *
  ****************************************************************************/
-void vp8cx_horizontal_line_5_4_scale_c
-(
-  const unsigned char *source,
-  unsigned int source_width,
-  unsigned char *dest,
-  unsigned int dest_width
-) {
+void vp8_horizontal_line_5_4_scale_c(const unsigned char *source,
+                                     unsigned int source_width,
+                                     unsigned char *dest,
+                                     unsigned int dest_width) {
   unsigned i;
   unsigned int a, b, c, d, e;
   unsigned char *des = dest;
@@ -744,7 +746,11 @@ void vp8cx_horizontal_line_5_4_scale_c
 
 
 
-void vp8cx_vertical_band_5_4_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_vertical_band_5_4_scale_c(unsigned char *source,
+                                   unsigned int src_pitch,
+                                   unsigned char *dest,
+                                   unsigned int dest_pitch,
+                                   unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c, d, e;
   unsigned char *des = dest;
@@ -772,7 +778,7 @@ void vp8cx_vertical_band_5_4_scale_c(unsigned char *source, unsigned int src_pit
 
 /*7***************************************************************************
  *
- *  ROUTINE       : vp8cx_horizontal_line_3_5_scale_c
+ *  ROUTINE       : vp8_horizontal_line_3_5_scale_c
  *
  *  INPUTS        : const unsigned char *source : Pointer to source data.
  *                  unsigned int source_width    : Stride of source.
@@ -790,13 +796,10 @@ void vp8cx_vertical_band_5_4_scale_c(unsigned char *source, unsigned int src_pit
  *
  *
  ****************************************************************************/
-void vp8cx_horizontal_line_5_3_scale_c
-(
-  const unsigned char *source,
-  unsigned int source_width,
-  unsigned char *dest,
-  unsigned int dest_width
-) {
+void vp8_horizontal_line_5_3_scale_c(const unsigned char *source,
+                                     unsigned int source_width,
+                                     unsigned char *dest,
+                                     unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c, d, e;
   unsigned char *des = dest;
@@ -821,7 +824,11 @@ void vp8cx_horizontal_line_5_3_scale_c
 
 }
 
-void vp8cx_vertical_band_5_3_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_vertical_band_5_3_scale_c(unsigned char *source,
+                                   unsigned int src_pitch,
+                                   unsigned char *dest,
+                                   unsigned int dest_pitch,
+                                   unsigned int dest_width) {
   unsigned int i;
   unsigned int a, b, c, d, e;
   unsigned char *des = dest;
@@ -847,7 +854,7 @@ void vp8cx_vertical_band_5_3_scale_c(unsigned char *source, unsigned int src_pit
 
 /****************************************************************************
  *
- *  ROUTINE       : vp8cx_horizontal_line_1_2_scale_c
+ *  ROUTINE       : vp8_horizontal_line_1_2_scale_c
  *
  *  INPUTS        : const unsigned char *source : Pointer to source data.
  *                  unsigned int source_width    : Stride of source.
@@ -864,13 +871,10 @@ void vp8cx_vertical_band_5_3_scale_c(unsigned char *source, unsigned int src_pit
  *  SPECIAL NOTES : None.
  *
  ****************************************************************************/
-void vp8cx_horizontal_line_2_1_scale_c
-(
-  const unsigned char *source,
-  unsigned int source_width,
-  unsigned char *dest,
-  unsigned int dest_width
-) {
+void vp8_horizontal_line_2_1_scale_c(const unsigned char *source,
+                                     unsigned int source_width,
+                                     unsigned char *dest,
+                                     unsigned int dest_width) {
   unsigned int i;
   unsigned int a;
   unsigned char *des = dest;
@@ -884,17 +888,23 @@ void vp8cx_horizontal_line_2_1_scale_c
     src += 2;
     des += 1;
   }
-
-
-
 }
-void vp8cx_vertical_band_2_1_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+
+void vp8_vertical_band_2_1_scale_c(unsigned char *source,
+                                   unsigned int src_pitch,
+                                   unsigned char *dest,
+                                   unsigned int dest_pitch,
+                                   unsigned int dest_width) {
   (void) dest_pitch;
   (void) src_pitch;
   vpx_memcpy(dest, source, dest_width);
 }
 
-void vp8cx_vertical_band_2_1_scale_i_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) {
+void vp8_vertical_band_2_1_scale_i_c(unsigned char *source,
+                                     unsigned int src_pitch,
+                                     unsigned char *dest,
+                                     unsigned int dest_pitch,
+                                     unsigned int dest_width) {
   int i;
   int temp;
   int width = dest_width;
@@ -909,5 +919,4 @@ void vp8cx_vertical_band_2_1_scale_i_c(unsigned char *source, unsigned int src_p
     temp >>= 4;
     dest[i] = (unsigned char)(temp);
   }
-
 }
diff --git a/vpx_scale/generic/scalesystemdependent.c b/vpx_scale/generic/scalesystemdependent.c
deleted file mode 100644
index b9d6de4b1..000000000
--- a/vpx_scale/generic/scalesystemdependent.c
+++ /dev/null
@@ -1,50 +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.
- */
-
-
-#include "vpx_ports/config.h"
-#include "vpx_scale/vpxscale.h"
-
-
-void (*vp8_yv12_extend_frame_borders_ptr)(YV12_BUFFER_CONFIG *ybf);
-extern void vp8_yv12_extend_frame_borders(YV12_BUFFER_CONFIG *ybf);
-
-void (*vp8_yv12_copy_frame_yonly_ptr)(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-extern void vp8_yv12_copy_frame_yonly(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-
-void (*vp8_yv12_copy_frame_ptr)(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-extern void vp8_yv12_copy_frame(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-
-/****************************************************************************
-*  Imports
-*****************************************************************************/
-
-/****************************************************************************
- *
- *  ROUTINE       : vp8_scale_machine_specific_config
- *
- *  INPUTS        : UINT32 Version : Codec version number.
- *
- *  OUTPUTS       : None.
- *
- *  RETURNS       : void
- *
- *  FUNCTION      : Checks for machine specifc features such as MMX support
- *                  sets appropriate flags and function pointers.
- *
- *  SPECIAL NOTES : None.
- *
- ****************************************************************************/
-void vp8_scale_machine_specific_config() {
-  vp8_yv12_extend_frame_borders_ptr      = vp8_yv12_extend_frame_borders;
-  vp8_yv12_copy_frame_yonly_ptr          = vp8_yv12_copy_frame_yonly;
-  vp8_yv12_copy_frame_ptr           = vp8_yv12_copy_frame;
-
-}
diff --git a/vpx_scale/generic/vpxscale.c b/vpx_scale/generic/vpxscale.c
index 82485c73b..7de85ca34 100644
--- a/vpx_scale/generic/vpxscale.c
+++ b/vpx_scale/generic/vpxscale.c
@@ -20,41 +20,11 @@
 /****************************************************************************
 *  Header Files
 ****************************************************************************/
+#include "./vpx_rtcd.h"
 #include "vpx_mem/vpx_mem.h"
 #include "vpx_scale/yv12config.h"
 #include "vpx_scale/scale_mode.h"
 
-/****************************************************************************
-*  Exports
-****************************************************************************/
-#ifndef VPX_NO_GLOBALS
-void (*vp8_vertical_band_4_5_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_last_vertical_band_4_5_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_vertical_band_2_3_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_last_vertical_band_2_3_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_vertical_band_3_5_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_last_vertical_band_3_5_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_vertical_band_3_4_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_last_vertical_band_3_4_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_horizontal_line_1_2_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width) = 0;
-void (*vp8_horizontal_line_3_5_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width) = 0;
-void (*vp8_horizontal_line_3_4_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width) = 0;
-void (*vp8_horizontal_line_2_3_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width) = 0;
-void (*vp8_horizontal_line_4_5_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width) = 0;
-void (*vp8_vertical_band_1_2_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_last_vertical_band_1_2_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-
-void (*vp8_vertical_band_5_4_scale)(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_vertical_band_5_3_scale)(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_vertical_band_2_1_scale)(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_vertical_band_2_1_scale_i)(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width) = 0;
-void (*vp8_horizontal_line_2_1_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width) = 0;
-void (*vp8_horizontal_line_5_3_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width) = 0;
-void (*vp8_horizontal_line_5_4_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width) = 0;
-#else
-# include "vpxscale_nofp.h"
-#endif
-
 typedef struct {
   int     expanded_frame_width;
   int     expanded_frame_height;
diff --git a/vpx_scale/generic/yv12extend.c b/vpx_scale/generic/yv12extend.c
index cac8ae9b4..247078c0c 100644
--- a/vpx_scale/generic/yv12extend.c
+++ b/vpx_scale/generic/yv12extend.c
@@ -21,7 +21,7 @@
  *
  ****************************************************************************/
 void
-vp8_yv12_extend_frame_borders(YV12_BUFFER_CONFIG *ybf) {
+vp8_yv12_extend_frame_borders_c(YV12_BUFFER_CONFIG *ybf) {
   int i;
   unsigned char *src_ptr1, *src_ptr2;
   unsigned char *dest_ptr1, *dest_ptr2;
@@ -139,7 +139,7 @@ vp8_yv12_extend_frame_borders(YV12_BUFFER_CONFIG *ybf) {
 
 
 static void
-extend_frame_borders_yonly(YV12_BUFFER_CONFIG *ybf) {
+extend_frame_borders_yonly_c(YV12_BUFFER_CONFIG *ybf) {
   int i;
   unsigned char *src_ptr1, *src_ptr2;
   unsigned char *dest_ptr1, *dest_ptr2;
@@ -211,7 +211,8 @@ extend_frame_borders_yonly(YV12_BUFFER_CONFIG *ybf) {
  *
  ****************************************************************************/
 void
-vp8_yv12_copy_frame(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc) {
+vp8_yv12_copy_frame_c(YV12_BUFFER_CONFIG *src_ybc,
+                      YV12_BUFFER_CONFIG *dst_ybc) {
   int row;
   unsigned char *source, *dest;
 
@@ -242,11 +243,11 @@ vp8_yv12_copy_frame(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc) {
     dest   += dst_ybc->uv_stride;
   }
 
-  vp8_yv12_extend_frame_borders_ptr(dst_ybc);
+  vp8_yv12_extend_frame_borders_c(dst_ybc);
 }
 
-void
-vp8_yv12_copy_frame_yonly(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc) {
+void vp8_yv12_copy_y_c(YV12_BUFFER_CONFIG *src_ybc,
+                       YV12_BUFFER_CONFIG *dst_ybc) {
   int row;
   unsigned char *source, *dest;
 
@@ -259,6 +260,4 @@ vp8_yv12_copy_frame_yonly(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_y
     source += src_ybc->y_stride;
     dest   += dst_ybc->y_stride;
   }
-
-  extend_frame_borders_yonly(dst_ybc);
 }
diff --git a/vpx_scale/include/arm/vpxscale_nofp.h b/vpx_scale/include/arm/vpxscale_nofp.h
deleted file mode 100644
index 3e1a9fa83..000000000
--- a/vpx_scale/include/arm/vpxscale_nofp.h
+++ /dev/null
@@ -1,68 +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.
- */
-
-
-void  vp8cx_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_3_4_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_3_4_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_horizontal_line_1_2_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_3_4_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_3_5_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_2_3_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_4_5_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-
-void  vp8cx_vertical_band_5_4_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_5_3_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_2_1_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_2_1_scale_i_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_horizontal_line_2_1_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_5_3_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_5_4_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-
-void horizontal_line_4_5_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void horizontal_line_2_3_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void horizontal_line_3_5_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void horizontal_line_3_4_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void horizontal_line_1_2_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void vertical_band_4_5_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vertical_band_2_3_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vertical_band_3_5_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vertical_band_3_4_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vertical_band_1_2_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-
-#define vp8_vertical_band_4_5_scale     vertical_band_4_5_scale_armv4
-#define vp8_last_vertical_band_4_5_scale vp8cx_last_vertical_band_4_5_scale_c
-#define vp8_vertical_band_2_3_scale     vertical_band_2_3_scale_armv4
-#define vp8_last_vertical_band_2_3_scale vp8cx_last_vertical_band_2_3_scale_c
-#define vp8_vertical_band_3_5_scale     vertical_band_3_5_scale_armv4
-#define vp8_last_vertical_band_3_5_scale vp8cx_last_vertical_band_3_5_scale_c
-#define vp8_vertical_band_3_4_scale     vertical_band_3_4_scale_armv4
-#define vp8_last_vertical_band_3_4_scale vp8cx_last_vertical_band_3_4_scale_c
-#define vp8_horizontal_line_1_2_scale   horizontal_line_1_2_scale_armv4
-#define vp8_horizontal_line_3_5_scale   horizontal_line_3_5_scale_armv4
-#define vp8_horizontal_line_3_4_scale   horizontal_line_3_4_scale_armv4
-#define vp8_horizontal_line_4_5_scale   horizontal_line_4_5_scale_armv4
-#define vp8_horizontal_line_2_3_scale   horizontal_line_2_3_scale_armv4
-#define vp8_vertical_band_1_2_scale     vertical_band_1_2_scale_armv4
-#define vp8_last_vertical_band_1_2_scale vp8cx_last_vertical_band_1_2_scale_c
-#define vp8_vertical_band_5_4_scale     vp8cx_vertical_band_5_4_scale_c
-#define vp8_vertical_band_5_3_scale     vp8cx_vertical_band_5_3_scale_c
-#define vp8_vertical_band_2_1_scale     vp8cx_vertical_band_2_1_scale_c
-#define vp8_vertical_band_2_1_scale_i   vp8cx_vertical_band_2_1_scale_i_c
-#define vp8_horizontal_line_2_1_scale   vp8cx_horizontal_line_2_1_scale_c
-#define vp8_horizontal_line_5_3_scale   vp8cx_horizontal_line_5_3_scale_c
-#define vp8_horizontal_line_5_4_scale   vp8cx_horizontal_line_5_4_scale_c
diff --git a/vpx_scale/include/generic/vpxscale_nofp.h b/vpx_scale/include/generic/vpxscale_nofp.h
deleted file mode 100644
index 7b8205a1b..000000000
--- a/vpx_scale/include/generic/vpxscale_nofp.h
+++ /dev/null
@@ -1,51 +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.
- */
-
-
-void  vp8cx_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_horizontal_line_1_2_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_3_5_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_2_3_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_4_5_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-
-void  vp8cx_vertical_band_5_4_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_5_3_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_2_1_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_2_1_scale_i_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_horizontal_line_2_1_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_5_3_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_5_4_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-
-#define vp8_vertical_band_4_5_scale     vp8cx_vertical_band_4_5_scale_c
-#define vp8_last_vertical_band_4_5_scale vp8cx_last_vertical_band_4_5_scale_c
-#define vp8_vertical_band_2_3_scale     vp8cx_vertical_band_2_3_scale_c
-#define vp8_last_vertical_band_2_3_scale vp8cx_last_vertical_band_2_3_scale_c
-#define vp8_vertical_band_3_5_scale     vp8cx_vertical_band_3_5_scale_c
-#define vp8_last_vertical_band_3_5_scale vp8cx_last_vertical_band_3_5_scale_c
-#define vp8_horizontal_line_1_2_scale   vp8cx_horizontal_line_1_2_scale_c
-#define vp8_horizontal_line_3_5_scale   vp8cx_horizontal_line_3_5_scale_c
-#define vp8_horizontal_line_4_5_scale   vp8cx_horizontal_line_4_5_scale_c
-#define vp8_horizontal_line_2_3_scale   vp8cx_horizontal_line_2_3_scale_c
-#define vp8_vertical_band_1_2_scale     vp8cx_vertical_band_1_2_scale_c
-#define vp8_last_vertical_band_1_2_scale vp8cx_last_vertical_band_1_2_scale_c
-#define vp8_vertical_band_5_4_scale     vp8cx_vertical_band_5_4_scale_c
-#define vp8_vertical_band_5_3_scale     vp8cx_vertical_band_5_3_scale_c
-#define vp8_vertical_band_2_1_scale     vp8cx_vertical_band_2_1_scale_c
-#define vp8_vertical_band_2_1_scale_i   vp8cx_vertical_band_2_1_scale_i_c
-#define vp8_horizontal_line_2_1_scale   vp8cx_horizontal_line_2_1_scale_c
-#define vp8_horizontal_line_5_3_scale   vp8cx_horizontal_line_5_3_scale_c
-#define vp8_horizontal_line_5_4_scale   vp8cx_horizontal_line_5_4_scale_c
diff --git a/vpx_scale/include/symbian/vpxscale_nofp.h b/vpx_scale/include/symbian/vpxscale_nofp.h
deleted file mode 100644
index 3e1a9fa83..000000000
--- a/vpx_scale/include/symbian/vpxscale_nofp.h
+++ /dev/null
@@ -1,68 +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.
- */
-
-
-void  vp8cx_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_3_4_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_3_4_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_horizontal_line_1_2_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_3_4_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_3_5_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_2_3_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_4_5_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_last_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-
-void  vp8cx_vertical_band_5_4_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_5_3_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_2_1_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_vertical_band_2_1_scale_i_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void  vp8cx_horizontal_line_2_1_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_5_3_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void  vp8cx_horizontal_line_5_4_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-
-void horizontal_line_4_5_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void horizontal_line_2_3_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void horizontal_line_3_5_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void horizontal_line_3_4_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void horizontal_line_1_2_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void vertical_band_4_5_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vertical_band_2_3_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vertical_band_3_5_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vertical_band_3_4_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vertical_band_1_2_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-
-#define vp8_vertical_band_4_5_scale     vertical_band_4_5_scale_armv4
-#define vp8_last_vertical_band_4_5_scale vp8cx_last_vertical_band_4_5_scale_c
-#define vp8_vertical_band_2_3_scale     vertical_band_2_3_scale_armv4
-#define vp8_last_vertical_band_2_3_scale vp8cx_last_vertical_band_2_3_scale_c
-#define vp8_vertical_band_3_5_scale     vertical_band_3_5_scale_armv4
-#define vp8_last_vertical_band_3_5_scale vp8cx_last_vertical_band_3_5_scale_c
-#define vp8_vertical_band_3_4_scale     vertical_band_3_4_scale_armv4
-#define vp8_last_vertical_band_3_4_scale vp8cx_last_vertical_band_3_4_scale_c
-#define vp8_horizontal_line_1_2_scale   horizontal_line_1_2_scale_armv4
-#define vp8_horizontal_line_3_5_scale   horizontal_line_3_5_scale_armv4
-#define vp8_horizontal_line_3_4_scale   horizontal_line_3_4_scale_armv4
-#define vp8_horizontal_line_4_5_scale   horizontal_line_4_5_scale_armv4
-#define vp8_horizontal_line_2_3_scale   horizontal_line_2_3_scale_armv4
-#define vp8_vertical_band_1_2_scale     vertical_band_1_2_scale_armv4
-#define vp8_last_vertical_band_1_2_scale vp8cx_last_vertical_band_1_2_scale_c
-#define vp8_vertical_band_5_4_scale     vp8cx_vertical_band_5_4_scale_c
-#define vp8_vertical_band_5_3_scale     vp8cx_vertical_band_5_3_scale_c
-#define vp8_vertical_band_2_1_scale     vp8cx_vertical_band_2_1_scale_c
-#define vp8_vertical_band_2_1_scale_i   vp8cx_vertical_band_2_1_scale_i_c
-#define vp8_horizontal_line_2_1_scale   vp8cx_horizontal_line_2_1_scale_c
-#define vp8_horizontal_line_5_3_scale   vp8cx_horizontal_line_5_3_scale_c
-#define vp8_horizontal_line_5_4_scale   vp8cx_horizontal_line_5_4_scale_c
diff --git a/vpx_scale/include/vpxscale_nofp.h b/vpx_scale/include/vpxscale_nofp.h
deleted file mode 100644
index a704bd92c..000000000
--- a/vpx_scale/include/vpxscale_nofp.h
+++ /dev/null
@@ -1,16 +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.
- */
-
-
-#if defined(__S60_V20__) || defined(__SYMBIAN32__) && !defined(__WINS__)
-#include "symbian\vpxscale_nofp.h"
-#else
-#include "generic\vpxscale_nofp.h"
-#endif
diff --git a/vpx_scale/vpx_scale.mk b/vpx_scale/vpx_scale.mk
index 9680ded3c..dc89478bd 100644
--- a/vpx_scale/vpx_scale.mk
+++ b/vpx_scale/vpx_scale.mk
@@ -1,23 +1,18 @@
 SCALE_SRCS-yes += vpx_scale.mk
 SCALE_SRCS-yes += scale_mode.h
-SCALE_SRCS-yes += yv12extend.h
 SCALE_SRCS-yes += yv12config.h
 SCALE_SRCS-yes += vpxscale.h
 SCALE_SRCS-yes += generic/vpxscale.c
 SCALE_SRCS-yes += generic/yv12config.c
 SCALE_SRCS-yes += generic/yv12extend.c
-SCALE_SRCS-yes += generic/scalesystemdependent.c
+SCALE_SRCS-yes += generic/yv12extend_generic.h
 SCALE_SRCS-$(CONFIG_SPATIAL_RESAMPLING) += generic/gen_scalers.c
 
-#arm
-SCALE_SRCS-$(HAVE_ARMV7)         += arm/scalesystemdependent.c
-SCALE_SRCS_REMOVE-$(HAVE_ARMV7)  += generic/scalesystemdependent.c
-
 #neon
-SCALE_SRCS-$(HAVE_ARMV7)  += arm/neon/vp8_vpxyv12_copyframe_func_neon$(ASM)
-SCALE_SRCS-$(HAVE_ARMV7)  += arm/neon/vp8_vpxyv12_copyframeyonly_neon$(ASM)
-SCALE_SRCS-$(HAVE_ARMV7)  += arm/neon/vp8_vpxyv12_copysrcframe_func_neon$(ASM)
-SCALE_SRCS-$(HAVE_ARMV7)  += arm/neon/vp8_vpxyv12_extendframeborders_neon$(ASM)
-SCALE_SRCS-$(HAVE_ARMV7)  += arm/neon/yv12extend_arm.c
+SCALE_SRCS-$(HAVE_NEON)  += arm/neon/vp8_vpxyv12_copyframe_func_neon$(ASM)
+SCALE_SRCS-$(HAVE_NEON)  += arm/neon/vp8_vpxyv12_copy_y_neon$(ASM)
+SCALE_SRCS-$(HAVE_NEON)  += arm/neon/vp8_vpxyv12_copysrcframe_func_neon$(ASM)
+SCALE_SRCS-$(HAVE_NEON)  += arm/neon/vp8_vpxyv12_extendframeborders_neon$(ASM)
+SCALE_SRCS-$(HAVE_NEON)  += arm/neon/yv12extend_arm.c
 
 SCALE_SRCS-no += $(SCALE_SRCS_REMOVE-yes)
diff --git a/vpx_scale/vpxscale.h b/vpx_scale/vpxscale.h
index 899a50a89..3c2194d65 100644
--- a/vpx_scale/vpxscale.h
+++ b/vpx_scale/vpxscale.h
@@ -13,102 +13,25 @@
 #define VPXSCALE_H
 
 #include "vpx_scale/yv12config.h"
-void vp8cx_horizontal_line_4_5_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void vp8cx_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_last_vertical_band_4_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_horizontal_line_2_3_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void vp8cx_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_last_vertical_band_2_3_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_horizontal_line_3_5_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void vp8cx_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_last_vertical_band_3_5_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_horizontal_line_3_4_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void vp8cx_vertical_band_3_4_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_last_vertical_band_3_4_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_horizontal_line_1_2_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void vp8cx_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_last_vertical_band_1_2_scale_c(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_horizontal_line_5_4_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void vp8cx_vertical_band_5_4_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_horizontal_line_5_3_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void vp8cx_vertical_band_5_3_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_horizontal_line_2_1_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void vp8cx_vertical_band_2_1_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vp8cx_vertical_band_2_1_scale_i_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
 
-
-extern void (*vp8_vertical_band_4_5_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_last_vertical_band_4_5_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_vertical_band_2_3_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_last_vertical_band_2_3_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_vertical_band_3_5_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_last_vertical_band_3_5_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_vertical_band_3_4_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_last_vertical_band_3_4_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_horizontal_line_1_2_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-extern void (*vp8_horizontal_line_3_4_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-extern void (*vp8_horizontal_line_3_5_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-extern void (*vp8_horizontal_line_2_3_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-extern void (*vp8_horizontal_line_4_5_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-extern void (*vp8_vertical_band_1_2_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_last_vertical_band_1_2_scale)(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_vertical_band_5_4_scale)(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_vertical_band_5_3_scale)(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_vertical_band_2_1_scale)(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_vertical_band_2_1_scale_i)(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-extern void (*vp8_horizontal_line_2_1_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-extern void (*vp8_horizontal_line_5_3_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-extern void (*vp8_horizontal_line_5_4_scale)(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-
-void horizontal_line_4_5_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void horizontal_line_2_3_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void horizontal_line_3_5_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void horizontal_line_3_4_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void horizontal_line_1_2_scale_armv4(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width);
-void vertical_band_4_5_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vertical_band_2_3_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vertical_band_3_5_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vertical_band_3_4_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-void vertical_band_1_2_scale_armv4(unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width);
-
-
-extern void  dmachine_specific_config(int mmx_enabled, int xmm_enabled, int wmt_enabled);
-extern void vp8_yv12_scale_or_center
-(
-  YV12_BUFFER_CONFIG *src_yuv_config,
-  YV12_BUFFER_CONFIG *dst_yuv_config,
-  int expanded_frame_width,
-  int expanded_frame_height,
-  int scaling_mode,
-  int HScale,
-  int HRatio,
-  int VScale,
-  int VRatio
-);
-extern void vp8_scale_frame
-(
-  YV12_BUFFER_CONFIG *src,
-  YV12_BUFFER_CONFIG *dst,
-  unsigned char *temp_area,
-  unsigned char temp_height,
-  unsigned int hscale,
-  unsigned int hratio,
-  unsigned int vscale,
-  unsigned int vratio,
-  unsigned int interlaced
-);
-extern void vp8_scale_machine_specific_config(void);
-
-extern void (*vp8_yv12_extend_frame_borders_ptr)(YV12_BUFFER_CONFIG *ybf);
-extern void vp8_yv12_extend_frame_borders(YV12_BUFFER_CONFIG *ybf);
-extern void vp8_yv12_extend_frame_borders_neon(YV12_BUFFER_CONFIG *ybf);
-
-extern void (*vp8_yv12_copy_frame_yonly_ptr)(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-extern void vp8_yv12_copy_frame_yonly(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-extern void vp8_yv12_copy_frame_yonly_neon(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-
-extern void (*vp8_yv12_copy_frame_ptr)(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-extern void vp8_yv12_copy_frame(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-extern void vp8_yv12_copy_frame_neon(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
+extern void vp8_yv12_scale_or_center(YV12_BUFFER_CONFIG *src_yuv_config,
+                                     YV12_BUFFER_CONFIG *dst_yuv_config,
+                                     int expanded_frame_width,
+                                     int expanded_frame_height,
+                                     int scaling_mode,
+                                     int HScale,
+                                     int HRatio,
+                                     int VScale,
+                                     int VRatio);
+
+extern void vp8_scale_frame(YV12_BUFFER_CONFIG *src,
+                            YV12_BUFFER_CONFIG *dst,
+                            unsigned char *temp_area,
+                            unsigned char temp_height,
+                            unsigned int hscale,
+                            unsigned int hratio,
+                            unsigned int vscale,
+                            unsigned int vratio,
+                            unsigned int interlaced);
 
 #endif
diff --git a/vpx_scale/yv12config.h b/vpx_scale/yv12config.h
index 83523e253..6a8a1fc52 100644
--- a/vpx_scale/yv12config.h
+++ b/vpx_scale/yv12config.h
@@ -11,18 +11,14 @@
 
 #ifndef YV12_CONFIG_H
 #define YV12_CONFIG_H
-
-#include "vpx_config.h"
-
 #ifdef __cplusplus
 extern "C"
 {
 #endif
 
-#define VP7BORDERINPIXELS       48
-
-#define VP8BORDERINPIXELS       64
-#define INTERP_EXTEND            4
+#define VP8BORDERINPIXELS       32
+#define VP9BORDERINPIXELS       64
+#define VP9_INTERP_EXTEND        4
 
   /*************************************
    For INT_YUV:
@@ -42,7 +38,7 @@ extern "C"
   }
             YUV_TYPE;
 
-  typedef struct {
+  typedef struct yv12_buffer_config {
     int   y_width;
     int   y_height;
     int   y_stride;
diff --git a/vpx_scale/yv12extend.h b/vpx_scale/yv12extend.h
deleted file mode 100644
index c7fcedf21..000000000
--- a/vpx_scale/yv12extend.h
+++ /dev/null
@@ -1,33 +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.
- */
-
-
-#ifndef YV12_EXTEND_H
-#define YV12_EXTEND_H
-
-#include "vpx_scale/yv12config.h"
-
-#ifdef __cplusplus
-extern "C"
-{
-#endif
-
-  void vp8_yv12_extend_frame_borders(YV12_BUFFER_CONFIG *ybf);
-
-  /* Copy Y,U,V buffer data from src to dst, filling border of dst as well. */
-
-  void vp8_yv12_copy_frame(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-  void vp8_yv12_copy_frame_yonly(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif