libvpx: Pull from upstream

source/libvpx/vpx_dsp/arm/sad4d_neon.c

 /*
  *  Copyright (c) 2015 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 <arm_neon.h>
-#include "./vp9_rtcd.h"
+
 #include "./vpx_config.h"
-
+#include "./vpx_dsp_rtcd.h"
 #include "vpx/vpx_integer.h"
 
 static INLINE unsigned int horizontal_long_add_16x8(const uint16x8_t vec_lo,
                                                     const uint16x8_t vec_hi) {
   const uint32x4_t vec_l_lo = vaddl_u16(vget_low_u16(vec_lo),
                                         vget_high_u16(vec_lo));
   const uint32x4_t vec_l_hi = vaddl_u16(vget_low_u16(vec_hi),
                                         vget_high_u16(vec_hi));
   const uint32x4_t a = vaddq_u32(vec_l_lo, vec_l_hi);
   const uint64x2_t b = vpaddlq_u32(a);
@@ skipping 48 matching lines @@
   *vec_sum_ref_lo = vabal_u8(*vec_sum_ref_lo, vget_low_u8(vec_src_00),
                              vget_low_u8(vec_ref_00));
   *vec_sum_ref_hi = vabal_u8(*vec_sum_ref_hi, vget_high_u8(vec_src_00),
                              vget_high_u8(vec_ref_00));
   *vec_sum_ref_lo = vabal_u8(*vec_sum_ref_lo, vget_low_u8(vec_src_16),
                              vget_low_u8(vec_ref_16));
   *vec_sum_ref_hi = vabal_u8(*vec_sum_ref_hi, vget_high_u8(vec_src_16),
                              vget_high_u8(vec_ref_16));
 }
 
-void vp9_sad64x64x4d_neon(const uint8_t *src, int src_stride,
+void vpx_sad64x64x4d_neon(const uint8_t *src, int src_stride,
                           const uint8_t* const ref[4], int ref_stride,
-                          unsigned int *res) {
+                          uint32_t *res) {
   int i;
   uint16x8_t vec_sum_ref0_lo = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref0_hi = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref1_lo = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref1_hi = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref2_lo = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref2_hi = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref3_lo = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref3_hi = vdupq_n_u16(0);
   const uint8_t *ref0, *ref1, *ref2, *ref3;
@@ skipping 23 matching lines @@
     ref2 += ref_stride;
     ref3 += ref_stride;
   }
 
   res[0] = horizontal_long_add_16x8(vec_sum_ref0_lo, vec_sum_ref0_hi);
   res[1] = horizontal_long_add_16x8(vec_sum_ref1_lo, vec_sum_ref1_hi);
   res[2] = horizontal_long_add_16x8(vec_sum_ref2_lo, vec_sum_ref2_hi);
   res[3] = horizontal_long_add_16x8(vec_sum_ref3_lo, vec_sum_ref3_hi);
 }
 
-void vp9_sad32x32x4d_neon(const uint8_t *src, int src_stride,
+void vpx_sad32x32x4d_neon(const uint8_t *src, int src_stride,
                           const uint8_t* const ref[4], int ref_stride,
-                          unsigned int *res) {
+                          uint32_t *res) {
   int i;
   uint16x8_t vec_sum_ref0_lo = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref0_hi = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref1_lo = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref1_hi = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref2_lo = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref2_hi = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref3_lo = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref3_hi = vdupq_n_u16(0);
   const uint8_t *ref0, *ref1, *ref2, *ref3;
@@ skipping 21 matching lines @@
     ref2 += ref_stride;
     ref3 += ref_stride;
   }
 
   res[0] = horizontal_long_add_16x8(vec_sum_ref0_lo, vec_sum_ref0_hi);
   res[1] = horizontal_long_add_16x8(vec_sum_ref1_lo, vec_sum_ref1_hi);
   res[2] = horizontal_long_add_16x8(vec_sum_ref2_lo, vec_sum_ref2_hi);
   res[3] = horizontal_long_add_16x8(vec_sum_ref3_lo, vec_sum_ref3_hi);
 }
 
-void vp9_sad16x16x4d_neon(const uint8_t *src, int src_stride,
+void vpx_sad16x16x4d_neon(const uint8_t *src, int src_stride,
                           const uint8_t* const ref[4], int ref_stride,
-                          unsigned int *res) {
+                          uint32_t *res) {
   int i;
   uint16x8_t vec_sum_ref0_lo = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref0_hi = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref1_lo = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref1_hi = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref2_lo = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref2_hi = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref3_lo = vdupq_n_u16(0);
   uint16x8_t vec_sum_ref3_hi = vdupq_n_u16(0);
   const uint8_t *ref0, *ref1, *ref2, *ref3;
@@ skipping 31 matching lines @@
     ref1 += ref_stride;
     ref2 += ref_stride;
     ref3 += ref_stride;
   }
 
   res[0] = horizontal_long_add_16x8(vec_sum_ref0_lo, vec_sum_ref0_hi);
   res[1] = horizontal_long_add_16x8(vec_sum_ref1_lo, vec_sum_ref1_hi);
   res[2] = horizontal_long_add_16x8(vec_sum_ref2_lo, vec_sum_ref2_hi);
   res[3] = horizontal_long_add_16x8(vec_sum_ref3_lo, vec_sum_ref3_hi);
 }