Skip to content

GitLab

A
aom-rav1e
Commit d5d92898 authored by Johann's avatar Johann
Browse files
Options

Move shared SAD code to vpx_dsp 

Create a new component, vpx_dsp, for code that can be shared
between codecs. Move the SAD code into the component.

This reduces the size of vpxenc/dec by 36k on x86_64 builds.

Change-Id: I73f837ddaecac6b350bf757af0cfe19c4ab9327a
parent c77b1f5a
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 2135 additions and 4352 deletions
libs.mk
View file @ d5d92898
......@@ -54,6 +54,9 @@ CODEC_SRCS-yes += $(addprefix vpx_scale/,$(call enabled,SCALE_SRCS))
include $(SRC_PATH_BARE)/vpx_ports/vpx_ports.mk
CODEC_SRCS-yes += $(addprefix vpx_ports/,$(call enabled,PORTS_SRCS))
include $(SRC_PATH_BARE)/vpx_dsp/vpx_dsp.mk
CODEC_SRCS-yes += $(addprefix vpx_dsp/,$(call enabled,DSP_SRCS))
ifneq ($(CONFIG_VP8_ENCODER)$(CONFIG_VP8_DECODER),)
VP8_PREFIX=vp8/
include $(SRC_PATH_BARE)/$(VP8_PREFIX)vp8_common.mk
......
test/sad_test.cc
View file @ d5d92898
This diff is collapsed.
test/test_libvpx.cc
View file @ d5d92898
......@@ -19,6 +19,7 @@ extern void vp8_rtcd();
#if CONFIG_VP9
extern void vp9_rtcd();
#endif // CONFIG_VP9
extern void vpx_dsp_rtcd();
extern void vpx_scale_rtcd();
}
#include "third_party/googletest/src/include/gtest/gtest.h"
......@@ -64,6 +65,7 @@ int main(int argc, char **argv) {
#if CONFIG_VP9
vp9_rtcd();
#endif // CONFIG_VP9
vpx_dsp_rtcd();
vpx_scale_rtcd();
#endif // !CONFIG_SHARED
......
vp8/common/arm/neon/sad_neon.c deleted 100644 → 0
View file @ c77b1f5a
/*
* Copyright (c) 2014 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>
unsigned int vp8_sad8x8_neon(
unsigned char *src_ptr,
int src_stride,
unsigned char *ref_ptr,
int ref_stride) {
uint8x8_t d0, d8;
uint16x8_t q12;
uint32x4_t q1;
uint64x2_t q3;
uint32x2_t d5;
int i;
d0 = vld1_u8(src_ptr);
src_ptr += src_stride;
d8 = vld1_u8(ref_ptr);
ref_ptr += ref_stride;
q12 = vabdl_u8(d0, d8);
for (i = 0; i < 7; i++) {
d0 = vld1_u8(src_ptr);
src_ptr += src_stride;
d8 = vld1_u8(ref_ptr);
ref_ptr += ref_stride;
q12 = vabal_u8(q12, d0, d8);
}
q1 = vpaddlq_u16(q12);
q3 = vpaddlq_u32(q1);
d5 = vadd_u32(vreinterpret_u32_u64(vget_low_u64(q3)),
vreinterpret_u32_u64(vget_high_u64(q3)));
return vget_lane_u32(d5, 0);
}
unsigned int vp8_sad8x16_neon(
unsigned char *src_ptr,
int src_stride,
unsigned char *ref_ptr,
int ref_stride) {
uint8x8_t d0, d8;
uint16x8_t q12;
uint32x4_t q1;
uint64x2_t q3;
uint32x2_t d5;
int i;
d0 = vld1_u8(src_ptr);
src_ptr += src_stride;
d8 = vld1_u8(ref_ptr);
ref_ptr += ref_stride;
q12 = vabdl_u8(d0, d8);
for (i = 0; i < 15; i++) {
d0 = vld1_u8(src_ptr);
src_ptr += src_stride;
d8 = vld1_u8(ref_ptr);
ref_ptr += ref_stride;
q12 = vabal_u8(q12, d0, d8);
}
q1 = vpaddlq_u16(q12);
q3 = vpaddlq_u32(q1);
d5 = vadd_u32(vreinterpret_u32_u64(vget_low_u64(q3)),
vreinterpret_u32_u64(vget_high_u64(q3)));
return vget_lane_u32(d5, 0);
}
unsigned int vp8_sad4x4_neon(
unsigned char *src_ptr,
int src_stride,
unsigned char *ref_ptr,
int ref_stride) {
uint8x8_t d0, d8;
uint16x8_t q12;
uint32x2_t d1;
uint64x1_t d3;
int i;
d0 = vld1_u8(src_ptr);
src_ptr += src_stride;
d8 = vld1_u8(ref_ptr);
ref_ptr += ref_stride;
q12 = vabdl_u8(d0, d8);
for (i = 0; i < 3; i++) {
d0 = vld1_u8(src_ptr);
src_ptr += src_stride;
d8 = vld1_u8(ref_ptr);
ref_ptr += ref_stride;
q12 = vabal_u8(q12, d0, d8);
}
d1 = vpaddl_u16(vget_low_u16(q12));
d3 = vpaddl_u32(d1);
return vget_lane_u32(vreinterpret_u32_u64(d3), 0);
}
unsigned int vp8_sad16x16_neon(
unsigned char *src_ptr,
int src_stride,
unsigned char *ref_ptr,
int ref_stride) {
uint8x16_t q0, q4;
uint16x8_t q12, q13;
uint32x4_t q1;
uint64x2_t q3;
uint32x2_t d5;
int i;
q0 = vld1q_u8(src_ptr);
src_ptr += src_stride;
q4 = vld1q_u8(ref_ptr);
ref_ptr += ref_stride;
q12 = vabdl_u8(vget_low_u8(q0), vget_low_u8(q4));
q13 = vabdl_u8(vget_high_u8(q0), vget_high_u8(q4));
for (i = 0; i < 15; i++) {
q0 = vld1q_u8(src_ptr);
src_ptr += src_stride;
q4 = vld1q_u8(ref_ptr);
ref_ptr += ref_stride;
q12 = vabal_u8(q12, vget_low_u8(q0), vget_low_u8(q4));
q13 = vabal_u8(q13, vget_high_u8(q0), vget_high_u8(q4));
}
q12 = vaddq_u16(q12, q13);
q1 = vpaddlq_u16(q12);
q3 = vpaddlq_u32(q1);
d5 = vadd_u32(vreinterpret_u32_u64(vget_low_u64(q3)),
vreinterpret_u32_u64(vget_high_u64(q3)));
return vget_lane_u32(d5, 0);
}
unsigned int vp8_sad16x8_neon(
unsigned char *src_ptr,
int src_stride,
unsigned char *ref_ptr,
int ref_stride) {
uint8x16_t q0, q4;
uint16x8_t q12, q13;
uint32x4_t q1;
uint64x2_t q3;
uint32x2_t d5;
int i;
q0 = vld1q_u8(src_ptr);
src_ptr += src_stride;
q4 = vld1q_u8(ref_ptr);
ref_ptr += ref_stride;
q12 = vabdl_u8(vget_low_u8(q0), vget_low_u8(q4));
q13 = vabdl_u8(vget_high_u8(q0), vget_high_u8(q4));
for (i = 0; i < 7; i++) {
q0 = vld1q_u8(src_ptr);
src_ptr += src_stride;
q4 = vld1q_u8(ref_ptr);
ref_ptr += ref_stride;
q12 = vabal_u8(q12, vget_low_u8(q0), vget_low_u8(q4));
q13 = vabal_u8(q13, vget_high_u8(q0), vget_high_u8(q4));
}
q12 = vaddq_u16(q12, q13);
q1 = vpaddlq_u16(q12);
q3 = vpaddlq_u32(q1);
d5 = vadd_u32(vreinterpret_u32_u64(vget_low_u64(q3)),
vreinterpret_u32_u64(vget_high_u64(q3)));
return vget_lane_u32(d5, 0);
}
vp8/common/copy_c.c 0 → 100644
View file @ d5d92898
/*
* 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_config.h"
#include "vpx/vpx_integer.h"
/* Copy 2 macroblocks to a buffer */
void vp8_copy32xn_c(unsigned char *src_ptr, int src_stride,
unsigned char *dst_ptr, int dst_stride,
int height)
{
int r;
for (r = 0; r < height; r++)
{
#if !(CONFIG_FAST_UNALIGNED)
dst_ptr[0] = src_ptr[0];
dst_ptr[1] = src_ptr[1];
dst_ptr[2] = src_ptr[2];
dst_ptr[3] = src_ptr[3];
dst_ptr[4] = src_ptr[4];
dst_ptr[5] = src_ptr[5];
dst_ptr[6] = src_ptr[6];
dst_ptr[7] = src_ptr[7];
dst_ptr[8] = src_ptr[8];
dst_ptr[9] = src_ptr[9];
dst_ptr[10] = src_ptr[10];
dst_ptr[11] = src_ptr[11];
dst_ptr[12] = src_ptr[12];
dst_ptr[13] = src_ptr[13];
dst_ptr[14] = src_ptr[14];
dst_ptr[15] = src_ptr[15];
dst_ptr[16] = src_ptr[16];
dst_ptr[17] = src_ptr[17];
dst_ptr[18] = src_ptr[18];
dst_ptr[19] = src_ptr[19];
dst_ptr[20] = src_ptr[20];
dst_ptr[21] = src_ptr[21];
dst_ptr[22] = src_ptr[22];
dst_ptr[23] = src_ptr[23];
dst_ptr[24] = src_ptr[24];
dst_ptr[25] = src_ptr[25];
dst_ptr[26] = src_ptr[26];
dst_ptr[27] = src_ptr[27];
dst_ptr[28] = src_ptr[28];
dst_ptr[29] = src_ptr[29];
dst_ptr[30] = src_ptr[30];
dst_ptr[31] = src_ptr[31];
#else
((uint32_t *)dst_ptr)[0] = ((uint32_t *)src_ptr)[0] ;
((uint32_t *)dst_ptr)[1] = ((uint32_t *)src_ptr)[1] ;
((uint32_t *)dst_ptr)[2] = ((uint32_t *)src_ptr)[2] ;
((uint32_t *)dst_ptr)[3] = ((uint32_t *)src_ptr)[3] ;
((uint32_t *)dst_ptr)[4] = ((uint32_t *)src_ptr)[4] ;
((uint32_t *)dst_ptr)[5] = ((uint32_t *)src_ptr)[5] ;
((uint32_t *)dst_ptr)[6] = ((uint32_t *)src_ptr)[6] ;
((uint32_t *)dst_ptr)[7] = ((uint32_t *)src_ptr)[7] ;
#endif
src_ptr += src_stride;
dst_ptr += dst_stride;
}
}
vp8/common/mfqe.c
View file @ d5d92898
......@@ -17,10 +17,11 @@
* higher quality.
*/
#include "postproc.h"
#include "variance.h"
#include "./vp8_rtcd.h"
#include "./vpx_dsp_rtcd.h"
#include "vp8/common/postproc.h"
#include "vp8/common/variance.h"
#include "vpx_mem/vpx_mem.h"
#include "vp8_rtcd.h"
#include "vpx_scale/yv12config.h"
#include <limits.h>
......@@ -160,9 +161,9 @@ static void multiframe_quality_enhance_block
vp8_variance8x8(v, uv_stride, vd, uvd_stride, &sse);
vsad = (sse + 32)>>6;
#else
sad = (vp8_sad16x16(y, y_stride, yd, yd_stride, UINT_MAX) + 128) >> 8;
usad = (vp8_sad8x8(u, uv_stride, ud, uvd_stride, UINT_MAX) + 32) >> 6;
vsad = (vp8_sad8x8(v, uv_stride, vd, uvd_stride, UINT_MAX)+ 32) >> 6;
sad = (vpx_sad16x16(y, y_stride, yd, yd_stride) + 128) >> 8;
usad = (vpx_sad8x8(u, uv_stride, ud, uvd_stride) + 32) >> 6;
vsad = (vpx_sad8x8(v, uv_stride, vd, uvd_stride)+ 32) >> 6;
#endif
}
else /* if (blksize == 8) */
......@@ -177,9 +178,9 @@ static void multiframe_quality_enhance_block
vp8_variance4x4(v, uv_stride, vd, uvd_stride, &sse);
vsad = (sse + 8)>>4;
#else
sad = (vp8_sad8x8(y, y_stride, yd, yd_stride, UINT_MAX) + 32) >> 6;
usad = (vp8_sad4x4(u, uv_stride, ud, uvd_stride, UINT_MAX) + 8) >> 4;
vsad = (vp8_sad4x4(v, uv_stride, vd, uvd_stride, UINT_MAX) + 8) >> 4;
sad = (vpx_sad8x8(y, y_stride, yd, yd_stride) + 32) >> 6;
usad = (vpx_sad4x4(u, uv_stride, ud, uvd_stride) + 8) >> 4;
vsad = (vpx_sad4x4(v, uv_stride, vd, uvd_stride) + 8) >> 4;
#endif
}
......
vp8/common/rtcd_defs.pl
View file @ d5d92898
......@@ -303,88 +303,6 @@ specialize qw/vp8_variance_halfpixvar16x16_hv mmx sse2 media neon/;
$vp8_variance_halfpixvar16x16_hv_sse2=vp8_variance_halfpixvar16x16_hv_wmt;
$vp8_variance_halfpixvar16x16_hv_media=vp8_variance_halfpixvar16x16_hv_armv6;
#
# Single block SAD
#
add_proto qw/unsigned int vp8_sad4x4/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int max_sad";
specialize qw/vp8_sad4x4 mmx sse2 neon/;
$vp8_sad4x4_sse2=vp8_sad4x4_wmt;
add_proto qw/unsigned int vp8_sad8x8/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int max_sad";
specialize qw/vp8_sad8x8 mmx sse2 neon/;
$vp8_sad8x8_sse2=vp8_sad8x8_wmt;
add_proto qw/unsigned int vp8_sad8x16/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int max_sad";
specialize qw/vp8_sad8x16 mmx sse2 neon/;
$vp8_sad8x16_sse2=vp8_sad8x16_wmt;
add_proto qw/unsigned int vp8_sad16x8/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int max_sad";
specialize qw/vp8_sad16x8 mmx sse2 neon/;
$vp8_sad16x8_sse2=vp8_sad16x8_wmt;
add_proto qw/unsigned int vp8_sad16x16/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int max_sad";
specialize qw/vp8_sad16x16 mmx sse2 sse3 media neon/;
$vp8_sad16x16_sse2=vp8_sad16x16_wmt;
$vp8_sad16x16_media=vp8_sad16x16_armv6;
#
# Multi-block SAD, comparing a reference to N blocks 1 pixel apart horizontally
#
add_proto qw/void vp8_sad4x4x3/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int *sad_array";
specialize qw/vp8_sad4x4x3 sse3/;
add_proto qw/void vp8_sad8x8x3/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int *sad_array";
specialize qw/vp8_sad8x8x3 sse3/;
add_proto qw/void vp8_sad8x16x3/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int *sad_array";
specialize qw/vp8_sad8x16x3 sse3/;
add_proto qw/void vp8_sad16x8x3/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int *sad_array";
specialize qw/vp8_sad16x8x3 sse3 ssse3/;
add_proto qw/void vp8_sad16x16x3/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned int *sad_array";
specialize qw/vp8_sad16x16x3 sse3 ssse3/;
# Note the only difference in the following prototypes is that they return into
# an array of short
add_proto qw/void vp8_sad4x4x8/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned short *sad_array";
specialize qw/vp8_sad4x4x8 sse4_1/;
$vp8_sad4x4x8_sse4_1=vp8_sad4x4x8_sse4;
add_proto qw/void vp8_sad8x8x8/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned short *sad_array";
specialize qw/vp8_sad8x8x8 sse4_1/;
$vp8_sad8x8x8_sse4_1=vp8_sad8x8x8_sse4;
add_proto qw/void vp8_sad8x16x8/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned short *sad_array";
specialize qw/vp8_sad8x16x8 sse4_1/;
$vp8_sad8x16x8_sse4_1=vp8_sad8x16x8_sse4;
add_proto qw/void vp8_sad16x8x8/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned short *sad_array";
specialize qw/vp8_sad16x8x8 sse4_1/;
$vp8_sad16x8x8_sse4_1=vp8_sad16x8x8_sse4;
add_proto qw/void vp8_sad16x16x8/, "const unsigned char *src_ptr, int src_stride, const unsigned char *ref_ptr, int ref_stride, unsigned short *sad_array";
specialize qw/vp8_sad16x16x8 sse4_1/;
$vp8_sad16x16x8_sse4_1=vp8_sad16x16x8_sse4;
#
# Multi-block SAD, comparing a reference to N independent blocks
#
add_proto qw/void vp8_sad4x4x4d/, "const unsigned char *src_ptr, int src_stride, const unsigned char * const ref_ptr[], int ref_stride, unsigned int *sad_array";
specialize qw/vp8_sad4x4x4d sse3/;
add_proto qw/void vp8_sad8x8x4d/, "const unsigned char *src_ptr, int src_stride, const unsigned char * const ref_ptr[], int ref_stride, unsigned int *sad_array";
specialize qw/vp8_sad8x8x4d sse3/;
add_proto qw/void vp8_sad8x16x4d/, "const unsigned char *src_ptr, int src_stride, const unsigned char * const ref_ptr[], int ref_stride, unsigned int *sad_array";
specialize qw/vp8_sad8x16x4d sse3/;
add_proto qw/void vp8_sad16x8x4d/, "const unsigned char *src_ptr, int src_stride, const unsigned char * const ref_ptr[], int ref_stride, unsigned int *sad_array";
specialize qw/vp8_sad16x8x4d sse3/;
add_proto qw/void vp8_sad16x16x4d/, "const unsigned char *src_ptr, int src_stride, const unsigned char * const ref_ptr[], int ref_stride, unsigned int *sad_array";
specialize qw/vp8_sad16x16x4d sse3/;
#
# Encoder functions below this point.
#
......
vp8/common/sad_c.c deleted 100644 → 0
View file @ c77b1f5a
/*
* 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 <limits.h>
#include <stdlib.h>
#include "vpx_config.h"
#include "vpx/vpx_integer.h"
static unsigned int sad_mx_n_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned int max_sad, int m, int n)
{
int r, c;
unsigned int sad = 0;
for (r = 0; r < n; r++)
{
for (c = 0; c < m; c++)
{
sad += abs(src_ptr[c] - ref_ptr[c]);
}
if (sad > max_sad)
break;
src_ptr += src_stride;
ref_ptr += ref_stride;
}
return sad;
}
/* max_sad is provided as an optional optimization point. Alternative
* implementations of these functions are not required to check it.
*/
unsigned int vp8_sad16x16_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned int max_sad)
{
return sad_mx_n_c(src_ptr, src_stride, ref_ptr, ref_stride, max_sad, 16, 16);
}
unsigned int vp8_sad8x8_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned int max_sad)
{
return sad_mx_n_c(src_ptr, src_stride, ref_ptr, ref_stride, max_sad, 8, 8);
}
unsigned int vp8_sad16x8_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned int max_sad)
{
return sad_mx_n_c(src_ptr, src_stride, ref_ptr, ref_stride, max_sad, 16, 8);
}
unsigned int vp8_sad8x16_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned int max_sad)
{
return sad_mx_n_c(src_ptr, src_stride, ref_ptr, ref_stride, max_sad, 8, 16);
}
unsigned int vp8_sad4x4_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned int max_sad)
{
return sad_mx_n_c(src_ptr, src_stride, ref_ptr, ref_stride, max_sad, 4, 4);
}
void vp8_sad16x16x3_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned int *sad_array)
{
sad_array[0] = vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 0, ref_stride, UINT_MAX);
sad_array[1] = vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, UINT_MAX);
sad_array[2] = vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, UINT_MAX);
}
void vp8_sad16x16x8_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned short *sad_array)
{
sad_array[0] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 0, ref_stride, UINT_MAX);
sad_array[1] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, UINT_MAX);
sad_array[2] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, UINT_MAX);
sad_array[3] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 3, ref_stride, UINT_MAX);
sad_array[4] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 4, ref_stride, UINT_MAX);
sad_array[5] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 5, ref_stride, UINT_MAX);
sad_array[6] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 6, ref_stride, UINT_MAX);
sad_array[7] = (unsigned short)vp8_sad16x16_c(src_ptr, src_stride, ref_ptr + 7, ref_stride, UINT_MAX);
}
void vp8_sad16x8x3_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned int *sad_array)
{
sad_array[0] = vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 0, ref_stride, UINT_MAX);
sad_array[1] = vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, UINT_MAX);
sad_array[2] = vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, UINT_MAX);
}
void vp8_sad16x8x8_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned short *sad_array)
{
sad_array[0] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 0, ref_stride, UINT_MAX);
sad_array[1] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, UINT_MAX);
sad_array[2] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, UINT_MAX);
sad_array[3] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 3, ref_stride, UINT_MAX);
sad_array[4] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 4, ref_stride, UINT_MAX);
sad_array[5] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 5, ref_stride, UINT_MAX);
sad_array[6] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 6, ref_stride, UINT_MAX);
sad_array[7] = (unsigned short)vp8_sad16x8_c(src_ptr, src_stride, ref_ptr + 7, ref_stride, UINT_MAX);
}
void vp8_sad8x8x3_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned int *sad_array)
{
sad_array[0] = vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 0, ref_stride, UINT_MAX);
sad_array[1] = vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, UINT_MAX);
sad_array[2] = vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, UINT_MAX);
}
void vp8_sad8x8x8_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned short *sad_array)
{
sad_array[0] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 0, ref_stride, UINT_MAX);
sad_array[1] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, UINT_MAX);
sad_array[2] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, UINT_MAX);
sad_array[3] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 3, ref_stride, UINT_MAX);
sad_array[4] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 4, ref_stride, UINT_MAX);
sad_array[5] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 5, ref_stride, UINT_MAX);
sad_array[6] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 6, ref_stride, UINT_MAX);
sad_array[7] = (unsigned short)vp8_sad8x8_c(src_ptr, src_stride, ref_ptr + 7, ref_stride, UINT_MAX);
}
void vp8_sad8x16x3_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned int *sad_array)
{
sad_array[0] = vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 0, ref_stride, UINT_MAX);
sad_array[1] = vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, UINT_MAX);
sad_array[2] = vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, UINT_MAX);
}
void vp8_sad8x16x8_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned short *sad_array)
{
sad_array[0] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 0, ref_stride, UINT_MAX);
sad_array[1] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, UINT_MAX);
sad_array[2] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, UINT_MAX);
sad_array[3] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 3, ref_stride, UINT_MAX);
sad_array[4] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 4, ref_stride, UINT_MAX);
sad_array[5] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 5, ref_stride, UINT_MAX);
sad_array[6] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 6, ref_stride, UINT_MAX);
sad_array[7] = (unsigned short)vp8_sad8x16_c(src_ptr, src_stride, ref_ptr + 7, ref_stride, UINT_MAX);
}
void vp8_sad4x4x3_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned int *sad_array)
{
sad_array[0] = vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 0, ref_stride, UINT_MAX);
sad_array[1] = vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, UINT_MAX);
sad_array[2] = vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 2, ref_stride, UINT_MAX);
}
void vp8_sad4x4x8_c(const unsigned char *src_ptr, int src_stride,
const unsigned char *ref_ptr, int ref_stride,
unsigned short *sad_array)
{
sad_array[0] = (unsigned short)vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 0, ref_stride, UINT_MAX);
sad_array[1] = (unsigned short)vp8_sad4x4_c(src_ptr, src_stride, ref_ptr + 1, ref_stride, UINT_MAX);