source/libvpx/vp9/common/x86/vp9_asm_stubs.c - Issue 23530058: libvpx: Pull from upstream

Unified Diff: source/libvpx/vp9/common/x86/vp9_asm_stubs.c

Issue 23530058: libvpx: Pull from upstream (Closed) Base URL: svn://chrome-svn/chrome/trunk/deps/third_party/libvpx/

Patch Set: Created 7 years, 3 months ago

Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.

Jump to:

View side-by-side diff with in-line comments

Download patch

Index: source/libvpx/vp9/common/x86/vp9_asm_stubs.c

===================================================================

--- source/libvpx/vp9/common/x86/vp9_asm_stubs.c (revision 223100)

+++ source/libvpx/vp9/common/x86/vp9_asm_stubs.c (working copy)

@@ -13,6 +13,7 @@

#include "./vpx_config.h"

#include "./vp9_rtcd.h"

#include "vpx_ports/mem.h"

///////////////////////////////////////////////////////////////////////////

// the mmx function that does the bilinear filtering and var calculation //

// int one pass //

@@ -36,6 +37,8 @@

{ 8, 8, 8, 8, 120, 120, 120, 120 }

};

+int num_func_entry = 0;

#if HAVE_SSSE3

void vp9_filter_block1d16_v8_ssse3(const unsigned char *src_ptr,

const unsigned int src_pitch,

@@ -44,6 +47,13 @@

unsigned int output_height,

const short *filter);

+void vp9_filter_block1d16_v8_intrin_ssse3(const unsigned char *src_ptr,

+ const unsigned int src_pitch,

+ unsigned char *output_ptr,

+ unsigned int out_pitch,

+ unsigned int output_height,

+ const short *filter);

void vp9_filter_block1d16_h8_ssse3(const unsigned char *src_ptr,

const unsigned int src_pitch,

unsigned char *output_ptr,

@@ -51,6 +61,13 @@

unsigned int output_height,

const short *filter);

+void vp9_filter_block1d16_h8_intrin_ssse3(const unsigned char *src_ptr,

+ const unsigned int src_pitch,

+ unsigned char *output_ptr,

+ unsigned int out_pitch,

+ unsigned int output_height,

+ const short *filter);

void vp9_filter_block1d8_v8_ssse3(const unsigned char *src_ptr,

const unsigned int src_pitch,

unsigned char *output_ptr,

@@ -58,6 +75,13 @@

unsigned int output_height,

const short *filter);

+void vp9_filter_block1d8_v8_intrin_ssse3(const unsigned char *src_ptr,

+ const unsigned int src_pitch,

+ unsigned char *output_ptr,

+ unsigned int out_pitch,

+ unsigned int output_height,

+ const short *filter);

void vp9_filter_block1d8_h8_ssse3(const unsigned char *src_ptr,

const unsigned int src_pitch,

unsigned char *output_ptr,

@@ -65,6 +89,13 @@

unsigned int output_height,

const short *filter);

+void vp9_filter_block1d8_h8_intrin_ssse3(const unsigned char *src_ptr,

+ const unsigned int src_pitch,

+ unsigned char *output_ptr,

+ unsigned int out_pitch,

+ unsigned int output_height,

+ const short *filter);

void vp9_filter_block1d4_v8_ssse3(const unsigned char *src_ptr,

const unsigned int src_pitch,

unsigned char *output_ptr,

@@ -72,6 +103,14 @@

unsigned int output_height,

const short *filter);

+void vp9_filter_block1d4_v8_intrin_ssse3(const unsigned char *src_ptr,

+ const unsigned int src_pitch,

+ unsigned char *output_ptr,

+ unsigned int out_pitch,

+ unsigned int output_height,

+ const short *filter);

void vp9_filter_block1d4_h8_ssse3(const unsigned char *src_ptr,

const unsigned int src_pitch,

unsigned char *output_ptr,

@@ -79,6 +118,13 @@

unsigned int output_height,

const short *filter);

+void vp9_filter_block1d4_h8_intrin_ssse3(const unsigned char *src_ptr,

+ const unsigned int src_pitch,

+ unsigned char *output_ptr,

+ unsigned int out_pitch,

+ unsigned int output_height,

+ const short *filter);

void vp9_filter_block1d16_v8_avg_ssse3(const unsigned char *src_ptr,

const unsigned int src_pitch,

unsigned char *output_ptr,

@@ -129,7 +175,7 @@

/* Ensure the filter can be compressed to int16_t. */

if (x_step_q4 == 16 && filter_x[3] != 128) {

while (w >= 16) {

- vp9_filter_block1d16_h8_ssse3(src, src_stride,

+ vp9_filter_block1d16_h8_intrin_ssse3(src, src_stride,

dst, dst_stride,

h, filter_x);

src += 16;

@@ -137,7 +183,7 @@

w -= 16;

}

while (w >= 8) {

- vp9_filter_block1d8_h8_ssse3(src, src_stride,

+ vp9_filter_block1d8_h8_intrin_ssse3(src, src_stride,

dst, dst_stride,

h, filter_x);

src += 8;

@@ -145,7 +191,7 @@

w -= 8;

}

while (w >= 4) {

- vp9_filter_block1d4_h8_ssse3(src, src_stride,

+ vp9_filter_block1d4_h8_intrin_ssse3(src, src_stride,

dst, dst_stride,

h, filter_x);

src += 4;

@@ -167,25 +213,25 @@

int w, int h) {

if (y_step_q4 == 16 && filter_y[3] != 128) {

while (w >= 16) {

- vp9_filter_block1d16_v8_ssse3(src - src_stride * 3, src_stride,

- dst, dst_stride,

- h, filter_y);

+ vp9_filter_block1d16_v8_intrin_ssse3(src - src_stride * 3, src_stride,

+ dst, dst_stride,

+ h, filter_y);

src += 16;

dst += 16;

w -= 16;

}

while (w >= 8) {

- vp9_filter_block1d8_v8_ssse3(src - src_stride * 3, src_stride,

- dst, dst_stride,

- h, filter_y);

+ vp9_filter_block1d8_v8_intrin_ssse3(src - src_stride * 3, src_stride,

+ dst, dst_stride,

+ h, filter_y);

src += 8;

dst += 8;

w -= 8;

}

while (w >= 4) {

- vp9_filter_block1d4_v8_ssse3(src - src_stride * 3, src_stride,

- dst, dst_stride,

- h, filter_y);

+ vp9_filter_block1d4_v8_intrin_ssse3(src - src_stride * 3, src_stride,

+ dst, dst_stride,

+ h, filter_y);

src += 4;

dst += 4;

w -= 4;

@@ -206,24 +252,24 @@

if (x_step_q4 == 16 && filter_x[3] != 128) {

while (w >= 16) {

vp9_filter_block1d16_h8_avg_ssse3(src, src_stride,

- dst, dst_stride,

- h, filter_x);

+ dst, dst_stride,

+ h, filter_x);

src += 16;

dst += 16;

w -= 16;

}

while (w >= 8) {

vp9_filter_block1d8_h8_avg_ssse3(src, src_stride,

- dst, dst_stride,

- h, filter_x);

+ dst, dst_stride,

+ h, filter_x);

src += 8;

dst += 8;

w -= 8;

}

while (w >= 4) {

vp9_filter_block1d4_h8_avg_ssse3(src, src_stride,

- dst, dst_stride,

- h, filter_x);

+ dst, dst_stride,

+ h, filter_x);

src += 4;

dst += 4;

w -= 4;

@@ -244,24 +290,24 @@

if (y_step_q4 == 16 && filter_y[3] != 128) {

while (w >= 16) {

vp9_filter_block1d16_v8_avg_ssse3(src - src_stride * 3, src_stride,

- dst, dst_stride,

- h, filter_y);

+ dst, dst_stride,

+ h, filter_y);

src += 16;

dst += 16;

w -= 16;

}

while (w >= 8) {

vp9_filter_block1d8_v8_avg_ssse3(src - src_stride * 3, src_stride,

- dst, dst_stride,

- h, filter_y);

+ dst, dst_stride,

+ h, filter_y);

src += 8;

dst += 8;

w -= 8;

}

while (w >= 4) {

vp9_filter_block1d4_v8_avg_ssse3(src - src_stride * 3, src_stride,

- dst, dst_stride,

- h, filter_y);

+ dst, dst_stride,

+ h, filter_y);

src += 4;

dst += 4;

w -= 4;

« no previous file with comments | « source/libvpx/vp9/common/vp9_systemdependent.h ('k') | source/libvpx/vp9/common/x86/vp9_loopfilter_intrin_sse2.c » ('j') | no next file with comments »