Skip to content

L
libyuv
Commit 04f40278 authored by fbarchard@google.com's avatar fbarchard@google.com
Browse files
Options

yasm ALIGN uppercase 

BUG=none
TEST=untested
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/4769005

git-svn-id: http://libyuv.googlecode.com/svn/trunk@885 16f28f9a-4ce2-e073-06de-1de4eb20be90
parent 545a51c1
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 117 additions and 117 deletions
README.chromium
View file @ 04f40278
Name: libyuv
URL: http://code.google.com/p/libyuv/
Version: 884
Version: 885
License: BSD
License File: LICENSE
......
include/libyuv/convert_from_argb.h
View file @ 04f40278
This diff is collapsed.
include/libyuv/version.h
View file @ 04f40278
......@@ -11,6 +11,6 @@
#ifndef INCLUDE_LIBYUV_VERSION_H_ // NOLINT
#define INCLUDE_LIBYUV_VERSION_H_
#define LIBYUV_VERSION 884
#define LIBYUV_VERSION 885
#endif // INCLUDE_LIBYUV_VERSION_H_ NOLINT
source/compare_common.cc
View file @ 04f40278
/*
* Copyright 2012 The LibYuv 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 "libyuv/basic_types.h"
#ifdef __cplusplus
namespace libyuv {
extern "C" {
#endif
uint32 SumSquareError_C(const uint8* src_a, const uint8* src_b, int count) {
uint32 sse = 0u;
for (int i = 0; i < count; ++i) {
int diff = src_a[i] - src_b[i];
sse += static_cast<uint32>(diff * diff);
}
return sse;
}
// hash seed of 5381 recommended.
// Internal C version of HashDjb2 with int sized count for efficiency.
uint32 HashDjb2_C(const uint8* src, int count, uint32 seed) {
uint32 hash = seed;
for (int i = 0; i < count; ++i) {
hash += (hash << 5) + src[i];
}
return hash;
}
#ifdef __cplusplus
} // extern "C"
} // namespace libyuv
#endif
/*
* Copyright 2012 The LibYuv 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 "libyuv/basic_types.h"
#ifdef __cplusplus
namespace libyuv {
extern "C" {
#endif
uint32 SumSquareError_C(const uint8* src_a, const uint8* src_b, int count) {
uint32 sse = 0u;
for (int i = 0; i < count; ++i) {
int diff = src_a[i] - src_b[i];
sse += static_cast<uint32>(diff * diff);
}
return sse;
}
// hash seed of 5381 recommended.
// Internal C version of HashDjb2 with int sized count for efficiency.
uint32 HashDjb2_C(const uint8* src, int count, uint32 seed) {
uint32 hash = seed;
for (int i = 0; i < count; ++i) {
hash += (hash << 5) + src[i];
}
return hash;
}
#ifdef __cplusplus
} // extern "C"
} // namespace libyuv
#endif
source/compare_neon.cc
View file @ 04f40278
/*
* Copyright 2012 The LibYuv 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 "libyuv/basic_types.h"
#ifdef __cplusplus
namespace libyuv {
extern "C" {
#endif
#if !defined(LIBYUV_DISABLE_NEON) && defined(__ARM_NEON__)
uint32 SumSquareError_NEON(const uint8* src_a, const uint8* src_b, int count) {
volatile uint32 sse;
asm volatile (
"vmov.u8 q8, #0 \n"
"vmov.u8 q10, #0 \n"
"vmov.u8 q9, #0 \n"
"vmov.u8 q11, #0 \n"
".p2align 2 \n"
"1: \n"
"vld1.8 {q0}, [%0]! \n"
"vld1.8 {q1}, [%1]! \n"
"subs %2, %2, #16 \n"
"vsubl.u8 q2, d0, d2 \n"
"vsubl.u8 q3, d1, d3 \n"
"vmlal.s16 q8, d4, d4 \n"
"vmlal.s16 q9, d6, d6 \n"
"vmlal.s16 q10, d5, d5 \n"
"vmlal.s16 q11, d7, d7 \n"
"bgt 1b \n"
"vadd.u32 q8, q8, q9 \n"
"vadd.u32 q10, q10, q11 \n"
"vadd.u32 q11, q8, q10 \n"
"vpaddl.u32 q1, q11 \n"
"vadd.u64 d0, d2, d3 \n"
"vmov.32 %3, d0[0] \n"
: "+r"(src_a),
"+r"(src_b),
"+r"(count),
"=r"(sse)
:
: "memory", "cc", "q0", "q1", "q2", "q3", "q8", "q9", "q10", "q11");
return sse;
}
#endif // __ARM_NEON__
#ifdef __cplusplus
} // extern "C"
} // namespace libyuv
#endif
/*
* Copyright 2012 The LibYuv 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 "libyuv/basic_types.h"
#ifdef __cplusplus
namespace libyuv {
extern "C" {
#endif
#if !defined(LIBYUV_DISABLE_NEON) && defined(__ARM_NEON__)
uint32 SumSquareError_NEON(const uint8* src_a, const uint8* src_b, int count) {
volatile uint32 sse;
asm volatile (
"vmov.u8 q8, #0 \n"
"vmov.u8 q10, #0 \n"
"vmov.u8 q9, #0 \n"
"vmov.u8 q11, #0 \n"
".p2align 2 \n"
"1: \n"
"vld1.8 {q0}, [%0]! \n"
"vld1.8 {q1}, [%1]! \n"
"subs %2, %2, #16 \n"
"vsubl.u8 q2, d0, d2 \n"
"vsubl.u8 q3, d1, d3 \n"
"vmlal.s16 q8, d4, d4 \n"
"vmlal.s16 q9, d6, d6 \n"
"vmlal.s16 q10, d5, d5 \n"
"vmlal.s16 q11, d7, d7 \n"
"bgt 1b \n"
"vadd.u32 q8, q8, q9 \n"
"vadd.u32 q10, q10, q11 \n"
"vadd.u32 q11, q8, q10 \n"
"vpaddl.u32 q1, q11 \n"
"vadd.u64 d0, d2, d3 \n"
"vmov.32 %3, d0[0] \n"
: "+r"(src_a),
"+r"(src_b),
"+r"(count),
"=r"(sse)
:
: "memory", "cc", "q0", "q1", "q2", "q3", "q8", "q9", "q10", "q11");
return sse;
}
#endif // __ARM_NEON__
#ifdef __cplusplus
} // extern "C"
} // namespace libyuv
#endif
source/compare_posix.cc
View file @ 04f40278
This diff is collapsed.
source/compare_win.cc
View file @ 04f40278
This diff is collapsed.
source/convert_from_argb.cc
View file @ 04f40278
......@@ -49,17 +49,17 @@ int ARGBToI444(const uint8* src_argb, int src_stride_argb,
ARGBToYRow_C;
void (*ARGBToUV444Row)(const uint8* src_argb, uint8* dst_u, uint8* dst_v,
int pix) = ARGBToUV444Row_C;
#if defined(HAS_ARGBTOUV444ROW_SSSE3)
if (TestCpuFlag(kCpuHasSSSE3) && width >= 16) {
ARGBToUV444Row = ARGBToUV444Row_Any_SSSE3;
if (IS_ALIGNED(width, 16)) {
ARGBToUV444Row = ARGBToUV444Row_Unaligned_SSSE3;
if (IS_ALIGNED(src_argb, 16) && IS_ALIGNED(src_stride_argb, 16)) {
ARGBToUV444Row = ARGBToUV444Row_SSSE3;
}
}
}
#endif
#if defined(HAS_ARGBTOUV444ROW_SSSE3)
if (TestCpuFlag(kCpuHasSSSE3) && width >= 16) {
ARGBToUV444Row = ARGBToUV444Row_Any_SSSE3;
if (IS_ALIGNED(width, 16)) {
ARGBToUV444Row = ARGBToUV444Row_Unaligned_SSSE3;
if (IS_ALIGNED(src_argb, 16) && IS_ALIGNED(src_stride_argb, 16)) {
ARGBToUV444Row = ARGBToUV444Row_SSSE3;
}
}
}
#endif
#if defined(HAS_ARGBTOYROW_SSSE3)
if (TestCpuFlag(kCpuHasSSSE3) && width >= 16) {
ARGBToYRow = ARGBToYRow_Any_SSSE3;
......
source/row_x86.asm
View file @ 04f40278
......@@ -28,7 +28,7 @@ cglobal %1ToYRow%3, 3, 3, 3, src_yuy2, dst_y, pix
psrlw m2, m2, 8
%endif
align 4
ALIGN 4
.convertloop:
mov%2 m0, [src_yuy2q]
mov%2 m1, [src_yuy2q + mmsize]
......@@ -74,7 +74,7 @@ cglobal SplitUVRow%2, 4, 4, 5, src_uv, dst_u, dst_v, pix
psrlw m4, m4, 8
sub dst_vq, dst_uq
align 4
ALIGN 4
.convertloop:
mov%1 m0, [src_uvq]
mov%1 m1, [src_uvq + mmsize]
......@@ -113,7 +113,7 @@ SplitUVRow a,
cglobal MergeUVRow_%2, 4, 4, 3, src_u, src_v, dst_uv, pix
sub src_vq, src_uq
align 4
ALIGN 4
.convertloop:
mov%1 m0, [src_uq]
mov%1 m1, [src_vq]
......
unit_test/convert_test.cc
View file @ 04f40278
This source diff could not be displayed because it is too large. You can view the blob instead.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment