chromium/third_party/libaom/source/libaom/av1/encoder/x86/av1_txfm1d_sse4.h

/*
 * Copyright (c) 2018, Alliance for Open Media. All rights reserved.
 *
 * This source code is subject to the terms of the BSD 2 Clause License and
 * the Alliance for Open Media Patent License 1.0. If the BSD 2 Clause License
 * was not distributed with this source code in the LICENSE file, you can
 * obtain it at www.aomedia.org/license/software. If the Alliance for Open
 * Media Patent License 1.0 was not distributed with this source code in the
 * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
 */

#ifndef AOM_AV1_ENCODER_X86_AV1_TXFM1D_SSE4_H_
#define AOM_AV1_ENCODER_X86_AV1_TXFM1D_SSE4_H_

#include <smmintrin.h>
#include "av1/common/av1_txfm.h"
#include "av1/common/x86/av1_txfm_sse4.h"

#ifdef __cplusplus
extern "C" {
#endif

void av1_fdct4_sse4_1(const __m128i *input, __m128i *output,
                      const int8_t cos_bit, const int8_t *stage_range);
void av1_fdct8_sse4_1(const __m128i *input, __m128i *output,
                      const int8_t cos_bit, const int8_t *stage_range);
void av1_fdct16_sse4_1(const __m128i *input, __m128i *output,
                       const int8_t cos_bit, const int8_t *stage_range);
void av1_fdct32_sse4_1(__m128i *input, __m128i *output, int cos_bit,
                       const int stride);
void av1_fdct64_sse4_1(__m128i *input, __m128i *output, int8_t cos_bit,
                       const int instride, const int outstride);
void av1_fadst4_sse4_1(const __m128i *input, __m128i *output,
                       const int8_t cos_bit, const int8_t *stage_range);
void av1_fadst8_sse4_1(const __m128i *input, __m128i *output,
                       const int8_t cos_bit, const int8_t *stage_range);
void av1_fadst16_sse4_1(const __m128i *input, __m128i *output,
                        const int8_t cos_bit, const int8_t *stage_range);

void av1_idct4_sse4_1(const __m128i *input, __m128i *output,
                      const int8_t cos_bit, const int8_t *stage_range);
void av1_idct8_sse4_1(const __m128i *input, __m128i *output,
                      const int8_t cos_bit, const int8_t *stage_range);
void av1_idct16_sse4_1(const __m128i *input, __m128i *output,
                       const int8_t cos_bit, const int8_t *stage_range);
void av1_idct32_sse4_1(const __m128i *input, __m128i *output,
                       const int8_t cos_bit, const int8_t *stage_range);
void av1_idct64_sse4_1(const __m128i *input, __m128i *output,
                       const int8_t cos_bit, const int8_t *stage_range);

void av1_iadst4_sse4_1(const __m128i *input, __m128i *output,
                       const int8_t cos_bit, const int8_t *stage_range);
void av1_iadst8_sse4_1(const __m128i *input, __m128i *output,
                       const int8_t cos_bit, const int8_t *stage_range);
void av1_iadst16_sse4_1(const __m128i *input, __m128i *output,
                        const int8_t cos_bit, const int8_t *stage_range);

void av1_idtx32_sse4_1(__m128i *input, __m128i *output, int cos_bit,
                       const int col_num);

static inline void transpose_32_4x4(int stride, const __m128i *input,
                                    __m128i *output) { … }

// the entire input block can be represent by a grid of 4x4 blocks
// each 4x4 blocks can be represent by 4 vertical __m128i
// we first transpose each 4x4 block internally
// then transpose the grid
static inline void transpose_32(int txfm_size, const __m128i *input,
                                __m128i *output) { … }

// out0 = in0*w0 + in1*w1
// out1 = -in1*w0 + in0*w1
#define btf_32_sse4_1_type0(w0, w1, in0, in1, out0, out1, bit) …

// out0 = in0*w0 + in1*w1
// out1 = in1*w0 - in0*w1
#define btf_32_sse4_1_type1(w0, w1, in0, in1, out0, out1, bit) …

// out0 = in0*w0 + in1*w1
// out1 = -in1*w0 + in0*w1
#define btf_32_type0_sse4_1_new(ww0, ww1, in0, in1, out0, out1, r, bit) …

// out0 = in0*w0 + in1*w1
// out1 = in1*w0 - in0*w1
#define btf_32_type1_sse4_1_new(ww0, ww1, in0, in1, out0, out1, r, bit) …

#ifdef __cplusplus
}
#endif

#endif  // AOM_AV1_ENCODER_X86_AV1_TXFM1D_SSE4_H_