/* * 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_COMMON_X86_AV1_TXFM_SSE2_H_ #define AOM_AV1_COMMON_X86_AV1_TXFM_SSE2_H_ #include <emmintrin.h> // SSE2 #include "config/aom_config.h" #include "config/av1_rtcd.h" #include "aom/aom_integer.h" #include "aom_dsp/x86/transpose_sse2.h" #include "aom_dsp/x86/txfm_common_sse2.h" #include "av1/common/av1_txfm.h" #ifdef __cplusplus extern "C" { #endif static inline void btf_16_w4_sse2( const __m128i *const w0, const __m128i *const w1, const __m128i __rounding, const int8_t cos_bit, const __m128i *const in0, const __m128i *const in1, __m128i *const out0, __m128i *const out1) { … } #define btf_16_4p_sse2(w0, w1, in0, in1, out0, out1) … #define btf_16_sse2(w0, w1, in0, in1, out0, out1) … static inline __m128i load_16bit_to_16bit(const int16_t *a) { … } static inline __m128i load_32bit_to_16bit(const int32_t *a) { … } static inline __m128i load_32bit_to_16bit_w4(const int32_t *a) { … } // Store 4 16 bit values. Sign extend the values. static inline void store_16bit_to_32bit_w4(const __m128i a, int32_t *const b) { … } // Store 8 16 bit values. Sign extend the values. static inline void store_16bit_to_32bit(__m128i a, int32_t *b) { … } static inline __m128i scale_round_sse2(const __m128i a, const int scale) { … } static inline void store_rect_16bit_to_32bit_w4(const __m128i a, int32_t *const b) { … } static inline void store_rect_16bit_to_32bit(const __m128i a, int32_t *const b) { … } static inline void load_buffer_16bit_to_16bit_w4(const int16_t *const in, const int stride, __m128i *const out, const int out_size) { … } static inline void load_buffer_16bit_to_16bit_w4_flip(const int16_t *const in, const int stride, __m128i *const out, const int out_size) { … } static inline void load_buffer_16bit_to_16bit(const int16_t *in, int stride, __m128i *out, int out_size) { … } static inline void load_buffer_16bit_to_16bit_flip(const int16_t *in, int stride, __m128i *out, int out_size) { … } static inline void load_buffer_32bit_to_16bit(const int32_t *in, int stride, __m128i *out, int out_size) { … } static inline void load_buffer_32bit_to_16bit_w4(const int32_t *in, int stride, __m128i *out, int out_size) { … } static inline void load_buffer_32bit_to_16bit_flip(const int32_t *in, int stride, __m128i *out, int out_size) { … } static inline void store_buffer_16bit_to_32bit_w4(const __m128i *const in, int32_t *const out, const int stride, const int out_size) { … } static inline void store_buffer_16bit_to_32bit_w8(const __m128i *const in, int32_t *const out, const int stride, const int out_size) { … } static inline void store_rect_buffer_16bit_to_32bit_w4(const __m128i *const in, int32_t *const out, const int stride, const int out_size) { … } static inline void store_rect_buffer_16bit_to_32bit_w8(const __m128i *const in, int32_t *const out, const int stride, const int out_size) { … } static inline void store_buffer_16bit_to_16bit_8x8(const __m128i *in, uint16_t *out, const int stride) { … } static inline void round_shift_16bit(__m128i *in, int size, int bit) { … } static inline void flip_buf_sse2(__m128i *in, __m128i *out, int size) { … } void av1_lowbd_fwd_txfm2d_4x4_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_4x8_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_4x16_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_8x4_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_8x8_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_8x16_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_8x32_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_16x4_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_16x8_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_16x16_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_16x32_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_32x8_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_32x16_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_32x32_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_16x64_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); void av1_lowbd_fwd_txfm2d_64x16_sse2(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); transform_1d_sse2; void av1_iadst8_sse2(const __m128i *input, __m128i *output); void av1_idct8_sse2(const __m128i *input, __m128i *output); transform_2d_sse2; #ifdef __cplusplus } #endif // __cplusplus #endif // AOM_AV1_COMMON_X86_AV1_TXFM_SSE2_H_
Codebase Browser
chromium