xref: /aosp_15_r20/external/libaom/av1/common/x86/cdef_block_sse4.c (revision 77c1e3ccc04c968bd2bc212e87364f250e820521)
1 /*
2  * Copyright (c) 2016, Alliance for Open Media. All rights reserved.
3  *
4  * This source code is subject to the terms of the BSD 2 Clause License and
5  * the Alliance for Open Media Patent License 1.0. If the BSD 2 Clause License
6  * was not distributed with this source code in the LICENSE file, you can
7  * obtain it at www.aomedia.org/license/software. If the Alliance for Open
8  * Media Patent License 1.0 was not distributed with this source code in the
9  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
10  */
11 
12 #include "aom_dsp/aom_simd.h"
13 #define SIMD_FUNC(name) name##_sse4_1
14 #include "av1/common/cdef_block_simd.h"
15 
cdef_find_dir_dual_sse4_1(const uint16_t * img1,const uint16_t * img2,int stride,int32_t * var_out_1st,int32_t * var_out_2nd,int coeff_shift,int * out_dir_1st_8x8,int * out_dir_2nd_8x8)16 void cdef_find_dir_dual_sse4_1(const uint16_t *img1, const uint16_t *img2,
17                                int stride, int32_t *var_out_1st,
18                                int32_t *var_out_2nd, int coeff_shift,
19                                int *out_dir_1st_8x8, int *out_dir_2nd_8x8) {
20   // Process first 8x8.
21   *out_dir_1st_8x8 = cdef_find_dir(img1, stride, var_out_1st, coeff_shift);
22 
23   // Process second 8x8.
24   *out_dir_2nd_8x8 = cdef_find_dir(img2, stride, var_out_2nd, coeff_shift);
25 }
26 
cdef_copy_rect8_8bit_to_16bit_sse4_1(uint16_t * dst,int dstride,const uint8_t * src,int sstride,int width,int height)27 void cdef_copy_rect8_8bit_to_16bit_sse4_1(uint16_t *dst, int dstride,
28                                           const uint8_t *src, int sstride,
29                                           int width, int height) {
30   int j = 0;
31   for (int i = 0; i < height; i++) {
32     for (j = 0; j < (width & ~0x7); j += 8) {
33       v64 row = v64_load_unaligned(&src[i * sstride + j]);
34       v128_store_unaligned(&dst[i * dstride + j], v128_unpack_u8_s16(row));
35     }
36     for (; j < width; j++) {
37       dst[i * dstride + j] = src[i * sstride + j];
38     }
39   }
40 }
41