1 /*!
2 * \copy
3 * Copyright (c) 2009-2013, Cisco Systems
4 * All rights reserved.
5 *
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions
8 * are met:
9 *
10 * * Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 *
13 * * Redistributions in binary form must reproduce the above copyright
14 * notice, this list of conditions and the following disclaimer in
15 * the documentation and/or other materials provided with the
16 * distribution.
17 *
18 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
19 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
20 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
21 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
22 * COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
23 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
24 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
25 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
26 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
27 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
28 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
29 * POSSIBILITY OF SUCH DAMAGE.
30 *
31 *
32 * \file get_intra_predictor.c
33 *
34 * \brief implementation for get intra predictor about 16x16, 4x4, chroma.
35 *
36 * \date 4/2/2009 Created
37 * 9/14/2009 C level based optimization with high performance gained.
38 * [const, using ST32/ST64 to replace memset, memcpy and memmove etc.]
39 *
40 *************************************************************************************
41 */
42 #include "ls_defines.h"
43 #include "cpu_core.h"
44 #include "intra_pred_common.h"
45
46
WelsI16x16LumaPredV_c(uint8_t * pPred,uint8_t * pRef,const int32_t kiStride)47 void WelsI16x16LumaPredV_c (uint8_t* pPred, uint8_t* pRef, const int32_t kiStride) {
48 uint8_t i = 15;
49 const int8_t* kpSrc = (int8_t*)&pRef[-kiStride];
50 const uint64_t kuiT1 = LD64 (kpSrc);
51 const uint64_t kuiT2 = LD64 (kpSrc + 8);
52 uint8_t* pDst = pPred;
53
54 do {
55 ST64 (pDst , kuiT1);
56 ST64 (pDst + 8, kuiT2);
57 pDst += 16;
58 } while (i-- > 0);
59 }
60
WelsI16x16LumaPredH_c(uint8_t * pPred,uint8_t * pRef,const int32_t kiStride)61 void WelsI16x16LumaPredH_c (uint8_t* pPred, uint8_t* pRef, const int32_t kiStride) {
62 int32_t iStridex15 = (kiStride << 4) - kiStride;
63 int32_t iPredStride = 16;
64 int32_t iPredStridex15 = 240; //(iPredStride<<4)-iPredStride;
65 uint8_t i = 15;
66
67 do {
68 const uint8_t kuiSrc8 = pRef[iStridex15 - 1];
69 const uint64_t kuiV64 = (uint64_t) (0x0101010101010101ULL * kuiSrc8);
70 ST64 (&pPred[iPredStridex15], kuiV64);
71 ST64 (&pPred[iPredStridex15 + 8], kuiV64);
72
73 iStridex15 -= kiStride;
74 iPredStridex15 -= iPredStride;
75 } while (i-- > 0);
76 }
77
78