1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
|
///*****************************************************************************
//*
//* Copyright (C) 2012 Ittiam Systems Pvt Ltd, Bangalore
//*
//* Licensed under the Apache License, Version 2.0 (the "License");
//* you may not use this file except in compliance with the License.
//* You may obtain a copy of the License at:
//*
//* http://www.apache.org/licenses/LICENSE-2.0
//*
//* Unless required by applicable law or agreed to in writing, software
//* distributed under the License is distributed on an "AS IS" BASIS,
//* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
//* See the License for the specific language governing permissions and
//* limitations under the License.
//*
//*****************************************************************************/
///**
//*******************************************************************************
//* @file
//* ihevc_intra_pred_luma_mode_18_34_neon.s
//*
//* @brief
//* contains function definitions for intra prediction dc filtering.
//* functions are coded using neon intrinsics and can be compiled using
//* rvct
//*
//* @author
//* yogeswaran rs
//*
//* @par list of functions:
//*
//*
//* @remarks
//* none
//*
//*******************************************************************************
//*/
///**
//*******************************************************************************
//*
//* @brief
//* luma intraprediction filter for dc input
//*
//* @par description:
//*
//* @param[in] pu1_ref
//* uword8 pointer to the source
//*
//* @param[out] pu1_dst
//* uword8 pointer to the destination
//*
//* @param[in] src_strd
//* integer source stride
//*
//* @param[in] dst_strd
//* integer destination stride
//*
//* @param[in] pi1_coeff
//* word8 pointer to the planar coefficients
//*
//* @param[in] nt
//* size of tranform block
//*
//* @param[in] mode
//* type of filtering
//*
//* @returns
//*
//* @remarks
//* none
//*
//*******************************************************************************
//*/
//void ihevc_intra_pred_chroma_mode_18_34(uword8 *pu1_ref,
// word32 src_strd,
// uword8 *pu1_dst,
// word32 dst_strd,
// word32 nt,
// word32 mode)
//
//**************variables vs registers*****************************************
//x0 => *pu1_ref
//x1 => src_strd
//x2 => *pu1_dst
//x3 => dst_strd
//stack contents from #40
// nt
// mode
// pi1_coeff
.text
.align 4
.include "ihevc_neon_macros.s"
.globl ihevc_intra_pred_chroma_mode_18_34_av8
.type ihevc_intra_pred_chroma_mode_18_34_av8, %function
ihevc_intra_pred_chroma_mode_18_34_av8:
// stmfd sp!, {x4-x12, x14} //stack stores the values of the arguments
push_v_regs
stp x19, x20,[sp,#-16]!
cmp x4,#4
beq mode2_4
mov x12,x4
mov x11,x4
add x0,x0,x4,lsl #2
cmp x5,#0x22
mov x10,x2
add x0,x0,#4
sub x20,x0,#4
csel x0, x20, x0,ne
mov x20,#2
csel x6, x20, x6,eq
mov x20,#-2
csel x6, x20, x6,ne
mov x8,x0
kernel:
ld1 {v0.8b, v1.8b},[x8],x6
st1 {v0.8b, v1.8b},[x10],x3
ld1 {v2.8b, v3.8b},[x8],x6
st1 {v2.8b, v3.8b},[x10],x3
ld1 {v4.8b, v5.8b},[x8],x6
st1 {v4.8b, v5.8b},[x10],x3
ld1 {v6.8b, v7.8b},[x8],x6
st1 {v6.8b, v7.8b},[x10],x3
ld1 {v8.8b, v9.8b},[x8],x6
st1 {v8.8b, v9.8b},[x10],x3
ld1 {v10.8b, v11.8b},[x8],x6
st1 {v10.8b, v11.8b},[x10],x3
ld1 {v12.8b, v13.8b},[x8],x6
st1 {v12.8b, v13.8b},[x10],x3
ld1 {v14.8b, v15.8b},[x8],x6
st1 {v14.8b, v15.8b},[x10],x3
subs x12,x12,#8
bne kernel
cmp x11,#16
add x8,x0,#16
add x10,x2,#16
sub x11, x11,#16
mov x12,#16
beq kernel
b end_func
mode2_4:
add x0,x0,#20
cmp x5,#0x22
sub x20,x0,#4
csel x0, x20, x0,ne
mov x20,#2
csel x8, x20, x8,eq
mov x20,#-2
csel x8, x20, x8,ne
ld1 {v0.8b},[x0],x8
st1 {v0.2s},[x2],x3
ld1 {v0.8b},[x0],x8
st1 {v0.2s},[x2],x3
ld1 {v0.8b},[x0],x8
st1 {v0.2s},[x2],x3
ld1 {v0.8b},[x0],x8
st1 {v0.2s},[x2],x3
end_func:
// ldmfd sp!,{x4-x12,x15} //reload the registers from sp
ldp x19, x20,[sp],#16
pop_v_regs
ret
|
