summaryrefslogtreecommitdiff
path: root/chromium/third_party/libvpx/source/libvpx/vpx_scale/arm/neon/vp8_vpxyv12_copysrcframe_func_neon.asm
blob: d452ad255f4b29276b7ee96c38a71376831f3dc9 (plain)
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
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
;
;  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
;
;  Use of this source code is governed by a BSD-style license
;  that can be found in the LICENSE file in the root of the source
;  tree. An additional intellectual property rights grant can be found
;  in the file PATENTS.  All contributing project authors may
;  be found in the AUTHORS file in the root of the source tree.
;


    EXPORT  |vp8_yv12_copy_src_frame_func_neon|
    ARM
    REQUIRE8
    PRESERVE8

    INCLUDE vpx_scale_asm_offsets.asm

    AREA ||.text||, CODE, READONLY, ALIGN=2
;Note: This function is used to copy source data in src_buffer[i] at beginning of
;the encoding. The buffer has a width and height of cpi->oxcf.Width and cpi->oxcf.Height,
;which can be ANY numbers(NOT always multiples of 16 or 4).

;void vp8_yv12_copy_src_frame_func_neon(YV12_BUFFER_CONFIG *src_ybc, YV12_BUFFER_CONFIG *dst_ybc);

|vp8_yv12_copy_src_frame_func_neon| PROC
    push            {r4 - r11, lr}
    vpush           {d8 - d15}

    ;Copy Y plane
    ldr             r4, [r0, #yv12_buffer_config_y_height]
    ldr             r5, [r0, #yv12_buffer_config_y_width]
    ldr             r6, [r0, #yv12_buffer_config_y_stride]
    ldr             r7, [r1, #yv12_buffer_config_y_stride]
    ldr             r2, [r0, #yv12_buffer_config_y_buffer]       ;srcptr1
    ldr             r3, [r1, #yv12_buffer_config_y_buffer]       ;dstptr1

    add             r10, r2, r6             ;second row src
    add             r11, r3, r7             ;second row dst
    mov             r6, r6, lsl #1
    mov             r7, r7, lsl #1
    sub             r6, r6, r5              ;adjust stride
    sub             r7, r7, r5

    ; copy two rows at one time
    mov             lr, r4, lsr #1

cp_src_to_dst_height_loop
    mov             r12, r5

cp_width_128_loop
    vld1.8          {q0, q1}, [r2]!
    vld1.8          {q4, q5}, [r10]!
    vld1.8          {q2, q3}, [r2]!
    vld1.8          {q6, q7}, [r10]!
    vld1.8          {q8, q9}, [r2]!
    vld1.8          {q12, q13}, [r10]!
    vld1.8          {q10, q11}, [r2]!
    vld1.8          {q14, q15}, [r10]!
    sub             r12, r12, #128
    cmp             r12, #128
    vst1.8          {q0, q1}, [r3]!
    vst1.8          {q4, q5}, [r11]!
    vst1.8          {q2, q3}, [r3]!
    vst1.8          {q6, q7}, [r11]!
    vst1.8          {q8, q9}, [r3]!
    vst1.8          {q12, q13}, [r11]!
    vst1.8          {q10, q11}, [r3]!
    vst1.8          {q14, q15}, [r11]!
    bhs             cp_width_128_loop

    cmp             r12, #0
    beq             cp_width_done

cp_width_8_loop
    vld1.8          {d0}, [r2]!
    vld1.8          {d1}, [r10]!
    sub             r12, r12, #8
    cmp             r12, #8
    vst1.8          {d0}, [r3]!
    vst1.8          {d1}, [r11]!
    bhs             cp_width_8_loop

    cmp             r12, #0
    beq             cp_width_done

cp_width_1_loop
    ldrb            r8, [r2], #1
    subs            r12, r12, #1
    strb            r8, [r3], #1
    ldrb            r8, [r10], #1
    strb            r8, [r11], #1
    bne             cp_width_1_loop

cp_width_done
    subs            lr, lr, #1
    add             r2, r2, r6
    add             r3, r3, r7
    add             r10, r10, r6
    add             r11, r11, r7
    bne             cp_src_to_dst_height_loop

;copy last line for Y if y_height is odd
    tst             r4, #1
    beq             cp_width_done_1
    mov             r12, r5

cp_width_128_loop_1
    vld1.8          {q0, q1}, [r2]!
    vld1.8          {q2, q3}, [r2]!
    vld1.8          {q8, q9}, [r2]!
    vld1.8          {q10, q11}, [r2]!
    sub             r12, r12, #128
    cmp             r12, #128
    vst1.8          {q0, q1}, [r3]!
    vst1.8          {q2, q3}, [r3]!
    vst1.8          {q8, q9}, [r3]!
    vst1.8          {q10, q11}, [r3]!
    bhs             cp_width_128_loop_1

    cmp             r12, #0
    beq             cp_width_done_1

cp_width_8_loop_1
    vld1.8          {d0}, [r2]!
    sub             r12, r12, #8
    cmp             r12, #8
    vst1.8          {d0}, [r3]!
    bhs             cp_width_8_loop_1

    cmp             r12, #0
    beq             cp_width_done_1

cp_width_1_loop_1
    ldrb            r8, [r2], #1
    subs            r12, r12, #1
    strb            r8, [r3], #1
    bne             cp_width_1_loop_1
cp_width_done_1

;Copy U & V planes
    ldr             r4, [r0, #yv12_buffer_config_uv_height]
    ldr             r5, [r0, #yv12_buffer_config_uv_width]
    ldr             r6, [r0, #yv12_buffer_config_uv_stride]
    ldr             r7, [r1, #yv12_buffer_config_uv_stride]
    ldr             r2, [r0, #yv12_buffer_config_u_buffer]       ;srcptr1
    ldr             r3, [r1, #yv12_buffer_config_u_buffer]       ;dstptr1

    add             r10, r2, r6             ;second row src
    add             r11, r3, r7             ;second row dst
    mov             r6, r6, lsl #1
    mov             r7, r7, lsl #1
    sub             r6, r6, r5              ;adjust stride
    sub             r7, r7, r5

    mov             r9, #2

cp_uv_loop
    ;copy two rows at one time
    mov             lr, r4, lsr #1

cp_src_to_dst_height_uv_loop
    mov             r12, r5

cp_width_uv_64_loop
    vld1.8          {q0, q1}, [r2]!
    vld1.8          {q4, q5}, [r10]!
    vld1.8          {q2, q3}, [r2]!
    vld1.8          {q6, q7}, [r10]!
    sub             r12, r12, #64
    cmp             r12, #64
    vst1.8          {q0, q1}, [r3]!
    vst1.8          {q4, q5}, [r11]!
    vst1.8          {q2, q3}, [r3]!
    vst1.8          {q6, q7}, [r11]!
    bhs             cp_width_uv_64_loop

    cmp             r12, #0
    beq             cp_width_uv_done

cp_width_uv_8_loop
    vld1.8          {d0}, [r2]!
    vld1.8          {d1}, [r10]!
    sub             r12, r12, #8
    cmp             r12, #8
    vst1.8          {d0}, [r3]!
    vst1.8          {d1}, [r11]!
    bhs             cp_width_uv_8_loop

    cmp             r12, #0
    beq             cp_width_uv_done

cp_width_uv_1_loop
    ldrb            r8, [r2], #1
    subs            r12, r12, #1
    strb            r8, [r3], #1
    ldrb            r8, [r10], #1
    strb            r8, [r11], #1
    bne             cp_width_uv_1_loop

cp_width_uv_done
    subs            lr, lr, #1
    add             r2, r2, r6
    add             r3, r3, r7
    add             r10, r10, r6
    add             r11, r11, r7
    bne             cp_src_to_dst_height_uv_loop

;copy last line for U & V if uv_height is odd
    tst             r4, #1
    beq             cp_width_uv_done_1
    mov             r12, r5

cp_width_uv_64_loop_1
    vld1.8          {q0, q1}, [r2]!
    vld1.8          {q2, q3}, [r2]!
    sub             r12, r12, #64
    cmp             r12, #64
    vst1.8          {q0, q1}, [r3]!
    vst1.8          {q2, q3}, [r3]!
    bhs             cp_width_uv_64_loop_1

    cmp             r12, #0
    beq             cp_width_uv_done_1

cp_width_uv_8_loop_1
    vld1.8          {d0}, [r2]!
    sub             r12, r12, #8
    cmp             r12, #8
    vst1.8          {d0}, [r3]!
    bhs             cp_width_uv_8_loop_1

    cmp             r12, #0
    beq             cp_width_uv_done_1

cp_width_uv_1_loop_1
    ldrb            r8, [r2], #1
    subs            r12, r12, #1
    strb            r8, [r3], #1
    bne             cp_width_uv_1_loop_1
cp_width_uv_done_1

    subs            r9, r9, #1
    ldrne           r2, [r0, #yv12_buffer_config_v_buffer]      ;srcptr1
    ldrne           r3, [r1, #yv12_buffer_config_v_buffer]      ;dstptr1
    ldrne           r10, [r0, #yv12_buffer_config_uv_stride]
    ldrne           r11, [r1, #yv12_buffer_config_uv_stride]

    addne           r10, r2, r10                ;second row src
    addne           r11, r3, r11                ;second row dst

    bne             cp_uv_loop

    vpop            {d8 - d15}
    pop             {r4 - r11, pc}

    ENDP
    END