aboutsummaryrefslogtreecommitdiffstats
path: root/libswscale/x86/rgb_2_rgb.asm
blob: 76ca1eec0339680a17ade4c56888d467612493a0 (plain) (blame)
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
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
;******************************************************************************
;* Copyright Nick Kurshev
;* Copyright Michael (michaelni@gmx.at)
;* Copyright 2018 Jokyo Images
;* Copyright Ivo van Poorten
;*
;* This file is part of FFmpeg.
;*
;* FFmpeg is free software; you can redistribute it and/or
;* modify it under the terms of the GNU Lesser General Public
;* License as published by the Free Software Foundation; either
;* version 2.1 of the License, or (at your option) any later version.
;*
;* FFmpeg is distributed in the hope that it will be useful,
;* but WITHOUT ANY WARRANTY; without even the implied warranty of
;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
;* Lesser General Public License for more details.
;*
;* You should have received a copy of the GNU Lesser General Public
;* License along with FFmpeg; if not, write to the Free Software
;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
;******************************************************************************

%include "libavutil/x86/x86util.asm"

SECTION_RODATA

pb_mask_shuffle2103_mmx times 8 dw 255
pb_shuffle2103: db 2, 1, 0, 3, 6, 5, 4, 7, 10, 9, 8, 11, 14, 13, 12, 15
pb_shuffle0321: db 0, 3, 2, 1, 4, 7, 6, 5, 8, 11, 10, 9, 12, 15, 14, 13
pb_shuffle1230: db 1, 2, 3, 0, 5, 6, 7, 4, 9, 10, 11, 8, 13, 14, 15, 12
pb_shuffle3012: db 3, 0, 1, 2, 7, 4, 5, 6, 11, 8, 9, 10, 15, 12, 13, 14
pb_shuffle3210: db 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12

SECTION .text

%macro RSHIFT_COPY 3
; %1 dst ; %2 src ; %3 shift
%if cpuflag(avx)
    psrldq  %1, %2, %3
%else
    mova           %1, %2
    RSHIFT         %1, %3
%endif
%endmacro

;------------------------------------------------------------------------------
; shuffle_bytes_2103_mmext (const uint8_t *src, uint8_t *dst, int src_size)
;------------------------------------------------------------------------------
INIT_MMX mmxext
cglobal shuffle_bytes_2103, 3, 5, 8, src, dst, w, tmp, x
    mova   m6, [pb_mask_shuffle2103_mmx]
    mova   m7, m6
    psllq  m7, 8

    movsxdifnidn wq, wd
    mov xq, wq

    add        srcq, wq
    add        dstq, wq
    neg          wq

;calc scalar loop
    and xq, mmsize*2 -4
    je .loop_simd

.loop_scalar:
   mov          tmpb, [srcq + wq + 2]
   mov [dstq+wq + 0], tmpb
   mov          tmpb, [srcq + wq + 1]
   mov [dstq+wq + 1], tmpb
   mov          tmpb, [srcq + wq + 0]
   mov [dstq+wq + 2], tmpb
   mov          tmpb, [srcq + wq + 3]
   mov [dstq+wq + 3], tmpb
   add            wq, 4
   sub            xq, 4
   jg .loop_scalar

;check if src_size < mmsize * 2
cmp wq, 0
jge .end

.loop_simd:
    movu     m0, [srcq+wq]
    movu     m1, [srcq+wq+8]

    pshufw   m3, m0, 177
    pshufw   m5, m1, 177

    pand     m0, m7
    pand     m3, m6

    pand     m1, m7
    pand     m5, m6

    por      m0, m3
    por      m1, m5

    movu      [dstq+wq], m0
    movu  [dstq+wq + 8], m1

    add              wq, mmsize*2
    jl .loop_simd

.end:
    emms
    RET

;------------------------------------------------------------------------------
; shuffle_bytes_## (const uint8_t *src, uint8_t *dst, int src_size)
;------------------------------------------------------------------------------
; %1-4 index shuffle
%macro SHUFFLE_BYTES 4
cglobal shuffle_bytes_%1%2%3%4, 3, 5, 2, src, dst, w, tmp, x
    VBROADCASTI128    m0, [pb_shuffle%1%2%3%4]
    movsxdifnidn wq, wd
    mov xq, wq

    add        srcq, wq
    add        dstq, wq
    neg          wq

;calc scalar loop
    and xq, mmsize-4
    je .loop_simd

.loop_scalar:
   mov          tmpb, [srcq + wq + %1]
   mov [dstq+wq + 0], tmpb
   mov          tmpb, [srcq + wq + %2]
   mov [dstq+wq + 1], tmpb
   mov          tmpb, [srcq + wq + %3]
   mov [dstq+wq + 2], tmpb
   mov          tmpb, [srcq + wq + %4]
   mov [dstq+wq + 3], tmpb
   add            wq, 4
   sub            xq, 4
   jg .loop_scalar

;check if src_size < mmsize
cmp wq, 0
jge .end

.loop_simd:
    movu           m1, [srcq+wq]
    pshufb         m1, m0
    movu    [dstq+wq], m1
    add            wq, mmsize
    jl .loop_simd

.end:
    RET
%endmacro

INIT_XMM ssse3
SHUFFLE_BYTES 2, 1, 0, 3
SHUFFLE_BYTES 0, 3, 2, 1
SHUFFLE_BYTES 1, 2, 3, 0
SHUFFLE_BYTES 3, 0, 1, 2
SHUFFLE_BYTES 3, 2, 1, 0

%if ARCH_X86_64
%if HAVE_AVX2_EXTERNAL
INIT_YMM avx2
SHUFFLE_BYTES 2, 1, 0, 3
SHUFFLE_BYTES 0, 3, 2, 1
SHUFFLE_BYTES 1, 2, 3, 0
SHUFFLE_BYTES 3, 0, 1, 2
SHUFFLE_BYTES 3, 2, 1, 0
%endif
%endif

;-----------------------------------------------------------------------------------------------
; uyvytoyuv422(uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
;              const uint8_t *src, int width, int height,
;              int lumStride, int chromStride, int srcStride)
;-----------------------------------------------------------------------------------------------
%macro UYVY_TO_YUV422 0
cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_stride, src_stride, wtwo, whalf, tmp, x, back_w
    pxor         m0, m0
    pcmpeqw      m1, m1
    psrlw        m1, 8

    movsxdifnidn            wq, wd
    movsxdifnidn   lum_strideq, lum_strided
    movsxdifnidn chrom_strideq, chrom_strided
    movsxdifnidn   src_strideq, src_strided

    mov     back_wq, wq
    mov      whalfq, wq
    shr      whalfq, 1     ; whalf = width / 2

    lea srcq, [srcq + wq * 2]
    add    ydstq, wq
    add    udstq, whalfq
    add    vdstq, whalfq

.loop_line:
    mov          xq, wq
    mov       wtwoq, wq
    add       wtwoq, wtwoq ; wtwo = width * 2

    neg       wq
    neg    wtwoq
    neg   whalfq

    ;calc scalar loop count
    and       xq, mmsize * 2 - 1
    je .loop_simd

    .loop_scalar:
        mov             tmpb, [srcq + wtwoq + 0]
        mov [udstq + whalfq], tmpb

        mov             tmpb, [srcq + wtwoq + 1]
        mov     [ydstq + wq], tmpb

        mov             tmpb, [srcq + wtwoq + 2]
        mov [vdstq + whalfq], tmpb

        mov             tmpb, [srcq + wtwoq + 3]
        mov [ydstq + wq + 1], tmpb

        add      wq, 2
        add   wtwoq, 4
        add  whalfq, 1
        sub      xq, 2
        jg .loop_scalar

    ; check if simd loop is need
    cmp      wq, 0
    jge .end_line

    .loop_simd:
        movu    m2, [srcq + wtwoq             ]
        movu    m3, [srcq + wtwoq + mmsize    ]
        movu    m4, [srcq + wtwoq + mmsize * 2]
        movu    m5, [srcq + wtwoq + mmsize * 3]

        ; extract y part 1
        RSHIFT_COPY    m6, m2, 1 ; UYVY UYVY -> YVYU YVY...
        pand           m6, m1; YxYx YxYx...

        RSHIFT_COPY    m7, m3, 1 ; UYVY UYVY -> YVYU YVY...
        pand           m7, m1 ; YxYx YxYx...

        packuswb       m6, m7 ; YYYY YYYY...
        movu [ydstq + wq], m6

        ; extract y part 2
        RSHIFT_COPY    m6, m4, 1 ; UYVY UYVY -> YVYU YVY...
        pand           m6, m1; YxYx YxYx...

        RSHIFT_COPY    m7, m5, 1 ; UYVY UYVY -> YVYU YVY...
        pand           m7, m1 ; YxYx YxYx...

        packuswb                m6, m7 ; YYYY YYYY...
        movu [ydstq + wq + mmsize], m6

        ; extract uv
        pand       m2, m1   ; UxVx...
        pand       m3, m1   ; UxVx...
        pand       m4, m1   ; UxVx...
        pand       m5, m1   ; UxVx...

        packuswb   m2, m3   ; UVUV...
        packuswb   m4, m5   ; UVUV...

        ; U
        pand       m6, m2, m1 ; UxUx...
        pand       m7, m4, m1 ; UxUx...

        packuswb m6, m7 ; UUUU
        movu   [udstq + whalfq], m6


        ; V
        psrlw      m2, 8  ; VxVx...
        psrlw      m4, 8  ; VxVx...
        packuswb   m2, m4 ; VVVV
        movu   [vdstq + whalfq], m2

        add   whalfq, mmsize
        add    wtwoq, mmsize * 4
        add       wq, mmsize * 2
        jl .loop_simd

    .end_line:
        add        srcq, src_strideq
        add        ydstq, lum_strideq
        add        udstq, chrom_strideq
        add        vdstq, chrom_strideq

        ;restore initial state of line variable
        mov           wq, back_wq
        mov          xq, wq
        mov      whalfq, wq
        shr      whalfq, 1     ; whalf = width / 2
        sub          hd, 1
        jg .loop_line

    RET
%endmacro

%if ARCH_X86_64
INIT_XMM sse2
UYVY_TO_YUV422

INIT_XMM avx
UYVY_TO_YUV422
%endif