summaryrefslogtreecommitdiff
path: root/pixman/pixman-arm-simd.c
blob: f5953259fb0984621028a4bb021cbf4fbe0845d1 (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
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
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
/*
 * Copyright © 2008 Mozilla Corporation
 *
 * Permission to use, copy, modify, distribute, and sell this software and its
 * documentation for any purpose is hereby granted without fee, provided that
 * the above copyright notice appear in all copies and that both that
 * copyright notice and this permission notice appear in supporting
 * documentation, and that the name of Mozilla Corporation not be used in
 * advertising or publicity pertaining to distribution of the software without
 * specific, written prior permission.  Mozilla Corporation makes no
 * representations about the suitability of this software for any purpose.  It
 * is provided "as is" without express or implied warranty.
 *
 * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS
 * SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
 * FITNESS, IN NO EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY
 * SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
 * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN
 * AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING
 * OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS
 * SOFTWARE.
 *
 * Author:  Jeff Muizelaar (jeff@infidigm.net)
 *
 */
#ifdef HAVE_CONFIG_H
#include <config.h>
#endif

#include "pixman-arm-simd.h"

void
fbCompositeSrcAdd_8000x8000arm (pixman_op_t op,
				pixman_image_t * pSrc,
				pixman_image_t * pMask,
				pixman_image_t * pDst,
				int16_t      xSrc,
				int16_t      ySrc,
				int16_t      xMask,
				int16_t      yMask,
				int16_t      xDst,
				int16_t      yDst,
				uint16_t     width,
				uint16_t     height)
{
    uint8_t	*dstLine, *dst;
    uint8_t	*srcLine, *src;
    int	dstStride, srcStride;
    uint16_t	w;
    uint8_t	s, d;

    fbComposeGetStart (pSrc, xSrc, ySrc, uint8_t, srcStride, srcLine, 1);
    fbComposeGetStart (pDst, xDst, yDst, uint8_t, dstStride, dstLine, 1);

    while (height--)
    {
	dst = dstLine;
	dstLine += dstStride;
	src = srcLine;
	srcLine += srcStride;
	w = width;

	while (w && (((unsigned long)dst & 3) || ((unsigned long)src & 3)))
	{
	    s = *src;
	    d = *dst;
	    asm("uqadd8 %0, %1, %2" : "+r"(d) : "r"(s));
	    *dst = d;

	    dst++;
	    src++;
	    w--;
	}

	while (w >= 4)
	{
	    asm("uqadd8 %0, %1, %2" : "=r"(*(uint32_t*)dst) : "r"(*(uint32_t*)src), "r"(*(uint32_t*)dst));
	    dst += 4;
	    src += 4;
	    w -= 4;
	}

	while (w)
	{
	    s = *src;
	    d = *dst;
	    asm("uqadd8 %0, %1, %2" : "+r"(d) : "r"(s));
	    *dst = d;

	    dst++;
	    src++;
	    w--;
	}
    }

}

void
fbCompositeSrc_8888x8888arm (pixman_op_t op,
			 pixman_image_t * pSrc,
			 pixman_image_t * pMask,
			 pixman_image_t * pDst,
			 int16_t      xSrc,
			 int16_t      ySrc,
			 int16_t      xMask,
			 int16_t      yMask,
			 int16_t      xDst,
			 int16_t      yDst,
			 uint16_t     width,
			 uint16_t     height)
{
    uint32_t	*dstLine, *dst;
    uint32_t	*srcLine, *src;
    int	dstStride, srcStride;
    uint16_t	w;
    uint32_t component_half = 0x800080;
    uint32_t upper_component_mask = 0xff00ff00;
    uint32_t alpha_mask = 0xff;

    fbComposeGetStart (pDst, xDst, yDst, uint32_t, dstStride, dstLine, 1);
    fbComposeGetStart (pSrc, xSrc, ySrc, uint32_t, srcStride, srcLine, 1);

    while (height--)
    {
	dst = dstLine;
	dstLine += dstStride;
	src = srcLine;
	srcLine += srcStride;
	w = width;

//#define inner_branch
	asm volatile (
			"cmp %[w], #0\n\t"
			"beq 2f\n\t"
			"1:\n\t"
			/* load src */
			"ldr r5, [%[src]], #4\n\t"
#ifdef inner_branch
			/* We can avoid doing the multiplication in two cases: 0x0 or 0xff.
			 * The 0x0 case also allows us to avoid doing an unecessary data
			 * write which is more valuable so we only check for that */
			"cmp r5, #0\n\t"
			"beq 3f\n\t"

			/* = 255 - alpha */
			"sub r8, %[alpha_mask], r5, lsr #24\n\t"

			"ldr r4, [%[dest]] \n\t"

#else
			"ldr r4, [%[dest]] \n\t"

			/* = 255 - alpha */
			"sub r8, %[alpha_mask], r5, lsr #24\n\t"
#endif
			"uxtb16 r6, r4\n\t"
			"uxtb16 r7, r4, ror #8\n\t"

			/* multiply by 257 and divide by 65536 */
			"mla r6, r6, r8, %[component_half]\n\t"
			"mla r7, r7, r8, %[component_half]\n\t"

			"uxtab16 r6, r6, r6, ror #8\n\t"
			"uxtab16 r7, r7, r7, ror #8\n\t"

			/* recombine the 0xff00ff00 bytes of r6 and r7 */
			"and r7, r7, %[upper_component_mask]\n\t"
			"uxtab16 r6, r7, r6, ror #8\n\t"

			"uqadd8 r5, r6, r5\n\t"

#ifdef inner_branch
			"3:\n\t"

#endif
			"str r5, [%[dest]], #4\n\t"
			/* increment counter and jmp to top */
			"subs	%[w], %[w], #1\n\t"
			"bne	1b\n\t"
			"2:\n\t"
			: [w] "+r" (w), [dest] "+r" (dst), [src] "+r" (src)
			: [component_half] "r" (component_half), [upper_component_mask] "r" (upper_component_mask),
			  [alpha_mask] "r" (alpha_mask)
			: "r4", "r5", "r6", "r7", "r8", "cc", "memory"
			);
    }
}

void
fbCompositeSrc_8888x8x8888arm (pixman_op_t op,
			       pixman_image_t * pSrc,
			       pixman_image_t * pMask,
			       pixman_image_t * pDst,
			       int16_t	xSrc,
			       int16_t	ySrc,
			       int16_t      xMask,
			       int16_t      yMask,
			       int16_t      xDst,
			       int16_t      yDst,
			       uint16_t     width,
			       uint16_t     height)
{
    uint32_t	*dstLine, *dst;
    uint32_t	*srcLine, *src;
    uint32_t	mask;
    int	dstStride, srcStride;
    uint16_t	w;
    uint32_t component_half = 0x800080;
    uint32_t alpha_mask = 0xff;

    fbComposeGetStart (pDst, xDst, yDst, uint32_t, dstStride, dstLine, 1);
    fbComposeGetStart (pSrc, xSrc, ySrc, uint32_t, srcStride, srcLine, 1);

    fbComposeGetSolid (pMask, mask, pDst->bits.format);
    mask = (mask) >> 24;

    while (height--)
    {
	dst = dstLine;
	dstLine += dstStride;
	src = srcLine;
	srcLine += srcStride;
	w = width;

//#define inner_branch
	asm volatile (
			"cmp %[w], #0\n\t"
			"beq 2f\n\t"
			"1:\n\t"
			/* load src */
			"ldr r5, [%[src]], #4\n\t"
#ifdef inner_branch
			/* We can avoid doing the multiplication in two cases: 0x0 or 0xff.
			 * The 0x0 case also allows us to avoid doing an unecessary data
			 * write which is more valuable so we only check for that */
			"cmp r5, #0\n\t"
			"beq 3f\n\t"

#endif
			"ldr r4, [%[dest]] \n\t"

			"uxtb16 r6, r5\n\t"
			"uxtb16 r7, r5, ror #8\n\t"

			/* multiply by alpha (r8) then by 257 and divide by 65536 */
			"mla r6, r6, %[mask_alpha], %[component_half]\n\t"
			"mla r7, r7, %[mask_alpha], %[component_half]\n\t"

			"uxtab16 r6, r6, r6, ror #8\n\t"
			"uxtab16 r7, r7, r7, ror #8\n\t"

			"uxtb16 r6, r6, ror #8\n\t"
			"uxtb16 r7, r7, ror #8\n\t"

			/* recombine */
			"orr r5, r6, r7, lsl #8\n\t"

			"uxtb16 r6, r4\n\t"
			"uxtb16 r7, r4, ror #8\n\t"

			/* 255 - alpha */
			"sub r8, %[alpha_mask], r5, lsr #24\n\t"

			/* multiply by alpha (r8) then by 257 and divide by 65536 */
			"mla r6, r6, r8, %[component_half]\n\t"
			"mla r7, r7, r8, %[component_half]\n\t"

			"uxtab16 r6, r6, r6, ror #8\n\t"
			"uxtab16 r7, r7, r7, ror #8\n\t"

			"uxtb16 r6, r6, ror #8\n\t"
			"uxtb16 r7, r7, ror #8\n\t"

			/* recombine */
			"orr r6, r6, r7, lsl #8\n\t"

			"uqadd8 r5, r6, r5\n\t"

#ifdef inner_branch
			"3:\n\t"

#endif
			"str r5, [%[dest]], #4\n\t"
			/* increment counter and jmp to top */
			"subs	%[w], %[w], #1\n\t"
			"bne	1b\n\t"
			"2:\n\t"
			: [w] "+r" (w), [dest] "+r" (dst), [src] "+r" (src)
			: [component_half] "r" (component_half), [mask_alpha] "r" (mask),
			  [alpha_mask] "r" (alpha_mask)
			: "r4", "r5", "r6", "r7", "r8", "r9", "cc", "memory"
			);
    }
}

void
fbCompositeSolidMask_nx8x8888arm (pixman_op_t      op,
			       pixman_image_t * pSrc,
			       pixman_image_t * pMask,
			       pixman_image_t * pDst,
			       int16_t      xSrc,
			       int16_t      ySrc,
			       int16_t      xMask,
			       int16_t      yMask,
			       int16_t      xDst,
			       int16_t      yDst,
			       uint16_t     width,
			       uint16_t     height)
{
    uint32_t	 src, srca;
    uint32_t	*dstLine, *dst;
    uint8_t	*maskLine, *mask;
    int		 dstStride, maskStride;
    uint16_t	 w;

    fbComposeGetSolid(pSrc, src, pDst->bits.format);

    srca = src >> 24;
    if (src == 0)
	return;

    uint32_t component_mask = 0xff00ff;
    uint32_t component_half = 0x800080;

    uint32_t src_hi = (src >> 8) & component_mask;
    uint32_t src_lo = src & component_mask;

    fbComposeGetStart (pDst, xDst, yDst, uint32_t, dstStride, dstLine, 1);
    fbComposeGetStart (pMask, xMask, yMask, uint8_t, maskStride, maskLine, 1);

    while (height--)
    {
	dst = dstLine;
	dstLine += dstStride;
	mask = maskLine;
	maskLine += maskStride;
	w = width;

//#define inner_branch
	asm volatile (
			"cmp %[w], #0\n\t"
			"beq 2f\n\t"
			"1:\n\t"
			/* load mask */
			"ldrb r5, [%[mask]], #1\n\t"
#ifdef inner_branch
			/* We can avoid doing the multiplication in two cases: 0x0 or 0xff.
			 * The 0x0 case also allows us to avoid doing an unecessary data
			 * write which is more valuable so we only check for that */
			"cmp r5, #0\n\t"
			"beq 3f\n\t"

#endif
			"ldr r4, [%[dest]] \n\t"

			/* multiply by alpha (r8) then by 257 and divide by 65536 */
			"mla r6, %[src_lo], r5, %[component_half]\n\t"
			"mla r7, %[src_hi], r5, %[component_half]\n\t"

			"uxtab16 r6, r6, r6, ror #8\n\t"
			"uxtab16 r7, r7, r7, ror #8\n\t"

			"uxtb16 r6, r6, ror #8\n\t"
			"uxtb16 r7, r7, ror #8\n\t"

			/* recombine */
			"orr r5, r6, r7, lsl #8\n\t"

			"uxtb16 r6, r4\n\t"
			"uxtb16 r7, r4, ror #8\n\t"

			/* we could simplify this to use 'sub' if we were
			 * willing to give up a register for alpha_mask */
			"mvn r8, r5\n\t"
			"mov r8, r8, lsr #24\n\t"

			/* multiply by alpha (r8) then by 257 and divide by 65536 */
			"mla r6, r6, r8, %[component_half]\n\t"
			"mla r7, r7, r8, %[component_half]\n\t"

			"uxtab16 r6, r6, r6, ror #8\n\t"
			"uxtab16 r7, r7, r7, ror #8\n\t"

			"uxtb16 r6, r6, ror #8\n\t"
			"uxtb16 r7, r7, ror #8\n\t"

			/* recombine */
			"orr r6, r6, r7, lsl #8\n\t"

			"uqadd8 r5, r6, r5\n\t"

#ifdef inner_branch
			"3:\n\t"

#endif
			"str r5, [%[dest]], #4\n\t"
			/* increment counter and jmp to top */
			"subs	%[w], %[w], #1\n\t"
			"bne	1b\n\t"
			"2:\n\t"
			: [w] "+r" (w), [dest] "+r" (dst), [src] "+r" (src), [mask] "+r" (mask)
			: [component_half] "r" (component_half),
			  [src_hi] "r" (src_hi), [src_lo] "r" (src_lo)
			: "r4", "r5", "r6", "r7", "r8", "cc", "memory"
			);
    }
}