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
|
/* blend mask x color -> dst */
#ifdef BUILD_SSE3
static void
_op_blend_mas_c_dp_sse3(DATA32 *s __UNUSED__, DATA8 *m, DATA32 c, DATA32 *d, int l) {
const __m128i c_packed = _mm_set_epi32(c, c, c, c);
LOOP_ALIGNED_U1_A48_SSE3(d, l,
{ /* UOP */
DATA32 a = *m;
DATA32 mc = MUL_SYM(a, c);
a = 256 - (mc >> 24);
*d = mc + MUL_256(a, *d);
m++; d++; l--;
},
{ /* A4OP */
if ((m[3] | m[2] | m[1] | m[0]) == 0) {
m += 4; d += 4; l -= 4;
continue;
}
__m128i m0 = _mm_set_epi32(m[3], m[2], m[1], m[0]);
__m128i d0 = _mm_load_si128((__m128i *)d);
__m128i mc0 = mul_sym_sse3(m0, c_packed);
__m128i a0 = sub4_alpha_sse3(mc0);
__m128i mul0 = mul_256_sse3(a0, d0);
mul0 = _mm_add_epi32(mul0, mc0);
_mm_store_si128((__m128i *)d, mul0);
m += 4; d += 4; l -= 4;
},
{ /* A8OP */
if((m[7] | m[6] | m[5] | m[4] | m[3] | m[2] | m[1] | m[0]) == 0) {
m += 8; d += 8; l -= 8;
continue;
}
__m128i m0 = _mm_set_epi32(m[3], m[2], m[1], m[0]);
__m128i d0 = _mm_load_si128((__m128i *)d);
__m128i m1 = _mm_set_epi32(m[7], m[6], m[5], m[4]);
__m128i d1 = _mm_load_si128((__m128i *)(d+4));
__m128i mc0 = mul_sym_sse3(m0, c_packed);
__m128i a0 = sub4_alpha_sse3(mc0);
__m128i mul0 = mul_256_sse3(a0, d0);
mul0 = _mm_add_epi32(mc0, mul0);
__m128i mc1 = mul_sym_sse3(m1, c_packed);
__m128i a1 = sub4_alpha_sse3(mc1);
__m128i mul1 = mul_256_sse3(a1, d1);
mul1 = _mm_add_epi32(mc1, mul1);
_mm_store_si128((__m128i *)d, mul0);
_mm_store_si128((__m128i *)(d+4), mul1);
m += 8; d += 8; l -= 8;
})
}
static void
_op_blend_mas_can_dp_sse3(DATA32 *s __UNUSED__, DATA8 *m, DATA32 c, DATA32 *d, int l) {
DATA32 alpha;
const __m128i one = _mm_set_epi32(1, 1, 1, 1);
const __m128i c_packed = _mm_set_epi32(c, c, c, c);
LOOP_ALIGNED_U1_A48_SSE3(d, l,
{ /* UOP */
alpha = *m;
switch(alpha)
{
case 0:
break;
case 255:
*d = c;
break;
default:
alpha++;
*d = INTERP_256(alpha, c, *d);
break;
}
m++; d++; l--;
},
{ /* A4OP */
if ((m[3] | m[2] | m[1] | m[0]) == 0) {
m += 4; d += 4; l -= 4;
continue;
}
__m128i m0 = _mm_set_epi32(m[3], m[2], m[1], m[0]);
__m128i d0 = _mm_load_si128((__m128i *)d);
__m128i zm0 = _mm_cmpeq_epi32(m0, _mm_setzero_si128());
m0 = _mm_add_epi32(one, m0);
__m128i r0 = interp4_256_sse3(m0, c_packed, d0);
r0 = _mm_and_si128(~zm0, r0);
d0 = _mm_and_si128(zm0, d0);
d0 = _mm_add_epi32(r0, d0);
_mm_store_si128((__m128i *)d, d0);
m += 4; d += 4; l -= 4;
},
{ /* A8OP */
if ((m[7] | m[6] | m[5] | m[4] | m[3] | m[2] | m[1] | m[0]) == 0) {
m += 8; d += 8; l -= 8;
continue;
}
__m128i m0 = _mm_set_epi32(m[3], m[2], m[1], m[0]);
__m128i d0 = _mm_load_si128((__m128i *)d);
__m128i m1 = _mm_set_epi32(m[7], m[6], m[5], m[4]);
__m128i d1 = _mm_load_si128((__m128i *)(d+4));
__m128i zm0 = _mm_cmpeq_epi32(m0, _mm_setzero_si128());
__m128i zm1 = _mm_cmpeq_epi32(m1, _mm_setzero_si128());
m0 = _mm_add_epi32(one, m0);
m1 = _mm_add_epi32(one, m1);
__m128i r0 = interp4_256_sse3(m0, c_packed, d0);
__m128i r1 = interp4_256_sse3(m1, c_packed, d1);
r0 = _mm_and_si128(~zm0, r0);
d0 = _mm_and_si128(zm0, d0);
r1 = _mm_and_si128(~zm1, r1);
d1 = _mm_and_si128(zm1, d1);
d0 = _mm_add_epi32(d0, r0);
d1 = _mm_add_epi32(d1, r1);
_mm_store_si128((__m128i *)d, d0);
_mm_store_si128((__m128i *)(d+4), d1);
m += 8; d += 8; l -= 8;
})
}
#define _op_blend_mas_cn_dp_sse3 _op_blend_mas_can_dp_sse3
#define _op_blend_mas_caa_dp_sse3 _op_blend_mas_c_dp_sse3
#define _op_blend_mas_c_dpan_sse3 _op_blend_mas_c_dp_sse3
#define _op_blend_mas_cn_dpan_sse3 _op_blend_mas_cn_dp_sse3
#define _op_blend_mas_can_dpan_sse3 _op_blend_mas_can_dp_sse3
#define _op_blend_mas_caa_dpan_sse3 _op_blend_mas_caa_dp_sse3
static void
init_blend_mask_color_span_funcs_sse3(void)
{
// FIXME: BUGGY BUGGY Core i5 750 (32bit), 4.5.2 (Ubuntu/Linaro 4.5.2-8ubuntu4), ello (text and rectangle)
// op_blend_span_funcs[SP_N][SM_AS][SC][DP][CPU_SSE3] = _op_blend_mas_c_dp_sse3;
op_blend_span_funcs[SP_N][SM_AS][SC_N][DP][CPU_SSE3] = _op_blend_mas_cn_dp_sse3;
op_blend_span_funcs[SP_N][SM_AS][SC_AN][DP][CPU_SSE3] = _op_blend_mas_can_dp_sse3;
op_blend_span_funcs[SP_N][SM_AS][SC_AA][DP][CPU_SSE3] = _op_blend_mas_caa_dp_sse3;
// FIXME: BUGGY BUGGY Core i5 2500 (64bit), gcc version 4.5.2 (Ubuntu/Linaro 4.5.2-8ubuntu4), ello (text)
// op_blend_span_funcs[SP_N][SM_AS][SC][DP_AN][CPU_SSE3] = _op_blend_mas_c_dpan_sse3;
op_blend_span_funcs[SP_N][SM_AS][SC_N][DP_AN][CPU_SSE3] = _op_blend_mas_cn_dpan_sse3;
op_blend_span_funcs[SP_N][SM_AS][SC_AN][DP_AN][CPU_SSE3] = _op_blend_mas_can_dpan_sse3;
op_blend_span_funcs[SP_N][SM_AS][SC_AA][DP_AN][CPU_SSE3] = _op_blend_mas_caa_dpan_sse3;
}
#define _op_blend_pt_mas_c_dp_sse3 NULL
#define _op_blend_pt_mas_can_dp_sse3 NULL
#define _op_blend_pt_mas_cn_dp_sse3 _op_blend_pt_mas_can_dp_sse3
#define _op_blend_pt_mas_caa_dp_sse3 _op_blend_pt_mas_c_dp_sse3
#define _op_blend_pt_mas_c_dpan_sse3 _op_blend_pt_mas_c_dp_sse3
#define _op_blend_pt_mas_cn_dpan_sse3 _op_blend_pt_mas_cn_dp_sse3
#define _op_blend_pt_mas_can_dpan_sse3 _op_blend_pt_mas_can_dp_sse3
#define _op_blend_pt_mas_caa_dpan_sse3 _op_blend_pt_mas_caa_dp_sse3
static void
init_blend_mask_color_pt_funcs_sse3(void)
{
op_blend_pt_funcs[SP_N][SM_AS][SC][DP][CPU_SSE3] = _op_blend_pt_mas_c_dp_sse3;
op_blend_pt_funcs[SP_N][SM_AS][SC_N][DP][CPU_SSE3] = _op_blend_pt_mas_cn_dp_sse3;
op_blend_pt_funcs[SP_N][SM_AS][SC_AN][DP][CPU_SSE3] = _op_blend_pt_mas_can_dp_sse3;
op_blend_pt_funcs[SP_N][SM_AS][SC_AA][DP][CPU_SSE3] = _op_blend_pt_mas_caa_dp_sse3;
op_blend_pt_funcs[SP_N][SM_AS][SC][DP_AN][CPU_SSE3] = _op_blend_pt_mas_c_dpan_sse3;
op_blend_pt_funcs[SP_N][SM_AS][SC_N][DP_AN][CPU_SSE3] = _op_blend_pt_mas_cn_dpan_sse3;
op_blend_pt_funcs[SP_N][SM_AS][SC_AN][DP_AN][CPU_SSE3] = _op_blend_pt_mas_can_dpan_sse3;
op_blend_pt_funcs[SP_N][SM_AS][SC_AA][DP_AN][CPU_SSE3] = _op_blend_pt_mas_caa_dpan_sse3;
}
/*-----*/
/* blend_rel mask x color --> dst */
static void
_op_blend_rel_mas_c_dp_sse3(DATA32 *s __UNUSED__, DATA8 *m, DATA32 c, DATA32 *d, int l) {
const __m128i c_packed = _mm_set_epi32(c, c, c, c);
LOOP_ALIGNED_U1_A48_SSE3(d, l,
{ /* UOP */
DATA32 mc = MUL_SYM(*m, c);
int alpha = 256 - (mc >> 24);
*d = MUL_SYM(*d >> 24, mc) + MUL_256(alpha, *d);
d++; m++; l--;
},
{ /* A4OP */
__m128i m0 = _mm_set_epi32(m[3], m[2], m[1], m[0]);
__m128i d0 = _mm_load_si128((__m128i *) d);
__m128i mc0 = mul_sym_sse3(m0, c_packed);
__m128i a0 = sub4_alpha_sse3(mc0);
__m128i d0_sym = mul_sym_sse3(_mm_srli_epi32(d0, 24), mc0);
d0 = mul_256_sse3(a0, d0);
d0 = _mm_add_epi32(d0, d0_sym);
_mm_store_si128((__m128i *)d, d0);
d += 4; m += 4; l -= 4;
},
{ /* A8OP */
__m128i m0 = _mm_set_epi32(m[3], m[2], m[1], m[0]);
__m128i d0 = _mm_load_si128((__m128i *)d);
__m128i m1 = _mm_set_epi32(m[7], m[6], m[5], m[4]);
__m128i d1 = _mm_load_si128((__m128i *)(d+4));
__m128i mc0 = mul_sym_sse3(m0, c_packed);
__m128i mc1 = mul_sym_sse3(m1, c_packed);
__m128i a0 = sub4_alpha_sse3(mc0);
__m128i a1 = sub4_alpha_sse3(mc1);
__m128i d0_sym = mul_sym_sse3(_mm_srli_epi32(d0, 24), mc0);
__m128i d1_sym = mul_sym_sse3(_mm_srli_epi32(d1, 24), mc1);
d0 = mul_256_sse3(a0, d0);
d1 = mul_256_sse3(a1, d1);
d0 = _mm_add_epi32(d0, d0_sym);
d1 = _mm_add_epi32(d1, d1_sym);
_mm_store_si128((__m128i *)d, d0);
_mm_store_si128((__m128i *)(d+4), d1);
d += 8; m += 8; l -= 8;
})
}
#define _op_blend_rel_mas_cn_dp_sse3 _op_blend_rel_mas_c_dp_sse3
#define _op_blend_rel_mas_can_dp_sse3 _op_blend_rel_mas_c_dp_sse3
#define _op_blend_rel_mas_caa_dp_sse3 _op_blend_rel_mas_c_dp_sse3
#define _op_blend_rel_mas_c_dpan_sse3 _op_blend_mas_c_dpan_sse3
#define _op_blend_rel_mas_cn_dpan_sse3 _op_blend_mas_cn_dpan_sse3
#define _op_blend_rel_mas_can_dpan_sse3 _op_blend_mas_can_dpan_sse3
#define _op_blend_rel_mas_caa_dpan_sse3 _op_blend_mas_caa_dpan_sse3
static void
init_blend_rel_mask_color_span_funcs_sse3(void)
{
op_blend_rel_span_funcs[SP_N][SM_AS][SC][DP][CPU_SSE3] = _op_blend_rel_mas_c_dp_sse3;
op_blend_rel_span_funcs[SP_N][SM_AS][SC_N][DP][CPU_SSE3] = _op_blend_rel_mas_can_dp_sse3;
op_blend_rel_span_funcs[SP_N][SM_AS][SC_AN][DP][CPU_SSE3] = _op_blend_rel_mas_can_dp_sse3;
op_blend_rel_span_funcs[SP_N][SM_AS][SC_AA][DP][CPU_SSE3] = _op_blend_rel_mas_caa_dp_sse3;
op_blend_rel_span_funcs[SP_N][SM_AS][SC][DP_AN][CPU_SSE3] = _op_blend_rel_mas_c_dpan_sse3;
op_blend_rel_span_funcs[SP_N][SM_AS][SC_N][DP_AN][CPU_SSE3] = _op_blend_rel_mas_cn_dpan_sse3;
op_blend_rel_span_funcs[SP_N][SM_AS][SC_AN][DP_AN][CPU_SSE3] = _op_blend_rel_mas_can_dpan_sse3;
op_blend_rel_span_funcs[SP_N][SM_AS][SC_AA][DP_AN][CPU_SSE3] = _op_blend_rel_mas_caa_dpan_sse3;
}
#define _op_blend_rel_pt_mas_c_dp_sse3 NULL
#define _op_blend_rel_pt_mas_cn_dp_sse3 _op_blend_rel_pt_mas_c_dp_sse3
#define _op_blend_rel_pt_mas_can_dp_sse3 _op_blend_rel_pt_mas_c_dp_sse3
#define _op_blend_rel_pt_mas_caa_dp_sse3 _op_blend_rel_pt_mas_c_dp_sse3
#define _op_blend_rel_pt_mas_c_dpan_sse3 _op_blend_pt_mas_c_dpan_sse3
#define _op_blend_rel_pt_mas_cn_dpan_sse3 _op_blend_pt_mas_cn_dpan_sse3
#define _op_blend_rel_pt_mas_can_dpan_sse3 _op_blend_pt_mas_can_dpan_sse3
#define _op_blend_rel_pt_mas_caa_dpan_sse3 _op_blend_pt_mas_caa_dpan_sse3
static void
init_blend_rel_mask_color_pt_funcs_sse3(void)
{
op_blend_rel_pt_funcs[SP_N][SM_AS][SC][DP][CPU_SSE3] = _op_blend_rel_pt_mas_c_dp_sse3;
op_blend_rel_pt_funcs[SP_N][SM_AS][SC_N][DP][CPU_SSE3] = _op_blend_rel_pt_mas_cn_dp_sse3;
op_blend_rel_pt_funcs[SP_N][SM_AS][SC_AN][DP][CPU_SSE3] = _op_blend_rel_pt_mas_can_dp_sse3;
op_blend_rel_pt_funcs[SP_N][SM_AS][SC_AA][DP][CPU_SSE3] = _op_blend_rel_pt_mas_caa_dp_sse3;
op_blend_rel_pt_funcs[SP_N][SM_AS][SC][DP_AN][CPU_SSE3] = _op_blend_rel_pt_mas_c_dpan_sse3;
op_blend_rel_pt_funcs[SP_N][SM_AS][SC_N][DP_AN][CPU_SSE3] = _op_blend_rel_pt_mas_cn_dpan_sse3;
op_blend_rel_pt_funcs[SP_N][SM_AS][SC_AN][DP_AN][CPU_SSE3] = _op_blend_rel_pt_mas_can_dpan_sse3;
op_blend_rel_pt_funcs[SP_N][SM_AS][SC_AA][DP_AN][CPU_SSE3] = _op_blend_rel_pt_mas_caa_dpan_sse3;
}
#endif
|
