-
-
Notifications
You must be signed in to change notification settings - Fork 1.6k
/
GSVector4i.h
2362 lines (1840 loc) · 62.1 KB
/
GSVector4i.h
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
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Copyright (C) 2007-2017 Gabest
* http://www.gabest.org
*
* This Program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2, or (at your option)
* any later version.
*
* This Program 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with GNU Make; see the file COPYING. If not, write to
* the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA USA.
* http://www.gnu.org/copyleft/gpl.html
*
*/
class alignas(16) GSVector4i
{
static GSVector4i m_xff[17];
static GSVector4i m_x0f[17];
public:
union
{
struct {int x, y, z, w;};
struct {int r, g, b, a;};
struct {int left, top, right, bottom;};
int v[4];
float f32[4];
int8 i8[16];
int16 i16[8];
int32 i32[4];
int64 i64[2];
uint8 u8[16];
uint16 u16[8];
uint32 u32[4];
uint64 u64[2];
__m128i m;
};
static void InitVectors();
__forceinline GSVector4i()
{
x = 0;
y = 0;
z = 0;
w = 0;
}
__forceinline GSVector4i(int x, int y, int z, int w)
{
// 4 gprs
// m = _mm_set_epi32(w, z, y, x);
// 2 gprs
GSVector4i xz = load(x).upl32(load(z));
GSVector4i yw = load(y).upl32(load(w));
*this = xz.upl32(yw);
}
__forceinline GSVector4i(int x, int y)
{
*this = load(x).upl32(load(y));
}
__forceinline GSVector4i(short s0, short s1, short s2, short s3, short s4, short s5, short s6, short s7)
{
m = _mm_set_epi16(s7, s6, s5, s4, s3, s2, s1, s0);
}
__forceinline GSVector4i(char b0, char b1, char b2, char b3, char b4, char b5, char b6, char b7, char b8, char b9, char b10, char b11, char b12, char b13, char b14, char b15)
{
m = _mm_set_epi8(b15, b14, b13, b12, b11, b10, b9, b8, b7, b6, b5, b4, b3, b2, b1, b0);
}
__forceinline GSVector4i(const GSVector4i& v)
{
m = v.m;
}
__forceinline explicit GSVector4i(const GSVector2i& v)
{
m = _mm_loadl_epi64((__m128i*)&v);
}
__forceinline explicit GSVector4i(int i)
{
*this = i;
}
__forceinline explicit GSVector4i(__m128i m)
{
this->m = m;
}
__forceinline explicit GSVector4i(const GSVector4& v, bool truncate = true);
__forceinline static GSVector4i cast(const GSVector4& v);
#if _M_SSE >= 0x500
__forceinline static GSVector4i cast(const GSVector8& v);
#endif
#if _M_SSE >= 0x501
__forceinline static GSVector4i cast(const GSVector8i& v);
#endif
__forceinline void operator = (const GSVector4i& v)
{
m = v.m;
}
__forceinline void operator = (int i)
{
#if _M_SSE >= 0x501
m = _mm_broadcastd_epi32(_mm_cvtsi32_si128(i));
#else
m = _mm_set1_epi32(i);
#endif
}
__forceinline void operator = (__m128i m)
{
this->m = m;
}
__forceinline operator __m128i() const
{
return m;
}
// rect
__forceinline int width() const
{
return right - left;
}
__forceinline int height() const
{
return bottom - top;
}
__forceinline GSVector4i rsize() const
{
return *this - xyxy(); // same as GSVector4i(0, 0, width(), height());
}
__forceinline unsigned int rarea() const
{
return width() * height();
}
__forceinline bool rempty() const
{
return (*this < zwzw()).mask() != 0x00ff;
}
__forceinline GSVector4i runion(const GSVector4i& a) const
{
int i = (upl64(a) < uph64(a)).mask();
if(i == 0xffff)
{
return runion_ordered(a);
}
if((i & 0x00ff) == 0x00ff)
{
return *this;
}
if((i & 0xff00) == 0xff00)
{
return a;
}
return GSVector4i::zero();
}
__forceinline GSVector4i runion_ordered(const GSVector4i& a) const
{
#if _M_SSE >= 0x401
return min_i32(a).upl64(max_i32(a).srl<8>());
#else
return GSVector4i(std::min(x, a.x), std::min(y, a.y), std::max(z, a.z), std::max(w, a.w));
#endif
}
__forceinline GSVector4i rintersect(const GSVector4i& a) const
{
return sat_i32(a);
}
template<int mode> __forceinline GSVector4i ralign(const GSVector2i& a) const
{
// a must be 1 << n
GSVector4i mask = GSVector4i(a) - GSVector4i(1, 1);
GSVector4i v;
switch(mode)
{
case Align_Inside: v = *this + mask; break;
case Align_Outside: v = *this + mask.zwxy(); break;
case Align_NegInf: v = *this; break;
case Align_PosInf: v = *this + mask.zwzw(); break;
default: ASSERT(0); break;
}
return v.andnot(mask.xyxy());
}
GSVector4i fit(int arx, int ary) const;
GSVector4i fit(int preset) const;
#ifdef _WIN32
__forceinline operator LPCRECT() const
{
return (LPCRECT)this;
}
__forceinline operator LPRECT()
{
return (LPRECT)this;
}
#endif
//
__forceinline uint32 rgba32() const
{
GSVector4i v = *this;
v = v.ps32(v);
v = v.pu16(v);
return (uint32)store(v);
}
#if _M_SSE >= 0x401
__forceinline GSVector4i sat_i8(const GSVector4i& a, const GSVector4i& b) const
{
return max_i8(a).min_i8(b);
}
__forceinline GSVector4i sat_i8(const GSVector4i& a) const
{
return max_i8(a.xyxy()).min_i8(a.zwzw());
}
#endif
__forceinline GSVector4i sat_i16(const GSVector4i& a, const GSVector4i& b) const
{
return max_i16(a).min_i16(b);
}
__forceinline GSVector4i sat_i16(const GSVector4i& a) const
{
return max_i16(a.xyxy()).min_i16(a.zwzw());
}
#if _M_SSE >= 0x401
__forceinline GSVector4i sat_i32(const GSVector4i& a, const GSVector4i& b) const
{
return max_i32(a).min_i32(b);
}
__forceinline GSVector4i sat_i32(const GSVector4i& a) const
{
return max_i32(a.xyxy()).min_i32(a.zwzw());
}
#else
__forceinline GSVector4i sat_i32(const GSVector4i& a, const GSVector4i& b) const
{
GSVector4i v;
v.x = std::min(std::max(x, a.x), b.x);
v.y = std::min(std::max(y, a.y), b.y);
v.z = std::min(std::max(z, a.z), b.z);
v.w = std::min(std::max(w, a.w), b.w);
return v;
}
__forceinline GSVector4i sat_i32(const GSVector4i& a) const
{
GSVector4i v;
v.x = std::min(std::max(x, a.x), a.z);
v.y = std::min(std::max(y, a.y), a.w);
v.z = std::min(std::max(z, a.x), a.z);
v.w = std::min(std::max(w, a.y), a.w);
return v;
}
#endif
__forceinline GSVector4i sat_u8(const GSVector4i& a, const GSVector4i& b) const
{
return max_u8(a).min_u8(b);
}
__forceinline GSVector4i sat_u8(const GSVector4i& a) const
{
return max_u8(a.xyxy()).min_u8(a.zwzw());
}
#if _M_SSE >= 0x401
__forceinline GSVector4i sat_u16(const GSVector4i& a, const GSVector4i& b) const
{
return max_u16(a).min_u16(b);
}
__forceinline GSVector4i sat_u16(const GSVector4i& a) const
{
return max_u16(a.xyxy()).min_u16(a.zwzw());
}
#endif
#if _M_SSE >= 0x401
__forceinline GSVector4i sat_u32(const GSVector4i& a, const GSVector4i& b) const
{
return max_u32(a).min_u32(b);
}
__forceinline GSVector4i sat_u32(const GSVector4i& a) const
{
return max_u32(a.xyxy()).min_u32(a.zwzw());
}
#endif
#if _M_SSE >= 0x401
__forceinline GSVector4i min_i8(const GSVector4i& a) const
{
return GSVector4i(_mm_min_epi8(m, a));
}
__forceinline GSVector4i max_i8(const GSVector4i& a) const
{
return GSVector4i(_mm_max_epi8(m, a));
}
#endif
__forceinline GSVector4i min_i16(const GSVector4i& a) const
{
return GSVector4i(_mm_min_epi16(m, a));
}
__forceinline GSVector4i max_i16(const GSVector4i& a) const
{
return GSVector4i(_mm_max_epi16(m, a));
}
#if _M_SSE >= 0x401
__forceinline GSVector4i min_i32(const GSVector4i& a) const
{
return GSVector4i(_mm_min_epi32(m, a));
}
__forceinline GSVector4i max_i32(const GSVector4i& a) const
{
return GSVector4i(_mm_max_epi32(m, a));
}
#endif
__forceinline GSVector4i min_u8(const GSVector4i& a) const
{
return GSVector4i(_mm_min_epu8(m, a));
}
__forceinline GSVector4i max_u8(const GSVector4i& a) const
{
return GSVector4i(_mm_max_epu8(m, a));
}
#if _M_SSE >= 0x401
__forceinline GSVector4i min_u16(const GSVector4i& a) const
{
return GSVector4i(_mm_min_epu16(m, a));
}
__forceinline GSVector4i max_u16(const GSVector4i& a) const
{
return GSVector4i(_mm_max_epu16(m, a));
}
__forceinline GSVector4i min_u32(const GSVector4i& a) const
{
return GSVector4i(_mm_min_epu32(m, a));
}
__forceinline GSVector4i max_u32(const GSVector4i& a) const
{
return GSVector4i(_mm_max_epu32(m, a));
}
#endif
__forceinline static int min_i16(int a, int b)
{
return store(load(a).min_i16(load(b)));
}
__forceinline GSVector4i clamp8() const
{
return pu16().upl8();
}
__forceinline GSVector4i blend8(const GSVector4i& a, const GSVector4i& mask) const
{
#if _M_SSE >= 0x401
return GSVector4i(_mm_blendv_epi8(m, a, mask));
#else
return GSVector4i(_mm_or_si128(_mm_andnot_si128(mask, m), _mm_and_si128(mask, a)));
#endif
}
#if _M_SSE >= 0x401
template<int mask> __forceinline GSVector4i blend16(const GSVector4i& a) const
{
return GSVector4i(_mm_blend_epi16(m, a, mask));
}
#endif
#if _M_SSE >= 0x501
template<int mask> __forceinline GSVector4i blend32(const GSVector4i& v) const
{
return GSVector4i(_mm_blend_epi32(m, v.m, mask));
}
#endif
__forceinline GSVector4i blend(const GSVector4i& a, const GSVector4i& mask) const
{
return GSVector4i(_mm_or_si128(_mm_andnot_si128(mask, m), _mm_and_si128(mask, a)));
}
__forceinline GSVector4i mix16(const GSVector4i& a) const
{
#if _M_SSE >= 0x401
return blend16<0xaa>(a);
#else
return blend8(a, GSVector4i::xffff0000());
#endif
}
#if _M_SSE >= 0x301
__forceinline GSVector4i shuffle8(const GSVector4i& mask) const
{
return GSVector4i(_mm_shuffle_epi8(m, mask));
}
#endif
__forceinline GSVector4i ps16(const GSVector4i& a) const
{
return GSVector4i(_mm_packs_epi16(m, a));
}
__forceinline GSVector4i ps16() const
{
return GSVector4i(_mm_packs_epi16(m, m));
}
__forceinline GSVector4i pu16(const GSVector4i& a) const
{
return GSVector4i(_mm_packus_epi16(m, a));
}
__forceinline GSVector4i pu16() const
{
return GSVector4i(_mm_packus_epi16(m, m));
}
__forceinline GSVector4i ps32(const GSVector4i& a) const
{
return GSVector4i(_mm_packs_epi32(m, a));
}
__forceinline GSVector4i ps32() const
{
return GSVector4i(_mm_packs_epi32(m, m));
}
#if _M_SSE >= 0x401
__forceinline GSVector4i pu32(const GSVector4i& a) const
{
return GSVector4i(_mm_packus_epi32(m, a));
}
__forceinline GSVector4i pu32() const
{
return GSVector4i(_mm_packus_epi32(m, m));
}
#endif
__forceinline GSVector4i upl8(const GSVector4i& a) const
{
return GSVector4i(_mm_unpacklo_epi8(m, a));
}
__forceinline GSVector4i uph8(const GSVector4i& a) const
{
return GSVector4i(_mm_unpackhi_epi8(m, a));
}
__forceinline GSVector4i upl16(const GSVector4i& a) const
{
return GSVector4i(_mm_unpacklo_epi16(m, a));
}
__forceinline GSVector4i uph16(const GSVector4i& a) const
{
return GSVector4i(_mm_unpackhi_epi16(m, a));
}
__forceinline GSVector4i upl32(const GSVector4i& a) const
{
return GSVector4i(_mm_unpacklo_epi32(m, a));
}
__forceinline GSVector4i uph32(const GSVector4i& a) const
{
return GSVector4i(_mm_unpackhi_epi32(m, a));
}
__forceinline GSVector4i upl64(const GSVector4i& a) const
{
return GSVector4i(_mm_unpacklo_epi64(m, a));
}
__forceinline GSVector4i uph64(const GSVector4i& a) const
{
return GSVector4i(_mm_unpackhi_epi64(m, a));
}
__forceinline GSVector4i upl8() const
{
#if 0 // _M_SSE >= 0x401 // TODO: compiler bug
return GSVector4i(_mm_cvtepu8_epi16(m));
#else
return GSVector4i(_mm_unpacklo_epi8(m, _mm_setzero_si128()));
#endif
}
__forceinline GSVector4i uph8() const
{
return GSVector4i(_mm_unpackhi_epi8(m, _mm_setzero_si128()));
}
__forceinline GSVector4i upl16() const
{
#if 0 //_M_SSE >= 0x401 // TODO: compiler bug
return GSVector4i(_mm_cvtepu16_epi32(m));
#else
return GSVector4i(_mm_unpacklo_epi16(m, _mm_setzero_si128()));
#endif
}
__forceinline GSVector4i uph16() const
{
return GSVector4i(_mm_unpackhi_epi16(m, _mm_setzero_si128()));
}
__forceinline GSVector4i upl32() const
{
#if 0 //_M_SSE >= 0x401 // TODO: compiler bug
return GSVector4i(_mm_cvtepu32_epi64(m));
#else
return GSVector4i(_mm_unpacklo_epi32(m, _mm_setzero_si128()));
#endif
}
__forceinline GSVector4i uph32() const
{
return GSVector4i(_mm_unpackhi_epi32(m, _mm_setzero_si128()));
}
__forceinline GSVector4i upl64() const
{
return GSVector4i(_mm_unpacklo_epi64(m, _mm_setzero_si128()));
}
__forceinline GSVector4i uph64() const
{
return GSVector4i(_mm_unpackhi_epi64(m, _mm_setzero_si128()));
}
#if _M_SSE >= 0x401
// WARNING!!!
//
// MSVC (2008, 2010 ctp) believes that there is a "mem, reg" form of the pmovz/sx* instructions,
// turning these intrinsics into a minefield, don't spill regs when using them...
__forceinline GSVector4i i8to16() const
{
return GSVector4i(_mm_cvtepi8_epi16(m));
}
__forceinline GSVector4i u8to16() const
{
return GSVector4i(_mm_cvtepu8_epi16(m));
}
__forceinline GSVector4i i8to32() const
{
return GSVector4i(_mm_cvtepi8_epi32(m));
}
__forceinline GSVector4i u8to32() const
{
return GSVector4i(_mm_cvtepu8_epi32(m));
}
__forceinline GSVector4i i8to64() const
{
return GSVector4i(_mm_cvtepi8_epi64(m));
}
__forceinline GSVector4i u8to64() const
{
return GSVector4i(_mm_cvtepu16_epi64(m));
}
__forceinline GSVector4i i16to32() const
{
return GSVector4i(_mm_cvtepi16_epi32(m));
}
__forceinline GSVector4i u16to32() const
{
return GSVector4i(_mm_cvtepu16_epi32(m));
}
__forceinline GSVector4i i16to64() const
{
return GSVector4i(_mm_cvtepi16_epi64(m));
}
__forceinline GSVector4i u16to64() const
{
return GSVector4i(_mm_cvtepu16_epi64(m));
}
__forceinline GSVector4i i32to64() const
{
return GSVector4i(_mm_cvtepi32_epi64(m));
}
__forceinline GSVector4i u32to64() const
{
return GSVector4i(_mm_cvtepu32_epi64(m));
}
#else
__forceinline GSVector4i u8to16() const
{
return upl8();
}
__forceinline GSVector4i u8to32() const
{
return upl8().upl16();
}
__forceinline GSVector4i u8to64() const
{
return upl8().upl16().upl32();
}
__forceinline GSVector4i u16to32() const
{
return upl16();
}
__forceinline GSVector4i u16to64() const
{
return upl16().upl32();
}
__forceinline GSVector4i u32to64() const
{
return upl32();
}
__forceinline GSVector4i i8to16() const
{
return zero().upl8(*this).sra16(8);
}
__forceinline GSVector4i i16to32() const
{
return zero().upl16(*this).sra32(16);
}
#endif
template<int i> __forceinline GSVector4i srl() const
{
return GSVector4i(_mm_srli_si128(m, i));
}
template<int i> __forceinline GSVector4i srl(const GSVector4i& v)
{
#if _M_SSE >= 0x301
return GSVector4i(_mm_alignr_epi8(v.m, m, i));
#else
if(i == 0) return *this;
else if(i < 16) return srl<i>() | v.sll<16 - i>();
else if(i == 16) return v;
else if(i < 32) return v.srl<i - 16>();
else return zero();
#endif
}
template<int i> __forceinline GSVector4i sll() const
{
return GSVector4i(_mm_slli_si128(m, i));
}
__forceinline GSVector4i sra16(int i) const
{
return GSVector4i(_mm_srai_epi16(m, i));
}
__forceinline GSVector4i sra16(__m128i i) const
{
return GSVector4i(_mm_sra_epi16(m, i));
}
__forceinline GSVector4i sra32(int i) const
{
return GSVector4i(_mm_srai_epi32(m, i));
}
__forceinline GSVector4i sra32(__m128i i) const
{
return GSVector4i(_mm_sra_epi32(m, i));
}
__forceinline GSVector4i sll16(int i) const
{
return GSVector4i(_mm_slli_epi16(m, i));
}
__forceinline GSVector4i sll16(__m128i i) const
{
return GSVector4i(_mm_sll_epi16(m, i));
}
__forceinline GSVector4i sll32(int i) const
{
return GSVector4i(_mm_slli_epi32(m, i));
}
__forceinline GSVector4i sll32(__m128i i) const
{
return GSVector4i(_mm_sll_epi32(m, i));
}
#if _M_SSE >= 0x501
__forceinline GSVector4i sllv32(__m128i i) const
{
return GSVector4i(_mm_sllv_epi32(m, i));
}
#endif
__forceinline GSVector4i sll64(int i) const
{
return GSVector4i(_mm_slli_epi64(m, i));
}
__forceinline GSVector4i sll64(__m128i i) const
{
return GSVector4i(_mm_sll_epi64(m, i));
}
__forceinline GSVector4i srl16(int i) const
{
return GSVector4i(_mm_srli_epi16(m, i));
}
__forceinline GSVector4i srl16(__m128i i) const
{
return GSVector4i(_mm_srl_epi16(m, i));
}
__forceinline GSVector4i srl32(int i) const
{
return GSVector4i(_mm_srli_epi32(m, i));
}
__forceinline GSVector4i srl32(__m128i i) const
{
return GSVector4i(_mm_srl_epi32(m, i));
}
#if _M_SSE >= 0x501
__forceinline GSVector4i srlv32(__m128i i) const
{
return GSVector4i(_mm_srlv_epi32(m, i));
}
#endif
__forceinline GSVector4i srl64(int i) const
{
return GSVector4i(_mm_srli_epi64(m, i));
}
__forceinline GSVector4i srl64(__m128i i) const
{
return GSVector4i(_mm_srl_epi64(m, i));
}
__forceinline GSVector4i add8(const GSVector4i& v) const
{
return GSVector4i(_mm_add_epi8(m, v.m));
}
__forceinline GSVector4i add16(const GSVector4i& v) const
{
return GSVector4i(_mm_add_epi16(m, v.m));
}
__forceinline GSVector4i add32(const GSVector4i& v) const
{
return GSVector4i(_mm_add_epi32(m, v.m));
}
__forceinline GSVector4i adds8(const GSVector4i& v) const
{
return GSVector4i(_mm_adds_epi8(m, v.m));
}
__forceinline GSVector4i adds16(const GSVector4i& v) const
{
return GSVector4i(_mm_adds_epi16(m, v.m));
}
__forceinline GSVector4i addus8(const GSVector4i& v) const
{
return GSVector4i(_mm_adds_epu8(m, v.m));
}
__forceinline GSVector4i addus16(const GSVector4i& v) const
{
return GSVector4i(_mm_adds_epu16(m, v.m));
}
__forceinline GSVector4i sub8(const GSVector4i& v) const
{
return GSVector4i(_mm_sub_epi8(m, v.m));
}
__forceinline GSVector4i sub16(const GSVector4i& v) const
{
return GSVector4i(_mm_sub_epi16(m, v.m));
}
__forceinline GSVector4i sub32(const GSVector4i& v) const
{
return GSVector4i(_mm_sub_epi32(m, v.m));
}
__forceinline GSVector4i subs8(const GSVector4i& v) const
{
return GSVector4i(_mm_subs_epi8(m, v.m));
}
__forceinline GSVector4i subs16(const GSVector4i& v) const
{
return GSVector4i(_mm_subs_epi16(m, v.m));
}
__forceinline GSVector4i subus8(const GSVector4i& v) const
{
return GSVector4i(_mm_subs_epu8(m, v.m));
}
__forceinline GSVector4i subus16(const GSVector4i& v) const
{
return GSVector4i(_mm_subs_epu16(m, v.m));
}
__forceinline GSVector4i avg8(const GSVector4i& v) const
{
return GSVector4i(_mm_avg_epu8(m, v.m));
}
__forceinline GSVector4i avg16(const GSVector4i& v) const
{
return GSVector4i(_mm_avg_epu16(m, v.m));
}
__forceinline GSVector4i mul16hs(const GSVector4i& v) const
{
return GSVector4i(_mm_mulhi_epi16(m, v.m));
}
__forceinline GSVector4i mul16hu(const GSVector4i& v) const
{
return GSVector4i(_mm_mulhi_epu16(m, v.m));
}
__forceinline GSVector4i mul16l(const GSVector4i& v) const
{
return GSVector4i(_mm_mullo_epi16(m, v.m));
}
#if _M_SSE >= 0x301
__forceinline GSVector4i mul16hrs(const GSVector4i& v) const
{
return GSVector4i(_mm_mulhrs_epi16(m, v.m));
}
#endif
GSVector4i madd(const GSVector4i& v) const
{
return GSVector4i(_mm_madd_epi16(m, v.m));
}
template<int shift> __forceinline GSVector4i lerp16(const GSVector4i& a, const GSVector4i& f) const
{
// (a - this) * f << shift + this