aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Headers/xmmintrin.h
blob: 5a1c572ce6141121934415dfae4a54c6b99682fe (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
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
/*===---- xmmintrin.h - SSE intrinsics -------------------------------------===
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 *
 *===-----------------------------------------------------------------------===
 */

#ifndef __XMMINTRIN_H
#define __XMMINTRIN_H

#include <mmintrin.h>

typedef int __v4si __attribute__((__vector_size__(16)));
typedef float __v4sf __attribute__((__vector_size__(16)));
typedef float __m128 __attribute__((__vector_size__(16)));

/* Unsigned types */
typedef unsigned int __v4su __attribute__((__vector_size__(16)));

/* This header should only be included in a hosted environment as it depends on
 * a standard library to provide allocation routines. */
#if __STDC_HOSTED__
#include <mm_malloc.h>
#endif

/* Define the default attributes for the functions in this file. */
#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("sse")))

/// \brief Adds the 32-bit float values in the low-order bits of the operands.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VADDSS / ADDSS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the source operands.
///    The lower 32 bits of this operand are used in the calculation.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the source operands.
///    The lower 32 bits of this operand are used in the calculation.
/// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the sum
///    of the lower 32 bits of both operands. The upper 96 bits are copied from
///    the upper 96 bits of the first source operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_add_ss(__m128 __a, __m128 __b)
{
  __a[0] += __b[0];
  return __a;
}

/// \brief Adds two 128-bit vectors of [4 x float], and returns the results of
///    the addition.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VADDPS / ADDPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the source operands.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the source operands.
/// \returns A 128-bit vector of [4 x float] containing the sums of both
///    operands.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_add_ps(__m128 __a, __m128 __b)
{
  return (__m128)((__v4sf)__a + (__v4sf)__b);
}

/// \brief Subtracts the 32-bit float value in the low-order bits of the second
///    operand from the corresponding value in the first operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VSUBSS / SUBSS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing the minuend. The lower 32 bits
///    of this operand are used in the calculation.
/// \param __b
///    A 128-bit vector of [4 x float] containing the subtrahend. The lower 32
///    bits of this operand are used in the calculation.
/// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
///    difference of the lower 32 bits of both operands. The upper 96 bits are
///    copied from the upper 96 bits of the first source operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_sub_ss(__m128 __a, __m128 __b)
{
  __a[0] -= __b[0];
  return __a;
}

/// \brief Subtracts each of the values of the second operand from the first
///    operand, both of which are 128-bit vectors of [4 x float] and returns
///    the results of the subtraction.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VSUBPS / SUBPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing the minuend.
/// \param __b
///    A 128-bit vector of [4 x float] containing the subtrahend.
/// \returns A 128-bit vector of [4 x float] containing the differences between
///    both operands.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_sub_ps(__m128 __a, __m128 __b)
{
  return (__m128)((__v4sf)__a - (__v4sf)__b);
}

/// \brief Multiplies two 32-bit float values in the low-order bits of the
///    operands.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMULSS / MULSS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the source operands.
///    The lower 32 bits of this operand are used in the calculation.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the source operands.
///    The lower 32 bits of this operand are used in the calculation.
/// \returns A 128-bit vector of [4 x float] containing the product of the lower
///    32 bits of both operands. The upper 96 bits are copied from the upper 96
///    bits of the first source operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_mul_ss(__m128 __a, __m128 __b)
{
  __a[0] *= __b[0];
  return __a;
}

/// \brief Multiplies two 128-bit vectors of [4 x float] and returns the
///    results of the multiplication.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMULPS / MULPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the source operands.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the source operands.
/// \returns A 128-bit vector of [4 x float] containing the products of both
///    operands.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_mul_ps(__m128 __a, __m128 __b)
{
  return (__m128)((__v4sf)__a * (__v4sf)__b);
}

/// \brief Divides the value in the low-order 32 bits of the first operand by
///    the corresponding value in the second operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VDIVSS / DIVSS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing the dividend. The lower 32
///    bits of this operand are used in the calculation.
/// \param __b
///    A 128-bit vector of [4 x float] containing the divisor. The lower 32 bits
///    of this operand are used in the calculation.
/// \returns A 128-bit vector of [4 x float] containing the quotients of the
///    lower 32 bits of both operands. The upper 96 bits are copied from the
///    upper 96 bits of the first source operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_div_ss(__m128 __a, __m128 __b)
{
  __a[0] /= __b[0];
  return __a;
}

/// \brief Divides two 128-bit vectors of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VDIVPS / DIVPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing the dividend.
/// \param __b
///    A 128-bit vector of [4 x float] containing the divisor.
/// \returns A 128-bit vector of [4 x float] containing the quotients of both
///    operands.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_div_ps(__m128 __a, __m128 __b)
{
  return (__m128)((__v4sf)__a / (__v4sf)__b);
}

/// \brief Calculates the square root of the value stored in the low-order bits
///    of a 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VSQRTSS / SQRTSS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the calculation.
/// \returns A 128-bit vector of [4 x float] containing the square root of the
///    value in the low-order bits of the operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_sqrt_ss(__m128 __a)
{
  __m128 __c = __builtin_ia32_sqrtss((__v4sf)__a);
  return (__m128) { __c[0], __a[1], __a[2], __a[3] };
}

/// \brief Calculates the square roots of the values stored in a 128-bit vector
///    of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VSQRTPS / SQRTPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the square roots of the
///    values in the operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_sqrt_ps(__m128 __a)
{
  return __builtin_ia32_sqrtps((__v4sf)__a);
}

/// \brief Calculates the approximate reciprocal of the value stored in the
///    low-order bits of a 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VRCPSS / RCPSS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the calculation.
/// \returns A 128-bit vector of [4 x float] containing the approximate
///    reciprocal of the value in the low-order bits of the operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_rcp_ss(__m128 __a)
{
  __m128 __c = __builtin_ia32_rcpss((__v4sf)__a);
  return (__m128) { __c[0], __a[1], __a[2], __a[3] };
}

/// \brief Calculates the approximate reciprocals of the values stored in a
///    128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VRCPPS / RCPPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the approximate
///    reciprocals of the values in the operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_rcp_ps(__m128 __a)
{
  return __builtin_ia32_rcpps((__v4sf)__a);
}

/// \brief Calculates the approximate reciprocal of the square root of the value
///    stored in the low-order bits of a 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VRSQRTSS / RSQRTSS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the calculation.
/// \returns A 128-bit vector of [4 x float] containing the approximate
///    reciprocal of the square root of the value in the low-order bits of the
///    operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_rsqrt_ss(__m128 __a)
{
  __m128 __c = __builtin_ia32_rsqrtss((__v4sf)__a);
  return (__m128) { __c[0], __a[1], __a[2], __a[3] };
}

/// \brief Calculates the approximate reciprocals of the square roots of the
///    values stored in a 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VRSQRTPS / RSQRTPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the approximate
///    reciprocals of the square roots of the values in the operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_rsqrt_ps(__m128 __a)
{
  return __builtin_ia32_rsqrtps((__v4sf)__a);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands and returns the lesser value in the low-order bits of the
///    vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMINSS / MINSS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
///    minimum value between both operands. The upper 96 bits are copied from
///    the upper 96 bits of the first source operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_min_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_minss((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 128-bit vectors of [4 x float] and returns the lesser
///    of each pair of values.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMINPS / MINPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands.
/// \returns A 128-bit vector of [4 x float] containing the minimum values
///    between both operands.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_min_ps(__m128 __a, __m128 __b)
{
  return __builtin_ia32_minps((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands and returns the greater value in the low-order bits of a 128-bit
///    vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMAXSS / MAXSS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
///    maximum value between both operands. The upper 96 bits are copied from
///    the upper 96 bits of the first source operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_max_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_maxss((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 128-bit vectors of [4 x float] and returns the greater
///    of each pair of values.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMAXPS / MAXPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands.
/// \returns A 128-bit vector of [4 x float] containing the maximum values
///    between both operands.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_max_ps(__m128 __a, __m128 __b)
{
  return __builtin_ia32_maxps((__v4sf)__a, (__v4sf)__b);
}

/// \brief Performs a bitwise AND of two 128-bit vectors of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VANDPS / ANDPS </c> instructions.
///
/// \param __a
///    A 128-bit vector containing one of the source operands.
/// \param __b
///    A 128-bit vector containing one of the source operands.
/// \returns A 128-bit vector of [4 x float] containing the bitwise AND of the
///    values between both operands.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_and_ps(__m128 __a, __m128 __b)
{
  return (__m128)((__v4su)__a & (__v4su)__b);
}

/// \brief Performs a bitwise AND of two 128-bit vectors of [4 x float], using
///    the one's complement of the values contained in the first source
///    operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VANDNPS / ANDNPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing the first source operand. The
///    one's complement of this value is used in the bitwise AND.
/// \param __b
///    A 128-bit vector of [4 x float] containing the second source operand.
/// \returns A 128-bit vector of [4 x float] containing the bitwise AND of the
///    one's complement of the first operand and the values in the second
///    operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_andnot_ps(__m128 __a, __m128 __b)
{
  return (__m128)(~(__v4su)__a & (__v4su)__b);
}

/// \brief Performs a bitwise OR of two 128-bit vectors of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VORPS / ORPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the source operands.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the source operands.
/// \returns A 128-bit vector of [4 x float] containing the bitwise OR of the
///    values between both operands.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_or_ps(__m128 __a, __m128 __b)
{
  return (__m128)((__v4su)__a | (__v4su)__b);
}

/// \brief Performs a bitwise exclusive OR of two 128-bit vectors of
///    [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VXORPS / XORPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the source operands.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the source operands.
/// \returns A 128-bit vector of [4 x float] containing the bitwise exclusive OR
///    of the values between both operands.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_xor_ps(__m128 __a, __m128 __b)
{
  return (__m128)((__v4su)__a ^ (__v4su)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands for equality and returns the result of the comparison in the
///    low-order bits of a vector [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPEQSS / CMPEQSS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] containing the comparison results
///    in the low-order bits.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpeq_ss(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpeqss((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares each of the corresponding 32-bit float values of the
///    128-bit vectors of [4 x float] for equality.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPEQPS / CMPEQPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpeq_ps(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpeqps((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the value in the first operand is less than the
///    corresponding value in the second operand and returns the result of the
///    comparison in the low-order bits of a vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPLTSS / CMPLTSS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] containing the comparison results
///    in the low-order bits.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmplt_ss(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpltss((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares each of the corresponding 32-bit float values of the
///    128-bit vectors of [4 x float] to determine if the values in the first
///    operand are less than those in the second operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPLTPS / CMPLTPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmplt_ps(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpltps((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the value in the first operand is less than or
///    equal to the corresponding value in the second operand and returns the
///    result of the comparison in the low-order bits of a vector of
///    [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPLESS / CMPLESS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] containing the comparison results
///    in the low-order bits.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmple_ss(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpless((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares each of the corresponding 32-bit float values of the
///    128-bit vectors of [4 x float] to determine if the values in the first
///    operand are less than or equal to those in the second operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPLEPS / CMPLEPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmple_ps(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpleps((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the value in the first operand is greater than
///    the corresponding value in the second operand and returns the result of
///    the comparison in the low-order bits of a vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPLTSS / CMPLTSS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] containing the comparison results
///    in the low-order bits.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpgt_ss(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_shufflevector((__v4sf)__a,
                                         (__v4sf)__builtin_ia32_cmpltss((__v4sf)__b, (__v4sf)__a),
                                         4, 1, 2, 3);
}

/// \brief Compares each of the corresponding 32-bit float values of the
///    128-bit vectors of [4 x float] to determine if the values in the first
///    operand are greater than those in the second operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPLTPS / CMPLTPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpgt_ps(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpltps((__v4sf)__b, (__v4sf)__a);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the value in the first operand is greater than
///    or equal to the corresponding value in the second operand and returns
///    the result of the comparison in the low-order bits of a vector of
///    [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPLESS / CMPLESS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] containing the comparison results
///    in the low-order bits.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpge_ss(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_shufflevector((__v4sf)__a,
                                         (__v4sf)__builtin_ia32_cmpless((__v4sf)__b, (__v4sf)__a),
                                         4, 1, 2, 3);
}

/// \brief Compares each of the corresponding 32-bit float values of the
///    128-bit vectors of [4 x float] to determine if the values in the first
///    operand are greater than or equal to those in the second operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPLEPS / CMPLEPS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpge_ps(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpleps((__v4sf)__b, (__v4sf)__a);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands for inequality and returns the result of the comparison in the
///    low-order bits of a vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPNEQSS / CMPNEQSS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] containing the comparison results
///    in the low-order bits.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpneq_ss(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpneqss((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares each of the corresponding 32-bit float values of the
///    128-bit vectors of [4 x float] for inequality.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPNEQPS / CMPNEQPS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpneq_ps(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpneqps((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the value in the first operand is not less than
///    the corresponding value in the second operand and returns the result of
///    the comparison in the low-order bits of a vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPNLTSS / CMPNLTSS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] containing the comparison results
///    in the low-order bits.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpnlt_ss(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpnltss((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares each of the corresponding 32-bit float values of the
///    128-bit vectors of [4 x float] to determine if the values in the first
///    operand are not less than those in the second operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPNLTPS / CMPNLTPS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpnlt_ps(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpnltps((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the value in the first operand is not less than
///    or equal to the corresponding value in the second operand and returns
///    the result of the comparison in the low-order bits of a vector of
///    [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPNLESS / CMPNLESS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] containing the comparison results
///    in the low-order bits.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpnle_ss(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpnless((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares each of the corresponding 32-bit float values of the
///    128-bit vectors of [4 x float] to determine if the values in the first
///    operand are not less than or equal to those in the second operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPNLEPS / CMPNLEPS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpnle_ps(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpnleps((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the value in the first operand is not greater
///    than the corresponding value in the second operand and returns the
///    result of the comparison in the low-order bits of a vector of
///    [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPNLTSS / CMPNLTSS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] containing the comparison results
///    in the low-order bits.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpngt_ss(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_shufflevector((__v4sf)__a,
                                         (__v4sf)__builtin_ia32_cmpnltss((__v4sf)__b, (__v4sf)__a),
                                         4, 1, 2, 3);
}

/// \brief Compares each of the corresponding 32-bit float values of the
///    128-bit vectors of [4 x float] to determine if the values in the first
///    operand are not greater than those in the second operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPNLTPS / CMPNLTPS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpngt_ps(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpnltps((__v4sf)__b, (__v4sf)__a);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the value in the first operand is not greater
///    than or equal to the corresponding value in the second operand and
///    returns the result of the comparison in the low-order bits of a vector
///    of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPNLESS / CMPNLESS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] containing the comparison results
///    in the low-order bits.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpnge_ss(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_shufflevector((__v4sf)__a,
                                         (__v4sf)__builtin_ia32_cmpnless((__v4sf)__b, (__v4sf)__a),
                                         4, 1, 2, 3);
}

/// \brief Compares each of the corresponding 32-bit float values of the
///    128-bit vectors of [4 x float] to determine if the values in the first
///    operand are not greater than or equal to those in the second operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPNLEPS / CMPNLEPS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpnge_ps(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpnleps((__v4sf)__b, (__v4sf)__a);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the value in the first operand is ordered with
///    respect to the corresponding value in the second operand and returns the
///    result of the comparison in the low-order bits of a vector of
///    [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPORDSS / CMPORDSS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] containing the comparison results
///    in the low-order bits.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpord_ss(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpordss((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares each of the corresponding 32-bit float values of the
///    128-bit vectors of [4 x float] to determine if the values in the first
///    operand are ordered with respect to those in the second operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPORDPS / CMPORDPS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpord_ps(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpordps((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the value in the first operand is unordered
///    with respect to the corresponding value in the second operand and
///    returns the result of the comparison in the low-order bits of a vector
///    of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPUNORDSS / CMPUNORDSS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float] containing one of the operands. The lower
///    32 bits of this operand are used in the comparison.
/// \returns A 128-bit vector of [4 x float] containing the comparison results
///    in the low-order bits.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpunord_ss(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpunordss((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares each of the corresponding 32-bit float values of the
///    128-bit vectors of [4 x float] to determine if the values in the first
///    operand are unordered with respect to those in the second operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCMPUNORDPS / CMPUNORDPS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cmpunord_ps(__m128 __a, __m128 __b)
{
  return (__m128)__builtin_ia32_cmpunordps((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands for equality and returns the result of the comparison.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCOMISS / COMISS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \returns An integer containing the comparison results.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_comieq_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_comieq((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the first operand is less than the second
///    operand and returns the result of the comparison.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCOMISS / COMISS </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \returns An integer containing the comparison results.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_comilt_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_comilt((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the first operand is less than or equal to the
///    second operand and returns the result of the comparison.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCOMISS / COMISS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \returns An integer containing the comparison results.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_comile_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_comile((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the first operand is greater than the second
///    operand and returns the result of the comparison.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCOMISS / COMISS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \returns An integer containing the comparison results.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_comigt_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_comigt((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the first operand is greater than or equal to
///    the second operand and returns the result of the comparison.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCOMISS / COMISS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \returns An integer containing the comparison results.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_comige_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_comige((__v4sf)__a, (__v4sf)__b);
}

/// \brief Compares two 32-bit float values in the low-order bits of both
///    operands to determine if the first operand is not equal to the second
///    operand and returns the result of the comparison.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCOMISS / COMISS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \returns An integer containing the comparison results.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_comineq_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_comineq((__v4sf)__a, (__v4sf)__b);
}

/// \brief Performs an unordered comparison of two 32-bit float values using
///    the low-order bits of both operands to determine equality and returns
///    the result of the comparison.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUCOMISS / UCOMISS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \returns An integer containing the comparison results.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_ucomieq_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_ucomieq((__v4sf)__a, (__v4sf)__b);
}

/// \brief Performs an unordered comparison of two 32-bit float values using
///    the low-order bits of both operands to determine if the first operand is
///    less than the second operand and returns the result of the comparison.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUCOMISS / UCOMISS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \returns An integer containing the comparison results.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_ucomilt_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_ucomilt((__v4sf)__a, (__v4sf)__b);
}

/// \brief Performs an unordered comparison of two 32-bit float values using
///    the low-order bits of both operands to determine if the first operand is
///    less than or equal to the second operand and returns the result of the
///    comparison.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUCOMISS / UCOMISS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \returns An integer containing the comparison results.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_ucomile_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_ucomile((__v4sf)__a, (__v4sf)__b);
}

/// \brief Performs an unordered comparison of two 32-bit float values using
///    the low-order bits of both operands to determine if the first operand is
///    greater than the second operand and returns the result of the
///    comparison.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUCOMISS / UCOMISS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \returns An integer containing the comparison results.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_ucomigt_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_ucomigt((__v4sf)__a, (__v4sf)__b);
}

/// \brief Performs an unordered comparison of two 32-bit float values using
///    the low-order bits of both operands to determine if the first operand is
///    greater than or equal to the second operand and returns the result of
///    the comparison.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUCOMISS / UCOMISS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \returns An integer containing the comparison results.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_ucomige_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_ucomige((__v4sf)__a, (__v4sf)__b);
}

/// \brief Performs an unordered comparison of two 32-bit float values using
///    the low-order bits of both operands to determine inequality and returns
///    the result of the comparison.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUCOMISS / UCOMISS </c> instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \param __b
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the comparison.
/// \returns An integer containing the comparison results.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_ucomineq_ss(__m128 __a, __m128 __b)
{
  return __builtin_ia32_ucomineq((__v4sf)__a, (__v4sf)__b);
}

/// \brief Converts a float value contained in the lower 32 bits of a vector of
///    [4 x float] into a 32-bit integer.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCVTSS2SI / CVTSS2SI </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the conversion.
/// \returns A 32-bit integer containing the converted value.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_cvtss_si32(__m128 __a)
{
  return __builtin_ia32_cvtss2si((__v4sf)__a);
}

/// \brief Converts a float value contained in the lower 32 bits of a vector of
///    [4 x float] into a 32-bit integer.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCVTSS2SI / CVTSS2SI </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the conversion.
/// \returns A 32-bit integer containing the converted value.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_cvt_ss2si(__m128 __a)
{
  return _mm_cvtss_si32(__a);
}

#ifdef __x86_64__

/// \brief Converts a float value contained in the lower 32 bits of a vector of
///    [4 x float] into a 64-bit integer.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCVTSS2SI / CVTSS2SI </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the conversion.
/// \returns A 64-bit integer containing the converted value.
static __inline__ long long __DEFAULT_FN_ATTRS
_mm_cvtss_si64(__m128 __a)
{
  return __builtin_ia32_cvtss2si64((__v4sf)__a);
}

#endif

/// \brief Converts two low-order float values in a 128-bit vector of
///    [4 x float] into a 64-bit vector of [2 x i32].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTPS2PI </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \returns A 64-bit integer vector containing the converted values.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_cvtps_pi32(__m128 __a)
{
  return (__m64)__builtin_ia32_cvtps2pi((__v4sf)__a);
}

/// \brief Converts two low-order float values in a 128-bit vector of
///    [4 x float] into a 64-bit vector of [2 x i32].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTPS2PI </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \returns A 64-bit integer vector containing the converted values.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_cvt_ps2pi(__m128 __a)
{
  return _mm_cvtps_pi32(__a);
}

/// \brief Converts a float value contained in the lower 32 bits of a vector of
///    [4 x float] into a 32-bit integer, truncating the result when it is
///    inexact.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCVTTSS2SI / CVTTSS2SI </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the conversion.
/// \returns A 32-bit integer containing the converted value.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_cvttss_si32(__m128 __a)
{
  return __builtin_ia32_cvttss2si((__v4sf)__a);
}

/// \brief Converts a float value contained in the lower 32 bits of a vector of
///    [4 x float] into a 32-bit integer, truncating the result when it is
///    inexact.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCVTTSS2SI / CVTTSS2SI </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the conversion.
/// \returns A 32-bit integer containing the converted value.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_cvtt_ss2si(__m128 __a)
{
  return _mm_cvttss_si32(__a);
}

#ifdef __x86_64__
/// \brief Converts a float value contained in the lower 32 bits of a vector of
///    [4 x float] into a 64-bit integer, truncating the result when it is
///    inexact.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCVTTSS2SI / CVTTSS2SI </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the conversion.
/// \returns A 64-bit integer containing the converted value.
static __inline__ long long __DEFAULT_FN_ATTRS
_mm_cvttss_si64(__m128 __a)
{
  return __builtin_ia32_cvttss2si64((__v4sf)__a);
}
#endif

/// \brief Converts two low-order float values in a 128-bit vector of
///    [4 x float] into a 64-bit vector of [2 x i32], truncating the result
///    when it is inexact.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTTPS2PI / VTTPS2PI </c>
///   instructions.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \returns A 64-bit integer vector containing the converted values.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_cvttps_pi32(__m128 __a)
{
  return (__m64)__builtin_ia32_cvttps2pi((__v4sf)__a);
}

/// \brief Converts two low-order float values in a 128-bit vector of [4 x
///    float] into a 64-bit vector of [2 x i32], truncating the result when it
///    is inexact.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTTPS2PI </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \returns A 64-bit integer vector containing the converted values.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_cvtt_ps2pi(__m128 __a)
{
  return _mm_cvttps_pi32(__a);
}

/// \brief Converts a 32-bit signed integer value into a floating point value
///    and writes it to the lower 32 bits of the destination. The remaining
///    higher order elements of the destination vector are copied from the
///    corresponding elements in the first operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCVTSI2SS / CVTSI2SS </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 32-bit signed integer operand containing the value to be converted.
/// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
///    converted value of the second operand. The upper 96 bits are copied from
///    the upper 96 bits of the first operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cvtsi32_ss(__m128 __a, int __b)
{
  __a[0] = __b;
  return __a;
}

/// \brief Converts a 32-bit signed integer value into a floating point value
///    and writes it to the lower 32 bits of the destination. The remaining
///    higher order elements of the destination are copied from the
///    corresponding elements in the first operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCVTSI2SS / CVTSI2SS </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 32-bit signed integer operand containing the value to be converted.
/// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
///    converted value of the second operand. The upper 96 bits are copied from
///    the upper 96 bits of the first operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cvt_si2ss(__m128 __a, int __b)
{
  return _mm_cvtsi32_ss(__a, __b);
}

#ifdef __x86_64__

/// \brief Converts a 64-bit signed integer value into a floating point value
///    and writes it to the lower 32 bits of the destination. The remaining
///    higher order elements of the destination are copied from the
///    corresponding elements in the first operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCVTSI2SS / CVTSI2SS </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 64-bit signed integer operand containing the value to be converted.
/// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
///    converted value of the second operand. The upper 96 bits are copied from
///    the upper 96 bits of the first operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cvtsi64_ss(__m128 __a, long long __b)
{
  __a[0] = __b;
  return __a;
}

#endif

/// \brief Converts two elements of a 64-bit vector of [2 x i32] into two
///    floating point values and writes them to the lower 64-bits of the
///    destination. The remaining higher order elements of the destination are
///    copied from the corresponding elements in the first operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTPI2PS </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 64-bit vector of [2 x i32]. The elements in this vector are converted
///    and written to the corresponding low-order elements in the destination.
/// \returns A 128-bit vector of [4 x float] whose lower 64 bits contain the
///    converted value of the second operand. The upper 64 bits are copied from
///    the upper 64 bits of the first operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cvtpi32_ps(__m128 __a, __m64 __b)
{
  return __builtin_ia32_cvtpi2ps((__v4sf)__a, (__v2si)__b);
}

/// \brief Converts two elements of a 64-bit vector of [2 x i32] into two
///    floating point values and writes them to the lower 64-bits of the
///    destination. The remaining higher order elements of the destination are
///    copied from the corresponding elements in the first operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTPI2PS </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float].
/// \param __b
///    A 64-bit vector of [2 x i32]. The elements in this vector are converted
///    and written to the corresponding low-order elements in the destination.
/// \returns A 128-bit vector of [4 x float] whose lower 64 bits contain the
///    converted value from the second operand. The upper 64 bits are copied
///    from the upper 64 bits of the first operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cvt_pi2ps(__m128 __a, __m64 __b)
{
  return _mm_cvtpi32_ps(__a, __b);
}

/// \brief Extracts a float value contained in the lower 32 bits of a vector of
///    [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVSS / MOVSS </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
///    used in the extraction.
/// \returns A 32-bit float containing the extracted value.
static __inline__ float __DEFAULT_FN_ATTRS
_mm_cvtss_f32(__m128 __a)
{
  return __a[0];
}

/// \brief Loads two packed float values from the address \a __p into the
///     high-order bits of a 128-bit vector of [4 x float]. The low-order bits
///     are copied from the low-order bits of the first operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVHPD / MOVHPD </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float]. Bits [63:0] are written to bits [63:0]
///    of the destination.
/// \param __p
///    A pointer to two packed float values. Bits [63:0] are written to bits
///    [127:64] of the destination.
/// \returns A 128-bit vector of [4 x float] containing the moved values.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_loadh_pi(__m128 __a, const __m64 *__p)
{
  typedef float __mm_loadh_pi_v2f32 __attribute__((__vector_size__(8)));
  struct __mm_loadh_pi_struct {
    __mm_loadh_pi_v2f32 __u;
  } __attribute__((__packed__, __may_alias__));
  __mm_loadh_pi_v2f32 __b = ((struct __mm_loadh_pi_struct*)__p)->__u;
  __m128 __bb = __builtin_shufflevector(__b, __b, 0, 1, 0, 1);
  return __builtin_shufflevector(__a, __bb, 0, 1, 4, 5);
}

/// \brief Loads two packed float values from the address \a __p into the
///    low-order bits of a 128-bit vector of [4 x float]. The high-order bits
///    are copied from the high-order bits of the first operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVLPD / MOVLPD </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float]. Bits [127:64] are written to bits
///    [127:64] of the destination.
/// \param __p
///    A pointer to two packed float values. Bits [63:0] are written to bits
///    [63:0] of the destination.
/// \returns A 128-bit vector of [4 x float] containing the moved values.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_loadl_pi(__m128 __a, const __m64 *__p)
{
  typedef float __mm_loadl_pi_v2f32 __attribute__((__vector_size__(8)));
  struct __mm_loadl_pi_struct {
    __mm_loadl_pi_v2f32 __u;
  } __attribute__((__packed__, __may_alias__));
  __mm_loadl_pi_v2f32 __b = ((struct __mm_loadl_pi_struct*)__p)->__u;
  __m128 __bb = __builtin_shufflevector(__b, __b, 0, 1, 0, 1);
  return __builtin_shufflevector(__a, __bb, 4, 5, 2, 3);
}

/// \brief Constructs a 128-bit floating-point vector of [4 x float]. The lower
///    32 bits of the vector are initialized with the single-precision
///    floating-point value loaded from a specified memory location. The upper
///    96 bits are set to zero.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVSS / MOVSS </c> instruction.
///
/// \param __p
///    A pointer to a 32-bit memory location containing a single-precision
///    floating-point value.
/// \returns An initialized 128-bit floating-point vector of [4 x float]. The
///    lower 32 bits contain the value loaded from the memory location. The
///    upper 96 bits are set to zero.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_load_ss(const float *__p)
{
  struct __mm_load_ss_struct {
    float __u;
  } __attribute__((__packed__, __may_alias__));
  float __u = ((struct __mm_load_ss_struct*)__p)->__u;
  return (__m128){ __u, 0, 0, 0 };
}

/// \brief Loads a 32-bit float value and duplicates it to all four vector
///    elements of a 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVSS / MOVSS + shuffling </c>
///    instruction.
///
/// \param __p
///    A pointer to a float value to be loaded and duplicated.
/// \returns A 128-bit vector of [4 x float] containing the loaded and
///    duplicated values.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_load1_ps(const float *__p)
{
  struct __mm_load1_ps_struct {
    float __u;
  } __attribute__((__packed__, __may_alias__));
  float __u = ((struct __mm_load1_ps_struct*)__p)->__u;
  return (__m128){ __u, __u, __u, __u };
}

#define        _mm_load_ps1(p) _mm_load1_ps(p)

/// \brief Loads a 128-bit floating-point vector of [4 x float] from an aligned
///    memory location.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVAPS / MOVAPS </c> instruction.
///
/// \param __p
///    A pointer to a 128-bit memory location. The address of the memory
///    location has to be 128-bit aligned.
/// \returns A 128-bit vector of [4 x float] containing the loaded valus.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_load_ps(const float *__p)
{
  return *(__m128*)__p;
}

/// \brief Loads a 128-bit floating-point vector of [4 x float] from an
///    unaligned memory location.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVUPS / MOVUPS </c> instruction.
///
/// \param __p
///    A pointer to a 128-bit memory location. The address of the memory
///    location does not have to be aligned.
/// \returns A 128-bit vector of [4 x float] containing the loaded values.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_loadu_ps(const float *__p)
{
  struct __loadu_ps {
    __m128 __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_ps*)__p)->__v;
}

/// \brief Loads four packed float values, in reverse order, from an aligned
///    memory location to 32-bit elements in a 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVAPS / MOVAPS + shuffling </c>
///    instruction.
///
/// \param __p
///    A pointer to a 128-bit memory location. The address of the memory
///    location has to be 128-bit aligned.
/// \returns A 128-bit vector of [4 x float] containing the moved values, loaded
///    in reverse order.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_loadr_ps(const float *__p)
{
  __m128 __a = _mm_load_ps(__p);
  return __builtin_shufflevector((__v4sf)__a, (__v4sf)__a, 3, 2, 1, 0);
}

/// \brief Create a 128-bit vector of [4 x float] with undefined values.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic has no corresponding instruction.
///
/// \returns A 128-bit vector of [4 x float] containing undefined values.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_undefined_ps(void)
{
  return (__m128)__builtin_ia32_undef128();
}

/// \brief Constructs a 128-bit floating-point vector of [4 x float]. The lower
///    32 bits of the vector are initialized with the specified single-precision
///    floating-point value. The upper 96 bits are set to zero.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVSS / MOVSS </c> instruction.
///
/// \param __w
///    A single-precision floating-point value used to initialize the lower 32
///    bits of the result.
/// \returns An initialized 128-bit floating-point vector of [4 x float]. The
///    lower 32 bits contain the value provided in the source operand. The
///    upper 96 bits are set to zero.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_set_ss(float __w)
{
  return (__m128){ __w, 0, 0, 0 };
}

/// \brief Constructs a 128-bit floating-point vector of [4 x float], with each
///    of the four single-precision floating-point vector elements set to the
///    specified single-precision floating-point value.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VPERMILPS / PERMILPS </c> instruction.
///
/// \param __w
///    A single-precision floating-point value used to initialize each vector
///    element of the result.
/// \returns An initialized 128-bit floating-point vector of [4 x float].
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_set1_ps(float __w)
{
  return (__m128){ __w, __w, __w, __w };
}

/* Microsoft specific. */
/// \brief Constructs a 128-bit floating-point vector of [4 x float], with each
///    of the four single-precision floating-point vector elements set to the
///    specified single-precision floating-point value.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VPERMILPS / PERMILPS </c> instruction.
///
/// \param __w
///    A single-precision floating-point value used to initialize each vector
///    element of the result.
/// \returns An initialized 128-bit floating-point vector of [4 x float].
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_set_ps1(float __w)
{
    return _mm_set1_ps(__w);
}

/// \brief Constructs a 128-bit floating-point vector of [4 x float]
///    initialized with the specified single-precision floating-point values.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic is a utility function and does not correspond to a specific
///    instruction.
///
/// \param __z
///    A single-precision floating-point value used to initialize bits [127:96]
///    of the result.
/// \param __y
///    A single-precision floating-point value used to initialize bits [95:64]
///    of the result.
/// \param __x
///    A single-precision floating-point value used to initialize bits [63:32]
///    of the result.
/// \param __w
///    A single-precision floating-point value used to initialize bits [31:0]
///    of the result.
/// \returns An initialized 128-bit floating-point vector of [4 x float].
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_set_ps(float __z, float __y, float __x, float __w)
{
  return (__m128){ __w, __x, __y, __z };
}

/// \brief Constructs a 128-bit floating-point vector of [4 x float],
///    initialized in reverse order with the specified 32-bit single-precision
///    float-point values.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic is a utility function and does not correspond to a specific
///    instruction.
///
/// \param __z
///    A single-precision floating-point value used to initialize bits [31:0]
///    of the result.
/// \param __y
///    A single-precision floating-point value used to initialize bits [63:32]
///    of the result.
/// \param __x
///    A single-precision floating-point value used to initialize bits [95:64]
///    of the result.
/// \param __w
///    A single-precision floating-point value used to initialize bits [127:96]
///    of the result.
/// \returns An initialized 128-bit floating-point vector of [4 x float].
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_setr_ps(float __z, float __y, float __x, float __w)
{
  return (__m128){ __z, __y, __x, __w };
}

/// \brief Constructs a 128-bit floating-point vector of [4 x float] initialized
///    to zero.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VXORPS / XORPS </c> instruction.
///
/// \returns An initialized 128-bit floating-point vector of [4 x float] with
///    all elements set to zero.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_setzero_ps(void)
{
  return (__m128){ 0, 0, 0, 0 };
}

/// \brief Stores the upper 64 bits of a 128-bit vector of [4 x float] to a
///    memory location.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VPEXTRQ / MOVQ </c> instruction.
///
/// \param __p
///    A pointer to a 64-bit memory location.
/// \param __a
///    A 128-bit vector of [4 x float] containing the values to be stored.
static __inline__ void __DEFAULT_FN_ATTRS
_mm_storeh_pi(__m64 *__p, __m128 __a)
{
  __builtin_ia32_storehps((__v2si *)__p, (__v4sf)__a);
}

/// \brief Stores the lower 64 bits of a 128-bit vector of [4 x float] to a
///     memory location.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVLPS / MOVLPS </c> instruction.
///
/// \param __p
///    A pointer to a memory location that will receive the float values.
/// \param __a
///    A 128-bit vector of [4 x float] containing the values to be stored.
static __inline__ void __DEFAULT_FN_ATTRS
_mm_storel_pi(__m64 *__p, __m128 __a)
{
  __builtin_ia32_storelps((__v2si *)__p, (__v4sf)__a);
}

/// \brief Stores the lower 32 bits of a 128-bit vector of [4 x float] to a
///     memory location.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVSS / MOVSS </c> instruction.
///
/// \param __p
///    A pointer to a 32-bit memory location.
/// \param __a
///    A 128-bit vector of [4 x float] containing the value to be stored.
static __inline__ void __DEFAULT_FN_ATTRS
_mm_store_ss(float *__p, __m128 __a)
{
  struct __mm_store_ss_struct {
    float __u;
  } __attribute__((__packed__, __may_alias__));
  ((struct __mm_store_ss_struct*)__p)->__u = __a[0];
}

/// \brief Stores a 128-bit vector of [4 x float] to an unaligned memory
///    location.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVUPS / MOVUPS </c> instruction.
///
/// \param __p
///    A pointer to a 128-bit memory location. The address of the memory
///    location does not have to be aligned.
/// \param __a
///    A 128-bit vector of [4 x float] containing the values to be stored.
static __inline__ void __DEFAULT_FN_ATTRS
_mm_storeu_ps(float *__p, __m128 __a)
{
  struct __storeu_ps {
    __m128 __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_ps*)__p)->__v = __a;
}

/// \brief Stores a 128-bit vector of [4 x float] into an aligned memory
///    location.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVAPS / MOVAPS </c> instruction.
///
/// \param __p
///    A pointer to a 128-bit memory location. The address of the memory
///    location has to be 16-byte aligned.
/// \param __a
///    A 128-bit vector of [4 x float] containing the values to be stored.
static __inline__ void __DEFAULT_FN_ATTRS
_mm_store_ps(float *__p, __m128 __a)
{
  *(__m128*)__p = __a;
}

/// \brief Stores the lower 32 bits of a 128-bit vector of [4 x float] into
///    four contiguous elements in an aligned memory location.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to <c> VMOVAPS / MOVAPS + shuffling </c>
///    instruction.
///
/// \param __p
///    A pointer to a 128-bit memory location.
/// \param __a
///    A 128-bit vector of [4 x float] whose lower 32 bits are stored to each
///    of the four contiguous elements pointed by \a __p.
static __inline__ void __DEFAULT_FN_ATTRS
_mm_store1_ps(float *__p, __m128 __a)
{
  __a = __builtin_shufflevector((__v4sf)__a, (__v4sf)__a, 0, 0, 0, 0);
  _mm_store_ps(__p, __a);
}

/// \brief Stores the lower 32 bits of a 128-bit vector of [4 x float] into
///    four contiguous elements in an aligned memory location.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to <c> VMOVAPS / MOVAPS + shuffling </c>
///    instruction.
///
/// \param __p
///    A pointer to a 128-bit memory location.
/// \param __a
///    A 128-bit vector of [4 x float] whose lower 32 bits are stored to each
///    of the four contiguous elements pointed by \a __p.
static __inline__ void __DEFAULT_FN_ATTRS
_mm_store_ps1(float *__p, __m128 __a)
{
  return _mm_store1_ps(__p, __a);
}

/// \brief Stores float values from a 128-bit vector of [4 x float] to an
///    aligned memory location in reverse order.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVAPS / MOVAPS + shuffling </c>
///    instruction.
///
/// \param __p
///    A pointer to a 128-bit memory location. The address of the memory
///    location has to be 128-bit aligned.
/// \param __a
///    A 128-bit vector of [4 x float] containing the values to be stored.
static __inline__ void __DEFAULT_FN_ATTRS
_mm_storer_ps(float *__p, __m128 __a)
{
  __a = __builtin_shufflevector((__v4sf)__a, (__v4sf)__a, 3, 2, 1, 0);
  _mm_store_ps(__p, __a);
}

#define _MM_HINT_T0 3
#define _MM_HINT_T1 2
#define _MM_HINT_T2 1
#define _MM_HINT_NTA 0

#ifndef _MSC_VER
/* FIXME: We have to #define this because "sel" must be a constant integer, and
   Sema doesn't do any form of constant propagation yet. */

/// \brief Loads one cache line of data from the specified address to a location
///    closer to the processor.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// void _mm_prefetch(const void * a, const int sel);
/// \endcode
///
/// This intrinsic corresponds to the <c> PREFETCHNTA </c> instruction.
///
/// \param a
///    A pointer to a memory location containing a cache line of data.
/// \param sel
///    A predefined integer constant specifying the type of prefetch
///    operation: \n
///    _MM_HINT_NTA: Move data using the non-temporal access (NTA) hint. The
///    PREFETCHNTA instruction will be generated. \n
///    _MM_HINT_T0: Move data using the T0 hint. The PREFETCHT0 instruction will
///    be generated. \n
///    _MM_HINT_T1: Move data using the T1 hint. The PREFETCHT1 instruction will
///    be generated. \n
///    _MM_HINT_T2: Move data using the T2 hint. The PREFETCHT2 instruction will
///    be generated.
#define _mm_prefetch(a, sel) (__builtin_prefetch((void *)(a), 0, (sel)))
#endif

/// \brief Stores a 64-bit integer in the specified aligned memory location. To
///    minimize caching, the data is flagged as non-temporal (unlikely to be
///    used again soon).
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> MOVNTQ </c> instruction.
///
/// \param __p
///    A pointer to an aligned memory location used to store the register value.
/// \param __a
///    A 64-bit integer containing the value to be stored.
static __inline__ void __DEFAULT_FN_ATTRS
_mm_stream_pi(__m64 *__p, __m64 __a)
{
  __builtin_ia32_movntq(__p, __a);
}

/// \brief Moves packed float values from a 128-bit vector of [4 x float] to a
///    128-bit aligned memory location. To minimize caching, the data is flagged
///    as non-temporal (unlikely to be used again soon).
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVNTPS / MOVNTPS </c> instruction.
///
/// \param __p
///    A pointer to a 128-bit aligned memory location that will receive the
///    integer values.
/// \param __a
///    A 128-bit vector of [4 x float] containing the values to be moved.
static __inline__ void __DEFAULT_FN_ATTRS
_mm_stream_ps(float *__p, __m128 __a)
{
  __builtin_nontemporal_store((__v4sf)__a, (__v4sf*)__p);
}

#if defined(__cplusplus)
extern "C" {
#endif

/// \brief Forces strong memory ordering (serialization) between store
///    instructions preceding this instruction and store instructions following
///    this instruction, ensuring the system completes all previous stores
///    before executing subsequent stores.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> SFENCE </c> instruction.
///
void _mm_sfence(void);

#if defined(__cplusplus)
} // extern "C"
#endif

/// \brief Extracts 16-bit element from a 64-bit vector of [4 x i16] and
///    returns it, as specified by the immediate integer operand.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// int _mm_extract_pi16(__m64 a, int n);
/// \endcode
///
/// This intrinsic corresponds to the <c> VPEXTRW / PEXTRW </c> instruction.
///
/// \param a
///    A 64-bit vector of [4 x i16].
/// \param n
///    An immediate integer operand that determines which bits are extracted: \n
///    0: Bits [15:0] are copied to the destination. \n
///    1: Bits [31:16] are copied to the destination. \n
///    2: Bits [47:32] are copied to the destination. \n
///    3: Bits [63:48] are copied to the destination.
/// \returns A 16-bit integer containing the extracted 16 bits of packed data.
#define _mm_extract_pi16(a, n) __extension__ ({ \
  (int)__builtin_ia32_vec_ext_v4hi((__m64)a, (int)n); })

/// \brief Copies data from the 64-bit vector of [4 x i16] to the destination,
///    and inserts the lower 16-bits of an integer operand at the 16-bit offset
///    specified by the immediate operand \a n.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// __m64 _mm_insert_pi16(__m64 a, int d, int n);
/// \endcode
///
/// This intrinsic corresponds to the <c> VPINSRW / PINSRW </c> instruction.
///
/// \param a
///    A 64-bit vector of [4 x i16].
/// \param d
///    An integer. The lower 16-bit value from this operand is written to the
///    destination at the offset specified by operand \a n.
/// \param n
///    An immediate integer operant that determines which the bits to be used
///    in the destination. \n
///    0: Bits [15:0] are copied to the destination. \n
///    1: Bits [31:16] are copied to the destination. \n
///    2: Bits [47:32] are copied to the destination. \n
///    3: Bits [63:48] are copied to the destination.  \n
///    The remaining bits in the destination are copied from the corresponding
///    bits in operand \a a.
/// \returns A 64-bit integer vector containing the copied packed data from the
///    operands.
#define _mm_insert_pi16(a, d, n) __extension__ ({ \
  (__m64)__builtin_ia32_vec_set_v4hi((__m64)a, (int)d, (int)n); })

/// \brief Compares each of the corresponding packed 16-bit integer values of
///    the 64-bit integer vectors, and writes the greater value to the
///    corresponding bits in the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> PMAXSW </c> instruction.
///
/// \param __a
///    A 64-bit integer vector containing one of the source operands.
/// \param __b
///    A 64-bit integer vector containing one of the source operands.
/// \returns A 64-bit integer vector containing the comparison results.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_max_pi16(__m64 __a, __m64 __b)
{
  return (__m64)__builtin_ia32_pmaxsw((__v4hi)__a, (__v4hi)__b);
}

/// \brief Compares each of the corresponding packed 8-bit unsigned integer
///    values of the 64-bit integer vectors, and writes the greater value to the
///    corresponding bits in the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> PMAXUB </c> instruction.
///
/// \param __a
///    A 64-bit integer vector containing one of the source operands.
/// \param __b
///    A 64-bit integer vector containing one of the source operands.
/// \returns A 64-bit integer vector containing the comparison results.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_max_pu8(__m64 __a, __m64 __b)
{
  return (__m64)__builtin_ia32_pmaxub((__v8qi)__a, (__v8qi)__b);
}

/// \brief Compares each of the corresponding packed 16-bit integer values of
///    the 64-bit integer vectors, and writes the lesser value to the
///    corresponding bits in the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> PMINSW </c> instruction.
///
/// \param __a
///    A 64-bit integer vector containing one of the source operands.
/// \param __b
///    A 64-bit integer vector containing one of the source operands.
/// \returns A 64-bit integer vector containing the comparison results.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_min_pi16(__m64 __a, __m64 __b)
{
  return (__m64)__builtin_ia32_pminsw((__v4hi)__a, (__v4hi)__b);
}

/// \brief Compares each of the corresponding packed 8-bit unsigned integer
///    values of the 64-bit integer vectors, and writes the lesser value to the
///    corresponding bits in the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> PMINUB </c> instruction.
///
/// \param __a
///    A 64-bit integer vector containing one of the source operands.
/// \param __b
///    A 64-bit integer vector containing one of the source operands.
/// \returns A 64-bit integer vector containing the comparison results.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_min_pu8(__m64 __a, __m64 __b)
{
  return (__m64)__builtin_ia32_pminub((__v8qi)__a, (__v8qi)__b);
}

/// \brief Takes the most significant bit from each 8-bit element in a 64-bit
///    integer vector to create a 16-bit mask value. Zero-extends the value to
///    32-bit integer and writes it to the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> PMOVMSKB </c> instruction.
///
/// \param __a
///    A 64-bit integer vector containing the values with bits to be extracted.
/// \returns The most significant bit from each 8-bit element in the operand,
///    written to bits [15:0].
static __inline__ int __DEFAULT_FN_ATTRS
_mm_movemask_pi8(__m64 __a)
{
  return __builtin_ia32_pmovmskb((__v8qi)__a);
}

/// \brief Multiplies packed 16-bit unsigned integer values and writes the
///    high-order 16 bits of each 32-bit product to the corresponding bits in
///    the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> PMULHUW </c> instruction.
///
/// \param __a
///    A 64-bit integer vector containing one of the source operands.
/// \param __b
///    A 64-bit integer vector containing one of the source operands.
/// \returns A 64-bit integer vector containing the products of both operands.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_mulhi_pu16(__m64 __a, __m64 __b)
{
  return (__m64)__builtin_ia32_pmulhuw((__v4hi)__a, (__v4hi)__b);
}

/// \brief Shuffles the 4 16-bit integers from a 64-bit integer vector to the
///    destination, as specified by the immediate value operand.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// __m64 _mm_shuffle_pi16(__m64 a, const int n);
/// \endcode
///
/// This intrinsic corresponds to the <c> PSHUFW </c> instruction.
///
/// \param a
///    A 64-bit integer vector containing the values to be shuffled.
/// \param n
///    An immediate value containing an 8-bit value specifying which elements to
///    copy from \a a. The destinations within the 64-bit destination are
///    assigned values as follows: \n
///    Bits [1:0] are used to assign values to bits [15:0] in the
///    destination. \n
///    Bits [3:2] are used to assign values to bits [31:16] in the
///    destination. \n
///    Bits [5:4] are used to assign values to bits [47:32] in the
///    destination. \n
///    Bits [7:6] are used to assign values to bits [63:48] in the
///    destination. \n
///    Bit value assignments: \n
///    00: assigned from bits [15:0] of \a a. \n
///    01: assigned from bits [31:16] of \a a. \n
///    10: assigned from bits [47:32] of \a a. \n
///    11: assigned from bits [63:48] of \a a.
/// \returns A 64-bit integer vector containing the shuffled values.
#define _mm_shuffle_pi16(a, n) __extension__ ({ \
  (__m64)__builtin_ia32_pshufw((__v4hi)(__m64)(a), (n)); })

/// \brief Conditionally copies the values from each 8-bit element in the first
///    64-bit integer vector operand to the specified memory location, as
///    specified by the most significant bit in the corresponding element in the
///    second 64-bit integer vector operand.
///
///    To minimize caching, the data is flagged as non-temporal
///    (unlikely to be used again soon).
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> MASKMOVQ </c> instruction.
///
/// \param __d
///    A 64-bit integer vector containing the values with elements to be copied.
/// \param __n
///    A 64-bit integer vector operand. The most significant bit from each 8-bit
///    element determines whether the corresponding element in operand \a __d
///    is copied. If the most significant bit of a given element is 1, the
///    corresponding element in operand \a __d is copied.
/// \param __p
///    A pointer to a 64-bit memory location that will receive the conditionally
///    copied integer values. The address of the memory location does not have
///    to be aligned.
static __inline__ void __DEFAULT_FN_ATTRS
_mm_maskmove_si64(__m64 __d, __m64 __n, char *__p)
{
  __builtin_ia32_maskmovq((__v8qi)__d, (__v8qi)__n, __p);
}

/// \brief Computes the rounded averages of the packed unsigned 8-bit integer
///    values and writes the averages to the corresponding bits in the
///    destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> PAVGB </c> instruction.
///
/// \param __a
///    A 64-bit integer vector containing one of the source operands.
/// \param __b
///    A 64-bit integer vector containing one of the source operands.
/// \returns A 64-bit integer vector containing the averages of both operands.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_avg_pu8(__m64 __a, __m64 __b)
{
  return (__m64)__builtin_ia32_pavgb((__v8qi)__a, (__v8qi)__b);
}

/// \brief Computes the rounded averages of the packed unsigned 16-bit integer
///    values and writes the averages to the corresponding bits in the
///    destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> PAVGW </c> instruction.
///
/// \param __a
///    A 64-bit integer vector containing one of the source operands.
/// \param __b
///    A 64-bit integer vector containing one of the source operands.
/// \returns A 64-bit integer vector containing the averages of both operands.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_avg_pu16(__m64 __a, __m64 __b)
{
  return (__m64)__builtin_ia32_pavgw((__v4hi)__a, (__v4hi)__b);
}

/// \brief Subtracts the corresponding 8-bit unsigned integer values of the two
///    64-bit vector operands and computes the absolute value for each of the
///    difference. Then sum of the 8 absolute differences is written to the
///    bits [15:0] of the destination; the remaining bits [63:16] are cleared.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> PSADBW </c> instruction.
///
/// \param __a
///    A 64-bit integer vector containing one of the source operands.
/// \param __b
///    A 64-bit integer vector containing one of the source operands.
/// \returns A 64-bit integer vector whose lower 16 bits contain the sums of the
///    sets of absolute differences between both operands. The upper bits are
///    cleared.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_sad_pu8(__m64 __a, __m64 __b)
{
  return (__m64)__builtin_ia32_psadbw((__v8qi)__a, (__v8qi)__b);
}

#if defined(__cplusplus)
extern "C" {
#endif

/// \brief Returns the contents of the MXCSR register as a 32-bit unsigned
///    integer value.
///
///    There are several groups of macros associated with this
///    intrinsic, including:
///    <ul>
///    <li>
///      For checking exception states: _MM_EXCEPT_INVALID, _MM_EXCEPT_DIV_ZERO,
///      _MM_EXCEPT_DENORM, _MM_EXCEPT_OVERFLOW, _MM_EXCEPT_UNDERFLOW,
///      _MM_EXCEPT_INEXACT. There is a convenience wrapper
///      _MM_GET_EXCEPTION_STATE().
///    </li>
///    <li>
///      For checking exception masks: _MM_MASK_UNDERFLOW, _MM_MASK_OVERFLOW,
///      _MM_MASK_INVALID, _MM_MASK_DENORM, _MM_MASK_DIV_ZERO, _MM_MASK_INEXACT.
///      There is a convenience wrapper _MM_GET_EXCEPTION_MASK().
///    </li>
///    <li>
///      For checking rounding modes: _MM_ROUND_NEAREST, _MM_ROUND_DOWN,
///      _MM_ROUND_UP, _MM_ROUND_TOWARD_ZERO. There is a convenience wrapper
///      _MM_GET_ROUNDING_MODE(x) where x is one of these macros.
///    </li>
///    <li>
///      For checking flush-to-zero mode: _MM_FLUSH_ZERO_ON, _MM_FLUSH_ZERO_OFF.
///      There is a convenience wrapper _MM_GET_FLUSH_ZERO_MODE().
///    </li>
///    <li>
///      For checking denormals-are-zero mode: _MM_DENORMALS_ZERO_ON,
///      _MM_DENORMALS_ZERO_OFF. There is a convenience wrapper
///      _MM_GET_DENORMALS_ZERO_MODE().
///    </li>
///    </ul>
///
///    For example, the expression below checks if an overflow exception has
///    occurred:
///      ( _mm_getcsr() & _MM_EXCEPT_OVERFLOW )
///
///    The following example gets the current rounding mode:
///      _MM_GET_ROUNDING_MODE()
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VSTMXCSR / STMXCSR </c> instruction.
///
/// \returns A 32-bit unsigned integer containing the contents of the MXCSR
///    register.
unsigned int _mm_getcsr(void);

/// \brief Sets the MXCSR register with the 32-bit unsigned integer value.
///
///    There are several groups of macros associated with this intrinsic,
///    including:
///    <ul>
///    <li>
///      For setting exception states: _MM_EXCEPT_INVALID, _MM_EXCEPT_DIV_ZERO,
///      _MM_EXCEPT_DENORM, _MM_EXCEPT_OVERFLOW, _MM_EXCEPT_UNDERFLOW,
///      _MM_EXCEPT_INEXACT. There is a convenience wrapper
///      _MM_SET_EXCEPTION_STATE(x) where x is one of these macros.
///    </li>
///    <li>
///      For setting exception masks: _MM_MASK_UNDERFLOW, _MM_MASK_OVERFLOW,
///      _MM_MASK_INVALID, _MM_MASK_DENORM, _MM_MASK_DIV_ZERO, _MM_MASK_INEXACT.
///      There is a convenience wrapper _MM_SET_EXCEPTION_MASK(x) where x is one
///      of these macros.
///    </li>
///    <li>
///      For setting rounding modes: _MM_ROUND_NEAREST, _MM_ROUND_DOWN,
///      _MM_ROUND_UP, _MM_ROUND_TOWARD_ZERO. There is a convenience wrapper
///      _MM_SET_ROUNDING_MODE(x) where x is one of these macros.
///    </li>
///    <li>
///      For setting flush-to-zero mode: _MM_FLUSH_ZERO_ON, _MM_FLUSH_ZERO_OFF.
///      There is a convenience wrapper _MM_SET_FLUSH_ZERO_MODE(x) where x is
///      one of these macros.
///    </li>
///    <li>
///      For setting denormals-are-zero mode: _MM_DENORMALS_ZERO_ON,
///      _MM_DENORMALS_ZERO_OFF. There is a convenience wrapper
///      _MM_SET_DENORMALS_ZERO_MODE(x) where x is one of these macros.
///    </li>
///    </ul>
///
///    For example, the following expression causes subsequent floating-point
///    operations to round up:
///      _mm_setcsr(_mm_getcsr() | _MM_ROUND_UP)
///
///    The following example sets the DAZ and FTZ flags:
///      void setFlags() {
///        _MM_SET_FLUSH_ZERO_MODE(_MM_FLUSH_ZERO_ON)
///        _MM_SET_DENORMALS_ZERO_MODE(_MM_DENORMALS_ZERO_ON)
///      }
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VLDMXCSR / LDMXCSR </c> instruction.
///
/// \param __i
///    A 32-bit unsigned integer value to be written to the MXCSR register.
void _mm_setcsr(unsigned int __i);

#if defined(__cplusplus)
} // extern "C"
#endif

/// \brief Selects 4 float values from the 128-bit operands of [4 x float], as
///    specified by the immediate value operand.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// __m128 _mm_shuffle_ps(__m128 a, __m128 b, const int mask);
/// \endcode
///
/// This intrinsic corresponds to the <c> VSHUFPS / SHUFPS </c> instruction.
///
/// \param a
///    A 128-bit vector of [4 x float].
/// \param b
///    A 128-bit vector of [4 x float].
/// \param mask
///    An immediate value containing an 8-bit value specifying which elements to
///    copy from \a a and \a b. \n
///    Bits [3:0] specify the values copied from operand \a a. \n
///    Bits [7:4] specify the values copied from operand \a b. \n
///    The destinations within the 128-bit destination are assigned values as
///    follows: \n
///    Bits [1:0] are used to assign values to bits [31:0] in the
///    destination. \n
///    Bits [3:2] are used to assign values to bits [63:32] in the
///    destination. \n
///    Bits [5:4] are used to assign values to bits [95:64] in the
///    destination. \n
///    Bits [7:6] are used to assign values to bits [127:96] in the
///    destination. \n
///    Bit value assignments: \n
///    00: Bits [31:0] copied from the specified operand. \n
///    01: Bits [63:32] copied from the specified operand. \n
///    10: Bits [95:64] copied from the specified operand. \n
///    11: Bits [127:96] copied from the specified operand.
/// \returns A 128-bit vector of [4 x float] containing the shuffled values.
#define _mm_shuffle_ps(a, b, mask) __extension__ ({ \
  (__m128)__builtin_shufflevector((__v4sf)(__m128)(a), (__v4sf)(__m128)(b), \
                                  0 + (((mask) >> 0) & 0x3), \
                                  0 + (((mask) >> 2) & 0x3), \
                                  4 + (((mask) >> 4) & 0x3), \
                                  4 + (((mask) >> 6) & 0x3)); })

/// \brief Unpacks the high-order (index 2,3) values from two 128-bit vectors of
///    [4 x float] and interleaves them into a 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUNPCKHPS / UNPCKHPS </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float]. \n
///    Bits [95:64] are written to bits [31:0] of the destination. \n
///    Bits [127:96] are written to bits [95:64] of the destination.
/// \param __b
///    A 128-bit vector of [4 x float].
///    Bits [95:64] are written to bits [63:32] of the destination. \n
///    Bits [127:96] are written to bits [127:96] of the destination.
/// \returns A 128-bit vector of [4 x float] containing the interleaved values.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_unpackhi_ps(__m128 __a, __m128 __b)
{
  return __builtin_shufflevector((__v4sf)__a, (__v4sf)__b, 2, 6, 3, 7);
}

/// \brief Unpacks the low-order (index 0,1) values from two 128-bit vectors of
///    [4 x float] and interleaves them into a 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUNPCKLPS / UNPCKLPS </c> instruction.
///
/// \param __a
///    A 128-bit vector of [4 x float]. \n
///    Bits [31:0] are written to bits [31:0] of the destination.  \n
///    Bits [63:32] are written to bits [95:64] of the destination.
/// \param __b
///    A 128-bit vector of [4 x float]. \n
///    Bits [31:0] are written to bits [63:32] of the destination. \n
///    Bits [63:32] are written to bits [127:96] of the destination.
/// \returns A 128-bit vector of [4 x float] containing the interleaved values.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_unpacklo_ps(__m128 __a, __m128 __b)
{
  return __builtin_shufflevector((__v4sf)__a, (__v4sf)__b, 0, 4, 1, 5);
}

/// \brief Constructs a 128-bit floating-point vector of [4 x float]. The lower
///    32 bits are set to the lower 32 bits of the second parameter. The upper
///    96 bits are set to the upper 96 bits of the first parameter.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVSS / MOVSS </c> instruction.
///
/// \param __a
///    A 128-bit floating-point vector of [4 x float]. The upper 96 bits are
///    written to the upper 96 bits of the result.
/// \param __b
///    A 128-bit floating-point vector of [4 x float]. The lower 32 bits are
///    written to the lower 32 bits of the result.
/// \returns A 128-bit floating-point vector of [4 x float].
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_move_ss(__m128 __a, __m128 __b)
{
  return __builtin_shufflevector((__v4sf)__a, (__v4sf)__b, 4, 1, 2, 3);
}

/// \brief Constructs a 128-bit floating-point vector of [4 x float]. The lower
///    64 bits are set to the upper 64 bits of the second parameter. The upper
///    64 bits are set to the upper 64 bits of the first parameter.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUNPCKHPD / UNPCKHPD </c> instruction.
///
/// \param __a
///    A 128-bit floating-point vector of [4 x float]. The upper 64 bits are
///    written to the upper 64 bits of the result.
/// \param __b
///    A 128-bit floating-point vector of [4 x float]. The upper 64 bits are
///    written to the lower 64 bits of the result.
/// \returns A 128-bit floating-point vector of [4 x float].
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_movehl_ps(__m128 __a, __m128 __b)
{
  return __builtin_shufflevector((__v4sf)__a, (__v4sf)__b, 6, 7, 2, 3);
}

/// \brief Constructs a 128-bit floating-point vector of [4 x float]. The lower
///    64 bits are set to the lower 64 bits of the first parameter. The upper
///    64 bits are set to the lower 64 bits of the second parameter.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUNPCKLPD / UNPCKLPD </c> instruction.
///
/// \param __a
///    A 128-bit floating-point vector of [4 x float]. The lower 64 bits are
///    written to the lower 64 bits of the result.
/// \param __b
///    A 128-bit floating-point vector of [4 x float]. The lower 64 bits are
///    written to the upper 64 bits of the result.
/// \returns A 128-bit floating-point vector of [4 x float].
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_movelh_ps(__m128 __a, __m128 __b)
{
  return __builtin_shufflevector((__v4sf)__a, (__v4sf)__b, 0, 1, 4, 5);
}

/// \brief Converts a 64-bit vector of [4 x i16] into a 128-bit vector of [4 x
///    float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTPI2PS + COMPOSITE </c> instruction.
///
/// \param __a
///    A 64-bit vector of [4 x i16]. The elements of the destination are copied
///    from the corresponding elements in this operand.
/// \returns A 128-bit vector of [4 x float] containing the copied and converted
///    values from the operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cvtpi16_ps(__m64 __a)
{
  __m64 __b, __c;
  __m128 __r;

  __b = _mm_setzero_si64();
  __b = _mm_cmpgt_pi16(__b, __a);
  __c = _mm_unpackhi_pi16(__a, __b);
  __r = _mm_setzero_ps();
  __r = _mm_cvtpi32_ps(__r, __c);
  __r = _mm_movelh_ps(__r, __r);
  __c = _mm_unpacklo_pi16(__a, __b);
  __r = _mm_cvtpi32_ps(__r, __c);

  return __r;
}

/// \brief Converts a 64-bit vector of 16-bit unsigned integer values into a
///    128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTPI2PS + COMPOSITE </c> instruction.
///
/// \param __a
///    A 64-bit vector of 16-bit unsigned integer values. The elements of the
///    destination are copied from the corresponding elements in this operand.
/// \returns A 128-bit vector of [4 x float] containing the copied and converted
///    values from the operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cvtpu16_ps(__m64 __a)
{
  __m64 __b, __c;
  __m128 __r;

  __b = _mm_setzero_si64();
  __c = _mm_unpackhi_pi16(__a, __b);
  __r = _mm_setzero_ps();
  __r = _mm_cvtpi32_ps(__r, __c);
  __r = _mm_movelh_ps(__r, __r);
  __c = _mm_unpacklo_pi16(__a, __b);
  __r = _mm_cvtpi32_ps(__r, __c);

  return __r;
}

/// \brief Converts the lower four 8-bit values from a 64-bit vector of [8 x i8]
///    into a 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTPI2PS + COMPOSITE </c> instruction.
///
/// \param __a
///    A 64-bit vector of [8 x i8]. The elements of the destination are copied
///    from the corresponding lower 4 elements in this operand.
/// \returns A 128-bit vector of [4 x float] containing the copied and converted
///    values from the operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cvtpi8_ps(__m64 __a)
{
  __m64 __b;

  __b = _mm_setzero_si64();
  __b = _mm_cmpgt_pi8(__b, __a);
  __b = _mm_unpacklo_pi8(__a, __b);

  return _mm_cvtpi16_ps(__b);
}

/// \brief Converts the lower four unsigned 8-bit integer values from a 64-bit
///    vector of [8 x u8] into a 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTPI2PS + COMPOSITE </c> instruction.
///
/// \param __a
///    A 64-bit vector of unsigned 8-bit integer values. The elements of the
///    destination are copied from the corresponding lower 4 elements in this
///    operand.
/// \returns A 128-bit vector of [4 x float] containing the copied and converted
///    values from the source operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cvtpu8_ps(__m64 __a)
{
  __m64 __b;

  __b = _mm_setzero_si64();
  __b = _mm_unpacklo_pi8(__a, __b);

  return _mm_cvtpi16_ps(__b);
}

/// \brief Converts the two 32-bit signed integer values from each 64-bit vector
///    operand of [2 x i32] into a 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTPI2PS + COMPOSITE </c> instruction.
///
/// \param __a
///    A 64-bit vector of [2 x i32]. The lower elements of the destination are
///    copied from the elements in this operand.
/// \param __b
///    A 64-bit vector of [2 x i32]. The upper elements of the destination are
///    copied from the elements in this operand.
/// \returns A 128-bit vector of [4 x float] whose lower 64 bits contain the
///    copied and converted values from the first operand. The upper 64 bits
///    contain the copied and converted values from the second operand.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_cvtpi32x2_ps(__m64 __a, __m64 __b)
{
  __m128 __c;

  __c = _mm_setzero_ps();
  __c = _mm_cvtpi32_ps(__c, __b);
  __c = _mm_movelh_ps(__c, __c);

  return _mm_cvtpi32_ps(__c, __a);
}

/// \brief Converts each single-precision floating-point element of a 128-bit
///    floating-point vector of [4 x float] into a 16-bit signed integer, and
///    packs the results into a 64-bit integer vector of [4 x i16].
///
///    If the floating-point element is NaN or infinity, or if the
///    floating-point element is greater than 0x7FFFFFFF or less than -0x8000,
///    it is converted to 0x8000. Otherwise if the floating-point element is
///    greater than 0x7FFF, it is converted to 0x7FFF.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTPS2PI + COMPOSITE </c> instruction.
///
/// \param __a
///    A 128-bit floating-point vector of [4 x float].
/// \returns A 64-bit integer vector of [4 x i16] containing the converted
///    values.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_cvtps_pi16(__m128 __a)
{
  __m64 __b, __c;

  __b = _mm_cvtps_pi32(__a);
  __a = _mm_movehl_ps(__a, __a);
  __c = _mm_cvtps_pi32(__a);

  return _mm_packs_pi32(__b, __c);
}

/// \brief Converts each single-precision floating-point element of a 128-bit
///    floating-point vector of [4 x float] into an 8-bit signed integer, and
///    packs the results into the lower 32 bits of a 64-bit integer vector of
///    [8 x i8]. The upper 32 bits of the vector are set to 0.
///
///    If the floating-point element is NaN or infinity, or if the
///    floating-point element is greater than 0x7FFFFFFF or less than -0x80, it
///    is converted to 0x80. Otherwise if the floating-point element is greater
///    than 0x7F, it is converted to 0x7F.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> CVTPS2PI + COMPOSITE </c> instruction.
///
/// \param __a
///    128-bit floating-point vector of [4 x float].
/// \returns A 64-bit integer vector of [8 x i8]. The lower 32 bits contain the
///    converted values and the uppper 32 bits are set to zero.
static __inline__ __m64 __DEFAULT_FN_ATTRS
_mm_cvtps_pi8(__m128 __a)
{
  __m64 __b, __c;

  __b = _mm_cvtps_pi16(__a);
  __c = _mm_setzero_si64();

  return _mm_packs_pi16(__b, __c);
}

/// \brief Extracts the sign bits from each single-precision floating-point
///    element of a 128-bit floating-point vector of [4 x float] and returns the
///    sign bits in bits [0:3] of the result. Bits [31:4] of the result are set
///    to zero.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVMSKPS / MOVMSKPS </c> instruction.
///
/// \param __a
///    A 128-bit floating-point vector of [4 x float].
/// \returns A 32-bit integer value. Bits [3:0] contain the sign bits from each
///    single-precision floating-point element of the parameter. Bits [31:4] are
///    set to zero.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_movemask_ps(__m128 __a)
{
  return __builtin_ia32_movmskps((__v4sf)__a);
}


#define _MM_ALIGN16 __attribute__((aligned(16)))

#define _MM_SHUFFLE(z, y, x, w) (((z) << 6) | ((y) << 4) | ((x) << 2) | (w))

#define _MM_EXCEPT_INVALID    (0x0001)
#define _MM_EXCEPT_DENORM     (0x0002)
#define _MM_EXCEPT_DIV_ZERO   (0x0004)
#define _MM_EXCEPT_OVERFLOW   (0x0008)
#define _MM_EXCEPT_UNDERFLOW  (0x0010)
#define _MM_EXCEPT_INEXACT    (0x0020)
#define _MM_EXCEPT_MASK       (0x003f)

#define _MM_MASK_INVALID      (0x0080)
#define _MM_MASK_DENORM       (0x0100)
#define _MM_MASK_DIV_ZERO     (0x0200)
#define _MM_MASK_OVERFLOW     (0x0400)
#define _MM_MASK_UNDERFLOW    (0x0800)
#define _MM_MASK_INEXACT      (0x1000)
#define _MM_MASK_MASK         (0x1f80)

#define _MM_ROUND_NEAREST     (0x0000)
#define _MM_ROUND_DOWN        (0x2000)
#define _MM_ROUND_UP          (0x4000)
#define _MM_ROUND_TOWARD_ZERO (0x6000)
#define _MM_ROUND_MASK        (0x6000)

#define _MM_FLUSH_ZERO_MASK   (0x8000)
#define _MM_FLUSH_ZERO_ON     (0x8000)
#define _MM_FLUSH_ZERO_OFF    (0x0000)

#define _MM_GET_EXCEPTION_MASK() (_mm_getcsr() & _MM_MASK_MASK)
#define _MM_GET_EXCEPTION_STATE() (_mm_getcsr() & _MM_EXCEPT_MASK)
#define _MM_GET_FLUSH_ZERO_MODE() (_mm_getcsr() & _MM_FLUSH_ZERO_MASK)
#define _MM_GET_ROUNDING_MODE() (_mm_getcsr() & _MM_ROUND_MASK)

#define _MM_SET_EXCEPTION_MASK(x) (_mm_setcsr((_mm_getcsr() & ~_MM_MASK_MASK) | (x)))
#define _MM_SET_EXCEPTION_STATE(x) (_mm_setcsr((_mm_getcsr() & ~_MM_EXCEPT_MASK) | (x)))
#define _MM_SET_FLUSH_ZERO_MODE(x) (_mm_setcsr((_mm_getcsr() & ~_MM_FLUSH_ZERO_MASK) | (x)))
#define _MM_SET_ROUNDING_MODE(x) (_mm_setcsr((_mm_getcsr() & ~_MM_ROUND_MASK) | (x)))

#define _MM_TRANSPOSE4_PS(row0, row1, row2, row3) \
do { \
  __m128 tmp3, tmp2, tmp1, tmp0; \
  tmp0 = _mm_unpacklo_ps((row0), (row1)); \
  tmp2 = _mm_unpacklo_ps((row2), (row3)); \
  tmp1 = _mm_unpackhi_ps((row0), (row1)); \
  tmp3 = _mm_unpackhi_ps((row2), (row3)); \
  (row0) = _mm_movelh_ps(tmp0, tmp2); \
  (row1) = _mm_movehl_ps(tmp2, tmp0); \
  (row2) = _mm_movelh_ps(tmp1, tmp3); \
  (row3) = _mm_movehl_ps(tmp3, tmp1); \
} while (0)

/* Aliases for compatibility. */
#define _m_pextrw _mm_extract_pi16
#define _m_pinsrw _mm_insert_pi16
#define _m_pmaxsw _mm_max_pi16
#define _m_pmaxub _mm_max_pu8
#define _m_pminsw _mm_min_pi16
#define _m_pminub _mm_min_pu8
#define _m_pmovmskb _mm_movemask_pi8
#define _m_pmulhuw _mm_mulhi_pu16
#define _m_pshufw _mm_shuffle_pi16
#define _m_maskmovq _mm_maskmove_si64
#define _m_pavgb _mm_avg_pu8
#define _m_pavgw _mm_avg_pu16
#define _m_psadbw _mm_sad_pu8
#define _m_ _mm_
#define _m_ _mm_

#undef __DEFAULT_FN_ATTRS

/* Ugly hack for backwards-compatibility (compatible with gcc) */
#if defined(__SSE2__) && !__building_module(_Builtin_intrinsics)
#include <emmintrin.h>
#endif

#endif /* __XMMINTRIN_H */