summaryrefslogtreecommitdiff
path: root/lib/AsmJit/AssemblerX86X64.h
blob: b660336e8926b14957b2d1eaef0e1a9b395300a9 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
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
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
// AsmJit - Complete JIT Assembler for C++ Language.

// Copyright (c) 2008-2010, Petr Kobalicek <kobalicek.petr@gmail.com>
//
// 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.

// [Guard]
#ifndef _ASMJIT_ASSEMBLERX86X64_H
#define _ASMJIT_ASSEMBLERX86X64_H

#if !defined(_ASMJIT_ASSEMBLER_H)
#warning "AsmJit/AssemblerX86X64.h can be only included by AsmJit/Assembler.h"
#endif // _ASMJIT_ASSEMBLER_H

// [Dependencies]
#include "Build.h"
#include "Defs.h"
#include "Operand.h"
#include "Util.h"

// [Api-Begin]
#include "ApiBegin.h"

namespace AsmJit {

//! @addtogroup AsmJit_Core
//! @{

// ============================================================================
// [Forward Declarations]
// ============================================================================

struct CodeGenerator;

// ============================================================================
// [AsmJit::AssemblerCore]
// ============================================================================

//! @brief AssemblerCore is part of @c Assembler class.
//!
//! @c AssemblerCore class implements part of assembler serializing API. The
//! reason why @c Assembler class was split is that we want to hide exported
//! symbols in dynamically linked libraries.
//!
//! Please always use @c Assembler class instead.
//!
//! @sa @c Assembler.
struct ASMJIT_API AssemblerCore
{
  // --------------------------------------------------------------------------
  // [Construction / Destruction]
  // --------------------------------------------------------------------------

  //! @brief Creates Assembler instance.
  AssemblerCore(CodeGenerator* codeGenerator) ASMJIT_NOTHROW;
  //! @brief Destroys Assembler instance
  virtual ~AssemblerCore() ASMJIT_NOTHROW;

  // --------------------------------------------------------------------------
  // [LabelLink]
  // --------------------------------------------------------------------------

  //! @brief Data structure used to link linked-labels.
  struct LabelLink
  {
    //! @brief Previous link.
    LabelLink* prev;
    //! @brief Offset.
    sysint_t offset;
    //! @brief Inlined displacement.
    sysint_t displacement;
    //! @brief RelocId if link must be absolute when relocated.
    sysint_t relocId;
  };

  // --------------------------------------------------------------------------
  // [LabelData]
  // --------------------------------------------------------------------------

  //! @brief Label data.
  struct LabelData
  {
    //! @brief Label offset.
    sysint_t offset;
    //! @brief Label links chain.
    LabelLink* links;
  };

  // --------------------------------------------------------------------------
  // [RelocData]
  // --------------------------------------------------------------------------

  // X86 architecture uses 32-bit absolute addressing model by memory operands,
  // but 64-bit mode uses relative addressing model (RIP + displacement). In
  // code we are always using relative addressing model for referencing labels
  // and embedded data. In 32-bit mode we must patch all references to absolute
  // address before we can call generated function. We are patching only memory
  // operands.

  //! @brief Code relocation data (relative vs absolute addresses).
  struct RelocData
  {
    enum Type
    {
      ABSOLUTE_TO_ABSOLUTE = 0,
      RELATIVE_TO_ABSOLUTE = 1,
      ABSOLUTE_TO_RELATIVE = 2,
      ABSOLUTE_TO_RELATIVE_TRAMPOLINE = 3
    };

    //! @brief Type of relocation.
    uint32_t type;

    //! @brief Size of relocation (4 or 8 bytes).
    uint32_t size;

    //! @brief Offset from code begin address.
    sysint_t offset;

    //! @brief Relative displacement or absolute address.
    union
    {
      //! @brief Relative displacement from code begin address (not to @c offset).
      sysint_t destination;
      //! @brief Absolute address where to jump;
      void* address;
    };
  };

  // --------------------------------------------------------------------------
  // [Code Generator]
  // --------------------------------------------------------------------------

  //! @brief Get code generator.
  inline CodeGenerator* getCodeGenerator() const { return _codeGenerator; }

  // --------------------------------------------------------------------------
  // [Memory Management]
  // --------------------------------------------------------------------------

  //! @brief Get zone memory manager.
  inline Zone& getZone() ASMJIT_NOTHROW { return _zone; }

  // --------------------------------------------------------------------------
  // [Logging]
  // --------------------------------------------------------------------------

  //! @brief Get logger.
  inline Logger* getLogger() const ASMJIT_NOTHROW { return _logger; }

  //! @brief Set logger to @a logger.
  virtual void setLogger(Logger* logger) ASMJIT_NOTHROW;

  // --------------------------------------------------------------------------
  // [Error Handling]
  // --------------------------------------------------------------------------

  //! @brief Get error code.
  inline uint32_t getError() const ASMJIT_NOTHROW { return _error; }

  //! @brief Set error code.
  //!
  //! This method is virtual, because higher classes can use it to catch all
  //! errors.
  virtual void setError(uint32_t error) ASMJIT_NOTHROW;

  // --------------------------------------------------------------------------
  // [Properties]
  // --------------------------------------------------------------------------

  //! @brief Get assembler property.
  uint32_t getProperty(uint32_t propertyId);
  //! @brief Set assembler property.
  void setProperty(uint32_t propertyId, uint32_t value);

  // --------------------------------------------------------------------------
  // [Buffer Getters / Setters]
  // --------------------------------------------------------------------------

  //! @brief Return start of assembler code buffer.
  //!
  //! Note that buffer address can change if you emit instruction or something
  //! else. Use this pointer only when you finished or make sure you do not
  //! use returned pointer after emitting.
  inline uint8_t* getCode() const ASMJIT_NOTHROW
  { return _buffer.getData(); }

  //! @brief Ensure space for next instruction.
  //!
  //! Note that this method can return false. It's rare and probably you never
  //! get this, but in some situations it's still possible.
  inline bool ensureSpace() ASMJIT_NOTHROW
  { return _buffer.ensureSpace(); }

  //! @brief Return current offset in buffer).
  inline sysint_t getOffset() const ASMJIT_NOTHROW
  { return _buffer.getOffset(); }

  //! @brief Return current offset in buffer (same as getCffset() + getTramplineSize()).
  inline sysint_t getCodeSize() const ASMJIT_NOTHROW
  { return _buffer.getOffset() + getTrampolineSize(); }

  //! @brief Get size of all possible trampolines needed to successfuly generate
  //! relative jumps to absolute addresses. This value is only non-zero if jmp
  //! of call instructions were used with immediate operand (this means jump or
  //! call absolute address directly).
  //!
  //! Currently only _emitJmpOrCallReloc() method can increase trampoline size
  //! value.
  inline sysint_t getTrampolineSize() const ASMJIT_NOTHROW
  { return _trampolineSize; }

  //! @brief Set offset to @a o and returns previous offset.
  //!
  //! This method can be used to truncate code (previous offset is not
  //! recorded) or to overwrite instruction stream at position @a o.
  //!
  //! @return Previous offset value that can be uset to set offset back later.
  inline sysint_t toOffset(sysint_t o) ASMJIT_NOTHROW
  { return _buffer.toOffset(o); }

  //! @brief Get capacity of internal code buffer.
  inline sysint_t getCapacity() const ASMJIT_NOTHROW
  { return _buffer.getCapacity(); }

  //! @brief Clear everything, but not deallocate buffers.
  void clear() ASMJIT_NOTHROW;

  //! @brief Free internal buffer and NULL all pointers.
  void free() ASMJIT_NOTHROW;

  //! @brief Take internal code buffer and NULL all pointers (you take the ownership).
  uint8_t* takeCode() ASMJIT_NOTHROW;

  // --------------------------------------------------------------------------
  // [Stream Setters / Getters]
  // --------------------------------------------------------------------------

  //! @brief Set byte at position @a pos.
  inline uint8_t getByteAt(sysint_t pos) const ASMJIT_NOTHROW
  { return _buffer.getByteAt(pos); }
  
  //! @brief Set word at position @a pos.
  inline uint16_t getWordAt(sysint_t pos) const ASMJIT_NOTHROW
  { return _buffer.getWordAt(pos); }
  
  //! @brief Set word at position @a pos.
  inline uint32_t getDWordAt(sysint_t pos) const ASMJIT_NOTHROW
  { return _buffer.getDWordAt(pos); }
  
  //! @brief Set word at position @a pos.
  inline uint64_t getQWordAt(sysint_t pos) const ASMJIT_NOTHROW
  { return _buffer.getQWordAt(pos); }

  //! @brief Set byte at position @a pos.
  inline void setByteAt(sysint_t pos, uint8_t x) ASMJIT_NOTHROW
  { _buffer.setByteAt(pos, x); }
  
  //! @brief Set word at position @a pos.
  inline void setWordAt(sysint_t pos, uint16_t x) ASMJIT_NOTHROW
  { _buffer.setWordAt(pos, x); }
  
  //! @brief Set word at position @a pos.
  inline void setDWordAt(sysint_t pos, uint32_t x) ASMJIT_NOTHROW
  { _buffer.setDWordAt(pos, x); }
  
  //! @brief Set word at position @a pos.
  inline void setQWordAt(sysint_t pos, uint64_t x) ASMJIT_NOTHROW
  { _buffer.setQWordAt(pos, x); }

  //! @brief Set word at position @a pos.
  inline int32_t getInt32At(sysint_t pos) const ASMJIT_NOTHROW
  { return (int32_t)_buffer.getDWordAt(pos); }
  
  //! @brief Set int32 at position @a pos.
  inline void setInt32At(sysint_t pos, int32_t x) ASMJIT_NOTHROW
  { _buffer.setDWordAt(pos, (int32_t)x); }

  //! @brief Set custom variable @a imm at position @a pos.
  //!
  //! @note This function is used to patch existing code.
  void setVarAt(sysint_t pos, sysint_t i, uint8_t isUnsigned, uint32_t size) ASMJIT_NOTHROW;

  // --------------------------------------------------------------------------
  // [Assembler Emitters]
  //
  // These emitters are not protecting buffer from overrun, this must be 
  // done is emitX86() methods by:
  //   if (!canEmit()) return;
  // --------------------------------------------------------------------------

  //! @brief Get whether next instruction can be emitted.
  //!
  //! This function behaves like @c ensureSpace(), but it also checks if
  //! assembler is in error state and in that case it returns @c false.
  //! Assembler internally always uses this function before new instruction is
  //! emitted.
  //!
  //! It's implemented like:
  //!   <code>return ensureSpace() && !getError();</code>
  bool canEmit() ASMJIT_NOTHROW;

  //! @brief Emit Byte to internal buffer.
  inline void _emitByte(uint8_t x) ASMJIT_NOTHROW
  { _buffer.emitByte(x); }

  //! @brief Emit Word (2 bytes) to internal buffer.
  inline void _emitWord(uint16_t x) ASMJIT_NOTHROW
  { _buffer.emitWord(x); }

  //! @brief Emit DWord (4 bytes) to internal buffer.
  inline void _emitDWord(uint32_t x) ASMJIT_NOTHROW
  { _buffer.emitDWord(x); }

  //! @brief Emit QWord (8 bytes) to internal buffer.
  inline void _emitQWord(uint64_t x) ASMJIT_NOTHROW
  { _buffer.emitQWord(x); }

  //! @brief Emit Int32 (4 bytes) to internal buffer.
  inline void _emitInt32(int32_t x) ASMJIT_NOTHROW
  { _buffer.emitDWord((uint32_t)x); }

  //! @brief Emit system signed integer (4 or 8 bytes) to internal buffer.
  inline void _emitSysInt(sysint_t x) ASMJIT_NOTHROW
  { _buffer.emitSysInt(x); }

  //! @brief Emit system unsigned integer (4 or 8 bytes) to internal buffer.
  inline void _emitSysUInt(sysuint_t x) ASMJIT_NOTHROW
  { _buffer.emitSysUInt(x); }

  //! @brief Emit single @a opCode without operands.
  inline void _emitOpCode(uint32_t opCode) ASMJIT_NOTHROW
  {
    // instruction prefix
    if (opCode & 0xFF000000) _emitByte((uint8_t)((opCode & 0xFF000000) >> 24));
    // instruction opcodes
    if (opCode & 0x00FF0000) _emitByte((uint8_t)((opCode & 0x00FF0000) >> 16));
    if (opCode & 0x0000FF00) _emitByte((uint8_t)((opCode & 0x0000FF00) >>  8));
    // last opcode is always emitted (can be also 0x00)
    _emitByte((uint8_t)(opCode & 0x000000FF));
  }

  //! @brief Emit CS (code segmend) prefix.
  //!
  //! Behavior of this function is to emit code prefix only if memory operand
  //! address uses code segment. Code segment is used through memory operand
  //! with attached @c AsmJit::Label.
  void _emitSegmentPrefix(const Operand& rm) ASMJIT_NOTHROW;

  //! @brief Emit MODR/M byte.
  inline void _emitMod(uint8_t m, uint8_t o, uint8_t r) ASMJIT_NOTHROW
  { _emitByte(((m & 0x03) << 6) | ((o & 0x07) << 3) | (r & 0x07)); }

  //! @brief Emit SIB byte.
  inline void _emitSib(uint8_t s, uint8_t i, uint8_t b) ASMJIT_NOTHROW
  { _emitByte(((s & 0x03) << 6) | ((i & 0x07) << 3) | (b & 0x07)); }

  //! @brief Emit REX prefix (64-bit mode only).
  inline void _emitRexR(uint8_t w, uint8_t opReg, uint8_t regCode, bool forceRexPrefix) ASMJIT_NOTHROW
  {
#if defined(ASMJIT_X64)
    uint8_t r = (opReg & 0x8) != 0;
    uint8_t b = (regCode & 0x8) != 0;

    // w Default operand size(0=Default, 1=64-bit).
    // r Register field (1=high bit extension of the ModR/M REG field).
    // x Index field not used in RexR
    // b Base field (1=high bit extension of the ModR/M or SIB Base field).
    if (w || r || b || forceRexPrefix)
    {
      _emitByte(0x40 | (w << 3) | (r << 2) | b);
    }
#else
    ASMJIT_UNUSED(w);
    ASMJIT_UNUSED(opReg);
    ASMJIT_UNUSED(regCode);
    ASMJIT_UNUSED(forceRexPrefix);
#endif // ASMJIT_X64
  }

  //! @brief Emit REX prefix (64-bit mode only).
  inline void _emitRexRM(uint8_t w, uint8_t opReg, const Operand& rm, bool forceRexPrefix) ASMJIT_NOTHROW
  {
#if defined(ASMJIT_X64)
    uint8_t r = (opReg & 0x8) != 0;
    uint8_t x = 0;
    uint8_t b = 0;

    if (rm.isReg())
    {
      b = (reinterpret_cast<const BaseReg&>(rm).getRegCode() & 0x8) != 0;
    }
    else if (rm.isMem())
    {
      x = ((reinterpret_cast<const Mem&>(rm).getIndex() & 0x8) != 0) & (reinterpret_cast<const Mem&>(rm).getIndex() != INVALID_VALUE);
      b = ((reinterpret_cast<const Mem&>(rm).getBase() & 0x8) != 0) & (reinterpret_cast<const Mem&>(rm).getBase() != INVALID_VALUE);
    }

    // w Default operand size(0=Default, 1=64-bit).
    // r Register field (1=high bit extension of the ModR/M REG field).
    // x Index field (1=high bit extension of the SIB Index field).
    // b Base field (1=high bit extension of the ModR/M or SIB Base field).
    if (w || r || x || b || forceRexPrefix)
    {
      _emitByte(0x40 | (w << 3) | (r << 2) | (x << 1) | b);
    }
#else
    ASMJIT_UNUSED(w);
    ASMJIT_UNUSED(opReg);
    ASMJIT_UNUSED(rm);
#endif // ASMJIT_X64
  }

  //! @brief Emit Register / Register - calls _emitMod(3, opReg, r)
  inline void _emitModR(uint8_t opReg, uint8_t r) ASMJIT_NOTHROW
  { _emitMod(3, opReg, r); }

  //! @brief Emit Register / Register - calls _emitMod(3, opReg, r.code())
  inline void _emitModR(uint8_t opReg, const BaseReg& r) ASMJIT_NOTHROW
  { _emitMod(3, opReg, r.getRegCode()); }

  //! @brief Emit register / memory address combination to buffer.
  //!
  //! This method can hangle addresses from simple to complex ones with
  //! index and displacement.
  void _emitModM(uint8_t opReg, const Mem& mem, sysint_t immSize) ASMJIT_NOTHROW;

  //! @brief Emit Reg<-Reg or Reg<-Reg|Mem ModRM (can be followed by SIB 
  //! and displacement) to buffer.
  //!
  //! This function internally calls @c _emitModM() or _emitModR() that depends
  //! to @a op type.
  //!
  //! @note @a opReg is usually real register ID (see @c R) but some instructions
  //! have specific format and in that cases @a opReg is part of opcode.
  void _emitModRM(uint8_t opReg, const Operand& op, sysint_t immSize) ASMJIT_NOTHROW;

  //! @brief Emit instruction where register is inlined to opcode.
  void _emitX86Inl(uint32_t opCode, uint8_t i16bit, uint8_t rexw, uint8_t reg, bool forceRexPrefix) ASMJIT_NOTHROW;

  //! @brief Emit instruction with reg/memory operand.
  void _emitX86RM(uint32_t opCode, uint8_t i16bit, uint8_t rexw, uint8_t o,
    const Operand& op, sysint_t immSize, bool forceRexPrefix) ASMJIT_NOTHROW;

  //! @brief Emit FPU instruction with no operands.
  void _emitFpu(uint32_t opCode) ASMJIT_NOTHROW;

  //! @brief Emit FPU instruction with one operand @a sti (index of FPU register).
  void _emitFpuSTI(uint32_t opCode, uint32_t sti) ASMJIT_NOTHROW;

  //! @brief Emit FPU instruction with one operand @a opReg and memory operand @a mem.
  void _emitFpuMEM(uint32_t opCode, uint8_t opReg, const Mem& mem) ASMJIT_NOTHROW;

  //! @brief Emit MMX/SSE instruction.
  void _emitMmu(uint32_t opCode, uint8_t rexw, uint8_t opReg, const Operand& src,
    sysint_t immSize) ASMJIT_NOTHROW;

  //! @brief Emit displacement.
  LabelLink* _emitDisplacement(LabelData& l_data, sysint_t inlinedDisplacement, int size) ASMJIT_NOTHROW;

  //! @brief Emit relative relocation to absolute pointer @a target. It's needed
  //! to add what instruction is emitting this, because in x64 mode the relative
  //! displacement can be impossible to calculate and in this case the trampoline
  //! is used.
  void _emitJmpOrCallReloc(uint32_t instruction, void* target) ASMJIT_NOTHROW;

  // Helpers to decrease binary code size. These four emit methods are just
  // helpers thats used by assembler. They call emitX86() adding NULLs
  // to first, second and third operand, if needed.

  //! @brief Emit X86/FPU or MM/XMM instruction.
  void _emitInstruction(uint32_t code) ASMJIT_NOTHROW;

  //! @brief Emit X86/FPU or MM/XMM instruction.
  void _emitInstruction(uint32_t code, const Operand* o0) ASMJIT_NOTHROW;

  //! @brief Emit X86/FPU or MM/XMM instruction.
  void _emitInstruction(uint32_t code, const Operand* o0, const Operand* o1) ASMJIT_NOTHROW;

  //! @brief Emit X86/FPU or MM/XMM instruction.
  //!
  //! Operands @a o1, @a o2 or @a o3 can be @c NULL if they are not used.
  //!
  //! Hint: Use @c emitX86() helpers to emit instructions.
  void _emitInstruction(uint32_t code, const Operand* o0, const Operand* o1, const Operand* o2) ASMJIT_NOTHROW;

  //! @brief Private method for emitting jcc.
  void _emitJcc(uint32_t code, const Label* label, uint32_t hint) ASMJIT_NOTHROW;

  //! @brief Private method for emitting short jcc.
  inline void _emitShortJcc(uint32_t code, const Label* label, uint32_t hint)
  {
    _emitOptions |= EMIT_OPTION_SHORT_JUMP;
    _emitJcc(code, label, hint);
  }

  // --------------------------------------------------------------------------
  // [Relocation helpers]
  // --------------------------------------------------------------------------

  //! @brief Relocate code to a given address @a dst.
  //!
  //! @param dst Where the relocated code should me stored. The pointer can be
  //! address returned by virtual memory allocator or your own address if you
  //! want only to store the code for later reuse (or load, etc...).
  //! @param addressBase Base address used for relocation. When using JIT code
  //! generation, this will be the same as @a dst, only casted to system
  //! integer type. But when generating code for remote process then the value
  //! can be different.
  //!
  //! @retval The bytes used. Code-generator can create trampolines which are
  //! used when calling other functions inside the JIT code. However, these
  //! trampolines can be unused so the relocCode() returns the exact size needed
  //! for the function.
  //!
  //! A given buffer will be overwritten, to get number of bytes required use
  //! @c getCodeSize() .
  virtual sysuint_t relocCode(void* dst, sysuint_t addressBase) const ASMJIT_NOTHROW;

  //! @brief Simplifed version of @c relocCode() method.
  inline sysuint_t relocCode(void* dst) const ASMJIT_NOTHROW
  {
    return relocCode(dst, (sysuint_t)dst);
  }

  // --------------------------------------------------------------------------
  // [Embed]
  // --------------------------------------------------------------------------

  //! @brief Embed data into instruction stream.
  void embed(const void* data, sysuint_t length) ASMJIT_NOTHROW;
  //! @brief Embed absolute label pointer (4 or 8 bytes).
  void embedLabel(const Label& label) ASMJIT_NOTHROW;

  // --------------------------------------------------------------------------
  // [Align]
  // --------------------------------------------------------------------------

  //! @brief Align target buffer to @a m bytes.
  //!
  //! Typical usage of this is to align labels at start of the inner loops.
  //!
  //! Inserts @c nop() instructions or CPU optimized NOPs.
  void align(uint32_t m) ASMJIT_NOTHROW;

  // --------------------------------------------------------------------------
  // [Label]
  // --------------------------------------------------------------------------

  //! @brief Create and return new label.
  Label newLabel() ASMJIT_NOTHROW;

  //! @brief Register labels (used by @c Compiler).
  void registerLabels(sysuint_t count) ASMJIT_NOTHROW;

  //! @brief Bind label to the current offset.
  //!
  //! @note Label can be bound only once!
  void bind(const Label& label) ASMJIT_NOTHROW;

  // --------------------------------------------------------------------------
  // [Make]
  // --------------------------------------------------------------------------

  //! @brief Make is convenience method to make currently serialized code and
  //! return pointer to generated function.
  //!
  //! What you need is only to cast this pointer to your function type and call
  //! it. Note that if there was an error and calling @c getError() method not
  //! returns @c ERROR_NONE (zero) then this function always return @c NULL and
  //! error value remains the same.
  virtual void* make() ASMJIT_NOTHROW;

  // --------------------------------------------------------------------------
  // [Links]
  // --------------------------------------------------------------------------

  LabelLink* _newLabelLink() ASMJIT_NOTHROW;

  // --------------------------------------------------------------------------
  // [Members]
  // --------------------------------------------------------------------------

protected:

  //! @brief Code generator instance.
  CodeGenerator* _codeGenerator;

  //! @brief Zone memory management.
  Zone _zone;

  //! @brief Logger.
  Logger* _logger;

  //! @brief Last error code.
  uint32_t _error;

  //! @brief Properties.
  uint32_t _properties;

  //! @brief Emit flags for next instruction (cleared after emit).
  uint32_t _emitOptions;

  //! @brief Binary code buffer.
  Buffer _buffer;

  //! @brief Size of possible trampolines.
  sysint_t _trampolineSize;

  //! @brief Linked list of unused links (@c LabelLink* structures)
  LabelLink* _unusedLinks;

  //! @brief Labels data.
  PodVector<LabelData> _labelData;

  //! @brief Relocations data.
  PodVector<RelocData> _relocData;

  //! @brief Comment that will be logger by next emitted instruction. After
  //! instruction is logger the _comment is set to NULL.
  const char* _comment;

  friend struct CompilerCore;
  friend struct EInstruction;
};

// ============================================================================
// [AsmJit::AssemblerIntrinsics]
// ============================================================================

//! @brief AssemblerIntrinsics is part of @c Assembler class.
//!
//! @c AssemblerIntrinsics class implements part of assembler serializing API.
//! The reason why @c Assembler class was split is that we want to hide exported
//! symbols in dynamically linked libraries.
//!
//! Please always use @c Assembler class instead.
//!
//! @sa @c Assembler.
struct ASMJIT_HIDDEN AssemblerIntrinsics : public AssemblerCore
{
  // --------------------------------------------------------------------------
  // [Construction / Destruction]
  // --------------------------------------------------------------------------

  inline AssemblerIntrinsics(CodeGenerator* codeGenerator) ASMJIT_NOTHROW :
    AssemblerCore(codeGenerator)
  {
  }

  // --------------------------------------------------------------------------
  // [Embed]
  // --------------------------------------------------------------------------

  //! @brief Add 8-bit integer data to the instuction stream.
  inline void db(uint8_t  x) ASMJIT_NOTHROW { embed(&x, 1); }
  //! @brief Add 16-bit integer data to the instuction stream.
  inline void dw(uint16_t x) ASMJIT_NOTHROW { embed(&x, 2); }
  //! @brief Add 32-bit integer data to the instuction stream.
  inline void dd(uint32_t x) ASMJIT_NOTHROW { embed(&x, 4); }
  //! @brief Add 64-bit integer data to the instuction stream.
  inline void dq(uint64_t x) ASMJIT_NOTHROW { embed(&x, 8); }

  //! @brief Add 8-bit integer data to the instuction stream.
  inline void dint8(int8_t x) ASMJIT_NOTHROW { embed(&x, sizeof(int8_t)); }
  //! @brief Add 8-bit integer data to the instuction stream.
  inline void duint8(uint8_t x) ASMJIT_NOTHROW { embed(&x, sizeof(uint8_t)); }

  //! @brief Add 16-bit integer data to the instuction stream.
  inline void dint16(int16_t x) ASMJIT_NOTHROW { embed(&x, sizeof(int16_t)); }
  //! @brief Add 16-bit integer data to the instuction stream.
  inline void duint16(uint16_t x) ASMJIT_NOTHROW { embed(&x, sizeof(uint16_t)); }

  //! @brief Add 32-bit integer data to the instuction stream.
  inline void dint32(int32_t x) ASMJIT_NOTHROW { embed(&x, sizeof(int32_t)); }
  //! @brief Add 32-bit integer data to the instuction stream.
  inline void duint32(uint32_t x) ASMJIT_NOTHROW { embed(&x, sizeof(uint32_t)); }

  //! @brief Add 64-bit integer data to the instuction stream.
  inline void dint64(int64_t x) ASMJIT_NOTHROW { embed(&x, sizeof(int64_t)); }
  //! @brief Add 64-bit integer data to the instuction stream.
  inline void duint64(uint64_t x) ASMJIT_NOTHROW { embed(&x, sizeof(uint64_t)); }

  //! @brief Add system-integer data to the instuction stream.
  inline void dsysint(sysint_t x) ASMJIT_NOTHROW { embed(&x, sizeof(sysint_t)); }
  //! @brief Add system-integer data to the instuction stream.
  inline void dsysuint(sysuint_t x) ASMJIT_NOTHROW { embed(&x, sizeof(sysuint_t)); }

  //! @brief Add float data to the instuction stream.
  inline void dfloat(float x) ASMJIT_NOTHROW { embed(&x, sizeof(float)); }
  //! @brief Add double data to the instuction stream.
  inline void ddouble(double x) ASMJIT_NOTHROW { embed(&x, sizeof(double)); }

  //! @brief Add pointer data to the instuction stream.
  inline void dptr(void* x) ASMJIT_NOTHROW { embed(&x, sizeof(void*)); }

  //! @brief Add MM data to the instuction stream.
  inline void dmm(const MMData& x) ASMJIT_NOTHROW { embed(&x, sizeof(MMData)); }
  //! @brief Add XMM data to the instuction stream.
  inline void dxmm(const XMMData& x) ASMJIT_NOTHROW { embed(&x, sizeof(XMMData)); }

  //! @brief Add data to the instuction stream.
  inline void data(const void* data, sysuint_t size) ASMJIT_NOTHROW { embed(data, size); }

  //! @brief Add data in a given structure instance to the instuction stream.
  template<typename T>
  inline void dstruct(const T& x) ASMJIT_NOTHROW { embed(&x, sizeof(T)); }

  // --------------------------------------------------------------------------
  // [X86 Instructions]
  // --------------------------------------------------------------------------

  //! @brief Add with Carry.
  inline void adc(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_ADC, &dst, &src);
  }
  //! @brief Add with Carry.
  inline void adc(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ADC, &dst, &src);
  }
  //! @brief Add with Carry.
  inline void adc(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_ADC, &dst, &src);
  }
  //! @brief Add with Carry.
  inline void adc(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_ADC, &dst, &src);
  }
  //! @brief Add with Carry.
  inline void adc(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_ADC, &dst, &src);
  }

  //! @brief Add.
  inline void add(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_ADD, &dst, &src);
  }
  //! @brief Add.
  inline void add(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ADD, &dst, &src);
  }
  //! @brief Add.
  inline void add(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_ADD, &dst, &src);
  }
  //! @brief Add.
  inline void add(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_ADD, &dst, &src);
  }
  //! @brief Add.
  inline void add(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_ADD, &dst, &src);
  }

  //! @brief Logical And.
  inline void and_(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_AND, &dst, &src);
  }
  //! @brief Logical And.
  inline void and_(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_AND, &dst, &src);
  }
  //! @brief Logical And.
  inline void and_(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_AND, &dst, &src);
  }
  //! @brief Logical And.
  inline void and_(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_AND, &dst, &src);
  }
  //! @brief Logical And.
  inline void and_(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_AND, &dst, &src);
  }

  //! @brief Bit Scan Forward.
  inline void bsf(const GPReg& dst, const GPReg& src)
  {
    ASMJIT_ASSERT(!dst.isGPB());
    _emitInstruction(INST_BSF, &dst, &src);
  }
  //! @brief Bit Scan Forward.
  inline void bsf(const GPReg& dst, const Mem& src)
  {
    ASMJIT_ASSERT(!dst.isGPB());
    _emitInstruction(INST_BSF, &dst, &src);
  }

  //! @brief Bit Scan Reverse.
  inline void bsr(const GPReg& dst, const GPReg& src)
  {
    ASMJIT_ASSERT(!dst.isGPB());
    _emitInstruction(INST_BSR, &dst, &src);
  }
  //! @brief Bit Scan Reverse.
  inline void bsr(const GPReg& dst, const Mem& src)
  {
    ASMJIT_ASSERT(!dst.isGPB());
    _emitInstruction(INST_BSR, &dst, &src);
  }

  //! @brief Byte swap (32-bit or 64-bit registers only) (i486).
  inline void bswap(const GPReg& dst)
  {
    ASMJIT_ASSERT(dst.getRegType() == REG_TYPE_GPD || dst.getRegType() == REG_TYPE_GPQ);
    _emitInstruction(INST_BSWAP, &dst);
  }

  //! @brief Bit test.
  inline void bt(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_BT, &dst, &src);
  }
  //! @brief Bit test.
  inline void bt(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_BT, &dst, &src);
  }
  //! @brief Bit test.
  inline void bt(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_BT, &dst, &src);
  }
  //! @brief Bit test.
  inline void bt(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_BT, &dst, &src);
  }

  //! @brief Bit test and complement.
  inline void btc(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_BTC, &dst, &src);
  }
  //! @brief Bit test and complement.
  inline void btc(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_BTC, &dst, &src);
  }
  //! @brief Bit test and complement.
  inline void btc(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_BTC, &dst, &src);
  }
  //! @brief Bit test and complement.
  inline void btc(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_BTC, &dst, &src);
  }

  //! @brief Bit test and reset.
  inline void btr(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_BTR, &dst, &src);
  }
  //! @brief Bit test and reset.
  inline void btr(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_BTR, &dst, &src);
  }
  //! @brief Bit test and reset.
  inline void btr(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_BTR, &dst, &src);
  }
  //! @brief Bit test and reset.
  inline void btr(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_BTR, &dst, &src);
  }

  //! @brief Bit test and set.
  inline void bts(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_BTS, &dst, &src);
  }
  //! @brief Bit test and set.
  inline void bts(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_BTS, &dst, &src);
  }
  //! @brief Bit test and set.
  inline void bts(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_BTS, &dst, &src);
  }
  //! @brief Bit test and set.
  inline void bts(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_BTS, &dst, &src);
  }

  //! @brief Call Procedure.
  inline void call(const GPReg& dst)
  {
    ASMJIT_ASSERT(dst.isRegType(REG_TYPE_GPN));
    _emitInstruction(INST_CALL, &dst);
  }
  //! @brief Call Procedure.
  inline void call(const Mem& dst)
  {
    _emitInstruction(INST_CALL, &dst);
  }
  //! @brief Call Procedure.
  inline void call(const Imm& dst)
  {
    _emitInstruction(INST_CALL, &dst);
  }
  //! @brief Call Procedure.
  //! @overload
  inline void call(void* dst)
  {
    Imm imm((sysint_t)dst);
    _emitInstruction(INST_CALL, &imm);
  }

  //! @brief Call Procedure.
  inline void call(const Label& label)
  {
    _emitInstruction(INST_CALL, &label);
  }

  //! @brief Convert Byte to Word (Sign Extend).
  //!
  //! AX <- Sign Extend AL
  inline void cbw()
  {
    _emitInstruction(INST_CBW);
  }

  //! @brief Convert Word to DWord (Sign Extend).
  //!
  //! EAX <- Sign Extend AX
  inline void cwde()
  {
    _emitInstruction(INST_CWDE);
  }

#if defined(ASMJIT_X64)
  //! @brief Convert DWord to QWord (Sign Extend).
  //!
  //! RAX <- Sign Extend EAX
  inline void cdqe()
  {
    _emitInstruction(INST_CDQE);
  }
#endif // ASMJIT_X64

  //! @brief Clear Carry flag
  //!
  //! This instruction clears the CF flag in the EFLAGS register.
  inline void clc()
  {
    _emitInstruction(INST_CLC);
  }

  //! @brief Clear Direction flag
  //!
  //! This instruction clears the DF flag in the EFLAGS register.
  inline void cld()
  {
    _emitInstruction(INST_CLD);
  }

  //! @brief Complement Carry Flag.
  //!
  //! This instruction complements the CF flag in the EFLAGS register.
  //! (CF = NOT CF)
  inline void cmc()
  {
    _emitInstruction(INST_CMC);
  }

  //! @brief Conditional Move.
  inline void cmov(CONDITION cc, const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(ConditionToInstruction::toCMovCC(cc), &dst, &src);
  }

  //! @brief Conditional Move.
  inline void cmov(CONDITION cc, const GPReg& dst, const Mem& src)
  {
    _emitInstruction(ConditionToInstruction::toCMovCC(cc), &dst, &src);
  }

  //! @brief Conditional Move.
  inline void cmova  (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVA  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmova  (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVA  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovae (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVAE , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovae (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVAE , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovb  (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVB  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovb  (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVB  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovbe (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVBE , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovbe (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVBE , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovc  (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVC  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovc  (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVC  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmove  (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVE  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmove  (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVE  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovg  (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVG  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovg  (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVG  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovge (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVGE , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovge (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVGE , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovl  (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVL  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovl  (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVL  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovle (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVLE , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovle (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVLE , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovna (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNA , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovna (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNA , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnae(const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNAE, &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnae(const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNAE, &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnb (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNB , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnb (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNB , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnbe(const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNBE, &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnbe(const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNBE, &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnc (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNC , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnc (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNC , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovne (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNE , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovne (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNE , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovng (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNG , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovng (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNG , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnge(const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNGE, &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnge(const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNGE, &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnl (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNL , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnl (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNL , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnle(const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNLE, &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnle(const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNLE, &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovno (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNO , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovno (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNO , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnp (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNP , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnp (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNP , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovns (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNS , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovns (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNS , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnz (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVNZ , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovnz (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVNZ , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovo  (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVO  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovo  (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVO  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovp  (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVP  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovp  (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVP  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovpe (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVPE , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovpe (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVPE , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovpo (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVPO , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovpo (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVPO , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovs  (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVS  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovs  (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVS  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovz  (const GPReg& dst, const GPReg& src) { _emitInstruction(INST_CMOVZ  , &dst, &src); }
  //! @brief Conditional Move.
  inline void cmovz  (const GPReg& dst, const Mem& src)   { _emitInstruction(INST_CMOVZ  , &dst, &src); }

  //! @brief Compare Two Operands.
  inline void cmp(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_CMP, &dst, &src);
  }
  //! @brief Compare Two Operands.
  inline void cmp(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CMP, &dst, &src);
  }
  //! @brief Compare Two Operands.
  inline void cmp(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_CMP, &dst, &src);
  }
  //! @brief Compare Two Operands.
  inline void cmp(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_CMP, &dst, &src);
  }
  //! @brief Compare Two Operands.
  inline void cmp(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_CMP, &dst, &src);
  }

  //! @brief Compare and Exchange (i486).
  inline void cmpxchg(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_CMPXCHG, &dst, &src);
  }
  //! @brief Compare and Exchange (i486).
  inline void cmpxchg(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_CMPXCHG, &dst, &src);
  }

  //! @brief Compares the 64-bit value in EDX:EAX with the memory operand (Pentium).
  //!
  //! If the values are equal, then this instruction stores the 64-bit value
  //! in ECX:EBX into the memory operand and sets the zero flag. Otherwise,
  //! this instruction copies the 64-bit memory operand into the EDX:EAX
  //! registers and clears the zero flag.
  inline void cmpxchg8b(const Mem& dst)
  {
    _emitInstruction(INST_CMPXCHG8B, &dst);
  }

#if defined(ASMJIT_X64)
  //! @brief Compares the 128-bit value in RDX:RAX with the memory operand (X64).
  //!
  //! If the values are equal, then this instruction stores the 128-bit value
  //! in RCX:RBX into the memory operand and sets the zero flag. Otherwise,
  //! this instruction copies the 128-bit memory operand into the RDX:RAX
  //! registers and clears the zero flag.
  inline void cmpxchg16b(const Mem& dst)
  {
    _emitInstruction(INST_CMPXCHG16B, &dst);
  }
#endif // ASMJIT_X64

  //! @brief CPU Identification (i486).
  inline void cpuid()
  {
    _emitInstruction(INST_CPUID);
  }

#if defined(ASMJIT_X86)
  //! @brief Decimal adjust AL after addition
  //!
  //! This instruction adjusts the sum of two packed BCD values to create
  //! a packed BCD result.
  //!
  //! @note This instruction is only available in 32-bit mode.
  inline void daa()
  {
    _emitInstruction(INST_DAA);
  }
#endif // ASMJIT_X86

#if defined(ASMJIT_X86)
  //! @brief Decimal adjust AL after subtraction
  //!
  //! This instruction adjusts the result of the subtraction of two packed
  //! BCD values to create a packed BCD result.
  //!
  //! @note This instruction is only available in 32-bit mode.
  inline void das()
  {
    _emitInstruction(INST_DAS);
  }
#endif // ASMJIT_X86

  //! @brief Decrement by 1.
  //! @note This instruction can be slower than sub(dst, 1)
  inline void dec(const GPReg& dst)
  {
    _emitInstruction(INST_DEC, &dst);
  }
  //! @brief Decrement by 1.
  //! @note This instruction can be slower than sub(dst, 1)
  inline void dec(const Mem& dst)
  {
    _emitInstruction(INST_DEC, &dst);
  }

  //! @brief Unsigned divide.
  //!
  //! This instruction divides (unsigned) the value in the AL, AX, or EAX
  //! register by the source operand and stores the result in the AX,
  //! DX:AX, or EDX:EAX registers.
  inline void div(const GPReg& src)
  {
    _emitInstruction(INST_DIV, &src);
  }
  //! @brief Unsigned divide.
  //! @overload
  inline void div(const Mem& src)
  {
    _emitInstruction(INST_DIV, &src);
  }

  //! @brief Make Stack Frame for Procedure Parameters.
  inline void enter(const Imm& imm16, const Imm& imm8)
  {
    _emitInstruction(INST_ENTER, &imm16, &imm8);
  }

  //! @brief Signed divide.
  //!
  //! This instruction divides (signed) the value in the AL, AX, or EAX
  //! register by the source operand and stores the result in the AX,
  //! DX:AX, or EDX:EAX registers.
  inline void idiv(const GPReg& src)
  {
    _emitInstruction(INST_IDIV, &src);
  }
  //! @brief Signed divide.
  //! @overload
  inline void idiv(const Mem& src)
  {
    _emitInstruction(INST_IDIV, &src);
  }

  //! @brief Signed multiply.
  //!
  //! Source operand (in a general-purpose register or memory location)
  //! is multiplied by the value in the AL, AX, or EAX register (depending
  //! on the operand size) and the product is stored in the AX, DX:AX, or
  //! EDX:EAX registers, respectively.
  inline void imul(const GPReg& src)
  {
    _emitInstruction(INST_IMUL, &src);
  }
  //! @overload
  inline void imul(const Mem& src)
  {
    _emitInstruction(INST_IMUL, &src);
  }

  //! @brief Signed multiply.
  //!
  //! Destination operand (the first operand) is multiplied by the source
  //! operand (second operand). The destination operand is a general-purpose
  //! register and the source operand is an immediate value, a general-purpose
  //! register, or a memory location. The product is then stored in the
  //! destination operand location.
  inline void imul(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_IMUL, &dst, &src);
  }
  //! @brief Signed multiply.
  //! @overload
  inline void imul(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_IMUL, &dst, &src);
  }
  //! @brief Signed multiply.
  //! @overload
  inline void imul(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_IMUL, &dst, &src);
  }

  //! @brief Signed multiply.
  //!
  //! source operand (which can be a general-purpose register or a memory
  //! location) is multiplied by the second source operand (an immediate
  //! value). The product is then stored in the destination operand
  //! (a general-purpose register).
  inline void imul(const GPReg& dst, const GPReg& src, const Imm& imm)
  {
    _emitInstruction(INST_IMUL, &dst, &src, &imm);
  }
  //! @overload
  inline void imul(const GPReg& dst, const Mem& src, const Imm& imm)
  {
    _emitInstruction(INST_IMUL, &dst, &src, &imm);
  }

  //! @brief Increment by 1.
  //! @note This instruction can be slower than add(dst, 1)
  inline void inc(const GPReg& dst)
  {
    _emitInstruction(INST_INC, &dst);
  }
  //! @brief Increment by 1.
  //! @note This instruction can be slower than add(dst, 1)
  inline void inc(const Mem& dst)
  {
    _emitInstruction(INST_INC, &dst);
  }

  //! @brief Interrupt 3 - trap to debugger.
  inline void int3()
  {
    _emitInstruction(INST_INT3);
  }

  //! @brief Jump to label @a label if condition @a cc is met.
  //!
  //! This instruction checks the state of one or more of the status flags in
  //! the EFLAGS register (CF, OF, PF, SF, and ZF) and, if the flags are in the
  //! specified state (condition), performs a jump to the target instruction
  //! specified by the destination operand. A condition code (cc) is associated
  //! with each instruction to indicate the condition being tested for. If the
  //! condition is not satisfied, the jump is not performed and execution
  //! continues with the instruction following the Jcc instruction.
  inline void j(CONDITION cc, const Label& label, uint32_t hint = HINT_NONE)
  {
    _emitJcc(ConditionToInstruction::toJCC(cc), &label, hint);
  }

  //! @brief Jump to label @a label if condition is met.
  inline void ja  (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JA  , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jae (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JAE , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jb  (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JB  , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jbe (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JBE , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jc  (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JC  , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void je  (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JE  , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jg  (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JG  , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jge (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JGE , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jl  (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JL  , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jle (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JLE , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jna (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNA , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jnae(const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNAE, &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jnb (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNB , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jnbe(const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNBE, &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jnc (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNC , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jne (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNE , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jng (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNG , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jnge(const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNGE, &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jnl (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNL , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jnle(const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNLE, &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jno (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNO , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jnp (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNP , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jns (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNS , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jnz (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JNZ , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jo  (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JO  , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jp  (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JP  , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jpe (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JPE , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jpo (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JPO , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void js  (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JS  , &label, hint); }
  //! @brief Jump to label @a label if condition is met.
  inline void jz  (const Label& label, uint32_t hint = HINT_NONE) { _emitJcc(INST_JZ  , &label, hint); }

  //! @brief Short jump to label @a label if condition @a cc is met.
  //! @sa j()
  inline void short_j(CONDITION cc, const Label& label, uint32_t hint = HINT_NONE)
  {
    _emitOptions |= EMIT_OPTION_SHORT_JUMP;
    j(cc, label, hint);
  }

  //! @brief Short jump to label @a label if condition is met.
  inline void short_ja  (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JA  , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jae (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JAE , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jb  (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JB  , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jbe (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JBE , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jc  (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JC  , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_je  (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JE  , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jg  (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JG  , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jge (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JGE , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jl  (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JL  , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jle (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JLE , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jna (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNA , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jnae(const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNAE, &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jnb (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNB , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jnbe(const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNBE, &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jnc (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNC , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jne (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNE , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jng (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNG , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jnge(const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNGE, &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jnl (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNL , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jnle(const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNLE, &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jno (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNO , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jnp (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNP , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jns (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNS , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jnz (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JNZ , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jo  (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JO  , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jp  (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JP  , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jpe (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JPE , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jpo (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JPO , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_js  (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JS  , &label, hint); }
  //! @brief Short jump to label @a label if condition is met.
  inline void short_jz  (const Label& label, uint32_t hint = HINT_NONE) { _emitShortJcc(INST_JZ  , &label, hint); }

  //! @brief Jump.
  //! @overload
  inline void jmp(const GPReg& dst)
  {
    _emitInstruction(INST_JMP, &dst);
  }
  //! @brief Jump.
  //! @overload
  inline void jmp(const Mem& dst)
  {
    _emitInstruction(INST_JMP, &dst);
  }
  //! @brief Jump.
  //! @overload
  inline void jmp(const Imm& dst)
  {
    _emitInstruction(INST_JMP, &dst);
  }

  //! @brief Jump.
  //! @overload
  inline void jmp(void* dst)
  {
    Imm imm((sysint_t)dst);
    _emitInstruction(INST_JMP, &imm);
  }

  //! @brief Jump.
  //!
  //! This instruction transfers program control to a different point
  //! in the instruction stream without recording return information.
  //! The destination (target) operand specifies the label of the
  //! instruction being jumped to.
  inline void jmp(const Label& label)
  {
    _emitInstruction(INST_JMP, &label);
  }

  //! @brief Short jump.
  //! @sa jmp()
  inline void short_jmp(const Label& label)
  {
    _emitOptions |= EMIT_OPTION_SHORT_JUMP;
    _emitInstruction(INST_JMP, &label);
  }

  //! @brief Load Effective Address
  //!
  //! This instruction computes the effective address of the second
  //! operand (the source operand) and stores it in the first operand
  //! (destination operand). The source operand is a memory address
  //! (offset part) specified with one of the processors addressing modes.
  //! The destination operand is a general-purpose register.
  inline void lea(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_LEA, &dst, &src);
  }

  //! @brief High Level Procedure Exit.
  inline void leave()
  {
    _emitInstruction(INST_LEAVE);
  }

  //! @brief Move.
  //!
  //! This instruction copies the second operand (source operand) to the first
  //! operand (destination operand). The source operand can be an immediate
  //! value, general-purpose register, segment register, or memory location.
  //! The destination register can be a general-purpose register, segment
  //! register, or memory location. Both operands must be the same size, which
  //! can be a byte, a word, or a DWORD.
  //!
  //! @note To move MMX or SSE registers to/from GP registers or memory, use
  //! corresponding functions: @c movd(), @c movq(), etc. Passing MMX or SSE
  //! registers to @c mov() is illegal.
  inline void mov(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_MOV, &dst, &src);
  }
  //! @brief Move.
  //! @overload
  inline void mov(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOV, &dst, &src);
  }
  //! @brief Move.
  //! @overload
  inline void mov(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_MOV, &dst, &src);
  }
  //! @brief Move.
  //! @overload
  inline void mov(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_MOV, &dst, &src);
  }
  //! @brief Move.
  //! @overload
  inline void mov(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_MOV, &dst, &src);
  }

  //! @brief Move byte, word, dword or qword from absolute address @a src to
  //! AL, AX, EAX or RAX register.
  inline void mov_ptr(const GPReg& dst, void* src)
  {
    ASMJIT_ASSERT(dst.getRegIndex() == 0);
    Imm imm((sysint_t)src);
    _emitInstruction(INST_MOV_PTR, &dst, &imm);
  }

  //! @brief Move byte, word, dword or qword from AL, AX, EAX or RAX register
  //! to absolute address @a dst.
  inline void mov_ptr(void* dst, const GPReg& src)
  {
    ASMJIT_ASSERT(src.getRegIndex() == 0);
    Imm imm((sysint_t)dst);
    _emitInstruction(INST_MOV_PTR, &imm, &src);
  }

  //! @brief Move with Sign-Extension.
  //!
  //! This instruction copies the contents of the source operand (register
  //! or memory location) to the destination operand (register) and sign
  //! extends the value to 16, 32 or 64-bits.
  //!
  //! @sa movsxd().
  void movsx(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_MOVSX, &dst, &src);
  }
  //! @brief Move with Sign-Extension.
  //! @overload
  void movsx(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVSX, &dst, &src);
  }

#if defined(ASMJIT_X64)
  //! @brief Move DWord to QWord with sign-extension.
  inline void movsxd(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_MOVSXD, &dst, &src);
  }
  //! @brief Move DWord to QWord with sign-extension.
  //! @overload
  inline void movsxd(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVSXD, &dst, &src);
  }
#endif // ASMJIT_X64

  //! @brief Move with Zero-Extend.
  //!
  //! This instruction copies the contents of the source operand (register
  //! or memory location) to the destination operand (register) and zero
  //! extends the value to 16 or 32-bits. The size of the converted value
  //! depends on the operand-size attribute.
  inline void movzx(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_MOVZX, &dst, &src);
  }
  //! @brief Move with Zero-Extend.
  //! @brief Overload
  inline void movzx(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVZX, &dst, &src);
  }

  //! @brief Unsigned multiply.
  //!
  //! Source operand (in a general-purpose register or memory location)
  //! is multiplied by the value in the AL, AX, or EAX register (depending
  //! on the operand size) and the product is stored in the AX, DX:AX, or
  //! EDX:EAX registers, respectively.
  inline void mul(const GPReg& src)
  {
    _emitInstruction(INST_MUL, &src);
  }
  //! @brief Unsigned multiply.
  //! @overload
  inline void mul(const Mem& src)
  {
    _emitInstruction(INST_MUL, &src);
  }

  //! @brief Two's Complement Negation.
  inline void neg(const GPReg& dst)
  {
    _emitInstruction(INST_NEG, &dst);
  }
  //! @brief Two's Complement Negation.
  inline void neg(const Mem& dst)
  {
    _emitInstruction(INST_NEG, &dst);
  }

  //! @brief No Operation.
  //!
  //! This instruction performs no operation. This instruction is a one-byte
  //! instruction that takes up space in the instruction stream but does not
  //! affect the machine context, except the EIP register. The NOP instruction
  //! is an alias mnemonic for the XCHG (E)AX, (E)AX instruction.
  inline void nop()
  {
    _emitInstruction(INST_NOP);
  }

  //! @brief One's Complement Negation.
  inline void not_(const GPReg& dst)
  {
    _emitInstruction(INST_NOT, &dst);
  }
  //! @brief One's Complement Negation.
  inline void not_(const Mem& dst)
  {
    _emitInstruction(INST_NOT, &dst);
  }

  //! @brief Logical Inclusive OR.
  inline void or_(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_OR, &dst, &src);
  }
  //! @brief Logical Inclusive OR.
  inline void or_(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_OR, &dst, &src);
  }
  //! @brief Logical Inclusive OR.
  inline void or_(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_OR, &dst, &src);
  }
  //! @brief Logical Inclusive OR.
  inline void or_(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_OR, &dst, &src);
  }
  //! @brief Logical Inclusive OR.
  inline void or_(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_OR, &dst, &src);
  }

  //! @brief Pop a Value from the Stack.
  //!
  //! This instruction loads the value from the top of the stack to the location
  //! specified with the destination operand and then increments the stack pointer.
  //! The destination operand can be a general purpose register, memory location,
  //! or segment register.
  inline void pop(const GPReg& dst)
  {
    ASMJIT_ASSERT(dst.isRegType(REG_TYPE_GPW) || dst.isRegType(REG_TYPE_GPN));
    _emitInstruction(INST_POP, &dst);
  }

  inline void pop(const Mem& dst)
  {
    ASMJIT_ASSERT(dst.getSize() == 2 || dst.getSize() == sizeof(sysint_t));
    _emitInstruction(INST_POP, &dst);
  }

#if defined(ASMJIT_X86)
  //! @brief Pop All General-Purpose Registers.
  //!
  //! Pop EDI, ESI, EBP, EBX, EDX, ECX, and EAX.
  inline void popad()
  {
    _emitInstruction(INST_POPAD);
  }
#endif // ASMJIT_X86

  //! @brief Pop Stack into EFLAGS Register (32-bit or 64-bit).
  inline void popf()
  {
#if defined(ASMJIT_X86)
    popfd();
#else
    popfq();
#endif
  }

#if defined(ASMJIT_X86)
  //! @brief Pop Stack into EFLAGS Register (32-bit).
  inline void popfd() { _emitInstruction(INST_POPFD); }
#else
  //! @brief Pop Stack into EFLAGS Register (64-bit).
  inline void popfq() { _emitInstruction(INST_POPFQ); }
#endif

  //! @brief Push WORD/DWORD/QWORD Onto the Stack.
  //!
  //! @note 32-bit architecture pushed DWORD while 64-bit
  //! pushes QWORD. 64-bit mode not provides instruction to
  //! push 32-bit register/memory.
  inline void push(const GPReg& src)
  {
    ASMJIT_ASSERT(src.isRegType(REG_TYPE_GPW) || src.isRegType(REG_TYPE_GPN));
    _emitInstruction(INST_PUSH, &src);
  }
  //! @brief Push WORD/DWORD/QWORD Onto the Stack.
  inline void push(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 2 || src.getSize() == sizeof(sysint_t));
    _emitInstruction(INST_PUSH, &src);
  }
  //! @brief Push WORD/DWORD/QWORD Onto the Stack.
  inline void push(const Imm& src)
  {
    _emitInstruction(INST_PUSH, &src);
  }

#if defined(ASMJIT_X86)
  //! @brief Push All General-Purpose Registers.
  //!
  //! Push EAX, ECX, EDX, EBX, original ESP, EBP, ESI, and EDI.
  inline void pushad()
  {
    _emitInstruction(INST_PUSHAD);
  }
#endif // ASMJIT_X86

  //! @brief Push EFLAGS Register (32-bit or 64-bit) onto the Stack.
  inline void pushf()
  {
#if defined(ASMJIT_X86)
    pushfd();
#else
    pushfq();
#endif
  }

#if defined(ASMJIT_X86)
  //! @brief Push EFLAGS Register (32-bit) onto the Stack.
  inline void pushfd() { _emitInstruction(INST_PUSHFD); }
#else
  //! @brief Push EFLAGS Register (64-bit) onto the Stack.
  inline void pushfq() { _emitInstruction(INST_PUSHFQ); }
#endif // ASMJIT_X86

  //! @brief Rotate Bits Left.
  //! @note @a src register can be only @c cl.
  inline void rcl(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_RCL, &dst, &src);
  }
  //! @brief Rotate Bits Left.
  inline void rcl(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_RCL, &dst, &src);
  }
  //! @brief Rotate Bits Left.
  //! @note @a src register can be only @c cl.
  inline void rcl(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_RCL, &dst, &src);
  }
  //! @brief Rotate Bits Left.
  inline void rcl(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_RCL, &dst, &src);
  }

  //! @brief Rotate Bits Right.
  //! @note @a src register can be only @c cl.
  inline void rcr(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_RCR, &dst, &src);
  }
  //! @brief Rotate Bits Right.
  inline void rcr(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_RCR, &dst, &src);
  }
  //! @brief Rotate Bits Right.
  //! @note @a src register can be only @c cl.
  inline void rcr(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_RCR, &dst, &src);
  }
  //! @brief Rotate Bits Right.
  inline void rcr(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_RCR, &dst, &src);
  }

  //! @brief Read Time-Stamp Counter (Pentium).
  inline void rdtsc()
  {
    _emitInstruction(INST_RDTSC);
  }

  //! @brief Read Time-Stamp Counter and Processor ID (New).
  inline void rdtscp()
  {
    _emitInstruction(INST_RDTSCP);
  }

  //! @brief Load ECX/RCX BYTEs from DS:[ESI/RSI] to AL.
  inline void rep_lodsb()
  {
    _emitInstruction(INST_REP_LODSB);
  }

  //! @brief Load ECX/RCX DWORDs from DS:[ESI/RSI] to EAX.
  inline void rep_lodsd()
  {
    _emitInstruction(INST_REP_LODSD);
  }

#if defined(ASMJIT_X64)
  //! @brief Load ECX/RCX QWORDs from DS:[ESI/RSI] to RAX.
  inline void rep_lodsq()
  {
    _emitInstruction(INST_REP_LODSQ);
  }
#endif // ASMJIT_X64

  //! @brief Load ECX/RCX WORDs from DS:[ESI/RSI] to AX.
  inline void rep_lodsw()
  {
    _emitInstruction(INST_REP_LODSW);
  }

  //! @brief Move ECX/RCX BYTEs from DS:[ESI/RSI] to ES:[EDI/RDI].
  inline void rep_movsb()
  {
    _emitInstruction(INST_REP_MOVSB);
  }

  //! @brief Move ECX/RCX DWORDs from DS:[ESI/RSI] to ES:[EDI/RDI].
  inline void rep_movsd()
  {
    _emitInstruction(INST_REP_MOVSD);
  }

#if defined(ASMJIT_X64)
  //! @brief Move ECX/RCX QWORDs from DS:[ESI/RSI] to ES:[EDI/RDI].
  inline void rep_movsq()
  {
    _emitInstruction(INST_REP_MOVSQ);
  }
#endif // ASMJIT_X64

  //! @brief Move ECX/RCX WORDs from DS:[ESI/RSI] to ES:[EDI/RDI].
  inline void rep_movsw()
  {
    _emitInstruction(INST_REP_MOVSW);
  }

  //! @brief Fill ECX/RCX BYTEs at ES:[EDI/RDI] with AL.
  inline void rep_stosb()
  {
    _emitInstruction(INST_REP_STOSB);
  }

  //! @brief Fill ECX/RCX DWORDs at ES:[EDI/RDI] with EAX.
  inline void rep_stosd()
  {
    _emitInstruction(INST_REP_STOSD);
  }

#if defined(ASMJIT_X64)
  //! @brief Fill ECX/RCX QWORDs at ES:[EDI/RDI] with RAX.
  inline void rep_stosq()
  {
    _emitInstruction(INST_REP_STOSQ);
  }
#endif // ASMJIT_X64

  //! @brief Fill ECX/RCX WORDs at ES:[EDI/RDI] with AX.
  inline void rep_stosw()
  {
    _emitInstruction(INST_REP_STOSW);
  }

  //! @brief Repeated find nonmatching BYTEs in ES:[EDI/RDI] and DS:[ESI/RDI].
  inline void repe_cmpsb()
  {
    _emitInstruction(INST_REPE_CMPSB);
  }
  
  //! @brief Repeated find nonmatching DWORDs in ES:[EDI/RDI] and DS:[ESI/RDI].
  inline void repe_cmpsd()
  {
    _emitInstruction(INST_REPE_CMPSD);
  }

#if defined(ASMJIT_X64)
  //! @brief Repeated find nonmatching QWORDs in ES:[EDI/RDI] and DS:[ESI/RDI].
  inline void repe_cmpsq()
  {
    _emitInstruction(INST_REPE_CMPSQ);
  }
#endif // ASMJIT_X64
  
  //! @brief Repeated find nonmatching WORDs in ES:[EDI/RDI] and DS:[ESI/RDI].
  inline void repe_cmpsw()
  {
    _emitInstruction(INST_REPE_CMPSW);
  }

  //! @brief Find non-AL BYTE starting at ES:[EDI/RDI].
  inline void repe_scasb()
  {
    _emitInstruction(INST_REPE_SCASB);
  }
  
  //! @brief Find non-EAX DWORD starting at ES:[EDI/RDI].
  inline void repe_scasd()
  {
    _emitInstruction(INST_REPE_SCASD);
  }

#if defined(ASMJIT_X64)
  //! @brief Find non-RAX QWORD starting at ES:[EDI/RDI].
  inline void repe_scasq()
  {
    _emitInstruction(INST_REPE_SCASQ);
  }
#endif // ASMJIT_X64

  //! @brief Find non-AX WORD starting at ES:[EDI/RDI].
  inline void repe_scasw()
  {
    _emitInstruction(INST_REPE_SCASW);
  }

  //! @brief Repeated find nonmatching BYTEs in ES:[EDI/RDI] and DS:[ESI/RDI].
  inline void repne_cmpsb()
  {
    _emitInstruction(INST_REPNE_CMPSB);
  }

  //! @brief Repeated find nonmatching DWORDs in ES:[EDI/RDI] and DS:[ESI/RDI].
  inline void repne_cmpsd()
  {
    _emitInstruction(INST_REPNE_CMPSD);
  }

#if defined(ASMJIT_X64)
  //! @brief Repeated find nonmatching QWORDs in ES:[EDI/RDI] and DS:[ESI/RDI].
  inline void repne_cmpsq()
  {
    _emitInstruction(INST_REPNE_CMPSQ);
  }
#endif // ASMJIT_X64

  //! @brief Repeated find nonmatching WORDs in ES:[EDI/RDI] and DS:[ESI/RDI].
  inline void repne_cmpsw()
  {
    _emitInstruction(INST_REPNE_CMPSW);
  }

  //! @brief Find AL, starting at ES:[EDI/RDI].
  inline void repne_scasb()
  {
    _emitInstruction(INST_REPNE_SCASB);
  }

  //! @brief Find EAX, starting at ES:[EDI/RDI].
  inline void repne_scasd()
  {
    _emitInstruction(INST_REPNE_SCASD);
  }

#if defined(ASMJIT_X64)
  //! @brief Find RAX, starting at ES:[EDI/RDI].
  inline void repne_scasq()
  {
    _emitInstruction(INST_REPNE_SCASQ);
  }
#endif // ASMJIT_X64

  //! @brief Find AX, starting at ES:[EDI/RDI].
  inline void repne_scasw()
  {
    _emitInstruction(INST_REPNE_SCASW);
  }

  //! @brief Return from Procedure.
  inline void ret()
  {
    _emitInstruction(INST_RET);
  }

  //! @brief Return from Procedure.
  inline void ret(const Imm& imm16)
  {
    _emitInstruction(INST_RET, &imm16);
  }

  //! @brief Rotate Bits Left.
  //! @note @a src register can be only @c cl.
  inline void rol(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_ROL, &dst, &src);
  }
  //! @brief Rotate Bits Left.
  inline void rol(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_ROL, &dst, &src);
  }
  //! @brief Rotate Bits Left.
  //! @note @a src register can be only @c cl.
  inline void rol(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_ROL, &dst, &src);
  }
  //! @brief Rotate Bits Left.
  inline void rol(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_ROL, &dst, &src);
  }

  //! @brief Rotate Bits Right.
  //! @note @a src register can be only @c cl.
  inline void ror(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_ROR, &dst, &src);
  }
  //! @brief Rotate Bits Right.
  inline void ror(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_ROR, &dst, &src);
  }
  //! @brief Rotate Bits Right.
  //! @note @a src register can be only @c cl.
  inline void ror(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_ROR, &dst, &src);
  }
  //! @brief Rotate Bits Right.
  inline void ror(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_ROR, &dst, &src);
  }

#if defined(ASMJIT_X86)
  //! @brief Store AH into Flags.
  inline void sahf()
  {
    _emitInstruction(INST_SAHF);
  }
#endif // ASMJIT_X86

  //! @brief Integer subtraction with borrow.
  inline void sbb(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_SBB, &dst, &src);
  }
  //! @brief Integer subtraction with borrow.
  inline void sbb(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_SBB, &dst, &src);
  }
  //! @brief Integer subtraction with borrow.
  inline void sbb(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_SBB, &dst, &src);
  }
  //! @brief Integer subtraction with borrow.
  inline void sbb(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_SBB, &dst, &src);
  }
  //! @brief Integer subtraction with borrow.
  inline void sbb(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_SBB, &dst, &src);
  }

  //! @brief Shift Bits Left.
  //! @note @a src register can be only @c cl.
  inline void sal(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_SAL, &dst, &src);
  }
  //! @brief Shift Bits Left.
  inline void sal(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_SAL, &dst, &src);
  }
  //! @brief Shift Bits Left.
  //! @note @a src register can be only @c cl.
  inline void sal(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_SAL, &dst, &src);
  }
  //! @brief Shift Bits Left.
  inline void sal(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_SAL, &dst, &src);
  }

  //! @brief Shift Bits Right.
  //! @note @a src register can be only @c cl.
  inline void sar(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_SAR, &dst, &src);
  }
  //! @brief Shift Bits Right.
  inline void sar(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_SAR, &dst, &src);
  }
  //! @brief Shift Bits Right.
  //! @note @a src register can be only @c cl.
  inline void sar(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_SAR, &dst, &src);
  }
  //! @brief Shift Bits Right.
  inline void sar(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_SAR, &dst, &src);
  }

  //! @brief Set Byte on Condition.
  inline void set(CONDITION cc, const GPReg& dst)
  {
    ASMJIT_ASSERT(dst.getSize() == 1);
    _emitInstruction(ConditionToInstruction::toSetCC(cc), &dst);
  }

  //! @brief Set Byte on Condition.
  inline void set(CONDITION cc, const Mem& dst)
  {
    ASMJIT_ASSERT(dst.getSize() <= 1);
    _emitInstruction(ConditionToInstruction::toSetCC(cc), &dst);
  }

  //! @brief Set Byte on Condition.
  inline void seta  (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETA  , &dst); }
  //! @brief Set Byte on Condition.
  inline void seta  (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETA  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setae (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETAE , &dst); }
  //! @brief Set Byte on Condition.
  inline void setae (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETAE , &dst); }
  //! @brief Set Byte on Condition.
  inline void setb  (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETB  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setb  (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETB  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setbe (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETBE , &dst); }
  //! @brief Set Byte on Condition.
  inline void setbe (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETBE , &dst); }
  //! @brief Set Byte on Condition.
  inline void setc  (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETC  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setc  (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETC  , &dst); }
  //! @brief Set Byte on Condition.
  inline void sete  (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETE  , &dst); }
  //! @brief Set Byte on Condition.
  inline void sete  (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETE  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setg  (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETG  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setg  (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETG  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setge (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETGE , &dst); }
  //! @brief Set Byte on Condition.
  inline void setge (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETGE , &dst); }
  //! @brief Set Byte on Condition.
  inline void setl  (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETL  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setl  (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETL  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setle (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETLE , &dst); }
  //! @brief Set Byte on Condition.
  inline void setle (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETLE , &dst); }
  //! @brief Set Byte on Condition.
  inline void setna (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNA , &dst); }
  //! @brief Set Byte on Condition.
  inline void setna (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNA , &dst); }
  //! @brief Set Byte on Condition.
  inline void setnae(const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNAE, &dst); }
  //! @brief Set Byte on Condition.
  inline void setnae(const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNAE, &dst); }
  //! @brief Set Byte on Condition.
  inline void setnb (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNB , &dst); }
  //! @brief Set Byte on Condition.
  inline void setnb (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNB , &dst); }
  //! @brief Set Byte on Condition.
  inline void setnbe(const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNBE, &dst); }
  //! @brief Set Byte on Condition.
  inline void setnbe(const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNBE, &dst); }
  //! @brief Set Byte on Condition.
  inline void setnc (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNC , &dst); }
  //! @brief Set Byte on Condition.
  inline void setnc (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNC , &dst); }
  //! @brief Set Byte on Condition.
  inline void setne (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNE , &dst); }
  //! @brief Set Byte on Condition.
  inline void setne (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNE , &dst); }
  //! @brief Set Byte on Condition.
  inline void setng (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNG , &dst); }
  //! @brief Set Byte on Condition.
  inline void setng (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNG , &dst); }
  //! @brief Set Byte on Condition.
  inline void setnge(const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNGE, &dst); }
  //! @brief Set Byte on Condition.
  inline void setnge(const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNGE, &dst); }
  //! @brief Set Byte on Condition.
  inline void setnl (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNL , &dst); }
  //! @brief Set Byte on Condition.
  inline void setnl (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNL , &dst); }
  //! @brief Set Byte on Condition.
  inline void setnle(const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNLE, &dst); }
  //! @brief Set Byte on Condition.
  inline void setnle(const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNLE, &dst); }
  //! @brief Set Byte on Condition.
  inline void setno (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNO , &dst); }
  //! @brief Set Byte on Condition.
  inline void setno (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNO , &dst); }
  //! @brief Set Byte on Condition.
  inline void setnp (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNP , &dst); }
  //! @brief Set Byte on Condition.
  inline void setnp (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNP , &dst); }
  //! @brief Set Byte on Condition.
  inline void setns (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNS , &dst); }
  //! @brief Set Byte on Condition.
  inline void setns (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNS , &dst); }
  //! @brief Set Byte on Condition.
  inline void setnz (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETNZ , &dst); }
  //! @brief Set Byte on Condition.
  inline void setnz (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETNZ , &dst); }
  //! @brief Set Byte on Condition.
  inline void seto  (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETO  , &dst); }
  //! @brief Set Byte on Condition.
  inline void seto  (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETO  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setp  (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETP  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setp  (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETP  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setpe (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETPE , &dst); }
  //! @brief Set Byte on Condition.
  inline void setpe (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETPE , &dst); }
  //! @brief Set Byte on Condition.
  inline void setpo (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETPO , &dst); }
  //! @brief Set Byte on Condition.
  inline void setpo (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETPO , &dst); }
  //! @brief Set Byte on Condition.
  inline void sets  (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETS  , &dst); }
  //! @brief Set Byte on Condition.
  inline void sets  (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETS  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setz  (const GPReg& dst) { ASMJIT_ASSERT(dst.getSize() == 1); _emitInstruction(INST_SETZ  , &dst); }
  //! @brief Set Byte on Condition.
  inline void setz  (const Mem& dst)   { ASMJIT_ASSERT(dst.getSize() <= 1); _emitInstruction(INST_SETZ  , &dst); }

  //! @brief Shift Bits Left.
  //! @note @a src register can be only @c cl.
  inline void shl(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_SHL, &dst, &src);
  }
  //! @brief Shift Bits Left.
  inline void shl(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_SHL, &dst, &src);
  }
  //! @brief Shift Bits Left.
  //! @note @a src register can be only @c cl.
  inline void shl(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_SHL, &dst, &src);
  }
  //! @brief Shift Bits Left.
  inline void shl(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_SHL, &dst, &src);
  }

  //! @brief Shift Bits Right.
  //! @note @a src register can be only @c cl.
  inline void shr(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_SHR, &dst, &src);
  }
  //! @brief Shift Bits Right.
  inline void shr(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_SHR, &dst, &src);
  }
  //! @brief Shift Bits Right.
  //! @note @a src register can be only @c cl.
  inline void shr(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_SHR, &dst, &src);
  }
  //! @brief Shift Bits Right.
  inline void shr(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_SHR, &dst, &src);
  }

  //! @brief Double Precision Shift Left.
  //! @note src2 register can be only @c cl register.
  inline void shld(const GPReg& dst, const GPReg& src1, const GPReg& src2)
  {
    _emitInstruction(INST_SHLD, &dst, &src1, &src2);
  }
  //! @brief Double Precision Shift Left.
  inline void shld(const GPReg& dst, const GPReg& src1, const Imm& src2)
  {
    _emitInstruction(INST_SHLD, &dst, &src1, &src2);
  }
  //! @brief Double Precision Shift Left.
  //! @note src2 register can be only @c cl register.
  inline void shld(const Mem& dst, const GPReg& src1, const GPReg& src2)
  {
    _emitInstruction(INST_SHLD, &dst, &src1, &src2);
  }
  //! @brief Double Precision Shift Left.
  inline void shld(const Mem& dst, const GPReg& src1, const Imm& src2)
  {
    _emitInstruction(INST_SHLD, &dst, &src1, &src2);
  }

  //! @brief Double Precision Shift Right.
  //! @note src2 register can be only @c cl register.
  inline void shrd(const GPReg& dst, const GPReg& src1, const GPReg& src2)
  {
    _emitInstruction(INST_SHRD, &dst, &src1, &src2);
  }
  //! @brief Double Precision Shift Right.
  inline void shrd(const GPReg& dst, const GPReg& src1, const Imm& src2)
  {
    _emitInstruction(INST_SHRD, &dst, &src1, &src2);
  }
  //! @brief Double Precision Shift Right.
  //! @note src2 register can be only @c cl register.
  inline void shrd(const Mem& dst, const GPReg& src1, const GPReg& src2)
  {
    _emitInstruction(INST_SHRD, &dst, &src1, &src2);
  }
  //! @brief Double Precision Shift Right.
  inline void shrd(const Mem& dst, const GPReg& src1, const Imm& src2)
  {
    _emitInstruction(INST_SHRD, &dst, &src1, &src2);
  }

  //! @brief Set Carry Flag to 1.
  inline void stc()
  {
    _emitInstruction(INST_STC);
  }

  //! @brief Set Direction Flag to 1.
  inline void std()
  {
    _emitInstruction(INST_STD);
  }

  //! @brief Subtract.
  inline void sub(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_SUB, &dst, &src);
  }
  //! @brief Subtract.
  inline void sub(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_SUB, &dst, &src);
  }
  //! @brief Subtract.
  inline void sub(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_SUB, &dst, &src);
  }
  //! @brief Subtract.
  inline void sub(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_SUB, &dst, &src);
  }
  //! @brief Subtract.
  inline void sub(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_SUB, &dst, &src);
  }

  //! @brief Logical Compare.
  inline void test(const GPReg& op1, const GPReg& op2)
  {
    _emitInstruction(INST_TEST, &op1, &op2);
  }
  //! @brief Logical Compare.
  inline void test(const GPReg& op1, const Imm& op2)
  {
    _emitInstruction(INST_TEST, &op1, &op2);
  }
  //! @brief Logical Compare.
  inline void test(const Mem& op1, const GPReg& op2)
  {
    _emitInstruction(INST_TEST, &op1, &op2);
  }
  //! @brief Logical Compare.
  inline void test(const Mem& op1, const Imm& op2)
  {
    _emitInstruction(INST_TEST, &op1, &op2);
  }

  //! @brief Undefined instruction - Raise invalid opcode exception.
  inline void ud2()
  {
    _emitInstruction(INST_UD2);
  }

  //! @brief Exchange and Add.
  inline void xadd(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_XADD, &dst, &src);
  }
  //! @brief Exchange and Add.
  inline void xadd(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_XADD, &dst, &src);
  }

  //! @brief Exchange Register/Memory with Register.
  inline void xchg(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_XCHG, &dst, &src);
  }
  //! @brief Exchange Register/Memory with Register.
  inline void xchg(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_XCHG, &dst, &src);
  }
  //! @brief Exchange Register/Memory with Register.
  inline void xchg(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_XCHG, &src, &dst);
  }

  //! @brief Exchange Register/Memory with Register.
  inline void xor_(const GPReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_XOR, &dst, &src);
  }
  //! @brief Exchange Register/Memory with Register.
  inline void xor_(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_XOR, &dst, &src);
  }
  //! @brief Exchange Register/Memory with Register.
  inline void xor_(const GPReg& dst, const Imm& src)
  {
    _emitInstruction(INST_XOR, &dst, &src);
  }
  //! @brief Exchange Register/Memory with Register.
  inline void xor_(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_XOR, &dst, &src);
  }
  //! @brief Exchange Register/Memory with Register.
  inline void xor_(const Mem& dst, const Imm& src)
  {
    _emitInstruction(INST_XOR, &dst, &src);
  }

  // --------------------------------------------------------------------------
  // [X87 Instructions (FPU)]
  // --------------------------------------------------------------------------

  //! @brief Compute 2^x - 1 (FPU).
  inline void f2xm1()
  {
    _emitInstruction(INST_F2XM1);
  }

  //! @brief Absolute Value of st(0) (FPU).
  inline void fabs()
  {
    _emitInstruction(INST_FABS);
  }

  //! @brief Add @a src to @a dst and store result in @a dst (FPU).
  //!
  //! @note One of dst or src must be st(0).
  inline void fadd(const X87Reg& dst, const X87Reg& src)
  {
    ASMJIT_ASSERT(dst.getRegIndex() == 0 || src.getRegIndex() == 0);
    _emitInstruction(INST_FADD, &dst, &src);
  }

  //! @brief Add @a src to st(0) and store result in st(0) (FPU).
  //!
  //! @note SP-FP or DP-FP determined by @a adr size.
  inline void fadd(const Mem& src)
  {
    _emitInstruction(INST_FADD, &src);
  }

  //! @brief Add st(0) to @a dst and POP register stack (FPU).
  inline void faddp(const X87Reg& dst = st(1))
  {
    _emitInstruction(INST_FADDP, &dst);
  }

  //! @brief Load Binary Coded Decimal (FPU).
  inline void fbld(const Mem& src)
  {
    _emitInstruction(INST_FBLD, &src);
  }

  //! @brief Store BCD Integer and Pop (FPU).
  inline void fbstp(const Mem& dst)
  {
    _emitInstruction(INST_FBSTP, &dst);
  }

  //! @brief Change st(0) Sign (FPU).
  inline void fchs()
  {
    _emitInstruction(INST_FCHS);
  }

  //! @brief Clear Exceptions (FPU).
  //!
  //! Clear floating-point exception flags after checking for pending unmasked
  //! floating-point exceptions.
  //!
  //! Clears the floating-point exception flags (PE, UE, OE, ZE, DE, and IE),
  //! the exception summary status flag (ES), the stack fault flag (SF), and
  //! the busy flag (B) in the FPU status word. The FCLEX instruction checks
  //! for and handles any pending unmasked floating-point exceptions before
  //! clearing the exception flags.
  inline void fclex()
  {
    _emitInstruction(INST_FCLEX);
  }

  //! @brief FP Conditional Move (FPU).
  inline void fcmovb(const X87Reg& src)
  {
    _emitInstruction(INST_FCMOVB, &src);
  }
  //! @brief FP Conditional Move (FPU).
  inline void fcmovbe(const X87Reg& src)
  {
    _emitInstruction(INST_FCMOVBE, &src);
  }
  //! @brief FP Conditional Move (FPU).
  inline void fcmove(const X87Reg& src)
  {
    _emitInstruction(INST_FCMOVE, &src);
  }
  //! @brief FP Conditional Move (FPU).
  inline void fcmovnb(const X87Reg& src)
  {
    _emitInstruction(INST_FCMOVNB, &src);
  }
  //! @brief FP Conditional Move (FPU).
  inline void fcmovnbe(const X87Reg& src)
  {
    _emitInstruction(INST_FCMOVNBE, &src);
  }
  //! @brief FP Conditional Move (FPU).
  inline void fcmovne(const X87Reg& src)
  {
    _emitInstruction(INST_FCMOVNE, &src);
  }
  //! @brief FP Conditional Move (FPU).
  inline void fcmovnu(const X87Reg& src)
  {
    _emitInstruction(INST_FCMOVNU, &src);
  }
  //! @brief FP Conditional Move (FPU).
  inline void fcmovu(const X87Reg& src)
  {
    _emitInstruction(INST_FCMOVU, &src);
  }

  //! @brief Compare st(0) with @a reg (FPU).
  inline void fcom(const X87Reg& reg = st(1))
  {
    _emitInstruction(INST_FCOM, &reg);
  }
  //! @brief Compare st(0) with 4-byte or 8-byte FP at @a src (FPU).
  inline void fcom(const Mem& src)
  {
    _emitInstruction(INST_FCOM, &src);
  }

  //! @brief Compare st(0) with @a reg and pop the stack (FPU).
  inline void fcomp(const X87Reg& reg = st(1))
  {
    _emitInstruction(INST_FCOMP, &reg);
  }
  //! @brief Compare st(0) with 4-byte or 8-byte FP at @a adr and pop the
  //! stack (FPU).
  inline void fcomp(const Mem& mem)
  {
    _emitInstruction(INST_FCOMP, &mem);
  }

  //! @brief Compare st(0) with st(1) and pop register stack twice (FPU).
  inline void fcompp()
  {
    _emitInstruction(INST_FCOMPP);
  }

  //! @brief Compare st(0) and @a reg and Set EFLAGS (FPU).
  inline void fcomi(const X87Reg& reg)
  {
    _emitInstruction(INST_FCOMI, &reg);
  }

  //! @brief Compare st(0) and @a reg and Set EFLAGS and pop the stack (FPU).
  inline void fcomip(const X87Reg& reg)
  {
    _emitInstruction(INST_FCOMIP, &reg);
  }

  //! @brief Cosine (FPU).
  //!
  //! This instruction calculates the cosine of the source operand in
  //! register st(0) and stores the result in st(0).
  inline void fcos()
  {
    _emitInstruction(INST_FCOS);
  }

  //! @brief Decrement Stack-Top Pointer (FPU).
  //!
  //! Subtracts one from the TOP field of the FPU status word (decrements
  //! the top-ofstack pointer). If the TOP field contains a 0, it is set
  //! to 7. The effect of this instruction is to rotate the stack by one
  //! position. The contents of the FPU data registers and tag register
  //! are not affected.
  inline void fdecstp()
  {
    _emitInstruction(INST_FDECSTP);
  }

  //! @brief Divide @a dst by @a src (FPU).
  //!
  //! @note One of @a dst or @a src register must be st(0).
  inline void fdiv(const X87Reg& dst, const X87Reg& src)
  {
    ASMJIT_ASSERT(dst.getRegIndex() == 0 || src.getRegIndex() == 0);
    _emitInstruction(INST_FDIV, &dst, &src);
  }
  //! @brief Divide st(0) by 32-bit or 64-bit FP value (FPU).
  inline void fdiv(const Mem& src)
  {
    _emitInstruction(INST_FDIV, &src);
  }

  //! @brief Divide @a reg by st(0) (FPU).
  inline void fdivp(const X87Reg& reg = st(1))
  {
    _emitInstruction(INST_FDIVP, &reg);
  }

  //! @brief Reverse Divide @a dst by @a src (FPU).
  //!
  //! @note One of @a dst or @a src register must be st(0).
  inline void fdivr(const X87Reg& dst, const X87Reg& src)
  {
    ASMJIT_ASSERT(dst.getRegIndex() == 0 || src.getRegIndex() == 0);
    _emitInstruction(INST_FDIVR, &dst, &src);
  }
  //! @brief Reverse Divide st(0) by 32-bit or 64-bit FP value (FPU).
  inline void fdivr(const Mem& src)
  {
    _emitInstruction(INST_FDIVR, &src);
  }

  //! @brief Reverse Divide @a reg by st(0) (FPU).
  inline void fdivrp(const X87Reg& reg = st(1))
  {
    _emitInstruction(INST_FDIVRP, &reg);
  }

  //! @brief Free Floating-Point Register (FPU).
  //!
  //! Sets the tag in the FPU tag register associated with register @a reg
  //! to empty (11B). The contents of @a reg and the FPU stack-top pointer
  //! (TOP) are not affected.
  inline void ffree(const X87Reg& reg)
  {
    _emitInstruction(INST_FFREE, &reg);
  }

  //! @brief Add 16-bit or 32-bit integer to st(0) (FPU).
  inline void fiadd(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 2 || src.getSize() == 4);
    _emitInstruction(INST_FIADD, &src);
  }

  //! @brief Compare st(0) with 16-bit or 32-bit Integer (FPU).
  inline void ficom(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 2 || src.getSize() == 4);
    _emitInstruction(INST_FICOM, &src);
  }

  //! @brief Compare st(0) with 16-bit or 32-bit Integer and pop the stack (FPU).
  inline void ficomp(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 2 || src.getSize() == 4);
    _emitInstruction(INST_FICOMP, &src);
  }

  //! @brief Divide st(0) by 32-bit or 16-bit integer (@a src) (FPU).
  inline void fidiv(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 2 || src.getSize() == 4);
    _emitInstruction(INST_FIDIV, &src);
  }

  //! @brief Reverse Divide st(0) by 32-bit or 16-bit integer (@a src) (FPU).
  inline void fidivr(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 2 || src.getSize() == 4);
    _emitInstruction(INST_FIDIVR, &src);
  }

  //! @brief Load 16-bit, 32-bit or 64-bit Integer and push it to the stack (FPU).
  //!
  //! Converts the signed-integer source operand into double extended-precision
  //! floating point format and pushes the value onto the FPU register stack.
  //! The source operand can be a word, doubleword, or quadword integer. It is
  //! loaded without rounding errors. The sign of the source operand is
  //! preserved.
  inline void fild(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 2 || src.getSize() == 4 || src.getSize() == 8);
    _emitInstruction(INST_FILD, &src);
  }

  //! @brief Multiply st(0) by 16-bit or 32-bit integer and store it
  //! to st(0) (FPU).
  inline void fimul(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 2 || src.getSize() == 4);
    _emitInstruction(INST_FIMUL, &src);
  }

  //! @brief Increment Stack-Top Pointer (FPU).
  //!
  //! Adds one to the TOP field of the FPU status word (increments the
  //! top-of-stack pointer). If the TOP field contains a 7, it is set to 0.
  //! The effect of this instruction is to rotate the stack by one position.
  //! The contents of the FPU data registers and tag register are not affected.
  //! This operation is not equivalent to popping the stack, because the tag
  //! for the previous top-of-stack register is not marked empty.
  inline void fincstp()
  {
    _emitInstruction(INST_FINCSTP);
  }

  //! @brief Initialize Floating-Point Unit (FPU).
  //!
  //! Initialize FPU after checking for pending unmasked floating-point
  //! exceptions.
  inline void finit()
  {
    _emitInstruction(INST_FINIT);
  }

  //! @brief Subtract 16-bit or 32-bit integer from st(0) and store result to
  //! st(0) (FPU).
  inline void fisub(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 2 || src.getSize() == 4);
    _emitInstruction(INST_FISUB, &src);
  }

  //! @brief Reverse Subtract 16-bit or 32-bit integer from st(0) and
  //! store result to  st(0) (FPU).
  inline void fisubr(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 2 || src.getSize() == 4);
    _emitInstruction(INST_FISUBR, &src);
  }

  //! @brief Initialize Floating-Point Unit (FPU).
  //!
  //! Initialize FPU without checking for pending unmasked floating-point
  //! exceptions.
  inline void fninit()
  {
    _emitInstruction(INST_FNINIT);
  }

  //! @brief Store st(0) as 16-bit or 32-bit Integer to @a dst (FPU).
  inline void fist(const Mem& dst)
  {
    ASMJIT_ASSERT(dst.getSize() == 2 || dst.getSize() == 4);
    _emitInstruction(INST_FIST, &dst);
  }

  //! @brief Store st(0) as 16-bit, 32-bit or 64-bit Integer to @a dst and pop
  //! stack (FPU).
  inline void fistp(const Mem& dst)
  {
    ASMJIT_ASSERT(dst.getSize() == 2 || dst.getSize() == 4 || dst.getSize() == 8);
    _emitInstruction(INST_FISTP, &dst);
  }

  //! @brief Push 32-bit, 64-bit or 80-bit Floating Point Value onto the FPU
  //! register stack (FPU).
  inline void fld(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 4 || src.getSize() == 8 || src.getSize() == 10);
    _emitInstruction(INST_FLD, &src);
  }

  //! @brief Push @a reg onto the FPU register stack (FPU).
  inline void fld(const X87Reg& reg)
  {
    _emitInstruction(INST_FLD, &reg);
  }

  //! @brief Push +1.0 onto the FPU register stack (FPU).
  inline void fld1()
  {
    _emitInstruction(INST_FLD1);
  }

  //! @brief Push log2(10) onto the FPU register stack (FPU).
  inline void fldl2t()
  {
    _emitInstruction(INST_FLDL2T);
  }

  //! @brief Push log2(e) onto the FPU register stack (FPU).
  inline void fldl2e()
  {
    _emitInstruction(INST_FLDL2E);
  }

  //! @brief Push pi onto the FPU register stack (FPU).
  inline void fldpi()
  {
    _emitInstruction(INST_FLDPI);
  }

  //! @brief Push log10(2) onto the FPU register stack (FPU).
  inline void fldlg2()
  {
    _emitInstruction(INST_FLDLG2);
  }

  //! @brief Push ln(2) onto the FPU register stack (FPU).
  inline void fldln2()
  {
    _emitInstruction(INST_FLDLN2);
  }

  //! @brief Push +0.0 onto the FPU register stack (FPU).
  inline void fldz()
  {
    _emitInstruction(INST_FLDZ);
  }

  //! @brief Load x87 FPU Control Word (2 bytes) (FPU).
  inline void fldcw(const Mem& src)
  {
    _emitInstruction(INST_FLDCW, &src);
  }

  //! @brief Load x87 FPU Environment (14 or 28 bytes) (FPU).
  inline void fldenv(const Mem& src)
  {
    _emitInstruction(INST_FLDENV, &src);
  }

  //! @brief Multiply @a dst by @a src and store result in @a dst (FPU).
  //!
  //! @note One of dst or src must be st(0).
  inline void fmul(const X87Reg& dst, const X87Reg& src)
  {
    ASMJIT_ASSERT(dst.getRegIndex() == 0 || src.getRegIndex() == 0);
    _emitInstruction(INST_FMUL, &dst, &src);
  }
  //! @brief Multiply st(0) by @a src and store result in st(0) (FPU).
  //!
  //! @note SP-FP or DP-FP determined by @a adr size.
  inline void fmul(const Mem& src)
  {
    _emitInstruction(INST_FMUL, &src);
  }

  //! @brief Multiply st(0) by @a dst and POP register stack (FPU).
  inline void fmulp(const X87Reg& dst = st(1))
  {
    _emitInstruction(INST_FMULP, &dst);
  }

  //! @brief Clear Exceptions (FPU).
  //!
  //! Clear floating-point exception flags without checking for pending
  //! unmasked floating-point exceptions.
  //!
  //! Clears the floating-point exception flags (PE, UE, OE, ZE, DE, and IE),
  //! the exception summary status flag (ES), the stack fault flag (SF), and
  //! the busy flag (B) in the FPU status word. The FCLEX instruction does
  //! not checks for and handles any pending unmasked floating-point exceptions
  //! before clearing the exception flags.
  inline void fnclex()
  {
    _emitInstruction(INST_FNCLEX);
  }

  //! @brief No Operation (FPU).
  inline void fnop()
  {
    _emitInstruction(INST_FNOP);
  }

  //! @brief Save FPU State (FPU).
  //!
  //! Store FPU environment to m94byte or m108byte without
  //! checking for pending unmasked FP exceptions.
  //! Then re-initialize the FPU.
  inline void fnsave(const Mem& dst)
  {
    _emitInstruction(INST_FNSAVE, &dst);
  }

  //! @brief Store x87 FPU Environment (FPU).
  //!
  //! Store FPU environment to @a dst (14 or 28 Bytes) without checking for
  //! pending unmasked floating-point exceptions. Then mask all floating
  //! point exceptions.
  inline void fnstenv(const Mem& dst)
  {
    _emitInstruction(INST_FNSTENV, &dst);
  }

  //! @brief Store x87 FPU Control Word (FPU).
  //!
  //! Store FPU control word to @a dst (2 Bytes) without checking for pending
  //! unmasked floating-point exceptions.
  inline void fnstcw(const Mem& dst)
  {
    _emitInstruction(INST_FNSTCW, &dst);
  }

  //! @brief Store x87 FPU Status Word (2 Bytes) (FPU).
  inline void fnstsw(const GPReg& dst)
  {
    ASMJIT_ASSERT(dst.isRegCode(REG_AX));
    _emitInstruction(INST_FNSTSW, &dst);
  }
  //! @brief Store x87 FPU Status Word (2 Bytes) (FPU).
  inline void fnstsw(const Mem& dst)
  {
    _emitInstruction(INST_FNSTSW, &dst);
  }

  //! @brief Partial Arctangent (FPU).
  //!
  //! Replace st(1) with arctan(st(1)/st(0)) and pop the register stack.
  inline void fpatan()
  {
    _emitInstruction(INST_FPATAN);
  }

  //! @brief Partial Remainder (FPU).
  //!
  //! Replace st(0) with the remainder obtained from dividing st(0) by st(1).
  inline void fprem()
  {
    _emitInstruction(INST_FPREM);
  }

  //! @brief Partial Remainder (FPU).
  //!
  //! Replace st(0) with the IEEE remainder obtained from dividing st(0) by
  //! st(1).
  inline void fprem1()
  {
    _emitInstruction(INST_FPREM1);
  }

  //! @brief Partial Tangent (FPU).
  //!
  //! Replace st(0) with its tangent and push 1 onto the FPU stack.
  inline void fptan()
  {
    _emitInstruction(INST_FPTAN);
  }

  //! @brief Round to Integer (FPU).
  //!
  //! Rount st(0) to an Integer.
  inline void frndint()
  {
    _emitInstruction(INST_FRNDINT);
  }

  //! @brief Restore FPU State (FPU).
  //!
  //! Load FPU state from src (94 or 108 bytes).
  inline void frstor(const Mem& src)
  {
    _emitInstruction(INST_FRSTOR, &src);
  }

  //! @brief Save FPU State (FPU).
  //!
  //! Store FPU state to 94 or 108-bytes after checking for
  //! pending unmasked FP exceptions. Then reinitialize
  //! the FPU.
  inline void fsave(const Mem& dst)
  {
    _emitInstruction(INST_FSAVE, &dst);
  }

  //! @brief Scale (FPU).
  //!
  //! Scale st(0) by st(1).
  inline void fscale()
  {
    _emitInstruction(INST_FSCALE);
  }

  //! @brief Sine (FPU).
  //!
  //! This instruction calculates the sine of the source operand in
  //! register st(0) and stores the result in st(0).
  inline void fsin()
  {
    _emitInstruction(INST_FSIN);
  }

  //! @brief Sine and Cosine (FPU).
  //!
  //! Compute the sine and cosine of st(0); replace st(0) with
  //! the sine, and push the cosine onto the register stack.
  inline void fsincos()
  {
    _emitInstruction(INST_FSINCOS);
  }

  //! @brief Square Root (FPU).
  //!
  //! Calculates square root of st(0) and stores the result in st(0).
  inline void fsqrt()
  {
    _emitInstruction(INST_FSQRT);
  }

  //! @brief Store Floating Point Value (FPU).
  //!
  //! Store st(0) as 32-bit or 64-bit floating point value to @a dst.
  inline void fst(const Mem& dst)
  {
    ASMJIT_ASSERT(dst.getSize() == 4 || dst.getSize() == 8);
    _emitInstruction(INST_FST, &dst);
  }

  //! @brief Store Floating Point Value (FPU).
  //!
  //! Store st(0) to @a reg.
  inline void fst(const X87Reg& reg)
  {
    _emitInstruction(INST_FST, &reg);
  }

  //! @brief Store Floating Point Value and Pop Register Stack (FPU).
  //!
  //! Store st(0) as 32-bit or 64-bit floating point value to @a dst
  //! and pop register stack.
  inline void fstp(const Mem& dst)
  {
    ASMJIT_ASSERT(dst.getSize() == 4 || dst.getSize() == 8 || dst.getSize() == 10);
    _emitInstruction(INST_FSTP, &dst);
  }

  //! @brief Store Floating Point Value and Pop Register Stack (FPU).
  //!
  //! Store st(0) to @a reg and pop register stack.
  inline void fstp(const X87Reg& reg)
  {
    _emitInstruction(INST_FSTP, &reg);
  }

  //! @brief Store x87 FPU Control Word (FPU).
  //!
  //! Store FPU control word to @a dst (2 Bytes) after checking for pending
  //! unmasked floating-point exceptions.
  inline void fstcw(const Mem& dst)
  {
    _emitInstruction(INST_FSTCW, &dst);
  }

  //! @brief Store x87 FPU Environment (FPU).
  //!
  //! Store FPU environment to @a dst (14 or 28 Bytes) after checking for
  //! pending unmasked floating-point exceptions. Then mask all floating
  //! point exceptions.
  inline void fstenv(const Mem& dst)
  {
    _emitInstruction(INST_FSTENV, &dst);
  }

  //! @brief Store x87 FPU Status Word (2 Bytes) (FPU).
  inline void fstsw(const GPReg& dst)
  {
    ASMJIT_ASSERT(dst.isRegCode(REG_AX));
    _emitInstruction(INST_FSTSW, &dst);
  }
  //! @brief Store x87 FPU Status Word (2 Bytes) (FPU).
  inline void fstsw(const Mem& dst)
  {
    _emitInstruction(INST_FSTSW, &dst);
  }

  //! @brief Subtract @a src from @a dst and store result in @a dst (FPU).
  //!
  //! @note One of dst or src must be st(0).
  inline void fsub(const X87Reg& dst, const X87Reg& src)
  {
    ASMJIT_ASSERT(dst.getRegIndex() == 0 || src.getRegIndex() == 0);
    _emitInstruction(INST_FSUB, &dst, &src);
  }
  //! @brief Subtract @a src from st(0) and store result in st(0) (FPU).
  //!
  //! @note SP-FP or DP-FP determined by @a adr size.
  inline void fsub(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 4 || src.getSize() == 8);
    _emitInstruction(INST_FSUB, &src);
  }

  //! @brief Subtract st(0) from @a dst and POP register stack (FPU).
  inline void fsubp(const X87Reg& dst = st(1))
  {
    _emitInstruction(INST_FSUBP, &dst);
  }

  //! @brief Reverse Subtract @a src from @a dst and store result in @a dst (FPU).
  //!
  //! @note One of dst or src must be st(0).
  inline void fsubr(const X87Reg& dst, const X87Reg& src)
  {
    ASMJIT_ASSERT(dst.getRegIndex() == 0 || src.getRegIndex() == 0);
    _emitInstruction(INST_FSUBR, &dst, &src);
  }

  //! @brief Reverse Subtract @a src from st(0) and store result in st(0) (FPU).
  //!
  //! @note SP-FP or DP-FP determined by @a adr size.
  inline void fsubr(const Mem& src)
  {
    ASMJIT_ASSERT(src.getSize() == 4 || src.getSize() == 8);
    _emitInstruction(INST_FSUBR, &src);
  }

  //! @brief Reverse Subtract st(0) from @a dst and POP register stack (FPU).
  inline void fsubrp(const X87Reg& dst = st(1))
  {
    _emitInstruction(INST_FSUBRP, &dst);
  }

  //! @brief Floating point test - Compare st(0) with 0.0. (FPU).
  inline void ftst()
  {
    _emitInstruction(INST_FTST);
  }

  //! @brief Unordered Compare st(0) with @a reg (FPU).
  inline void fucom(const X87Reg& reg = st(1))
  {
    _emitInstruction(INST_FUCOM, &reg);
  }

  //! @brief Unordered Compare st(0) and @a reg, check for ordered values
  //! and Set EFLAGS (FPU).
  inline void fucomi(const X87Reg& reg)
  {
    _emitInstruction(INST_FUCOMI, &reg);
  }

  //! @brief UnorderedCompare st(0) and @a reg, Check for ordered values
  //! and Set EFLAGS and pop the stack (FPU).
  inline void fucomip(const X87Reg& reg = st(1))
  {
    _emitInstruction(INST_FUCOMIP, &reg);
  }

  //! @brief Unordered Compare st(0) with @a reg and pop register stack (FPU).
  inline void fucomp(const X87Reg& reg = st(1))
  {
    _emitInstruction(INST_FUCOMP, &reg);
  }

  //! @brief Unordered compare st(0) with st(1) and pop register stack twice
  //! (FPU).
  inline void fucompp()
  {
    _emitInstruction(INST_FUCOMPP);
  }

  inline void fwait()
  {
    _emitInstruction(INST_FWAIT);
  }

  //! @brief Examine st(0) (FPU).
  //!
  //! Examines the contents of the ST(0) register and sets the condition code
  //! flags C0, C2, and C3 in the FPU status word to indicate the class of
  //! value or number in the register.
  inline void fxam()
  {
    _emitInstruction(INST_FXAM);
  }

  //! @brief Exchange Register Contents (FPU).
  //!
  //! Exchange content of st(0) with @a reg.
  inline void fxch(const X87Reg& reg = st(1))
  {
    _emitInstruction(INST_FXCH, &reg);
  }

  //! @brief Restore FP And MMX(tm) State And Streaming SIMD Extension State
  //! (FPU, MMX, SSE).
  //!
  //! Load FP and MMX(tm) technology and Streaming SIMD Extension state from
  //! src (512 bytes).
  inline void fxrstor(const Mem& src)
  {
    _emitInstruction(INST_FXRSTOR, &src);
  }

  //! @brief Store FP and MMX(tm) State and Streaming SIMD Extension State
  //! (FPU, MMX, SSE).
  //!
  //! Store FP and MMX(tm) technology state and Streaming SIMD Extension state
  //! to dst (512 bytes).
  inline void fxsave(const Mem& dst)
  {
    _emitInstruction(INST_FXSAVE, &dst);
  }

  //! @brief Extract Exponent and Significand (FPU).
  //!
  //! Separate value in st(0) into exponent and significand, store exponent
  //! in st(0), and push the significand onto the register stack.
  inline void fxtract()
  {
    _emitInstruction(INST_FXTRACT);
  }

  //! @brief Compute y * log2(x).
  //!
  //! Replace st(1) with (st(1) * log2st(0)) and pop the register stack.
  inline void fyl2x()
  {
    _emitInstruction(INST_FYL2X);
  }

  //! @brief Compute y * log_2(x+1).
  //!
  //! Replace st(1) with (st(1) * (log2st(0) + 1.0)) and pop the register stack.
  inline void fyl2xp1()
  {
    _emitInstruction(INST_FYL2XP1);
  }

  // --------------------------------------------------------------------------
  // [MMX]
  // --------------------------------------------------------------------------

  //! @brief Empty MMX state.
  inline void emms()
  {
    _emitInstruction(INST_EMMS);
  }

  //! @brief Move DWord (MMX).
  inline void movd(const Mem& dst, const MMReg& src)
  {
    _emitInstruction(INST_MOVD, &dst, &src);
  }
  //! @brief Move DWord (MMX).
  inline void movd(const GPReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_MOVD, &dst, &src);
  }
  //! @brief Move DWord (MMX).
  inline void movd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVD, &dst, &src);
  }
  //! @brief Move DWord (MMX).
  inline void movd(const MMReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_MOVD, &dst, &src);
  }

  //! @brief Move QWord (MMX).
  inline void movq(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_MOVQ, &dst, &src);
  }
  //! @brief Move QWord (MMX).
  inline void movq(const Mem& dst, const MMReg& src)
  {
    _emitInstruction(INST_MOVQ, &dst, &src);
  }
#if defined(ASMJIT_X64)
  //! @brief Move QWord (MMX).
  inline void movq(const GPReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_MOVQ, &dst, &src);
  }
#endif
  //! @brief Move QWord (MMX).
  inline void movq(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVQ, &dst, &src);
  }
#if defined(ASMJIT_X64)
  //! @brief Move QWord (MMX).
  inline void movq(const MMReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_MOVQ, &dst, &src);
  }
#endif

  //! @brief Pack with Unsigned Saturation (MMX).
  inline void packuswb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PACKUSWB, &dst, &src);
  }
  //! @brief Pack with Unsigned Saturation (MMX).
  inline void packuswb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PACKUSWB, &dst, &src);
  }

  //! @brief Packed BYTE Add (MMX).
  inline void paddb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PADDB, &dst, &src);
  }
  //! @brief Packed BYTE Add (MMX).
  inline void paddb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDB, &dst, &src);
  }

  //! @brief Packed WORD Add (MMX).
  inline void paddw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PADDW, &dst, &src);
  }
  //! @brief Packed WORD Add (MMX).
  inline void paddw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDW, &dst, &src);
  }

  //! @brief Packed DWORD Add (MMX).
  inline void paddd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PADDD, &dst, &src);
  }
  //! @brief Packed DWORD Add (MMX).
  inline void paddd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDD, &dst, &src);
  }

  //! @brief Packed Add with Saturation (MMX).
  inline void paddsb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PADDSB, &dst, &src);
  }
  //! @brief Packed Add with Saturation (MMX).
  inline void paddsb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDSB, &dst, &src);
  }

  //! @brief Packed Add with Saturation (MMX).
  inline void paddsw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PADDSW, &dst, &src);
  }
  //! @brief Packed Add with Saturation (MMX).
  inline void paddsw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDSW, &dst, &src);
  }

  //! @brief Packed Add Unsigned with Saturation (MMX).
  inline void paddusb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PADDUSB, &dst, &src);
  }
  //! @brief Packed Add Unsigned with Saturation (MMX).
  inline void paddusb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDUSB, &dst, &src);
  }

  //! @brief Packed Add Unsigned with Saturation (MMX).
  inline void paddusw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PADDUSW, &dst, &src);
  }
  //! @brief Packed Add Unsigned with Saturation (MMX).
  inline void paddusw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDUSW, &dst, &src);
  }

  //! @brief Logical AND (MMX).
  inline void pand(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PAND, &dst, &src);
  }
  //! @brief Logical AND (MMX).
  inline void pand(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PAND, &dst, &src);
  }

  //! @brief Logical AND Not (MMX).
  inline void pandn(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PANDN, &dst, &src);
  }
  //! @brief Logical AND Not (MMX).
  inline void pandn(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PANDN, &dst, &src);
  }

  //! @brief Packed Compare for Equal (BYTES) (MMX).
  inline void pcmpeqb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PCMPEQB, &dst, &src);
  }
  //! @brief Packed Compare for Equal (BYTES) (MMX).
  inline void pcmpeqb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPEQB, &dst, &src);
  }

  //! @brief Packed Compare for Equal (WORDS) (MMX).
  inline void pcmpeqw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PCMPEQW, &dst, &src);
  }
  //! @brief Packed Compare for Equal (WORDS) (MMX).
  inline void pcmpeqw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPEQW, &dst, &src);
  }

  //! @brief Packed Compare for Equal (DWORDS) (MMX).
  inline void pcmpeqd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PCMPEQD, &dst, &src);
  }
  //! @brief Packed Compare for Equal (DWORDS) (MMX).
  inline void pcmpeqd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPEQD, &dst, &src);
  }

  //! @brief Packed Compare for Greater Than (BYTES) (MMX).
  inline void pcmpgtb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PCMPGTB, &dst, &src);
  }
  //! @brief Packed Compare for Greater Than (BYTES) (MMX).
  inline void pcmpgtb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPGTB, &dst, &src);
  }

  //! @brief Packed Compare for Greater Than (WORDS) (MMX).
  inline void pcmpgtw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PCMPGTW, &dst, &src);
  }
  //! @brief Packed Compare for Greater Than (WORDS) (MMX).
  inline void pcmpgtw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPGTW, &dst, &src);
  }

  //! @brief Packed Compare for Greater Than (DWORDS) (MMX).
  inline void pcmpgtd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PCMPGTD, &dst, &src);
  }
  //! @brief Packed Compare for Greater Than (DWORDS) (MMX).
  inline void pcmpgtd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPGTD, &dst, &src);
  }

  //! @brief Packed Multiply High (MMX).
  inline void pmulhw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PMULHW, &dst, &src);
  }
  //! @brief Packed Multiply High (MMX).
  inline void pmulhw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMULHW, &dst, &src);
  }

  //! @brief Packed Multiply Low (MMX).
  inline void pmullw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PMULLW, &dst, &src);
  }
  //! @brief Packed Multiply Low (MMX).
  inline void pmullw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMULLW, &dst, &src);
  }

  //! @brief Bitwise Logical OR (MMX).
  inline void por(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_POR, &dst, &src);
  }
  //! @brief Bitwise Logical OR (MMX).
  inline void por(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_POR, &dst, &src);
  }

  //! @brief Packed Multiply and Add (MMX).
  inline void pmaddwd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PMADDWD, &dst, &src);
  }
  //! @brief Packed Multiply and Add (MMX).
  inline void pmaddwd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMADDWD, &dst, &src);
  }

  //! @brief Packed Shift Left Logical (MMX).
  inline void pslld(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSLLD, &dst, &src);
  }
  //! @brief Packed Shift Left Logical (MMX).
  inline void pslld(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSLLD, &dst, &src);
  }
  //! @brief Packed Shift Left Logical (MMX).
  inline void pslld(const MMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSLLD, &dst, &src);
  }

  //! @brief Packed Shift Left Logical (MMX).
  inline void psllq(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSLLQ, &dst, &src);
  }
  //! @brief Packed Shift Left Logical (MMX).
  inline void psllq(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSLLQ, &dst, &src);
  }
  //! @brief Packed Shift Left Logical (MMX).
  inline void psllq(const MMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSLLQ, &dst, &src);
  }

  //! @brief Packed Shift Left Logical (MMX).
  inline void psllw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSLLW, &dst, &src);
  }
  //! @brief Packed Shift Left Logical (MMX).
  inline void psllw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSLLW, &dst, &src);
  }
  //! @brief Packed Shift Left Logical (MMX).
  inline void psllw(const MMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSLLW, &dst, &src);
  }

  //! @brief Packed Shift Right Arithmetic (MMX).
  inline void psrad(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSRAD, &dst, &src);
  }
  //! @brief Packed Shift Right Arithmetic (MMX).
  inline void psrad(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSRAD, &dst, &src);
  }
  //! @brief Packed Shift Right Arithmetic (MMX).
  inline void psrad(const MMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSRAD, &dst, &src);
  }

  //! @brief Packed Shift Right Arithmetic (MMX).
  inline void psraw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSRAW, &dst, &src);
  }
  //! @brief Packed Shift Right Arithmetic (MMX).
  inline void psraw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSRAW, &dst, &src);
  }
  //! @brief Packed Shift Right Arithmetic (MMX).
  inline void psraw(const MMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSRAW, &dst, &src);
  }

  //! @brief Packed Shift Right Logical (MMX).
  inline void psrld(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSRLD, &dst, &src);
  }
  //! @brief Packed Shift Right Logical (MMX).
  inline void psrld(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSRLD, &dst, &src);
  }
  //! @brief Packed Shift Right Logical (MMX).
  inline void psrld(const MMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSRLD, &dst, &src);
  }

  //! @brief Packed Shift Right Logical (MMX).
  inline void psrlq(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSRLQ, &dst, &src);
  }
  //! @brief Packed Shift Right Logical (MMX).
  inline void psrlq(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSRLQ, &dst, &src);
  }
  //! @brief Packed Shift Right Logical (MMX).
  inline void psrlq(const MMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSRLQ, &dst, &src);
  }

  //! @brief Packed Shift Right Logical (MMX).
  inline void psrlw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSRLW, &dst, &src);
  }
  //! @brief Packed Shift Right Logical (MMX).
  inline void psrlw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSRLW, &dst, &src);
  }
  //! @brief Packed Shift Right Logical (MMX).
  inline void psrlw(const MMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSRLW, &dst, &src);
  }

  //! @brief Packed Subtract (MMX).
  inline void psubb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSUBB, &dst, &src);
  }
  //! @brief Packed Subtract (MMX).
  inline void psubb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBB, &dst, &src);
  }

  //! @brief Packed Subtract (MMX).
  inline void psubw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSUBW, &dst, &src);
  }
  //! @brief Packed Subtract (MMX).
  inline void psubw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBW, &dst, &src);
  }

  //! @brief Packed Subtract (MMX).
  inline void psubd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSUBD, &dst, &src);
  }
  //! @brief Packed Subtract (MMX).
  inline void psubd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBD, &dst, &src);
  }

  //! @brief Packed Subtract with Saturation (MMX).
  inline void psubsb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSUBSB, &dst, &src);
  }
  //! @brief Packed Subtract with Saturation (MMX).
  inline void psubsb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBSB, &dst, &src);
  }

  //! @brief Packed Subtract with Saturation (MMX).
  inline void psubsw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSUBSW, &dst, &src);
  }
  //! @brief Packed Subtract with Saturation (MMX).
  inline void psubsw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBSW, &dst, &src);
  }

  //! @brief Packed Subtract with Unsigned Saturation (MMX).
  inline void psubusb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSUBUSB, &dst, &src);
  }
  //! @brief Packed Subtract with Unsigned Saturation (MMX).
  inline void psubusb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBUSB, &dst, &src);
  }

  //! @brief Packed Subtract with Unsigned Saturation (MMX).
  inline void psubusw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSUBUSW, &dst, &src);
  }
  //! @brief Packed Subtract with Unsigned Saturation (MMX).
  inline void psubusw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBUSW, &dst, &src);
  }

  //! @brief Unpack High Packed Data (MMX).
  inline void punpckhbw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PUNPCKHBW, &dst, &src);
  }
  //! @brief Unpack High Packed Data (MMX).
  inline void punpckhbw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKHBW, &dst, &src);
  }

  //! @brief Unpack High Packed Data (MMX).
  inline void punpckhwd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PUNPCKHWD, &dst, &src);
  }
  //! @brief Unpack High Packed Data (MMX).
  inline void punpckhwd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKHWD, &dst, &src);
  }

  //! @brief Unpack High Packed Data (MMX).
  inline void punpckhdq(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PUNPCKHDQ, &dst, &src);
  }
  //! @brief Unpack High Packed Data (MMX).
  inline void punpckhdq(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKHDQ, &dst, &src);
  }

  //! @brief Unpack High Packed Data (MMX).
  inline void punpcklbw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PUNPCKLBW, &dst, &src);
  }
  //! @brief Unpack High Packed Data (MMX).
  inline void punpcklbw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKLBW, &dst, &src);
  }

  //! @brief Unpack High Packed Data (MMX).
  inline void punpcklwd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PUNPCKLWD, &dst, &src);
  }
  //! @brief Unpack High Packed Data (MMX).
  inline void punpcklwd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKLWD, &dst, &src);
  }

  //! @brief Unpack High Packed Data (MMX).
  inline void punpckldq(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PUNPCKLDQ, &dst, &src);
  }
  //! @brief Unpack High Packed Data (MMX).
  inline void punpckldq(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKLDQ, &dst, &src);
  }

  //! @brief Bitwise Exclusive OR (MMX).
  inline void pxor(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PXOR, &dst, &src);
  }
  //! @brief Bitwise Exclusive OR (MMX).
  inline void pxor(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PXOR, &dst, &src);
  }

  // -------------------------------------------------------------------------
  // [3dNow]
  // -------------------------------------------------------------------------

  //! @brief Faster EMMS (3dNow!).
  //!
  //! @note Use only for early AMD processors where is only 3dNow! or SSE. If
  //! CPU contains SSE2, it's better to use @c emms() ( @c femms() is mapped
  //! to @c emms() ).
  inline void femms()
  {
    _emitInstruction(INST_FEMMS);
  }

  //! @brief Packed SP-FP to Integer Convert (3dNow!).
  inline void pf2id(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PF2ID, &dst, &src);
  }
  //! @brief Packed SP-FP to Integer Convert (3dNow!).
  inline void pf2id(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PF2ID, &dst, &src);
  }

  //! @brief  Packed SP-FP to Integer Word Convert (3dNow!).
  inline void pf2iw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PF2IW, &dst, &src);
  }
  //! @brief  Packed SP-FP to Integer Word Convert (3dNow!).
  inline void pf2iw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PF2IW, &dst, &src);
  }

  //! @brief Packed SP-FP Accumulate (3dNow!).
  inline void pfacc(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFACC, &dst, &src);
  }
  //! @brief Packed SP-FP Accumulate (3dNow!).
  inline void pfacc(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFACC, &dst, &src);
  }

  //! @brief Packed SP-FP Addition (3dNow!).
  inline void pfadd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFADD, &dst, &src);
  }
  //! @brief Packed SP-FP Addition (3dNow!).
  inline void pfadd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFADD, &dst, &src);
  }

  //! @brief Packed SP-FP Compare - dst == src (3dNow!).
  inline void pfcmpeq(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFCMPEQ, &dst, &src);
  }
  //! @brief Packed SP-FP Compare - dst == src (3dNow!).
  inline void pfcmpeq(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFCMPEQ, &dst, &src);
  }

  //! @brief Packed SP-FP Compare - dst >= src (3dNow!).
  inline void pfcmpge(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFCMPGE, &dst, &src);
  }
  //! @brief Packed SP-FP Compare - dst >= src (3dNow!).
  inline void pfcmpge(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFCMPGE, &dst, &src);
  }

  //! @brief Packed SP-FP Compare - dst > src (3dNow!).
  inline void pfcmpgt(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFCMPGT, &dst, &src);
  }
  //! @brief Packed SP-FP Compare - dst > src (3dNow!).
  inline void pfcmpgt(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFCMPGT, &dst, &src);
  }

  //! @brief Packed SP-FP Maximum (3dNow!).
  inline void pfmax(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFMAX, &dst, &src);
  }
  //! @brief Packed SP-FP Maximum (3dNow!).
  inline void pfmax(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFMAX, &dst, &src);
  }

  //! @brief Packed SP-FP Minimum (3dNow!).
  inline void pfmin(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFMIN, &dst, &src);
  }
  //! @brief Packed SP-FP Minimum (3dNow!).
  inline void pfmin(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFMIN, &dst, &src);
  }

  //! @brief Packed SP-FP Multiply (3dNow!).
  inline void pfmul(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFMUL, &dst, &src);
  }
  //! @brief Packed SP-FP Multiply (3dNow!).
  inline void pfmul(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFMUL, &dst, &src);
  }

  //! @brief Packed SP-FP Negative Accumulate (3dNow!).
  inline void pfnacc(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFNACC, &dst, &src);
  }
  //! @brief Packed SP-FP Negative Accumulate (3dNow!).
  inline void pfnacc(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFNACC, &dst, &src);
  }

  //! @brief Packed SP-FP Mixed Accumulate (3dNow!).
  inline void pfpnaxx(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFPNACC, &dst, &src);
  }
  //! @brief Packed SP-FP Mixed Accumulate (3dNow!).
  inline void pfpnacc(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFPNACC, &dst, &src);
  }

  //! @brief Packed SP-FP Reciprocal Approximation (3dNow!).
  inline void pfrcp(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFRCP, &dst, &src);
  }
  //! @brief Packed SP-FP Reciprocal Approximation (3dNow!).
  inline void pfrcp(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFRCP, &dst, &src);
  }

  //! @brief Packed SP-FP Reciprocal, First Iteration Step (3dNow!).
  inline void pfrcpit1(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFRCPIT1, &dst, &src);
  }
  //! @brief Packed SP-FP Reciprocal, First Iteration Step (3dNow!).
  inline void pfrcpit1(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFRCPIT1, &dst, &src);
  }

  //! @brief Packed SP-FP Reciprocal, Second Iteration Step (3dNow!).
  inline void pfrcpit2(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFRCPIT2, &dst, &src);
  }
  //! @brief Packed SP-FP Reciprocal, Second Iteration Step (3dNow!).
  inline void pfrcpit2(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFRCPIT2, &dst, &src);
  }

  //! @brief Packed SP-FP Reciprocal Square Root, First Iteration Step (3dNow!).
  inline void pfrsqit1(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFRSQIT1, &dst, &src);
  }
  //! @brief Packed SP-FP Reciprocal Square Root, First Iteration Step (3dNow!).
  inline void pfrsqit1(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFRSQIT1, &dst, &src);
  }

  //! @brief Packed SP-FP Reciprocal Square Root Approximation (3dNow!).
  inline void pfrsqrt(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFRSQRT, &dst, &src);
  }
  //! @brief Packed SP-FP Reciprocal Square Root Approximation (3dNow!).
  inline void pfrsqrt(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFRSQRT, &dst, &src);
  }

  //! @brief Packed SP-FP Subtract (3dNow!).
  inline void pfsub(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFSUB, &dst, &src);
  }
  //! @brief Packed SP-FP Subtract (3dNow!).
  inline void pfsub(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFSUB, &dst, &src);
  }

  //! @brief Packed SP-FP Reverse Subtract (3dNow!).
  inline void pfsubr(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PFSUBR, &dst, &src);
  }
  //! @brief Packed SP-FP Reverse Subtract (3dNow!).
  inline void pfsubr(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PFSUBR, &dst, &src);
  }

  //! @brief Packed DWords to SP-FP (3dNow!).
  inline void pi2fd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PI2FD, &dst, &src);
  }
  //! @brief Packed DWords to SP-FP (3dNow!).
  inline void pi2fd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PI2FD, &dst, &src);
  }

  //! @brief Packed Words to SP-FP (3dNow!).
  inline void pi2fw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PI2FW, &dst, &src);
  }
  //! @brief Packed Words to SP-FP (3dNow!).
  inline void pi2fw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PI2FW, &dst, &src);
  }

  //! @brief Packed swap DWord (3dNow!)
  inline void pswapd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSWAPD, &dst, &src);
  }
  //! @brief Packed swap DWord (3dNow!)
  inline void pswapd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSWAPD, &dst, &src);
  }

  // --------------------------------------------------------------------------
  // [SSE]
  // --------------------------------------------------------------------------

  //! @brief Packed SP-FP Add (SSE).
  inline void addps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_ADDPS, &dst, &src);
  }
  //! @brief Packed SP-FP Add (SSE).
  inline void addps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ADDPS, &dst, &src);
  }

  //! @brief Scalar SP-FP Add (SSE).
  inline void addss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_ADDSS, &dst, &src);
  }
  //! @brief Scalar SP-FP Add (SSE).
  inline void addss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ADDSS, &dst, &src);
  }

  //! @brief Bit-wise Logical And Not For SP-FP (SSE).
  inline void andnps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_ANDNPS, &dst, &src);
  }
  //! @brief Bit-wise Logical And Not For SP-FP (SSE).
  inline void andnps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ANDNPS, &dst, &src);
  }

  //! @brief Bit-wise Logical And For SP-FP (SSE).
  inline void andps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_ANDPS, &dst, &src);
  }
  //! @brief Bit-wise Logical And For SP-FP (SSE).
  inline void andps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ANDPS, &dst, &src);
  }

  //! @brief Packed SP-FP Compare (SSE).
  inline void cmpps(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_CMPPS, &dst, &src, &imm8);
  }
  //! @brief Packed SP-FP Compare (SSE).
  inline void cmpps(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_CMPPS, &dst, &src, &imm8);
  }

  //! @brief Compare Scalar SP-FP Values (SSE).
  inline void cmpss(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_CMPSS, &dst, &src, &imm8);
  }
  //! @brief Compare Scalar SP-FP Values (SSE).
  inline void cmpss(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_CMPSS, &dst, &src, &imm8);
  }

  //! @brief Scalar Ordered SP-FP Compare and Set EFLAGS (SSE).
  inline void comiss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_COMISS, &dst, &src);
  }
  //! @brief Scalar Ordered SP-FP Compare and Set EFLAGS (SSE).
  inline void comiss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_COMISS, &dst, &src);
  }

  //! @brief Packed Signed INT32 to Packed SP-FP Conversion (SSE).
  inline void cvtpi2ps(const XMMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_CVTPI2PS, &dst, &src);
  }
  //! @brief Packed Signed INT32 to Packed SP-FP Conversion (SSE).
  inline void cvtpi2ps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTPI2PS, &dst, &src);
  }

  //! @brief Packed SP-FP to Packed INT32 Conversion (SSE).
  inline void cvtps2pi(const MMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTPS2PI, &dst, &src);
  }
  //! @brief Packed SP-FP to Packed INT32 Conversion (SSE).
  inline void cvtps2pi(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTPS2PI, &dst, &src);
  }

  //! @brief Scalar Signed INT32 to SP-FP Conversion (SSE).
  inline void cvtsi2ss(const XMMReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_CVTSI2SS, &dst, &src);
  }
  //! @brief Scalar Signed INT32 to SP-FP Conversion (SSE).
  inline void cvtsi2ss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTSI2SS, &dst, &src);
  }

  //! @brief Scalar SP-FP to Signed INT32 Conversion (SSE).
  inline void cvtss2si(const GPReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTSS2SI, &dst, &src);
  }
  //! @brief Scalar SP-FP to Signed INT32 Conversion (SSE).
  inline void cvtss2si(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTSS2SI, &dst, &src);
  }

  //! @brief Packed SP-FP to Packed INT32 Conversion (truncate) (SSE).
  inline void cvttps2pi(const MMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTTPS2PI, &dst, &src);
  }
  //! @brief Packed SP-FP to Packed INT32 Conversion (truncate) (SSE).
  inline void cvttps2pi(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTTPS2PI, &dst, &src);
  }

  //! @brief Scalar SP-FP to Signed INT32 Conversion (truncate) (SSE).
  inline void cvttss2si(const GPReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTTSS2SI, &dst, &src);
  }
  //! @brief Scalar SP-FP to Signed INT32 Conversion (truncate) (SSE).
  inline void cvttss2si(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTTSS2SI, &dst, &src);
  }

  //! @brief Packed SP-FP Divide (SSE).
  inline void divps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_DIVPS, &dst, &src);
  }
  //! @brief Packed SP-FP Divide (SSE).
  inline void divps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_DIVPS, &dst, &src);
  }

  //! @brief Scalar SP-FP Divide (SSE).
  inline void divss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_DIVSS, &dst, &src);
  }
  //! @brief Scalar SP-FP Divide (SSE).
  inline void divss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_DIVSS, &dst, &src);
  }

  //! @brief Load Streaming SIMD Extension Control/Status (SSE).
  inline void ldmxcsr(const Mem& src)
  {
    _emitInstruction(INST_LDMXCSR, &src);
  }

  //! @brief Byte Mask Write (SSE).
  //!
  //! @note The default memory location is specified by DS:EDI.
  inline void maskmovq(const MMReg& data, const MMReg& mask)
  {
    _emitInstruction(INST_MASKMOVQ, &data, &mask);
  }

  //! @brief Packed SP-FP Maximum (SSE).
  inline void maxps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MAXPS, &dst, &src);
  }
  //! @brief Packed SP-FP Maximum (SSE).
  inline void maxps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MAXPS, &dst, &src);
  }

  //! @brief Scalar SP-FP Maximum (SSE).
  inline void maxss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MAXSS, &dst, &src);
  }
  //! @brief Scalar SP-FP Maximum (SSE).
  inline void maxss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MAXSS, &dst, &src);
  }

  //! @brief Packed SP-FP Minimum (SSE).
  inline void minps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MINPS, &dst, &src);
  }
  //! @brief Packed SP-FP Minimum (SSE).
  inline void minps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MINPS, &dst, &src);
  }

  //! @brief Scalar SP-FP Minimum (SSE).
  inline void minss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MINSS, &dst, &src);
  }
  //! @brief Scalar SP-FP Minimum (SSE).
  inline void minss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MINSS, &dst, &src);
  }

  //! @brief Move Aligned Packed SP-FP Values (SSE).
  inline void movaps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVAPS, &dst, &src);
  }
  //! @brief Move Aligned Packed SP-FP Values (SSE).
  inline void movaps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVAPS, &dst, &src);
  }

  //! @brief Move Aligned Packed SP-FP Values (SSE).
  inline void movaps(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVAPS, &dst, &src);
  }

  //! @brief Move DWord.
  inline void movd(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVD, &dst, &src);
  }
  //! @brief Move DWord.
  inline void movd(const GPReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVD, &dst, &src);
  }
  //! @brief Move DWord.
  inline void movd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVD, &dst, &src);
  }
  //! @brief Move DWord.
  inline void movd(const XMMReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_MOVD, &dst, &src);
  }

  //! @brief Move QWord (SSE).
  inline void movq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVQ, &dst, &src);
  }
  //! @brief Move QWord (SSE).
  inline void movq(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVQ, &dst, &src);
  }
#if defined(ASMJIT_X64)
  //! @brief Move QWord (SSE).
  inline void movq(const GPReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVQ, &dst, &src);
  }
#endif // ASMJIT_X64
  //! @brief Move QWord (SSE).
  inline void movq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVQ, &dst, &src);
  }
#if defined(ASMJIT_X64)
  //! @brief Move QWord (SSE).
  inline void movq(const XMMReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_MOVQ, &dst, &src);
  }
#endif // ASMJIT_X64

  //! @brief Move 64 Bits Non Temporal (SSE).
  inline void movntq(const Mem& dst, const MMReg& src)
  {
    _emitInstruction(INST_MOVNTQ, &dst, &src);
  }

  //! @brief High to Low Packed SP-FP (SSE).
  inline void movhlps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVHLPS, &dst, &src);
  }

  //! @brief Move High Packed SP-FP (SSE).
  inline void movhps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVHPS, &dst, &src);
  }

  //! @brief Move High Packed SP-FP (SSE).
  inline void movhps(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVHPS, &dst, &src);
  }

  //! @brief Move Low to High Packed SP-FP (SSE).
  inline void movlhps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVLHPS, &dst, &src);
  }

  //! @brief Move Low Packed SP-FP (SSE).
  inline void movlps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVLPS, &dst, &src);
  }

  //! @brief Move Low Packed SP-FP (SSE).
  inline void movlps(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVLPS, &dst, &src);
  }

  //! @brief Move Aligned Four Packed SP-FP Non Temporal (SSE).
  inline void movntps(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVNTPS, &dst, &src);
  }

  //! @brief Move Scalar SP-FP (SSE).
  inline void movss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVSS, &dst, &src);
  }

  //! @brief Move Scalar SP-FP (SSE).
  inline void movss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVSS, &dst, &src);
  }

  //! @brief Move Scalar SP-FP (SSE).
  inline void movss(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVSS, &dst, &src);
  }

  //! @brief Move Unaligned Packed SP-FP Values (SSE).
  inline void movups(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVUPS, &dst, &src);
  }
  //! @brief Move Unaligned Packed SP-FP Values (SSE).
  inline void movups(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVUPS, &dst, &src);
  }

  //! @brief Move Unaligned Packed SP-FP Values (SSE).
  inline void movups(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVUPS, &dst, &src);
  }

  //! @brief Packed SP-FP Multiply (SSE).
  inline void mulps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MULPS, &dst, &src);
  }
  //! @brief Packed SP-FP Multiply (SSE).
  inline void mulps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MULPS, &dst, &src);
  }

  //! @brief Scalar SP-FP Multiply (SSE).
  inline void mulss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MULSS, &dst, &src);
  }
  //! @brief Scalar SP-FP Multiply (SSE).
  inline void mulss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MULSS, &dst, &src);
  }

  //! @brief Bit-wise Logical OR for SP-FP Data (SSE).
  inline void orps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_ORPS, &dst, &src);
  }
  //! @brief Bit-wise Logical OR for SP-FP Data (SSE).
  inline void orps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ORPS, &dst, &src);
  }

  //! @brief Packed Average (SSE).
  inline void pavgb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PAVGB, &dst, &src);
  }
  //! @brief Packed Average (SSE).
  inline void pavgb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PAVGB, &dst, &src);
  }

  //! @brief Packed Average (SSE).
  inline void pavgw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PAVGW, &dst, &src);
  }
  //! @brief Packed Average (SSE).
  inline void pavgw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PAVGW, &dst, &src);
  }

  //! @brief Extract Word (SSE).
  inline void pextrw(const GPReg& dst, const MMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PEXTRW, &dst, &src, &imm8);
  }

  //! @brief Insert Word (SSE).
  inline void pinsrw(const MMReg& dst, const GPReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PINSRW, &dst, &src, &imm8);
  }
  //! @brief Insert Word (SSE).
  inline void pinsrw(const MMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PINSRW, &dst, &src, &imm8);
  }

  //! @brief Packed Signed Integer Word Maximum (SSE).
  inline void pmaxsw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PMAXSW, &dst, &src);
  }
  //! @brief Packed Signed Integer Word Maximum (SSE).
  inline void pmaxsw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMAXSW, &dst, &src);
  }

  //! @brief Packed Unsigned Integer Byte Maximum (SSE).
  inline void pmaxub(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PMAXUB, &dst, &src);
  }
  //! @brief Packed Unsigned Integer Byte Maximum (SSE).
  inline void pmaxub(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMAXUB, &dst, &src);
  }

  //! @brief Packed Signed Integer Word Minimum (SSE).
  inline void pminsw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PMINSW, &dst, &src);
  }
  //! @brief Packed Signed Integer Word Minimum (SSE).
  inline void pminsw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMINSW, &dst, &src);
  }

  //! @brief Packed Unsigned Integer Byte Minimum (SSE).
  inline void pminub(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PMINUB, &dst, &src);
  }
  //! @brief Packed Unsigned Integer Byte Minimum (SSE).
  inline void pminub(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMINUB, &dst, &src);
  }

  //! @brief Move Byte Mask To Integer (SSE).
  inline void pmovmskb(const GPReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PMOVMSKB, &dst, &src);
  }

  //! @brief Packed Multiply High Unsigned (SSE).
  inline void pmulhuw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PMULHUW, &dst, &src);
  }
  //! @brief Packed Multiply High Unsigned (SSE).
  inline void pmulhuw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMULHUW, &dst, &src);
  }

  //! @brief Packed Sum of Absolute Differences (SSE).
  inline void psadbw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSADBW, &dst, &src);
  }
  //! @brief Packed Sum of Absolute Differences (SSE).
  inline void psadbw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSADBW, &dst, &src);
  }

  //! @brief Packed Shuffle word (SSE).
  inline void pshufw(const MMReg& dst, const MMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PSHUFW, &dst, &src, &imm8);
  }
  //! @brief Packed Shuffle word (SSE).
  inline void pshufw(const MMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PSHUFW, &dst, &src, &imm8);
  }

  //! @brief Packed SP-FP Reciprocal (SSE).
  inline void rcpps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_RCPPS, &dst, &src);
  }
  //! @brief Packed SP-FP Reciprocal (SSE).
  inline void rcpps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_RCPPS, &dst, &src);
  }

  //! @brief Scalar SP-FP Reciprocal (SSE).
  inline void rcpss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_RCPSS, &dst, &src);
  }
  //! @brief Scalar SP-FP Reciprocal (SSE).
  inline void rcpss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_RCPSS, &dst, &src);
  }

  //! @brief Prefetch (SSE).
  inline void prefetch(const Mem& mem, const Imm& hint)
  {
    _emitInstruction(INST_PREFETCH, &mem, &hint);
  }

  //! @brief Compute Sum of Absolute Differences (SSE).
  inline void psadbw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSADBW, &dst, &src);
  }
  //! @brief Compute Sum of Absolute Differences (SSE).
  inline void psadbw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSADBW, &dst, &src);
  }

  //! @brief Packed SP-FP Square Root Reciprocal (SSE).
  inline void rsqrtps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_RSQRTPS, &dst, &src);
  }
  //! @brief Packed SP-FP Square Root Reciprocal (SSE).
  inline void rsqrtps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_RSQRTPS, &dst, &src);
  }

  //! @brief Scalar SP-FP Square Root Reciprocal (SSE).
  inline void rsqrtss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_RSQRTSS, &dst, &src);
  }
  //! @brief Scalar SP-FP Square Root Reciprocal (SSE).
  inline void rsqrtss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_RSQRTSS, &dst, &src);
  }

  //! @brief Store fence (SSE).
  inline void sfence()
  {
    _emitInstruction(INST_SFENCE);
  }

  //! @brief Shuffle SP-FP (SSE).
  inline void shufps(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_SHUFPS, &dst, &src, &imm8);
  }
  //! @brief Shuffle SP-FP (SSE).
  inline void shufps(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_SHUFPS, &dst, &src, &imm8);
  }

  //! @brief Packed SP-FP Square Root (SSE).
  inline void sqrtps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_SQRTPS, &dst, &src);
  }
  //! @brief Packed SP-FP Square Root (SSE).
  inline void sqrtps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_SQRTPS, &dst, &src);
  }

  //! @brief Scalar SP-FP Square Root (SSE).
  inline void sqrtss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_SQRTSS, &dst, &src);
  }
  //! @brief Scalar SP-FP Square Root (SSE).
  inline void sqrtss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_SQRTSS, &dst, &src);
  }

  //! @brief Store Streaming SIMD Extension Control/Status (SSE).
  inline void stmxcsr(const Mem& dst)
  {
    _emitInstruction(INST_STMXCSR, &dst);
  }

  //! @brief Packed SP-FP Subtract (SSE).
  inline void subps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_SUBPS, &dst, &src);
  }
  //! @brief Packed SP-FP Subtract (SSE).
  inline void subps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_SUBPS, &dst, &src);
  }

  //! @brief Scalar SP-FP Subtract (SSE).
  inline void subss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_SUBSS, &dst, &src);
  }
  //! @brief Scalar SP-FP Subtract (SSE).
  inline void subss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_SUBSS, &dst, &src);
  }

  //! @brief Unordered Scalar SP-FP compare and set EFLAGS (SSE).
  inline void ucomiss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_UCOMISS, &dst, &src);
  }
  //! @brief Unordered Scalar SP-FP compare and set EFLAGS (SSE).
  inline void ucomiss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_UCOMISS, &dst, &src);
  }

  //! @brief Unpack High Packed SP-FP Data (SSE).
  inline void unpckhps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_UNPCKHPS, &dst, &src);
  }
  //! @brief Unpack High Packed SP-FP Data (SSE).
  inline void unpckhps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_UNPCKHPS, &dst, &src);
  }

  //! @brief Unpack Low Packed SP-FP Data (SSE).
  inline void unpcklps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_UNPCKLPS, &dst, &src);
  }
  //! @brief Unpack Low Packed SP-FP Data (SSE).
  inline void unpcklps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_UNPCKLPS, &dst, &src);
  }

  //! @brief Bit-wise Logical Xor for SP-FP Data (SSE).
  inline void xorps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_XORPS, &dst, &src);
  }
  //! @brief Bit-wise Logical Xor for SP-FP Data (SSE).
  inline void xorps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_XORPS, &dst, &src);
  }

  // --------------------------------------------------------------------------
  // [SSE2]
  // --------------------------------------------------------------------------

  //! @brief Packed DP-FP Add (SSE2).
  inline void addpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_ADDPD, &dst, &src);
  }
  //! @brief Packed DP-FP Add (SSE2).
  inline void addpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ADDPD, &dst, &src);
  }

  //! @brief Scalar DP-FP Add (SSE2).
  inline void addsd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_ADDSD, &dst, &src);
  }
  //! @brief Scalar DP-FP Add (SSE2).
  inline void addsd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ADDSD, &dst, &src);
  }

  //! @brief Bit-wise Logical And Not For DP-FP (SSE2).
  inline void andnpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_ANDNPD, &dst, &src);
  }
  //! @brief Bit-wise Logical And Not For DP-FP (SSE2).
  inline void andnpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ANDNPD, &dst, &src);
  }

  //! @brief Bit-wise Logical And For DP-FP (SSE2).
  inline void andpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_ANDPD, &dst, &src);
  }
  //! @brief Bit-wise Logical And For DP-FP (SSE2).
  inline void andpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ANDPD, &dst, &src);
  }

  //! @brief Flush Cache Line (SSE2).
  inline void clflush(const Mem& mem)
  {
    _emitInstruction(INST_CLFLUSH, &mem);
  }

  //! @brief Packed DP-FP Compare (SSE2).
  inline void cmppd(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_CMPPD, &dst, &src, &imm8);
  }
  //! @brief Packed DP-FP Compare (SSE2).
  inline void cmppd(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_CMPPD, &dst, &src, &imm8);
  }

  //! @brief Compare Scalar SP-FP Values (SSE2).
  inline void cmpsd(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_CMPSD, &dst, &src, &imm8);
  }
  //! @brief Compare Scalar SP-FP Values (SSE2).
  inline void cmpsd(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_CMPSD, &dst, &src, &imm8);
  }

  //! @brief Scalar Ordered DP-FP Compare and Set EFLAGS (SSE2).
  inline void comisd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_COMISD, &dst, &src);
  }
  //! @brief Scalar Ordered DP-FP Compare and Set EFLAGS (SSE2).
  inline void comisd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_COMISD, &dst, &src);
  }

  //! @brief Convert Packed Dword Integers to Packed DP-FP Values (SSE2).
  inline void cvtdq2pd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTDQ2PD, &dst, &src);
  }
  //! @brief Convert Packed Dword Integers to Packed DP-FP Values (SSE2).
  inline void cvtdq2pd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTDQ2PD, &dst, &src);
  }

  //! @brief Convert Packed Dword Integers to Packed SP-FP Values (SSE2).
  inline void cvtdq2ps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTDQ2PS, &dst, &src);
  }
  //! @brief Convert Packed Dword Integers to Packed SP-FP Values (SSE2).
  inline void cvtdq2ps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTDQ2PS, &dst, &src);
  }

  //! @brief Convert Packed DP-FP Values to Packed Dword Integers (SSE2).
  inline void cvtpd2dq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTPD2DQ, &dst, &src);
  }
  //! @brief Convert Packed DP-FP Values to Packed Dword Integers (SSE2).
  inline void cvtpd2dq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTPD2DQ, &dst, &src);
  }

  //! @brief Convert Packed DP-FP Values to Packed Dword Integers (SSE2).
  inline void cvtpd2pi(const MMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTPD2PI, &dst, &src);
  }
  //! @brief Convert Packed DP-FP Values to Packed Dword Integers (SSE2).
  inline void cvtpd2pi(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTPD2PI, &dst, &src);
  }

  //! @brief Convert Packed DP-FP Values to Packed SP-FP Values (SSE2).
  inline void cvtpd2ps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTPD2PS, &dst, &src);
  }
  //! @brief Convert Packed DP-FP Values to Packed SP-FP Values (SSE2).
  inline void cvtpd2ps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTPD2PS, &dst, &src);
  }

  //! @brief Convert Packed Dword Integers to Packed DP-FP Values (SSE2).
  inline void cvtpi2pd(const XMMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_CVTPI2PD, &dst, &src);
  }
  //! @brief Convert Packed Dword Integers to Packed DP-FP Values (SSE2).
  inline void cvtpi2pd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTPI2PD, &dst, &src);
  }

  //! @brief Convert Packed SP-FP Values to Packed Dword Integers (SSE2).
  inline void cvtps2dq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTPS2DQ, &dst, &src);
  }
  //! @brief Convert Packed SP-FP Values to Packed Dword Integers (SSE2).
  inline void cvtps2dq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTPS2DQ, &dst, &src);
  }

  //! @brief Convert Packed SP-FP Values to Packed DP-FP Values (SSE2).
  inline void cvtps2pd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTPS2PD, &dst, &src);
  }
  //! @brief Convert Packed SP-FP Values to Packed DP-FP Values (SSE2).
  inline void cvtps2pd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTPS2PD, &dst, &src);
  }

  //! @brief Convert Scalar DP-FP Value to Dword Integer (SSE2).
  inline void cvtsd2si(const GPReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTSD2SI, &dst, &src);
  }
  //! @brief Convert Scalar DP-FP Value to Dword Integer (SSE2).
  inline void cvtsd2si(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTSD2SI, &dst, &src);
  }

  //! @brief Convert Scalar DP-FP Value to Scalar SP-FP Value (SSE2).
  inline void cvtsd2ss(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTSD2SS, &dst, &src);
  }
  //! @brief Convert Scalar DP-FP Value to Scalar SP-FP Value (SSE2).
  inline void cvtsd2ss(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTSD2SS, &dst, &src);
  }

  //! @brief Convert Dword Integer to Scalar DP-FP Value (SSE2).
  inline void cvtsi2sd(const XMMReg& dst, const GPReg& src)
  {
    _emitInstruction(INST_CVTSI2SD, &dst, &src);
  }
  //! @brief Convert Dword Integer to Scalar DP-FP Value (SSE2).
  inline void cvtsi2sd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTSI2SD, &dst, &src);
  }

  //! @brief Convert Scalar SP-FP Value to Scalar DP-FP Value (SSE2).
  inline void cvtss2sd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTSS2SD, &dst, &src);
  }
  //! @brief Convert Scalar SP-FP Value to Scalar DP-FP Value (SSE2).
  inline void cvtss2sd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTSS2SD, &dst, &src);
  }

  //! @brief Convert with Truncation Packed DP-FP Values to Packed Dword Integers (SSE2).
  inline void cvttpd2pi(const MMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTTPD2PI, &dst, &src);
  }
  //! @brief Convert with Truncation Packed DP-FP Values to Packed Dword Integers (SSE2).
  inline void cvttpd2pi(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTTPD2PI, &dst, &src);
  }

  //! @brief Convert with Truncation Packed DP-FP Values to Packed Dword Integers (SSE2).
  inline void cvttpd2dq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTTPD2DQ, &dst, &src);
  }
  //! @brief Convert with Truncation Packed DP-FP Values to Packed Dword Integers (SSE2).
  inline void cvttpd2dq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTTPD2DQ, &dst, &src);
  }

  //! @brief Convert with Truncation Packed SP-FP Values to Packed Dword Integers (SSE2).
  inline void cvttps2dq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTTPS2DQ, &dst, &src);
  }
  //! @brief Convert with Truncation Packed SP-FP Values to Packed Dword Integers (SSE2).
  inline void cvttps2dq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTTPS2DQ, &dst, &src);
  }

  //! @brief Convert with Truncation Scalar DP-FP Value to Signed Dword Integer (SSE2).
  inline void cvttsd2si(const GPReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_CVTTSD2SI, &dst, &src);
  }
  //! @brief Convert with Truncation Scalar DP-FP Value to Signed Dword Integer (SSE2).
  inline void cvttsd2si(const GPReg& dst, const Mem& src)
  {
    _emitInstruction(INST_CVTTSD2SI, &dst, &src);
  }

  //! @brief Packed DP-FP Divide (SSE2).
  inline void divpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_DIVPD, &dst, &src);
  }
  //! @brief Packed DP-FP Divide (SSE2).
  inline void divpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_DIVPD, &dst, &src);
  }

  //! @brief Scalar DP-FP Divide (SSE2).
  inline void divsd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_DIVSD, &dst, &src);
  }
  //! @brief Scalar DP-FP Divide (SSE2).
  inline void divsd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_DIVSD, &dst, &src);
  }

  //! @brief Load Fence (SSE2).
  inline void lfence()
  {
    _emitInstruction(INST_LFENCE);
  }

  //! @brief Store Selected Bytes of Double Quadword (SSE2).
  //!
  //! @note Target is DS:EDI.
  inline void maskmovdqu(const XMMReg& src, const XMMReg& mask)
  {
    _emitInstruction(INST_MASKMOVDQU, &src, &mask);
  }

  //! @brief Return Maximum Packed Double-Precision FP Values (SSE2).
  inline void maxpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MAXPD, &dst, &src);
  }
  //! @brief Return Maximum Packed Double-Precision FP Values (SSE2).
  inline void maxpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MAXPD, &dst, &src);
  }

  //! @brief Return Maximum Scalar Double-Precision FP Value (SSE2).
  inline void maxsd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MAXSD, &dst, &src);
  }
  //! @brief Return Maximum Scalar Double-Precision FP Value (SSE2).
  inline void maxsd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MAXSD, &dst, &src);
  }

  //! @brief Memory Fence (SSE2).
  inline void mfence()
  {
    _emitInstruction(INST_MFENCE);
  }

  //! @brief Return Minimum Packed DP-FP Values (SSE2).
  inline void minpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MINPD, &dst, &src);
  }
  //! @brief Return Minimum Packed DP-FP Values (SSE2).
  inline void minpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MINPD, &dst, &src);
  }

  //! @brief Return Minimum Scalar DP-FP Value (SSE2).
  inline void minsd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MINSD, &dst, &src);
  }
  //! @brief Return Minimum Scalar DP-FP Value (SSE2).
  inline void minsd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MINSD, &dst, &src);
  }

  //! @brief Move Aligned DQWord (SSE2).
  inline void movdqa(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVDQA, &dst, &src);
  }
  //! @brief Move Aligned DQWord (SSE2).
  inline void movdqa(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVDQA, &dst, &src);
  }

  //! @brief Move Aligned DQWord (SSE2).
  inline void movdqa(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVDQA, &dst, &src);
  }

  //! @brief Move Unaligned Double Quadword (SSE2).
  inline void movdqu(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVDQU, &dst, &src);
  }
  //! @brief Move Unaligned Double Quadword (SSE2).
  inline void movdqu(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVDQU, &dst, &src);
  }

  //! @brief Move Unaligned Double Quadword (SSE2).
  inline void movdqu(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVDQU, &dst, &src);
  }

  //! @brief Extract Packed SP-FP Sign Mask (SSE2).
  inline void movmskps(const GPReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVMSKPS, &dst, &src);
  }

  //! @brief Extract Packed DP-FP Sign Mask (SSE2).
  inline void movmskpd(const GPReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVMSKPD, &dst, &src);
  }

  //! @brief Move Scalar Double-Precision FP Value (SSE2).
  inline void movsd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVSD, &dst, &src);
  }
  //! @brief Move Scalar Double-Precision FP Value (SSE2).
  inline void movsd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVSD, &dst, &src);
  }

  //! @brief Move Scalar Double-Precision FP Value (SSE2).
  inline void movsd(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVSD, &dst, &src);
  }

  //! @brief Move Aligned Packed Double-Precision FP Values (SSE2).
  inline void movapd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVAPD, &dst, &src);
  }

  //! @brief Move Aligned Packed Double-Precision FP Values (SSE2).
  inline void movapd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVAPD, &dst, &src);
  }

  //! @brief Move Aligned Packed Double-Precision FP Values (SSE2).
  inline void movapd(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVAPD, &dst, &src);
  }

  //! @brief Move Quadword from XMM to MMX Technology Register (SSE2).
  inline void movdq2q(const MMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVDQ2Q, &dst, &src);
  }

  //! @brief Move Quadword from MMX Technology to XMM Register (SSE2).
  inline void movq2dq(const XMMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_MOVQ2DQ, &dst, &src);
  }

  //! @brief Move High Packed Double-Precision FP Value (SSE2).
  inline void movhpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVHPD, &dst, &src);
  }

  //! @brief Move High Packed Double-Precision FP Value (SSE2).
  inline void movhpd(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVHPD, &dst, &src);
  }

  //! @brief Move Low Packed Double-Precision FP Value (SSE2).
  inline void movlpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVLPD, &dst, &src);
  }

  //! @brief Move Low Packed Double-Precision FP Value (SSE2).
  inline void movlpd(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVLPD, &dst, &src);
  }

  //! @brief Store Double Quadword Using Non-Temporal Hint (SSE2).
  inline void movntdq(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVNTDQ, &dst, &src);
  }

  //! @brief Store Store DWORD Using Non-Temporal Hint (SSE2).
  inline void movnti(const Mem& dst, const GPReg& src)
  {
    _emitInstruction(INST_MOVNTI, &dst, &src);
  }

  //! @brief Store Packed Double-Precision FP Values Using Non-Temporal Hint (SSE2).
  inline void movntpd(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVNTPD, &dst, &src);
  }

  //! @brief Move Unaligned Packed Double-Precision FP Values (SSE2).
  inline void movupd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVUPD, &dst, &src);
  }

  //! @brief Move Unaligned Packed Double-Precision FP Values (SSE2).
  inline void movupd(const Mem& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVUPD, &dst, &src);
  }

  //! @brief Packed DP-FP Multiply (SSE2).
  inline void mulpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MULPD, &dst, &src);
  }
  //! @brief Packed DP-FP Multiply (SSE2).
  inline void mulpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MULPD, &dst, &src);
  }

  //! @brief Scalar DP-FP Multiply (SSE2).
  inline void mulsd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MULSD, &dst, &src);
  }
  //! @brief Scalar DP-FP Multiply (SSE2).
  inline void mulsd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MULSD, &dst, &src);
  }

  //! @brief Bit-wise Logical OR for DP-FP Data (SSE2).
  inline void orpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_ORPD, &dst, &src);
  }
  //! @brief Bit-wise Logical OR for DP-FP Data (SSE2).
  inline void orpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ORPD, &dst, &src);
  }

  //! @brief Pack with Signed Saturation (SSE2).
  inline void packsswb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PACKSSWB, &dst, &src);
  }
  //! @brief Pack with Signed Saturation (SSE2).
  inline void packsswb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PACKSSWB, &dst, &src);
  }

  //! @brief Pack with Signed Saturation (SSE2).
  inline void packssdw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PACKSSDW, &dst, &src);
  }
  //! @brief Pack with Signed Saturation (SSE2).
  inline void packssdw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PACKSSDW, &dst, &src);
  }

  //! @brief Pack with Unsigned Saturation (SSE2).
  inline void packuswb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PACKUSWB, &dst, &src);
  }
  //! @brief Pack with Unsigned Saturation (SSE2).
  inline void packuswb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PACKUSWB, &dst, &src);
  }

  //! @brief Packed BYTE Add (SSE2).
  inline void paddb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PADDB, &dst, &src);
  }
  //! @brief Packed BYTE Add (SSE2).
  inline void paddb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDB, &dst, &src);
  }

  //! @brief Packed WORD Add (SSE2).
  inline void paddw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PADDW, &dst, &src);
  }
  //! @brief Packed WORD Add (SSE2).
  inline void paddw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDW, &dst, &src);
  }

  //! @brief Packed DWORD Add (SSE2).
  inline void paddd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PADDD, &dst, &src);
  }
  //! @brief Packed DWORD Add (SSE2).
  inline void paddd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDD, &dst, &src);
  }

  //! @brief Packed QWORD Add (SSE2).
  inline void paddq(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PADDQ, &dst, &src);
  }
  //! @brief Packed QWORD Add (SSE2).
  inline void paddq(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDQ, &dst, &src);
  }

  //! @brief Packed QWORD Add (SSE2).
  inline void paddq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PADDQ, &dst, &src);
  }
  //! @brief Packed QWORD Add (SSE2).
  inline void paddq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDQ, &dst, &src);
  }

  //! @brief Packed Add with Saturation (SSE2).
  inline void paddsb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PADDSB, &dst, &src);
  }
  //! @brief Packed Add with Saturation (SSE2).
  inline void paddsb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDSB, &dst, &src);
  }

  //! @brief Packed Add with Saturation (SSE2).
  inline void paddsw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PADDSW, &dst, &src);
  }
  //! @brief Packed Add with Saturation (SSE2).
  inline void paddsw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDSW, &dst, &src);
  }

  //! @brief Packed Add Unsigned with Saturation (SSE2).
  inline void paddusb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PADDUSB, &dst, &src);
  }
  //! @brief Packed Add Unsigned with Saturation (SSE2).
  inline void paddusb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDUSB, &dst, &src);
  }

  //! @brief Packed Add Unsigned with Saturation (SSE2).
  inline void paddusw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PADDUSW, &dst, &src);
  }
  //! @brief Packed Add Unsigned with Saturation (SSE2).
  inline void paddusw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PADDUSW, &dst, &src);
  }

  //! @brief Logical AND (SSE2).
  inline void pand(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PAND, &dst, &src);
  }
  //! @brief Logical AND (SSE2).
  inline void pand(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PAND, &dst, &src);
  }

  //! @brief Logical AND Not (SSE2).
  inline void pandn(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PANDN, &dst, &src);
  }
  //! @brief Logical AND Not (SSE2).
  inline void pandn(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PANDN, &dst, &src);
  }

  //! @brief Spin Loop Hint (SSE2).
  inline void pause()
  {
    _emitInstruction(INST_PAUSE);
  }

  //! @brief Packed Average (SSE2).
  inline void pavgb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PAVGB, &dst, &src);
  }
  //! @brief Packed Average (SSE2).
  inline void pavgb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PAVGB, &dst, &src);
  }

  //! @brief Packed Average (SSE2).
  inline void pavgw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PAVGW, &dst, &src);
  }
  //! @brief Packed Average (SSE2).
  inline void pavgw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PAVGW, &dst, &src);
  }

  //! @brief Packed Compare for Equal (BYTES) (SSE2).
  inline void pcmpeqb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PCMPEQB, &dst, &src);
  }
  //! @brief Packed Compare for Equal (BYTES) (SSE2).
  inline void pcmpeqb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPEQB, &dst, &src);
  }

  //! @brief Packed Compare for Equal (WORDS) (SSE2).
  inline void pcmpeqw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PCMPEQW, &dst, &src);
  }
  //! @brief Packed Compare for Equal (WORDS) (SSE2).
  inline void pcmpeqw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPEQW, &dst, &src);
  }

  //! @brief Packed Compare for Equal (DWORDS) (SSE2).
  inline void pcmpeqd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PCMPEQD, &dst, &src);
  }
  //! @brief Packed Compare for Equal (DWORDS) (SSE2).
  inline void pcmpeqd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPEQD, &dst, &src);
  }

  //! @brief Packed Compare for Greater Than (BYTES) (SSE2).
  inline void pcmpgtb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PCMPGTB, &dst, &src);
  }
  //! @brief Packed Compare for Greater Than (BYTES) (SSE2).
  inline void pcmpgtb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPGTB, &dst, &src);
  }

  //! @brief Packed Compare for Greater Than (WORDS) (SSE2).
  inline void pcmpgtw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PCMPGTW, &dst, &src);
  }
  //! @brief Packed Compare for Greater Than (WORDS) (SSE2).
  inline void pcmpgtw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPGTW, &dst, &src);
  }

  //! @brief Packed Compare for Greater Than (DWORDS) (SSE2).
  inline void pcmpgtd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PCMPGTD, &dst, &src);
  }
  //! @brief Packed Compare for Greater Than (DWORDS) (SSE2).
  inline void pcmpgtd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPGTD, &dst, &src);
  }

  //! @brief Packed Signed Integer Word Maximum (SSE2).
  inline void pmaxsw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMAXSW, &dst, &src);
  }
  //! @brief Packed Signed Integer Word Maximum (SSE2).
  inline void pmaxsw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMAXSW, &dst, &src);
  }

  //! @brief Packed Unsigned Integer Byte Maximum (SSE2).
  inline void pmaxub(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMAXUB, &dst, &src);
  }
  //! @brief Packed Unsigned Integer Byte Maximum (SSE2).
  inline void pmaxub(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMAXUB, &dst, &src);
  }

  //! @brief Packed Signed Integer Word Minimum (SSE2).
  inline void pminsw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMINSW, &dst, &src);
  }
  //! @brief Packed Signed Integer Word Minimum (SSE2).
  inline void pminsw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMINSW, &dst, &src);
  }

  //! @brief Packed Unsigned Integer Byte Minimum (SSE2).
  inline void pminub(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMINUB, &dst, &src);
  }
  //! @brief Packed Unsigned Integer Byte Minimum (SSE2).
  inline void pminub(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMINUB, &dst, &src);
  }

  //! @brief Move Byte Mask (SSE2).
  inline void pmovmskb(const GPReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVMSKB, &dst, &src);
  }

  //! @brief Packed Multiply High (SSE2).
  inline void pmulhw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMULHW, &dst, &src);
  }
  //! @brief Packed Multiply High (SSE2).
  inline void pmulhw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMULHW, &dst, &src);
  }

  //! @brief Packed Multiply High Unsigned (SSE2).
  inline void pmulhuw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMULHUW, &dst, &src);
  }
  //! @brief Packed Multiply High Unsigned (SSE2).
  inline void pmulhuw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMULHUW, &dst, &src);
  }

  //! @brief Packed Multiply Low (SSE2).
  inline void pmullw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMULLW, &dst, &src);
  }
  //! @brief Packed Multiply Low (SSE2).
  inline void pmullw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMULLW, &dst, &src);
  }

  //! @brief Packed Multiply to QWORD (SSE2).
  inline void pmuludq(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PMULUDQ, &dst, &src);
  }
  //! @brief Packed Multiply to QWORD (SSE2).
  inline void pmuludq(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMULUDQ, &dst, &src);
  }

  //! @brief Packed Multiply to QWORD (SSE2).
  inline void pmuludq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMULUDQ, &dst, &src);
  }
  //! @brief Packed Multiply to QWORD (SSE2).
  inline void pmuludq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMULUDQ, &dst, &src);
  }

  //! @brief Bitwise Logical OR (SSE2).
  inline void por(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_POR, &dst, &src);
  }
  //! @brief Bitwise Logical OR (SSE2).
  inline void por(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_POR, &dst, &src);
  }

  //! @brief Packed Shift Left Logical (SSE2).
  inline void pslld(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSLLD, &dst, &src);
  }
  //! @brief Packed Shift Left Logical (SSE2).
  inline void pslld(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSLLD, &dst, &src);
  }
  //! @brief Packed Shift Left Logical (SSE2).
  inline void pslld(const XMMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSLLD, &dst, &src);
  }

  //! @brief Packed Shift Left Logical (SSE2).
  inline void psllq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSLLQ, &dst, &src);
  }
  //! @brief Packed Shift Left Logical (SSE2).
  inline void psllq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSLLQ, &dst, &src);
  }
  //! @brief Packed Shift Left Logical (SSE2).
  inline void psllq(const XMMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSLLQ, &dst, &src);
  }

  //! @brief Packed Shift Left Logical (SSE2).
  inline void psllw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSLLW, &dst, &src);
  }
  //! @brief Packed Shift Left Logical (SSE2).
  inline void psllw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSLLW, &dst, &src);
  }
  //! @brief Packed Shift Left Logical (SSE2).
  inline void psllw(const XMMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSLLW, &dst, &src);
  }

  //! @brief Packed Shift Left Logical (SSE2).
  inline void pslldq(const XMMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSLLDQ, &dst, &src);
  }

  //! @brief Packed Shift Right Arithmetic (SSE2).
  inline void psrad(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSRAD, &dst, &src);
  }
  //! @brief Packed Shift Right Arithmetic (SSE2).
  inline void psrad(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSRAD, &dst, &src);
  }
  //! @brief Packed Shift Right Arithmetic (SSE2).
  inline void psrad(const XMMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSRAD, &dst, &src);
  }

  //! @brief Packed Shift Right Arithmetic (SSE2).
  inline void psraw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSRAW, &dst, &src);
  }
  //! @brief Packed Shift Right Arithmetic (SSE2).
  inline void psraw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSRAW, &dst, &src);
  }
  //! @brief Packed Shift Right Arithmetic (SSE2).
  inline void psraw(const XMMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSRAW, &dst, &src);
  }

  //! @brief Packed Subtract (SSE2).
  inline void psubb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSUBB, &dst, &src);
  }
  //! @brief Packed Subtract (SSE2).
  inline void psubb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBB, &dst, &src);
  }

  //! @brief Packed Subtract (SSE2).
  inline void psubw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSUBW, &dst, &src);
  }
  //! @brief Packed Subtract (SSE2).
  inline void psubw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBW, &dst, &src);
  }

  //! @brief Packed Subtract (SSE2).
  inline void psubd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSUBD, &dst, &src);
  }
  //! @brief Packed Subtract (SSE2).
  inline void psubd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBD, &dst, &src);
  }

  //! @brief Packed Subtract (SSE2).
  inline void psubq(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSUBQ, &dst, &src);
  }
  //! @brief Packed Subtract (SSE2).
  inline void psubq(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBQ, &dst, &src);
  }

  //! @brief Packed Subtract (SSE2).
  inline void psubq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSUBQ, &dst, &src);
  }
  //! @brief Packed Subtract (SSE2).
  inline void psubq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBQ, &dst, &src);
  }

  //! @brief Packed Multiply and Add (SSE2).
  inline void pmaddwd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMADDWD, &dst, &src);
  }
  //! @brief Packed Multiply and Add (SSE2).
  inline void pmaddwd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMADDWD, &dst, &src);
  }

  //! @brief Shuffle Packed DWORDs (SSE2).
  inline void pshufd(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PSHUFD, &dst, &src, &imm8);
  }
  //! @brief Shuffle Packed DWORDs (SSE2).
  inline void pshufd(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PSHUFD, &dst, &src, &imm8);
  }

  //! @brief Shuffle Packed High Words (SSE2).
  inline void pshufhw(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PSHUFHW, &dst, &src, &imm8);
  }
  //! @brief Shuffle Packed High Words (SSE2).
  inline void pshufhw(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PSHUFHW, &dst, &src, &imm8);
  }

  //! @brief Shuffle Packed Low Words (SSE2).
  inline void pshuflw(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PSHUFLW, &dst, &src, &imm8);
  }
  //! @brief Shuffle Packed Low Words (SSE2).
  inline void pshuflw(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PSHUFLW, &dst, &src, &imm8);
  }

  //! @brief Packed Shift Right Logical (SSE2).
  inline void psrld(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSRLD, &dst, &src);
  }
  //! @brief Packed Shift Right Logical (SSE2).
  inline void psrld(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSRLD, &dst, &src);
  }
  //! @brief Packed Shift Right Logical (SSE2).
  inline void psrld(const XMMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSRLD, &dst, &src);
  }

  //! @brief Packed Shift Right Logical (SSE2).
  inline void psrlq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSRLQ, &dst, &src);
  }
  //! @brief Packed Shift Right Logical (SSE2).
  inline void psrlq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSRLQ, &dst, &src);
  }
  //! @brief Packed Shift Right Logical (SSE2).
  inline void psrlq(const XMMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSRLQ, &dst, &src);
  }

  //! @brief DQWord Shift Right Logical (MMX).
  inline void psrldq(const XMMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSRLDQ, &dst, &src);
  }

  //! @brief Packed Shift Right Logical (SSE2).
  inline void psrlw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSRLW, &dst, &src);
  }
  //! @brief Packed Shift Right Logical (SSE2).
  inline void psrlw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSRLW, &dst, &src);
  }
  //! @brief Packed Shift Right Logical (SSE2).
  inline void psrlw(const XMMReg& dst, const Imm& src)
  {
    _emitInstruction(INST_PSRLW, &dst, &src);
  }

  //! @brief Packed Subtract with Saturation (SSE2).
  inline void psubsb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSUBSB, &dst, &src);
  }
  //! @brief Packed Subtract with Saturation (SSE2).
  inline void psubsb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBSB, &dst, &src);
  }

  //! @brief Packed Subtract with Saturation (SSE2).
  inline void psubsw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSUBSW, &dst, &src);
  }
  //! @brief Packed Subtract with Saturation (SSE2).
  inline void psubsw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBSW, &dst, &src);
  }

  //! @brief Packed Subtract with Unsigned Saturation (SSE2).
  inline void psubusb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSUBUSB, &dst, &src);
  }
  //! @brief Packed Subtract with Unsigned Saturation (SSE2).
  inline void psubusb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBUSB, &dst, &src);
  }

  //! @brief Packed Subtract with Unsigned Saturation (SSE2).
  inline void psubusw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSUBUSW, &dst, &src);
  }
  //! @brief Packed Subtract with Unsigned Saturation (SSE2).
  inline void psubusw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSUBUSW, &dst, &src);
  }

  //! @brief Unpack High Data (SSE2).
  inline void punpckhbw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PUNPCKHBW, &dst, &src);
  }
  //! @brief Unpack High Data (SSE2).
  inline void punpckhbw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKHBW, &dst, &src);
  }

  //! @brief Unpack High Data (SSE2).
  inline void punpckhwd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PUNPCKHWD, &dst, &src);
  }
  //! @brief Unpack High Data (SSE2).
  inline void punpckhwd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKHWD, &dst, &src);
  }

  //! @brief Unpack High Data (SSE2).
  inline void punpckhdq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PUNPCKHDQ, &dst, &src);
  }
  //! @brief Unpack High Data (SSE2).
  inline void punpckhdq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKHDQ, &dst, &src);
  }

  //! @brief Unpack High Data (SSE2).
  inline void punpckhqdq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PUNPCKHQDQ, &dst, &src);
  }
  //! @brief Unpack High Data (SSE2).
  inline void punpckhqdq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKHQDQ, &dst, &src);
  }

  //! @brief Unpack Low Data (SSE2).
  inline void punpcklbw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PUNPCKLBW, &dst, &src);
  }
  //! @brief Unpack Low Data (SSE2).
  inline void punpcklbw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKLBW, &dst, &src);
  }

  //! @brief Unpack Low Data (SSE2).
  inline void punpcklwd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PUNPCKLWD, &dst, &src);
  }
  //! @brief Unpack Low Data (SSE2).
  inline void punpcklwd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKLWD, &dst, &src);
  }

  //! @brief Unpack Low Data (SSE2).
  inline void punpckldq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PUNPCKLDQ, &dst, &src);
  }
  //! @brief Unpack Low Data (SSE2).
  inline void punpckldq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKLDQ, &dst, &src);
  }

  //! @brief Unpack Low Data (SSE2).
  inline void punpcklqdq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PUNPCKLQDQ, &dst, &src);
  }
  //! @brief Unpack Low Data (SSE2).
  inline void punpcklqdq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PUNPCKLQDQ, &dst, &src);
  }

  //! @brief Bitwise Exclusive OR (SSE2).
  inline void pxor(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PXOR, &dst, &src);
  }
  //! @brief Bitwise Exclusive OR (SSE2).
  inline void pxor(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PXOR, &dst, &src);
  }

  //! @brief Shuffle DP-FP (SSE2).
  inline void shufpd(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_SHUFPD, &dst, &src, &imm8);
  }
  //! @brief Shuffle DP-FP (SSE2).
  inline void shufpd(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_SHUFPD, &dst, &src, &imm8);
  }

  //! @brief Compute Square Roots of Packed DP-FP Values (SSE2).
  inline void sqrtpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_SQRTPD, &dst, &src);
  }
  //! @brief Compute Square Roots of Packed DP-FP Values (SSE2).
  inline void sqrtpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_SQRTPD, &dst, &src);
  }

  //! @brief Compute Square Root of Scalar DP-FP Value (SSE2).
  inline void sqrtsd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_SQRTSD, &dst, &src);
  }
  //! @brief Compute Square Root of Scalar DP-FP Value (SSE2).
  inline void sqrtsd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_SQRTSD, &dst, &src);
  }

  //! @brief Packed DP-FP Subtract (SSE2).
  inline void subpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_SUBPD, &dst, &src);
  }
  //! @brief Packed DP-FP Subtract (SSE2).
  inline void subpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_SUBPD, &dst, &src);
  }

  //! @brief Scalar DP-FP Subtract (SSE2).
  inline void subsd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_SUBSD, &dst, &src);
  }
  //! @brief Scalar DP-FP Subtract (SSE2).
  inline void subsd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_SUBSD, &dst, &src);
  }

  //! @brief Scalar Unordered DP-FP Compare and Set EFLAGS (SSE2).
  inline void ucomisd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_UCOMISD, &dst, &src);
  }
  //! @brief Scalar Unordered DP-FP Compare and Set EFLAGS (SSE2).
  inline void ucomisd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_UCOMISD, &dst, &src);
  }

  //! @brief Unpack and Interleave High Packed Double-Precision FP Values (SSE2).
  inline void unpckhpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_UNPCKHPD, &dst, &src);
  }
  //! @brief Unpack and Interleave High Packed Double-Precision FP Values (SSE2).
  inline void unpckhpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_UNPCKHPD, &dst, &src);
  }

  //! @brief Unpack and Interleave Low Packed Double-Precision FP Values (SSE2).
  inline void unpcklpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_UNPCKLPD, &dst, &src);
  }
  //! @brief Unpack and Interleave Low Packed Double-Precision FP Values (SSE2).
  inline void unpcklpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_UNPCKLPD, &dst, &src);
  }

  //! @brief Bit-wise Logical OR for DP-FP Data (SSE2).
  inline void xorpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_XORPD, &dst, &src);
  }
  //! @brief Bit-wise Logical OR for DP-FP Data (SSE2).
  inline void xorpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_XORPD, &dst, &src);
  }

  // --------------------------------------------------------------------------
  // [SSE3]
  // --------------------------------------------------------------------------

  //! @brief Packed DP-FP Add/Subtract (SSE3).
  inline void addsubpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_ADDSUBPD, &dst, &src);
  }
  //! @brief Packed DP-FP Add/Subtract (SSE3).
  inline void addsubpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ADDSUBPD, &dst, &src);
  }

  //! @brief Packed SP-FP Add/Subtract (SSE3).
  inline void addsubps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_ADDSUBPS, &dst, &src);
  }
  //! @brief Packed SP-FP Add/Subtract (SSE3).
  inline void addsubps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_ADDSUBPS, &dst, &src);
  }

  //! @brief Store Integer with Truncation (SSE3).
  inline void fisttp(const Mem& dst)
  {
    _emitInstruction(INST_FISTTP, &dst);
  }

  //! @brief Packed DP-FP Horizontal Add (SSE3).
  inline void haddpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_HADDPD, &dst, &src);
  }
  //! @brief Packed DP-FP Horizontal Add (SSE3).
  inline void haddpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_HADDPD, &dst, &src);
  }

  //! @brief Packed SP-FP Horizontal Add (SSE3).
  inline void haddps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_HADDPS, &dst, &src);
  }
  //! @brief Packed SP-FP Horizontal Add (SSE3).
  inline void haddps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_HADDPS, &dst, &src);
  }

  //! @brief Packed DP-FP Horizontal Subtract (SSE3).
  inline void hsubpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_HSUBPD, &dst, &src);
  }
  //! @brief Packed DP-FP Horizontal Subtract (SSE3).
  inline void hsubpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_HSUBPD, &dst, &src);
  }

  //! @brief Packed SP-FP Horizontal Subtract (SSE3).
  inline void hsubps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_HSUBPS, &dst, &src);
  }
  //! @brief Packed SP-FP Horizontal Subtract (SSE3).
  inline void hsubps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_HSUBPS, &dst, &src);
  }

  //! @brief Load Unaligned Integer 128 Bits (SSE3).
  inline void lddqu(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_LDDQU, &dst, &src);
  }

  //! @brief Set Up Monitor Address (SSE3).
  inline void monitor()
  {
    _emitInstruction(INST_MONITOR);
  }

  //! @brief Move One DP-FP and Duplicate (SSE3).
  inline void movddup(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVDDUP, &dst, &src);
  }
  //! @brief Move One DP-FP and Duplicate (SSE3).
  inline void movddup(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVDDUP, &dst, &src);
  }

  //! @brief Move Packed SP-FP High and Duplicate (SSE3).
  inline void movshdup(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVSHDUP, &dst, &src);
  }
  //! @brief Move Packed SP-FP High and Duplicate (SSE3).
  inline void movshdup(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVSHDUP, &dst, &src);
  }

  //! @brief Move Packed SP-FP Low and Duplicate (SSE3).
  inline void movsldup(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_MOVSLDUP, &dst, &src);
  }
  //! @brief Move Packed SP-FP Low and Duplicate (SSE3).
  inline void movsldup(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVSLDUP, &dst, &src);
  }

  //! @brief Monitor Wait (SSE3).
  inline void mwait()
  {
    _emitInstruction(INST_MWAIT);
  }

  // --------------------------------------------------------------------------
  // [SSSE3]
  // --------------------------------------------------------------------------

  //! @brief Packed SIGN (SSSE3).
  inline void psignb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSIGNB, &dst, &src);
  }
  //! @brief Packed SIGN (SSSE3).
  inline void psignb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSIGNB, &dst, &src);
  }

  //! @brief Packed SIGN (SSSE3).
  inline void psignb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSIGNB, &dst, &src);
  }
  //! @brief Packed SIGN (SSSE3).
  inline void psignb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSIGNB, &dst, &src);
  }

  //! @brief Packed SIGN (SSSE3).
  inline void psignw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSIGNW, &dst, &src);
  }
  //! @brief Packed SIGN (SSSE3).
  inline void psignw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSIGNW, &dst, &src);
  }

  //! @brief Packed SIGN (SSSE3).
  inline void psignw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSIGNW, &dst, &src);
  }
  //! @brief Packed SIGN (SSSE3).
  inline void psignw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSIGNW, &dst, &src);
  }

  //! @brief Packed SIGN (SSSE3).
  inline void psignd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSIGND, &dst, &src);
  }
  //! @brief Packed SIGN (SSSE3).
  inline void psignd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSIGND, &dst, &src);
  }

  //! @brief Packed SIGN (SSSE3).
  inline void psignd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSIGND, &dst, &src);
  }
  //! @brief Packed SIGN (SSSE3).
  inline void psignd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSIGND, &dst, &src);
  }

  //! @brief Packed Horizontal Add (SSSE3).
  inline void phaddw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PHADDW, &dst, &src);
  }
  //! @brief Packed Horizontal Add (SSSE3).
  inline void phaddw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHADDW, &dst, &src);
  }

  //! @brief Packed Horizontal Add (SSSE3).
  inline void phaddw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PHADDW, &dst, &src);
  }
  //! @brief Packed Horizontal Add (SSSE3).
  inline void phaddw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHADDW, &dst, &src);
  }

  //! @brief Packed Horizontal Add (SSSE3).
  inline void phaddd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PHADDD, &dst, &src);
  }
  //! @brief Packed Horizontal Add (SSSE3).
  inline void phaddd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHADDD, &dst, &src);
  }

  //! @brief Packed Horizontal Add (SSSE3).
  inline void phaddd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PHADDD, &dst, &src);
  }
  //! @brief Packed Horizontal Add (SSSE3).
  inline void phaddd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHADDD, &dst, &src);
  }

  //! @brief Packed Horizontal Add and Saturate (SSSE3).
  inline void phaddsw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PHADDSW, &dst, &src);
  }
  //! @brief Packed Horizontal Add and Saturate (SSSE3).
  inline void phaddsw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHADDSW, &dst, &src);
  }

  //! @brief Packed Horizontal Add and Saturate (SSSE3).
  inline void phaddsw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PHADDSW, &dst, &src);
  }
  //! @brief Packed Horizontal Add and Saturate (SSSE3).
  inline void phaddsw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHADDSW, &dst, &src);
  }

  //! @brief Packed Horizontal Subtract (SSSE3).
  inline void phsubw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PHSUBW, &dst, &src);
  }
  //! @brief Packed Horizontal Subtract (SSSE3).
  inline void phsubw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHSUBW, &dst, &src);
  }

  //! @brief Packed Horizontal Subtract (SSSE3).
  inline void phsubw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PHSUBW, &dst, &src);
  }
  //! @brief Packed Horizontal Subtract (SSSE3).
  inline void phsubw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHSUBW, &dst, &src);
  }

  //! @brief Packed Horizontal Subtract (SSSE3).
  inline void phsubd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PHSUBD, &dst, &src);
  }
  //! @brief Packed Horizontal Subtract (SSSE3).
  inline void phsubd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHSUBD, &dst, &src);
  }

  //! @brief Packed Horizontal Subtract (SSSE3).
  inline void phsubd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PHSUBD, &dst, &src);
  }
  //! @brief Packed Horizontal Subtract (SSSE3).
  inline void phsubd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHSUBD, &dst, &src);
  }

  //! @brief Packed Horizontal Subtract and Saturate (SSSE3).
  inline void phsubsw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PHSUBSW, &dst, &src);
  }
  //! @brief Packed Horizontal Subtract and Saturate (SSSE3).
  inline void phsubsw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHSUBSW, &dst, &src);
  }

  //! @brief Packed Horizontal Subtract and Saturate (SSSE3).
  inline void phsubsw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PHSUBSW, &dst, &src);
  }
  //! @brief Packed Horizontal Subtract and Saturate (SSSE3).
  inline void phsubsw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHSUBSW, &dst, &src);
  }

  //! @brief Multiply and Add Packed Signed and Unsigned Bytes (SSSE3).
  inline void pmaddubsw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PMADDUBSW, &dst, &src);
  }
  //! @brief Multiply and Add Packed Signed and Unsigned Bytes (SSSE3).
  inline void pmaddubsw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMADDUBSW, &dst, &src);
  }

  //! @brief Multiply and Add Packed Signed and Unsigned Bytes (SSSE3).
  inline void pmaddubsw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMADDUBSW, &dst, &src);
  }
  //! @brief Multiply and Add Packed Signed and Unsigned Bytes (SSSE3).
  inline void pmaddubsw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMADDUBSW, &dst, &src);
  }

  //! @brief Packed Absolute Value (SSSE3).
  inline void pabsb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PABSB, &dst, &src);
  }
  //! @brief Packed Absolute Value (SSSE3).
  inline void pabsb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PABSB, &dst, &src);
  }

  //! @brief Packed Absolute Value (SSSE3).
  inline void pabsb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PABSB, &dst, &src);
  }
  //! @brief Packed Absolute Value (SSSE3).
  inline void pabsb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PABSB, &dst, &src);
  }

  //! @brief Packed Absolute Value (SSSE3).
  inline void pabsw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PABSW, &dst, &src);
  }
  //! @brief Packed Absolute Value (SSSE3).
  inline void pabsw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PABSW, &dst, &src);
  }

  //! @brief Packed Absolute Value (SSSE3).
  inline void pabsw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PABSW, &dst, &src);
  }
  //! @brief Packed Absolute Value (SSSE3).
  inline void pabsw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PABSW, &dst, &src);
  }

  //! @brief Packed Absolute Value (SSSE3).
  inline void pabsd(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PABSD, &dst, &src);
  }
  //! @brief Packed Absolute Value (SSSE3).
  inline void pabsd(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PABSD, &dst, &src);
  }

  //! @brief Packed Absolute Value (SSSE3).
  inline void pabsd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PABSD, &dst, &src);
  }
  //! @brief Packed Absolute Value (SSSE3).
  inline void pabsd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PABSD, &dst, &src);
  }

  //! @brief Packed Multiply High with Round and Scale (SSSE3).
  inline void pmulhrsw(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PMULHRSW, &dst, &src);
  }
  //! @brief Packed Multiply High with Round and Scale (SSSE3).
  inline void pmulhrsw(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMULHRSW, &dst, &src);
  }

  //! @brief Packed Multiply High with Round and Scale (SSSE3).
  inline void pmulhrsw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMULHRSW, &dst, &src);
  }
  //! @brief Packed Multiply High with Round and Scale (SSSE3).
  inline void pmulhrsw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMULHRSW, &dst, &src);
  }

  //! @brief Packed Shuffle Bytes (SSSE3).
  inline void pshufb(const MMReg& dst, const MMReg& src)
  {
    _emitInstruction(INST_PSHUFB, &dst, &src);
  }
  //! @brief Packed Shuffle Bytes (SSSE3).
  inline void pshufb(const MMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSHUFB, &dst, &src);
  }

  //! @brief Packed Shuffle Bytes (SSSE3).
  inline void pshufb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PSHUFB, &dst, &src);
  }
  //! @brief Packed Shuffle Bytes (SSSE3).
  inline void pshufb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PSHUFB, &dst, &src);
  }

  //! @brief Packed Shuffle Bytes (SSSE3).
  inline void palignr(const MMReg& dst, const MMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PALIGNR, &dst, &src, &imm8);
  }
  //! @brief Packed Shuffle Bytes (SSSE3).
  inline void palignr(const MMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PALIGNR, &dst, &src, &imm8);
  }

  //! @brief Packed Shuffle Bytes (SSSE3).
  inline void palignr(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PALIGNR, &dst, &src, &imm8);
  }
  //! @brief Packed Shuffle Bytes (SSSE3).
  inline void palignr(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PALIGNR, &dst, &src, &imm8);
  }

  // --------------------------------------------------------------------------
  // [SSE4.1]
  // --------------------------------------------------------------------------

  //! @brief Blend Packed DP-FP Values (SSE4.1).
  inline void blendpd(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_BLENDPD, &dst, &src, &imm8);
  }
  //! @brief Blend Packed DP-FP Values (SSE4.1).
  inline void blendpd(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_BLENDPD, &dst, &src, &imm8);
  }

  //! @brief Blend Packed SP-FP Values (SSE4.1).
  inline void blendps(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_BLENDPS, &dst, &src, &imm8);
  }
  //! @brief Blend Packed SP-FP Values (SSE4.1).
  inline void blendps(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_BLENDPS, &dst, &src, &imm8);
  }

  //! @brief Variable Blend Packed DP-FP Values (SSE4.1).
  inline void blendvpd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_BLENDVPD, &dst, &src);
  }
  //! @brief Variable Blend Packed DP-FP Values (SSE4.1).
  inline void blendvpd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_BLENDVPD, &dst, &src);
  }

  //! @brief Variable Blend Packed SP-FP Values (SSE4.1).
  inline void blendvps(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_BLENDVPS, &dst, &src);
  }
  //! @brief Variable Blend Packed SP-FP Values (SSE4.1).
  inline void blendvps(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_BLENDVPS, &dst, &src);
  }

  //! @brief Dot Product of Packed DP-FP Values (SSE4.1).
  inline void dppd(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_DPPD, &dst, &src, &imm8);
  }
  //! @brief Dot Product of Packed DP-FP Values (SSE4.1).
  inline void dppd(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_DPPD, &dst, &src, &imm8);
  }

  //! @brief Dot Product of Packed SP-FP Values (SSE4.1).
  inline void dpps(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_DPPS, &dst, &src, &imm8);
  }
  //! @brief Dot Product of Packed SP-FP Values (SSE4.1).
  inline void dpps(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_DPPS, &dst, &src, &imm8);
  }

  //! @brief Extract Packed SP-FP Value (SSE4.1).
  inline void extractps(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_EXTRACTPS, &dst, &src, &imm8);
  }
  //! @brief Extract Packed SP-FP Value (SSE4.1).
  inline void extractps(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_EXTRACTPS, &dst, &src, &imm8);
  }

  //! @brief Load Double Quadword Non-Temporal Aligned Hint (SSE4.1).
  inline void movntdqa(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_MOVNTDQA, &dst, &src);
  }

  //! @brief Compute Multiple Packed Sums of Absolute Difference (SSE4.1).
  inline void mpsadbw(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_MPSADBW, &dst, &src, &imm8);
  }
  //! @brief Compute Multiple Packed Sums of Absolute Difference (SSE4.1).
  inline void mpsadbw(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_MPSADBW, &dst, &src, &imm8);
  }

  //! @brief Pack with Unsigned Saturation (SSE4.1).
  inline void packusdw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PACKUSDW, &dst, &src);
  }
  //! @brief Pack with Unsigned Saturation (SSE4.1).
  inline void packusdw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PACKUSDW, &dst, &src);
  }

  //! @brief Variable Blend Packed Bytes (SSE4.1).
  inline void pblendvb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PBLENDVB, &dst, &src);
  }
  //! @brief Variable Blend Packed Bytes (SSE4.1).
  inline void pblendvb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PBLENDVB, &dst, &src);
  }

  //! @brief Blend Packed Words (SSE4.1).
  inline void pblendw(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PBLENDW, &dst, &src, &imm8);
  }
  //! @brief Blend Packed Words (SSE4.1).
  inline void pblendw(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PBLENDW, &dst, &src, &imm8);
  }

  //! @brief Compare Packed Qword Data for Equal (SSE4.1).
  inline void pcmpeqq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PCMPEQQ, &dst, &src);
  }
  //! @brief Compare Packed Qword Data for Equal (SSE4.1).
  inline void pcmpeqq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPEQQ, &dst, &src);
  }

  //! @brief Extract Byte (SSE4.1).
  inline void pextrb(const GPReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PEXTRB, &dst, &src, &imm8);
  }
  //! @brief Extract Byte (SSE4.1).
  inline void pextrb(const Mem& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PEXTRB, &dst, &src, &imm8);
  }

  //! @brief Extract Dword (SSE4.1).
  inline void pextrd(const GPReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PEXTRD, &dst, &src, &imm8);
  }
  //! @brief Extract Dword (SSE4.1).
  inline void pextrd(const Mem& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PEXTRD, &dst, &src, &imm8);
  }

  //! @brief Extract Dword (SSE4.1).
  inline void pextrq(const GPReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PEXTRQ, &dst, &src, &imm8);
  }
  //! @brief Extract Dword (SSE4.1).
  inline void pextrq(const Mem& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PEXTRQ, &dst, &src, &imm8);
  }

  //! @brief Extract Word (SSE4.1).
  inline void pextrw(const GPReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PEXTRW, &dst, &src, &imm8);
  }
  //! @brief Extract Word (SSE4.1).
  inline void pextrw(const Mem& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PEXTRW, &dst, &src, &imm8);
  }

  //! @brief Packed Horizontal Word Minimum (SSE4.1).
  inline void phminposuw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PHMINPOSUW, &dst, &src);
  }
  //! @brief Packed Horizontal Word Minimum (SSE4.1).
  inline void phminposuw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PHMINPOSUW, &dst, &src);
  }

  //! @brief Insert Byte (SSE4.1).
  inline void pinsrb(const XMMReg& dst, const GPReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PINSRB, &dst, &src, &imm8);
  }
  //! @brief Insert Byte (SSE4.1).
  inline void pinsrb(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PINSRB, &dst, &src, &imm8);
  }

  //! @brief Insert Dword (SSE4.1).
  inline void pinsrd(const XMMReg& dst, const GPReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PINSRD, &dst, &src, &imm8);
  }
  //! @brief Insert Dword (SSE4.1).
  inline void pinsrd(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PINSRD, &dst, &src, &imm8);
  }

  //! @brief Insert Dword (SSE4.1).
  inline void pinsrq(const XMMReg& dst, const GPReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PINSRQ, &dst, &src, &imm8);
  }
  //! @brief Insert Dword (SSE4.1).
  inline void pinsrq(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PINSRQ, &dst, &src, &imm8);
  }

  //! @brief Insert Word (SSE2).
  inline void pinsrw(const XMMReg& dst, const GPReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PINSRW, &dst, &src, &imm8);
  }
  //! @brief Insert Word (SSE2).
  inline void pinsrw(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PINSRW, &dst, &src, &imm8);
  }

  //! @brief Maximum of Packed Word Integers (SSE4.1).
  inline void pmaxuw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMAXUW, &dst, &src);
  }
  //! @brief Maximum of Packed Word Integers (SSE4.1).
  inline void pmaxuw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMAXUW, &dst, &src);
  }

  //! @brief Maximum of Packed Signed Byte Integers (SSE4.1).
  inline void pmaxsb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMAXSB, &dst, &src);
  }
  //! @brief Maximum of Packed Signed Byte Integers (SSE4.1).
  inline void pmaxsb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMAXSB, &dst, &src);
  }

  //! @brief Maximum of Packed Signed Dword Integers (SSE4.1).
  inline void pmaxsd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMAXSD, &dst, &src);
  }
  //! @brief Maximum of Packed Signed Dword Integers (SSE4.1).
  inline void pmaxsd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMAXSD, &dst, &src);
  }

  //! @brief Maximum of Packed Unsigned Dword Integers (SSE4.1).
  inline void pmaxud(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMAXUD, &dst, &src);
  }
  //! @brief Maximum of Packed Unsigned Dword Integers (SSE4.1).
  inline void pmaxud(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMAXUD, &dst, &src);
  }

  //! @brief Minimum of Packed Signed Byte Integers (SSE4.1).
  inline void pminsb(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMINSB, &dst, &src);
  }
  //! @brief Minimum of Packed Signed Byte Integers (SSE4.1).
  inline void pminsb(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMINSB, &dst, &src);
  }

  //! @brief Minimum of Packed Word Integers (SSE4.1).
  inline void pminuw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMINUW, &dst, &src);
  }
  //! @brief Minimum of Packed Word Integers (SSE4.1).
  inline void pminuw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMINUW, &dst, &src);
  }

  //! @brief Minimum of Packed Dword Integers (SSE4.1).
  inline void pminud(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMINUD, &dst, &src);
  }
  //! @brief Minimum of Packed Dword Integers (SSE4.1).
  inline void pminud(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMINUD, &dst, &src);
  }

  //! @brief Minimum of Packed Dword Integers (SSE4.1).
  inline void pminsd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMINSD, &dst, &src);
  }
  //! @brief Minimum of Packed Dword Integers (SSE4.1).
  inline void pminsd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMINSD, &dst, &src);
  }

  //! @brief Packed Move with Sign Extend (SSE4.1).
  inline void pmovsxbw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVSXBW, &dst, &src);
  }
  //! @brief Packed Move with Sign Extend (SSE4.1).
  inline void pmovsxbw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMOVSXBW, &dst, &src);
  }

  //! @brief Packed Move with Sign Extend (SSE4.1).
  inline void pmovsxbd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVSXBD, &dst, &src);
  }
  //! @brief Packed Move with Sign Extend (SSE4.1).
  inline void pmovsxbd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMOVSXBD, &dst, &src);
  }

  //! @brief Packed Move with Sign Extend (SSE4.1).
  inline void pmovsxbq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVSXBQ, &dst, &src);
  }
  //! @brief Packed Move with Sign Extend (SSE4.1).
  inline void pmovsxbq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMOVSXBQ, &dst, &src);
  }

  //! @brief Packed Move with Sign Extend (SSE4.1).
  inline void pmovsxwd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVSXWD, &dst, &src);
  }
  //! @brief Packed Move with Sign Extend (SSE4.1).
  inline void pmovsxwd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMOVSXWD, &dst, &src);
  }

  //! @brief (SSE4.1).
  inline void pmovsxwq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVSXWQ, &dst, &src);
  }
  //! @brief (SSE4.1).
  inline void pmovsxwq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMOVSXWQ, &dst, &src);
  }

  //! @brief (SSE4.1).
  inline void pmovsxdq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVSXDQ, &dst, &src);
  }
  //! @brief (SSE4.1).
  inline void pmovsxdq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMOVSXDQ, &dst, &src);
  }

  //! @brief Packed Move with Zero Extend (SSE4.1).
  inline void pmovzxbw(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVZXBW, &dst, &src);
  }
  //! @brief Packed Move with Zero Extend (SSE4.1).
  inline void pmovzxbw(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMOVZXBW, &dst, &src);
  }

  //! @brief Packed Move with Zero Extend (SSE4.1).
  inline void pmovzxbd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVZXBD, &dst, &src);
  }
  //! @brief Packed Move with Zero Extend (SSE4.1).
  inline void pmovzxbd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMOVZXBD, &dst, &src);
  }

  //! @brief Packed Move with Zero Extend (SSE4.1).
  inline void pmovzxbq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVZXBQ, &dst, &src);
  }
  //! @brief Packed Move with Zero Extend (SSE4.1).
  inline void pmovzxbq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMOVZXBQ, &dst, &src);
  }

  //! @brief Packed Move with Zero Extend (SSE4.1).
  inline void pmovzxwd(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVZXWD, &dst, &src);
  }
  //! @brief Packed Move with Zero Extend (SSE4.1).
  inline void pmovzxwd(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMOVZXWD, &dst, &src);
  }

  //! @brief (SSE4.1).
  inline void pmovzxwq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVZXWQ, &dst, &src);
  }
  //! @brief (SSE4.1).
  inline void pmovzxwq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMOVZXWQ, &dst, &src);
  }

  //! @brief (SSE4.1).
  inline void pmovzxdq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMOVZXDQ, &dst, &src);
  }
  //! @brief (SSE4.1).
  inline void pmovzxdq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMOVZXDQ, &dst, &src);
  }

  //! @brief Multiply Packed Signed Dword Integers (SSE4.1).
  inline void pmuldq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMULDQ, &dst, &src);
  }
  //! @brief Multiply Packed Signed Dword Integers (SSE4.1).
  inline void pmuldq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMULDQ, &dst, &src);
  }

  //! @brief Multiply Packed Signed Integers and Store Low Result (SSE4.1).
  inline void pmulld(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PMULLD, &dst, &src);
  }
  //! @brief Multiply Packed Signed Integers and Store Low Result (SSE4.1).
  inline void pmulld(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PMULLD, &dst, &src);
  }

  //! @brief Logical Compare (SSE4.1).
  inline void ptest(const XMMReg& op1, const XMMReg& op2)
  {
    _emitInstruction(INST_PTEST, &op1, &op2);
  }
  //! @brief Logical Compare (SSE4.1).
  inline void ptest(const XMMReg& op1, const Mem& op2)
  {
    _emitInstruction(INST_PTEST, &op1, &op2);
  }

  //! Round Packed SP-FP Values @brief (SSE4.1).
  inline void roundps(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_ROUNDPS, &dst, &src, &imm8);
  }
  //! Round Packed SP-FP Values @brief (SSE4.1).
  inline void roundps(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_ROUNDPS, &dst, &src, &imm8);
  }

  //! @brief Round Scalar SP-FP Values (SSE4.1).
  inline void roundss(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_ROUNDSS, &dst, &src, &imm8);
  }
  //! @brief Round Scalar SP-FP Values (SSE4.1).
  inline void roundss(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_ROUNDSS, &dst, &src, &imm8);
  }

  //! @brief Round Packed DP-FP Values (SSE4.1).
  inline void roundpd(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_ROUNDPD, &dst, &src, &imm8);
  }
  //! @brief Round Packed DP-FP Values (SSE4.1).
  inline void roundpd(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_ROUNDPD, &dst, &src, &imm8);
  }

  //! @brief Round Scalar DP-FP Values (SSE4.1).
  inline void roundsd(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_ROUNDSD, &dst, &src, &imm8);
  }
  //! @brief Round Scalar DP-FP Values (SSE4.1).
  inline void roundsd(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_ROUNDSD, &dst, &src, &imm8);
  }

  // --------------------------------------------------------------------------
  // [SSE4.2]
  // --------------------------------------------------------------------------

  //! @brief Accumulate CRC32 Value (polynomial 0x11EDC6F41) (SSE4.2).
  inline void crc32(const GPReg& dst, const GPReg& src)
  {
    ASMJIT_ASSERT(dst.isRegType(REG_TYPE_GPD) || dst.isRegType(REG_TYPE_GPQ));
    _emitInstruction(INST_CRC32, &dst, &src);
  }
  //! @brief Accumulate CRC32 Value (polynomial 0x11EDC6F41) (SSE4.2).
  inline void crc32(const GPReg& dst, const Mem& src)
  {
    ASMJIT_ASSERT(dst.isRegType(REG_TYPE_GPD) || dst.isRegType(REG_TYPE_GPQ));
    _emitInstruction(INST_CRC32, &dst, &src);
  }

  //! @brief Packed Compare Explicit Length Strings, Return Index (SSE4.2).
  inline void pcmpestri(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PCMPESTRI, &dst, &src, &imm8);
  }
  //! @brief Packed Compare Explicit Length Strings, Return Index (SSE4.2).
  inline void pcmpestri(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PCMPESTRI, &dst, &src, &imm8);
  }

  //! @brief Packed Compare Explicit Length Strings, Return Mask (SSE4.2).
  inline void pcmpestrm(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PCMPESTRM, &dst, &src, &imm8);
  }
  //! @brief Packed Compare Explicit Length Strings, Return Mask (SSE4.2).
  inline void pcmpestrm(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PCMPESTRM, &dst, &src, &imm8);
  }

  //! @brief Packed Compare Implicit Length Strings, Return Index (SSE4.2).
  inline void pcmpistri(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PCMPISTRI, &dst, &src, &imm8);
  }
  //! @brief Packed Compare Implicit Length Strings, Return Index (SSE4.2).
  inline void pcmpistri(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PCMPISTRI, &dst, &src, &imm8);
  }

  //! @brief Packed Compare Implicit Length Strings, Return Mask (SSE4.2).
  inline void pcmpistrm(const XMMReg& dst, const XMMReg& src, const Imm& imm8)
  {
    _emitInstruction(INST_PCMPISTRM, &dst, &src, &imm8);
  }
  //! @brief Packed Compare Implicit Length Strings, Return Mask (SSE4.2).
  inline void pcmpistrm(const XMMReg& dst, const Mem& src, const Imm& imm8)
  {
    _emitInstruction(INST_PCMPISTRM, &dst, &src, &imm8);
  }

  //! @brief Compare Packed Data for Greater Than (SSE4.2).
  inline void pcmpgtq(const XMMReg& dst, const XMMReg& src)
  {
    _emitInstruction(INST_PCMPGTQ, &dst, &src);
  }
  //! @brief Compare Packed Data for Greater Than (SSE4.2).
  inline void pcmpgtq(const XMMReg& dst, const Mem& src)
  {
    _emitInstruction(INST_PCMPGTQ, &dst, &src);
  }

  //! @brief Return the Count of Number of Bits Set to 1 (SSE4.2).
  inline void popcnt(const GPReg& dst, const GPReg& src)
  {
    ASMJIT_ASSERT(!dst.isGPB());
    ASMJIT_ASSERT(src.getRegType() == dst.getRegType());
    _emitInstruction(INST_POPCNT, &dst, &src);
  }
  //! @brief Return the Count of Number of Bits Set to 1 (SSE4.2).
  inline void popcnt(const GPReg& dst, const Mem& src)
  {
    ASMJIT_ASSERT(!dst.isGPB());
    _emitInstruction(INST_POPCNT, &dst, &src);
  }

  // -------------------------------------------------------------------------
  // [AMD only]
  // -------------------------------------------------------------------------

  //! @brief Prefetch (3dNow - Amd).
  //!
  //! Loads the entire 64-byte aligned memory sequence containing the
  //! specified memory address into the L1 data cache. The position of
  //! the specified memory address within the 64-byte cache line is
  //! irrelevant. If a cache hit occurs, or if a memory fault is detected,
  //! no bus cycle is initiated and the instruction is treated as a NOP.
  inline void amd_prefetch(const Mem& mem)
  {
    _emitInstruction(INST_AMD_PREFETCH, &mem);
  }

  //! @brief Prefetch and set cache to modified (3dNow - Amd).
  //!
  //! The PREFETCHW instruction loads the prefetched line and sets the
  //! cache-line state to Modified, in anticipation of subsequent data
  //! writes to the line. The PREFETCH instruction, by contrast, typically
  //! sets the cache-line state to Exclusive (depending on the hardware
  //! implementation).
  inline void amd_prefetchw(const Mem& mem)
  {
    _emitInstruction(INST_AMD_PREFETCHW, &mem);
  }

  // -------------------------------------------------------------------------
  // [Intel only]
  // -------------------------------------------------------------------------

  //! @brief Move Data After Swapping Bytes (SSE3 - Intel Atom).
  inline void movbe(const GPReg& dst, const Mem& src)
  {
    ASMJIT_ASSERT(!dst.isGPB());
    _emitInstruction(INST_MOVBE, &dst, &src);
  }

  //! @brief Move Data After Swapping Bytes (SSE3 - Intel Atom).
  inline void movbe(const Mem& dst, const GPReg& src)
  {
    ASMJIT_ASSERT(!src.isGPB());
    _emitInstruction(INST_MOVBE, &dst, &src);
  }

  // -------------------------------------------------------------------------
  // [Emit Options]
  // -------------------------------------------------------------------------

  //! @brief Assert LOCK# Signal Prefix.
  //!
  //! This instruction causes the processor's LOCK# signal to be asserted
  //! during execution of the accompanying instruction (turns the
  //! instruction into an atomic instruction). In a multiprocessor environment,
  //! the LOCK# signal insures that the processor has exclusive use of any shared
  //! memory while the signal is asserted.
  //!
  //! The LOCK prefix can be prepended only to the following instructions and
  //! to those forms of the instructions that use a memory operand: ADD, ADC,
  //! AND, BTC, BTR, BTS, CMPXCHG, DEC, INC, NEG, NOT, OR, SBB, SUB, XOR, XADD,
  //! and XCHG. An undefined opcode exception will be generated if the LOCK
  //! prefix is used with any other instruction. The XCHG instruction always
  //! asserts the LOCK# signal regardless of the presence or absence of the LOCK
  //! prefix.
  //!
  //! @sa @c EMIT_OPTION_LOCK_PREFIX.
  inline void lock()
  {
    _emitOptions |= EMIT_OPTION_LOCK_PREFIX;
  }

  //! @brief Force REX prefix to be emitted.
  //!
  //! This option should be used carefully, because there are unencodable
  //! combinations. If you want to access ah, bh, ch or dh registers then you
  //! can't emit REX prefix and it will cause an illegal instruction error.
  //!
  //! @note REX prefix is only valid for X64/AMD64 platform.
  //!
  //! @sa @c EMIT_OPTION_REX_PREFIX.
  inline void rex()
  {
    _emitOptions |= EMIT_OPTION_REX_PREFIX;
  }
};

// ============================================================================
// [AsmJit::Assembler]
// ============================================================================

//! @brief Assembler - low level code generation.
//!
//! @c Assembler is the main class in AsmJit for generating low level x86/x64
//! binary stream. It creates internal buffer where opcodes are stored and
//! contains methods that mimics x86/x64 assembler instructions. Code generation
//! should be safe, because basic type-checks are done by the C++ compiler. It's
//! nearly impossible to create invalid instruction (for example
//! <code>mov [eax], [eax]</code> that will not be detected at compile time.
//!
//! Each call to assembler intrinsics directly emits instruction to internal
//! binary stream. Instruction emitting also contains runtime checks so it's
//! impossible to create instruction that is not valid.
//!
//! @c AsmJit::Assembler contains internal buffer where all emitted
//! instructions are stored. Look at @c AsmJit::Buffer for buffer
//! implementation. To generate and allocate memory for function use
//! @c AsmJit::Assembler::make() method that will allocate memory using
//! provided memory manager ( see @c AsmJit::MemoryManager::getGlobal() ) and
//! relocates code to provided address. If you want to create your function
//! manually, you should look at @c AsmJit::VirtualMemory and use
//! @c AsmJit::Assembler::relocCode() method to relocate emitted code into
//! provided memory location. You can also take emitted buffer by @c take()
//! method to do something else with it. If you take buffer, you must free it
//! manually by @c ASMJIT_FREE() macro.
//!
//! @note Always use this class and never use @c AssemblerCore or
//! @c AssemblerIntrinsics classes directly.
//!
//! @section AsmJit_Assembler_CodeGeneration Code Generation
//!
//! To generate code is only needed to create instance of @c AsmJit::Assembler
//! and to use intrinsics. See example how to do that:
//!
//! @code
//! // Use AsmJit namespace.
//! using namespace AsmJit;
//!
//! // Create Assembler instance.
//! Assembler a;
//!
//! // Prolog.
//! a.push(ebp);
//! a.mov(ebp, esp);
//!
//! // Mov 1024 to EAX, EAX is also return value.
//! a.mov(eax, imm(1024));
//!
//! // Epilog.
//! a.mov(esp, ebp);
//! a.pop(ebp);
//!
//! // Return.
//! a.ret();
//! @endcode
//!
//! You can see that syntax is very close to Intel one. Only difference is that
//! you are calling functions that emits the binary code for you. All registers
//! are in @c AsmJit namespace, so it's very comfortable to use it (look at
//! first line). There is also used method @c AsmJit::imm() to create an
//! immediate value. Use @c AsmJit::uimm() to create unsigned immediate value.
//!
//! There is also possibility to use memory addresses and immediates. To build
//! memory address use @c ptr(), @c byte_ptr(), @c word_ptr(), @c dword_ptr()
//! or other friend methods. In most cases you needs only @c ptr() method, but
//! there are instructions where you must specify address size,
//!
//! for example (a is @c AsmJit::Assembler instance):
//!
//! @code
//! a.mov(ptr(eax), imm(0));                   // mov ptr [eax], 0
//! a.mov(ptr(eax), edx);                      // mov ptr [eax], edx
//! @endcode
//!
//! But it's also possible to create complex addresses:
//!
//! @code
//! // eax + ecx*x addresses
//! a.mov(ptr(eax, ecx, TIMES_1), imm(0));     // mov ptr [eax + ecx], 0
//! a.mov(ptr(eax, ecx, TIMES_2), imm(0));     // mov ptr [eax + ecx * 2], 0
//! a.mov(ptr(eax, ecx, TIMES_4), imm(0));     // mov ptr [eax + ecx * 4], 0
//! a.mov(ptr(eax, ecx, TIMES_8), imm(0));     // mov ptr [eax + ecx * 8], 0
//! // eax + ecx*x + disp addresses
//! a.mov(ptr(eax, ecx, TIMES_1,  4), imm(0)); // mov ptr [eax + ecx     +  4], 0
//! a.mov(ptr(eax, ecx, TIMES_2,  8), imm(0)); // mov ptr [eax + ecx * 2 +  8], 0
//! a.mov(ptr(eax, ecx, TIMES_4, 12), imm(0)); // mov ptr [eax + ecx * 4 + 12], 0
//! a.mov(ptr(eax, ecx, TIMES_8, 16), imm(0)); // mov ptr [eax + ecx * 8 + 16], 0
//! @endcode
//!
//! All addresses shown are using @c AsmJit::ptr() to make memory operand.
//! Some assembler instructions (single operand ones) needs to specify memory
//! operand size. For example calling <code>a.inc(ptr(eax))</code> can't be
//! used. @c AsmJit::Assembler::inc(), @c AsmJit::Assembler::dec() and similar
//! instructions can't be serialized without specifying how bytes they are
//! operating on. See next code how assembler works:
//!
//! @code
//! // [byte] address
//! a.inc(byte_ptr(eax));                      // inc byte ptr [eax]
//! a.dec(byte_ptr(eax));                      // dec byte ptr [eax]
//! // [word] address
//! a.inc(word_ptr(eax));                      // inc word ptr [eax]
//! a.dec(word_ptr(eax));                      // dec word ptr [eax]
//! // [dword] address
//! a.inc(dword_ptr(eax));                     // inc dword ptr [eax]
//! a.dec(dword_ptr(eax));                     // dec dword ptr [eax]
//! @endcode
//!
//! @section AsmJit_Assembler_CallingJitCode Calling JIT Code
//!
//! While you are over from emitting instructions, you can make your function
//! using @c AsmJit::Assembler::make() method. This method will use memory
//! manager to allocate virtual memory and relocates generated code to it. For
//! memory allocation is used global memory manager by default and memory is
//! freeable, but of course this default behavior can be overriden specifying
//! your memory manager and allocation type. If you want to do with code
//! something else you can always override make() method and do what you want.
//!
//! You can get size of generated code by @c getCodeSize() or @c getOffset()
//! methods. These methods returns you code size (or more precisely current code 
//! offset) in bytes. Use takeCode() to take internal buffer (all pointers in
//! @c AsmJit::Assembler instance will be zeroed and current buffer returned)
//! to use it. If you don't take it,  @c AsmJit::Assembler destructor will
//! free it automatically. To alloc and run code manually don't use
//! @c malloc()'ed memory, but instead use @c AsmJit::VirtualMemory::alloc()
//! to get memory for executing (specify @c canExecute to @c true) or
//! @c AsmJit::MemoryManager that provides more effective and comfortable way
//! to allocate virtual memory.
//!
//! See next example how to allocate memory where you can execute code created
//! by @c AsmJit::Assembler:
//!
//! @code
//! using namespace AsmJit;
//!
//! Assembler a;
//!
//! // ... your code generation
//!
//! // your function prototype
//! typedef void (*MyFn)();
//!
//! // make your function
//! MyFn fn = function_cast<MyFn>(a.make());
//!
//! // call your function
//! fn();
//!
//! // If you don't need your function again, free it.
//! MemoryManager::getGlobal()->free(fn);
//! @endcode
//!
//! There is also low level alternative how to allocate virtual memory and
//! relocate code to it:
//!
//! @code
//! using namespace AsmJit;
//!
//! Assembler a;
//! // Your code generation ...
//!
//! // Your function prototype.
//! typedef void (*MyFn)();
//!
//! // Alloc memory for your function.
//! MyFn fn = function_cast<MyFn>(
//!   MemoryManager::getGlobal()->alloc(a.getCodeSize());
//!
//! // Relocate the code (will make the function).
//! a.relocCode(fn);
//!
//! // Call the generated function.
//! fn();
//!
//! // If you don't need your function anymore, it should be freed.
//! MemoryManager::getGlobal()->free(fn);
//! @endcode
//!
//! @c note This was very primitive example how to call generated code.
//! In real production code you will never alloc and free code for one run,
//! you will usually use generated code many times.
//!
//! @section AsmJit_Assembler_Labels Labels
//!
//! While generating assembler code, you will usually need to create complex
//! code with labels. Labels are fully supported and you can call @c jmp or
//! @c je (and similar) instructions to initialized or yet uninitialized label.
//! Each label expects to be bound into offset. To bind label to specific
//! offset, use @c bind() method.
//!
//! See next example that contains complete code that creates simple memory
//! copy function (in DWORD entities).
//!
//! @code
//! // Example: Usage of Label (32-bit code).
//! //
//! // Create simple DWORD memory copy function:
//! // ASMJIT_STDCALL void copy32(uint32_t* dst, const uint32_t* src, sysuint_t count);
//! using namespace AsmJit;
//!
//! // Assembler instance.
//! Assembler a;
//!
//! // Constants.
//! const int arg_offset = 8; // Arguments offset (STDCALL EBP).
//! const int arg_size = 12;  // Arguments size.
//!
//! // Labels.
//! Label L_Loop = a.newLabel();
//!
//! // Prolog.
//! a.push(ebp);
//! a.mov(ebp, esp);
//! a.push(esi);
//! a.push(edi);
//!
//! // Fetch arguments
//! a.mov(esi, dword_ptr(ebp, arg_offset + 0)); // Get dst.
//! a.mov(edi, dword_ptr(ebp, arg_offset + 4)); // Get src.
//! a.mov(ecx, dword_ptr(ebp, arg_offset + 8)); // Get count.
//!
//! // Bind L_Loop label to here.
//! a.bind(L_Loop);
//!
//! Copy 4 bytes.
//! a.mov(eax, dword_ptr(esi));
//! a.mov(dword_ptr(edi), eax);
//!
//! // Increment pointers.
//! a.add(esi, 4);
//! a.add(edi, 4);
//!
//! // Repeat loop until (--ecx != 0).
//! a.dec(ecx);
//! a.jz(L_Loop);
//!
//! // Epilog.
//! a.pop(edi);
//! a.pop(esi);
//! a.mov(esp, ebp);
//! a.pop(ebp);
//!
//! // Return: STDCALL convention is to pop stack in called function.
//! a.ret(arg_size);
//! @endcode
//!
//! If you need more abstraction for generating assembler code and you want
//! to hide calling conventions between 32-bit and 64-bit operating systems,
//! look at @c Compiler class that is designed for higher level code
//! generation.
//!
//! @section AsmJit_Assembler_AdvancedCodeGeneration Advanced Code Generation
//!
//! This section describes some advanced generation features of @c Assembler
//! class which can be simply overlooked. The first thing that is very likely
//! needed is generic register support. In previous example the named registers
//! were used. AsmJit contains functions which can convert register index into
//! operand and back.
//!
//! Let's define function which can be used to generate some abstract code:
//!
//! @code
//! // Simple function that generates dword copy.
//! void genCopyDWord(
//!   Assembler& a,
//!   const GPReg& dst, const GPReg& src, const GPReg& tmp)
//! {
//!   a.mov(tmp, dword_ptr(src));
//!   a.mov(dword_ptr(dst), tmp);
//! }
//! @endcode
//!
//! This function can be called like <code>genCopyDWord(a, edi, esi, ebx)</code>
//! or by using existing @ref GPReg instances. This abstraction allows to join
//! more code sections together without rewriting each to use specific registers.
//! You need to take care only about implicit registers which may be used by 
//! several instructions (like mul, imul, div, idiv, shifting, etc...).
//!
//! Next, more advanced, but often needed technique is that you can build your
//! own registers allocator. X86 architecture contains 8 general purpose registers,
//! 8 MMX (MM) registers and 8 SSE (XMM) registers. The X64 (AMD64) architecture
//! extends count of general purpose registers and SSE2 registers to 16. Use the
//! @c REG_NUM_BASE constant to get count of GP or XMM registers or @c REG_NUM_GP,
//! @c REG_NUM_MM and @c REG_NUM_XMM constants individually.
//!
//! To build register from index (value from 0 inclusive to REG_NUM_XXX 
//! exclusive) use @ref gpd(), @ref gpq() or @ref gpn() functions. To create
//! a 8 or 16-bit register use @ref gpw(), @ref gpb_lo() or @ref gpb_hi(). 
//! To create other registers there are similar methods @ref mm(), @ref xmm() and
//! @ref st().
//!
//! So our function call to genCopyDWord can be also used like this:
//!
//! @code
//! genCopyDWord(a, gpd(REG_INDEX_EDI), gpd(REG_INDEX_ESI), gpd(REG_INDEX_EBX));
//! @endcode
//!
//! REG_INDEX_XXX are constants defined by @ref REG_INDEX enum. You can use your
//! own register allocator (or register slot manager) to alloc / free registers
//! so REG_INDEX_XXX values can be replaced by your variables (0 to REG_NUM_XXX-1).
//!
//! @sa @c AssemblerCore, @c AssemblerIntrinsics, @c Operand, @c Compiler.
struct ASMJIT_API Assembler : public AssemblerIntrinsics
{
  Assembler(CodeGenerator* codeGenerator = NULL) ASMJIT_NOTHROW;
  virtual ~Assembler() ASMJIT_NOTHROW;
};

//! @}

} // AsmJit namespace

// [Api-End]
#include "ApiEnd.h"

// [Guard]
#endif // _ASMJIT_ASSEMBLERX86X64_H