aboutsummaryrefslogtreecommitdiffstats
path: root/recipes/xorg-driver/xf86-video-msm/no_neon.patch
blob: c0aa92e76afb596313274d61097b4c1d3a2b46db (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
commit d8910bf773fbecf7cdea359d4b530a3672e27180
Author: David Lanzend�rfer <david.lanzendoerfer@o2s.ch>
Date:   Wed Feb 10 16:18:39 2010 +0100

    Removed neon because its not available in our kerne�l
    and so its causing trubble (Illegal instruction)

diff --git git/src/msm-swblits.h git/src/msm-swblits.h
index f89f00e..a40b24b 100755
--- git/src/msm-swblits.h
+++ git/src/msm-swblits.h
@@ -38,16 +38,6 @@
 #include <stdint.h>
 #include <stdlib.h>
 
-/* Neon intrinsics are part of the ARM or GCC compiler used.                                                              */
-/* Tested with: /pkg/asw/compilers/gnu/codesourcery/arm-2008q3-72/lib/gcc/arm-none-linux-gnueabi/4.3.2/include/arm_neon.h */
-#include <arm_neon.h>
-
-/* These are NEON-optimized functions linked to by various tests.  */
-extern void * neon_memcpy (void * dest, const void * source, unsigned int numBytes);
-extern void * neon_memmove (void * dest, const void * source, unsigned int numBytes);
-extern void memset16(uint16_t *dst, uint16_t value, int count);
-extern void memset32(uint32_t *dst, uint32_t value, int count);
-
 /* Make definitions to clarify memory-related sizes to enable avoidance of magic numbers. */
 #define BITS_PER_BYTE (8)
 #define BYTES_PER_16BPP_PIXEL (2)
diff --git git/src/msm-swfill.c git/src/msm-swfill.c
index 108fd94..3dd1ef2 100755
--- git/src/msm-swfill.c
+++ git/src/msm-swfill.c
@@ -212,7 +212,7 @@ memset16_NeonAlignmentAssumptions_UpTo7Count(uint8_t *dst, uint16_t src, int cou
    }
 }
 
-
+/*
 static inline void
 memset16_AssumesNeonAlignment(uint8_t *dst, uint16_t src, int count)
 {
@@ -333,7 +333,7 @@ memset16_AssumesNeonAlignment(uint8_t *dst, uint16_t src, int count)
    // Quickly fill remaining pixels (up to 7).
    memset16_NeonAlignmentAssumptions_UpTo7Count(dst, src, count);
 }
-
+*/
 
 static inline void
 memset16_Test(uint16_t *dst, uint16_t src, int count)
@@ -368,7 +368,8 @@ memset16_Test(uint16_t *dst, uint16_t src, int count)
 
       // Copy remaining pixels using Neon and non-Neon instructions.
       // NOTE: This assumes that dst is aligned optimally for Neon instructions.
-      memset16_AssumesNeonAlignment((void *) dst, src, count);
+      //memset16_AssumesNeonAlignment((void *) dst, src, count);
+      memset((void *) dst, src, count);
    }
 }
 
@@ -435,12 +436,14 @@ swFillRect32Bpp_Unaligned(unsigned char *dst, uint32_t src, int w, int h, int dp
    if (w < 32) {
       // For narrow rectangles, block signals only once for the entire rectangles.
       BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS();
-      DO_MULTIPLE_FILLS_WITH_MEMSET(memset32,SIGNAL_BLOCK_NOOP,SIGNAL_BLOCK_NOOP);
+      //DO_MULTIPLE_FILLS_WITH_MEMSET(memset32,SIGNAL_BLOCK_NOOP,SIGNAL_BLOCK_NOOP);
+      DO_MULTIPLE_FILLS_WITH_MEMSET(memset,SIGNAL_BLOCK_NOOP,SIGNAL_BLOCK_NOOP);
       UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS();
    }
    else {
       // For wider rectangles, block and unblock signals for every row.
-      DO_MULTIPLE_FILLS_WITH_MEMSET(memset32,BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS,UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
+      //DO_MULTIPLE_FILLS_WITH_MEMSET(memset32,BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS,UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
+      DO_MULTIPLE_FILLS_WITH_MEMSET(memset,BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS,UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
    }
 }
 
diff --git git/src/msm-swrender.c git/src/msm-swrender.c
index a7a9abc..835dc03 100755
--- git/src/msm-swrender.c
+++ git/src/msm-swrender.c
@@ -214,160 +214,6 @@ swCopy16BppSmallFixedWidths1Row_Unaligned(unsigned char *dst, unsigned char *src
                   }
                }
                break;
-      case  7: if (xdir >= 0) {
-                  swCopy16BppSmallFixedWidths1Row_Unaligned(dst, src, 4, xdir);
-                  swCopy16BppSmallFixedWidths1Row_Unaligned(dst + 4 * BYTES_PER_UINT16_T, src + 4 * BYTES_PER_UINT16_T, 3, xdir);
-                  return TRUE;
-               } else {
-                  swCopy16BppSmallFixedWidths1Row_Unaligned(dst + 4 * BYTES_PER_UINT16_T, src + 4 * BYTES_PER_UINT16_T, 3, xdir);
-                  swCopy16BppSmallFixedWidths1Row_Unaligned(dst, src, 4, xdir);
-                  return TRUE;
-               }
-               break;
-      case  8: if (SW_CHECK_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,0)) {
-                  uint32x4_t src1 = vld1q_u32((uint32_t *)(src+0*BYTES_PER_UINT32X4_T));
-                  vst1q_u32((uint32_t *)(dst+0*BYTES_PER_UINT32X4_T),src1);
-                  return TRUE;
-               }
-               else if (SW_CHECK_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,0)) {
-                  uint64_t src1  = *(uint64_t *) (src+0*BYTES_PER_UINT64_T);
-                  uint64_t src2  = *(uint64_t *) (src+1*BYTES_PER_UINT64_T);
-                  *(uint64_t *) (dst+0*BYTES_PER_UINT64_T)  = src1;
-                  *(uint64_t *) (dst+1*BYTES_PER_UINT64_T)  = src2;
-                  return TRUE;
-               }
-               else if (SW_CHECK_ALIGNMENT(WORD_ALIGNMENT_BYTE_SIZE,dst,src,0)) {
-                  uint32_t src1  = *(uint32_t *) (src+0*BYTES_PER_UINT32_T);
-                  uint32_t src2  = *(uint32_t *) (src+1*BYTES_PER_UINT32_T);
-                  uint32_t src3  = *(uint32_t *) (src+2*BYTES_PER_UINT32_T);
-                  uint32_t src4  = *(uint32_t *) (src+3*BYTES_PER_UINT32_T);
-                  *(uint32_t *) (dst+0*BYTES_PER_UINT32_T)  = src1;
-                  *(uint32_t *) (dst+1*BYTES_PER_UINT32_T)  = src2;
-                  *(uint32_t *) (dst+2*BYTES_PER_UINT32_T)  = src3;
-                  *(uint32_t *) (dst+3*BYTES_PER_UINT32_T)  = src4;
-                  return TRUE;
-               }
-               else {
-                  uint16_t src1  = *(uint16_t *) (src+0*BYTES_PER_UINT16_T);
-                  uint16_t src2  = *(uint16_t *) (src+1*BYTES_PER_UINT16_T);
-                  uint16_t src3  = *(uint16_t *) (src+2*BYTES_PER_UINT16_T);
-                  uint16_t src4  = *(uint16_t *) (src+3*BYTES_PER_UINT16_T);
-                  uint16_t src5  = *(uint16_t *) (src+4*BYTES_PER_UINT16_T);
-                  uint16_t src6  = *(uint16_t *) (src+5*BYTES_PER_UINT16_T);
-                  uint16_t src7  = *(uint16_t *) (src+6*BYTES_PER_UINT16_T);
-                  uint16_t src8  = *(uint16_t *) (src+7*BYTES_PER_UINT16_T);
-                  *(uint16_t *) (dst+0*BYTES_PER_UINT16_T)  = src1;
-                  *(uint16_t *) (dst+1*BYTES_PER_UINT16_T)  = src2;
-                  *(uint16_t *) (dst+2*BYTES_PER_UINT16_T)  = src3;
-                  *(uint16_t *) (dst+3*BYTES_PER_UINT16_T)  = src4;
-                  *(uint16_t *) (dst+4*BYTES_PER_UINT16_T)  = src5;
-                  *(uint16_t *) (dst+5*BYTES_PER_UINT16_T)  = src6;
-                  *(uint16_t *) (dst+6*BYTES_PER_UINT16_T)  = src7;
-                  *(uint16_t *) (dst+7*BYTES_PER_UINT16_T)  = src8;
-                  return TRUE;
-               }
-               break;
-      case 16: if (SW_CHECK_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,0)) {
-                  uint32x4_t src1 = vld1q_u32((uint32_t *)(src+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2 = vld1q_u32((uint32_t *)(src+1*BYTES_PER_UINT32X4_T));
-                  vst1q_u32((uint32_t *)(dst+0*BYTES_PER_UINT32X4_T),src1);
-                  vst1q_u32((uint32_t *)(dst+1*BYTES_PER_UINT32X4_T),src2);
-                  return TRUE;
-               }
-               else if (SW_CHECK_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,0)) {
-                  uint64_t src1  = *(uint64_t *) (src+0*BYTES_PER_UINT64_T);
-                  uint64_t src2  = *(uint64_t *) (src+1*BYTES_PER_UINT64_T);
-                  uint64_t src3  = *(uint64_t *) (src+2*BYTES_PER_UINT64_T);
-                  uint64_t src4  = *(uint64_t *) (src+3*BYTES_PER_UINT64_T);
-                  *(uint64_t *) (dst+0*BYTES_PER_UINT64_T)  = src1;
-                  *(uint64_t *) (dst+1*BYTES_PER_UINT64_T)  = src2;
-                  *(uint64_t *) (dst+2*BYTES_PER_UINT64_T)  = src3;
-                  *(uint64_t *) (dst+3*BYTES_PER_UINT64_T)  = src4;
-                  return TRUE;
-               }
-               else if (SW_CHECK_ALIGNMENT(WORD_ALIGNMENT_BYTE_SIZE,dst,src,0)) {
-                  uint32_t src1  = *(uint32_t *) (src+0*BYTES_PER_UINT32_T);
-                  uint32_t src2  = *(uint32_t *) (src+1*BYTES_PER_UINT32_T);
-                  uint32_t src3  = *(uint32_t *) (src+2*BYTES_PER_UINT32_T);
-                  uint32_t src4  = *(uint32_t *) (src+3*BYTES_PER_UINT32_T);
-                  uint32_t src5  = *(uint32_t *) (src+4*BYTES_PER_UINT32_T);
-                  uint32_t src6  = *(uint32_t *) (src+5*BYTES_PER_UINT32_T);
-                  uint32_t src7  = *(uint32_t *) (src+6*BYTES_PER_UINT32_T);
-                  uint32_t src8  = *(uint32_t *) (src+7*BYTES_PER_UINT32_T);
-                  *(uint32_t *) (dst+0*BYTES_PER_UINT32_T)  = src1;
-                  *(uint32_t *) (dst+1*BYTES_PER_UINT32_T)  = src2;
-                  *(uint32_t *) (dst+2*BYTES_PER_UINT32_T)  = src3;
-                  *(uint32_t *) (dst+3*BYTES_PER_UINT32_T)  = src4;
-                  *(uint32_t *) (dst+4*BYTES_PER_UINT32_T)  = src5;
-                  *(uint32_t *) (dst+5*BYTES_PER_UINT32_T)  = src6;
-                  *(uint32_t *) (dst+6*BYTES_PER_UINT32_T)  = src7;
-                  *(uint32_t *) (dst+7*BYTES_PER_UINT32_T)  = src8;
-                  return TRUE;
-               }
-               else {
-                  // Don't bother unrolling loops here, since that won't help for more than around 8 operations.
-                  // Instead, just call multiple fixed functions.
-                  if (xdir >= 0) {
-                     swCopy16BppSmallFixedWidths1Row_Unaligned(dst, src, 8, xdir);
-                     swCopy16BppSmallFixedWidths1Row_Unaligned(dst + 8 * BYTES_PER_UINT16_T, src + 8 * BYTES_PER_UINT16_T, 8, xdir);
-                  } else {
-                     swCopy16BppSmallFixedWidths1Row_Unaligned(dst + 8 * BYTES_PER_UINT16_T, src + 8 * BYTES_PER_UINT16_T, 8, xdir);
-                     swCopy16BppSmallFixedWidths1Row_Unaligned(dst, src, 8, xdir);
-                  }
-                  return TRUE;
-               }
-               break;
-      case 32: if (SW_CHECK_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,0)) {
-                  uint32x4_t src1 = vld1q_u32((uint32_t *)(src+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2 = vld1q_u32((uint32_t *)(src+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src3 = vld1q_u32((uint32_t *)(src+2*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src4 = vld1q_u32((uint32_t *)(src+3*BYTES_PER_UINT32X4_T));
-                  vst1q_u32((uint32_t *)(dst+0*BYTES_PER_UINT32X4_T),src1);
-                  vst1q_u32((uint32_t *)(dst+1*BYTES_PER_UINT32X4_T),src2);
-                  vst1q_u32((uint32_t *)(dst+2*BYTES_PER_UINT32X4_T),src3);
-                  vst1q_u32((uint32_t *)(dst+3*BYTES_PER_UINT32X4_T),src4);
-                  return TRUE;
-               }
-               else if (SW_CHECK_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,0)) {
-                  uint64_t src1  = *(uint64_t *) (src+0*BYTES_PER_UINT64_T);
-                  uint64_t src2  = *(uint64_t *) (src+1*BYTES_PER_UINT64_T);
-                  uint64_t src3  = *(uint64_t *) (src+2*BYTES_PER_UINT64_T);
-                  uint64_t src4  = *(uint64_t *) (src+3*BYTES_PER_UINT64_T);
-                  uint64_t src5  = *(uint64_t *) (src+4*BYTES_PER_UINT64_T);
-                  uint64_t src6  = *(uint64_t *) (src+5*BYTES_PER_UINT64_T);
-                  uint64_t src7  = *(uint64_t *) (src+6*BYTES_PER_UINT64_T);
-                  uint64_t src8  = *(uint64_t *) (src+7*BYTES_PER_UINT64_T);
-                  *(uint64_t *) (dst+0*BYTES_PER_UINT64_T)  = src1;
-                  *(uint64_t *) (dst+1*BYTES_PER_UINT64_T)  = src2;
-                  *(uint64_t *) (dst+2*BYTES_PER_UINT64_T)  = src3;
-                  *(uint64_t *) (dst+3*BYTES_PER_UINT64_T)  = src4;
-                  *(uint64_t *) (dst+4*BYTES_PER_UINT64_T)  = src5;
-                  *(uint64_t *) (dst+5*BYTES_PER_UINT64_T)  = src6;
-                  *(uint64_t *) (dst+6*BYTES_PER_UINT64_T)  = src7;
-                  *(uint64_t *) (dst+7*BYTES_PER_UINT64_T)  = src8;
-                  return TRUE;
-               }
-               break;
-      case 64: if (SW_CHECK_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,0)) {
-                  uint32x4_t src1 = vld1q_u32((uint32_t *)(src+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2 = vld1q_u32((uint32_t *)(src+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src3 = vld1q_u32((uint32_t *)(src+2*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src4 = vld1q_u32((uint32_t *)(src+3*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src5 = vld1q_u32((uint32_t *)(src+4*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src6 = vld1q_u32((uint32_t *)(src+5*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src7 = vld1q_u32((uint32_t *)(src+6*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src8 = vld1q_u32((uint32_t *)(src+7*BYTES_PER_UINT32X4_T));
-                  vst1q_u32((uint32_t *)(dst+0*BYTES_PER_UINT32X4_T),src1);
-                  vst1q_u32((uint32_t *)(dst+1*BYTES_PER_UINT32X4_T),src2);
-                  vst1q_u32((uint32_t *)(dst+2*BYTES_PER_UINT32X4_T),src3);
-                  vst1q_u32((uint32_t *)(dst+3*BYTES_PER_UINT32X4_T),src4);
-                  vst1q_u32((uint32_t *)(dst+4*BYTES_PER_UINT32X4_T),src5);
-                  vst1q_u32((uint32_t *)(dst+5*BYTES_PER_UINT32X4_T),src6);
-                  vst1q_u32((uint32_t *)(dst+6*BYTES_PER_UINT32X4_T),src7);
-                  vst1q_u32((uint32_t *)(dst+7*BYTES_PER_UINT32X4_T),src8);
-                  return TRUE;
-               }
-               break;
    }
 
    return FALSE;
@@ -519,427 +365,6 @@ swCopy16BppSmallFixedWidths2Rows_Unaligned(unsigned char *dst, unsigned char *sr
                }
                return TRUE;
                break;
-      case  7: if (xdir >= 0) {
-                  swCopy16BppSmallFixedWidths2Rows_Unaligned(dst, src, 4, xdir, dpitch, spitch);
-                  swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 4 * BYTES_PER_UINT16_T, src + 4 * BYTES_PER_UINT16_T, 3, xdir, dpitch, spitch);
-               } else {
-                  swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 4 * BYTES_PER_UINT16_T, src + 4 * BYTES_PER_UINT16_T, 3, xdir, dpitch, spitch);
-                  swCopy16BppSmallFixedWidths2Rows_Unaligned(dst, src, 4, xdir, dpitch, spitch);
-               }
-               return TRUE;
-               break;
-      case  8: if (SW_CHECK_PITCHED_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint32x4_t src1a = vld1q_u32((uint32_t *)(src+0*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1b = vld1q_u32((uint32_t *)(src+1*spitch+0*BYTES_PER_UINT32X4_T));
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+0*BYTES_PER_UINT32X4_T),src1a);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+0*BYTES_PER_UINT32X4_T),src1b);
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint64_t src1a = *(uint64_t *) (src+0*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2a = *(uint64_t *) (src+0*spitch+1*BYTES_PER_UINT64_T);
-                  uint64_t src1b = *(uint64_t *) (src+1*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2b = *(uint64_t *) (src+1*spitch+1*BYTES_PER_UINT64_T);
-                  *(uint64_t *) (dst+0*dpitch+0*BYTES_PER_UINT64_T)  = src1a;
-                  *(uint64_t *) (dst+0*dpitch+1*BYTES_PER_UINT64_T)  = src2a;
-                  *(uint64_t *) (dst+1*dpitch+0*BYTES_PER_UINT64_T)  = src1b;
-                  *(uint64_t *) (dst+1*dpitch+1*BYTES_PER_UINT64_T)  = src2b;
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint32_t src1a = *(uint32_t *) (src+0*spitch+0*BYTES_PER_UINT32_T);
-                  uint32_t src2a = *(uint32_t *) (src+0*spitch+1*BYTES_PER_UINT32_T);
-                  uint32_t src3a = *(uint32_t *) (src+0*spitch+2*BYTES_PER_UINT32_T);
-                  uint32_t src4a = *(uint32_t *) (src+0*spitch+3*BYTES_PER_UINT32_T);
-                  uint32_t src1b = *(uint32_t *) (src+1*spitch+0*BYTES_PER_UINT32_T);
-                  uint32_t src2b = *(uint32_t *) (src+1*spitch+1*BYTES_PER_UINT32_T);
-                  uint32_t src3b = *(uint32_t *) (src+1*spitch+2*BYTES_PER_UINT32_T);
-                  uint32_t src4b = *(uint32_t *) (src+1*spitch+3*BYTES_PER_UINT32_T);
-                  *(uint32_t *) (dst+0*dpitch+0*BYTES_PER_UINT32_T)  = src1a;
-                  *(uint32_t *) (dst+0*dpitch+1*BYTES_PER_UINT32_T)  = src2a;
-                  *(uint32_t *) (dst+0*dpitch+2*BYTES_PER_UINT32_T)  = src3a;
-                  *(uint32_t *) (dst+0*dpitch+3*BYTES_PER_UINT32_T)  = src4a;
-                  *(uint32_t *) (dst+1*dpitch+0*BYTES_PER_UINT32_T)  = src1b;
-                  *(uint32_t *) (dst+1*dpitch+1*BYTES_PER_UINT32_T)  = src2b;
-                  *(uint32_t *) (dst+1*dpitch+2*BYTES_PER_UINT32_T)  = src3b;
-                  *(uint32_t *) (dst+1*dpitch+3*BYTES_PER_UINT32_T)  = src4b;
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,BYTES_PER_UINT16_T)) {
-                  uint16_t src1a = *(uint16_t *) (src+0*spitch+0);
-                  uint32_t src2a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T);
-                  uint32_t src3a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T);
-                  uint32_t src4a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T);
-                  uint16_t src5a = *(uint16_t *) (src+0*spitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T);
-                  uint16_t src1b = *(uint16_t *) (src+1*spitch+0);
-                  uint32_t src2b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T);
-                  uint32_t src3b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T);
-                  uint32_t src4b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T);
-                  uint16_t src5b = *(uint16_t *) (src+1*spitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T);
-                  *(uint16_t *) (dst+0*dpitch+0)                                        = src1a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T)  = src2a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T)  = src3a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T)  = src4a;
-                  *(uint16_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T)  = src5a;
-                  *(uint16_t *) (dst+1*dpitch+0)                                        = src1b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T)  = src2b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T)  = src3b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T)  = src4b;
-                  *(uint16_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T)  = src5b;
-                  return TRUE;
-               }
-               else {
-                  uint16_t src1a = *(uint16_t *) (src+0*spitch+0*BYTES_PER_UINT16_T);
-                  uint16_t src2a = *(uint16_t *) (src+0*spitch+1*BYTES_PER_UINT16_T);
-                  uint16_t src3a = *(uint16_t *) (src+0*spitch+2*BYTES_PER_UINT16_T);
-                  uint16_t src4a = *(uint16_t *) (src+0*spitch+3*BYTES_PER_UINT16_T);
-                  uint16_t src5a = *(uint16_t *) (src+0*spitch+4*BYTES_PER_UINT16_T);
-                  uint16_t src6a = *(uint16_t *) (src+0*spitch+5*BYTES_PER_UINT16_T);
-                  uint16_t src7a = *(uint16_t *) (src+0*spitch+6*BYTES_PER_UINT16_T);
-                  uint16_t src8a = *(uint16_t *) (src+0*spitch+7*BYTES_PER_UINT16_T);
-                  uint16_t src1b = *(uint16_t *) (src+1*spitch+0*BYTES_PER_UINT16_T);
-                  uint16_t src2b = *(uint16_t *) (src+1*spitch+1*BYTES_PER_UINT16_T);
-                  uint16_t src3b = *(uint16_t *) (src+1*spitch+2*BYTES_PER_UINT16_T);
-                  uint16_t src4b = *(uint16_t *) (src+1*spitch+3*BYTES_PER_UINT16_T);
-                  uint16_t src5b = *(uint16_t *) (src+1*spitch+4*BYTES_PER_UINT16_T);
-                  uint16_t src6b = *(uint16_t *) (src+1*spitch+5*BYTES_PER_UINT16_T);
-                  uint16_t src7b = *(uint16_t *) (src+1*spitch+6*BYTES_PER_UINT16_T);
-                  uint16_t src8b = *(uint16_t *) (src+1*spitch+7*BYTES_PER_UINT16_T);
-                  *(uint16_t *) (dst+0*dpitch+0*BYTES_PER_UINT16_T)  = src1a;
-                  *(uint16_t *) (dst+0*dpitch+1*BYTES_PER_UINT16_T)  = src2a;
-                  *(uint16_t *) (dst+0*dpitch+2*BYTES_PER_UINT16_T)  = src3a;
-                  *(uint16_t *) (dst+0*dpitch+3*BYTES_PER_UINT16_T)  = src4a;
-                  *(uint16_t *) (dst+0*dpitch+4*BYTES_PER_UINT16_T)  = src5a;
-                  *(uint16_t *) (dst+0*dpitch+5*BYTES_PER_UINT16_T)  = src6a;
-                  *(uint16_t *) (dst+0*dpitch+6*BYTES_PER_UINT16_T)  = src7a;
-                  *(uint16_t *) (dst+0*dpitch+7*BYTES_PER_UINT16_T)  = src8a;
-                  *(uint16_t *) (dst+1*dpitch+0*BYTES_PER_UINT16_T)  = src1b;
-                  *(uint16_t *) (dst+1*dpitch+1*BYTES_PER_UINT16_T)  = src2b;
-                  *(uint16_t *) (dst+1*dpitch+2*BYTES_PER_UINT16_T)  = src3b;
-                  *(uint16_t *) (dst+1*dpitch+3*BYTES_PER_UINT16_T)  = src4b;
-                  *(uint16_t *) (dst+1*dpitch+4*BYTES_PER_UINT16_T)  = src5b;
-                  *(uint16_t *) (dst+1*dpitch+5*BYTES_PER_UINT16_T)  = src6b;
-                  *(uint16_t *) (dst+1*dpitch+6*BYTES_PER_UINT16_T)  = src7b;
-                  *(uint16_t *) (dst+1*dpitch+7*BYTES_PER_UINT16_T)  = src8b;
-                  return TRUE;
-               }
-               break;
-      case 16: if (SW_CHECK_PITCHED_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint32x4_t src1a = vld1q_u32((uint32_t *)(src+0*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2a = vld1q_u32((uint32_t *)(src+0*spitch+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1b = vld1q_u32((uint32_t *)(src+1*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2b = vld1q_u32((uint32_t *)(src+1*spitch+1*BYTES_PER_UINT32X4_T));
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+0*BYTES_PER_UINT32X4_T),src1a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+1*BYTES_PER_UINT32X4_T),src2a);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+0*BYTES_PER_UINT32X4_T),src1b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+1*BYTES_PER_UINT32X4_T),src2b);
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint64_t src1a = *(uint64_t *) (src+0*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2a = *(uint64_t *) (src+0*spitch+1*BYTES_PER_UINT64_T);
-                  uint64_t src3a = *(uint64_t *) (src+0*spitch+2*BYTES_PER_UINT64_T);
-                  uint64_t src4a = *(uint64_t *) (src+0*spitch+3*BYTES_PER_UINT64_T);
-                  uint64_t src1b = *(uint64_t *) (src+1*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2b = *(uint64_t *) (src+1*spitch+1*BYTES_PER_UINT64_T);
-                  uint64_t src3b = *(uint64_t *) (src+1*spitch+2*BYTES_PER_UINT64_T);
-                  uint64_t src4b = *(uint64_t *) (src+1*spitch+3*BYTES_PER_UINT64_T);
-                  *(uint64_t *) (dst+0*dpitch+0*BYTES_PER_UINT64_T)  = src1a;
-                  *(uint64_t *) (dst+0*dpitch+1*BYTES_PER_UINT64_T)  = src2a;
-                  *(uint64_t *) (dst+0*dpitch+2*BYTES_PER_UINT64_T)  = src3a;
-                  *(uint64_t *) (dst+0*dpitch+3*BYTES_PER_UINT64_T)  = src4a;
-                  *(uint64_t *) (dst+1*dpitch+0*BYTES_PER_UINT64_T)  = src1b;
-                  *(uint64_t *) (dst+1*dpitch+1*BYTES_PER_UINT64_T)  = src2b;
-                  *(uint64_t *) (dst+1*dpitch+2*BYTES_PER_UINT64_T)  = src3b;
-                  *(uint64_t *) (dst+1*dpitch+3*BYTES_PER_UINT64_T)  = src4b;
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,BYTES_PER_UINT32_T)) {
-                  uint32_t src1a = *(uint32_t *) (src+0*spitch+0);
-                  uint64_t src2a = *(uint64_t *) (src+0*spitch+BYTES_PER_UINT32_T+0*BYTES_PER_UINT64_T);
-                  uint64_t src3a = *(uint64_t *) (src+0*spitch+BYTES_PER_UINT32_T+1*BYTES_PER_UINT64_T);
-                  uint64_t src4a = *(uint64_t *) (src+0*spitch+BYTES_PER_UINT32_T+2*BYTES_PER_UINT64_T);
-                  uint32_t src5a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT32_T+3*BYTES_PER_UINT64_T);
-                  uint32_t src1b = *(uint32_t *) (src+1*spitch+0);
-                  uint64_t src2b = *(uint64_t *) (src+1*spitch+BYTES_PER_UINT32_T+0*BYTES_PER_UINT64_T);
-                  uint64_t src3b = *(uint64_t *) (src+1*spitch+BYTES_PER_UINT32_T+1*BYTES_PER_UINT64_T);
-                  uint64_t src4b = *(uint64_t *) (src+1*spitch+BYTES_PER_UINT32_T+2*BYTES_PER_UINT64_T);
-                  uint32_t src5b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT32_T+3*BYTES_PER_UINT64_T);
-                  *(uint32_t *) (dst+0*dpitch+0)                                        = src1a;
-                  *(uint64_t *) (dst+0*dpitch+BYTES_PER_UINT32_T+0*BYTES_PER_UINT64_T)  = src2a;
-                  *(uint64_t *) (dst+0*dpitch+BYTES_PER_UINT32_T+1*BYTES_PER_UINT64_T)  = src3a;
-                  *(uint64_t *) (dst+0*dpitch+BYTES_PER_UINT32_T+2*BYTES_PER_UINT64_T)  = src4a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT32_T+3*BYTES_PER_UINT64_T)  = src5a;
-                  *(uint32_t *) (dst+1*dpitch+0)                                        = src1b;
-                  *(uint64_t *) (dst+1*dpitch+BYTES_PER_UINT32_T+0*BYTES_PER_UINT64_T)  = src2b;
-                  *(uint64_t *) (dst+1*dpitch+BYTES_PER_UINT32_T+1*BYTES_PER_UINT64_T)  = src3b;
-                  *(uint64_t *) (dst+1*dpitch+BYTES_PER_UINT32_T+2*BYTES_PER_UINT64_T)  = src4b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT32_T+3*BYTES_PER_UINT64_T)  = src5b;
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint32_t src1a = *(uint32_t *) (src+0*spitch+0*BYTES_PER_UINT32_T);
-                  uint32_t src2a = *(uint32_t *) (src+0*spitch+1*BYTES_PER_UINT32_T);
-                  uint32_t src3a = *(uint32_t *) (src+0*spitch+2*BYTES_PER_UINT32_T);
-                  uint32_t src4a = *(uint32_t *) (src+0*spitch+3*BYTES_PER_UINT32_T);
-                  uint32_t src5a = *(uint32_t *) (src+0*spitch+4*BYTES_PER_UINT32_T);
-                  uint32_t src6a = *(uint32_t *) (src+0*spitch+5*BYTES_PER_UINT32_T);
-                  uint32_t src7a = *(uint32_t *) (src+0*spitch+6*BYTES_PER_UINT32_T);
-                  uint32_t src8a = *(uint32_t *) (src+0*spitch+7*BYTES_PER_UINT32_T);
-                  uint32_t src1b = *(uint32_t *) (src+1*spitch+0*BYTES_PER_UINT32_T);
-                  uint32_t src2b = *(uint32_t *) (src+1*spitch+1*BYTES_PER_UINT32_T);
-                  uint32_t src3b = *(uint32_t *) (src+1*spitch+2*BYTES_PER_UINT32_T);
-                  uint32_t src4b = *(uint32_t *) (src+1*spitch+3*BYTES_PER_UINT32_T);
-                  uint32_t src5b = *(uint32_t *) (src+1*spitch+4*BYTES_PER_UINT32_T);
-                  uint32_t src6b = *(uint32_t *) (src+1*spitch+5*BYTES_PER_UINT32_T);
-                  uint32_t src7b = *(uint32_t *) (src+1*spitch+6*BYTES_PER_UINT32_T);
-                  uint32_t src8b = *(uint32_t *) (src+1*spitch+7*BYTES_PER_UINT32_T);
-                  *(uint32_t *) (dst+0*dpitch+0*BYTES_PER_UINT32_T)  = src1a;
-                  *(uint32_t *) (dst+0*dpitch+1*BYTES_PER_UINT32_T)  = src2a;
-                  *(uint32_t *) (dst+0*dpitch+2*BYTES_PER_UINT32_T)  = src3a;
-                  *(uint32_t *) (dst+0*dpitch+3*BYTES_PER_UINT32_T)  = src4a;
-                  *(uint32_t *) (dst+0*dpitch+4*BYTES_PER_UINT32_T)  = src5a;
-                  *(uint32_t *) (dst+0*dpitch+5*BYTES_PER_UINT32_T)  = src6a;
-                  *(uint32_t *) (dst+0*dpitch+6*BYTES_PER_UINT32_T)  = src7a;
-                  *(uint32_t *) (dst+0*dpitch+7*BYTES_PER_UINT32_T)  = src8a;
-                  *(uint32_t *) (dst+1*dpitch+0*BYTES_PER_UINT32_T)  = src1b;
-                  *(uint32_t *) (dst+1*dpitch+1*BYTES_PER_UINT32_T)  = src2b;
-                  *(uint32_t *) (dst+1*dpitch+2*BYTES_PER_UINT32_T)  = src3b;
-                  *(uint32_t *) (dst+1*dpitch+3*BYTES_PER_UINT32_T)  = src4b;
-                  *(uint32_t *) (dst+1*dpitch+4*BYTES_PER_UINT32_T)  = src5b;
-                  *(uint32_t *) (dst+1*dpitch+5*BYTES_PER_UINT32_T)  = src6b;
-                  *(uint32_t *) (dst+1*dpitch+6*BYTES_PER_UINT32_T)  = src7b;
-                  *(uint32_t *) (dst+1*dpitch+7*BYTES_PER_UINT32_T)  = src8b;
-                  return TRUE;
-               }
-               else {
-                  // Don't bother unrolling loops, since that won't help for more than around 8 operations.
-                  // Instead, just call multiple fixed functions.
-                  if (xdir >= 0) {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst, src, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 8 * BYTES_PER_UINT16_T, src + 8 * BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                  } else {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 8 * BYTES_PER_UINT16_T, src + 8 * BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst, src, 8, xdir, dpitch, spitch);
-                  }
-                  return TRUE;
-               }
-               break;
-      case 32: if (SW_CHECK_PITCHED_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint32x4_t src1a = vld1q_u32((uint32_t *)(src+0*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2a = vld1q_u32((uint32_t *)(src+0*spitch+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src3a = vld1q_u32((uint32_t *)(src+0*spitch+2*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src4a = vld1q_u32((uint32_t *)(src+0*spitch+3*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1b = vld1q_u32((uint32_t *)(src+1*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2b = vld1q_u32((uint32_t *)(src+1*spitch+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src3b = vld1q_u32((uint32_t *)(src+1*spitch+2*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src4b = vld1q_u32((uint32_t *)(src+1*spitch+3*BYTES_PER_UINT32X4_T));
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+0*BYTES_PER_UINT32X4_T),src1a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+1*BYTES_PER_UINT32X4_T),src2a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+2*BYTES_PER_UINT32X4_T),src3a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+3*BYTES_PER_UINT32X4_T),src4a);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+0*BYTES_PER_UINT32X4_T),src1b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+1*BYTES_PER_UINT32X4_T),src2b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+2*BYTES_PER_UINT32X4_T),src3b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+3*BYTES_PER_UINT32X4_T),src4b);
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,4*BYTES_PER_UINT16_T)) {
-                  if (xdir >= 0) {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0,                           src + 0,                            4, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (4)*BYTES_PER_UINT16_T,      src + (4)*BYTES_PER_UINT16_T,      16, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (16+4)*BYTES_PER_UINT16_T,   src + (16+4)*BYTES_PER_UINT16_T,    8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (8+16+4)*BYTES_PER_UINT16_T, src + (8+16+4)*BYTES_PER_UINT16_T,  4, xdir, dpitch, spitch);
-                  } else {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (8+16+4)*BYTES_PER_UINT16_T, src + (8+16+4)*BYTES_PER_UINT16_T,  4, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (16+4)*BYTES_PER_UINT16_T,   src + (16+4)*BYTES_PER_UINT16_T,    8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (4)*BYTES_PER_UINT16_T,      src + (4)*BYTES_PER_UINT16_T,      16, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0,                           src + 0,                            4, xdir, dpitch, spitch);
-                   }
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint64_t src1a = *(uint64_t *) (src+0*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2a = *(uint64_t *) (src+0*spitch+1*BYTES_PER_UINT64_T);
-                  uint64_t src3a = *(uint64_t *) (src+0*spitch+2*BYTES_PER_UINT64_T);
-                  uint64_t src4a = *(uint64_t *) (src+0*spitch+3*BYTES_PER_UINT64_T);
-                  uint64_t src5a = *(uint64_t *) (src+0*spitch+4*BYTES_PER_UINT64_T);
-                  uint64_t src6a = *(uint64_t *) (src+0*spitch+5*BYTES_PER_UINT64_T);
-                  uint64_t src7a = *(uint64_t *) (src+0*spitch+6*BYTES_PER_UINT64_T);
-                  uint64_t src8a = *(uint64_t *) (src+0*spitch+7*BYTES_PER_UINT64_T);
-                  uint64_t src1b = *(uint64_t *) (src+1*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2b = *(uint64_t *) (src+1*spitch+1*BYTES_PER_UINT64_T);
-                  uint64_t src3b = *(uint64_t *) (src+1*spitch+2*BYTES_PER_UINT64_T);
-                  uint64_t src4b = *(uint64_t *) (src+1*spitch+3*BYTES_PER_UINT64_T);
-                  uint64_t src5b = *(uint64_t *) (src+1*spitch+4*BYTES_PER_UINT64_T);
-                  uint64_t src6b = *(uint64_t *) (src+1*spitch+5*BYTES_PER_UINT64_T);
-                  uint64_t src7b = *(uint64_t *) (src+1*spitch+6*BYTES_PER_UINT64_T);
-                  uint64_t src8b = *(uint64_t *) (src+1*spitch+7*BYTES_PER_UINT64_T);
-                  *(uint64_t *) (dst+0*dpitch+0*BYTES_PER_UINT64_T)  = src1a;
-                  *(uint64_t *) (dst+0*dpitch+1*BYTES_PER_UINT64_T)  = src2a;
-                  *(uint64_t *) (dst+0*dpitch+2*BYTES_PER_UINT64_T)  = src3a;
-                  *(uint64_t *) (dst+0*dpitch+3*BYTES_PER_UINT64_T)  = src4a;
-                  *(uint64_t *) (dst+0*dpitch+4*BYTES_PER_UINT64_T)  = src5a;
-                  *(uint64_t *) (dst+0*dpitch+5*BYTES_PER_UINT64_T)  = src6a;
-                  *(uint64_t *) (dst+0*dpitch+6*BYTES_PER_UINT64_T)  = src7a;
-                  *(uint64_t *) (dst+0*dpitch+7*BYTES_PER_UINT64_T)  = src8a;
-                  *(uint64_t *) (dst+1*dpitch+0*BYTES_PER_UINT64_T)  = src1b;
-                  *(uint64_t *) (dst+1*dpitch+1*BYTES_PER_UINT64_T)  = src2b;
-                  *(uint64_t *) (dst+1*dpitch+2*BYTES_PER_UINT64_T)  = src3b;
-                  *(uint64_t *) (dst+1*dpitch+3*BYTES_PER_UINT64_T)  = src4b;
-                  *(uint64_t *) (dst+1*dpitch+4*BYTES_PER_UINT64_T)  = src5b;
-                  *(uint64_t *) (dst+1*dpitch+5*BYTES_PER_UINT64_T)  = src6b;
-                  *(uint64_t *) (dst+1*dpitch+6*BYTES_PER_UINT64_T)  = src7b;
-                  *(uint64_t *) (dst+1*dpitch+7*BYTES_PER_UINT64_T)  = src8b;
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,2*BYTES_PER_UINT16_T)) {
-                  if (xdir >= 0) {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0,                          src + 0                         , 2, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (0*8+2)*BYTES_PER_UINT16_T, src + (0*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (1*8+2)*BYTES_PER_UINT16_T, src + (1*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (2*8+2)*BYTES_PER_UINT16_T, src + (2*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (3*8+2)*BYTES_PER_UINT16_T, src + (3*8+2)*BYTES_PER_UINT16_T, 6, xdir, dpitch, spitch);
-                  } else {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (3*8+2)*BYTES_PER_UINT16_T, src + (3*8+2)*BYTES_PER_UINT16_T, 6, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (2*8+2)*BYTES_PER_UINT16_T, src + (2*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (1*8+2)*BYTES_PER_UINT16_T, src + (1*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (0*8+2)*BYTES_PER_UINT16_T, src + (0*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0,                          src + 0                         , 2, xdir, dpitch, spitch);
-                  }
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,BYTES_PER_UINT16_T)) {
-                  if (xdir >= 0) {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0,                          src + 0                         , 1, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (0*8+1)*BYTES_PER_UINT16_T, src + (0*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (1*8+1)*BYTES_PER_UINT16_T, src + (1*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (2*8+1)*BYTES_PER_UINT16_T, src + (2*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (3*8+1)*BYTES_PER_UINT16_T, src + (3*8+1)*BYTES_PER_UINT16_T, 7, xdir, dpitch, spitch);
-                  } else {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (3*8+1)*BYTES_PER_UINT16_T, src + (3*8+1)*BYTES_PER_UINT16_T, 7, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (2*8+1)*BYTES_PER_UINT16_T, src + (2*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (1*8+1)*BYTES_PER_UINT16_T, src + (1*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (0*8+1)*BYTES_PER_UINT16_T, src + (0*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0,                          src + 0                         , 1, xdir, dpitch, spitch);
-                  }
-                  return TRUE;
-               }
-               else {
-                  if (xdir >= 0) {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0*8*BYTES_PER_UINT16_T, src + 0*8*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 1*8*BYTES_PER_UINT16_T, src + 1*8*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 2*8*BYTES_PER_UINT16_T, src + 2*8*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 3*8*BYTES_PER_UINT16_T, src + 3*8*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                  } else {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 3*8*BYTES_PER_UINT16_T, src + 3*8*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 2*8*BYTES_PER_UINT16_T, src + 2*8*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 1*8*BYTES_PER_UINT16_T, src + 1*8*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0*8*BYTES_PER_UINT16_T, src + 0*8*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                  }
-                  return TRUE;
-               }
-               break;
-      case 64: if (SW_CHECK_PITCHED_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint32x4_t src1a = vld1q_u32((uint32_t *)(src+0*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2a = vld1q_u32((uint32_t *)(src+0*spitch+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src3a = vld1q_u32((uint32_t *)(src+0*spitch+2*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src4a = vld1q_u32((uint32_t *)(src+0*spitch+3*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src5a = vld1q_u32((uint32_t *)(src+0*spitch+4*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src6a = vld1q_u32((uint32_t *)(src+0*spitch+5*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src7a = vld1q_u32((uint32_t *)(src+0*spitch+6*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src8a = vld1q_u32((uint32_t *)(src+0*spitch+7*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1b = vld1q_u32((uint32_t *)(src+1*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2b = vld1q_u32((uint32_t *)(src+1*spitch+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src3b = vld1q_u32((uint32_t *)(src+1*spitch+2*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src4b = vld1q_u32((uint32_t *)(src+1*spitch+3*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src5b = vld1q_u32((uint32_t *)(src+1*spitch+4*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src6b = vld1q_u32((uint32_t *)(src+1*spitch+5*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src7b = vld1q_u32((uint32_t *)(src+1*spitch+6*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src8b = vld1q_u32((uint32_t *)(src+1*spitch+7*BYTES_PER_UINT32X4_T));
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+0*BYTES_PER_UINT32X4_T),src1a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+1*BYTES_PER_UINT32X4_T),src2a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+2*BYTES_PER_UINT32X4_T),src3a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+3*BYTES_PER_UINT32X4_T),src4a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+4*BYTES_PER_UINT32X4_T),src5a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+5*BYTES_PER_UINT32X4_T),src6a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+6*BYTES_PER_UINT32X4_T),src7a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+7*BYTES_PER_UINT32X4_T),src8a);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+0*BYTES_PER_UINT32X4_T),src1b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+1*BYTES_PER_UINT32X4_T),src2b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+2*BYTES_PER_UINT32X4_T),src3b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+3*BYTES_PER_UINT32X4_T),src4b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+4*BYTES_PER_UINT32X4_T),src5b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+5*BYTES_PER_UINT32X4_T),src6b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+6*BYTES_PER_UINT32X4_T),src7b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+7*BYTES_PER_UINT32X4_T),src8b);
-                  return TRUE;
-               }//HERE
-               else if (SW_CHECK_PITCHED_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,4*BYTES_PER_UINT16_T)) {
-                  if (xdir >= 0) {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0,                             src + 0,                             4,    xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (0*16+4)*BYTES_PER_UINT16_T,   src + (0*16+4)*BYTES_PER_UINT16_T,   2*16, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (2*16+4)*BYTES_PER_UINT16_T,   src + (2*16+4)*BYTES_PER_UINT16_T,   16,   xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (3*16+4)*BYTES_PER_UINT16_T,   src + (3*16+4)*BYTES_PER_UINT16_T,   8,    xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (8+3*16+4)*BYTES_PER_UINT16_T, src + (8+3*16+4)*BYTES_PER_UINT16_T, 4,    xdir, dpitch, spitch);
-                  } else {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (8+3*16+4)*BYTES_PER_UINT16_T, src + (8+3*16+4)*BYTES_PER_UINT16_T, 4,    xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (3*16+4)*BYTES_PER_UINT16_T,   src + (3*16+4)*BYTES_PER_UINT16_T,   8,    xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (2*16+4)*BYTES_PER_UINT16_T,   src + (2*16+4)*BYTES_PER_UINT16_T,   16,   xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (0*16+4)*BYTES_PER_UINT16_T,   src + (0*16+4)*BYTES_PER_UINT16_T,   2*16, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0,                             src + 0,                             4,    xdir, dpitch, spitch);
-                  }
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,2*BYTES_PER_UINT16_T)) {
-                  if (xdir >= 0) {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0,                          src + 0                         , 2, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (0*8+2)*BYTES_PER_UINT16_T, src + (0*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (1*8+2)*BYTES_PER_UINT16_T, src + (1*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (2*8+2)*BYTES_PER_UINT16_T, src + (2*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (3*8+2)*BYTES_PER_UINT16_T, src + (3*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (4*8+2)*BYTES_PER_UINT16_T, src + (4*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (5*8+2)*BYTES_PER_UINT16_T, src + (5*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (6*8+2)*BYTES_PER_UINT16_T, src + (6*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (7*8+2)*BYTES_PER_UINT16_T, src + (7*8+2)*BYTES_PER_UINT16_T, 6, xdir, dpitch, spitch);
-                  } else {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (7*8+2)*BYTES_PER_UINT16_T, src + (7*8+2)*BYTES_PER_UINT16_T, 6, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (6*8+2)*BYTES_PER_UINT16_T, src + (6*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (5*8+2)*BYTES_PER_UINT16_T, src + (5*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (4*8+2)*BYTES_PER_UINT16_T, src + (4*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (3*8+2)*BYTES_PER_UINT16_T, src + (3*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (2*8+2)*BYTES_PER_UINT16_T, src + (2*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (1*8+2)*BYTES_PER_UINT16_T, src + (1*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (0*8+2)*BYTES_PER_UINT16_T, src + (0*8+2)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0,                          src + 0                         , 2, xdir, dpitch, spitch);
-                  }
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,BYTES_PER_UINT16_T)) {
-                  if (xdir >= 0) {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0,                          src + 0                         , 1, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (0*8+1)*BYTES_PER_UINT16_T, src + (0*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (1*8+1)*BYTES_PER_UINT16_T, src + (1*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (2*8+1)*BYTES_PER_UINT16_T, src + (2*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (3*8+1)*BYTES_PER_UINT16_T, src + (3*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (4*8+1)*BYTES_PER_UINT16_T, src + (4*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (5*8+1)*BYTES_PER_UINT16_T, src + (5*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (6*8+1)*BYTES_PER_UINT16_T, src + (6*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (7*8+1)*BYTES_PER_UINT16_T, src + (7*8+1)*BYTES_PER_UINT16_T, 7, xdir, dpitch, spitch);
-                  } else {
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (7*8+1)*BYTES_PER_UINT16_T, src + (7*8+1)*BYTES_PER_UINT16_T, 7, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (6*8+1)*BYTES_PER_UINT16_T, src + (6*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (5*8+1)*BYTES_PER_UINT16_T, src + (5*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (4*8+1)*BYTES_PER_UINT16_T, src + (4*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (3*8+1)*BYTES_PER_UINT16_T, src + (3*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (2*8+1)*BYTES_PER_UINT16_T, src + (2*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (1*8+1)*BYTES_PER_UINT16_T, src + (1*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + (0*8+1)*BYTES_PER_UINT16_T, src + (0*8+1)*BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths2Rows_Unaligned(dst + 0,                          src + 0                         , 1, xdir, dpitch, spitch);
-                  }
-                  return TRUE;
-               }
-               break;
    }
 
    return FALSE;
@@ -1161,484 +586,7 @@ swCopy16BppSmallFixedWidths4Rows_Unaligned(unsigned char *dst, unsigned char *sr
                }
                return TRUE;
                break;
-      case  7: if (xdir >= 0) {
-                  swCopy16BppSmallFixedWidths4Rows_Unaligned(dst, src, 4, xdir, dpitch, spitch);
-                  swCopy16BppSmallFixedWidths4Rows_Unaligned(dst + 4 * BYTES_PER_UINT16_T, src + 4 * BYTES_PER_UINT16_T, 3, xdir, dpitch, spitch);
-               } else {
-                  swCopy16BppSmallFixedWidths4Rows_Unaligned(dst + 4 * BYTES_PER_UINT16_T, src + 4 * BYTES_PER_UINT16_T, 3, xdir, dpitch, spitch);
-                  swCopy16BppSmallFixedWidths4Rows_Unaligned(dst, src, 4, xdir, dpitch, spitch);
-               }
-               return TRUE;
-               break;
-      // TODO: Add more alignment checks for 8 pixel-wide cases for performance reasons?
-      //       For example, handling (SW_CHECK_PITCHED_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,DOUBLE_WORD_ALIGNMENT_BYTE_SIZE/2)) and related half-aligned cases...
-      case  8: if (SW_CHECK_PITCHED_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint32x4_t src1a = vld1q_u32((uint32_t *)(src+0*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1b = vld1q_u32((uint32_t *)(src+1*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1c = vld1q_u32((uint32_t *)(src+2*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1d = vld1q_u32((uint32_t *)(src+3*spitch+0*BYTES_PER_UINT32X4_T));
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+0*BYTES_PER_UINT32X4_T),src1a);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+0*BYTES_PER_UINT32X4_T),src1b);
-                  vst1q_u32((uint32_t *)(dst+2*dpitch+0*BYTES_PER_UINT32X4_T),src1c);
-                  vst1q_u32((uint32_t *)(dst+3*dpitch+0*BYTES_PER_UINT32X4_T),src1d);
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint64_t src1a = *(uint64_t *) (src+0*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2a = *(uint64_t *) (src+0*spitch+1*BYTES_PER_UINT64_T);
-                  uint64_t src1b = *(uint64_t *) (src+1*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2b = *(uint64_t *) (src+1*spitch+1*BYTES_PER_UINT64_T);
-                  uint64_t src1c = *(uint64_t *) (src+2*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2c = *(uint64_t *) (src+2*spitch+1*BYTES_PER_UINT64_T);
-                  uint64_t src1d = *(uint64_t *) (src+3*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2d = *(uint64_t *) (src+3*spitch+1*BYTES_PER_UINT64_T);
-                  *(uint64_t *) (dst+0*dpitch+0*BYTES_PER_UINT64_T)  = src1a;
-                  *(uint64_t *) (dst+0*dpitch+1*BYTES_PER_UINT64_T)  = src2a;
-                  *(uint64_t *) (dst+1*dpitch+0*BYTES_PER_UINT64_T)  = src1b;
-                  *(uint64_t *) (dst+1*dpitch+1*BYTES_PER_UINT64_T)  = src2b;
-                  *(uint64_t *) (dst+2*dpitch+0*BYTES_PER_UINT64_T)  = src1c;
-                  *(uint64_t *) (dst+2*dpitch+1*BYTES_PER_UINT64_T)  = src2c;
-                  *(uint64_t *) (dst+3*dpitch+0*BYTES_PER_UINT64_T)  = src1d;
-                  *(uint64_t *) (dst+3*dpitch+1*BYTES_PER_UINT64_T)  = src2d;
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint32_t src1a = *(uint32_t *) (src+0*spitch+0*BYTES_PER_UINT32_T);
-                  uint32_t src2a = *(uint32_t *) (src+0*spitch+1*BYTES_PER_UINT32_T);
-                  uint32_t src3a = *(uint32_t *) (src+0*spitch+2*BYTES_PER_UINT32_T);
-                  uint32_t src4a = *(uint32_t *) (src+0*spitch+3*BYTES_PER_UINT32_T);
-                  uint32_t src1b = *(uint32_t *) (src+1*spitch+0*BYTES_PER_UINT32_T);
-                  uint32_t src2b = *(uint32_t *) (src+1*spitch+1*BYTES_PER_UINT32_T);
-                  uint32_t src3b = *(uint32_t *) (src+1*spitch+2*BYTES_PER_UINT32_T);
-                  uint32_t src4b = *(uint32_t *) (src+1*spitch+3*BYTES_PER_UINT32_T);
-                  uint32_t src1c = *(uint32_t *) (src+2*spitch+0*BYTES_PER_UINT32_T);
-                  uint32_t src2c = *(uint32_t *) (src+2*spitch+1*BYTES_PER_UINT32_T);
-                  uint32_t src3c = *(uint32_t *) (src+2*spitch+2*BYTES_PER_UINT32_T);
-                  uint32_t src4c = *(uint32_t *) (src+2*spitch+3*BYTES_PER_UINT32_T);
-                  uint32_t src1d = *(uint32_t *) (src+3*spitch+0*BYTES_PER_UINT32_T);
-                  uint32_t src2d = *(uint32_t *) (src+3*spitch+1*BYTES_PER_UINT32_T);
-                  uint32_t src3d = *(uint32_t *) (src+3*spitch+2*BYTES_PER_UINT32_T);
-                  uint32_t src4d = *(uint32_t *) (src+3*spitch+3*BYTES_PER_UINT32_T);
-                  *(uint32_t *) (dst+0*dpitch+0*BYTES_PER_UINT32_T)  = src1a;
-                  *(uint32_t *) (dst+0*dpitch+1*BYTES_PER_UINT32_T)  = src2a;
-                  *(uint32_t *) (dst+0*dpitch+2*BYTES_PER_UINT32_T)  = src3a;
-                  *(uint32_t *) (dst+0*dpitch+3*BYTES_PER_UINT32_T)  = src4a;
-                  *(uint32_t *) (dst+1*dpitch+0*BYTES_PER_UINT32_T)  = src1b;
-                  *(uint32_t *) (dst+1*dpitch+1*BYTES_PER_UINT32_T)  = src2b;
-                  *(uint32_t *) (dst+1*dpitch+2*BYTES_PER_UINT32_T)  = src3b;
-                  *(uint32_t *) (dst+1*dpitch+3*BYTES_PER_UINT32_T)  = src4b;
-                  *(uint32_t *) (dst+2*dpitch+0*BYTES_PER_UINT32_T)  = src1c;
-                  *(uint32_t *) (dst+2*dpitch+1*BYTES_PER_UINT32_T)  = src2c;
-                  *(uint32_t *) (dst+2*dpitch+2*BYTES_PER_UINT32_T)  = src3c;
-                  *(uint32_t *) (dst+2*dpitch+3*BYTES_PER_UINT32_T)  = src4c;
-                  *(uint32_t *) (dst+3*dpitch+0*BYTES_PER_UINT32_T)  = src1d;
-                  *(uint32_t *) (dst+3*dpitch+1*BYTES_PER_UINT32_T)  = src2d;
-                  *(uint32_t *) (dst+3*dpitch+2*BYTES_PER_UINT32_T)  = src3d;
-                  *(uint32_t *) (dst+3*dpitch+3*BYTES_PER_UINT32_T)  = src4d;
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,BYTES_PER_UINT16_T)) {
-                  uint16_t src1a = *(uint16_t *) (src+0*spitch+0);
-                  uint32_t src2a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T);
-                  uint32_t src3a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T);
-                  uint32_t src4a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T);
-                  uint16_t src5a = *(uint16_t *) (src+0*spitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T);
-                  uint16_t src1b = *(uint16_t *) (src+1*spitch+0);
-                  uint32_t src2b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T);
-                  uint32_t src3b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T);
-                  uint32_t src4b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T);
-                  uint16_t src5b = *(uint16_t *) (src+1*spitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T);
-                  uint16_t src1c = *(uint16_t *) (src+2*spitch+0);
-                  uint32_t src2c = *(uint32_t *) (src+2*spitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T);
-                  uint32_t src3c = *(uint32_t *) (src+2*spitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T);
-                  uint32_t src4c = *(uint32_t *) (src+2*spitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T);
-                  uint16_t src5c = *(uint16_t *) (src+2*spitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T);
-                  uint16_t src1d = *(uint16_t *) (src+3*spitch+0);
-                  uint32_t src2d = *(uint32_t *) (src+3*spitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T);
-                  uint32_t src3d = *(uint32_t *) (src+3*spitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T);
-                  uint32_t src4d = *(uint32_t *) (src+3*spitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T);
-                  uint16_t src5d = *(uint16_t *) (src+3*spitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T);
-                  *(uint16_t *) (dst+0*dpitch+0)                                        = src1a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T)  = src2a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T)  = src3a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T)  = src4a;
-                  *(uint16_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T)  = src5a;
-                  *(uint16_t *) (dst+1*dpitch+0)                                        = src1b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T)  = src2b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T)  = src3b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T)  = src4b;
-                  *(uint16_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T)  = src5b;
-                  *(uint16_t *) (dst+2*dpitch+0)                                        = src1c;
-                  *(uint32_t *) (dst+2*dpitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T)  = src2c;
-                  *(uint32_t *) (dst+2*dpitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T)  = src3c;
-                  *(uint32_t *) (dst+2*dpitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T)  = src4c;
-                  *(uint16_t *) (dst+2*dpitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T)  = src5c;
-                  *(uint16_t *) (dst+3*dpitch+0)                                        = src1d;
-                  *(uint32_t *) (dst+3*dpitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T)  = src2d;
-                  *(uint32_t *) (dst+3*dpitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T)  = src3d;
-                  *(uint32_t *) (dst+3*dpitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T)  = src4d;
-                  *(uint16_t *) (dst+3*dpitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T)  = src5d;
-                  return TRUE;
-               }
-               else {
-                  uint16_t src1a = *(uint16_t *) (src+0*spitch+0*BYTES_PER_UINT16_T);
-                  uint16_t src2a = *(uint16_t *) (src+0*spitch+1*BYTES_PER_UINT16_T);
-                  uint16_t src3a = *(uint16_t *) (src+0*spitch+2*BYTES_PER_UINT16_T);
-                  uint16_t src4a = *(uint16_t *) (src+0*spitch+3*BYTES_PER_UINT16_T);
-                  uint16_t src5a = *(uint16_t *) (src+0*spitch+4*BYTES_PER_UINT16_T);
-                  uint16_t src6a = *(uint16_t *) (src+0*spitch+5*BYTES_PER_UINT16_T);
-                  uint16_t src7a = *(uint16_t *) (src+0*spitch+6*BYTES_PER_UINT16_T);
-                  uint16_t src8a = *(uint16_t *) (src+0*spitch+7*BYTES_PER_UINT16_T);
-                  uint16_t src1b = *(uint16_t *) (src+1*spitch+0*BYTES_PER_UINT16_T);
-                  uint16_t src2b = *(uint16_t *) (src+1*spitch+1*BYTES_PER_UINT16_T);
-                  uint16_t src3b = *(uint16_t *) (src+1*spitch+2*BYTES_PER_UINT16_T);
-                  uint16_t src4b = *(uint16_t *) (src+1*spitch+3*BYTES_PER_UINT16_T);
-                  uint16_t src5b = *(uint16_t *) (src+1*spitch+4*BYTES_PER_UINT16_T);
-                  uint16_t src6b = *(uint16_t *) (src+1*spitch+5*BYTES_PER_UINT16_T);
-                  uint16_t src7b = *(uint16_t *) (src+1*spitch+6*BYTES_PER_UINT16_T);
-                  uint16_t src8b = *(uint16_t *) (src+1*spitch+7*BYTES_PER_UINT16_T);
-                  uint16_t src1c = *(uint16_t *) (src+2*spitch+0*BYTES_PER_UINT16_T);
-                  uint16_t src2c = *(uint16_t *) (src+2*spitch+1*BYTES_PER_UINT16_T);
-                  uint16_t src3c = *(uint16_t *) (src+2*spitch+2*BYTES_PER_UINT16_T);
-                  uint16_t src4c = *(uint16_t *) (src+2*spitch+3*BYTES_PER_UINT16_T);
-                  uint16_t src5c = *(uint16_t *) (src+2*spitch+4*BYTES_PER_UINT16_T);
-                  uint16_t src6c = *(uint16_t *) (src+2*spitch+5*BYTES_PER_UINT16_T);
-                  uint16_t src7c = *(uint16_t *) (src+2*spitch+6*BYTES_PER_UINT16_T);
-                  uint16_t src8c = *(uint16_t *) (src+2*spitch+7*BYTES_PER_UINT16_T);
-                  uint16_t src1d = *(uint16_t *) (src+3*spitch+0*BYTES_PER_UINT16_T);
-                  uint16_t src2d = *(uint16_t *) (src+3*spitch+1*BYTES_PER_UINT16_T);
-                  uint16_t src3d = *(uint16_t *) (src+3*spitch+2*BYTES_PER_UINT16_T);
-                  uint16_t src4d = *(uint16_t *) (src+3*spitch+3*BYTES_PER_UINT16_T);
-                  uint16_t src5d = *(uint16_t *) (src+3*spitch+4*BYTES_PER_UINT16_T);
-                  uint16_t src6d = *(uint16_t *) (src+3*spitch+5*BYTES_PER_UINT16_T);
-                  uint16_t src7d = *(uint16_t *) (src+3*spitch+6*BYTES_PER_UINT16_T);
-                  uint16_t src8d = *(uint16_t *) (src+3*spitch+7*BYTES_PER_UINT16_T);
-                  *(uint16_t *) (dst+0*dpitch+0*BYTES_PER_UINT16_T)  = src1a;
-                  *(uint16_t *) (dst+0*dpitch+1*BYTES_PER_UINT16_T)  = src2a;
-                  *(uint16_t *) (dst+0*dpitch+2*BYTES_PER_UINT16_T)  = src3a;
-                  *(uint16_t *) (dst+0*dpitch+3*BYTES_PER_UINT16_T)  = src4a;
-                  *(uint16_t *) (dst+0*dpitch+4*BYTES_PER_UINT16_T)  = src5a;
-                  *(uint16_t *) (dst+0*dpitch+5*BYTES_PER_UINT16_T)  = src6a;
-                  *(uint16_t *) (dst+0*dpitch+6*BYTES_PER_UINT16_T)  = src7a;
-                  *(uint16_t *) (dst+0*dpitch+7*BYTES_PER_UINT16_T)  = src8a;
-                  *(uint16_t *) (dst+1*dpitch+0*BYTES_PER_UINT16_T)  = src1b;
-                  *(uint16_t *) (dst+1*dpitch+1*BYTES_PER_UINT16_T)  = src2b;
-                  *(uint16_t *) (dst+1*dpitch+2*BYTES_PER_UINT16_T)  = src3b;
-                  *(uint16_t *) (dst+1*dpitch+3*BYTES_PER_UINT16_T)  = src4b;
-                  *(uint16_t *) (dst+1*dpitch+4*BYTES_PER_UINT16_T)  = src5b;
-                  *(uint16_t *) (dst+1*dpitch+5*BYTES_PER_UINT16_T)  = src6b;
-                  *(uint16_t *) (dst+1*dpitch+6*BYTES_PER_UINT16_T)  = src7b;
-                  *(uint16_t *) (dst+1*dpitch+7*BYTES_PER_UINT16_T)  = src8b;
-                  *(uint16_t *) (dst+2*dpitch+0*BYTES_PER_UINT16_T)  = src1c;
-                  *(uint16_t *) (dst+2*dpitch+1*BYTES_PER_UINT16_T)  = src2c;
-                  *(uint16_t *) (dst+2*dpitch+2*BYTES_PER_UINT16_T)  = src3c;
-                  *(uint16_t *) (dst+2*dpitch+3*BYTES_PER_UINT16_T)  = src4c;
-                  *(uint16_t *) (dst+2*dpitch+4*BYTES_PER_UINT16_T)  = src5c;
-                  *(uint16_t *) (dst+2*dpitch+5*BYTES_PER_UINT16_T)  = src6c;
-                  *(uint16_t *) (dst+2*dpitch+6*BYTES_PER_UINT16_T)  = src7c;
-                  *(uint16_t *) (dst+2*dpitch+7*BYTES_PER_UINT16_T)  = src8c;
-                  *(uint16_t *) (dst+3*dpitch+0*BYTES_PER_UINT16_T)  = src1d;
-                  *(uint16_t *) (dst+3*dpitch+1*BYTES_PER_UINT16_T)  = src2d;
-                  *(uint16_t *) (dst+3*dpitch+2*BYTES_PER_UINT16_T)  = src3d;
-                  *(uint16_t *) (dst+3*dpitch+3*BYTES_PER_UINT16_T)  = src4d;
-                  *(uint16_t *) (dst+3*dpitch+4*BYTES_PER_UINT16_T)  = src5d;
-                  *(uint16_t *) (dst+3*dpitch+5*BYTES_PER_UINT16_T)  = src6d;
-                  *(uint16_t *) (dst+3*dpitch+6*BYTES_PER_UINT16_T)  = src7d;
-                  *(uint16_t *) (dst+3*dpitch+7*BYTES_PER_UINT16_T)  = src8d;
-                  return TRUE;
-               }
-               break;
-      case 16: if (SW_CHECK_PITCHED_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint32x4_t src1a = vld1q_u32((uint32_t *)(src+0*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2a = vld1q_u32((uint32_t *)(src+0*spitch+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1b = vld1q_u32((uint32_t *)(src+1*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2b = vld1q_u32((uint32_t *)(src+1*spitch+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1c = vld1q_u32((uint32_t *)(src+2*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2c = vld1q_u32((uint32_t *)(src+2*spitch+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1d = vld1q_u32((uint32_t *)(src+3*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2d = vld1q_u32((uint32_t *)(src+3*spitch+1*BYTES_PER_UINT32X4_T));
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+0*BYTES_PER_UINT32X4_T),src1a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+1*BYTES_PER_UINT32X4_T),src2a);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+0*BYTES_PER_UINT32X4_T),src1b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+1*BYTES_PER_UINT32X4_T),src2b);
-                  vst1q_u32((uint32_t *)(dst+2*dpitch+0*BYTES_PER_UINT32X4_T),src1c);
-                  vst1q_u32((uint32_t *)(dst+2*dpitch+1*BYTES_PER_UINT32X4_T),src2c);
-                  vst1q_u32((uint32_t *)(dst+3*dpitch+0*BYTES_PER_UINT32X4_T),src1d);
-                  vst1q_u32((uint32_t *)(dst+3*dpitch+1*BYTES_PER_UINT32X4_T),src2d);
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint64_t src1a = *(uint64_t *) (src+0*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2a = *(uint64_t *) (src+0*spitch+1*BYTES_PER_UINT64_T);
-                  uint64_t src3a = *(uint64_t *) (src+0*spitch+2*BYTES_PER_UINT64_T);
-                  uint64_t src4a = *(uint64_t *) (src+0*spitch+3*BYTES_PER_UINT64_T);
-                  uint64_t src1b = *(uint64_t *) (src+1*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2b = *(uint64_t *) (src+1*spitch+1*BYTES_PER_UINT64_T);
-                  uint64_t src3b = *(uint64_t *) (src+1*spitch+2*BYTES_PER_UINT64_T);
-                  uint64_t src4b = *(uint64_t *) (src+1*spitch+3*BYTES_PER_UINT64_T);
-                  uint64_t src1c = *(uint64_t *) (src+2*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2c = *(uint64_t *) (src+2*spitch+1*BYTES_PER_UINT64_T);
-                  uint64_t src3c = *(uint64_t *) (src+2*spitch+2*BYTES_PER_UINT64_T);
-                  uint64_t src4c = *(uint64_t *) (src+2*spitch+3*BYTES_PER_UINT64_T);
-                  uint64_t src1d = *(uint64_t *) (src+3*spitch+0*BYTES_PER_UINT64_T);
-                  uint64_t src2d = *(uint64_t *) (src+3*spitch+1*BYTES_PER_UINT64_T);
-                  uint64_t src3d = *(uint64_t *) (src+3*spitch+2*BYTES_PER_UINT64_T);
-                  uint64_t src4d = *(uint64_t *) (src+3*spitch+3*BYTES_PER_UINT64_T);
-                  *(uint64_t *) (dst+0*dpitch+0*BYTES_PER_UINT64_T)  = src1a;
-                  *(uint64_t *) (dst+0*dpitch+1*BYTES_PER_UINT64_T)  = src2a;
-                  *(uint64_t *) (dst+0*dpitch+2*BYTES_PER_UINT64_T)  = src3a;
-                  *(uint64_t *) (dst+0*dpitch+3*BYTES_PER_UINT64_T)  = src4a;
-                  *(uint64_t *) (dst+1*dpitch+0*BYTES_PER_UINT64_T)  = src1b;
-                  *(uint64_t *) (dst+1*dpitch+1*BYTES_PER_UINT64_T)  = src2b;
-                  *(uint64_t *) (dst+1*dpitch+2*BYTES_PER_UINT64_T)  = src3b;
-                  *(uint64_t *) (dst+1*dpitch+3*BYTES_PER_UINT64_T)  = src4b;
-                  *(uint64_t *) (dst+2*dpitch+0*BYTES_PER_UINT64_T)  = src1c;
-                  *(uint64_t *) (dst+2*dpitch+1*BYTES_PER_UINT64_T)  = src2c;
-                  *(uint64_t *) (dst+2*dpitch+2*BYTES_PER_UINT64_T)  = src3c;
-                  *(uint64_t *) (dst+2*dpitch+3*BYTES_PER_UINT64_T)  = src4c;
-                  *(uint64_t *) (dst+3*dpitch+0*BYTES_PER_UINT64_T)  = src1d;
-                  *(uint64_t *) (dst+3*dpitch+1*BYTES_PER_UINT64_T)  = src2d;
-                  *(uint64_t *) (dst+3*dpitch+2*BYTES_PER_UINT64_T)  = src3d;
-                  *(uint64_t *) (dst+3*dpitch+3*BYTES_PER_UINT64_T)  = src4d;
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,2*BYTES_PER_UINT16_T)) {
-                  uint32_t src1a = *(uint32_t *) (src+0*spitch+0);
-                  uint64_t src2a = *(uint64_t *) (src+0*spitch+BYTES_PER_UINT32_T+0*BYTES_PER_UINT64_T);
-                  uint64_t src3a = *(uint64_t *) (src+0*spitch+BYTES_PER_UINT32_T+1*BYTES_PER_UINT64_T);
-                  uint64_t src4a = *(uint64_t *) (src+0*spitch+BYTES_PER_UINT32_T+2*BYTES_PER_UINT64_T);
-                  uint32_t src5a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT32_T+3*BYTES_PER_UINT64_T);
-                  uint32_t src1b = *(uint32_t *) (src+1*spitch+0);
-                  uint64_t src2b = *(uint64_t *) (src+1*spitch+BYTES_PER_UINT32_T+0*BYTES_PER_UINT64_T);
-                  uint64_t src3b = *(uint64_t *) (src+1*spitch+BYTES_PER_UINT32_T+1*BYTES_PER_UINT64_T);
-                  uint64_t src4b = *(uint64_t *) (src+1*spitch+BYTES_PER_UINT32_T+2*BYTES_PER_UINT64_T);
-                  uint32_t src5b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT32_T+3*BYTES_PER_UINT64_T);
-                  uint32_t src1c = *(uint32_t *) (src+2*spitch+0);
-                  uint64_t src2c = *(uint64_t *) (src+2*spitch+BYTES_PER_UINT32_T+0*BYTES_PER_UINT64_T);
-                  uint64_t src3c = *(uint64_t *) (src+2*spitch+BYTES_PER_UINT32_T+1*BYTES_PER_UINT64_T);
-                  uint64_t src4c = *(uint64_t *) (src+2*spitch+BYTES_PER_UINT32_T+2*BYTES_PER_UINT64_T);
-                  uint32_t src5c = *(uint32_t *) (src+2*spitch+BYTES_PER_UINT32_T+3*BYTES_PER_UINT64_T);
-                  uint32_t src1d = *(uint32_t *) (src+3*spitch+0);
-                  uint64_t src2d = *(uint64_t *) (src+3*spitch+BYTES_PER_UINT32_T+0*BYTES_PER_UINT64_T);
-                  uint64_t src3d = *(uint64_t *) (src+3*spitch+BYTES_PER_UINT32_T+1*BYTES_PER_UINT64_T);
-                  uint64_t src4d = *(uint64_t *) (src+3*spitch+BYTES_PER_UINT32_T+2*BYTES_PER_UINT64_T);
-                  uint32_t src5d = *(uint32_t *) (src+3*spitch+BYTES_PER_UINT32_T+3*BYTES_PER_UINT64_T);
-                  *(uint32_t *) (dst+0*dpitch+0)                                        = src1a;
-                  *(uint64_t *) (dst+0*dpitch+BYTES_PER_UINT32_T+0*BYTES_PER_UINT64_T)  = src2a;
-                  *(uint64_t *) (dst+0*dpitch+BYTES_PER_UINT32_T+1*BYTES_PER_UINT64_T)  = src3a;
-                  *(uint64_t *) (dst+0*dpitch+BYTES_PER_UINT32_T+2*BYTES_PER_UINT64_T)  = src4a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT32_T+3*BYTES_PER_UINT64_T)  = src5a;
-                  *(uint32_t *) (dst+1*dpitch+0)                                        = src1b;
-                  *(uint64_t *) (dst+1*dpitch+BYTES_PER_UINT32_T+0*BYTES_PER_UINT64_T)  = src2b;
-                  *(uint64_t *) (dst+1*dpitch+BYTES_PER_UINT32_T+1*BYTES_PER_UINT64_T)  = src3b;
-                  *(uint64_t *) (dst+1*dpitch+BYTES_PER_UINT32_T+2*BYTES_PER_UINT64_T)  = src4b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT32_T+3*BYTES_PER_UINT64_T)  = src5b;
-                  *(uint32_t *) (dst+2*dpitch+0)                                        = src1c;
-                  *(uint64_t *) (dst+2*dpitch+BYTES_PER_UINT32_T+0*BYTES_PER_UINT64_T)  = src2c;
-                  *(uint64_t *) (dst+2*dpitch+BYTES_PER_UINT32_T+1*BYTES_PER_UINT64_T)  = src3c;
-                  *(uint64_t *) (dst+2*dpitch+BYTES_PER_UINT32_T+2*BYTES_PER_UINT64_T)  = src4c;
-                  *(uint32_t *) (dst+2*dpitch+BYTES_PER_UINT32_T+3*BYTES_PER_UINT64_T)  = src5c;
-                  *(uint32_t *) (dst+3*dpitch+0)                                        = src1d;
-                  *(uint64_t *) (dst+3*dpitch+BYTES_PER_UINT32_T+0*BYTES_PER_UINT64_T)  = src2d;
-                  *(uint64_t *) (dst+3*dpitch+BYTES_PER_UINT32_T+1*BYTES_PER_UINT64_T)  = src3d;
-                  *(uint64_t *) (dst+3*dpitch+BYTES_PER_UINT32_T+2*BYTES_PER_UINT64_T)  = src4d;
-                  *(uint32_t *) (dst+3*dpitch+BYTES_PER_UINT32_T+3*BYTES_PER_UINT64_T)  = src5d;
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint32_t src1a = *(uint32_t *) (src+0*spitch+0*BYTES_PER_UINT32_T);
-                  uint32_t src2a = *(uint32_t *) (src+0*spitch+1*BYTES_PER_UINT32_T);
-                  uint32_t src3a = *(uint32_t *) (src+0*spitch+2*BYTES_PER_UINT32_T);
-                  uint32_t src4a = *(uint32_t *) (src+0*spitch+3*BYTES_PER_UINT32_T);
-                  uint32_t src5a = *(uint32_t *) (src+0*spitch+4*BYTES_PER_UINT32_T);
-                  uint32_t src6a = *(uint32_t *) (src+0*spitch+5*BYTES_PER_UINT32_T);
-                  uint32_t src7a = *(uint32_t *) (src+0*spitch+6*BYTES_PER_UINT32_T);
-                  uint32_t src8a = *(uint32_t *) (src+0*spitch+7*BYTES_PER_UINT32_T);
-                  uint32_t src1b = *(uint32_t *) (src+1*spitch+0*BYTES_PER_UINT32_T);
-                  uint32_t src2b = *(uint32_t *) (src+1*spitch+1*BYTES_PER_UINT32_T);
-                  uint32_t src3b = *(uint32_t *) (src+1*spitch+2*BYTES_PER_UINT32_T);
-                  uint32_t src4b = *(uint32_t *) (src+1*spitch+3*BYTES_PER_UINT32_T);
-                  uint32_t src5b = *(uint32_t *) (src+1*spitch+4*BYTES_PER_UINT32_T);
-                  uint32_t src6b = *(uint32_t *) (src+1*spitch+5*BYTES_PER_UINT32_T);
-                  uint32_t src7b = *(uint32_t *) (src+1*spitch+6*BYTES_PER_UINT32_T);
-                  uint32_t src8b = *(uint32_t *) (src+1*spitch+7*BYTES_PER_UINT32_T);
-                  uint32_t src1c = *(uint32_t *) (src+2*spitch+0*BYTES_PER_UINT32_T);
-                  uint32_t src2c = *(uint32_t *) (src+2*spitch+1*BYTES_PER_UINT32_T);
-                  uint32_t src3c = *(uint32_t *) (src+2*spitch+2*BYTES_PER_UINT32_T);
-                  uint32_t src4c = *(uint32_t *) (src+2*spitch+3*BYTES_PER_UINT32_T);
-                  uint32_t src5c = *(uint32_t *) (src+2*spitch+4*BYTES_PER_UINT32_T);
-                  uint32_t src6c = *(uint32_t *) (src+2*spitch+5*BYTES_PER_UINT32_T);
-                  uint32_t src7c = *(uint32_t *) (src+2*spitch+6*BYTES_PER_UINT32_T);
-                  uint32_t src8c = *(uint32_t *) (src+2*spitch+7*BYTES_PER_UINT32_T);
-                  uint32_t src1d = *(uint32_t *) (src+3*spitch+0*BYTES_PER_UINT32_T);
-                  uint32_t src2d = *(uint32_t *) (src+3*spitch+1*BYTES_PER_UINT32_T);
-                  uint32_t src3d = *(uint32_t *) (src+3*spitch+2*BYTES_PER_UINT32_T);
-                  uint32_t src4d = *(uint32_t *) (src+3*spitch+3*BYTES_PER_UINT32_T);
-                  uint32_t src5d = *(uint32_t *) (src+3*spitch+4*BYTES_PER_UINT32_T);
-                  uint32_t src6d = *(uint32_t *) (src+3*spitch+5*BYTES_PER_UINT32_T);
-                  uint32_t src7d = *(uint32_t *) (src+3*spitch+6*BYTES_PER_UINT32_T);
-                  uint32_t src8d = *(uint32_t *) (src+3*spitch+7*BYTES_PER_UINT32_T);
-                  *(uint32_t *) (dst+0*dpitch+0*BYTES_PER_UINT32_T)  = src1a;
-                  *(uint32_t *) (dst+0*dpitch+1*BYTES_PER_UINT32_T)  = src2a;
-                  *(uint32_t *) (dst+0*dpitch+2*BYTES_PER_UINT32_T)  = src3a;
-                  *(uint32_t *) (dst+0*dpitch+3*BYTES_PER_UINT32_T)  = src4a;
-                  *(uint32_t *) (dst+0*dpitch+4*BYTES_PER_UINT32_T)  = src5a;
-                  *(uint32_t *) (dst+0*dpitch+5*BYTES_PER_UINT32_T)  = src6a;
-                  *(uint32_t *) (dst+0*dpitch+6*BYTES_PER_UINT32_T)  = src7a;
-                  *(uint32_t *) (dst+0*dpitch+7*BYTES_PER_UINT32_T)  = src8a;
-                  *(uint32_t *) (dst+1*dpitch+0*BYTES_PER_UINT32_T)  = src1b;
-                  *(uint32_t *) (dst+1*dpitch+1*BYTES_PER_UINT32_T)  = src2b;
-                  *(uint32_t *) (dst+1*dpitch+2*BYTES_PER_UINT32_T)  = src3b;
-                  *(uint32_t *) (dst+1*dpitch+3*BYTES_PER_UINT32_T)  = src4b;
-                  *(uint32_t *) (dst+1*dpitch+4*BYTES_PER_UINT32_T)  = src5b;
-                  *(uint32_t *) (dst+1*dpitch+5*BYTES_PER_UINT32_T)  = src6b;
-                  *(uint32_t *) (dst+1*dpitch+6*BYTES_PER_UINT32_T)  = src7b;
-                  *(uint32_t *) (dst+1*dpitch+7*BYTES_PER_UINT32_T)  = src8b;
-                  *(uint32_t *) (dst+2*dpitch+0*BYTES_PER_UINT32_T)  = src1c;
-                  *(uint32_t *) (dst+2*dpitch+1*BYTES_PER_UINT32_T)  = src2c;
-                  *(uint32_t *) (dst+2*dpitch+2*BYTES_PER_UINT32_T)  = src3c;
-                  *(uint32_t *) (dst+2*dpitch+3*BYTES_PER_UINT32_T)  = src4c;
-                  *(uint32_t *) (dst+2*dpitch+4*BYTES_PER_UINT32_T)  = src5c;
-                  *(uint32_t *) (dst+2*dpitch+5*BYTES_PER_UINT32_T)  = src6c;
-                  *(uint32_t *) (dst+2*dpitch+6*BYTES_PER_UINT32_T)  = src7c;
-                  *(uint32_t *) (dst+2*dpitch+7*BYTES_PER_UINT32_T)  = src8c;
-                  *(uint32_t *) (dst+3*dpitch+0*BYTES_PER_UINT32_T)  = src1d;
-                  *(uint32_t *) (dst+3*dpitch+1*BYTES_PER_UINT32_T)  = src2d;
-                  *(uint32_t *) (dst+3*dpitch+2*BYTES_PER_UINT32_T)  = src3d;
-                  *(uint32_t *) (dst+3*dpitch+3*BYTES_PER_UINT32_T)  = src4d;
-                  *(uint32_t *) (dst+3*dpitch+4*BYTES_PER_UINT32_T)  = src5d;
-                  *(uint32_t *) (dst+3*dpitch+5*BYTES_PER_UINT32_T)  = src6d;
-                  *(uint32_t *) (dst+3*dpitch+6*BYTES_PER_UINT32_T)  = src7d;
-                  *(uint32_t *) (dst+3*dpitch+7*BYTES_PER_UINT32_T)  = src8d;
-                  return TRUE;
-               }
-               else if (SW_CHECK_PITCHED_ALIGNMENT(WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,BYTES_PER_UINT16_T)) {
-                  uint16_t src1a = *(uint16_t *) (src+0*spitch+0);
-                  uint32_t src2a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T);
-                  uint32_t src3a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T);
-                  uint32_t src4a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T);
-                  uint32_t src5a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T);
-                  uint32_t src6a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+4*BYTES_PER_UINT32_T);
-                  uint32_t src7a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+5*BYTES_PER_UINT32_T);
-                  uint32_t src8a = *(uint32_t *) (src+0*spitch+BYTES_PER_UINT16_T+6*BYTES_PER_UINT32_T);
-                  uint16_t src9a = *(uint16_t *) (src+0*spitch+BYTES_PER_UINT16_T+7*BYTES_PER_UINT32_T);
-                  uint16_t src1b = *(uint16_t *) (src+1*spitch+0);
-                  uint32_t src2b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T);
-                  uint32_t src3b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T);
-                  uint32_t src4b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T);
-                  uint32_t src5b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T);
-                  uint32_t src6b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+4*BYTES_PER_UINT32_T);
-                  uint32_t src7b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+5*BYTES_PER_UINT32_T);
-                  uint32_t src8b = *(uint32_t *) (src+1*spitch+BYTES_PER_UINT16_T+6*BYTES_PER_UINT32_T);
-                  uint16_t src9b = *(uint16_t *) (src+1*spitch+BYTES_PER_UINT16_T+7*BYTES_PER_UINT32_T);
-                  uint16_t src1c = *(uint16_t *) (src+2*spitch+0);
-                  uint32_t src2c = *(uint32_t *) (src+2*spitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T);
-                  uint32_t src3c = *(uint32_t *) (src+2*spitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T);
-                  uint32_t src4c = *(uint32_t *) (src+2*spitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T);
-                  uint32_t src5c = *(uint32_t *) (src+2*spitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T);
-                  uint32_t src6c = *(uint32_t *) (src+2*spitch+BYTES_PER_UINT16_T+4*BYTES_PER_UINT32_T);
-                  uint32_t src7c = *(uint32_t *) (src+2*spitch+BYTES_PER_UINT16_T+5*BYTES_PER_UINT32_T);
-                  uint32_t src8c = *(uint32_t *) (src+2*spitch+BYTES_PER_UINT16_T+6*BYTES_PER_UINT32_T);
-                  uint16_t src9c = *(uint16_t *) (src+2*spitch+BYTES_PER_UINT16_T+7*BYTES_PER_UINT32_T);
-                  uint16_t src1d = *(uint16_t *) (src+3*spitch+0);
-                  uint32_t src2d = *(uint32_t *) (src+3*spitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T);
-                  uint32_t src3d = *(uint32_t *) (src+3*spitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T);
-                  uint32_t src4d = *(uint32_t *) (src+3*spitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T);
-                  uint32_t src5d = *(uint32_t *) (src+3*spitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T);
-                  uint32_t src6d = *(uint32_t *) (src+3*spitch+BYTES_PER_UINT16_T+4*BYTES_PER_UINT32_T);
-                  uint32_t src7d = *(uint32_t *) (src+3*spitch+BYTES_PER_UINT16_T+5*BYTES_PER_UINT32_T);
-                  uint32_t src8d = *(uint32_t *) (src+3*spitch+BYTES_PER_UINT16_T+6*BYTES_PER_UINT32_T);
-                  uint16_t src9d = *(uint16_t *) (src+3*spitch+BYTES_PER_UINT16_T+7*BYTES_PER_UINT32_T);
-                  *(uint16_t *) (dst+0*dpitch+0)                                        = src1a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T)  = src2a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T)  = src3a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T)  = src4a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T)  = src5a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+4*BYTES_PER_UINT32_T)  = src6a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+5*BYTES_PER_UINT32_T)  = src7a;
-                  *(uint32_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+6*BYTES_PER_UINT32_T)  = src8a;
-                  *(uint16_t *) (dst+0*dpitch+BYTES_PER_UINT16_T+7*BYTES_PER_UINT32_T)  = src9a;
-                  *(uint16_t *) (dst+1*dpitch+0)                                        = src1b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T)  = src2b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T)  = src3b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T)  = src4b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T)  = src5b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+4*BYTES_PER_UINT32_T)  = src6b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+5*BYTES_PER_UINT32_T)  = src7b;
-                  *(uint32_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+6*BYTES_PER_UINT32_T)  = src8b;
-                  *(uint16_t *) (dst+1*dpitch+BYTES_PER_UINT16_T+7*BYTES_PER_UINT32_T)  = src9b;
-                  *(uint16_t *) (dst+2*dpitch+0)                                        = src1c;
-                  *(uint32_t *) (dst+2*dpitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T)  = src2c;
-                  *(uint32_t *) (dst+2*dpitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T)  = src3c;
-                  *(uint32_t *) (dst+2*dpitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T)  = src4c;
-                  *(uint32_t *) (dst+2*dpitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T)  = src5c;
-                  *(uint32_t *) (dst+2*dpitch+BYTES_PER_UINT16_T+4*BYTES_PER_UINT32_T)  = src6c;
-                  *(uint32_t *) (dst+2*dpitch+BYTES_PER_UINT16_T+5*BYTES_PER_UINT32_T)  = src7c;
-                  *(uint32_t *) (dst+2*dpitch+BYTES_PER_UINT16_T+6*BYTES_PER_UINT32_T)  = src8c;
-                  *(uint16_t *) (dst+2*dpitch+BYTES_PER_UINT16_T+7*BYTES_PER_UINT32_T)  = src9c;
-                  *(uint16_t *) (dst+3*dpitch+0)                                        = src1d;
-                  *(uint32_t *) (dst+3*dpitch+BYTES_PER_UINT16_T+0*BYTES_PER_UINT32_T)  = src2d;
-                  *(uint32_t *) (dst+3*dpitch+BYTES_PER_UINT16_T+1*BYTES_PER_UINT32_T)  = src3d;
-                  *(uint32_t *) (dst+3*dpitch+BYTES_PER_UINT16_T+2*BYTES_PER_UINT32_T)  = src4d;
-                  *(uint32_t *) (dst+3*dpitch+BYTES_PER_UINT16_T+3*BYTES_PER_UINT32_T)  = src5d;
-                  *(uint32_t *) (dst+3*dpitch+BYTES_PER_UINT16_T+4*BYTES_PER_UINT32_T)  = src6d;
-                  *(uint32_t *) (dst+3*dpitch+BYTES_PER_UINT16_T+5*BYTES_PER_UINT32_T)  = src7d;
-                  *(uint32_t *) (dst+3*dpitch+BYTES_PER_UINT16_T+6*BYTES_PER_UINT32_T)  = src8d;
-                  *(uint16_t *) (dst+3*dpitch+BYTES_PER_UINT16_T+7*BYTES_PER_UINT32_T)  = src9d;
-                  return TRUE;
-               }
-               else {
-                  // Don't bother unrolling loops, since that won't help for more than around 8 operations.
-                  // Instead, just call multiple fixed functions.
-                  if (xdir >= 0) {
-                     swCopy16BppSmallFixedWidths4Rows_Unaligned(dst, src, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths4Rows_Unaligned(dst + 8 * BYTES_PER_UINT16_T, src + 8 * BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                  } else {
-                     swCopy16BppSmallFixedWidths4Rows_Unaligned(dst + 8 * BYTES_PER_UINT16_T, src + 8 * BYTES_PER_UINT16_T, 8, xdir, dpitch, spitch);
-                     swCopy16BppSmallFixedWidths4Rows_Unaligned(dst, src, 8, xdir, dpitch, spitch);
-                  }
-                  return TRUE;
-               }
-               break;
-      // TODO: Add more alignment checks for 32 pixel-wide cases for performance reasons?
-      //       For example, handling (SW_CHECK_PITCHED_ALIGNMENT(DOUBLE_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,XXX)) and related cases could make a big difference here...
-      case 32: if (SW_CHECK_PITCHED_ALIGNMENT(QUAD_WORD_ALIGNMENT_BYTE_SIZE,dst,src,dpitch,spitch,0)) {
-                  uint32x4_t src1a = vld1q_u32((uint32_t *)(src+0*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2a = vld1q_u32((uint32_t *)(src+0*spitch+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src3a = vld1q_u32((uint32_t *)(src+0*spitch+2*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src4a = vld1q_u32((uint32_t *)(src+0*spitch+3*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1b = vld1q_u32((uint32_t *)(src+1*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2b = vld1q_u32((uint32_t *)(src+1*spitch+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src3b = vld1q_u32((uint32_t *)(src+1*spitch+2*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src4b = vld1q_u32((uint32_t *)(src+1*spitch+3*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1c = vld1q_u32((uint32_t *)(src+2*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2c = vld1q_u32((uint32_t *)(src+2*spitch+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src3c = vld1q_u32((uint32_t *)(src+2*spitch+2*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src4c = vld1q_u32((uint32_t *)(src+2*spitch+3*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src1d = vld1q_u32((uint32_t *)(src+3*spitch+0*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src2d = vld1q_u32((uint32_t *)(src+3*spitch+1*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src3d = vld1q_u32((uint32_t *)(src+3*spitch+2*BYTES_PER_UINT32X4_T));
-                  uint32x4_t src4d = vld1q_u32((uint32_t *)(src+3*spitch+3*BYTES_PER_UINT32X4_T));
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+0*BYTES_PER_UINT32X4_T),src1a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+1*BYTES_PER_UINT32X4_T),src2a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+2*BYTES_PER_UINT32X4_T),src3a);
-                  vst1q_u32((uint32_t *)(dst+0*dpitch+3*BYTES_PER_UINT32X4_T),src4a);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+0*BYTES_PER_UINT32X4_T),src1b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+1*BYTES_PER_UINT32X4_T),src2b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+2*BYTES_PER_UINT32X4_T),src3b);
-                  vst1q_u32((uint32_t *)(dst+1*dpitch+3*BYTES_PER_UINT32X4_T),src4b);
-                  vst1q_u32((uint32_t *)(dst+2*dpitch+0*BYTES_PER_UINT32X4_T),src1c);
-                  vst1q_u32((uint32_t *)(dst+2*dpitch+1*BYTES_PER_UINT32X4_T),src2c);
-                  vst1q_u32((uint32_t *)(dst+2*dpitch+2*BYTES_PER_UINT32X4_T),src3c);
-                  vst1q_u32((uint32_t *)(dst+2*dpitch+3*BYTES_PER_UINT32X4_T),src4c);
-                  vst1q_u32((uint32_t *)(dst+3*dpitch+0*BYTES_PER_UINT32X4_T),src1d);
-                  vst1q_u32((uint32_t *)(dst+3*dpitch+1*BYTES_PER_UINT32X4_T),src2d);
-                  vst1q_u32((uint32_t *)(dst+3*dpitch+2*BYTES_PER_UINT32X4_T),src3d);
-                  vst1q_u32((uint32_t *)(dst+3*dpitch+3*BYTES_PER_UINT32X4_T),src4d);
-                  return TRUE;
-               }
-               break;
-   }
+         }
 
    return FALSE;
 }
@@ -1924,10 +872,12 @@ swCopyRect16BppFixedWidth_Unaligned(unsigned char *dst, unsigned char *src, int
       if (rowsOverlap)
       {
          if (w > 64) {
-            DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY_NO_NARROW_COPIES(neon_memmove, BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS, UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
+            //DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY_NO_NARROW_COPIES(neon_memmove, BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS, UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
+	    DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY_NO_NARROW_COPIES(memmove, BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS, UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
          }
          else if (w == 64) {
-            DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY(neon_memmove, BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS, UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
+            //DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY(neon_memmove, BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS, UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
+	    DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY(memmove, BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS, UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
          }
          else {
             DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY(memmove, SIGNAL_BLOCK_NOOP, SIGNAL_BLOCK_NOOP);
@@ -1936,10 +886,12 @@ swCopyRect16BppFixedWidth_Unaligned(unsigned char *dst, unsigned char *src, int
       else
       {
          if (w > 64) {
-            DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY_NO_NARROW_COPIES(neon_memcpy, BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS, UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
+            //DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY_NO_NARROW_COPIES(neon_memcpy, BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS, UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
+	    DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY_NO_NARROW_COPIES(memcpy, BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS, UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
          }
          else if (w == 64) {
-            DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY(neon_memcpy, BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS, UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
+            //DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY(neon_memcpy, BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS, UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
+	    DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY(memcpy, BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS, UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS);
          }
          else {
             DRAW_MULTIPLE_ROWS_WITH_MEMORY_COPY(memcpy, SIGNAL_BLOCK_NOOP, SIGNAL_BLOCK_NOOP);
@@ -1973,7 +925,8 @@ swCopyRect8Bpp_Unaligned(unsigned char *dst, unsigned char *src, int w, int h, i
       if (xdir >= 0 || !rowsOverlap) {
          if (w >= 128) {
             BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS();
-            neon_memcpy(dst, src, w);
+            //neon_memcpy(dst, src, w);
+	    memcpy(dst, src, w);
             UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS();
          }
          else
@@ -1982,7 +935,8 @@ swCopyRect8Bpp_Unaligned(unsigned char *dst, unsigned char *src, int w, int h, i
       else {
          if (w >= 128) {
             BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS();
-            neon_memmove(dst, src, w);
+            //neon_memmove(dst, src, w);
+	    memmove(dst, src, w);
             UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS();
          }
          else
@@ -2029,7 +983,8 @@ swCopyRect24Bpp_Unaligned(unsigned char *dst, unsigned char *src, int w, int h,
       if (xdir >= 0 || !rowsOverlap) {
          if (w >= 42) {
             BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS();
-            neon_memcpy(dst, src,  w * BYTES_PER_24BPP_PIXEL);
+            //neon_memcpy(dst, src,  w * BYTES_PER_24BPP_PIXEL);
+	    memcpy(dst, src,  w * BYTES_PER_24BPP_PIXEL);
             UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS();
          }
          else
@@ -2038,7 +993,8 @@ swCopyRect24Bpp_Unaligned(unsigned char *dst, unsigned char *src, int w, int h,
       else {
          if (w >= 42) {
             BLOCK_SIGNALS_BEFORE_VFP_OPERATIONS();
-            neon_memmove(dst, src,  w * BYTES_PER_24BPP_PIXEL);
+            //neon_memmove(dst, src,  w * BYTES_PER_24BPP_PIXEL);
+	    memmove(dst, src,  w * BYTES_PER_24BPP_PIXEL);
             UNBLOCK_SIGNALS_AFTER_VFP_OPERATIONS();
          }
          else
diff --git git/src/neon_memcpy.S git/src/neon_memcpy.S
deleted file mode 100644
index 5ecc5ce..0000000
--- git/src/neon_memcpy.S
+++ /dev/null
@@ -1,549 +0,0 @@
-/***************************************************************************
- Copyright (c) 2009, Code Aurora Forum. All rights reserved.
-
- Redistribution and use in source and binary forms, with or without
- modification, are permitted provided that the following conditions are met:
-     * Redistributions of source code must retain the above copyright
-       notice, this list of conditions and the following disclaimer.
-     * Redistributions in binary form must reproduce the above copyright
-       notice, this list of conditions and the following disclaimer in the
-       documentation and/or other materials provided with the distribution.
-     * Neither the name of Code Aurora nor the names of its contributors may
-       be used to endorse or promote products derived from this software
-       without specific prior written permission.
-
- THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
- LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- POSSIBILITY OF SUCH DAMAGE.
- ***************************************************************************/
-
-/***************************************************************************
-  Neon memcpy: Attempts to do a memcpy with Neon registers if possible,
-     Inputs:
-        dest: The destination buffer
-        src: The source buffer
-        n: The size of the buffer to transfer
-     Outputs:
-
-***************************************************************************/
-
-/*
- * General note:
- * The original code that was compiled for rvct used PUSH/POP and VPUSH/VPOP
- * However, it looks like the 2006 CodeSourcery Assembler has issues generating
- * the correct object code for VPOP, resulting in horrific stack crashes.
- * As a result, I've temporarily move PUSH->STMDB, POP->LDMIA, VPUSH->VSTMDB,
- * and VPOP->VLDMIA.  We can revert this back once we update our toolchain.
- *
- * Also, VSHL swaps the source register and the shift-amount register
- * around in 2006-q3.  I've coded this incorrectly so it turns out correct
- * in the object code, but we'll need to undo that later...
- */
-
-	.code 32
-	.align 4
-	.globl neon_memcpy
-	.func
-
-neon_memcpy:
-	/* 
-	 * First, make sure we're not copying < 4 bytes.  If so, we'll
-         * just handle it here.
-	 */
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	stmdb		sp!, {r0}
-#else
-	push		{r0}
-#endif
-	cmp		r2, #4
-	bgt		neon_gt_4
-	/* Copy 0-4 bytes, if needed, and return.*/
-	cmp		r2, #0
-neon_smallcopy_loop:
-	beq		neon_smallcopy_done
-	ldrb		r12, [r1], #1
-	subs		r2, r2, #1
-	strb		r12, [r0], #1
-	b		neon_smallcopy_loop
-neon_smallcopy_done:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	ldmia		sp!, {r0}
-#else
-	pop		{r0}
-#endif
-	bx		lr
-
-	/* Copy 4 or more bytes*/
-neon_gt_4:
-	/* Preload what we can...*/
-	pld		[r0,#0]
-	pld		[r1,#0]
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	stmdb		sp!, {r4-r5}
-#else
-	push		{r4-r5}
-#endif
-
-neon_check_align:
-	/* Check normal word alignment for target. */
-	ands		r12, r0, #0x3
-	beq		source_alignment_check
-	
-	/*
-	 * Target is not aligned.  Step through until we get that
-	 * word-aligned.  This works better than a loop, according
-	 * to our pipeline modeler.
-	 */
-	cmp		r12, #2
-	ldrb		r3, [r1], #1
-	ldrleb		r4, [r1], #1
-	ldrltb		r5, [r1], #1
-	rsb		r12, r12, #4
-	sub		r2, r2, r12
-	strb		r3, [r0], #1
-	strleb		r4, [r0], #1
-	strltb		r5, [r0], #1
-	
-source_alignment_check:
-	ands		r12, r1, #0x3
-	bne		neon_memcpy_nonaligned	/* Source is not word aligned.*/
-neon_try_16_align:
-	cmp		r2, #64
-	blt		neon_align_route
-	/* This is where we try 16-byte alignment. */
-	ands		r12, r0, #0xf
-	beq		neon_align_route
-	rsb		r12, r12, #16
-neon_16_start:
-	sub		r2, r2, r12
-	lsrs		r3, r12, #2
-neon_align_16_4:
-	ldr		r4, [r1], #4
-	subs		r3, r3, #1
-	str		r4, [r0], #4
-	bne		neon_align_16_4
-neon_align_route:
-	/* In this case, both source and target are word-aligned. */
-	cmp		r2, #32768
-	bge		neon_copy_128p_a
-	cmp		r2, #256
-	bge		neon_copy_128_a
-	cmp		r2, #64
-	bge		neon_copy_32_a
-	b		neon_copy_finish_a
-	nop
-neon_copy_128p_a:
-	/* We'll copy blocks 128-bytes at a time, but try to call pld to
-	 * load in the next page, if possible.
-	 */
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vstmdb		sp!, {q4-q7}
-#else
-	vpush		{q4-q7}
-#endif
-	mov		r12, r2, lsr #7
-neon_copy_128p_loop_a:
-	vld1.32		{q0, q1}, [r1]!
-	vld1.32		{q2, q3}, [r1]!
-	vld1.32		{q4, q5}, [r1]!
-	vld1.32		{q6, q7}, [r1]!
-	pld		[r1, #0]
-	pld		[r1, #1024]
-	vst1.32		{q0, q1}, [r0]!
-	vst1.32		{q2, q3}, [r0]!
-	vst1.32		{q4, q5}, [r0]!
-	vst1.32		{q6, q7}, [r0]!
-	subs		r12, r12, #1
-	bne		neon_copy_128p_loop_a
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vldmia		sp!, {q4-q7}
-#else
-	vpop		{q4-q7}
-#endif
-	ands		r2, r2, #0x7f
-	beq		neon_end
-	cmp		r2, #32
-	blt		neon_copy_finish_a
-	b		neon_copy_32_a
-	/* Copy blocks of 128-bytes (word-aligned) at a time*/
-neon_copy_128_a:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vstmdb		sp!, {q4-q7}
-#else
-	vpush		{q4-q7}
-#endif
-	/*
-	 * Move to a 1-s based countdown to determine when to loop.  That
-	 * allows the subs to set the Z flag without having to explicitly
-	 * call cmp to a value.
-	 */
-	mov		r12, r2, lsr #7
-neon_copy_128_loop_a:
-	vld1.32		{q0, q1}, [r1]!
-	vld1.32		{q2, q3}, [r1]!
-	vld1.32		{q4, q5}, [r1]!
-	vld1.32		{q6, q7}, [r1]!
-	pld		[r1, #0]
-	pld		[r1, #128]
-	vst1.32		{q0, q1}, [r0]!
-	vst1.32		{q2, q3}, [r0]!
-	vst1.32		{q4, q5}, [r0]!
-	vst1.32		{q6, q7}, [r0]!
-	subs		r12, r12, #1
-	pld		[r0, #0]
-	pld		[r0, #128]
-	bne		neon_copy_128_loop_a
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vldmia		sp!, {q4-q7}
-#else
-	vpop		{q4-q7}
-#endif
-	ands		r2, r2, #0x7f
-	beq		neon_end
-	cmp		r2, #32
-	blt		neon_copy_finish_a
-	/* Copy blocks of 32-bytes (word aligned) at a time*/
-neon_copy_32_a:
-	mov		r12, r2, lsr #5
-neon_copy_32_loop_a:
-	vld1.32		{q0,q1}, [r1]!
-	subs		r12, r12, #1
-	pld		[r1,#0]
-	vst1.32		{q0,q1}, [r0]!
-	bne		neon_copy_32_loop_a
-	ands		r2, r2, #0x1f
-	beq		neon_end
-neon_copy_finish_a:
-neon_copy_16_a:
-	movs		r12, r2, lsr #4
-	beq		neon_copy_8_a
-neon_copy_16_a_loop:
-	vld1.32		{q0}, [r1]!
-	subs		r12, r12, #1
-	vst1.32		{q0}, [r0]!
-	bne		neon_copy_16_a_loop
-	ands		r2, r2, #0xf
-	beq		neon_end
-neon_copy_8_a:
-	cmp		r2, #8
-	blt		neon_copy_4_a
-	ldm		r1!, {r4-r5}
-	subs		r2, r2, #8
-	stm		r0!, {r4-r5}
-	/* Copy 4-bytes of word-aligned data at a time*/
-neon_copy_4_a:
-	cmp		r2, #4
-	blt		neon_copy_finish
-	ldr		r4, [r1], #4
-	subs		r2, r2, #4
-	str		r4, [r0], #4
-	b		neon_copy_finish
-
-	/*
-	 * Handle unaligned data.  The basic concept here is that we'll
-	 * try to pull out enough data from the source to get that word-
-	 * aligned, then do our writes word-aligned, storing the difference
-	 * in a register, and shifting the data as needed.
-	 */
-neon_memcpy_nonaligned:
-	/*
-	 * If this is <8 bytes, it makes more sense to just copy it
-	 * quickly instead of incurring all kinds of overhead.
-	 */
-	cmp		r2, #8 /* Let's try this...*/
-	ble		neon_copy_finish
-	/*
-	 * This is where we'll pull out either 1, 2, or 3 bytes of data
-	 * from the source as needed to align it, then store off those
-	 * bytes in r4.  When we read in the (now) aligned data from the
-	 * source, we'll shift the bytes and AND in the r4 data, then write
-	 * to the target aligned.
-	 *
-	 * The conditional ldr calls work slightly faster than the
-	 * previous method, confirmed by our pipeline modeler.
-	 */
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	stmdb		sp!, {r6-r9}
-#else
-	push		{r6-r9}
-#endif
-	cmp		r12, #2
-	ldrb		r4, [r1], #1
-	ldrleb		r5, [r1], #1
-	ldrltb		r6, [r1], #1
-	rsb		r8, r12, #4
-	sub		r2, r2, r8
-	lsl		r8, r8, #3
-	orrle		r4, r4, r5, lsl #8
-	orrlt		r4, r4, r6, lsl #16
-	rsb		r9, r8, #32
-	
-	cmp		r2, #64
-	blt		neon_unaligned_route
-	ands		r12, r0, #0xf
-	beq		neon_unaligned_route
-	rsb		r12, r12, #16
-neon_16_start_u:
-	sub		r2, r2, r12
-	lsrs		r6, r12, #2
-neon_align_16_4_u:
-	ldr		r5, [r1], #4
-	subs		r6, r6, #1
-	orr		r4, r4, r5, lsl r8
-	str		r4, [r0], #4
-	mov		r4, r5, lsr r9
-	bne		neon_align_16_4_u
-neon_unaligned_route:
-	/* Decide which loop block to branch to.*/
-	cmp		r2, #256
-	bge		neon_copy_64_u
-	cmp		r2, #64
-	bge		neon_copy_32_u
-	b		neon_copy_finish_u
-	/* Copy data in 64-byte blocks.*/
-neon_copy_64_u:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vstmdb		sp!, {q4}
-	vstmdb		sp!, {q5-q8}
-#else
-	vpush		{q4}
-	vpush		{q5-q8}
-#endif
-	/* We'll need this for the q register shift later.*/
-	vdup.u32	q8, r8
-	/*
-	 * As above, we determine how many times we can go through the
-	 * 64-byte copy loop, then countdown.
-	 */
-	mov		r12, r2, lsr #6
-	and		r2, r2, #0x3f
-neon_copy_64_u_loop:
-	/* Load 64-bytes into q4-q7.*/
-	vld1.32		{q4, q5}, [r1]!
-	vld1.32		{q6, q7}, [r1]!
-	/*
-	 * Shift q0-q3 right so everything but the data we need due to the
-	 * alignment falls off the right-hand side.  The branching
-	 * is needed, since vshr requires the shift to be an immediate
-	 * value.
-	 */
-	lsls		r5, r8, #28
-	bcc		neon_copy_64_u_b8
-	bpl		neon_copy_64_u_b16
-	vshr.u64	q0, q4, #40
-	vshr.u64	q1, q5, #40
-	vshr.u64	q2, q6, #40
-	vshr.u64	q3, q7, #40
-	b		neon_copy_64_unify
-neon_copy_64_u_b8:
-	vshr.u64	q0, q4, #56
-	vshr.u64	q1, q5, #56
-	vshr.u64	q2, q6, #56
-	vshr.u64	q3, q7, #56
-	b		neon_copy_64_unify
-neon_copy_64_u_b16:
-	vshr.u64	q0, q4, #48
-	vshr.u64	q1, q5, #48
-	vshr.u64	q2, q6, #48
-	vshr.u64	q3, q7, #48
-neon_copy_64_unify:
-	/*
-	 * Shift q4-q7 left by r8 bits to take the alignment into
-	 * account.
-	 */
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vshl.u64	q4, q8, q4
-	vshl.u64	q5, q8, q5
-	vshl.u64	q6, q8, q6
-	vshl.u64	q7, q8, q7
-#else
-	vshl.u64	q4, q4, q8
-	vshl.u64	q5, q5, q8
-	vshl.u64	q6, q6, q8
-	vshl.u64	q7, q7, q8
-#endif
-	/*
-	 * The data in s14 will be needed for the next loop iteration.  Move
-	 * that to r5.
-	 */
-	vmov		r5, s14
-	/* We'll vorr the shifted data with the data that needs to move back.*/
-	vorr		d9, d9, d0
-	/* Copy the data from the previous loop into s14.*/
-	vmov		s14, r4
-	vorr		d10, d10, d1
-	vorr		d11, d11, d2
-	vorr		d12, d12, d3
-	vorr		d13, d13, d4
-	vorr		d14, d14, d5
-	vorr		d15, d15, d6
-	vorr		d8, d8, d7
-	subs		r12, r12, #1
-	pld		[r1, #0]
-	pld		[r1, #128]
-	/* Save off the r5 data into r4 for the next iteration.*/
-	mov		r4, r5
-	vst1.32		{q4, q5}, [r0]!
-	vst1.32		{q6, q7}, [r0]!
-	pld		[r0, #0]
-	pld		[r0, #128]
-	bne		neon_copy_64_u_loop
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vldmia		sp!, {q5-q8}
-	vldmia		sp!, {q4}
-#else
-	vpop		{q5-q8}
-	vpop		{q4}
-#endif
-	cmp		r2, #32
-	bge		neon_copy_32_u
-	b		neon_copy_finish_u
-neon_copy_32_u:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vstmdb		sp!, {q4}
-#else
-	vpush		{q4}
-#endif
-	vdup.u32	q4, r8
-	mov		r12, r2, lsr #5
-	and		r2, r2, #0x1f
-neon_copy_32_u_loop:
-	vld1.32		{q0, q1}, [r1]!
-	lsls		r5, r8, #28
-	bcc		neon_copy_32_u_b8
-	bpl		neon_copy_32_u_b16
-	vshr.u64	q2, q0, #40
-	vshr.u64	q3, q1, #40
-	b		neon_copy_32_unify
-neon_copy_32_u_b8:
-	vshr.u64	q2, q0, #56
-	vshr.u64	q3, q1, #56
-	b		neon_copy_32_unify
-neon_copy_32_u_b16:
-	vshr.u64	q2, q0, #48
-	vshr.u64	q3, q1, #48
-neon_copy_32_unify:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vshl.u64	q0, q4, q0
-	vshl.u64	q1, q4, q1
-#else
-	vshl.u64	q0, q0, q4
-	vshl.u64	q1, q1, q4
-#endif
-	vmov		r5, s14
-	vorr		d1, d1, d4
-	vmov		s14, r4
-	vorr		d2, d2, d5
-	vorr		d3, d3, d6
-	vorr		d0, d0, d7
-	subs		r12, r12, #1
-	pld		[r1, #0]
-	mov		r4, r5
-	vst1.32		{q0, q1}, [r0]!
-	bne		neon_copy_32_u_loop
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vldmia		sp!, {q4}
-#else
-	vpop		{q4}
-#endif
-neon_copy_finish_u:
-neon_copy_16_u:
-	movs		r12, r2, lsr #4
-	beq		neon_copy_8_u
-	vdup.u32	q2, r8
-	and		r2, r2, #0xf
-neon_copy_16_u_loop:
-	vld1.32		{q0}, [r1]!
-	lsls		r5, r8, #28
-	bcc		neon_copy_16_u_b8
-	bpl		neon_copy_16_u_b16
-	vshr.u64	q1, q0, #40
-	b		neon_copy_16_unify
-neon_copy_16_u_b8:
-	vshr.u64	q1, q0, #56
-	b		neon_copy_16_unify
-neon_copy_16_u_b16:
-	vshr.u64	q1, q0, #48
-neon_copy_16_unify:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vshl.u64	q0, q2, q0
-#else
-	vshl.u64	q0, q0, q2
-#endif
-	vmov		r5, s6
-	vorr		d1, d1, d2
-	vmov		s6, r4
-	vorr		d0, d0, d3
-	subs		r12, r12, #1
-	mov		r4, r5
-	vst1.32		{q0}, [r0]!
-	bne		neon_copy_16_u_loop
-neon_copy_8_u:
-	cmp		r2, #8
-	blt		neon_copy_4_u
-	ldm		r1!, {r6-r7}
-	subs		r2, r2, #8
-	orr		r4, r4, r6, lsl r8
-	mov		r5, r6, lsr r9
-	orr		r5, r5, r7, lsl r8
-	stm		r0!, {r4-r5}
-	mov		r4, r7, lsr r9
-neon_copy_4_u:
-	cmp		r2, #4
-	blt		neon_copy_last_bits_u
-	ldr		r5, [r1], #4
-	subs		r2, r2, #4
-	orr		r4, r4, r5, lsl r8
-	str		r4, [r0], #4
-	mov		r4, r5, lsr r9
-neon_copy_last_bits_u:
-	/*
-	 * Remember, r8 contains the size of the data in r4 in bits,
-	 * so to get to bytes we'll need to shift 3 places
-	 */
-	lsr		r8, r8, #0x3
-	/* Write out the bytes stored in r4.*/
-neon_copy_last_bits_u_loop:
-	strb		r4, [r0], #1
-	subs		r8, r8, #1
-	lsrne		r4, r4, #8
-	bne		neon_copy_last_bits_u_loop
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	ldmia		sp!, {r6-r9}
-#else
-	pop		{r6-r9}
-#endif
-neon_copy_finish:
-	cmp		r2, #0
-	beq		neon_end
-	/*
-	 * This just copies the data from source to target one byte
-	 * at a time.  For some small values, this makes more sense.
-	 * Note that since this code copies data a byte at a time,
-	 * both the aligned and unaligned paths can use it.
-	 */
-neon_copy_finish_loop:
-	ldrb		r4, [r1], #1
-	subs		r2, r2, #1
-	strb		r4, [r0], #1
-	bne		neon_copy_finish_loop
-neon_end:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	ldmia		sp!, {r4-r5}
-	ldmia		sp!, {r0}
-#else
-	pop		{r4-r5}
-	pop		{r0}
-#endif
-	bx		lr
-
-	.endfunc
-	.end
diff --git git/src/neon_memmove.S git/src/neon_memmove.S
deleted file mode 100644
index 1bfe597..0000000
--- git/src/neon_memmove.S
+++ /dev/null
@@ -1,939 +0,0 @@
-/***************************************************************************
- Copyright (c) 2009, Code Aurora Forum. All rights reserved.
-
- Redistribution and use in source and binary forms, with or without
- modification, are permitted provided that the following conditions are met:
-     * Redistributions of source code must retain the above copyright
-       notice, this list of conditions and the following disclaimer.
-     * Redistributions in binary form must reproduce the above copyright
-       notice, this list of conditions and the following disclaimer in the
-       documentation and/or other materials provided with the distribution.
-     * Neither the name of Code Aurora nor the names of its contributors may
-       be used to endorse or promote products derived from this software
-       without specific prior written permission.
-
- THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
- LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- POSSIBILITY OF SUCH DAMAGE.
-  ***************************************************************************/
-
-/***************************************************************************
- *  Neon memmove: Attempts to do a memmove with Neon registers if possible,
- *     Inputs:
- *        dest: The destination buffer
- *        src: The source buffer
- *        n: The size of the buffer to transfer
- *     Outputs:
- *
- ***************************************************************************/
-
-/*
- * General note:
- * The original code that was compiled for rvct used PUSH/POP and VPUSH/VPOP
- * However, it looks like the 2006 CodeSourcery Assembler has issues generating
- * the correct object code for VPOP, resulting in horrific stack crashes.
- * As a result, I've temporarily move PUSH->STMDB, POP->LDMIA, VPUSH->VSTMDB,
- * and VPOP->VLDMIA.  We can revert this back once we update our toolchain.
- *
- * Also, VSHL swaps the source register and the shift-amount register
- * around in 2006-q3.  I've coded this incorrectly so it turns out correct
- * in the object code, but we'll need to undo that later...
- */
-	.code 32
-	.align 4
-	.globl neon_memmove
-	.func
-
-neon_memmove:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	stmdb		sp!, {r0}
-#else
-	push		{r0}
-#endif
-
-	/*
-	 * The requirements for memmove state that the function should
-	 * operate as if data were being copied from the source to a
-	 * buffer, then to the destination.  This is to allow a user
-	 * to copy data from a source and target that overlap.
-	 *
-	 * We can't just do byte copies front-to-back automatically, since
-	 * there's a good chance we may have an overlap (why else would someone
-	 * intentionally use memmove then?).
-	 *
-	 * We'll break this into two parts.  Front-to-back, or back-to-front
-	 * copies.
-	 */
-neon_memmove_cmf:
-	cmp		r0, r1
-	blt		neon_front_to_back_copy
-	bgt		neon_back_to_front_copy
-	b		neon_memmove_done
-
-	/* #############################################################
-	 * Front to Back copy
-	 */
-neon_front_to_back_copy:
-	/*
-	 * For small copies, just do a quick memcpy.  We can do this for
-	 * front-to-back copies, aligned or unaligned, since we're only
-	 * doing 1 byte at a time...
-	 */
-	cmp		r2, #4
-	bgt		neon_f2b_gt4
-	cmp		r2, #0
-neon_f2b_smallcopy_loop:
-	beq		neon_memmove_done
-	ldrb		r12, [r1], #1
-	subs		r2, r2, #1
-	strb		r12, [r0], #1
-	b		neon_f2b_smallcopy_loop
-neon_f2b_gt4:
-	/* Preload what we can...*/
-	pld		[r0,#0]
-	pld		[r1,#0]	
-	/* The window size is in r3. */
-	sub		r3, r1, r0
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	stmdb		sp!, {r4-r6}
-#else
-	push		{r4-r6}
-#endif
-
-neon_f2b_check_align:
-	/* Check alignment. */
-	ands		r12, r0, #0x3
-	beq		neon_f2b_source_align_check
-	cmp		r12, #2
-	ldrb		r4, [r1], #1
-	ldrleb		r5, [r1], #1
-	ldrltb		r6, [r1], #1
-	rsb		r12, r12, #4
-	sub		r2, r2, r12
-	strb		r4, [r0], #1
-	strleb		r5, [r0], #1
-	strltb		r6, [r0], #1
-	
-neon_f2b_source_align_check:
-	ands		r12, r1, #0x3
-	bne		neon_f2b_nonaligned
-
-neon_f2b_try_16_align:
-	/* If we're >64, attempt to align on 16-bytes.  Smaller amounts
-	 * don't seem to be worth handling. */
-	cmp		r2, #64
-	blt		neon_f2b_align_route
-	/* This is where we try 16-byte alignment. */
-	ands		r12, r0, #0xf
-	beq		neon_f2b_align_route
-	rsb		r12, r12, #16
-neon_f2b_16_start:
-	sub		r2, r2, r12
-	lsrs		r5, r12, #2
-neon_f2b_align_16_4:
-	ldr		r4, [r1], #4
-	subs		r5, r5, #1
-	str		r4, [r0], #4
-	bne		neon_f2b_align_16_4
-neon_f2b_align_route:
-	/* #############################################################
-	 * Front to Back copy - aligned
-	 */
-	/*
-	 * Note that we can't just route based on the size in r2.  If that's
-	 * larger than the overlap window in r3, we could potentially
-	 * (and likely!) destroy data we're copying.
-	 */
-	cmp		r2, r3
-	movle		r12, r2
-	movgt		r12, r3
-	cmp		r12, #256
-	bge		neon_f2b_copy_128_a
-	cmp		r12, #64
-	bge		neon_f2b_copy_32_a
-	cmp		r12, #16
-	bge		neon_f2b_copy_16_a
-	cmp		r12, #8
-	bge		neon_f2b_copy_8_a
-	cmp		r12, #4
-	bge		neon_f2b_copy_4_a
-	b		neon_f2b_copy_1_a
-neon_f2b_copy_128_a:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vstmdb		sp!, {q4-q7}
-#else
-	vpush		{q4-q7}
-#endif
-	mov		r12, r2, lsr #7
-neon_f2b_copy_128_a_loop:
-	vld1.32		{q0,q1}, [r1]!
-	vld1.32		{q2,q3}, [r1]!
-	vld1.32		{q4,q5}, [r1]!
-	vld1.32		{q6,q7}, [r1]!
-	pld		[r1, #0]
-	pld		[r1, #128]
-	vst1.32		{q0,q1}, [r0]!
-	vst1.32		{q2,q3}, [r0]!
-	vst1.32		{q4,q5}, [r0]!
-	vst1.32		{q6,q7}, [r0]!
-	subs		r12, r12, #1
-	pld		[r0, #0]
-	pld		[r0, #128]
-	bne		neon_f2b_copy_128_a_loop
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vldmia		sp!, {q4-q7}
-#else
-	vpop		{q4-q7}
-#endif
-	ands		r2, r2, #0x7f
-	beq		neon_f2b_finish
-	cmp		r2, #32
-	bge		neon_f2b_copy_32_a
-	b		neon_f2b_copy_finish_a
-neon_f2b_copy_32_a:
-	mov		r12, r2, lsr #5
-neon_f2b_copy_32_a_loop:
-	vld1.32		{q0,q1}, [r1]!
-	subs		r12, r12, #1
-	pld		[r1, #0]
-	vst1.32		{q0,q1}, [r0]!
-	bne		neon_f2b_copy_32_a_loop
-	ands		r2, r2, #0x1f
-	beq		neon_f2b_finish
-neon_f2b_copy_finish_a:
-neon_f2b_copy_16_a:
-	movs		r12, r2, lsr #4
-	beq		neon_f2b_copy_8_a
-neon_f2b_copy_16_a_loop:
-	vld1.32		{q0}, [r1]!
-	subs		r12, r12, #1
-	vst1.32		{q0}, [r0]!
-	bne		neon_f2b_copy_16_a_loop
-	ands		r2, r2, #0xf
-	beq		neon_f2b_finish
-neon_f2b_copy_8_a:
-	cmp		r2, #8
-	blt		neon_f2b_copy_4_a
-	ldm		r1!, {r4-r5}
-	subs		r2, r2, #8
-	stm		r0!, {r4-r5}
-neon_f2b_copy_4_a:
-	cmp		r2, #4
-	blt		neon_f2b_copy_1_a
-	ldr		r4, [r1], #4
-	subs		r2, r2, #4
-	str		r4, [r0], #4
-neon_f2b_copy_1_a:
-	cmp		r2, #0
-	beq		neon_f2b_finish
-neon_f2b_copy_1_a_loop:
-	ldrb		r12, [r1], #1
-	subs		r2, r2, #1
-	strb		r12, [r0], #1
-	bne		neon_f2b_copy_1_a_loop
-	b		neon_f2b_finish
-		
-	/* #############################################################
-	 * Front to Back copy - unaligned
-	 */
-neon_f2b_nonaligned:
-	/*
-	 * For sizes < 8, does it really make sense to do the whole shift
-	 * party?  Note that we DON'T want to call neon_f2b_copy_1_u,
-	 * since we'll end up trying to pop r8-r11, and we DON'T want
-	 * to do that...
-	 */
-	cmp		r2, #8
-	ble		neon_f2b_copy_1_a
-
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	stmdb		sp!, {r7-r9}
-#else
-	push		{r7-r9}
-#endif
-	cmp		r12, #2
-	ldrb		r4, [r1], #1
-	ldrleb		r5, [r1], #1
-	ldrltb		r6, [r1], #1
-	rsb		r8, r12, #4
-	sub		r2, r2, r8
-	lsl		r8, r8, #3
-	orrle		r4, r4, r5, lsl #8
-	orrlt		r4, r4, r6, lsl #16
-	rsb		r9, r8, #32
-	/*
-	 * r4  = overflow bits
-	 * r8 = # of bits we copied into the r4 register to align source.
-	 * r9 = 32 - r8
-	 * r12 = Index counter for each size, so we determine how many times
-	 *       the given size will go into r2, then count down that # of
-	 *       times in r12.
-	 */
-	cmp		r2, #64
-	blt		neon_f2b_unaligned_route
-	ands		r12, r0, #0xf
-	beq		neon_f2b_unaligned_route
-	cmp		r3, #4
-	blt		neon_f2b_unaligned_route
-	rsb		r12, r12, #16
-neon_f2b_16_start_u:
-	sub		r2, r2, r12
-	lsrs		r6, r12, #2
-neon_f2b_align_16_4_u:
-	ldr		r5, [r1], #4
-	subs		r6, r6, #1
-	orr		r4, r4, r5, lsl r8
-	str		r4, [r0], #4
-	mov		r4, r5, lsr r9
-	bne		neon_f2b_align_16_4_u
-neon_f2b_unaligned_route:
-	cmp		r2, r3
-	movle		r12, r2
-	movgt		r12, r3
-	cmp		r12, #256
-	bge		neon_f2b_copy_64_u
-	cmp		r12, #64
-	bge		neon_f2b_copy_32_u
-	cmp		r12, #16
-	bge		neon_f2b_copy_16_u
-	cmp		r12, #8
-	bge		neon_f2b_copy_8_u
-	cmp		r12, #4
-	bge		neon_f2b_copy_4_u
-	b		neon_f2b_last_bits_u
-neon_f2b_copy_64_u:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vstmdb		sp!, {q4}
-	vstmdb		sp!, {q5-q8}
-#else
-	vpush		{q4}
-	vpush		{q5-q8}
-#endif
-	vdup.u32	q8, r8
-	mov		r12, r2, lsr #6
-	and		r2, r2, #0x3f
-neon_f2b_copy_64_u_loop:
-	vld1.32		{q4, q5}, [r1]!
-	vld1.32		{q6, q7}, [r1]!
-	lsls		r5, r8, #28
-	bcc		neon_f2b_copy_64_u_b8
-	bpl		neon_f2b_copy_64_u_b16
-	vshr.u64	q0, q4, #40
-	vshr.u64	q1, q5, #40
-	vshr.u64	q2, q6, #40
-	vshr.u64	q3, q7, #40
-	b		neon_f2b_copy_64_unify
-neon_f2b_copy_64_u_b8:
-	vshr.u64	q0, q4, #56
-	vshr.u64	q1, q5, #56
-	vshr.u64	q2, q6, #56
-	vshr.u64	q3, q7, #56
-	b		neon_f2b_copy_64_unify
-neon_f2b_copy_64_u_b16:
-	vshr.u64	q0, q4, #48
-	vshr.u64	q1, q5, #48
-	vshr.u64	q2, q6, #48
-	vshr.u64	q3, q7, #48
-neon_f2b_copy_64_unify:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vshl.u64	q4, q8, q4
-	vshl.u64	q5, q8, q5
-	vshl.u64	q6, q8, q6
-	vshl.u64	q7, q8, q7
-#else
-	vshl.u64	q4, q4, q8
-	vshl.u64	q5, q5, q8
-	vshl.u64	q6, q6, q8
-	vshl.u64	q7, q7, q8
-#endif
-	vmov		r5, s14
-	vorr		d9, d9, d0
-	vmov		s14, r4
-	vorr		d10, d10, d1
-	vorr		d11, d11, d2
-	vorr		d12, d12, d3
-	vorr		d13, d13, d4
-	vorr		d14, d14, d5
-	vorr		d15, d15, d6
-	vorr		d8, d8, d7
-	subs		r12, r12, #1
-	pld		[r1, #0]
-	pld		[r1, #128]
-	mov		r4, r5
-	vst1.32		{q4, q5}, [r0]!
-	vst1.32		{q6, q7}, [r0]!
-	pld		[r0, #0]
-	pld		[r0, #128]
-	bne		neon_f2b_copy_64_u_loop
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vldmia		sp!, {q5-q8}
-	vldmia		sp!, {q4}
-#else
-	vpop		{q5-q8}
-	vpop		{q4}
-#endif
-	cmp		r2, #32
-	bge		neon_f2b_copy_32_u
-	b		neon_f2b_copy_finish_u
-neon_f2b_copy_32_u:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vstmdb		sp!, {q4}
-#else
-	vpush		{q4}
-#endif
-	vdup.u32	q4, r8
-	mov		r12, r2, lsr #5
-	and		r2, r2, #0x1f
-neon_f2b_copy_32_u_loop:
-	vld1.32		{q0, q1}, [r1]!
-	lsls		r5, r8, #28
-	bcc		neon_f2b_copy_32_u_b8
-	bpl		neon_f2b_copy_32_u_b16
-	vshr.u64	q2, q0, #40
-	vshr.u64	q3, q1, #40
-	b		neon_f2b_copy_32_unify
-neon_f2b_copy_32_u_b8:
-	vshr.u64	q2, q0, #56
-	vshr.u64	q3, q1, #56
-	b		neon_f2b_copy_32_unify
-neon_f2b_copy_32_u_b16:
-	vshr.u64	q2, q0, #48
-	vshr.u64	q3, q1, #48
-neon_f2b_copy_32_unify:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vshl.u64	q0, q4, q0
-	vshl.u64	q1, q4, q1
-#else
-	vshl.u64	q0, q0, q4
-	vshl.u64	q1, q1, q4
-#endif
-	vmov		r5, s14
-	vorr		d1, d1, d4
-	vmov		s14, r4
-	vorr		d2, d2, d5
-	vorr		d3, d3, d6
-	vorr		d0, d0, d7
-	subs		r12, r12, #1
-	pld		[r1, #0]
-	mov		r4, r5
-	vst1.32		{q0, q1}, [r0]!
-	bne		neon_f2b_copy_32_u_loop
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vldmia		sp!, {q4}
-#else
-	vpop		{q4}
-#endif
-neon_f2b_copy_finish_u:
-neon_f2b_copy_16_u:
-	movs		r12, r2, lsr #4
-	beq		neon_f2b_copy_8_u
-	vdup.u32	q2, r8
-	and		r2, r2, #0xf
-neon_f2b_copy_16_u_loop:
-	vld1.32		{q0}, [r1]!
-	lsls		r5, r8, #28
-	bcc		neon_f2b_copy_16_u_b8
-	bpl		neon_f2b_copy_16_u_b16
-	vshr.u64	q1, q0, #40
-	b		neon_f2b_copy_16_unify
-neon_f2b_copy_16_u_b8:
-	vshr.u64	q1, q0, #56
-	b		neon_f2b_copy_16_unify
-neon_f2b_copy_16_u_b16:
-	vshr.u64	q1, q0, #48
-neon_f2b_copy_16_unify:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vshl.u64	q0, q2, q0
-#else
-	vshl.u64	q0, q0, q2
-#endif
-	vmov		r5, s6
-	vorr		d1, d1, d2
-	vmov		s6, r4
-	vorr		d0, d0, d3
-	subs		r12, r12, #1
-	mov		r4, r5
-	vst1.32		{q0}, [r0]!
-	bne		neon_f2b_copy_16_u_loop
-neon_f2b_copy_8_u:
-	cmp		r2, #8
-	blt		neon_f2b_copy_4_u
-	ldm		r1!, {r6-r7}
-	subs		r2, r2, #8
-	orr		r4, r4, r6, lsl r8
-	mov		r5, r6, lsr r9
-	orr		r5, r5, r7, lsl r8
-	stm		r0!, {r4-r5}
-	mov		r4, r7, lsr r9
-neon_f2b_copy_4_u:
-	cmp		r2, #4
-	blt		neon_f2b_last_bits_u
-	ldr		r5, [r1], #4
-	subs		r2, r2, #4
-	orr		r4, r4, r5, lsl r8
-	str		r4, [r0], #4
-	mov		r4, r5, lsr r9
-neon_f2b_last_bits_u:
-	lsr		r8, r8, #0x3
-neon_f2b_last_bits_u_loop:
-	strb		r4, [r0], #1
-	subs		r8, r8, #1
-	lsr		r4, r4, #8
-	bne		neon_f2b_last_bits_u_loop
-neon_f2b_copy_1_u:
-	cmp		r2, #0
-	beq		neon_f2b_finish_u
-neon_f2b_copy_1_u_loop:
-	ldrb		r12, [r1], #1
-	subs		r2, r2, #1
-	strb		r12, [r0], #1
-	bne		neon_f2b_copy_1_u_loop
-neon_f2b_finish_u:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	ldmia		sp!, {r7-r9}
-#else
-	pop		{r7-r9}
-#endif
-	/* #############################################################
-	 * Front to Back copy - finish
-	 */
-neon_f2b_finish:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	ldmia		sp!, {r4-r6}
-#else
-	pop		{r4-r6}
-#endif
-	b		neon_memmove_done
-
-	/* #############################################################
-	 * Back to Front copy
-	 */
-neon_back_to_front_copy:
-	/*
-	 * Here, we'll want to shift to the end of the buffers.  This
-	 * actually points us one past where we need to go, but since
-	 * we'll pre-decrement throughout, this will be fine.
-	 */
-	add		r0, r0, r2
-	add		r1, r1, r2
-	cmp		r2, #4
-	bgt		neon_b2f_gt4
-	cmp		r2, #0
-neon_b2f_smallcopy_loop:
-	beq		neon_memmove_done
-	ldrb		r12, [r1, #-1]!
-	subs		r2, r2, #1
-	strb		r12, [r0, #-1]!
-	b		neon_b2f_smallcopy_loop
-neon_b2f_gt4:
-	pld		[r0, #0]
-	pld		[r1, #0]
-	/*
-	 * The minimum of the overlap window size and the copy size
-	 * is in r3.
-	 */
-	sub		r3, r0, r1
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	stmdb		sp!, {r4-r5}
-#else
-	push		{r4-r5}
-#endif
-
-	/*
-	 * Check alignment.  Since we'll pre-decrement as we step thru, we'll
-	 * need to make sure we're on word-alignment.
-	 */
-neon_b2f_check_align:
-	ands		r12, r0, #0x3
-	beq		neon_b2f_source_align_check
-	sub		r2, r2, r12
-neon_b2f_shift_align:
-	ldrb		r4, [r1, #-1]!
-	subs		r12, r12, #1
-	strb		r4, [r0, #-1]!
-	bne		neon_b2f_shift_align
-neon_b2f_source_align_check:
-	ands		r4, r1, #0x3
-	bne		neon_b2f_nonaligned
-	
-neon_b2f_try_16_align:
-	/* If we're >64, attempt to align on 16-bytes.  Smaller amounts
-	 * don't seem to be worth handling. */
-	cmp		r2, #64
-	blt		neon_b2f_align_route
-	ands		r12, r0, #0xf
-	beq		neon_b2f_align_route
-	/* In this case, r12 has the number of bytes to roll backward. */
-neon_b2f_16_start:
-	sub		r2, r2, r12
-	lsrs		r5, r12, #2
-neon_b2f_align_16_4:
-	ldr		r4, [r1, #-4]!
-	subs		r5, r5, #1
-	str		r4, [r0, #-4]!
-	bne		neon_b2f_align_16_4
-neon_b2f_align_route:
-	/*
-	 * #############################################################
-	 * Back to Front copy - aligned
-	 */
-	cmp		r2, r3
-	movle		r12, r2
-	movgt		r12, r3
-	cmp		r12, #256
-	bge		neon_b2f_copy_128_a
-	cmp		r12, #64
-	bge		neon_b2f_copy_32_a
-	cmp		r12, #8
-	bge		neon_b2f_copy_8_a
-	cmp		r12, #4
-	bge		neon_b2f_copy_4_a
-	b		neon_b2f_copy_1_a
-neon_b2f_copy_128_a:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vstmdb		sp!, {q4-q7}
-#else
-	vpush		{q4-q7}
-#endif
-	movs		r12, r2, lsr #7
-	/*
-	 * This irks me.  There MUST be a better way to read these in and
-	 * scan the register backward instead of making it go forward.  Then
-	 * we need to do two subtractions...
-	 */
-neon_b2f_copy_128_a_loop:
-	sub		r1, r1, #128
-	sub		r0, r0, #128
-	vld1.32		{q0, q1}, [r1]!
-	vld1.32		{q2, q3}, [r1]!
-	vld1.32		{q4, q5}, [r1]!
-	vld1.32		{q6, q7}, [r1]!
-	pld		[r1, #-128]
-	pld		[r1, #-256]
-	vst1.32		{q0, q1}, [r0]!
-	vst1.32		{q2, q3}, [r0]!
-	vst1.32		{q4, q5}, [r0]!
-	vst1.32		{q6, q7}, [r0]!
-	subs		r12, r12, #1
-	pld		[r0, #-128]
-	pld		[r0, #-256]
-	sub		r1, r1, #128
-	sub		r0, r0, #128
-	bne		neon_b2f_copy_128_a_loop
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vldmia		sp!, {q4-q7}
-#else
-	vpop		{q4-q7}
-#endif
-	ands		r2, r2, #0x7f
-	beq		neon_b2f_finish
-	cmp		r2, #32
-	bge		neon_b2f_copy_32_a
-	b		neon_b2f_copy_finish_a
-neon_b2f_copy_32_a:
-	mov		r12, r2, lsr #5
-neon_b2f_copy_32_a_loop:
-	sub		r1, r1, #32
-	sub		r0, r0, #32
-	vld1.32		{q0,q1}, [r1]
-	subs		r12, r12, #1
-	vst1.32		{q0,q1}, [r0]
-	pld		[r1, #0]
-	bne		neon_b2f_copy_32_a_loop
-	ands		r2, r2, #0x1f
-	beq		neon_b2f_finish
-neon_b2f_copy_finish_a:
-neon_b2f_copy_8_a:
-	movs		r12, r2, lsr #0x3
-	beq		neon_b2f_copy_4_a
-neon_b2f_copy_8_a_loop:
-	ldmdb		r1!, {r4-r5}
-	subs		r12, r12, #1
-	stmdb		r0!, {r4-r5}
-	bne		neon_b2f_copy_8_a_loop
-	and		r2, r2, #0x7
-neon_b2f_copy_4_a:
-	movs		r12, r2, lsr #0x2
-	beq		neon_b2f_copy_1_a
-	and		r2, r2, #0x3
-neon_b2f_copy_4_a_loop:
-	ldr		r4, [r1, #-4]!
-	subs		r12, r12, #1
-	str		r4, [r0, #-4]!
-	bne		neon_b2f_copy_4_a_loop
-neon_b2f_copy_1_a:
-	cmp		r2, #0
-	beq		neon_b2f_finish
-neon_b2f_copy_1_a_loop:
-	ldrb		r12, [r1, #-1]!
-	subs		r2, r2, #1
-	strb		r12, [r0, #-1]!
-	bne		neon_b2f_copy_1_a_loop
-
-	/* #############################################################
-	 * Back to Front copy - unaligned
-	 */
-neon_b2f_nonaligned:
-	/*
-	 * For sizes < 8, does it really make sense to do the whole shift
-	 * party?
-	 */
-	cmp		r2, #8
-	ble		neon_b2f_copy_1_a
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	stmdb		sp!, {r6-r11}
-#else
-	push		{r6-r11}
-#endif
-	/*
-	 * r3 = max window size
-	 * r4 = overflow bytes
-	 * r5 = bytes we're reading into
-	 * r6 = # bytes we're off.
-	 * r10 = copy of r6
-	 */
-	and		r6, r1, #0x3
-	eor		r4, r4, r4
-	mov		r10, r6
-neon_b2f_realign:
-	ldrb		r5, [r1, #-1]!
-	subs		r6, r6, #1
-	orr		r4, r5, r4, lsl #8
-	bne		neon_b2f_realign
-	/*
-	 * r10 = # of bits we copied into the r4 register to align source.
-	 * r11 = 32 - r10
-	 * r12 = Index counter for each size, so we determine how many times
-	 *       the given size will go into r2, then count down that # of
-	 *       times in r12.
-	 */
-	sub		r2, r2, r10
-	lsl		r10, r10, #0x3
-	rsb		r11, r10, #32
-
-	cmp		r2, r3
-	movle		r12, r2
-	movgt		r12, r3
-	cmp		r12, #256
-	bge		neon_b2f_copy_64_u
-	cmp		r12, #64
-	bge		neon_b2f_copy_32_u
-	cmp		r12, #8
-	bge		neon_b2f_copy_8_u
-	cmp		r12, #4
-	bge		neon_b2f_copy_4_u
-	b		neon_b2f_last_bits_u
-neon_b2f_copy_64_u:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vstmdb		sp!, {q4,q5}
-	vstmdb		sp!, {q6-q8}
-#else
-	vpush		{q4,q5}
-	vpush		{q6-q8}
-#endif
-	add		r7, r11, #32
-	movs		r12, r2, lsr #6
-	vdup.u32	q8, r7
-neon_b2f_copy_64_u_loop:
-	sub		r1, r1, #64
-	sub		r0, r0, #64
-	vld1.32		{q0, q1}, [r1]!
-	vld1.32		{q2, q3}, [r1]
-	sub		r1, r1, #32
-	vmov		q4, q0
-	vmov		q5, q1
-	vmov		q6, q2
-	vmov		q7, q3
-	vmov		r5, s0
-	mov		r4, r4, lsl r11
-	lsls		r6, r10, #28
-	bcc		neon_b2f_copy_64_u_b8
-	bpl		neon_b2f_copy_64_u_b16
-	vshr.u64	q0, q0, #24
-	vshr.u64	q1, q1, #24
-	vshr.u64	q2, q2, #24
-	vshr.u64	q3, q3, #24
-	b		neon_b2f_copy_64_unify
-neon_b2f_copy_64_u_b8:
-	vshr.u64	q0, q0, #8
-	vshr.u64	q1, q1, #8
-	vshr.u64	q2, q2, #8
-	vshr.u64	q3, q3, #8
-	b		neon_b2f_copy_64_unify
-neon_b2f_copy_64_u_b16:
-	vshr.u64	q0, q0, #16
-	vshr.u64	q1, q1, #16
-	vshr.u64	q2, q2, #16
-	vshr.u64	q3, q3, #16
-neon_b2f_copy_64_unify:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vshl.u64	q4, q8, q4
-	vshl.u64	q5, q8, q5
-	vshl.u64	q6, q8, q6
-	vshl.u64	q7, q8, q7
-#else
-	vshl.u64	q4, q4, q8
-	vshl.u64	q5, q5, q8
-	vshl.u64	q6, q6, q8
-	vshl.u64	q7, q7, q8
-#endif
-	vmov		s17, r4
-	vorr		d7, d7, d8
-	vorr		d6, d6, d15
-	vorr		d5, d5, d14
-	vorr		d4, d4, d13
-	vorr		d3, d3, d12
-	vorr		d2, d2, d11
-	vorr		d1, d1, d10
-	vorr		d0, d0, d9
-	mov		r4, r5, lsl r11
-	subs		r12, r12, #1
-	lsr		r4, r4, r11
-	vst1.32		{q0, q1}, [r0]!
-	vst1.32		{q2, q3}, [r0]
-	pld		[r1, #0]
-	sub		r0, r0, #32
-	bne		neon_b2f_copy_64_u_loop
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vldmia		sp!, {q6-q8}
-	vldmia		sp!, {q4,q5}
-#else
-	vpop		{q6-q8}
-	vpop		{q4,q5}
-#endif
-	ands		r2, r2, #0x3f
-	cmp		r2, #32
-	bge		neon_b2f_copy_32_u
-	b		neon_b2f_copy_finish_u
-neon_b2f_copy_32_u:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vstmdb		sp!, {q4}
-#else
-	vpush		{q4}
-#endif
-	add		r7, r11, #32
-	movs		r12, r2, lsr #5
-	vdup.u32	q4, r7
-	and		r2, r2, #0x1f
-neon_b2f_copy_32_u_loop:
-	sub		r1, r1, #32
-	sub		r0, r0, #32
-	vld1.32		{q0, q1}, [r1]
-	vmov		q2, q0
-	vmov		q3, q1
-	vmov		r5, s0
-	mov		r4, r4, lsl r11
-	lsls		r6, r10, #28
-	bcc		neon_b2f_copy_32_u_b8
-	bpl		neon_b2f_copy_32_u_b16
-	vshr.u64	q0, q0, #24
-	vshr.u64	q1, q1, #24
-	b		neon_b2f_copy_32_unify
-neon_b2f_copy_32_u_b8:
-	vshr.u64	q0, q0, #8
-	vshr.u64	q1, q1, #8
-	b		neon_b2f_copy_32_unify
-neon_b2f_copy_32_u_b16:
-	vshr.u64	q0, q0, #16
-	vshr.u64	q1, q1, #16
-neon_b2f_copy_32_unify:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vshl.u64	q2, q4, q2
-	vshl.u64	q3, q4, q3
-#else
-	vshl.u64	q2, q2, q4
-	vshl.u64	q3, q3, q4
-#endif
-	vmov		s9, r4
-	vorr		d3, d3, d4
-	vorr		d2, d2, d7
-	vorr		d1, d1, d6
-	vorr		d0, d0, d5
-	mov		r4, r5, lsl r11
-	subs		r12, r12, #1
-	lsr		r4, r4, r11
-	vst1.32		{q0, q1}, [r0]
-	pld		[r1, #0]
-	bne		neon_b2f_copy_32_u_loop
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	vldmia		sp!, {q4}
-#else
-	vpop		{q4}
-#endif
-neon_b2f_copy_finish_u:
-neon_b2f_copy_8_u:
-	movs		r12, r2, lsr #0x3
-	beq		neon_b2f_copy_4_u
-	mov		r5, r4, lsl r11
-neon_b2f_copy_8_u_loop:
-	ldmdb		r1!, {r6-r7}
-	subs		r12, r12, #1
-	orr		r5, r5, r7, lsr r10
-	mov		r4, r7, lsl r11
-	orr		r4, r4, r6, lsr r10
-	stmdb		r0!, {r4-r5}
-	mov		r4, r6, lsl r11
-	lsr		r4, r4, r11
-	mov		r5, r4, lsl r11
-	bne		neon_b2f_copy_8_u_loop
-	ands		r2, r2, #0x7
-neon_b2f_copy_4_u:
-	movs		r12, r2, lsr #0x2
-	beq		neon_b2f_last_bits_u
-	mov		r5, r4, lsl r11
-neon_b2f_copy_4_u_loop:
-	ldr		r6, [r1, #-4]!
-	subs		r12, r12, #1
-	orr		r5, r5, r6, lsr r10
-	str		r5, [r0, #-4]!
-	mov		r4, r6, lsl r11
-	lsr		r4, r4, r11
-	mov		r5, r4, lsl r11
-	bne		neon_b2f_copy_4_u_loop
-	and		r2, r2, #0x3
-neon_b2f_last_bits_u:
-neon_b2f_last_bits_u_loop:
-	subs		r10, r10, #8
-	mov		r5, r4, lsr r10
-	strb		r5, [r0, #-1]!
-	bne		neon_b2f_last_bits_u_loop
-neon_b2f_copy_1_u:
-	cmp		r2, #0
-	beq		neon_b2f_finish_u
-neon_b2f_copy_1_u_loop:
-	ldrb		r12, [r1, #-1]!
-	subs		r2, r2, #1
-	strb		r12, [r0, #-1]!
-	bne		neon_b2f_copy_1_u_loop
-neon_b2f_finish_u:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	ldmia		sp!, {r6-r11}
-#else
-	pop		{r6-r11}
-#endif
-
-neon_b2f_finish:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	ldmia		sp!, {r4-r5}
-#else
-	pop		{r4-r5}
-#endif
-
-neon_memmove_done:
-#if defined __GNUC__ && (4 == __GNUC__ && 1 == __GNUC_MINOR__ && 1 == __GNUC_PATCHLEVEL__)
-	ldmia		sp!, {r0}
-#else
-	pop		{r0}
-#endif
-	bx		lr
-
-	.endfunc
-	.end
diff --git git/src/neon_memsets.c git/src/neon_memsets.c
deleted file mode 100755
index 740fc1e..0000000
--- git/src/neon_memsets.c
+++ /dev/null
@@ -1,169 +0,0 @@
-/* neon_memsets.c
- *
- * Copyright (c) 2009, Code Aurora Forum. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Code Aurora nor
- *       the names of its contributors may be used to endorse or promote
- *       products derived from this software without specific prior written
- *       permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NON-INFRINGEMENT ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
- * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
- * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
- * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
- * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
- * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
- * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
- * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include "msm-swblits.h"
-
-void memset16(uint16_t dst[], uint16_t value, int count)
-{
-    if (count <= 0)
-        return;
-
-    asm volatile(
-                 "       pld        [%[dst], #0]                           \n"
-                 "       cmp        %[count], #4                           \n"
-                 "       blt        6f                                     \n"
-                 "       tst        %[dst], #0x3                           \n"
-                 "       strneh     %[value], [%[dst]], #2                 \n"
-                 "       subne      %[count], %[count], #1                 \n"
-                 "       vdup.u16   q8, %[value]                           \n"
-                 "       vmov       q9, q8                                 \n"
-                 "       cmp        %[count], #64                          \n"
-                 "       bge        0f                                     \n"
-                 "       cmp        %[count], #32                          \n"
-                 "       bge        2f                                     \n"
-                 "       cmp        %[count], #16                          \n"
-                 "       bge        3f                                     \n"
-                 "       cmp        %[count], #8                           \n"
-                 "       bge        4f                                     \n"
-                 "       b          5f                                     \n"
-                 "0:                                                       \n"
-                 "       mov        r12, %[count], lsr #6                  \n"
-                 "1:                                                       \n"
-                 "       vst1.16    {q8, q9}, [%[dst]]!                    \n"
-                 "       vst1.16    {q8, q9}, [%[dst]]!                    \n"
-                 "       vst1.16    {q8, q9}, [%[dst]]!                    \n"
-                 "       vst1.16    {q8, q9}, [%[dst]]!                    \n"
-                 "       subs       r12, r12, #1                           \n"
-                 "       bne        1b                                     \n"
-                 "       ands       %[count], %[count], #0x3f              \n"
-                 "       beq        7f                                     \n"
-                 "2:                                                       \n"
-                 "       cmp        %[count], #32                          \n"
-                 "       blt        3f                                     \n"
-                 "       vst1.16    {q8, q9}, [%[dst]]!                    \n"
-                 "       vst1.16    {q8, q9}, [%[dst]]!                    \n"
-                 "       subs       %[count], %[count], #32                \n"
-                 "       beq        7f                                     \n"
-                 "3:                                                       \n"
-                 "       cmp        %[count], #16                          \n"
-                 "       blt        4f                                     \n"
-                 "       vst1.16    {q8, q9}, [%[dst]]!                    \n"
-                 "       subs       %[count], %[count], #16                \n"
-                 "       beq        7f                                     \n"
-                 "4:                                                       \n"
-                 "       cmp        %[count], #8                           \n"
-                 "       blt        5f                                     \n"
-                 "       vst1.16    {q8}, [%[dst]]!                        \n"
-                 "       subs       %[count], %[count], #8                 \n"
-                 "       beq        7f                                     \n"
-                 "5:                                                       \n"
-                 "       cmp        %[count], #4                           \n"
-                 "       blt        6f                                     \n"
-                 "       vst1.16    {d16}, [%[dst]]!                       \n"
-                 "       subs       %[count], %[count], #4                 \n"
-                 "       beq        7f                                     \n"
-                 "6:                                                       \n"
-                 "       cmp        %[count], #0                           \n"
-                 "       blt        7f                                     \n"
-                 "       lsls       %[count], #31                          \n"
-                 "       strmih     %[value], [%[dst]], #2                 \n"
-                 "       strcsh     %[value], [%[dst]], #2                 \n"
-                 "       strcsh     %[value], [%[dst]], #2                 \n"
-                 "7:                                                       \n"
-                 // Clobbered input registers
-                 : [dst] "+r" (dst), [count] "+r" (count)
-                 // Unclobbered input
-                 : [value] "r" (value)
-                 // Clobbered registers
-                 : "q8", "q9", "r12", "cc", "memory"
-                 );
-}
-
-void memset32(uint32_t dst[], uint32_t value, int count)
-{
-    asm volatile(
-                 "       pld        [%[dst], #0]                           \n"
-                 "       cmp        %[count], #4                           \n"
-                 "       blt        5f                                     \n"
-                 "       vdup.u32   q8, %[value]                           \n"
-                 "       vmov       q9, q8                                 \n"
-                 "       cmp        %[count], #32                          \n"
-                 "       bge        0f                                     \n"
-                 "       cmp        %[count], #16                          \n"
-                 "       bge        2f                                     \n"
-                 "       cmp        %[count], #8                           \n"
-                 "       bge        3f                                     \n"
-                 "       b          4f                                     \n"
-                 "0:                                                       \n"
-                 "       mov        r12, %[count], lsr #5                  \n"
-                 "1:                                                       \n"
-                 "       vst1.32    {q8, q9}, [%[dst]]!                    \n"
-                 "       vst1.32    {q8, q9}, [%[dst]]!                    \n"
-                 "       vst1.32    {q8, q9}, [%[dst]]!                    \n"
-                 "       vst1.32    {q8, q9}, [%[dst]]!                    \n"
-                 "       pld        [%[dst], #0]                           \n"
-                 "       subs       r12, r12, #1                           \n"
-                 "       bne        1b                                     \n"
-                 "       ands       %[count], %[count], #0x1f              \n"
-                 "       beq        6f                                     \n"
-                 "2:                                                       \n"
-                 "       cmp        %[count], #16                          \n"
-                 "       blt        3f                                     \n"
-                 "       vst1.32    {q8, q9}, [%[dst]]!                    \n"
-                 "       vst1.32    {q8, q9}, [%[dst]]!                    \n"
-                 "       subs       %[count], %[count], #16                \n"
-                 "       beq        6f                                     \n"
-                 "3:                                                       \n"
-                 "       cmp        %[count], #8                           \n"
-                 "       blt        4f                                     \n"
-                 "       vst1.32    {q8, q9}, [%[dst]]!                    \n"
-                 "       subs       %[count], %[count], #8                 \n"
-                 "       beq        6f                                     \n"
-                 "4:                                                       \n"
-                 "       cmp        %[count], #4                           \n"
-                 "       blt        5f                                     \n"
-                 "       vst1.32    {q8}, [%[dst]]!                        \n"
-                 "       subs       %[count], %[count], #4                 \n"
-                 "       beq        6f                                     \n"
-                 "5:                                                       \n"
-                 "       cmp        %[count], #0                           \n"
-                 "       beq        6f                                     \n"
-                 "       lsls       %[count], #31                          \n"
-                 "       strmi      %[value], [%[dst]], #4                 \n"
-                 "       strcs      %[value], [%[dst]], #4                 \n"
-                 "       strcs      %[value], [%[dst]], #4                 \n"
-                 "6: @end                                                  \n"
-                 // Clobbered input registers
-                 : [dst] "+r" (dst), [count] "+r" (count)
-                 // Unclobbered input
-                 : [value] "r" (value)
-                 // Clobbered registers
-                 : "q8", "q9", "r12", "cc", "memory"
-                 );
-}