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
diff --git a/apps/plugins/SUBDIRS b/apps/plugins/SUBDIRS
index d94a247..63761d5 100644
--- a/apps/plugins/SUBDIRS
+++ b/apps/plugins/SUBDIRS
@@ -53,6 +53,9 @@ mpegplayer
 #endif
 #endif
 #endif
+#ifdef CPU_ARM
+idct_test
+#endif

 /* Lua needs at least 160 KB to work in */
 #if (PLUGIN_BUFFER_SIZE >= 0x80000)
diff --git a/apps/plugins/idct_test/SOURCES b/apps/plugins/idct_test/SOURCES
new file mode 100644
index 0000000..3571c4d
--- /dev/null
+++ b/apps/plugins/idct_test/SOURCES
@@ -0,0 +1,2 @@
+idct_test.c
+idct.S
diff --git a/apps/plugins/idct_test/idct.S b/apps/plugins/idct_test/idct.S
new file mode 100644
index 0000000..e8bffbd
--- /dev/null
+++ b/apps/plugins/idct_test/idct.S
@@ -0,0 +1,948 @@
+#include "config.h"
+#undef HAVE_LCD_COLOR
+
+    .section .text
+    .align   2
+    .global jpeg_idct8v_armv4_1_z
+    .type   jpeg_idct8v_armv4_1_z, %function
+    .global jpeg_idct8v_armv4_1_n
+    .type   jpeg_idct8v_armv4_1_n, %function
+    .global jpeg_idct8v_armv5_1_z
+    .type   jpeg_idct8v_armv5_1_z, %function
+    .global jpeg_idct8v_armv6_1_z
+    .type   jpeg_idct8v_armv6_1_z, %function
+    .global jpeg_idct8h_armv4_1_z
+    .type   jpeg_idct8h_armv4_1_z, %function
+    .global jpeg_idct8h_armv4_1_n
+    .type   jpeg_idct8h_armv4_1_n, %function
+    .global jpeg_idct8h_armv5_1_z
+    .type   jpeg_idct8h_armv5_1_z, %function
+    .global jpeg_idct8h_armv6_1_z
+    .type   jpeg_idct8h_armv6_1_z, %function
+
+jpeg_idct8v_armv4_1_z:
+    stmdb  sp!, { r4-r11, lr }
+    add    r2,  r0,  #128
+1:
+    ldmia  r0!, { r4-r7 }
+    mov    r8,  r4,  lsl #16
+    orrs   r9,  r6,  r7
+    orreqs r9,  r5,  r4, lsr #16
+    bne    2f
+    mov    r8,  r8,  asr #14
+    strh   r8,  [r2]
+    strh   r8,  [r2, #16]
+    strh   r8,  [r2, #32]
+    strh   r8,  [r2, #48]
+    strh   r8,  [r2, #64]
+    strh   r8,  [r2, #80]
+    strh   r8,  [r2, #96]
+    strh   r8,  [r2, #112]
+    cmp    r0,  r1
+    add    r2,  r2,  #2
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+2:
+    ldr    r14, =4433
+    ldr    r12, =-15137
+    mov    r10, r5,  lsl #16
+    mov    r11, r7,  lsl #16
+    mov    r10, r10, asr #16        /* r10 = z2 = d2 */
+    mov    r11, r11, asr #16        /* r11 = z3 = d6 */
+    add    r8,  r8,  #8192
+    add    r9,  r10, r11
+    mov    r8,  r8,  asr #3         /* r8  = z4 = (d0 << 13) + 1024 */
+    mul    r9,  r14, r9             /* r9  = z1 = (z2 + z3) * 4433 */
+    ldr    r14, =6270
+    mla    r11, r12, r11, r9         /* r11 = tmp2 = z1 - z3 * 15137 */
+    mla    r10, r14, r10, r9         /* r10 = tmp3 = z1 + z2 * 6270 */
+    mov    r9,  r6,  lsl #16         /* r9  = z5 << 3 = d4 << 16 */
+    add    r12, r8,  r9,  asr #3     /* r12 = tmp0 = z4 + z5 */
+    sub    r14, r8,  r9,  asr #3     /* r14 = tmp1 = z4 - z5 */
+    add    r8,  r12, r10             /* r8  = tmp10 = tmp0 + tmp3 */
+    sub    r9,  r12, r10             /* r9  = tmp13 = tmp0 - tmp3 */
+    add    r10, r14, r11             /* r10 = tmp11 = tmp1 + tmp2 */
+    sub    r11, r14, r11             /* r11 = tmp12 = tmp1 - tmp2 */
+    stmdb  sp,  { r8-r11 }           /* tmp10 tmp13 tmp11 tmp12 */
+    mov    r4,  r4,  asr #16         /* r4  = tmp3 = d1 */
+    mov    r5,  r5,  asr #16         /* r5  = tmp2 = d3 */
+    mov    r6,  r6,  asr #16         /* r6  = tmp1 = d5 */
+    mov    r7,  r7,  asr #16         /* r7  = tmp0 = d7 */
+    ldr    r10, =9633
+    ldr    r11, =-16069
+    add    r12, r5,  r7              /* r12 = z3 = tmp0 + tmp2 */
+    add    r14, r4,  r6              /* r14 = z4 = tmp1 + tmp3 */
+    add    r9,  r12, r14             /* r9  = z3 + z4 */
+    mul    r9,  r10, r9              /* r9  = z5 = (z3 + z4) * 9633 */
+    ldr    r10, =-3196
+    mla    r12, r11, r12, r9         /* r12 = z3 = z5 - z3 * 16069 */
+    ldr    r11, =-7373
+    mla    r14, r10, r14, r9         /* r14 = z4 = z5 - z4 * 3196 */
+    ldr    r10, =2446
+    add    r9,  r4,  r7              /* r9  = tmp0 + tmp3 */
+    mla    r8,  r11, r9,  r12        /* r8  = z1 + z3 */
+    mla    r9,  r11, r9,  r14        /* r9  = z1 + z4 */
+    ldr    r11, =12299
+    mla    r7,  r10, r7,  r8         /* r7  = tmp0 = z1 + z3 + tmp0 * 2446 */
+    ldr    r10, =-20995
+    mla    r4,  r11, r4,  r9         /* r4  = tmp3 = z1 + z4 + tmp0 * 12299 */
+    ldr    r11, =25172
+    add    r9,  r5,  r6              /* r9  = tmp1 + tmp2 */
+    mla    r12, r10, r9, r12         /* r12 = z2 + z3 */
+    mla    r14, r10, r9, r14         /* r14 = z2 + z4 */
+    ldr    r10, =16819
+    mla    r5,  r11, r5, r12         /* r5  = tmp2 = z2 + z3 + tmp2 * 25172 */
+    mla    r6,  r10, r6, r14         /* r6  = tmp1 = z2 + z4 + tmp1 * 16819 */
+    ldmdb  sp,  { r8-r11 }
+    add    r12, r8,  r4              /* o0 */
+    sub    r14, r8,  r4              /* o7 */
+    add    r8,  r9,  r7              /* o3 */
+    sub    r9,  r9,  r7              /* o4 */
+    add    r4,  r10, r5              /* O1 */
+    sub    r5,  r10, r5              /* o6 */
+    add    r10, r11, r6              /* o2 */
+    sub    r11, r11, r6              /* o5 */
+    /* output in order: r12 r4  r10 r8  r9  r11 r5  r14 */
+    mov    r12, r12, asr #11
+    mov    r4,  r4,  asr #11
+    mov    r10, r10, asr #11
+    mov    r8,  r8,  asr #11
+    mov    r9,  r9,  asr #11
+    mov    r11, r11, asr #11
+    mov    r5,  r5,  asr #11
+    mov    r14, r14, asr #11
+    strh   r12, [r2]
+    strh   r4,  [r2, #16]
+    strh   r10, [r2, #32]
+    strh   r8,  [r2, #48]
+    strh   r9,  [r2, #64]
+    strh   r11, [r2, #80]
+    strh   r5,  [r2, #96]
+    strh   r14, [r2, #112]
+    cmp    r0,  r1
+    add    r2,  r2,  #2
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+    .size jpeg_idct8v_armv4_1_z, .-jpeg_idct8v_armv4_1_z
+
+jpeg_idct8v_armv4_1_n:
+    stmdb  sp!, { r4-r11, lr }
+    add    r2,  r0,  #128
+1:
+    ldmia  r0!, { r4-r7 }
+    mov    r8,  r4,  lsl #16
+    ldr    r14, =4433
+    ldr    r12, =-15137
+    mov    r10, r5,  lsl #16
+    mov    r11, r7,  lsl #16
+    mov    r10, r10, asr #16        /* r10 = z2 = d2 */
+    mov    r11, r11, asr #16        /* r11 = z3 = d6 */
+    add    r8,  r8,  #8192
+    add    r9,  r10, r11
+    mov    r8,  r8,  asr #3         /* r8  = z4 = (d0 << 13) + 1024 */
+    mul    r9,  r14, r9             /* r9  = z1 = (z2 + z3) * 4433 */
+    ldr    r14, =6270
+    mla    r11, r12, r11, r9         /* r11 = tmp2 = z1 - z3 * 15137 */
+    mla    r10, r14, r10, r9         /* r10 = tmp3 = z1 + z2 * 6270 */
+    mov    r9,  r6,  lsl #16         /* r9  = z5 << 3 = d4 << 16 */
+    add    r12, r8,  r9,  asr #3     /* r12 = tmp0 = z4 + z5 */
+    sub    r14, r8,  r9,  asr #3     /* r14 = tmp1 = z4 - z5 */
+    add    r8,  r12, r10             /* r8  = tmp10 = tmp0 + tmp3 */
+    sub    r9,  r12, r10             /* r9  = tmp13 = tmp0 - tmp3 */
+    add    r10, r14, r11             /* r10 = tmp11 = tmp1 + tmp2 */
+    sub    r11, r14, r11             /* r11 = tmp12 = tmp1 - tmp2 */
+    stmdb  sp,  { r8-r11 }           /* tmp10 tmp13 tmp11 tmp12 */
+    mov    r4,  r4,  asr #16         /* r4  = tmp3 = d1 */
+    mov    r5,  r5,  asr #16         /* r5  = tmp2 = d3 */
+    mov    r6,  r6,  asr #16         /* r6  = tmp1 = d5 */
+    mov    r7,  r7,  asr #16         /* r7  = tmp0 = d7 */
+    ldr    r10, =9633
+    ldr    r11, =-16069
+    add    r12, r5,  r7              /* r12 = z3 = tmp0 + tmp2 */
+    add    r14, r4,  r6              /* r14 = z4 = tmp1 + tmp3 */
+    add    r9,  r12, r14             /* r9  = z3 + z4 */
+    mul    r9,  r10, r9              /* r9  = z5 = (z3 + z4) * 9633 */
+    ldr    r10, =-3196
+    mla    r12, r11, r12, r9         /* r12 = z3 = z5 - z3 * 16069 */
+    ldr    r11, =-7373
+    mla    r14, r10, r14, r9         /* r14 = z4 = z5 - z4 * 3196 */
+    ldr    r10, =2446
+    add    r9,  r4,  r7              /* r9  = tmp0 + tmp3 */
+    mla    r8,  r11, r9,  r12        /* r8  = z1 + z3 */
+    mla    r9,  r11, r9,  r14        /* r9  = z1 + z4 */
+    ldr    r11, =12299
+    mla    r7,  r10, r7,  r8         /* r7  = tmp0 = z1 + z3 + tmp0 * 2446 */
+    ldr    r10, =-20995
+    mla    r4,  r11, r4,  r9         /* r4  = tmp3 = z1 + z4 + tmp0 * 12299 */
+    ldr    r11, =25172
+    add    r9,  r5,  r6              /* r9  = tmp1 + tmp2 */
+    mla    r12, r10, r9, r12         /* r12 = z2 + z3 */
+    mla    r14, r10, r9, r14         /* r14 = z2 + z4 */
+    ldr    r10, =16819
+    mla    r5,  r11, r5, r12         /* r5  = tmp2 = z2 + z3 + tmp2 * 25172 */
+    mla    r6,  r10, r6, r14         /* r6  = tmp1 = z2 + z4 + tmp1 * 16819 */
+    ldmdb  sp,  { r8-r11 }
+    add    r12, r8,  r4              /* o0 */
+    sub    r14, r8,  r4              /* o7 */
+    add    r8,  r9,  r7              /* o3 */
+    sub    r9,  r9,  r7              /* o4 */
+    add    r4,  r10, r5              /* O1 */
+    sub    r5,  r10, r5              /* o6 */
+    add    r10, r11, r6              /* o2 */
+    sub    r11, r11, r6              /* o5 */
+    /* output in order: r12 r4  r10 r8  r9  r11 r5  r14 */
+    mov    r12, r12, asr #11
+    mov    r4,  r4,  asr #11
+    mov    r10, r10, asr #11
+    mov    r8,  r8,  asr #11
+    mov    r9,  r9,  asr #11
+    mov    r11, r11, asr #11
+    mov    r5,  r5,  asr #11
+    mov    r14, r14, asr #11
+    strh   r12, [r2]
+    strh   r4,  [r2, #16]
+    strh   r10, [r2, #32]
+    strh   r8,  [r2, #48]
+    strh   r9,  [r2, #64]
+    strh   r11, [r2, #80]
+    strh   r5,  [r2, #96]
+    strh   r14, [r2, #112]
+    cmp    r0,  r1
+    add    r2,  r2,  #2
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+    .size jpeg_idct8v_armv4_1_n, .-jpeg_idct8v_armv4_1_n
+
+jpeg_idct8h_armv4_1_z:
+    stmdb  sp!, { r4-r11, lr }
+1:
+    ldmia  r0!, { r4-r7 }
+    ldr    r14, =(4112<<16)
+    add    r8,  r14, r8,  lsl #16
+    orrs   r9,  r6,  r7
+    orreqs r9,  r5,  r4, lsr #16
+    bne    2f
+    mov    r8,  r8,  asr #21
+    cmp    r8,  #255
+    mvnhi  r8,  r8,  asr #31
+#ifdef HAVE_LCD_COLOR
+    strb   r8,  [r1]
+    strb   r8,  [r1, #4]
+    strb   r8,  [r1, #8]
+    strb   r8,  [r1, #12]
+    strb   r8,  [r1, #16]
+    strb   r8,  [r1, #20]
+    strb   r8,  [r1, #24]
+    strb   r8,  [r1, #28]
+#else
+    strb   r8,  [r1]
+    strb   r8,  [r1, #1]
+    strb   r8,  [r1, #2]
+    strb   r8,  [r1, #3]
+    strb   r8,  [r1, #4]
+    strb   r8,  [r1, #5]
+    strb   r8,  [r1, #6]
+    strb   r8,  [r1, #7]
+#endif
+    add    r1,  r1,  r3
+    cmp    r0,  r2
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+2:
+    ldr    r14, =4433
+    ldr    r12, =-15137
+    mov    r10, r5,  lsl #16
+    mov    r11, r7,  lsl #16
+    mov    r10, r10, asr #16        /* r10 = z2 = d2 */
+    mov    r11, r11, asr #16        /* r11 = z3 = d6 */
+    add    r9,  r10, r11
+    mov    r8,  r8,  asr #3         /* r8  = z4 = (d0 + 4112) << 13 */
+    mul    r9,  r14, r9             /* r9  = z1 = (z2 + z3) * 4433 */
+    ldr    r14, =6270
+    mla    r11, r12, r11, r9         /* r11 = tmp2 = z1 - z3 * 15137 */
+    mla    r10, r14, r10, r9         /* r10 = tmp3 = z1 + z2 * 6270 */
+    mov    r9,  r6,  lsl #16         /* r9  = z5 << 3 = d4 << 16 */
+    add    r12, r8,  r9,  asr #3     /* r12 = tmp0 = z4 + z5 */
+    sub    r14, r8,  r9,  asr #3     /* r14 = tmp1 = z4 - z5 */
+    add    r8,  r12, r10             /* r8  = tmp10 = tmp0 + tmp3 */
+    sub    r9,  r12, r10             /* r9  = tmp13 = tmp0 - tmp3 */
+    add    r10, r14, r11             /* r10 = tmp11 = tmp1 + tmp2 */
+    sub    r11, r14, r11             /* r11 = tmp12 = tmp1 - tmp2 */
+    stmdb  sp,  { r8-r11 }           /* tmp10 tmp13 tmp11 tmp12 */
+    mov    r4,  r4,  asr #16         /* r4  = tmp3 = d1 */
+    mov    r5,  r5,  asr #16         /* r5  = tmp2 = d3 */
+    mov    r6,  r6,  asr #16         /* r6  = tmp1 = d5 */
+    mov    r7,  r7,  asr #16         /* r7  = tmp0 = d7 */
+    ldr    r10, =9633
+    ldr    r11, =-16069
+    add    r12, r5,  r7              /* r12 = z3 = tmp0 + tmp2 */
+    add    r14, r4,  r6              /* r14 = z4 = tmp1 + tmp3 */
+    add    r9,  r12, r14             /* r9  = z3 + z4 */
+    mul    r9,  r10, r9              /* r9  = z5 = (z3 + z4) * 9633 */
+    ldr    r10, =-3196
+    mla    r12, r11, r12, r9         /* r12 = z3 = z5 - z3 * 16069 */
+    ldr    r11, =-7373
+    mla    r14, r10, r14, r9         /* r14 = z4 = z5 - z4 * 3196 */
+    ldr    r10, =2446
+    add    r9,  r4,  r7              /* r9  = tmp0 + tmp3 */
+    mla    r8,  r11, r9,  r12        /* r8  = z1 + z3 */
+    mla    r9,  r11, r9,  r14        /* r9  = z1 + z4 */
+    ldr    r11, =12299
+    mla    r7,  r10, r7,  r8         /* r7  = tmp0 = z1 + z3 + tmp0 * 2446 */
+    ldr    r10, =-20995
+    mla    r4,  r11, r4,  r9         /* r4  = tmp3 = z1 + z4 + tmp0 * 12299 */
+    ldr    r11, =25172
+    add    r9,  r5,  r6              /* r9  = tmp1 + tmp2 */
+    mla    r12, r10, r9, r12         /* r12 = z2 + z3 */
+    mla    r14, r10, r9, r14         /* r14 = z2 + z4 */
+    ldr    r10, =16819
+    mla    r5,  r11, r5, r12         /* r5  = tmp2 = z2 + z3 + tmp2 * 25172 */
+    mla    r6,  r10, r6, r14         /* r6  = tmp1 = z2 + z4 + tmp1 * 16819 */
+    ldmdb  sp,  { r8-r11 }
+    add    r12, r8,  r4              /* o0 */
+    sub    r14, r8,  r4              /* o7 */
+    add    r8,  r9,  r7              /* o3 */
+    sub    r9,  r9,  r7              /* o4 */
+    add    r4,  r10, r5              /* O1 */
+    sub    r5,  r10, r5              /* o6 */
+    add    r10, r11, r6              /* o2 */
+    sub    r11, r11, r6              /* o5 */
+    /* output in order: r12 r4  r10 r8  r9  r11 r5  r14 */
+#if ARM_ARCH < 6
+    mov    r12, r12, asr #18
+    cmp    r12, #255
+    mvnhi  r12, r12, asr #31
+    mov    r4,  r4,  asr #18
+    cmp    r4,  #255
+    mvnhi  r4,  r4,  asr #31
+    mov    r10, r10, asr #18
+    cmp    r10, #255
+    mvnhi  r10, r10, asr #31
+    mov    r8,  r8,  asr #18
+    cmp    r8,  #255
+    mvnhi  r8,  r8,  asr #31
+    mov    r9,  r9,  asr #18
+    cmp    r9,  #255
+    mvnhi  r9,  r9,  asr #31
+    mov    r11, r11, asr #18
+    cmp    r11, #255
+    mvnhi  r11, r11, asr #31
+    mov    r5,  r5,  asr #18
+    cmp    r5,  #255
+    mvnhi  r5,  r5,  asr #31
+    mov    r14, r14, asr #18
+    cmp    r14, #255
+    mvnhi  r14, r14, asr #31
+#else
+    usat   r12, #8,  r12, asr #18
+    usat   r4,  #8,  r4,  asr #18
+    usat   r10, #8,  r10, asr #18
+    usat   r8,  #8,  r8,  asr #18
+    usat   r9,  #8,  r9,  asr #18
+    usat   r11, #8,  r11, asr #18
+    usat   r5,  #8,  r5,  asr #18
+    usat   r14, #8,  r14, asr #18
+#endif
+#ifdef HAVE_LCD_COLOR
+    strb   r12, [r1]
+    strb   r4,  [r1, #4]
+    strb   r10, [r1, #8]
+    strb   r8,  [r1, #12]
+    strb   r9,  [r1, #16]
+    strb   r11, [r1, #20]
+    strb   r5,  [r1, #24]
+    strb   r14, [r1, #28]
+#else
+    strb   r12, [r1]
+    strb   r4,  [r1, #1]
+    strb   r10, [r1, #2]
+    strb   r8,  [r1, #3]
+    strb   r9,  [r1, #4]
+    strb   r11, [r1, #5]
+    strb   r5,  [r1, #6]
+    strb   r14, [r1, #7]
+#endif
+    add    r1,  r1,  r3
+    cmp    r0,  r2
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+    .size jpeg_idct8h_armv4_1_z, .-jpeg_idct8h_armv4_1_z
+
+jpeg_idct8h_armv4_1_n:
+    stmdb  sp!, { r4-r11, lr }
+1:
+    ldmia  r0!, { r4-r7 }
+    ldr    r14, =(4112<<16)
+    add    r8,  r14, r8,  lsl #16
+    ldr    r14, =4433
+    ldr    r12, =-15137
+    mov    r10, r5,  lsl #16
+    mov    r11, r7,  lsl #16
+    mov    r10, r10, asr #16        /* r10 = z2 = d2 */
+    mov    r11, r11, asr #16        /* r11 = z3 = d6 */
+    add    r9,  r10, r11
+    mov    r8,  r8,  asr #3         /* r8  = z4 = (d0 + 4112) << 13 */
+    mul    r9,  r14, r9             /* r9  = z1 = (z2 + z3) * 4433 */
+    ldr    r14, =6270
+    mla    r11, r12, r11, r9         /* r11 = tmp2 = z1 - z3 * 15137 */
+    mla    r10, r14, r10, r9         /* r10 = tmp3 = z1 + z2 * 6270 */
+    mov    r9,  r6,  lsl #16         /* r9  = z5 << 3 = d4 << 16 */
+    add    r12, r8,  r9,  asr #3     /* r12 = tmp0 = z4 + z5 */
+    sub    r14, r8,  r9,  asr #3     /* r14 = tmp1 = z4 - z5 */
+    add    r8,  r12, r10             /* r8  = tmp10 = tmp0 + tmp3 */
+    sub    r9,  r12, r10             /* r9  = tmp13 = tmp0 - tmp3 */
+    add    r10, r14, r11             /* r10 = tmp11 = tmp1 + tmp2 */
+    sub    r11, r14, r11             /* r11 = tmp12 = tmp1 - tmp2 */
+    stmdb  sp,  { r8-r11 }           /* tmp10 tmp13 tmp11 tmp12 */
+    mov    r4,  r4,  asr #16         /* r4  = tmp3 = d1 */
+    mov    r5,  r5,  asr #16         /* r5  = tmp2 = d3 */
+    mov    r6,  r6,  asr #16         /* r6  = tmp1 = d5 */
+    mov    r7,  r7,  asr #16         /* r7  = tmp0 = d7 */
+    ldr    r10, =9633
+    ldr    r11, =-16069
+    add    r12, r5,  r7              /* r12 = z3 = tmp0 + tmp2 */
+    add    r14, r4,  r6              /* r14 = z4 = tmp1 + tmp3 */
+    add    r9,  r12, r14             /* r9  = z3 + z4 */
+    mul    r9,  r10, r9              /* r9  = z5 = (z3 + z4) * 9633 */
+    ldr    r10, =-3196
+    mla    r12, r11, r12, r9         /* r12 = z3 = z5 - z3 * 16069 */
+    ldr    r11, =-7373
+    mla    r14, r10, r14, r9         /* r14 = z4 = z5 - z4 * 3196 */
+    ldr    r10, =2446
+    add    r9,  r4,  r7              /* r9  = tmp0 + tmp3 */
+    mla    r8,  r11, r9,  r12        /* r8  = z1 + z3 */
+    mla    r9,  r11, r9,  r14        /* r9  = z1 + z4 */
+    ldr    r11, =12299
+    mla    r7,  r10, r7,  r8         /* r7  = tmp0 = z1 + z3 + tmp0 * 2446 */
+    ldr    r10, =-20995
+    mla    r4,  r11, r4,  r9         /* r4  = tmp3 = z1 + z4 + tmp0 * 12299 */
+    ldr    r11, =25172
+    add    r9,  r5,  r6              /* r9  = tmp1 + tmp2 */
+    mla    r12, r10, r9, r12         /* r12 = z2 + z3 */
+    mla    r14, r10, r9, r14         /* r14 = z2 + z4 */
+    ldr    r10, =16819
+    mla    r5,  r11, r5, r12         /* r5  = tmp2 = z2 + z3 + tmp2 * 25172 */
+    mla    r6,  r10, r6, r14         /* r6  = tmp1 = z2 + z4 + tmp1 * 16819 */
+    ldmdb  sp,  { r8-r11 }
+    add    r12, r8,  r4              /* o0 */
+    sub    r14, r8,  r4              /* o7 */
+    add    r8,  r9,  r7              /* o3 */
+    sub    r9,  r9,  r7              /* o4 */
+    add    r4,  r10, r5              /* O1 */
+    sub    r5,  r10, r5              /* o6 */
+    add    r10, r11, r6              /* o2 */
+    sub    r11, r11, r6              /* o5 */
+    /* output in order: r12 r4  r10 r8  r9  r11 r5  r14 */
+#if ARM_ARCH < 6
+    mov    r12, r12, asr #18
+    cmp    r12, #255
+    mvnhi  r12, r12, asr #31
+    mov    r4,  r4,  asr #18
+    cmp    r4,  #255
+    mvnhi  r4,  r4,  asr #31
+    mov    r10, r10, asr #18
+    cmp    r10, #255
+    mvnhi  r10, r10, asr #31
+    mov    r8,  r8,  asr #18
+    cmp    r8,  #255
+    mvnhi  r8,  r8,  asr #31
+    mov    r9,  r9,  asr #18
+    cmp    r9,  #255
+    mvnhi  r9,  r9,  asr #31
+    mov    r11, r11, asr #18
+    cmp    r11, #255
+    mvnhi  r11, r11, asr #31
+    mov    r5,  r5,  asr #18
+    cmp    r5,  #255
+    mvnhi  r5,  r5,  asr #31
+    mov    r14, r14, asr #18
+    cmp    r14, #255
+    mvnhi  r14, r14, asr #31
+#else
+    usat   r12, #8,  r12, asr #18
+    usat   r4,  #8,  r4,  asr #18
+    usat   r10, #8,  r10, asr #18
+    usat   r8,  #8,  r8,  asr #18
+    usat   r9,  #8,  r9,  asr #18
+    usat   r11, #8,  r11, asr #18
+    usat   r5,  #8,  r5,  asr #18
+    usat   r14, #8,  r14, asr #18
+#endif
+#ifdef HAVE_LCD_COLOR
+    strb   r12, [r1]
+    strb   r4,  [r1, #4]
+    strb   r10, [r1, #8]
+    strb   r8,  [r1, #12]
+    strb   r9,  [r1, #16]
+    strb   r11, [r1, #20]
+    strb   r5,  [r1, #24]
+    strb   r14, [r1, #28]
+#else
+    strb   r12, [r1]
+    strb   r4,  [r1, #1]
+    strb   r10, [r1, #2]
+    strb   r8,  [r1, #3]
+    strb   r9,  [r1, #4]
+    strb   r11, [r1, #5]
+    strb   r5,  [r1, #6]
+    strb   r14, [r1, #7]
+#endif
+    add    r1,  r1,  r3
+    cmp    r0,  r2
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+    .size jpeg_idct8h_armv4_1_n, .-jpeg_idct8h_armv4_1_n
+
+jpeg_idct8v_armv5_1_z:
+    stmdb  sp!, { r4-r11, lr }
+    add    r2,  r0,  #128
+1:
+    ldmia  r0!, { r4-r7 }
+    mov    r12, r4,  lsl #16
+    orrs   r9,  r6,  r7
+    orreqs r9,  r5,  r4,  lsr #16
+    bne    2f
+    mov    r12, r12, asr #14
+    strh   r12, [r2]
+    strh   r12, [r2, #16]
+    strh   r12, [r2, #32]
+    strh   r12, [r2, #48]
+    strh   r12, [r2, #64]
+    strh   r12, [r2, #80]
+    strh   r12, [r2, #96]
+    strh   r12, [r2, #112]
+    add    r2,  r2,  #2
+    cmp    r0,  r1
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+2:
+    ldrd   r8,  .Lpool81
+    add    r12, r12, #8192
+    add    r10, r5,  r7              /* r10[15:0] = d2 + d6 */
+    sub    r14, r12, r6,  lsl #16    /* r14 = tmp1 << 3 = (d0 - d4) << 16 */
+    smulbb r10, r8,  r10             /* r10 = z1 = (d2 + d6) * 4433 */
+    add    r12, r12, r6,  lsl #16    /* r12 = tmp0 << 3= (d0 + d4) << 16 */
+    smlatb r11, r8,  r7,  r10        /* r11 = tmp2 = z1 - d6 * 15137 */
+    smlabb r10, r9,  r5,  r10        /* r10 = tmp3 = z1 + d2 * 6270 */
+    add    r8,  r11, r14, asr #3     /* r8  = tmp11 */
+    rsb    r11, r11, r14, asr #3     /* r11 = tmp12 */
+    add    r14, r10, r12, asr #3     /* r14 = tmp10 */
+    rsb    r12, r10, r12, asr #3     /* r12 = tmp13 */
+    stmdb  sp,  { r8, r11, r12, r14 }/* tmp11 tmp12 tmp13 tmp10 */
+    mov    r6,  r6,  asr #16         /* r6  = tmp1 = d5 */
+    mov    r7,  r7,  asr #16         /* r7  = tmp0 = d7 */
+    add    r12, r6,  r4,  asr #16    /* r12 = z4 = tmp1 + tmp3 */
+    add    r14, r7,  r5,  asr #16    /* r14 = z3 = tmp0 + tmp2 */
+    add    r8,  r12, r14             /* r8  = z3 + z4 */
+    ldrd   r10, .Lpool81+8
+    smultb r8,  r9,  r8              /* r8  = z5 = (z3 + z4) * 9633 */
+    add    r9,  r7,  r4,  asr #16    /* r9  = z1 = tmp0 + tmp3 */
+    smlabb r14, r10, r14, r8         /* r14 = z3 = z5 - z3 * 16069 */
+    smlatb r12, r10, r12, r8         /* r12 = z4 = z5 - z4 * 3196 */
+    smlabb r8,  r11, r9,  r14        /* r8  = z3 - z1 * 7373 */
+    smlabb r9,  r11, r9,  r12        /* r9  = z4 - z1 * 7373 */
+    add    r10, r6,  r5,  asr #16    /* r10 = z2 = tmp1 + tmp2 */
+    smlatb r12, r11, r10, r12        /* r12 = z4 - z2 * 20995 */
+    smlatb r14, r11, r10, r14        /* r14 = z3 - z2 * 20995 */
+    ldrd   r10, .Lpool81+16
+    smlabb r7,  r10, r7,  r8         /* r7 = tmp0 */
+    smlatt r4,  r10, r4,  r9         /* r4 = tmp3 */
+    smlabb r6,  r11, r6,  r12        /* r6 = tmp1 */
+    smlatt r5,  r11, r5,  r14        /* r5 = tmp2 */
+    ldmdb  sp,  { r8-r11 }           /* tmp11 tmp12 tmp13 tmp10 */
+    add    r12, r8,  r5              /* o1 */
+    sub    r14, r8,  r5              /* o6 */
+    add    r8,  r9,  r6              /* o2 */
+    sub    r9,  r9,  r6              /* o5 */
+    add    r6,  r10, r7              /* o3 */
+    sub    r7,  r10, r7              /* o4 */
+    add    r10, r11, r4              /* o0 */
+    sub    r11, r11, r4              /* o7 */
+    mov    r12, r12, asr #11
+    mov    r14, r14, asr #11
+    mov    r8,  r8,  asr #11
+    mov    r9,  r9,  asr #11
+    mov    r6,  r6,  asr #11
+    mov    r7,  r7,  asr #11
+    mov    r10, r10, asr #11
+    mov    r11, r11, asr #11
+    strh   r10, [r2]
+    strh   r12, [r2, #16]
+    strh   r8,  [r2, #32]
+    strh   r6,  [r2, #48]
+    strh   r7,  [r2, #64]
+    strh   r9,  [r2, #80]
+    strh   r14, [r2, #96]
+    strh   r11, [r2, #112]
+    cmp    r0,  r1
+    add    r2,  r2,  #2
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+    .size jpeg_idct8v_armv5_1_z, .-jpeg_idct8v_armv5_1_z
+
+    .align 4
+.Lpool81:
+    .short 4433
+    .short -15137
+    .short 6270
+    .short 9633
+    .short -16069
+    .short -3196
+    .short -7373
+    .short -20995
+    .short 2446
+    .short 12299
+    .short 16819
+    .short 25172
+
+    .align 2
+jpeg_idct8h_armv5_1_z:
+    stmdb  sp!, { r4-r11, lr }
+1:
+    ldr    r14, =(4112<<16)
+    ldmia  r0!, { r4-r7 }
+    add    r12, r14, r4,  lsl #16
+    orrs   r9,  r6,  r7
+    orreqs r9,  r5,  r4,  lsr #16
+    bne    2f
+    mov    r12, r12, asr #21
+    cmp    r12, #255
+    mvnhi  r12, r12, asr #31
+#ifdef HAVE_LCD_COLOR
+    strb   r12, [r1]
+    strb   r12, [r1, #4]
+    strb   r12, [r1, #8]
+    strb   r12, [r1, #12]
+    strb   r12, [r1, #16]
+    strb   r12, [r1, #20]
+    strb   r12, [r1, #24]
+    strb   r12, [r1, #28]
+#else
+    strb   r12, [r1]
+    strb   r12, [r1, #1]
+    strb   r12, [r1, #2]
+    strb   r12, [r1, #3]
+    strb   r12, [r1, #4]
+    strb   r12, [r1, #5]
+    strb   r12, [r1, #6]
+    strb   r12, [r1, #7]
+#endif
+    add    r1,  r1,  r3
+    cmp    r0,  r2
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+2:
+    ldrd   r8,  .Lpool81
+    add    r10, r5,  r7              /* r10[15:0] = d2 + d6 */
+    sub    r14, r12, r6,  lsl #16    /* r14 = tmp1 << 3 = (d0 - d4) << 16 */
+    smulbb r10, r8,  r10             /* r10 = z1 = (d2 + d6) * 4433 */
+    add    r12, r12, r6,  lsl #16    /* r12 = tmp0 << 3= (d0 + d4) << 16 */
+    smlatb r11, r8,  r7,  r10        /* r11 = tmp2 = z1 - d6 * 15137 */
+    smlabb r10, r9,  r5,  r10        /* r10 = tmp3 = z1 + d2 * 6270 */
+    add    r8,  r11, r14, asr #3     /* r8  = tmp11 */
+    rsb    r11, r11, r14, asr #3     /* r11 = tmp12 */
+    add    r14, r10, r12, asr #3     /* r14 = tmp10 */
+    rsb    r12, r10, r12, asr #3     /* r12 = tmp13 */
+    stmdb  sp,  { r8, r11, r12, r14 }/* tmp11 tmp12 tmp13 tmp10 */
+    mov    r6,  r6,  asr #16         /* r6  = tmp1 = d5 */
+    mov    r7,  r7,  asr #16         /* r7  = tmp0 = d7 */
+    add    r12, r6,  r4,  asr #16    /* r12 = z4 = tmp1 + tmp3 */
+    add    r14, r7,  r5,  asr #16    /* r14 = z3 = tmp0 + tmp2 */
+    add    r8,  r12, r14             /* r8  = z3 + z4 */
+    ldrd   r10, .Lpool81+8
+    smultb r8,  r9,  r8              /* r8  = z5 = (z3 + z4) * 9633 */
+    add    r9,  r7,  r4,  asr #16    /* r9  = z1 = tmp0 + tmp3 */
+    smlabb r14, r10, r14, r8         /* r14 = z3 = z5 - z3 * 16069 */
+    smlatb r12, r10, r12, r8         /* r12 = z4 = z5 - z4 * 3196 */
+    smlabb r8,  r11, r9,  r14        /* r8  = z3 - z1 * 7373 */
+    smlabb r9,  r11, r9,  r12        /* r9  = z4 - z1 * 7373 */
+    add    r10, r6,  r5,  asr #16    /* r10 = z2 = tmp1 + tmp2 */
+    smlatb r12, r11, r10, r12        /* r12 = z4 - z2 * 20995 */
+    smlatb r14, r11, r10, r14        /* r14 = z3 - z2 * 20995 */
+    ldrd   r10, .Lpool81+16
+    smlabb r7,  r10, r7,  r8         /* r7 = tmp0 */
+    smlatt r4,  r10, r4,  r9         /* r4 = tmp3 */
+    smlabb r6,  r11, r6,  r12        /* r6 = tmp1 */
+    smlatt r5,  r11, r5,  r14        /* r5 = tmp2 */
+    ldmdb  sp,  { r8-r11 }           /* tmp11 tmp12 tmp13 tmp10 */
+    add    r12, r8,  r5              /* o1 */
+    sub    r14, r8,  r5              /* o6 */
+    add    r8,  r9,  r6              /* o2 */
+    sub    r9,  r9,  r6              /* o5 */
+    add    r6,  r10, r7              /* o3 */
+    sub    r7,  r10, r7              /* o4 */
+    add    r10, r11, r4              /* o0 */
+    sub    r11, r11, r4              /* o7 */
+    /* output in order: r10 r12 r8  r6  r7  r9  r14 r11 */
+#if ARM_ARCH < 6
+    mov    r10, r10, asr #18
+    cmp    r10, #255
+    mvnhi  r10, r10, asr #31
+    mov    r12, r12, asr #18
+    cmp    r12, #255
+    mvnhi  r12, r12, asr #31
+    mov    r8,  r8,  asr #18
+    cmp    r8,  #255
+    mvnhi  r8,  r8,  asr #31
+    mov    r6,  r6,  asr #18
+    cmp    r6,  #255
+    mvnhi  r6,  r6,  asr #31
+    mov    r7,  r7,  asr #18
+    cmp    r7,  #255
+    mvnhi  r7,  r7,  asr #31
+    mov    r9,  r9,  asr #18
+    cmp    r9,  #255
+    mvnhi  r9,  r9,  asr #31
+    mov    r14, r14, asr #18
+    cmp    r14, #255
+    mvnhi  r14, r14, asr #31
+    mov    r11, r11, asr #18
+    cmp    r11, #255
+    mvnhi  r11, r11, asr #31
+#else
+    usat   r10, #8,  r10, asr #18
+    usat   r12, #8,  r12, asr #18
+    usat   r8,  #8,  r8,  asr #18
+    usat   r6,  #8,  r6,  asr #18
+    usat   r7,  #8,  r7,  asr #18
+    usat   r9,  #8,  r9,  asr #18
+    usat   r14, #8,  r14, asr #18
+    usat   r11, #8,  r11, asr #18
+#endif
+#ifdef HAVE_LCD_COLOR
+    strb   r10, [r1]
+    strb   r12, [r1, #4]
+    strb   r8,  [r1, #8]
+    strb   r6,  [r1, #12]
+    strb   r7,  [r1, #16]
+    strb   r9,  [r1, #20]
+    strb   r14, [r1, #24]
+    strb   r11, [r1, #28]
+#else
+    strb   r10, [r1]
+    strb   r12, [r1, #1]
+    strb   r8,  [r1, #2]
+    strb   r6,  [r1, #3]
+    strb   r7,  [r1, #4]
+    strb   r9,  [r1, #5]
+    strb   r14, [r1, #6]
+    strb   r11, [r1, #7]
+#endif
+    cmp    r0,  r2
+    add    r1,  r1,  r3
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+    .size jpeg_idct8h_armv5_1_z, .-jpeg_idct8h_armv5_1_z
+
+jpeg_idct8v_armv6_1_z:
+    stmdb  sp!, { r4-r11, lr }
+    add    r2,  r0,  #128
+1:
+    ldmia  r0!, { r4-r7 }
+    orrs   r9,  r6,  r7
+    orreqs r9,  r5,  r4,  lsr #16
+    bne    2f
+    mov    r4,  r4,  lsl #2
+    strh   r4,  [r2]
+    strh   r4,  [r2, #16]
+    strh   r4,  [r2, #32]
+    strh   r4,  [r2, #48]
+    strh   r4,  [r2, #64]
+    strh   r4,  [r2, #80]
+    strh   r4,  [r2, #96]
+    strh   r4,  [r2, #112]
+    cmp    r0,  r1
+    add    r2,  r2,  #2
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+2:
+    ldrd   r8,  .Lpool82
+    mov    r12, r4,  lsl #16
+    add    r10, r5,  r7              /* r10 = (z1[e]*, z3[o]) = (d2 + d6, d3 + d7) */
+    add    r12, r12, #8192
+    add    r3,  r12, r6, lsl #16     /* tmp0 */
+    sub    r12, r12, r6, lsl #16     /* tmp1 */
+    pkhtb  r4,  r5,  r4,  asr #16    /* r4  = (tmp3[o], tmp2[0]) = (d1, d3) */
+    smulbb r14, r8,  r10             /* r14 = z1[e] = (d2 + d6) * 4433 */
+    pkhtb  r6,  r6,  r7,  asr #16    /* r6  = (tmp0[o], tmp1[o]) = (d7, d5) */
+    smlatb r7,  r8,  r7,  r14        /* r7  = tmp2[e] = z1 - d6 * 15137 */
+    smlabb r5,  r9,  r5,  r14        /* r5  = tmp3[e] = z1 + d2 * 6270 */
+    pkhtb  r9,  r9,  r9,  asr #16    /* r9  = (9633, 9633) */
+    add    r10, r5,  r3,  asr #3     /* r10 = tmp10 */
+    rsb    r11, r5,  r3,  asr #3     /* r11 = tmp13 */
+    mov    r3,  r4,  ror #16
+    rsb    r14, r7,  r12, asr #3     /* r14 = tmp12 */
+    add    r12, r7,  r12, asr #3     /* r12 = tmp11 */
+    sadd16 r8,  r3,  r6              /* z3, z4 */
+    stmdb  sp,   { r10-r12, r14 }    /* tmp10 tmp13 tmp11 tmp12 */
+    smuad  r5,  r9,  r8              /* r5  = z5 = (z3[o] + z4[o]) * 9633 */
+    ldrd   r10, .Lpool82+8
+    sadd16 r7,  r4,  r6              /* r7  = (z1, z2) */
+    smlatt r9,  r10, r8,  r5         /* r9  = z4 = z5 - z4 * 16069 */
+    smlabb r8,  r10, r8,  r5         /* r8  = z3 = z5 - z3 * 3196 */
+    smlabb r14, r11, r7,  r9         /* r14 = z1 + z4 */
+    smlabb r12, r11, r7,  r8         /* r12 = z1 + z3 */
+    smlatt r5,  r11, r7,  r9         /* r5  = z2 + z4 */
+    smlatt r7,  r11, r7,  r8         /* r7  = z2 + z3 */
+    ldrd   r8,  .Lpool82+16
+    smlabt r7,  r9,  r4,  r7         /* r7  = tmp2 */
+    smlatb r14, r9,  r4,  r14        /* r14 = tmp3 */
+    ldmdb  sp,  { r4, r9-r11 }       /* tmp10 tmp13 tmp11 tmp12 */
+    smlabb r12, r8,  r6,  r12        /* r12 = tmp0 */
+    smlatt r5,  r8,  r6,  r5         /* r5  = tmp1 */
+    /* used: r4, r5, r7, r9-r12, r14 */
+    add    r6,  r4,  r14             /* o0 */
+    sub    r8,  r4,  r14             /* o7 */
+    add    r14, r9,  r12             /* o3 */
+    sub    r12, r9,  r12             /* o4 */
+    add    r4,  r10, r7              /* o1 */
+    sub    r7,  r10, r7              /* o6 */
+    add    r9,  r11, r5              /* o2 */
+    sub    r10, r11, r5              /* o5 */
+    mov    r6,  r6,  asr #11
+    mov    r4,  r4,  asr #11
+    mov    r9,  r9,  asr #11
+    mov    r14, r14, asr #11
+    mov    r12, r12, asr #11
+    mov    r10, r10, asr #11
+    mov    r7,  r7,  asr #11
+    mov    r8,  r8,  asr #11
+    strh   r6,  [r2]
+    strh   r4,  [r2, #16]
+    strh   r9,  [r2, #32]
+    strh   r14, [r2, #48]
+    strh   r12, [r2, #64]
+    strh   r10, [r2, #80]
+    strh   r7,  [r2, #96]
+    strh   r8,  [r2, #112]
+    cmp    r0,  r1
+    add    r2,  r2,  #2
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+    .size jpeg_idct8v_armv6_1_z, .-jpeg_idct8v_armv6_1_z
+
+    .align 4
+.Lpool82:
+    .short 4433
+    .short -15137
+    .short 6270
+    .short 9633
+    .short -16069
+    .short -3196
+    .short -7373
+    .short -20995
+    .short 2446
+    .short 16819
+    .short 25172
+    .short 12299
+
+    .align 2
+jpeg_idct8h_armv6_1_z:
+    stmdb  sp!, { r4-r11, lr }
+1:
+    ldr    r14, =4112
+    ldmia  r0!, { r4-r7 }
+    sadd16 r4,  r4,  r14
+    orrs   r9,  r6,  r7
+    orreqs r9,  r5,  r4,  lsr #16
+    bne    2f
+    usat16 r4,  #13, r4
+    mov    r4,  r4,  asl #5
+#ifdef HAVE_LCD_COLOR
+    strb   r4,  [r1]
+    strb   r4,  [r1, #4]
+    strb   r4,  [r1, #8]
+    strb   r4,  [r1, #12]
+    strb   r4,  [r1, #16]
+    strb   r4,  [r1, #20]
+    strb   r4,  [r1, #24]
+    strb   r4,  [r1, #28]
+#else
+    strb   r4,  [r1]
+    strb   r4,  [r1, #1]
+    strb   r4,  [r1, #2]
+    strb   r4,  [r1, #3]
+    strb   r4,  [r1, #4]
+    strb   r4,  [r1, #5]
+    strb   r4,  [r1, #6]
+    strb   r4,  [r1, #7]
+#endif
+    add    r1,  r1,  r3
+    cmp    r0,  r2
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+2:
+    ldrd   r8,  .Lpool82
+    sadd16 r10, r5,  r7              /* r10 = (z1[e]*, z3[o]) = (d2 + d6, d3 + d7) */
+    ssub16 r12, r4,  r6              /* r12 = (tmp1[e], junk) = (d0 - d4, d1 - d5) */
+    sadd16 r11, r4,  r6              /* r11 = (tmp0[e], z4[o]) = (d0 + d4, d1 + d5) */
+    pkhtb  r4,  r5,  r4,  asr #16    /* r4  = (tmp3[o], tmp2[0]) = (d1, d3) */
+    smulbb r14, r8,  r10             /* r14 = z1[e] = (d2 + d6) * 4433 */
+    pkhtb  r6,  r6,  r7,  asr #16    /* r6  = (tmp0[o], tmp1[o]) = (d7, d5) */
+    smlatb r7,  r8,  r7,  r14        /* r7  = tmp2[e] = z1 - d6 * 15137 */
+    smlabb r5,  r9,  r5,  r14        /* r5  = tmp3[e] = z1 + d2 * 6270 */
+    sxth   r12, r12                  /* r12 = tmp1[e] = d0 - d4 */
+    pkhtb  r8,  r11, r10, asr #16    /* r8  = (z3[o], z4[o]) */
+    sxth   r14, r11                  /* r14 = tmp0[e] */
+    pkhtb  r9,  r9,  r9,  asr #16    /* r9  = (9633, 9633) */
+    add    r10, r5,  r14, lsl #13    /* r10 = tmp10 */
+    rsb    r11, r5,  r14, lsl #13    /* r11 = tmp13 */
+    rsb    r14, r7,  r12, lsl #13    /* r14 = tmp12 */
+    add    r12, r7,  r12, lsl #13    /* r12 = tmp11 */
+    stmdb  sp,   { r10-r12, r14 }    /* tmp10 tmp13 tmp11 tmp12 */
+    smuad  r5,  r9,  r8              /* r5  = z5 = (z3[o] + z4[o]) * 9633 */
+    ldrd   r10, .Lpool82+8
+    sadd16 r7,  r4,  r6              /* r7  = (z1, z2) */
+    smlatt r9,  r10, r8,  r5         /* r9  = z4 = z5 - z4 * 16069 */
+    smlabb r8,  r10, r8,  r5         /* r8  = z3 = z5 - z3 * 3196 */
+    smlabb r14, r11, r7,  r9         /* r14 = z1 + z4 */
+    smlabb r12, r11, r7,  r8         /* r12 = z1 + z3 */
+    smlatt r5,  r11, r7,  r9         /* r5  = z2 + z4 */
+    smlatt r7,  r11, r7,  r8         /* r7  = z2 + z3 */
+    ldrd   r8,  .Lpool82+16
+    smlabt r7,  r9,  r4,  r7         /* r7  = tmp2 */
+    smlatb r14, r9,  r4,  r14        /* r14 = tmp3 */
+    ldmdb  sp,  { r4, r9-r11 }       /* tmp10 tmp13 tmp11 tmp12 */
+    smlabb r12, r8,  r6,  r12        /* r12 = tmp0 */
+    smlatt r5,  r8,  r6,  r5         /* r5  = tmp1 */
+    /* used: r4, r5, r7, r9-r12, r14 */
+    add    r6,  r4,  r14             /* o0 */
+    sub    r8,  r4,  r14             /* o7 */
+    add    r14, r9,  r12             /* o3 */
+    sub    r12, r9,  r12             /* o4 */
+    add    r4,  r10, r7              /* o1 */
+    sub    r7,  r10, r7              /* o6 */
+    add    r9,  r11, r5              /* o2 */
+    sub    r10, r11, r5              /* o5 */
+    usat   r6,  #8,  r6,  asr #18
+    usat   r4,  #8,  r4,  asr #18
+    usat   r9,  #8,  r9,  asr #18
+    usat   r14, #8,  r14, asr #18
+    usat   r12, #8,  r12, asr #18
+    usat   r10, #8,  r10, asr #18
+    usat   r7,  #8,  r7,  asr #18
+    usat   r8,  #8,  r8,  asr #18
+#ifdef HAVE_LCD_COLOR
+    strb   r6,  [r1]
+    strb   r4,  [r1, #4]
+    strb   r9,  [r1, #8]
+    strb   r14, [r1, #12]
+    strb   r12, [r1, #16]
+    strb   r10, [r1, #20]
+    strb   r7,  [r1, #24]
+    strb   r8,  [r1, #28]
+#else
+    strb   r6,  [r1]
+    strb   r4,  [r1, #1]
+    strb   r9,  [r1, #2]
+    strb   r14, [r1, #3]
+    strb   r12, [r1, #4]
+    strb   r10, [r1, #5]
+    strb   r7,  [r1, #6]
+    strb   r8,  [r1, #7]
+#endif
+    cmp    r0,  r2
+    add    r1,  r1,  r3
+    bcc    1b
+    ldmia  sp!, { r4-r11, pc }
+    .size jpeg_idct8h_armv6_1_z, .-jpeg_idct8h_armv6_1_z
diff --git a/apps/plugins/idct_test/idct_test.c b/apps/plugins/idct_test/idct_test.c
new file mode 100644
index 0000000..b740b50
--- /dev/null
+++ b/apps/plugins/idct_test/idct_test.c
@@ -0,0 +1,545 @@
+/***************************************************************************
+*             __________               __   ___.
+*   Open      \______   \ ____   ____ |  | _\_ |__   _______  ___
+*   Source     |       _//  _ \_/ ___\|  |/ /| __ \ /  _ \  \/  /
+*   Jukebox    |    |   (  <_> )  \___|    < | \_\ (  <_> > <  <
+*   Firmware   |____|_  /\____/ \___  >__|_ \|___  /\____/__/\_ \
+*                     \/            \/     \/    \/            \/
+* $Id$
+*
+* This program is free software; you can redistribute it and/or
+* modify it under the terms of the GNU General Public License
+* as published by the Free Software Foundation; either version 2
+* of the License, or (at your option) any later version.
+*
+* This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
+* KIND, either express or implied.
+*
+****************************************************************************/
+
+#include "plugin.h"
+PLUGIN_HEADER
+static int log_fd;
+
+#define CONST_BITS 13
+#define PASS1_BITS 2
+#define FIX_0_298631336  2446 /* FIX(0.298631336) */
+#define FIX_0_390180644  3196 /* FIX(0.390180644) */
+#define FIX_0_541196100  4433 /* FIX(0.541196100) */
+#define FIX_0_765366865  6270 /* FIX(0.765366865) */
+#define FIX_0_899976223  7373 /* FIX(0.899976223) */
+#define FIX_1_175875602  9633 /* FIX(1.175875602) */
+#define FIX_1_501321110 12299 /* FIX(1.501321110) */
+#define FIX_1_847759065 15137 /* FIX(1.847759065) */
+#define FIX_1_961570560 16069 /* FIX(1.961570560) */
+#define FIX_2_053119869 16819 /* FIX(2.053119869) */
+#define FIX_2_562915447 20995 /* FIX(2.562915447) */
+#define FIX_3_072711026 25172 /* FIX(3.072711026) */
+#define MULTIPLY(var1, var2) ((var1) * (var2))
+
+#if defined(CPU_SH) || defined(CPU_COLDFIRE) || \
+    (defined(CPU_ARM) && ARM_ARCH > 4)
+#define MULTIPLY16(var,const)  (((short) (var)) * ((short) (const)))
+#else
+#define MULTIPLY16 MULTIPLY
+#endif
+#define ONE ((long)1)
+#define CONST_SCALE (ONE << CONST_BITS)
+#define FIX(x) ((long) ((x) * CONST_SCALE + 0.5))
+#define RIGHT_SHIFT(x,shft)     ((x) >> (shft))
+#define DESCALE(x,n) (((x) + (1l << ((n)-1))) >> (n))
+#define DS_OUT ((CONST_BITS)+(PASS1_BITS)+3)
+
+unsigned range_limit(int value)
+{
+    /* Note: Uses knowledge that only the low byte of the result is used */
+    asm (
+        "cmp     %[v], #255          \n"  /* out of range 0..255? */
+        "mvnhi   %[v], %[v], asr #31 \n"  /* yes: set all bits to ~(sign_bit) */
+        : /* outputs */
+        [v]"+r"(value)
+    );
+    return value;
+}
+
+#define JPEG_PIX_SZ 1
+/* vertical-pass 8-point IDCT */
+static void jpeg_idct8v_c_n(int16_t *ws, int16_t *end)
+{
+    long tmp0, tmp1, tmp2, tmp3;
+    long tmp10, tmp11, tmp12, tmp13;
+    long z1, z2, z3, z4, z5;
+    for (; ws < end; ws++)
+    {
+    /* Due to quantization, we will usually find that many of the input
+    * coefficients are zero, especially the AC terms.  We can exploit this
+    * by short-circuiting the IDCT calculation for any column in which all
+    * the AC terms are zero.  In that case each output is equal to the
+    * DC coefficient (with scale factor as needed).
+    * With typical images and quantization tables, half or more of the
+    * column DCT calculations can be simplified this way.
+    */
+        if ((ws[8*1] | ws[8*2] | ws[8*3]
+           | ws[8*4] | ws[8*5] | ws[8*6] | ws[8*7]) == 0)
+        {
+            /* AC terms all zero */
+            int dcval = ws[8*0] << PASS1_BITS;
+
+            ws[8*0] = dcval;
+            ws[8*1] = dcval;
+            ws[8*2] = dcval;
+            ws[8*3] = dcval;
+            ws[8*4] = dcval;
+            ws[8*5] = dcval;
+            ws[8*6] = dcval;
+            ws[8*7] = dcval;
+            continue;
+        }
+
+        /* Even part: reverse the even part of the forward DCT. */
+        /* The rotator is sqrt(2)*c(-6). */
+
+        z2 = ws[8*2];
+        z3 = ws[8*6];
+
+        z1 = MULTIPLY16(z2 + z3, FIX_0_541196100);
+        tmp2 = z1 + MULTIPLY16(z3, - FIX_1_847759065);
+        tmp3 = z1 + MULTIPLY16(z2, FIX_0_765366865);
+
+        z2 = ws[8*0] << CONST_BITS;
+        z2 += ONE << (CONST_BITS - PASS1_BITS - 1);
+        z3 = ws[8*4] << CONST_BITS;
+
+        tmp0 = (z2 + z3);
+        tmp1 = (z2 - z3);
+
+        tmp10 = tmp0 + tmp3;
+        tmp13 = tmp0 - tmp3;
+        tmp11 = tmp1 + tmp2;
+        tmp12 = tmp1 - tmp2;
+
+        /* Odd part per figure 8; the matrix is unitary and hence its
+           transpose is its inverse.  i0..i3 are y7,y5,y3,y1 respectively. */
+
+        tmp0 = ws[8*7];
+        tmp1 = ws[8*5];
+        tmp2 = ws[8*3];
+        tmp3 = ws[8*1];
+
+        z1 = tmp0 + tmp3;
+        z2 = tmp1 + tmp2;
+        z3 = tmp0 + tmp2;
+        z4 = tmp1 + tmp3;
+        z5 = MULTIPLY16(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */
+
+        tmp0 = MULTIPLY16(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */
+        tmp1 = MULTIPLY16(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */
+        tmp2 = MULTIPLY16(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */
+        tmp3 = MULTIPLY16(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */
+        z1 = MULTIPLY16(z1, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */
+        z2 = MULTIPLY16(z2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */
+        z3 = MULTIPLY16(z3, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */
+        z4 = MULTIPLY16(z4, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */
+
+        z3 += z5;
+        z4 += z5;
+
+        tmp0 += z1 + z3;
+        tmp1 += z2 + z4;
+        tmp2 += z2 + z3;
+        tmp3 += z1 + z4;
+
+        /* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */
+
+        ws[8*0] = (int) RIGHT_SHIFT(tmp10 + tmp3, CONST_BITS-PASS1_BITS);
+        ws[8*7] = (int) RIGHT_SHIFT(tmp10 - tmp3, CONST_BITS-PASS1_BITS);
+        ws[8*1] = (int) RIGHT_SHIFT(tmp11 + tmp2, CONST_BITS-PASS1_BITS);
+        ws[8*6] = (int) RIGHT_SHIFT(tmp11 - tmp2, CONST_BITS-PASS1_BITS);
+        ws[8*2] = (int) RIGHT_SHIFT(tmp12 + tmp1, CONST_BITS-PASS1_BITS);
+        ws[8*5] = (int) RIGHT_SHIFT(tmp12 - tmp1, CONST_BITS-PASS1_BITS);
+        ws[8*3] = (int) RIGHT_SHIFT(tmp13 + tmp0, CONST_BITS-PASS1_BITS);
+        ws[8*4] = (int) RIGHT_SHIFT(tmp13 - tmp0, CONST_BITS-PASS1_BITS);
+    }
+}
+
+/* vertical-pass 8-point IDCT */
+static void jpeg_idct8v_c_t(int16_t *ws, int16_t *end)
+{
+    long tmp0, tmp1, tmp2, tmp3;
+    long tmp10, tmp11, tmp12, tmp13;
+    long z1, z2, z3, z4, z5;
+    int16_t *ws2 = ws + 64;
+    for (; ws < end; ws += 8, ws2++)
+    {
+    /* Due to quantization, we will usually find that many of the input
+    * coefficients are zero, especially the AC terms.  We can exploit this
+    * by short-circuiting the IDCT calculation for any column in which all
+    * the AC terms are zero.  In that case each output is equal to the
+    * DC coefficient (with scale factor as needed).
+    * With typical images and quantization tables, half or more of the
+    * column DCT calculations can be simplified this way.
+    */
+        if ((ws[1*1] | ws[1*2] | ws[1*3]
+           | ws[1*4] | ws[1*5] | ws[1*6] | ws[1*7]) == 0)
+        {
+            /* AC terms all zero */
+            int dcval = ws[1*0] << PASS1_BITS;
+
+            ws2[8*0] = ws2[8*1] = ws2[8*2] = ws2[8*3] = ws2[8*4] = ws2[8*5] =
+                       ws2[8*6] = ws2[8*7] = dcval;
+            continue;
+        }
+
+        /* Even part: reverse the even part of the forward DCT. */
+        /* The rotator is sqrt(2)*c(-6). */
+
+        z2 = ws[1*2];
+        z3 = ws[1*6];
+
+        z1 = MULTIPLY16(z2 + z3, FIX_0_541196100);
+        tmp2 = z1 + MULTIPLY16(z3, - FIX_1_847759065);
+        tmp3 = z1 + MULTIPLY16(z2, FIX_0_765366865);
+
+        z2 = ws[1*0] << CONST_BITS;
+        z2 += ONE << (CONST_BITS - PASS1_BITS - 1);
+        z3 = ws[1*4] << CONST_BITS;
+
+        tmp0 = (z2 + z3);
+        tmp1 = (z2 - z3);
+
+        tmp10 = tmp0 + tmp3;
+        tmp13 = tmp0 - tmp3;
+        tmp11 = tmp1 + tmp2;
+        tmp12 = tmp1 - tmp2;
+
+        /* Odd part per figure 8; the matrix is unitary and hence its
+           transpose is its inverse.  i0..i3 are y7,y5,y3,y1 respectively. */
+
+        tmp0 = ws[1*7];
+        tmp1 = ws[1*5];
+        tmp2 = ws[1*3];
+        tmp3 = ws[1*1];
+
+        z1 = tmp0 + tmp3;
+        z2 = tmp1 + tmp2;
+        z3 = tmp0 + tmp2;
+        z4 = tmp1 + tmp3;
+        z5 = MULTIPLY16(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */
+
+        tmp0 = MULTIPLY16(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */
+        tmp1 = MULTIPLY16(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */
+        tmp2 = MULTIPLY16(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */
+        tmp3 = MULTIPLY16(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */
+        z1 = MULTIPLY16(z1, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */
+        z2 = MULTIPLY16(z2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */
+        z3 = MULTIPLY16(z3, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */
+        z4 = MULTIPLY16(z4, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */
+
+        z3 += z5;
+        z4 += z5;
+
+        tmp0 += z1 + z3;
+        tmp1 += z2 + z4;
+        tmp2 += z2 + z3;
+        tmp3 += z1 + z4;
+
+        /* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */
+
+        ws2[8*0] = (int) RIGHT_SHIFT(tmp10 + tmp3, CONST_BITS-PASS1_BITS);
+        ws2[8*7] = (int) RIGHT_SHIFT(tmp10 - tmp3, CONST_BITS-PASS1_BITS);
+        ws2[8*1] = (int) RIGHT_SHIFT(tmp11 + tmp2, CONST_BITS-PASS1_BITS);
+        ws2[8*6] = (int) RIGHT_SHIFT(tmp11 - tmp2, CONST_BITS-PASS1_BITS);
+        ws2[8*2] = (int) RIGHT_SHIFT(tmp12 + tmp1, CONST_BITS-PASS1_BITS);
+        ws2[8*5] = (int) RIGHT_SHIFT(tmp12 - tmp1, CONST_BITS-PASS1_BITS);
+        ws2[8*3] = (int) RIGHT_SHIFT(tmp13 + tmp0, CONST_BITS-PASS1_BITS);
+        ws2[8*4] = (int) RIGHT_SHIFT(tmp13 - tmp0, CONST_BITS-PASS1_BITS);
+    }
+}
+
+/* horizontal-pass 8-point IDCT */
+static void jpeg_idct8h_c_z(int16_t *ws, unsigned char *out, int16_t *end, int rowstep)
+{
+    long tmp0, tmp1, tmp2, tmp3;
+    long tmp10, tmp11, tmp12, tmp13;
+    long z1, z2, z3, z4, z5;
+    for (; ws < end; out += rowstep, ws += 8)
+    {
+        /* Rows of zeroes can be exploited in the same way as we did with
+         * columns. However, the column calculation has created many nonzero AC
+         * terms, so the simplification applies less often (typically 5% to 10%
+         * of the time). On machines with very fast multiplication, it's
+         * possible that the test takes more time than it's worth.  In that
+         * case this section may be commented out.
+        */
+
+#ifndef NO_ZERO_ROW_TEST
+        if ((ws[1] | ws[2] | ws[3]
+           | ws[4] | ws[5] | ws[6] | ws[7]) == 0)
+        {
+            /* AC terms all zero */
+            unsigned char dcval = range_limit(128 + (int) DESCALE((long) ws[0],
+                PASS1_BITS+3));
+
+            out[JPEG_PIX_SZ*0] = dcval;
+            out[JPEG_PIX_SZ*1] = dcval;
+            out[JPEG_PIX_SZ*2] = dcval;
+            out[JPEG_PIX_SZ*3] = dcval;
+            out[JPEG_PIX_SZ*4] = dcval;
+            out[JPEG_PIX_SZ*5] = dcval;
+            out[JPEG_PIX_SZ*6] = dcval;
+            out[JPEG_PIX_SZ*7] = dcval;
+            continue;
+        }
+#endif
+
+        /* Even part: reverse the even part of the forward DCT. */
+        /* The rotator is sqrt(2)*c(-6). */
+
+        z2 = (long) ws[2];
+        z3 = (long) ws[6];
+
+        z1 = MULTIPLY16(z2 + z3, FIX_0_541196100);
+        tmp2 = z1 + MULTIPLY16(z3, - FIX_1_847759065);
+        tmp3 = z1 + MULTIPLY16(z2, FIX_0_765366865);
+
+        z4 = (long) ws[0] + (ONE << (PASS1_BITS + 2))
+             + (128 << (PASS1_BITS + 3));
+        z4 <<= CONST_BITS;
+        z5 = (long) ws[4] << CONST_BITS;
+        tmp0 = z4 + z5;
+        tmp1 = z4 - z5;
+
+        tmp10 = tmp0 + tmp3;
+        tmp13 = tmp0 - tmp3;
+        tmp11 = tmp1 + tmp2;
+        tmp12 = tmp1 - tmp2;
+
+        /* Odd part per figure 8; the matrix is unitary and hence its
+        * transpose is its inverse. i0..i3 are y7,y5,y3,y1 respectively. */
+
+        tmp0 = (long) ws[7];
+        tmp1 = (long) ws[5];
+        tmp2 = (long) ws[3];
+        tmp3 = (long) ws[1];
+
+        z1 = tmp0 + tmp3;
+        z2 = tmp1 + tmp2;
+        z3 = tmp0 + tmp2;
+        z4 = tmp1 + tmp3;
+        z5 = MULTIPLY16(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */
+
+
+        tmp0 = MULTIPLY16(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */
+        tmp1 = MULTIPLY16(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */
+        tmp2 = MULTIPLY16(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */
+        tmp3 = MULTIPLY16(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */
+        z1 = MULTIPLY16(z1, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */
+        z2 = MULTIPLY16(z2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */
+        z3 = MULTIPLY16(z3, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */
+        z4 = MULTIPLY16(z4, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */
+
+        z3 += z5;
+        z4 += z5;
+
+        tmp0 += z1 + z3;
+        tmp1 += z2 + z4;
+        tmp2 += z2 + z3;
+        tmp3 += z1 + z4;
+
+        /* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */
+        out[JPEG_PIX_SZ*0] = range_limit((int) RIGHT_SHIFT(tmp10 + tmp3,
+            DS_OUT));
+        out[JPEG_PIX_SZ*7] = range_limit((int) RIGHT_SHIFT(tmp10 - tmp3,
+            DS_OUT));
+        out[JPEG_PIX_SZ*1] = range_limit((int) RIGHT_SHIFT(tmp11 + tmp2,
+            DS_OUT));
+        out[JPEG_PIX_SZ*6] = range_limit((int) RIGHT_SHIFT(tmp11 - tmp2,
+            DS_OUT));
+        out[JPEG_PIX_SZ*2] = range_limit((int) RIGHT_SHIFT(tmp12 + tmp1,
+            DS_OUT));
+        out[JPEG_PIX_SZ*5] = range_limit((int) RIGHT_SHIFT(tmp12 - tmp1,
+            DS_OUT));
+        out[JPEG_PIX_SZ*3] = range_limit((int) RIGHT_SHIFT(tmp13 + tmp0,
+            DS_OUT));
+        out[JPEG_PIX_SZ*4] = range_limit((int) RIGHT_SHIFT(tmp13 - tmp0,
+            DS_OUT));
+    }
+}
+
+#define DO_BENCH_CUSTOM(printf_func, min_time, min_iters, func, ...) \
+{ \
+    long t1, t2, t_end; \
+    long count = 0; \
+    uint64_t count_long; \
+    t2 = *(rb->current_tick); \
+    while (t2 != (t1 = *(rb->current_tick))); \
+    t_end = t1 + min_time; \
+    do { \
+        func(__VA_ARGS__); \
+        count++; \
+        t2 = *(rb->current_tick); \
+    } while (TIME_BEFORE(t2, t_end) || count < min_iters); \
+    t2 -= t1; \
+    count_long = (uint64_t)count * HZ; \
+    count_long += t2 >> 1; \
+    count_long /= t2; \
+    printf_func(#func ": %01d/sec", (int)count_long); \
+    rb->yield(); \
+}
+
+#define LOG_PRINTF(format, ...) rb->fdprintf(log_fd, format "\n" , ## __VA_ARGS__)
+
+static unsigned short testdata[128] = {
+#if 0
+    -384,    0,  -40,   32,   48,    0,    0,    0,
+       0,    0,  -28,    0,    0,    0,    0,    0,
+     -28,    0,   64,    0,    0,    0,    0,    0,
+     -28,    0,   44,    0,    0,    0,    0,    0,
+       0,    0,    0,    0,    0,    0,    0,    0,
+       0,    0,    0,    0,    0,    0,    0,    0,
+       0,    0,    0,    0,    0,    0,    0,    0,
+       0,    0,    0,    0,    0,    0,    0,    0,
+#else
+-415, -30, -61, 27, 56, -20, -2, 0,
+4, -22, -61, 10, 13, -7, -9, 5,
+-47, 7, 77, -25, -29, 10, 5, -6,
+-49, 12, 34, -15, -10, 6, 2, 2,
+12, -7, -13, -4, -2, 2, -3, 3,
+-8, 3, 2, -6, -2, 1, 4, 2,
+-1, 0, 0, -2, -1, -3, 4, -1,
+0, 0, -1, -4, -1, 0, 1, 2,
+#endif
+};
+
+static unsigned short testbuf[512];
+
+static void print_array_b(int w, int h, int s, unsigned char *d)
+{
+    int x,y;
+    for (y = 0; y < h; y++, d += s)
+    {
+        for (x = 0; x < w; x++)
+            rb->fdprintf(log_fd,"%4d,", (int)d[x]);
+        rb->fdprintf(log_fd,"\n");
+    }
+    rb->fdprintf(log_fd,"\n");
+}
+
+static void print_array_h(int w, int h, int s, short *d)
+{
+    int x,y;
+    for (y = 0; y < h; y++, d += s)
+    {
+        for (x = 0; x < w; x++)
+            rb->fdprintf(log_fd,"%6d,", (int)d[x]);
+        rb->fdprintf(log_fd,"\n");
+    }
+    rb->fdprintf(log_fd,"\n");
+}
+
+static void print_array_w(int w, int h, int s, int *d)
+{
+    int x,y;
+    for (y = 0; y < h; y++, d += s)
+    {
+        for (x = 0; x < w; x++)
+            rb->fdprintf(log_fd,"%6d,", (int)d[x]);
+        rb->fdprintf(log_fd,"\n");
+    }
+    rb->fdprintf(log_fd,"\n");
+}
+
+static void prep_transpose(void)
+{
+    int i;
+    for (i = 0; i < 64; i++)
+        testdata[i+64] = testdata[63&((i<<3)|(i>>3))];
+}
+
+static inline __attribute__((always_inline)) void prep_test(bool transpose)
+{
+    rb->memcpy(testbuf, testdata + (transpose ? 64 : 0), 128);
+}
+
+extern __attribute__((short_call)) void jpeg_idct8v_armv4_1_z(uint16_t *in, uint16_t *end);
+extern __attribute__((short_call)) void jpeg_idct8v_armv4_1_n(uint16_t *in, uint16_t *end);
+extern __attribute__((short_call)) void jpeg_idct8v_armv5_1_z(uint16_t *in, uint16_t *end);
+extern __attribute__((short_call)) void jpeg_idct8v_armv6_1_z(uint16_t *in, uint16_t *end);
+extern __attribute__((short_call)) void jpeg_idct8h_armv4_1_z(uint16_t *in, unsigned char *out, uint16_t *end, int stride);
+extern __attribute__((short_call)) void jpeg_idct8h_armv4_1_n(uint16_t *in, unsigned char *out, uint16_t *end, int stride);
+extern __attribute__((short_call)) void jpeg_idct8h_armv5_1_z(uint16_t *in, unsigned char *out, uint16_t *end, int stride);
+extern __attribute__((short_call)) void jpeg_idct8h_armv6_1_z(uint16_t *in, unsigned char *out, uint16_t *end, int stride);
+
+/*************************** Plugin entry point ****************************/
+
+//#define TEST_IDCT
+#define BENCH_IDCT
+
+enum plugin_status plugin_start(const void *parameter)
+{
+    (void) parameter;
+    char fn_buf[MAX_PATH + 10], *s1, *s2;
+    rb->strcpy(fn_buf, rb->plugin_get_current_filename());
+    s1 = rb->strrchr(fn_buf, '/');
+    if (!s1)
+        return PLUGIN_ERROR;
+    s2 = rb->strrchr(s1, '.');
+    if (s2)
+        *s2 = 0;
+    rb->strcat(s1, ".log.txt");
+    if (rb->file_exists(s1))
+        log_fd = rb->open(s1, O_WRONLY|O_APPEND);
+    else
+        log_fd = rb->creat(s1);
+    if (log_fd < 0)
+        return PLUGIN_ERROR;
+    
+#ifdef HAVE_ADJUSTABLE_CPU_FREQ
+    rb->cpu_boost(true);
+#endif
+    prep_transpose();
+    prep_test(true);
+#ifdef BENCH_IDCT
+    DO_BENCH_CUSTOM(LOG_PRINTF, HZ*2, 10000, jpeg_idct8v_c_t, testbuf, testbuf + 64);
+    rb->sleep(30);
+    DO_BENCH_CUSTOM(LOG_PRINTF, HZ*2, 10000, jpeg_idct8v_armv4_1_z, testbuf, testbuf + 64);
+    rb->sleep(30);
+    DO_BENCH_CUSTOM(LOG_PRINTF, HZ*2, 10000, jpeg_idct8v_armv4_1_n, testbuf, testbuf + 64);
+    rb->sleep(30);
+#if ARM_ARCH > 4
+    DO_BENCH_CUSTOM(LOG_PRINTF, HZ*2, 10000, jpeg_idct8v_armv5_1_z, testbuf, testbuf + 64);
+    rb->sleep(30);
+#endif
+#if ARM_ARCH > 5
+    DO_BENCH_CUSTOM(LOG_PRINTF, HZ*2, 10000, jpeg_idct8v_armv6_1_z, testbuf, testbuf + 64);
+    rb->sleep(30);
+#endif
+    jpeg_idct8v_c_t(testbuf, testbuf + 64);
+    DO_BENCH_CUSTOM(LOG_PRINTF, HZ*2, 10000, jpeg_idct8h_c_z, testbuf + 64, (unsigned char *)(testbuf + 128), testbuf + 128, 32);
+    rb->sleep(30);
+    DO_BENCH_CUSTOM(LOG_PRINTF, HZ*2, 10000, jpeg_idct8h_armv4_1_z, testbuf + 64, (unsigned char *)(testbuf + 128), testbuf + 128, 32);
+    rb->sleep(30);
+    DO_BENCH_CUSTOM(LOG_PRINTF, HZ*2, 10000, jpeg_idct8h_armv4_1_n, testbuf + 64, (unsigned char *)(testbuf + 128), testbuf + 128, 32);
+#if ARM_ARCH > 4
+    rb->sleep(30);
+    DO_BENCH_CUSTOM(LOG_PRINTF, HZ*2, 10000, jpeg_idct8h_armv5_1_z, testbuf + 64, (unsigned char *)(testbuf + 128), testbuf + 128, 32);
+#endif
+#if ARM_ARCH > 5
+    rb->sleep(30);
+    DO_BENCH_CUSTOM(LOG_PRINTF, HZ*2, 10000, jpeg_idct8h_armv6_1_z, testbuf + 64, (unsigned char *)(testbuf + 128), testbuf + 128, 32);
+#endif
+#endif
+#ifdef TEST_IDCT
+    jpeg_idct8v_c_t(testbuf, testbuf + 64);
+    print_array_h(8, 8, 8, (testbuf+64));
+#if ARM_ARCH > 4
+    jpeg_idct8v_armv6_1_z(testbuf, testbuf+64);
+    print_array_h(8, 8, 8, (testbuf+64));
+#endif
+#endif
+#ifdef HAVE_ADJUSTABLE_CPU_FREQ
+    rb->cpu_boost(false);
+#endif
+    rb->close(log_fd);
+    return PLUGIN_OK;
+}
diff --git a/apps/plugins/idct_test/idct_test.make b/apps/plugins/idct_test/idct_test.make
new file mode 100644
index 0000000..446bea6
--- /dev/null
+++ b/apps/plugins/idct_test/idct_test.make
@@ -0,0 +1,21 @@
+#             __________               __   ___.
+#   Open      \______   \ ____   ____ |  | _\_ |__   _______  ___
+#   Source     |       _//  _ \_/ ___\|  |/ /| __ \ /  _ \  \/  /
+#   Jukebox    |    |   (  <_> )  \___|    < | \_\ (  <_> > <  <
+#   Firmware   |____|_  /\____/ \___  >__|_ \|___  /\____/__/\_ \
+#                     \/            \/     \/    \/            \/
+# $Id$
+#
+
+IDCTTESTSRCDIR := $(APPSDIR)/plugins/idct_test
+IDCTTESTBUILDDIR := $(BUILDDIR)/apps/plugins/idct_test
+
+ROCKS += $(IDCTTESTBUILDDIR)/idct_test.rock
+
+IDCTTEST_SRC := $(call preprocess, $(IDCTTESTSRCDIR)/SOURCES)
+IDCTTEST_OBJ := $(call c2obj, $(IDCTTEST_SRC))
+
+# add source files to OTHER_SRC to get automatic dependencies
+OTHER_SRC += $(IDCTTEST_SRC)
+
+$(IDCTTESTBUILDDIR)/idct_test.rock: $(IDCTTEST_OBJ) $(IDCTTESTSRCDIR)/idct_test.make