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
|
/* 32 and 64-bit millicode, original author Hewlett-Packard
adapted for gcc by Paul Bame <bame@debian.org>
and Alan Modra <alan@linuxcare.com.au>.
Copyright (C) 2001-2022 Free Software Foundation, Inc.
This file is part of GCC.
GCC 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 3, or (at your option) any later
version.
GCC is distributed in the hope that it will be useful, but WITHOUT ANY
WARRANTY; without even the implied warranty of MERCHANTABILITY or
FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
for more details.
Under Section 7 of GPL version 3, you are granted additional
permissions described in the GCC Runtime Library Exception, version
3.1, as published by the Free Software Foundation.
You should have received a copy of the GNU General Public License and
a copy of the GCC Runtime Library Exception along with this program;
see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
<http://www.gnu.org/licenses/>. */
/* An executable stack is *not* required for these functions. */
#if defined(__ELF__) && defined(__linux__)
.section .note.GNU-stack,"",%progbits
.previous
#endif
#ifdef pa64
.level 2.0w
#endif
/* Hardware General Registers. */
r0: .reg %r0
r1: .reg %r1
r2: .reg %r2
r3: .reg %r3
r4: .reg %r4
r5: .reg %r5
r6: .reg %r6
r7: .reg %r7
r8: .reg %r8
r9: .reg %r9
r10: .reg %r10
r11: .reg %r11
r12: .reg %r12
r13: .reg %r13
r14: .reg %r14
r15: .reg %r15
r16: .reg %r16
r17: .reg %r17
r18: .reg %r18
r19: .reg %r19
r20: .reg %r20
r21: .reg %r21
r22: .reg %r22
r23: .reg %r23
r24: .reg %r24
r25: .reg %r25
r26: .reg %r26
r27: .reg %r27
r28: .reg %r28
r29: .reg %r29
r30: .reg %r30
r31: .reg %r31
/* Hardware Space Registers. */
sr0: .reg %sr0
sr1: .reg %sr1
sr2: .reg %sr2
sr3: .reg %sr3
sr4: .reg %sr4
sr5: .reg %sr5
sr6: .reg %sr6
sr7: .reg %sr7
/* Hardware Floating Point Registers. */
fr0: .reg %fr0
fr1: .reg %fr1
fr2: .reg %fr2
fr3: .reg %fr3
fr4: .reg %fr4
fr5: .reg %fr5
fr6: .reg %fr6
fr7: .reg %fr7
fr8: .reg %fr8
fr9: .reg %fr9
fr10: .reg %fr10
fr11: .reg %fr11
fr12: .reg %fr12
fr13: .reg %fr13
fr14: .reg %fr14
fr15: .reg %fr15
/* Hardware Control Registers. */
cr11: .reg %cr11
sar: .reg %cr11 /* Shift Amount Register */
/* Software Architecture General Registers. */
rp: .reg r2 /* return pointer */
#ifdef pa64
mrp: .reg r2 /* millicode return pointer */
#else
mrp: .reg r31 /* millicode return pointer */
#endif
ret0: .reg r28 /* return value */
ret1: .reg r29 /* return value (high part of double) */
sp: .reg r30 /* stack pointer */
dp: .reg r27 /* data pointer */
arg0: .reg r26 /* argument */
arg1: .reg r25 /* argument or high part of double argument */
arg2: .reg r24 /* argument */
arg3: .reg r23 /* argument or high part of double argument */
/* Software Architecture Space Registers. */
/* sr0 ; return link from BLE */
sret: .reg sr1 /* return value */
sarg: .reg sr1 /* argument */
/* sr4 ; PC SPACE tracker */
/* sr5 ; process private data */
/* Frame Offsets (millicode convention!) Used when calling other
millicode routines. Stack unwinding is dependent upon these
definitions. */
r31_slot: .equ -20 /* "current RP" slot */
sr0_slot: .equ -16 /* "static link" slot */
#if defined(pa64)
mrp_slot: .equ -16 /* "current RP" slot */
psp_slot: .equ -8 /* "previous SP" slot */
#else
mrp_slot: .equ -20 /* "current RP" slot (replacing "r31_slot") */
#endif
#define DEFINE(name,value)name: .EQU value
#define RDEFINE(name,value)name: .REG value
#ifdef milliext
#define MILLI_BE(lbl) BE lbl(sr7,r0)
#define MILLI_BEN(lbl) BE,n lbl(sr7,r0)
#define MILLI_BLE(lbl) BLE lbl(sr7,r0)
#define MILLI_BLEN(lbl) BLE,n lbl(sr7,r0)
#define MILLIRETN BE,n 0(sr0,mrp)
#define MILLIRET BE 0(sr0,mrp)
#define MILLI_RETN BE,n 0(sr0,mrp)
#define MILLI_RET BE 0(sr0,mrp)
#else
#define MILLI_BE(lbl) B lbl
#define MILLI_BEN(lbl) B,n lbl
#define MILLI_BLE(lbl) BL lbl,mrp
#define MILLI_BLEN(lbl) BL,n lbl,mrp
#define MILLIRETN BV,n 0(mrp)
#define MILLIRET BV 0(mrp)
#define MILLI_RETN BV,n 0(mrp)
#define MILLI_RET BV 0(mrp)
#endif
#ifdef __STDC__
#define CAT(a,b) a##b
#else
#define CAT(a,b) a/**/b
#endif
#ifdef ELF
#define SUBSPA_MILLI .section .text
#define SUBSPA_MILLI_DIV .section .text.div,"ax",@progbits! .align 16
#define SUBSPA_MILLI_MUL .section .text.mul,"ax",@progbits! .align 16
#define ATTR_MILLI
#define SUBSPA_DATA .section .data
#define ATTR_DATA
#define GLOBAL $global$
#define GSYM(sym) !sym:
#define LSYM(sym) !CAT(.L,sym:)
#define LREF(sym) CAT(.L,sym)
#else
#ifdef coff
/* This used to be .milli but since link32 places different named
sections in different segments millicode ends up a long ways away
from .text (1meg?). This way they will be a lot closer.
The SUBSPA_MILLI_* specify locality sets for certain millicode
modules in order to ensure that modules that call one another are
placed close together. Without locality sets this is unlikely to
happen because of the Dynamite linker library search algorithm. We
want these modules close together so that short calls always reach
(we don't want to require long calls or use long call stubs). */
#define SUBSPA_MILLI .subspa .text
#define SUBSPA_MILLI_DIV .subspa .text$dv,align=16
#define SUBSPA_MILLI_MUL .subspa .text$mu,align=16
#define ATTR_MILLI .attr code,read,execute
#define SUBSPA_DATA .subspa .data
#define ATTR_DATA .attr init_data,read,write
#define GLOBAL _gp
#else
#define SUBSPA_MILLI .subspa $MILLICODE$,QUAD=0,ALIGN=4,ACCESS=0x2c,SORT=8
#define SUBSPA_MILLI_DIV SUBSPA_MILLI
#define SUBSPA_MILLI_MUL SUBSPA_MILLI
#define ATTR_MILLI
#define SUBSPA_DATA .subspa $BSS$,quad=1,align=8,access=0x1f,sort=80,zero
#define ATTR_DATA
#define GLOBAL $global$
#endif
#define SPACE_DATA .space $PRIVATE$,spnum=1,sort=16
#define GSYM(sym) !sym
#define LSYM(sym) !CAT(L$,sym)
#define LREF(sym) CAT(L$,sym)
#endif
#ifdef L_dyncall
SUBSPA_MILLI
ATTR_DATA
GSYM($$dyncall)
.export $$dyncall,millicode
.proc
.callinfo millicode
.entry
#ifdef LINUX
extru,<> %r22,30,1,%r0 ; nullify if plabel bit set
bv,n %r0(%r22) ; branch to target
ldw -2(%r22),%r21 ; load address of target
bv %r0(%r21) ; branch to the real target
ldw 2(%r22),%r19 ; load new LTP value
#else
bb,>=,n %r22,30,LREF(1) ; branch if not plabel address
ldw -2(%r22),%r21 ; load address of target to r21
ldsid (%sr0,%r21),%r1 ; get the "space ident" selected by r21
ldw 2(%r22),%r19 ; load new LTP value
mtsp %r1,%sr0 ; move that space identifier into sr0
be 0(%sr0,%r21) ; branch to the real target
stw %r2,-24(%r30) ; save return address into frame marker
LSYM(1)
ldsid (%sr0,%r22),%r1 ; get the "space ident" selected by r22
mtsp %r1,%sr0 ; move that space identifier into sr0
be 0(%sr0,%r22) ; branch to the target
stw %r2,-24(%r30) ; save return address into frame marker
#endif
.exit
.procend
#endif
#ifdef L_divI
/* ROUTINES: $$divI, $$divoI
Single precision divide for signed binary integers.
The quotient is truncated towards zero.
The sign of the quotient is the XOR of the signs of the dividend and
divisor.
Divide by zero is trapped.
Divide of -2**31 by -1 is trapped for $$divoI but not for $$divI.
INPUT REGISTERS:
. arg0 == dividend
. arg1 == divisor
. mrp == return pc
. sr0 == return space when called externally
OUTPUT REGISTERS:
. arg0 = undefined
. arg1 = undefined
. ret1 = quotient
OTHER REGISTERS AFFECTED:
. r1 = undefined
SIDE EFFECTS:
. Causes a trap under the following conditions:
. divisor is zero (traps with ADDIT,= 0,25,0)
. dividend==-2**31 and divisor==-1 and routine is $$divoI
. (traps with ADDO 26,25,0)
. Changes memory at the following places:
. NONE
PERMISSIBLE CONTEXT:
. Unwindable.
. Suitable for internal or external millicode.
. Assumes the special millicode register conventions.
DISCUSSION:
. Branchs to other millicode routines using BE
. $$div_# for # being 2,3,4,5,6,7,8,9,10,12,14,15
.
. For selected divisors, calls a divide by constant routine written by
. Karl Pettis. Eligible divisors are 1..15 excluding 11 and 13.
.
. The only overflow case is -2**31 divided by -1.
. Both routines return -2**31 but only $$divoI traps. */
RDEFINE(temp,r1)
RDEFINE(retreg,ret1) /* r29 */
RDEFINE(temp1,arg0)
SUBSPA_MILLI_DIV
ATTR_MILLI
.import $$divI_2,millicode
.import $$divI_3,millicode
.import $$divI_4,millicode
.import $$divI_5,millicode
.import $$divI_6,millicode
.import $$divI_7,millicode
.import $$divI_8,millicode
.import $$divI_9,millicode
.import $$divI_10,millicode
.import $$divI_12,millicode
.import $$divI_14,millicode
.import $$divI_15,millicode
.export $$divI,millicode
.export $$divoI,millicode
.proc
.callinfo millicode
.entry
GSYM($$divoI)
comib,=,n -1,arg1,LREF(negative1) /* when divisor == -1 */
GSYM($$divI)
ldo -1(arg1),temp /* is there at most one bit set ? */
and,<> arg1,temp,r0 /* if not, don't use power of 2 divide */
addi,> 0,arg1,r0 /* if divisor > 0, use power of 2 divide */
b,n LREF(neg_denom)
LSYM(pow2)
addi,>= 0,arg0,retreg /* if numerator is negative, add the */
add arg0,temp,retreg /* (denominaotr -1) to correct for shifts */
extru,= arg1,15,16,temp /* test denominator with 0xffff0000 */
extrs retreg,15,16,retreg /* retreg = retreg >> 16 */
or arg1,temp,arg1 /* arg1 = arg1 | (arg1 >> 16) */
ldi 0xcc,temp1 /* setup 0xcc in temp1 */
extru,= arg1,23,8,temp /* test denominator with 0xff00 */
extrs retreg,23,24,retreg /* retreg = retreg >> 8 */
or arg1,temp,arg1 /* arg1 = arg1 | (arg1 >> 8) */
ldi 0xaa,temp /* setup 0xaa in temp */
extru,= arg1,27,4,r0 /* test denominator with 0xf0 */
extrs retreg,27,28,retreg /* retreg = retreg >> 4 */
and,= arg1,temp1,r0 /* test denominator with 0xcc */
extrs retreg,29,30,retreg /* retreg = retreg >> 2 */
and,= arg1,temp,r0 /* test denominator with 0xaa */
extrs retreg,30,31,retreg /* retreg = retreg >> 1 */
MILLIRETN
LSYM(neg_denom)
addi,< 0,arg1,r0 /* if arg1 >= 0, it's not power of 2 */
b,n LREF(regular_seq)
sub r0,arg1,temp /* make denominator positive */
comb,=,n arg1,temp,LREF(regular_seq) /* test against 0x80000000 and 0 */
ldo -1(temp),retreg /* is there at most one bit set ? */
and,= temp,retreg,r0 /* if so, the denominator is power of 2 */
b,n LREF(regular_seq)
sub r0,arg0,retreg /* negate numerator */
comb,=,n arg0,retreg,LREF(regular_seq) /* test against 0x80000000 */
copy retreg,arg0 /* set up arg0, arg1 and temp */
copy temp,arg1 /* before branching to pow2 */
b LREF(pow2)
ldo -1(arg1),temp
LSYM(regular_seq)
comib,>>=,n 15,arg1,LREF(small_divisor)
add,>= 0,arg0,retreg /* move dividend, if retreg < 0, */
LSYM(normal)
subi 0,retreg,retreg /* make it positive */
sub 0,arg1,temp /* clear carry, */
/* negate the divisor */
ds 0,temp,0 /* set V-bit to the comple- */
/* ment of the divisor sign */
add retreg,retreg,retreg /* shift msb bit into carry */
ds r0,arg1,temp /* 1st divide step, if no carry */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 2nd divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 3rd divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 4th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 5th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 6th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 7th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 8th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 9th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 10th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 11th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 12th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 13th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 14th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 15th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 16th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 17th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 18th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 19th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 20th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 21st divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 22nd divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 23rd divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 24th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 25th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 26th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 27th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 28th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 29th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 30th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 31st divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 32nd divide step, */
addc retreg,retreg,retreg /* shift last retreg bit into retreg */
xor,>= arg0,arg1,0 /* get correct sign of quotient */
sub 0,retreg,retreg /* based on operand signs */
MILLIRETN
nop
LSYM(small_divisor)
#if defined(pa64)
/* Clear the upper 32 bits of the arg1 register. We are working with */
/* small divisors (and 32-bit integers) We must not be mislead */
/* by "1" bits left in the upper 32 bits. */
depd %r0,31,32,%r25
#endif
blr,n arg1,r0
nop
/* table for divisor == 0,1, ... ,15 */
addit,= 0,arg1,r0 /* trap if divisor == 0 */
nop
MILLIRET /* divisor == 1 */
copy arg0,retreg
MILLI_BEN($$divI_2) /* divisor == 2 */
nop
MILLI_BEN($$divI_3) /* divisor == 3 */
nop
MILLI_BEN($$divI_4) /* divisor == 4 */
nop
MILLI_BEN($$divI_5) /* divisor == 5 */
nop
MILLI_BEN($$divI_6) /* divisor == 6 */
nop
MILLI_BEN($$divI_7) /* divisor == 7 */
nop
MILLI_BEN($$divI_8) /* divisor == 8 */
nop
MILLI_BEN($$divI_9) /* divisor == 9 */
nop
MILLI_BEN($$divI_10) /* divisor == 10 */
nop
b LREF(normal) /* divisor == 11 */
add,>= 0,arg0,retreg
MILLI_BEN($$divI_12) /* divisor == 12 */
nop
b LREF(normal) /* divisor == 13 */
add,>= 0,arg0,retreg
MILLI_BEN($$divI_14) /* divisor == 14 */
nop
MILLI_BEN($$divI_15) /* divisor == 15 */
nop
LSYM(negative1)
sub 0,arg0,retreg /* result is negation of dividend */
MILLIRET
addo arg0,arg1,r0 /* trap iff dividend==0x80000000 && divisor==-1 */
.exit
.procend
.end
#endif
#ifdef L_divU
/* ROUTINE: $$divU
.
. Single precision divide for unsigned integers.
.
. Quotient is truncated towards zero.
. Traps on divide by zero.
INPUT REGISTERS:
. arg0 == dividend
. arg1 == divisor
. mrp == return pc
. sr0 == return space when called externally
OUTPUT REGISTERS:
. arg0 = undefined
. arg1 = undefined
. ret1 = quotient
OTHER REGISTERS AFFECTED:
. r1 = undefined
SIDE EFFECTS:
. Causes a trap under the following conditions:
. divisor is zero
. Changes memory at the following places:
. NONE
PERMISSIBLE CONTEXT:
. Unwindable.
. Does not create a stack frame.
. Suitable for internal or external millicode.
. Assumes the special millicode register conventions.
DISCUSSION:
. Branchs to other millicode routines using BE:
. $$divU_# for 3,5,6,7,9,10,12,14,15
.
. For selected small divisors calls the special divide by constant
. routines written by Karl Pettis. These are: 3,5,6,7,9,10,12,14,15. */
RDEFINE(temp,r1)
RDEFINE(retreg,ret1) /* r29 */
RDEFINE(temp1,arg0)
SUBSPA_MILLI_DIV
ATTR_MILLI
.export $$divU,millicode
.import $$divU_3,millicode
.import $$divU_5,millicode
.import $$divU_6,millicode
.import $$divU_7,millicode
.import $$divU_9,millicode
.import $$divU_10,millicode
.import $$divU_12,millicode
.import $$divU_14,millicode
.import $$divU_15,millicode
.proc
.callinfo millicode
.entry
GSYM($$divU)
/* The subtract is not nullified since it does no harm and can be used
by the two cases that branch back to "normal". */
ldo -1(arg1),temp /* is there at most one bit set ? */
and,= arg1,temp,r0 /* if so, denominator is power of 2 */
b LREF(regular_seq)
addit,= 0,arg1,0 /* trap for zero dvr */
copy arg0,retreg
extru,= arg1,15,16,temp /* test denominator with 0xffff0000 */
extru retreg,15,16,retreg /* retreg = retreg >> 16 */
or arg1,temp,arg1 /* arg1 = arg1 | (arg1 >> 16) */
ldi 0xcc,temp1 /* setup 0xcc in temp1 */
extru,= arg1,23,8,temp /* test denominator with 0xff00 */
extru retreg,23,24,retreg /* retreg = retreg >> 8 */
or arg1,temp,arg1 /* arg1 = arg1 | (arg1 >> 8) */
ldi 0xaa,temp /* setup 0xaa in temp */
extru,= arg1,27,4,r0 /* test denominator with 0xf0 */
extru retreg,27,28,retreg /* retreg = retreg >> 4 */
and,= arg1,temp1,r0 /* test denominator with 0xcc */
extru retreg,29,30,retreg /* retreg = retreg >> 2 */
and,= arg1,temp,r0 /* test denominator with 0xaa */
extru retreg,30,31,retreg /* retreg = retreg >> 1 */
MILLIRETN
nop
LSYM(regular_seq)
comib,>= 15,arg1,LREF(special_divisor)
subi 0,arg1,temp /* clear carry, negate the divisor */
ds r0,temp,r0 /* set V-bit to 1 */
LSYM(normal)
add arg0,arg0,retreg /* shift msb bit into carry */
ds r0,arg1,temp /* 1st divide step, if no carry */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 2nd divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 3rd divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 4th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 5th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 6th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 7th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 8th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 9th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 10th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 11th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 12th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 13th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 14th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 15th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 16th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 17th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 18th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 19th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 20th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 21st divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 22nd divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 23rd divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 24th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 25th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 26th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 27th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 28th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 29th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 30th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 31st divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds temp,arg1,temp /* 32nd divide step, */
MILLIRET
addc retreg,retreg,retreg /* shift last retreg bit into retreg */
/* Handle the cases where divisor is a small constant or has high bit on. */
LSYM(special_divisor)
/* blr arg1,r0 */
/* comib,>,n 0,arg1,LREF(big_divisor) ; nullify previous instruction */
/* Pratap 8/13/90. The 815 Stirling chip set has a bug that prevents us from
generating such a blr, comib sequence. A problem in nullification. So I
rewrote this code. */
#if defined(pa64)
/* Clear the upper 32 bits of the arg1 register. We are working with
small divisors (and 32-bit unsigned integers) We must not be mislead
by "1" bits left in the upper 32 bits. */
depd %r0,31,32,%r25
#endif
comib,> 0,arg1,LREF(big_divisor)
nop
blr arg1,r0
nop
LSYM(zero_divisor) /* this label is here to provide external visibility */
addit,= 0,arg1,0 /* trap for zero dvr */
nop
MILLIRET /* divisor == 1 */
copy arg0,retreg
MILLIRET /* divisor == 2 */
extru arg0,30,31,retreg
MILLI_BEN($$divU_3) /* divisor == 3 */
nop
MILLIRET /* divisor == 4 */
extru arg0,29,30,retreg
MILLI_BEN($$divU_5) /* divisor == 5 */
nop
MILLI_BEN($$divU_6) /* divisor == 6 */
nop
MILLI_BEN($$divU_7) /* divisor == 7 */
nop
MILLIRET /* divisor == 8 */
extru arg0,28,29,retreg
MILLI_BEN($$divU_9) /* divisor == 9 */
nop
MILLI_BEN($$divU_10) /* divisor == 10 */
nop
b LREF(normal) /* divisor == 11 */
ds r0,temp,r0 /* set V-bit to 1 */
MILLI_BEN($$divU_12) /* divisor == 12 */
nop
b LREF(normal) /* divisor == 13 */
ds r0,temp,r0 /* set V-bit to 1 */
MILLI_BEN($$divU_14) /* divisor == 14 */
nop
MILLI_BEN($$divU_15) /* divisor == 15 */
nop
/* Handle the case where the high bit is on in the divisor.
Compute: if( dividend>=divisor) quotient=1; else quotient=0;
Note: dividend>==divisor iff dividend-divisor does not borrow
and not borrow iff carry. */
LSYM(big_divisor)
sub arg0,arg1,r0
MILLIRET
addc r0,r0,retreg
.exit
.procend
.end
#endif
#ifdef L_remI
/* ROUTINE: $$remI
DESCRIPTION:
. $$remI returns the remainder of the division of two signed 32-bit
. integers. The sign of the remainder is the same as the sign of
. the dividend.
INPUT REGISTERS:
. arg0 == dividend
. arg1 == divisor
. mrp == return pc
. sr0 == return space when called externally
OUTPUT REGISTERS:
. arg0 = destroyed
. arg1 = destroyed
. ret1 = remainder
OTHER REGISTERS AFFECTED:
. r1 = undefined
SIDE EFFECTS:
. Causes a trap under the following conditions: DIVIDE BY ZERO
. Changes memory at the following places: NONE
PERMISSIBLE CONTEXT:
. Unwindable
. Does not create a stack frame
. Is usable for internal or external microcode
DISCUSSION:
. Calls other millicode routines via mrp: NONE
. Calls other millicode routines: NONE */
RDEFINE(tmp,r1)
RDEFINE(retreg,ret1)
SUBSPA_MILLI
ATTR_MILLI
.proc
.callinfo millicode
.entry
GSYM($$remI)
GSYM($$remoI)
.export $$remI,MILLICODE
.export $$remoI,MILLICODE
ldo -1(arg1),tmp /* is there at most one bit set ? */
and,<> arg1,tmp,r0 /* if not, don't use power of 2 */
addi,> 0,arg1,r0 /* if denominator > 0, use power */
/* of 2 */
b,n LREF(neg_denom)
LSYM(pow2)
comb,>,n 0,arg0,LREF(neg_num) /* is numerator < 0 ? */
and arg0,tmp,retreg /* get the result */
MILLIRETN
LSYM(neg_num)
subi 0,arg0,arg0 /* negate numerator */
and arg0,tmp,retreg /* get the result */
subi 0,retreg,retreg /* negate result */
MILLIRETN
LSYM(neg_denom)
addi,< 0,arg1,r0 /* if arg1 >= 0, it's not power */
/* of 2 */
b,n LREF(regular_seq)
sub r0,arg1,tmp /* make denominator positive */
comb,=,n arg1,tmp,LREF(regular_seq) /* test against 0x80000000 and 0 */
ldo -1(tmp),retreg /* is there at most one bit set ? */
and,= tmp,retreg,r0 /* if not, go to regular_seq */
b,n LREF(regular_seq)
comb,>,n 0,arg0,LREF(neg_num_2) /* if arg0 < 0, negate it */
and arg0,retreg,retreg
MILLIRETN
LSYM(neg_num_2)
subi 0,arg0,tmp /* test against 0x80000000 */
and tmp,retreg,retreg
subi 0,retreg,retreg
MILLIRETN
LSYM(regular_seq)
addit,= 0,arg1,0 /* trap if div by zero */
add,>= 0,arg0,retreg /* move dividend, if retreg < 0, */
sub 0,retreg,retreg /* make it positive */
sub 0,arg1, tmp /* clear carry, */
/* negate the divisor */
ds 0, tmp,0 /* set V-bit to the comple- */
/* ment of the divisor sign */
or 0,0, tmp /* clear tmp */
add retreg,retreg,retreg /* shift msb bit into carry */
ds tmp,arg1, tmp /* 1st divide step, if no carry */
/* out, msb of quotient = 0 */
addc retreg,retreg,retreg /* shift retreg with/into carry */
LSYM(t1)
ds tmp,arg1, tmp /* 2nd divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 3rd divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 4th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 5th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 6th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 7th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 8th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 9th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 10th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 11th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 12th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 13th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 14th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 15th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 16th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 17th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 18th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 19th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 20th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 21st divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 22nd divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 23rd divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 24th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 25th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 26th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 27th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 28th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 29th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 30th divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 31st divide step */
addc retreg,retreg,retreg /* shift retreg with/into carry */
ds tmp,arg1, tmp /* 32nd divide step, */
addc retreg,retreg,retreg /* shift last bit into retreg */
movb,>=,n tmp,retreg,LREF(finish) /* branch if pos. tmp */
add,< arg1,0,0 /* if arg1 > 0, add arg1 */
add,tr tmp,arg1,retreg /* for correcting remainder tmp */
sub tmp,arg1,retreg /* else add absolute value arg1 */
LSYM(finish)
add,>= arg0,0,0 /* set sign of remainder */
sub 0,retreg,retreg /* to sign of dividend */
MILLIRET
nop
.exit
.procend
#ifdef milliext
.origin 0x00000200
#endif
.end
#endif
#ifdef L_remU
/* ROUTINE: $$remU
. Single precision divide for remainder with unsigned binary integers.
.
. The remainder must be dividend-(dividend/divisor)*divisor.
. Divide by zero is trapped.
INPUT REGISTERS:
. arg0 == dividend
. arg1 == divisor
. mrp == return pc
. sr0 == return space when called externally
OUTPUT REGISTERS:
. arg0 = undefined
. arg1 = undefined
. ret1 = remainder
OTHER REGISTERS AFFECTED:
. r1 = undefined
SIDE EFFECTS:
. Causes a trap under the following conditions: DIVIDE BY ZERO
. Changes memory at the following places: NONE
PERMISSIBLE CONTEXT:
. Unwindable.
. Does not create a stack frame.
. Suitable for internal or external millicode.
. Assumes the special millicode register conventions.
DISCUSSION:
. Calls other millicode routines using mrp: NONE
. Calls other millicode routines: NONE */
RDEFINE(temp,r1)
RDEFINE(rmndr,ret1) /* r29 */
SUBSPA_MILLI
ATTR_MILLI
.export $$remU,millicode
.proc
.callinfo millicode
.entry
GSYM($$remU)
ldo -1(arg1),temp /* is there at most one bit set ? */
and,= arg1,temp,r0 /* if not, don't use power of 2 */
b LREF(regular_seq)
addit,= 0,arg1,r0 /* trap on div by zero */
and arg0,temp,rmndr /* get the result for power of 2 */
MILLIRETN
LSYM(regular_seq)
comib,>=,n 0,arg1,LREF(special_case)
subi 0,arg1,rmndr /* clear carry, negate the divisor */
ds r0,rmndr,r0 /* set V-bit to 1 */
add arg0,arg0,temp /* shift msb bit into carry */
ds r0,arg1,rmndr /* 1st divide step, if no carry */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 2nd divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 3rd divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 4th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 5th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 6th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 7th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 8th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 9th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 10th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 11th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 12th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 13th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 14th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 15th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 16th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 17th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 18th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 19th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 20th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 21st divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 22nd divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 23rd divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 24th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 25th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 26th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 27th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 28th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 29th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 30th divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 31st divide step */
addc temp,temp,temp /* shift temp with/into carry */
ds rmndr,arg1,rmndr /* 32nd divide step, */
comiclr,<= 0,rmndr,r0
add rmndr,arg1,rmndr /* correction */
MILLIRETN
nop
/* Putting >= on the last DS and deleting COMICLR does not work! */
LSYM(special_case)
sub,>>= arg0,arg1,rmndr
copy arg0,rmndr
MILLIRETN
nop
.exit
.procend
.end
#endif
#ifdef L_div_const
/* ROUTINE: $$divI_2
. $$divI_3 $$divU_3
. $$divI_4
. $$divI_5 $$divU_5
. $$divI_6 $$divU_6
. $$divI_7 $$divU_7
. $$divI_8
. $$divI_9 $$divU_9
. $$divI_10 $$divU_10
.
. $$divI_12 $$divU_12
.
. $$divI_14 $$divU_14
. $$divI_15 $$divU_15
. $$divI_16
. $$divI_17 $$divU_17
.
. Divide by selected constants for single precision binary integers.
INPUT REGISTERS:
. arg0 == dividend
. mrp == return pc
. sr0 == return space when called externally
OUTPUT REGISTERS:
. arg0 = undefined
. arg1 = undefined
. ret1 = quotient
OTHER REGISTERS AFFECTED:
. r1 = undefined
SIDE EFFECTS:
. Causes a trap under the following conditions: NONE
. Changes memory at the following places: NONE
PERMISSIBLE CONTEXT:
. Unwindable.
. Does not create a stack frame.
. Suitable for internal or external millicode.
. Assumes the special millicode register conventions.
DISCUSSION:
. Calls other millicode routines using mrp: NONE
. Calls other millicode routines: NONE */
/* TRUNCATED DIVISION BY SMALL INTEGERS
We are interested in q(x) = floor(x/y), where x >= 0 and y > 0
(with y fixed).
Let a = floor(z/y), for some choice of z. Note that z will be
chosen so that division by z is cheap.
Let r be the remainder(z/y). In other words, r = z - ay.
Now, our method is to choose a value for b such that
q'(x) = floor((ax+b)/z)
is equal to q(x) over as large a range of x as possible. If the
two are equal over a sufficiently large range, and if it is easy to
form the product (ax), and it is easy to divide by z, then we can
perform the division much faster than the general division algorithm.
So, we want the following to be true:
. For x in the following range:
.
. ky <= x < (k+1)y
.
. implies that
.
. k <= (ax+b)/z < (k+1)
We want to determine b such that this is true for all k in the
range {0..K} for some maximum K.
Since (ax+b) is an increasing function of x, we can take each
bound separately to determine the "best" value for b.
(ax+b)/z < (k+1) implies
(a((k+1)y-1)+b < (k+1)z implies
b < a + (k+1)(z-ay) implies
b < a + (k+1)r
This needs to be true for all k in the range {0..K}. In
particular, it is true for k = 0 and this leads to a maximum
acceptable value for b.
b < a+r or b <= a+r-1
Taking the other bound, we have
k <= (ax+b)/z implies
k <= (aky+b)/z implies
k(z-ay) <= b implies
kr <= b
Clearly, the largest range for k will be achieved by maximizing b,
when r is not zero. When r is zero, then the simplest choice for b
is 0. When r is not 0, set
. b = a+r-1
Now, by construction, q'(x) = floor((ax+b)/z) = q(x) = floor(x/y)
for all x in the range:
. 0 <= x < (K+1)y
We need to determine what K is. Of our two bounds,
. b < a+(k+1)r is satisfied for all k >= 0, by construction.
The other bound is
. kr <= b
This is always true if r = 0. If r is not 0 (the usual case), then
K = floor((a+r-1)/r), is the maximum value for k.
Therefore, the formula q'(x) = floor((ax+b)/z) yields the correct
answer for q(x) = floor(x/y) when x is in the range
(0,(K+1)y-1) K = floor((a+r-1)/r)
To be most useful, we want (K+1)y-1 = (max x) >= 2**32-1 so that
the formula for q'(x) yields the correct value of q(x) for all x
representable by a single word in HPPA.
We are also constrained in that computing the product (ax), adding
b, and dividing by z must all be done quickly, otherwise we will be
better off going through the general algorithm using the DS
instruction, which uses approximately 70 cycles.
For each y, there is a choice of z which satisfies the constraints
for (K+1)y >= 2**32. We may not, however, be able to satisfy the
timing constraints for arbitrary y. It seems that z being equal to
a power of 2 or a power of 2 minus 1 is as good as we can do, since
it minimizes the time to do division by z. We want the choice of z
to also result in a value for (a) that minimizes the computation of
the product (ax). This is best achieved if (a) has a regular bit
pattern (so the multiplication can be done with shifts and adds).
The value of (a) also needs to be less than 2**32 so the product is
always guaranteed to fit in 2 words.
In actual practice, the following should be done:
1) For negative x, you should take the absolute value and remember
. the fact so that the result can be negated. This obviously does
. not apply in the unsigned case.
2) For even y, you should factor out the power of 2 that divides y
. and divide x by it. You can then proceed by dividing by the
. odd factor of y.
Here is a table of some odd values of y, and corresponding choices
for z which are "good".
y z r a (hex) max x (hex)
3 2**32 1 55555555 100000001
5 2**32 1 33333333 100000003
7 2**24-1 0 249249 (infinite)
9 2**24-1 0 1c71c7 (infinite)
11 2**20-1 0 1745d (infinite)
13 2**24-1 0 13b13b (infinite)
15 2**32 1 11111111 10000000d
17 2**32 1 f0f0f0f 10000000f
If r is 1, then b = a+r-1 = a. This simplifies the computation
of (ax+b), since you can compute (x+1)(a) instead. If r is 0,
then b = 0 is ok to use which simplifies (ax+b).
The bit patterns for 55555555, 33333333, and 11111111 are obviously
very regular. The bit patterns for the other values of a above are:
y (hex) (binary)
7 249249 001001001001001001001001 << regular >>
9 1c71c7 000111000111000111000111 << regular >>
11 1745d 000000010111010001011101 << irregular >>
13 13b13b 000100111011000100111011 << irregular >>
The bit patterns for (a) corresponding to (y) of 11 and 13 may be
too irregular to warrant using this method.
When z is a power of 2 minus 1, then the division by z is slightly
more complicated, involving an iterative solution.
The code presented here solves division by 1 through 17, except for
11 and 13. There are algorithms for both signed and unsigned
quantities given.
TIMINGS (cycles)
divisor positive negative unsigned
. 1 2 2 2
. 2 4 4 2
. 3 19 21 19
. 4 4 4 2
. 5 18 22 19
. 6 19 22 19
. 8 4 4 2
. 10 18 19 17
. 12 18 20 18
. 15 16 18 16
. 16 4 4 2
. 17 16 18 16
Now, the algorithm for 7, 9, and 14 is an iterative one. That is,
a loop body is executed until the tentative quotient is 0. The
number of times the loop body is executed varies depending on the
dividend, but is never more than two times. If the dividend is
less than the divisor, then the loop body is not executed at all.
Each iteration adds 4 cycles to the timings.
divisor positive negative unsigned
. 7 19+4n 20+4n 20+4n n = number of iterations
. 9 21+4n 22+4n 21+4n
. 14 21+4n 22+4n 20+4n
To give an idea of how the number of iterations varies, here is a
table of dividend versus number of iterations when dividing by 7.
smallest largest required
dividend dividend iterations
. 0 6 0
. 7 0x6ffffff 1
0x1000006 0xffffffff 2
There is some overlap in the range of numbers requiring 1 and 2
iterations. */
RDEFINE(t2,r1)
RDEFINE(x2,arg0) /* r26 */
RDEFINE(t1,arg1) /* r25 */
RDEFINE(x1,ret1) /* r29 */
SUBSPA_MILLI_DIV
ATTR_MILLI
.proc
.callinfo millicode
.entry
/* NONE of these routines require a stack frame
ALL of these routines are unwindable from millicode */
GSYM($$divide_by_constant)
.export $$divide_by_constant,millicode
/* Provides a "nice" label for the code covered by the unwind descriptor
for things like gprof. */
/* DIVISION BY 2 (shift by 1) */
GSYM($$divI_2)
.export $$divI_2,millicode
comclr,>= arg0,0,0
addi 1,arg0,arg0
MILLIRET
extrs arg0,30,31,ret1
/* DIVISION BY 4 (shift by 2) */
GSYM($$divI_4)
.export $$divI_4,millicode
comclr,>= arg0,0,0
addi 3,arg0,arg0
MILLIRET
extrs arg0,29,30,ret1
/* DIVISION BY 8 (shift by 3) */
GSYM($$divI_8)
.export $$divI_8,millicode
comclr,>= arg0,0,0
addi 7,arg0,arg0
MILLIRET
extrs arg0,28,29,ret1
/* DIVISION BY 16 (shift by 4) */
GSYM($$divI_16)
.export $$divI_16,millicode
comclr,>= arg0,0,0
addi 15,arg0,arg0
MILLIRET
extrs arg0,27,28,ret1
/****************************************************************************
*
* DIVISION BY DIVISORS OF FFFFFFFF, and powers of 2 times these
*
* includes 3,5,15,17 and also 6,10,12
*
****************************************************************************/
/* DIVISION BY 3 (use z = 2**32; a = 55555555) */
GSYM($$divI_3)
.export $$divI_3,millicode
comb,<,N x2,0,LREF(neg3)
addi 1,x2,x2 /* this cannot overflow */
extru x2,1,2,x1 /* multiply by 5 to get started */
sh2add x2,x2,x2
b LREF(pos)
addc x1,0,x1
LSYM(neg3)
subi 1,x2,x2 /* this cannot overflow */
extru x2,1,2,x1 /* multiply by 5 to get started */
sh2add x2,x2,x2
b LREF(neg)
addc x1,0,x1
GSYM($$divU_3)
.export $$divU_3,millicode
addi 1,x2,x2 /* this CAN overflow */
addc 0,0,x1
shd x1,x2,30,t1 /* multiply by 5 to get started */
sh2add x2,x2,x2
b LREF(pos)
addc x1,t1,x1
/* DIVISION BY 5 (use z = 2**32; a = 33333333) */
GSYM($$divI_5)
.export $$divI_5,millicode
comb,<,N x2,0,LREF(neg5)
addi 3,x2,t1 /* this cannot overflow */
sh1add x2,t1,x2 /* multiply by 3 to get started */
b LREF(pos)
addc 0,0,x1
LSYM(neg5)
sub 0,x2,x2 /* negate x2 */
addi 1,x2,x2 /* this cannot overflow */
shd 0,x2,31,x1 /* get top bit (can be 1) */
sh1add x2,x2,x2 /* multiply by 3 to get started */
b LREF(neg)
addc x1,0,x1
GSYM($$divU_5)
.export $$divU_5,millicode
addi 1,x2,x2 /* this CAN overflow */
addc 0,0,x1
shd x1,x2,31,t1 /* multiply by 3 to get started */
sh1add x2,x2,x2
b LREF(pos)
addc t1,x1,x1
/* DIVISION BY 6 (shift to divide by 2 then divide by 3) */
GSYM($$divI_6)
.export $$divI_6,millicode
comb,<,N x2,0,LREF(neg6)
extru x2,30,31,x2 /* divide by 2 */
addi 5,x2,t1 /* compute 5*(x2+1) = 5*x2+5 */
sh2add x2,t1,x2 /* multiply by 5 to get started */
b LREF(pos)
addc 0,0,x1
LSYM(neg6)
subi 2,x2,x2 /* negate, divide by 2, and add 1 */
/* negation and adding 1 are done */
/* at the same time by the SUBI */
extru x2,30,31,x2
shd 0,x2,30,x1
sh2add x2,x2,x2 /* multiply by 5 to get started */
b LREF(neg)
addc x1,0,x1
GSYM($$divU_6)
.export $$divU_6,millicode
extru x2,30,31,x2 /* divide by 2 */
addi 1,x2,x2 /* cannot carry */
shd 0,x2,30,x1 /* multiply by 5 to get started */
sh2add x2,x2,x2
b LREF(pos)
addc x1,0,x1
/* DIVISION BY 10 (shift to divide by 2 then divide by 5) */
GSYM($$divU_10)
.export $$divU_10,millicode
extru x2,30,31,x2 /* divide by 2 */
addi 3,x2,t1 /* compute 3*(x2+1) = (3*x2)+3 */
sh1add x2,t1,x2 /* multiply by 3 to get started */
addc 0,0,x1
LSYM(pos)
shd x1,x2,28,t1 /* multiply by 0x11 */
shd x2,0,28,t2
add x2,t2,x2
addc x1,t1,x1
LSYM(pos_for_17)
shd x1,x2,24,t1 /* multiply by 0x101 */
shd x2,0,24,t2
add x2,t2,x2
addc x1,t1,x1
shd x1,x2,16,t1 /* multiply by 0x10001 */
shd x2,0,16,t2
add x2,t2,x2
MILLIRET
addc x1,t1,x1
GSYM($$divI_10)
.export $$divI_10,millicode
comb,< x2,0,LREF(neg10)
copy 0,x1
extru x2,30,31,x2 /* divide by 2 */
addib,TR 1,x2,LREF(pos) /* add 1 (cannot overflow) */
sh1add x2,x2,x2 /* multiply by 3 to get started */
LSYM(neg10)
subi 2,x2,x2 /* negate, divide by 2, and add 1 */
/* negation and adding 1 are done */
/* at the same time by the SUBI */
extru x2,30,31,x2
sh1add x2,x2,x2 /* multiply by 3 to get started */
LSYM(neg)
shd x1,x2,28,t1 /* multiply by 0x11 */
shd x2,0,28,t2
add x2,t2,x2
addc x1,t1,x1
LSYM(neg_for_17)
shd x1,x2,24,t1 /* multiply by 0x101 */
shd x2,0,24,t2
add x2,t2,x2
addc x1,t1,x1
shd x1,x2,16,t1 /* multiply by 0x10001 */
shd x2,0,16,t2
add x2,t2,x2
addc x1,t1,x1
MILLIRET
sub 0,x1,x1
/* DIVISION BY 12 (shift to divide by 4 then divide by 3) */
GSYM($$divI_12)
.export $$divI_12,millicode
comb,< x2,0,LREF(neg12)
copy 0,x1
extru x2,29,30,x2 /* divide by 4 */
addib,tr 1,x2,LREF(pos) /* compute 5*(x2+1) = 5*x2+5 */
sh2add x2,x2,x2 /* multiply by 5 to get started */
LSYM(neg12)
subi 4,x2,x2 /* negate, divide by 4, and add 1 */
/* negation and adding 1 are done */
/* at the same time by the SUBI */
extru x2,29,30,x2
b LREF(neg)
sh2add x2,x2,x2 /* multiply by 5 to get started */
GSYM($$divU_12)
.export $$divU_12,millicode
extru x2,29,30,x2 /* divide by 4 */
addi 5,x2,t1 /* cannot carry */
sh2add x2,t1,x2 /* multiply by 5 to get started */
b LREF(pos)
addc 0,0,x1
/* DIVISION BY 15 (use z = 2**32; a = 11111111) */
GSYM($$divI_15)
.export $$divI_15,millicode
comb,< x2,0,LREF(neg15)
copy 0,x1
addib,tr 1,x2,LREF(pos)+4
shd x1,x2,28,t1
LSYM(neg15)
b LREF(neg)
subi 1,x2,x2
GSYM($$divU_15)
.export $$divU_15,millicode
addi 1,x2,x2 /* this CAN overflow */
b LREF(pos)
addc 0,0,x1
/* DIVISION BY 17 (use z = 2**32; a = f0f0f0f) */
GSYM($$divI_17)
.export $$divI_17,millicode
comb,<,n x2,0,LREF(neg17)
addi 1,x2,x2 /* this cannot overflow */
shd 0,x2,28,t1 /* multiply by 0xf to get started */
shd x2,0,28,t2
sub t2,x2,x2
b LREF(pos_for_17)
subb t1,0,x1
LSYM(neg17)
subi 1,x2,x2 /* this cannot overflow */
shd 0,x2,28,t1 /* multiply by 0xf to get started */
shd x2,0,28,t2
sub t2,x2,x2
b LREF(neg_for_17)
subb t1,0,x1
GSYM($$divU_17)
.export $$divU_17,millicode
addi 1,x2,x2 /* this CAN overflow */
addc 0,0,x1
shd x1,x2,28,t1 /* multiply by 0xf to get started */
LSYM(u17)
shd x2,0,28,t2
sub t2,x2,x2
b LREF(pos_for_17)
subb t1,x1,x1
/* DIVISION BY DIVISORS OF FFFFFF, and powers of 2 times these
includes 7,9 and also 14
z = 2**24-1
r = z mod x = 0
so choose b = 0
Also, in order to divide by z = 2**24-1, we approximate by dividing
by (z+1) = 2**24 (which is easy), and then correcting.
(ax) = (z+1)q' + r
. = zq' + (q'+r)
So to compute (ax)/z, compute q' = (ax)/(z+1) and r = (ax) mod (z+1)
Then the true remainder of (ax)/z is (q'+r). Repeat the process
with this new remainder, adding the tentative quotients together,
until a tentative quotient is 0 (and then we are done). There is
one last correction to be done. It is possible that (q'+r) = z.
If so, then (q'+r)/(z+1) = 0 and it looks like we are done. But,
in fact, we need to add 1 more to the quotient. Now, it turns
out that this happens if and only if the original value x is
an exact multiple of y. So, to avoid a three instruction test at
the end, instead use 1 instruction to add 1 to x at the beginning. */
/* DIVISION BY 7 (use z = 2**24-1; a = 249249) */
GSYM($$divI_7)
.export $$divI_7,millicode
comb,<,n x2,0,LREF(neg7)
LSYM(7)
addi 1,x2,x2 /* cannot overflow */
shd 0,x2,29,x1
sh3add x2,x2,x2
addc x1,0,x1
LSYM(pos7)
shd x1,x2,26,t1
shd x2,0,26,t2
add x2,t2,x2
addc x1,t1,x1
shd x1,x2,20,t1
shd x2,0,20,t2
add x2,t2,x2
addc x1,t1,t1
/* computed <t1,x2>. Now divide it by (2**24 - 1) */
copy 0,x1
shd,= t1,x2,24,t1 /* tentative quotient */
LSYM(1)
addb,tr t1,x1,LREF(2) /* add to previous quotient */
extru x2,31,24,x2 /* new remainder (unadjusted) */
MILLIRETN
LSYM(2)
addb,tr t1,x2,LREF(1) /* adjust remainder */
extru,= x2,7,8,t1 /* new quotient */
LSYM(neg7)
subi 1,x2,x2 /* negate x2 and add 1 */
LSYM(8)
shd 0,x2,29,x1
sh3add x2,x2,x2
addc x1,0,x1
LSYM(neg7_shift)
shd x1,x2,26,t1
shd x2,0,26,t2
add x2,t2,x2
addc x1,t1,x1
shd x1,x2,20,t1
shd x2,0,20,t2
add x2,t2,x2
addc x1,t1,t1
/* computed <t1,x2>. Now divide it by (2**24 - 1) */
copy 0,x1
shd,= t1,x2,24,t1 /* tentative quotient */
LSYM(3)
addb,tr t1,x1,LREF(4) /* add to previous quotient */
extru x2,31,24,x2 /* new remainder (unadjusted) */
MILLIRET
sub 0,x1,x1 /* negate result */
LSYM(4)
addb,tr t1,x2,LREF(3) /* adjust remainder */
extru,= x2,7,8,t1 /* new quotient */
GSYM($$divU_7)
.export $$divU_7,millicode
addi 1,x2,x2 /* can carry */
addc 0,0,x1
shd x1,x2,29,t1
sh3add x2,x2,x2
b LREF(pos7)
addc t1,x1,x1
/* DIVISION BY 9 (use z = 2**24-1; a = 1c71c7) */
GSYM($$divI_9)
.export $$divI_9,millicode
comb,<,n x2,0,LREF(neg9)
addi 1,x2,x2 /* cannot overflow */
shd 0,x2,29,t1
shd x2,0,29,t2
sub t2,x2,x2
b LREF(pos7)
subb t1,0,x1
LSYM(neg9)
subi 1,x2,x2 /* negate and add 1 */
shd 0,x2,29,t1
shd x2,0,29,t2
sub t2,x2,x2
b LREF(neg7_shift)
subb t1,0,x1
GSYM($$divU_9)
.export $$divU_9,millicode
addi 1,x2,x2 /* can carry */
addc 0,0,x1
shd x1,x2,29,t1
shd x2,0,29,t2
sub t2,x2,x2
b LREF(pos7)
subb t1,x1,x1
/* DIVISION BY 14 (shift to divide by 2 then divide by 7) */
GSYM($$divI_14)
.export $$divI_14,millicode
comb,<,n x2,0,LREF(neg14)
GSYM($$divU_14)
.export $$divU_14,millicode
b LREF(7) /* go to 7 case */
extru x2,30,31,x2 /* divide by 2 */
LSYM(neg14)
subi 2,x2,x2 /* negate (and add 2) */
b LREF(8)
extru x2,30,31,x2 /* divide by 2 */
.exit
.procend
.end
#endif
#ifdef L_mulI
/* VERSION "@(#)$$mulI $ Revision: 12.4 $ $ Date: 94/03/17 17:18:51 $" */
/******************************************************************************
This routine is used on PA2.0 processors when gcc -mno-fpregs is used
ROUTINE: $$mulI
DESCRIPTION:
$$mulI multiplies two single word integers, giving a single
word result.
INPUT REGISTERS:
arg0 = Operand 1
arg1 = Operand 2
r31 == return pc
sr0 == return space when called externally
OUTPUT REGISTERS:
arg0 = undefined
arg1 = undefined
ret1 = result
OTHER REGISTERS AFFECTED:
r1 = undefined
SIDE EFFECTS:
Causes a trap under the following conditions: NONE
Changes memory at the following places: NONE
PERMISSIBLE CONTEXT:
Unwindable
Does not create a stack frame
Is usable for internal or external microcode
DISCUSSION:
Calls other millicode routines via mrp: NONE
Calls other millicode routines: NONE
***************************************************************************/
#define a0 %arg0
#define a1 %arg1
#define t0 %r1
#define r %ret1
#define a0__128a0 zdep a0,24,25,a0
#define a0__256a0 zdep a0,23,24,a0
#define a1_ne_0_b_l0 comb,<> a1,0,LREF(l0)
#define a1_ne_0_b_l1 comb,<> a1,0,LREF(l1)
#define a1_ne_0_b_l2 comb,<> a1,0,LREF(l2)
#define b_n_ret_t0 b,n LREF(ret_t0)
#define b_e_shift b LREF(e_shift)
#define b_e_t0ma0 b LREF(e_t0ma0)
#define b_e_t0 b LREF(e_t0)
#define b_e_t0a0 b LREF(e_t0a0)
#define b_e_t02a0 b LREF(e_t02a0)
#define b_e_t04a0 b LREF(e_t04a0)
#define b_e_2t0 b LREF(e_2t0)
#define b_e_2t0a0 b LREF(e_2t0a0)
#define b_e_2t04a0 b LREF(e2t04a0)
#define b_e_3t0 b LREF(e_3t0)
#define b_e_4t0 b LREF(e_4t0)
#define b_e_4t0a0 b LREF(e_4t0a0)
#define b_e_4t08a0 b LREF(e4t08a0)
#define b_e_5t0 b LREF(e_5t0)
#define b_e_8t0 b LREF(e_8t0)
#define b_e_8t0a0 b LREF(e_8t0a0)
#define r__r_a0 add r,a0,r
#define r__r_2a0 sh1add a0,r,r
#define r__r_4a0 sh2add a0,r,r
#define r__r_8a0 sh3add a0,r,r
#define r__r_t0 add r,t0,r
#define r__r_2t0 sh1add t0,r,r
#define r__r_4t0 sh2add t0,r,r
#define r__r_8t0 sh3add t0,r,r
#define t0__3a0 sh1add a0,a0,t0
#define t0__4a0 sh2add a0,0,t0
#define t0__5a0 sh2add a0,a0,t0
#define t0__8a0 sh3add a0,0,t0
#define t0__9a0 sh3add a0,a0,t0
#define t0__16a0 zdep a0,27,28,t0
#define t0__32a0 zdep a0,26,27,t0
#define t0__64a0 zdep a0,25,26,t0
#define t0__128a0 zdep a0,24,25,t0
#define t0__t0ma0 sub t0,a0,t0
#define t0__t0_a0 add t0,a0,t0
#define t0__t0_2a0 sh1add a0,t0,t0
#define t0__t0_4a0 sh2add a0,t0,t0
#define t0__t0_8a0 sh3add a0,t0,t0
#define t0__2t0_a0 sh1add t0,a0,t0
#define t0__3t0 sh1add t0,t0,t0
#define t0__4t0 sh2add t0,0,t0
#define t0__4t0_a0 sh2add t0,a0,t0
#define t0__5t0 sh2add t0,t0,t0
#define t0__8t0 sh3add t0,0,t0
#define t0__8t0_a0 sh3add t0,a0,t0
#define t0__9t0 sh3add t0,t0,t0
#define t0__16t0 zdep t0,27,28,t0
#define t0__32t0 zdep t0,26,27,t0
#define t0__256a0 zdep a0,23,24,t0
SUBSPA_MILLI
ATTR_MILLI
.align 16
.proc
.callinfo millicode
.export $$mulI,millicode
GSYM($$mulI)
combt,<<= a1,a0,LREF(l4) /* swap args if unsigned a1>a0 */
copy 0,r /* zero out the result */
xor a0,a1,a0 /* swap a0 & a1 using the */
xor a0,a1,a1 /* old xor trick */
xor a0,a1,a0
LSYM(l4)
combt,<= 0,a0,LREF(l3) /* if a0>=0 then proceed like unsigned */
zdep a1,30,8,t0 /* t0 = (a1&0xff)<<1 ********* */
sub,> 0,a1,t0 /* otherwise negate both and */
combt,<=,n a0,t0,LREF(l2) /* swap back if |a0|<|a1| */
sub 0,a0,a1
movb,tr,n t0,a0,LREF(l2) /* 10th inst. */
LSYM(l0) r__r_t0 /* add in this partial product */
LSYM(l1) a0__256a0 /* a0 <<= 8 ****************** */
LSYM(l2) zdep a1,30,8,t0 /* t0 = (a1&0xff)<<1 ********* */
LSYM(l3) blr t0,0 /* case on these 8 bits ****** */
extru a1,23,24,a1 /* a1 >>= 8 ****************** */
/*16 insts before this. */
/* a0 <<= 8 ************************** */
LSYM(x0) a1_ne_0_b_l2 ! a0__256a0 ! MILLIRETN ! nop
LSYM(x1) a1_ne_0_b_l1 ! r__r_a0 ! MILLIRETN ! nop
LSYM(x2) a1_ne_0_b_l1 ! r__r_2a0 ! MILLIRETN ! nop
LSYM(x3) a1_ne_0_b_l0 ! t0__3a0 ! MILLIRET ! r__r_t0
LSYM(x4) a1_ne_0_b_l1 ! r__r_4a0 ! MILLIRETN ! nop
LSYM(x5) a1_ne_0_b_l0 ! t0__5a0 ! MILLIRET ! r__r_t0
LSYM(x6) t0__3a0 ! a1_ne_0_b_l1 ! r__r_2t0 ! MILLIRETN
LSYM(x7) t0__3a0 ! a1_ne_0_b_l0 ! r__r_4a0 ! b_n_ret_t0
LSYM(x8) a1_ne_0_b_l1 ! r__r_8a0 ! MILLIRETN ! nop
LSYM(x9) a1_ne_0_b_l0 ! t0__9a0 ! MILLIRET ! r__r_t0
LSYM(x10) t0__5a0 ! a1_ne_0_b_l1 ! r__r_2t0 ! MILLIRETN
LSYM(x11) t0__3a0 ! a1_ne_0_b_l0 ! r__r_8a0 ! b_n_ret_t0
LSYM(x12) t0__3a0 ! a1_ne_0_b_l1 ! r__r_4t0 ! MILLIRETN
LSYM(x13) t0__5a0 ! a1_ne_0_b_l0 ! r__r_8a0 ! b_n_ret_t0
LSYM(x14) t0__3a0 ! t0__2t0_a0 ! b_e_shift ! r__r_2t0
LSYM(x15) t0__5a0 ! a1_ne_0_b_l0 ! t0__3t0 ! b_n_ret_t0
LSYM(x16) t0__16a0 ! a1_ne_0_b_l1 ! r__r_t0 ! MILLIRETN
LSYM(x17) t0__9a0 ! a1_ne_0_b_l0 ! t0__t0_8a0 ! b_n_ret_t0
LSYM(x18) t0__9a0 ! a1_ne_0_b_l1 ! r__r_2t0 ! MILLIRETN
LSYM(x19) t0__9a0 ! a1_ne_0_b_l0 ! t0__2t0_a0 ! b_n_ret_t0
LSYM(x20) t0__5a0 ! a1_ne_0_b_l1 ! r__r_4t0 ! MILLIRETN
LSYM(x21) t0__5a0 ! a1_ne_0_b_l0 ! t0__4t0_a0 ! b_n_ret_t0
LSYM(x22) t0__5a0 ! t0__2t0_a0 ! b_e_shift ! r__r_2t0
LSYM(x23) t0__5a0 ! t0__2t0_a0 ! b_e_t0 ! t0__2t0_a0
LSYM(x24) t0__3a0 ! a1_ne_0_b_l1 ! r__r_8t0 ! MILLIRETN
LSYM(x25) t0__5a0 ! a1_ne_0_b_l0 ! t0__5t0 ! b_n_ret_t0
LSYM(x26) t0__3a0 ! t0__4t0_a0 ! b_e_shift ! r__r_2t0
LSYM(x27) t0__3a0 ! a1_ne_0_b_l0 ! t0__9t0 ! b_n_ret_t0
LSYM(x28) t0__3a0 ! t0__2t0_a0 ! b_e_shift ! r__r_4t0
LSYM(x29) t0__3a0 ! t0__2t0_a0 ! b_e_t0 ! t0__4t0_a0
LSYM(x30) t0__5a0 ! t0__3t0 ! b_e_shift ! r__r_2t0
LSYM(x31) t0__32a0 ! a1_ne_0_b_l0 ! t0__t0ma0 ! b_n_ret_t0
LSYM(x32) t0__32a0 ! a1_ne_0_b_l1 ! r__r_t0 ! MILLIRETN
LSYM(x33) t0__8a0 ! a1_ne_0_b_l0 ! t0__4t0_a0 ! b_n_ret_t0
LSYM(x34) t0__16a0 ! t0__t0_a0 ! b_e_shift ! r__r_2t0
LSYM(x35) t0__9a0 ! t0__3t0 ! b_e_t0 ! t0__t0_8a0
LSYM(x36) t0__9a0 ! a1_ne_0_b_l1 ! r__r_4t0 ! MILLIRETN
LSYM(x37) t0__9a0 ! a1_ne_0_b_l0 ! t0__4t0_a0 ! b_n_ret_t0
LSYM(x38) t0__9a0 ! t0__2t0_a0 ! b_e_shift ! r__r_2t0
LSYM(x39) t0__9a0 ! t0__2t0_a0 ! b_e_t0 ! t0__2t0_a0
LSYM(x40) t0__5a0 ! a1_ne_0_b_l1 ! r__r_8t0 ! MILLIRETN
LSYM(x41) t0__5a0 ! a1_ne_0_b_l0 ! t0__8t0_a0 ! b_n_ret_t0
LSYM(x42) t0__5a0 ! t0__4t0_a0 ! b_e_shift ! r__r_2t0
LSYM(x43) t0__5a0 ! t0__4t0_a0 ! b_e_t0 ! t0__2t0_a0
LSYM(x44) t0__5a0 ! t0__2t0_a0 ! b_e_shift ! r__r_4t0
LSYM(x45) t0__9a0 ! a1_ne_0_b_l0 ! t0__5t0 ! b_n_ret_t0
LSYM(x46) t0__9a0 ! t0__5t0 ! b_e_t0 ! t0__t0_a0
LSYM(x47) t0__9a0 ! t0__5t0 ! b_e_t0 ! t0__t0_2a0
LSYM(x48) t0__3a0 ! a1_ne_0_b_l0 ! t0__16t0 ! b_n_ret_t0
LSYM(x49) t0__9a0 ! t0__5t0 ! b_e_t0 ! t0__t0_4a0
LSYM(x50) t0__5a0 ! t0__5t0 ! b_e_shift ! r__r_2t0
LSYM(x51) t0__9a0 ! t0__t0_8a0 ! b_e_t0 ! t0__3t0
LSYM(x52) t0__3a0 ! t0__4t0_a0 ! b_e_shift ! r__r_4t0
LSYM(x53) t0__3a0 ! t0__4t0_a0 ! b_e_t0 ! t0__4t0_a0
LSYM(x54) t0__9a0 ! t0__3t0 ! b_e_shift ! r__r_2t0
LSYM(x55) t0__9a0 ! t0__3t0 ! b_e_t0 ! t0__2t0_a0
LSYM(x56) t0__3a0 ! t0__2t0_a0 ! b_e_shift ! r__r_8t0
LSYM(x57) t0__9a0 ! t0__2t0_a0 ! b_e_t0 ! t0__3t0
LSYM(x58) t0__3a0 ! t0__2t0_a0 ! b_e_2t0 ! t0__4t0_a0
LSYM(x59) t0__9a0 ! t0__2t0_a0 ! b_e_t02a0 ! t0__3t0
LSYM(x60) t0__5a0 ! t0__3t0 ! b_e_shift ! r__r_4t0
LSYM(x61) t0__5a0 ! t0__3t0 ! b_e_t0 ! t0__4t0_a0
LSYM(x62) t0__32a0 ! t0__t0ma0 ! b_e_shift ! r__r_2t0
LSYM(x63) t0__64a0 ! a1_ne_0_b_l0 ! t0__t0ma0 ! b_n_ret_t0
LSYM(x64) t0__64a0 ! a1_ne_0_b_l1 ! r__r_t0 ! MILLIRETN
LSYM(x65) t0__8a0 ! a1_ne_0_b_l0 ! t0__8t0_a0 ! b_n_ret_t0
LSYM(x66) t0__32a0 ! t0__t0_a0 ! b_e_shift ! r__r_2t0
LSYM(x67) t0__8a0 ! t0__4t0_a0 ! b_e_t0 ! t0__2t0_a0
LSYM(x68) t0__8a0 ! t0__2t0_a0 ! b_e_shift ! r__r_4t0
LSYM(x69) t0__8a0 ! t0__2t0_a0 ! b_e_t0 ! t0__4t0_a0
LSYM(x70) t0__64a0 ! t0__t0_4a0 ! b_e_t0 ! t0__t0_2a0
LSYM(x71) t0__9a0 ! t0__8t0 ! b_e_t0 ! t0__t0ma0
LSYM(x72) t0__9a0 ! a1_ne_0_b_l1 ! r__r_8t0 ! MILLIRETN
LSYM(x73) t0__9a0 ! t0__8t0_a0 ! b_e_shift ! r__r_t0
LSYM(x74) t0__9a0 ! t0__4t0_a0 ! b_e_shift ! r__r_2t0
LSYM(x75) t0__9a0 ! t0__4t0_a0 ! b_e_t0 ! t0__2t0_a0
LSYM(x76) t0__9a0 ! t0__2t0_a0 ! b_e_shift ! r__r_4t0
LSYM(x77) t0__9a0 ! t0__2t0_a0 ! b_e_t0 ! t0__4t0_a0
LSYM(x78) t0__9a0 ! t0__2t0_a0 ! b_e_2t0 ! t0__2t0_a0
LSYM(x79) t0__16a0 ! t0__5t0 ! b_e_t0 ! t0__t0ma0
LSYM(x80) t0__16a0 ! t0__5t0 ! b_e_shift ! r__r_t0
LSYM(x81) t0__9a0 ! t0__9t0 ! b_e_shift ! r__r_t0
LSYM(x82) t0__5a0 ! t0__8t0_a0 ! b_e_shift ! r__r_2t0
LSYM(x83) t0__5a0 ! t0__8t0_a0 ! b_e_t0 ! t0__2t0_a0
LSYM(x84) t0__5a0 ! t0__4t0_a0 ! b_e_shift ! r__r_4t0
LSYM(x85) t0__8a0 ! t0__2t0_a0 ! b_e_t0 ! t0__5t0
LSYM(x86) t0__5a0 ! t0__4t0_a0 ! b_e_2t0 ! t0__2t0_a0
LSYM(x87) t0__9a0 ! t0__9t0 ! b_e_t02a0 ! t0__t0_4a0
LSYM(x88) t0__5a0 ! t0__2t0_a0 ! b_e_shift ! r__r_8t0
LSYM(x89) t0__5a0 ! t0__2t0_a0 ! b_e_t0 ! t0__8t0_a0
LSYM(x90) t0__9a0 ! t0__5t0 ! b_e_shift ! r__r_2t0
LSYM(x91) t0__9a0 ! t0__5t0 ! b_e_t0 ! t0__2t0_a0
LSYM(x92) t0__5a0 ! t0__2t0_a0 ! b_e_4t0 ! t0__2t0_a0
LSYM(x93) t0__32a0 ! t0__t0ma0 ! b_e_t0 ! t0__3t0
LSYM(x94) t0__9a0 ! t0__5t0 ! b_e_2t0 ! t0__t0_2a0
LSYM(x95) t0__9a0 ! t0__2t0_a0 ! b_e_t0 ! t0__5t0
LSYM(x96) t0__8a0 ! t0__3t0 ! b_e_shift ! r__r_4t0
LSYM(x97) t0__8a0 ! t0__3t0 ! b_e_t0 ! t0__4t0_a0
LSYM(x98) t0__32a0 ! t0__3t0 ! b_e_t0 ! t0__t0_2a0
LSYM(x99) t0__8a0 ! t0__4t0_a0 ! b_e_t0 ! t0__3t0
LSYM(x100) t0__5a0 ! t0__5t0 ! b_e_shift ! r__r_4t0
LSYM(x101) t0__5a0 ! t0__5t0 ! b_e_t0 ! t0__4t0_a0
LSYM(x102) t0__32a0 ! t0__t0_2a0 ! b_e_t0 ! t0__3t0
LSYM(x103) t0__5a0 ! t0__5t0 ! b_e_t02a0 ! t0__4t0_a0
LSYM(x104) t0__3a0 ! t0__4t0_a0 ! b_e_shift ! r__r_8t0
LSYM(x105) t0__5a0 ! t0__4t0_a0 ! b_e_t0 ! t0__5t0
LSYM(x106) t0__3a0 ! t0__4t0_a0 ! b_e_2t0 ! t0__4t0_a0
LSYM(x107) t0__9a0 ! t0__t0_4a0 ! b_e_t02a0 ! t0__8t0_a0
LSYM(x108) t0__9a0 ! t0__3t0 ! b_e_shift ! r__r_4t0
LSYM(x109) t0__9a0 ! t0__3t0 ! b_e_t0 ! t0__4t0_a0
LSYM(x110) t0__9a0 ! t0__3t0 ! b_e_2t0 ! t0__2t0_a0
LSYM(x111) t0__9a0 ! t0__4t0_a0 ! b_e_t0 ! t0__3t0
LSYM(x112) t0__3a0 ! t0__2t0_a0 ! b_e_t0 ! t0__16t0
LSYM(x113) t0__9a0 ! t0__4t0_a0 ! b_e_t02a0 ! t0__3t0
LSYM(x114) t0__9a0 ! t0__2t0_a0 ! b_e_2t0 ! t0__3t0
LSYM(x115) t0__9a0 ! t0__2t0_a0 ! b_e_2t0a0 ! t0__3t0
LSYM(x116) t0__3a0 ! t0__2t0_a0 ! b_e_4t0 ! t0__4t0_a0
LSYM(x117) t0__3a0 ! t0__4t0_a0 ! b_e_t0 ! t0__9t0
LSYM(x118) t0__3a0 ! t0__4t0_a0 ! b_e_t0a0 ! t0__9t0
LSYM(x119) t0__3a0 ! t0__4t0_a0 ! b_e_t02a0 ! t0__9t0
LSYM(x120) t0__5a0 ! t0__3t0 ! b_e_shift ! r__r_8t0
LSYM(x121) t0__5a0 ! t0__3t0 ! b_e_t0 ! t0__8t0_a0
LSYM(x122) t0__5a0 ! t0__3t0 ! b_e_2t0 ! t0__4t0_a0
LSYM(x123) t0__5a0 ! t0__8t0_a0 ! b_e_t0 ! t0__3t0
LSYM(x124) t0__32a0 ! t0__t0ma0 ! b_e_shift ! r__r_4t0
LSYM(x125) t0__5a0 ! t0__5t0 ! b_e_t0 ! t0__5t0
LSYM(x126) t0__64a0 ! t0__t0ma0 ! b_e_shift ! r__r_2t0
LSYM(x127) t0__128a0 ! a1_ne_0_b_l0 ! t0__t0ma0 ! b_n_ret_t0
LSYM(x128) t0__128a0 ! a1_ne_0_b_l1 ! r__r_t0 ! MILLIRETN
LSYM(x129) t0__128a0 ! a1_ne_0_b_l0 ! t0__t0_a0 ! b_n_ret_t0
LSYM(x130) t0__64a0 ! t0__t0_a0 ! b_e_shift ! r__r_2t0
LSYM(x131) t0__8a0 ! t0__8t0_a0 ! b_e_t0 ! t0__2t0_a0
LSYM(x132) t0__8a0 ! t0__4t0_a0 ! b_e_shift ! r__r_4t0
LSYM(x133) t0__8a0 ! t0__4t0_a0 ! b_e_t0 ! t0__4t0_a0
LSYM(x134) t0__8a0 ! t0__4t0_a0 ! b_e_2t0 ! t0__2t0_a0
LSYM(x135) t0__9a0 ! t0__5t0 ! b_e_t0 ! t0__3t0
LSYM(x136) t0__8a0 ! t0__2t0_a0 ! b_e_shift ! r__r_8t0
LSYM(x137) t0__8a0 ! t0__2t0_a0 ! b_e_t0 ! t0__8t0_a0
LSYM(x138) t0__8a0 ! t0__2t0_a0 ! b_e_2t0 ! t0__4t0_a0
LSYM(x139) t0__8a0 ! t0__2t0_a0 ! b_e_2t0a0 ! t0__4t0_a0
LSYM(x140) t0__3a0 ! t0__2t0_a0 ! b_e_4t0 ! t0__5t0
LSYM(x141) t0__8a0 ! t0__2t0_a0 ! b_e_4t0a0 ! t0__2t0_a0
LSYM(x142) t0__9a0 ! t0__8t0 ! b_e_2t0 ! t0__t0ma0
LSYM(x143) t0__16a0 ! t0__9t0 ! b_e_t0 ! t0__t0ma0
LSYM(x144) t0__9a0 ! t0__8t0 ! b_e_shift ! r__r_2t0
LSYM(x145) t0__9a0 ! t0__8t0 ! b_e_t0 ! t0__2t0_a0
LSYM(x146) t0__9a0 ! t0__8t0_a0 ! b_e_shift ! r__r_2t0
LSYM(x147) t0__9a0 ! t0__8t0_a0 ! b_e_t0 ! t0__2t0_a0
LSYM(x148) t0__9a0 ! t0__4t0_a0 ! b_e_shift ! r__r_4t0
LSYM(x149) t0__9a0 ! t0__4t0_a0 ! b_e_t0 ! t0__4t0_a0
LSYM(x150) t0__9a0 ! t0__4t0_a0 ! b_e_2t0 ! t0__2t0_a0
LSYM(x151) t0__9a0 ! t0__4t0_a0 ! b_e_2t0a0 ! t0__2t0_a0
LSYM(x152) t0__9a0 ! t0__2t0_a0 ! b_e_shift ! r__r_8t0
LSYM(x153) t0__9a0 ! t0__2t0_a0 ! b_e_t0 ! t0__8t0_a0
LSYM(x154) t0__9a0 ! t0__2t0_a0 ! b_e_2t0 ! t0__4t0_a0
LSYM(x155) t0__32a0 ! t0__t0ma0 ! b_e_t0 ! t0__5t0
LSYM(x156) t0__9a0 ! t0__2t0_a0 ! b_e_4t0 ! t0__2t0_a0
LSYM(x157) t0__32a0 ! t0__t0ma0 ! b_e_t02a0 ! t0__5t0
LSYM(x158) t0__16a0 ! t0__5t0 ! b_e_2t0 ! t0__t0ma0
LSYM(x159) t0__32a0 ! t0__5t0 ! b_e_t0 ! t0__t0ma0
LSYM(x160) t0__5a0 ! t0__4t0 ! b_e_shift ! r__r_8t0
LSYM(x161) t0__8a0 ! t0__5t0 ! b_e_t0 ! t0__4t0_a0
LSYM(x162) t0__9a0 ! t0__9t0 ! b_e_shift ! r__r_2t0
LSYM(x163) t0__9a0 ! t0__9t0 ! b_e_t0 ! t0__2t0_a0
LSYM(x164) t0__5a0 ! t0__8t0_a0 ! b_e_shift ! r__r_4t0
LSYM(x165) t0__8a0 ! t0__4t0_a0 ! b_e_t0 ! t0__5t0
LSYM(x166) t0__5a0 ! t0__8t0_a0 ! b_e_2t0 ! t0__2t0_a0
LSYM(x167) t0__5a0 ! t0__8t0_a0 ! b_e_2t0a0 ! t0__2t0_a0
LSYM(x168) t0__5a0 ! t0__4t0_a0 ! b_e_shift ! r__r_8t0
LSYM(x169) t0__5a0 ! t0__4t0_a0 ! b_e_t0 ! t0__8t0_a0
LSYM(x170) t0__32a0 ! t0__t0_2a0 ! b_e_t0 ! t0__5t0
LSYM(x171) t0__9a0 ! t0__2t0_a0 ! b_e_t0 ! t0__9t0
LSYM(x172) t0__5a0 ! t0__4t0_a0 ! b_e_4t0 ! t0__2t0_a0
LSYM(x173) t0__9a0 ! t0__2t0_a0 ! b_e_t02a0 ! t0__9t0
LSYM(x174) t0__32a0 ! t0__t0_2a0 ! b_e_t04a0 ! t0__5t0
LSYM(x175) t0__8a0 ! t0__2t0_a0 ! b_e_5t0 ! t0__2t0_a0
LSYM(x176) t0__5a0 ! t0__4t0_a0 ! b_e_8t0 ! t0__t0_a0
LSYM(x177) t0__5a0 ! t0__4t0_a0 ! b_e_8t0a0 ! t0__t0_a0
LSYM(x178) t0__5a0 ! t0__2t0_a0 ! b_e_2t0 ! t0__8t0_a0
LSYM(x179) t0__5a0 ! t0__2t0_a0 ! b_e_2t0a0 ! t0__8t0_a0
LSYM(x180) t0__9a0 ! t0__5t0 ! b_e_shift ! r__r_4t0
LSYM(x181) t0__9a0 ! t0__5t0 ! b_e_t0 ! t0__4t0_a0
LSYM(x182) t0__9a0 ! t0__5t0 ! b_e_2t0 ! t0__2t0_a0
LSYM(x183) t0__9a0 ! t0__5t0 ! b_e_2t0a0 ! t0__2t0_a0
LSYM(x184) t0__5a0 ! t0__9t0 ! b_e_4t0 ! t0__t0_a0
LSYM(x185) t0__9a0 ! t0__4t0_a0 ! b_e_t0 ! t0__5t0
LSYM(x186) t0__32a0 ! t0__t0ma0 ! b_e_2t0 ! t0__3t0
LSYM(x187) t0__9a0 ! t0__4t0_a0 ! b_e_t02a0 ! t0__5t0
LSYM(x188) t0__9a0 ! t0__5t0 ! b_e_4t0 ! t0__t0_2a0
LSYM(x189) t0__5a0 ! t0__4t0_a0 ! b_e_t0 ! t0__9t0
LSYM(x190) t0__9a0 ! t0__2t0_a0 ! b_e_2t0 ! t0__5t0
LSYM(x191) t0__64a0 ! t0__3t0 ! b_e_t0 ! t0__t0ma0
LSYM(x192) t0__8a0 ! t0__3t0 ! b_e_shift ! r__r_8t0
LSYM(x193) t0__8a0 ! t0__3t0 ! b_e_t0 ! t0__8t0_a0
LSYM(x194) t0__8a0 ! t0__3t0 ! b_e_2t0 ! t0__4t0_a0
LSYM(x195) t0__8a0 ! t0__8t0_a0 ! b_e_t0 ! t0__3t0
LSYM(x196) t0__8a0 ! t0__3t0 ! b_e_4t0 ! t0__2t0_a0
LSYM(x197) t0__8a0 ! t0__3t0 ! b_e_4t0a0 ! t0__2t0_a0
LSYM(x198) t0__64a0 ! t0__t0_2a0 ! b_e_t0 ! t0__3t0
LSYM(x199) t0__8a0 ! t0__4t0_a0 ! b_e_2t0a0 ! t0__3t0
LSYM(x200) t0__5a0 ! t0__5t0 ! b_e_shift ! r__r_8t0
LSYM(x201) t0__5a0 ! t0__5t0 ! b_e_t0 ! t0__8t0_a0
LSYM(x202) t0__5a0 ! t0__5t0 ! b_e_2t0 ! t0__4t0_a0
LSYM(x203) t0__5a0 ! t0__5t0 ! b_e_2t0a0 ! t0__4t0_a0
LSYM(x204) t0__8a0 ! t0__2t0_a0 ! b_e_4t0 ! t0__3t0
LSYM(x205) t0__5a0 ! t0__8t0_a0 ! b_e_t0 ! t0__5t0
LSYM(x206) t0__64a0 ! t0__t0_4a0 ! b_e_t02a0 ! t0__3t0
LSYM(x207) t0__8a0 ! t0__2t0_a0 ! b_e_3t0 ! t0__4t0_a0
LSYM(x208) t0__5a0 ! t0__5t0 ! b_e_8t0 ! t0__t0_a0
LSYM(x209) t0__5a0 ! t0__5t0 ! b_e_8t0a0 ! t0__t0_a0
LSYM(x210) t0__5a0 ! t0__4t0_a0 ! b_e_2t0 ! t0__5t0
LSYM(x211) t0__5a0 ! t0__4t0_a0 ! b_e_2t0a0 ! t0__5t0
LSYM(x212) t0__3a0 ! t0__4t0_a0 ! b_e_4t0 ! t0__4t0_a0
LSYM(x213) t0__3a0 ! t0__4t0_a0 ! b_e_4t0a0 ! t0__4t0_a0
LSYM(x214) t0__9a0 ! t0__t0_4a0 ! b_e_2t04a0 ! t0__8t0_a0
LSYM(x215) t0__5a0 ! t0__4t0_a0 ! b_e_5t0 ! t0__2t0_a0
LSYM(x216) t0__9a0 ! t0__3t0 ! b_e_shift ! r__r_8t0
LSYM(x217) t0__9a0 ! t0__3t0 ! b_e_t0 ! t0__8t0_a0
LSYM(x218) t0__9a0 ! t0__3t0 ! b_e_2t0 ! t0__4t0_a0
LSYM(x219) t0__9a0 ! t0__8t0_a0 ! b_e_t0 ! t0__3t0
LSYM(x220) t0__3a0 ! t0__9t0 ! b_e_4t0 ! t0__2t0_a0
LSYM(x221) t0__3a0 ! t0__9t0 ! b_e_4t0a0 ! t0__2t0_a0
LSYM(x222) t0__9a0 ! t0__4t0_a0 ! b_e_2t0 ! t0__3t0
LSYM(x223) t0__9a0 ! t0__4t0_a0 ! b_e_2t0a0 ! t0__3t0
LSYM(x224) t0__9a0 ! t0__3t0 ! b_e_8t0 ! t0__t0_a0
LSYM(x225) t0__9a0 ! t0__5t0 ! b_e_t0 ! t0__5t0
LSYM(x226) t0__3a0 ! t0__2t0_a0 ! b_e_t02a0 ! t0__32t0
LSYM(x227) t0__9a0 ! t0__5t0 ! b_e_t02a0 ! t0__5t0
LSYM(x228) t0__9a0 ! t0__2t0_a0 ! b_e_4t0 ! t0__3t0
LSYM(x229) t0__9a0 ! t0__2t0_a0 ! b_e_4t0a0 ! t0__3t0
LSYM(x230) t0__9a0 ! t0__5t0 ! b_e_5t0 ! t0__t0_a0
LSYM(x231) t0__9a0 ! t0__2t0_a0 ! b_e_3t0 ! t0__4t0_a0
LSYM(x232) t0__3a0 ! t0__2t0_a0 ! b_e_8t0 ! t0__4t0_a0
LSYM(x233) t0__3a0 ! t0__2t0_a0 ! b_e_8t0a0 ! t0__4t0_a0
LSYM(x234) t0__3a0 ! t0__4t0_a0 ! b_e_2t0 ! t0__9t0
LSYM(x235) t0__3a0 ! t0__4t0_a0 ! b_e_2t0a0 ! t0__9t0
LSYM(x236) t0__9a0 ! t0__2t0_a0 ! b_e_4t08a0 ! t0__3t0
LSYM(x237) t0__16a0 ! t0__5t0 ! b_e_3t0 ! t0__t0ma0
LSYM(x238) t0__3a0 ! t0__4t0_a0 ! b_e_2t04a0 ! t0__9t0
LSYM(x239) t0__16a0 ! t0__5t0 ! b_e_t0ma0 ! t0__3t0
LSYM(x240) t0__9a0 ! t0__t0_a0 ! b_e_8t0 ! t0__3t0
LSYM(x241) t0__9a0 ! t0__t0_a0 ! b_e_8t0a0 ! t0__3t0
LSYM(x242) t0__5a0 ! t0__3t0 ! b_e_2t0 ! t0__8t0_a0
LSYM(x243) t0__9a0 ! t0__9t0 ! b_e_t0 ! t0__3t0
LSYM(x244) t0__5a0 ! t0__3t0 ! b_e_4t0 ! t0__4t0_a0
LSYM(x245) t0__8a0 ! t0__3t0 ! b_e_5t0 ! t0__2t0_a0
LSYM(x246) t0__5a0 ! t0__8t0_a0 ! b_e_2t0 ! t0__3t0
LSYM(x247) t0__5a0 ! t0__8t0_a0 ! b_e_2t0a0 ! t0__3t0
LSYM(x248) t0__32a0 ! t0__t0ma0 ! b_e_shift ! r__r_8t0
LSYM(x249) t0__32a0 ! t0__t0ma0 ! b_e_t0 ! t0__8t0_a0
LSYM(x250) t0__5a0 ! t0__5t0 ! b_e_2t0 ! t0__5t0
LSYM(x251) t0__5a0 ! t0__5t0 ! b_e_2t0a0 ! t0__5t0
LSYM(x252) t0__64a0 ! t0__t0ma0 ! b_e_shift ! r__r_4t0
LSYM(x253) t0__64a0 ! t0__t0ma0 ! b_e_t0 ! t0__4t0_a0
LSYM(x254) t0__128a0 ! t0__t0ma0 ! b_e_shift ! r__r_2t0
LSYM(x255) t0__256a0 ! a1_ne_0_b_l0 ! t0__t0ma0 ! b_n_ret_t0
/*1040 insts before this. */
LSYM(ret_t0) MILLIRET
LSYM(e_t0) r__r_t0
LSYM(e_shift) a1_ne_0_b_l2
a0__256a0 /* a0 <<= 8 *********** */
MILLIRETN
LSYM(e_t0ma0) a1_ne_0_b_l0
t0__t0ma0
MILLIRET
r__r_t0
LSYM(e_t0a0) a1_ne_0_b_l0
t0__t0_a0
MILLIRET
r__r_t0
LSYM(e_t02a0) a1_ne_0_b_l0
t0__t0_2a0
MILLIRET
r__r_t0
LSYM(e_t04a0) a1_ne_0_b_l0
t0__t0_4a0
MILLIRET
r__r_t0
LSYM(e_2t0) a1_ne_0_b_l1
r__r_2t0
MILLIRETN
LSYM(e_2t0a0) a1_ne_0_b_l0
t0__2t0_a0
MILLIRET
r__r_t0
LSYM(e2t04a0) t0__t0_2a0
a1_ne_0_b_l1
r__r_2t0
MILLIRETN
LSYM(e_3t0) a1_ne_0_b_l0
t0__3t0
MILLIRET
r__r_t0
LSYM(e_4t0) a1_ne_0_b_l1
r__r_4t0
MILLIRETN
LSYM(e_4t0a0) a1_ne_0_b_l0
t0__4t0_a0
MILLIRET
r__r_t0
LSYM(e4t08a0) t0__t0_2a0
a1_ne_0_b_l1
r__r_4t0
MILLIRETN
LSYM(e_5t0) a1_ne_0_b_l0
t0__5t0
MILLIRET
r__r_t0
LSYM(e_8t0) a1_ne_0_b_l1
r__r_8t0
MILLIRETN
LSYM(e_8t0a0) a1_ne_0_b_l0
t0__8t0_a0
MILLIRET
r__r_t0
.procend
.end
#endif
|