1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
|
/* IRA allocation based on graph coloring.
Copyright (C) 2006, 2007, 2008
Free Software Foundation, Inc.
Contributed by Vladimir Makarov <vmakarov@redhat.com>.
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.
You should have received a copy of the GNU General Public License
along with GCC; see the file COPYING3. If not see
<http://www.gnu.org/licenses/>. */
#include "config.h"
#include "system.h"
#include "coretypes.h"
#include "tm.h"
#include "rtl.h"
#include "tm_p.h"
#include "target.h"
#include "regs.h"
#include "flags.h"
#include "sbitmap.h"
#include "bitmap.h"
#include "hard-reg-set.h"
#include "basic-block.h"
#include "expr.h"
#include "toplev.h"
#include "reload.h"
#include "params.h"
#include "df.h"
#include "splay-tree.h"
#include "ira-int.h"
/* This file contains code for regional graph coloring, spill/restore
code placement optimization, and code helping the reload pass to do
a better job. */
/* Bitmap of allocnos which should be colored. */
static bitmap coloring_allocno_bitmap;
/* Bitmap of allocnos which should be taken into account during
coloring. In general case it contains allocnos from
coloring_allocno_bitmap plus other already colored conflicting
allocnos. */
static bitmap consideration_allocno_bitmap;
/* TRUE if we coalesced some allocnos. In other words, if we got
loops formed by members first_coalesced_allocno and
next_coalesced_allocno containing more one allocno. */
static bool allocno_coalesced_p;
/* Bitmap used to prevent a repeated allocno processing because of
coalescing. */
static bitmap processed_coalesced_allocno_bitmap;
/* All allocnos sorted according their priorities. */
static ira_allocno_t *sorted_allocnos;
/* Vec representing the stack of allocnos used during coloring. */
static VEC(ira_allocno_t,heap) *allocno_stack_vec;
/* Vec representing conflict allocnos used during assigning. */
static VEC(ira_allocno_t,heap) *conflict_allocno_vec;
/* Array used to choose an allocno for spilling. */
static ira_allocno_t *allocnos_for_spilling;
/* Pool for splay tree nodes. */
static alloc_pool splay_tree_node_pool;
/* When an allocno is removed from the splay tree, it is put in the
following vector for subsequent inserting it into the splay tree
after putting all colorable allocnos onto the stack. The allocno
could be removed from and inserted to the splay tree every time
when its spilling priority is changed but such solution would be
more costly although simpler. */
static VEC(ira_allocno_t,heap) *removed_splay_allocno_vec;
/* This page contains functions used to choose hard registers for
allocnos. */
/* Array whose element value is TRUE if the corresponding hard
register was already allocated for an allocno. */
static bool allocated_hardreg_p[FIRST_PSEUDO_REGISTER];
/* Array used to check already processed allocnos during the current
update_copy_costs call. */
static int *allocno_update_cost_check;
/* The current value of update_copy_cost call count. */
static int update_cost_check;
/* Allocate and initialize data necessary for function
update_copy_costs. */
static void
initiate_cost_update (void)
{
allocno_update_cost_check
= (int *) ira_allocate (ira_allocnos_num * sizeof (int));
memset (allocno_update_cost_check, 0, ira_allocnos_num * sizeof (int));
update_cost_check = 0;
}
/* Deallocate data used by function update_copy_costs. */
static void
finish_cost_update (void)
{
ira_free (allocno_update_cost_check);
}
/* When we traverse allocnos to update hard register costs, the cost
divisor will be multiplied by the following macro value for each
hop from given allocno to directly connected allocnos. */
#define COST_HOP_DIVISOR 4
/* This recursive function updates costs (decrease if DECR_P) of the
unassigned allocnos connected by copies with ALLOCNO. This update
increases chances to remove some copies. Copy cost is proportional
the copy frequency divided by DIVISOR. */
static void
update_copy_costs_1 (ira_allocno_t allocno, int hard_regno,
bool decr_p, int divisor)
{
int i, cost, update_cost;
enum machine_mode mode;
enum reg_class rclass, cover_class;
ira_allocno_t another_allocno;
ira_copy_t cp, next_cp;
cover_class = ALLOCNO_COVER_CLASS (allocno);
if (cover_class == NO_REGS)
return;
if (allocno_update_cost_check[ALLOCNO_NUM (allocno)] == update_cost_check)
return;
allocno_update_cost_check[ALLOCNO_NUM (allocno)] = update_cost_check;
ira_assert (hard_regno >= 0);
i = ira_class_hard_reg_index[cover_class][hard_regno];
ira_assert (i >= 0);
rclass = REGNO_REG_CLASS (hard_regno);
mode = ALLOCNO_MODE (allocno);
for (cp = ALLOCNO_COPIES (allocno); cp != NULL; cp = next_cp)
{
if (cp->first == allocno)
{
next_cp = cp->next_first_allocno_copy;
another_allocno = cp->second;
}
else if (cp->second == allocno)
{
next_cp = cp->next_second_allocno_copy;
another_allocno = cp->first;
}
else
gcc_unreachable ();
if (cover_class
!= ALLOCNO_COVER_CLASS (another_allocno)
|| ALLOCNO_ASSIGNED_P (another_allocno))
continue;
cost = (cp->second == allocno
? ira_register_move_cost[mode][rclass]
[ALLOCNO_COVER_CLASS (another_allocno)]
: ira_register_move_cost[mode]
[ALLOCNO_COVER_CLASS (another_allocno)][rclass]);
if (decr_p)
cost = -cost;
ira_allocate_and_set_or_copy_costs
(&ALLOCNO_UPDATED_HARD_REG_COSTS (another_allocno), cover_class,
ALLOCNO_COVER_CLASS_COST (another_allocno),
ALLOCNO_HARD_REG_COSTS (another_allocno));
ira_allocate_and_set_or_copy_costs
(&ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (another_allocno),
cover_class, 0,
ALLOCNO_CONFLICT_HARD_REG_COSTS (another_allocno));
update_cost = cp->freq * cost / divisor;
ALLOCNO_UPDATED_HARD_REG_COSTS (another_allocno)[i] += update_cost;
ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (another_allocno)[i]
+= update_cost;
if (update_cost != 0)
update_copy_costs_1 (another_allocno, hard_regno,
decr_p, divisor * COST_HOP_DIVISOR);
}
}
/* Update the cost of allocnos to increase chances to remove some
copies as the result of subsequent assignment. */
static void
update_copy_costs (ira_allocno_t allocno, bool decr_p)
{
update_cost_check++;
update_copy_costs_1 (allocno, ALLOCNO_HARD_REGNO (allocno), decr_p, 1);
}
/* This recursive function updates COSTS (decrease if DECR_P) by
conflict costs of the unassigned allocnos connected by copies with
ALLOCNO. This update increases chances to remove some copies.
Copy cost is proportional to the copy frequency divided by
DIVISOR. */
static void
update_conflict_hard_regno_costs (int *costs, ira_allocno_t allocno,
int divisor, bool decr_p)
{
int i, cost, class_size, mult, div;
int *conflict_costs;
bool cont_p;
enum machine_mode mode;
enum reg_class cover_class;
ira_allocno_t another_allocno;
ira_copy_t cp, next_cp;
cover_class = ALLOCNO_COVER_CLASS (allocno);
/* Probably 5 hops will be enough. */
if (divisor > (COST_HOP_DIVISOR * COST_HOP_DIVISOR
* COST_HOP_DIVISOR * COST_HOP_DIVISOR * COST_HOP_DIVISOR))
return;
if (cover_class == NO_REGS)
return;
/* Check that it was already visited. */
if (allocno_update_cost_check[ALLOCNO_NUM (allocno)] == update_cost_check)
return;
allocno_update_cost_check[ALLOCNO_NUM (allocno)] = update_cost_check;
mode = ALLOCNO_MODE (allocno);
class_size = ira_class_hard_regs_num[cover_class];
for (cp = ALLOCNO_COPIES (allocno); cp != NULL; cp = next_cp)
{
if (cp->first == allocno)
{
next_cp = cp->next_first_allocno_copy;
another_allocno = cp->second;
}
else if (cp->second == allocno)
{
next_cp = cp->next_second_allocno_copy;
another_allocno = cp->first;
}
else
gcc_unreachable ();
if (cover_class != ALLOCNO_COVER_CLASS (another_allocno)
|| ALLOCNO_ASSIGNED_P (another_allocno)
|| ALLOCNO_MAY_BE_SPILLED_P (another_allocno))
continue;
ira_allocate_and_copy_costs
(&ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (another_allocno),
cover_class, ALLOCNO_CONFLICT_HARD_REG_COSTS (another_allocno));
conflict_costs
= ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (another_allocno);
if (conflict_costs == NULL)
cont_p = true;
else
{
ira_assert (ALLOCNO_FREQ (another_allocno) != 0);
mult = cp->freq;
div = ALLOCNO_FREQ (another_allocno) * divisor;
cont_p = false;
for (i = class_size - 1; i >= 0; i--)
{
cost = conflict_costs [i] * mult / div;
if (cost == 0)
continue;
cont_p = true;
if (decr_p)
cost = -cost;
costs[i] += cost;
}
}
if (cont_p)
update_conflict_hard_regno_costs (costs, another_allocno,
divisor * COST_HOP_DIVISOR, decr_p);
}
}
/* Sort allocnos according to the profit of usage of a hard register
instead of memory for them. */
static int
allocno_cost_compare_func (const void *v1p, const void *v2p)
{
ira_allocno_t p1 = *(const ira_allocno_t *) v1p;
ira_allocno_t p2 = *(const ira_allocno_t *) v2p;
int c1, c2;
c1 = ALLOCNO_UPDATED_MEMORY_COST (p1) - ALLOCNO_COVER_CLASS_COST (p1);
c2 = ALLOCNO_UPDATED_MEMORY_COST (p2) - ALLOCNO_COVER_CLASS_COST (p2);
if (c1 - c2)
return c1 - c2;
/* If regs are equally good, sort by allocno numbers, so that the
results of qsort leave nothing to chance. */
return ALLOCNO_NUM (p1) - ALLOCNO_NUM (p2);
}
/* Print all allocnos coalesced with ALLOCNO. */
static void
print_coalesced_allocno (ira_allocno_t allocno)
{
ira_allocno_t a;
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
ira_print_expanded_allocno (a);
if (a == allocno)
break;
fprintf (ira_dump_file, "+");
}
}
/* Choose a hard register for ALLOCNO (or for all coalesced allocnos
represented by ALLOCNO). If RETRY_P is TRUE, it means that the
function called from function `ira_reassign_conflict_allocnos' and
`allocno_reload_assign'. This function implements the optimistic
coalescing too: if we failed to assign a hard register to set of
the coalesced allocnos, we put them onto the coloring stack for
subsequent separate assigning. */
static bool
assign_hard_reg (ira_allocno_t allocno, bool retry_p)
{
HARD_REG_SET conflicting_regs;
int i, j, hard_regno, best_hard_regno, class_size;
int cost, mem_cost, min_cost, full_cost, min_full_cost, add_cost;
int *a_costs;
int *conflict_costs;
enum reg_class cover_class, rclass;
enum machine_mode mode;
ira_allocno_t a, conflict_allocno;
ira_allocno_conflict_iterator aci;
static int costs[FIRST_PSEUDO_REGISTER], full_costs[FIRST_PSEUDO_REGISTER];
#ifdef STACK_REGS
bool no_stack_reg_p;
#endif
ira_assert (! ALLOCNO_ASSIGNED_P (allocno));
cover_class = ALLOCNO_COVER_CLASS (allocno);
class_size = ira_class_hard_regs_num[cover_class];
mode = ALLOCNO_MODE (allocno);
CLEAR_HARD_REG_SET (conflicting_regs);
best_hard_regno = -1;
memset (full_costs, 0, sizeof (int) * class_size);
mem_cost = 0;
if (allocno_coalesced_p)
bitmap_clear (processed_coalesced_allocno_bitmap);
memset (costs, 0, sizeof (int) * class_size);
memset (full_costs, 0, sizeof (int) * class_size);
#ifdef STACK_REGS
no_stack_reg_p = false;
#endif
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
mem_cost += ALLOCNO_UPDATED_MEMORY_COST (a);
IOR_HARD_REG_SET (conflicting_regs,
ALLOCNO_TOTAL_CONFLICT_HARD_REGS (a));
ira_allocate_and_copy_costs (&ALLOCNO_UPDATED_HARD_REG_COSTS (a),
cover_class, ALLOCNO_HARD_REG_COSTS (a));
a_costs = ALLOCNO_UPDATED_HARD_REG_COSTS (a);
#ifdef STACK_REGS
no_stack_reg_p = no_stack_reg_p || ALLOCNO_TOTAL_NO_STACK_REG_P (a);
#endif
for (cost = ALLOCNO_COVER_CLASS_COST (a), i = 0; i < class_size; i++)
if (a_costs != NULL)
{
costs[i] += a_costs[i];
full_costs[i] += a_costs[i];
}
else
{
costs[i] += cost;
full_costs[i] += cost;
}
/* Take preferences of conflicting allocnos into account. */
FOR_EACH_ALLOCNO_CONFLICT (a, conflict_allocno, aci)
/* Reload can give another class so we need to check all
allocnos. */
if (retry_p || bitmap_bit_p (consideration_allocno_bitmap,
ALLOCNO_NUM (conflict_allocno)))
{
ira_assert (cover_class == ALLOCNO_COVER_CLASS (conflict_allocno));
if (allocno_coalesced_p)
{
if (bitmap_bit_p (processed_coalesced_allocno_bitmap,
ALLOCNO_NUM (conflict_allocno)))
continue;
bitmap_set_bit (processed_coalesced_allocno_bitmap,
ALLOCNO_NUM (conflict_allocno));
}
if (ALLOCNO_ASSIGNED_P (conflict_allocno))
{
if ((hard_regno = ALLOCNO_HARD_REGNO (conflict_allocno)) >= 0)
{
IOR_HARD_REG_SET
(conflicting_regs,
ira_reg_mode_hard_regset
[hard_regno][ALLOCNO_MODE (conflict_allocno)]);
if (hard_reg_set_subset_p (reg_class_contents[cover_class],
conflicting_regs))
goto fail;
}
continue;
}
else if (! ALLOCNO_MAY_BE_SPILLED_P (conflict_allocno))
{
ira_allocate_and_copy_costs
(&ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (conflict_allocno),
cover_class,
ALLOCNO_CONFLICT_HARD_REG_COSTS (conflict_allocno));
conflict_costs
= ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (conflict_allocno);
if (conflict_costs != NULL)
for (j = class_size - 1; j >= 0; j--)
full_costs[j] -= conflict_costs[j];
VEC_safe_push (ira_allocno_t, heap, conflict_allocno_vec,
conflict_allocno);
}
}
if (a == allocno)
break;
}
/* Take into account preferences of allocnos connected by copies to
the conflict allocnos. */
update_cost_check++;
while (VEC_length (ira_allocno_t, conflict_allocno_vec) != 0)
{
conflict_allocno = VEC_pop (ira_allocno_t, conflict_allocno_vec);
update_conflict_hard_regno_costs (full_costs, conflict_allocno,
COST_HOP_DIVISOR, true);
}
update_cost_check++;
/* Take preferences of allocnos connected by copies into
account. */
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
update_conflict_hard_regno_costs (full_costs, a,
COST_HOP_DIVISOR, false);
if (a == allocno)
break;
}
min_cost = min_full_cost = INT_MAX;
/* We don't care about giving callee saved registers to allocnos no
living through calls because call clobbered registers are
allocated first (it is usual practice to put them first in
REG_ALLOC_ORDER). */
for (i = 0; i < class_size; i++)
{
hard_regno = ira_class_hard_regs[cover_class][i];
#ifdef STACK_REGS
if (no_stack_reg_p
&& FIRST_STACK_REG <= hard_regno && hard_regno <= LAST_STACK_REG)
continue;
#endif
if (! ira_hard_reg_not_in_set_p (hard_regno, mode, conflicting_regs)
|| TEST_HARD_REG_BIT (prohibited_class_mode_regs[cover_class][mode],
hard_regno))
continue;
cost = costs[i];
full_cost = full_costs[i];
if (! allocated_hardreg_p[hard_regno]
&& ira_hard_reg_not_in_set_p (hard_regno, mode, call_used_reg_set))
/* We need to save/restore the hard register in
epilogue/prologue. Therefore we increase the cost. */
{
/* ??? If only part is call clobbered. */
rclass = REGNO_REG_CLASS (hard_regno);
add_cost = (ira_memory_move_cost[mode][rclass][0]
+ ira_memory_move_cost[mode][rclass][1] - 1);
cost += add_cost;
full_cost += add_cost;
}
if (min_cost > cost)
min_cost = cost;
if (min_full_cost > full_cost)
{
min_full_cost = full_cost;
best_hard_regno = hard_regno;
ira_assert (hard_regno >= 0);
}
}
if (min_full_cost > mem_cost)
{
if (! retry_p && internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file, "(memory is more profitable %d vs %d) ",
mem_cost, min_full_cost);
best_hard_regno = -1;
}
fail:
if (best_hard_regno < 0
&& ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno) != allocno)
{
for (j = 0, a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
sorted_allocnos[j++] = a;
if (a == allocno)
break;
}
qsort (sorted_allocnos, j, sizeof (ira_allocno_t),
allocno_cost_compare_func);
for (i = 0; i < j; i++)
{
a = sorted_allocnos[i];
ALLOCNO_FIRST_COALESCED_ALLOCNO (a) = a;
ALLOCNO_NEXT_COALESCED_ALLOCNO (a) = a;
VEC_safe_push (ira_allocno_t, heap, allocno_stack_vec, a);
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
{
fprintf (ira_dump_file, " Pushing");
print_coalesced_allocno (a);
fprintf (ira_dump_file, "\n");
}
}
return false;
}
if (best_hard_regno >= 0)
allocated_hardreg_p[best_hard_regno] = true;
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
ALLOCNO_HARD_REGNO (a) = best_hard_regno;
ALLOCNO_ASSIGNED_P (a) = true;
if (best_hard_regno >= 0)
update_copy_costs (a, true);
ira_assert (ALLOCNO_COVER_CLASS (a) == cover_class);
/* We don't need updated costs anymore: */
ira_free_allocno_updated_costs (a);
if (a == allocno)
break;
}
return best_hard_regno >= 0;
}
/* This page contains the allocator based on the Chaitin-Briggs algorithm. */
/* Bucket of allocnos that can colored currently without spilling. */
static ira_allocno_t colorable_allocno_bucket;
/* Bucket of allocnos that might be not colored currently without
spilling. */
static ira_allocno_t uncolorable_allocno_bucket;
/* Each element of the array contains the current number of allocnos
of given *cover* class in the uncolorable_bucket. */
static int uncolorable_allocnos_num[N_REG_CLASSES];
/* Add ALLOCNO to bucket *BUCKET_PTR. ALLOCNO should be not in a bucket
before the call. */
static void
add_ira_allocno_to_bucket (ira_allocno_t allocno, ira_allocno_t *bucket_ptr)
{
ira_allocno_t first_allocno;
enum reg_class cover_class;
if (bucket_ptr == &uncolorable_allocno_bucket
&& (cover_class = ALLOCNO_COVER_CLASS (allocno)) != NO_REGS)
{
uncolorable_allocnos_num[cover_class]++;
ira_assert (uncolorable_allocnos_num[cover_class] > 0);
}
first_allocno = *bucket_ptr;
ALLOCNO_NEXT_BUCKET_ALLOCNO (allocno) = first_allocno;
ALLOCNO_PREV_BUCKET_ALLOCNO (allocno) = NULL;
if (first_allocno != NULL)
ALLOCNO_PREV_BUCKET_ALLOCNO (first_allocno) = allocno;
*bucket_ptr = allocno;
}
/* The function returns frequency and number of available hard
registers for allocnos coalesced with ALLOCNO. */
static void
get_coalesced_allocnos_attributes (ira_allocno_t allocno, int *freq, int *num)
{
ira_allocno_t a;
*freq = 0;
*num = 0;
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
*freq += ALLOCNO_FREQ (a);
*num += ALLOCNO_AVAILABLE_REGS_NUM (a);
if (a == allocno)
break;
}
}
/* Compare two allocnos to define which allocno should be pushed first
into the coloring stack. If the return is a negative number, the
allocno given by the first parameter will be pushed first. In this
case such allocno has less priority than the second one and the
hard register will be assigned to it after assignment to the second
one. As the result of such assignment order, the second allocno
has a better chance to get the best hard register. */
static int
bucket_allocno_compare_func (const void *v1p, const void *v2p)
{
ira_allocno_t a1 = *(const ira_allocno_t *) v1p;
ira_allocno_t a2 = *(const ira_allocno_t *) v2p;
int diff, a1_freq, a2_freq, a1_num, a2_num;
if ((diff = (int) ALLOCNO_COVER_CLASS (a2) - ALLOCNO_COVER_CLASS (a1)) != 0)
return diff;
get_coalesced_allocnos_attributes (a1, &a1_freq, &a1_num);
get_coalesced_allocnos_attributes (a2, &a2_freq, &a2_num);
if ((diff = a2_num - a1_num) != 0)
return diff;
else if ((diff = a1_freq - a2_freq) != 0)
return diff;
return ALLOCNO_NUM (a2) - ALLOCNO_NUM (a1);
}
/* Sort bucket *BUCKET_PTR and return the result through
BUCKET_PTR. */
static void
sort_bucket (ira_allocno_t *bucket_ptr)
{
ira_allocno_t a, head;
int n;
for (n = 0, a = *bucket_ptr; a != NULL; a = ALLOCNO_NEXT_BUCKET_ALLOCNO (a))
sorted_allocnos[n++] = a;
if (n <= 1)
return;
qsort (sorted_allocnos, n, sizeof (ira_allocno_t),
bucket_allocno_compare_func);
head = NULL;
for (n--; n >= 0; n--)
{
a = sorted_allocnos[n];
ALLOCNO_NEXT_BUCKET_ALLOCNO (a) = head;
ALLOCNO_PREV_BUCKET_ALLOCNO (a) = NULL;
if (head != NULL)
ALLOCNO_PREV_BUCKET_ALLOCNO (head) = a;
head = a;
}
*bucket_ptr = head;
}
/* Add ALLOCNO to bucket *BUCKET_PTR maintaining the order according
their priority. ALLOCNO should be not in a bucket before the
call. */
static void
add_ira_allocno_to_ordered_bucket (ira_allocno_t allocno,
ira_allocno_t *bucket_ptr)
{
ira_allocno_t before, after;
enum reg_class cover_class;
if (bucket_ptr == &uncolorable_allocno_bucket
&& (cover_class = ALLOCNO_COVER_CLASS (allocno)) != NO_REGS)
{
uncolorable_allocnos_num[cover_class]++;
ira_assert (uncolorable_allocnos_num[cover_class] > 0);
}
for (before = *bucket_ptr, after = NULL;
before != NULL;
after = before, before = ALLOCNO_NEXT_BUCKET_ALLOCNO (before))
if (bucket_allocno_compare_func (&allocno, &before) < 0)
break;
ALLOCNO_NEXT_BUCKET_ALLOCNO (allocno) = before;
ALLOCNO_PREV_BUCKET_ALLOCNO (allocno) = after;
if (after == NULL)
*bucket_ptr = allocno;
else
ALLOCNO_NEXT_BUCKET_ALLOCNO (after) = allocno;
if (before != NULL)
ALLOCNO_PREV_BUCKET_ALLOCNO (before) = allocno;
}
/* Delete ALLOCNO from bucket *BUCKET_PTR. It should be there before
the call. */
static void
delete_allocno_from_bucket (ira_allocno_t allocno, ira_allocno_t *bucket_ptr)
{
ira_allocno_t prev_allocno, next_allocno;
enum reg_class cover_class;
if (bucket_ptr == &uncolorable_allocno_bucket
&& (cover_class = ALLOCNO_COVER_CLASS (allocno)) != NO_REGS)
{
uncolorable_allocnos_num[cover_class]--;
ira_assert (uncolorable_allocnos_num[cover_class] >= 0);
}
prev_allocno = ALLOCNO_PREV_BUCKET_ALLOCNO (allocno);
next_allocno = ALLOCNO_NEXT_BUCKET_ALLOCNO (allocno);
if (prev_allocno != NULL)
ALLOCNO_NEXT_BUCKET_ALLOCNO (prev_allocno) = next_allocno;
else
{
ira_assert (*bucket_ptr == allocno);
*bucket_ptr = next_allocno;
}
if (next_allocno != NULL)
ALLOCNO_PREV_BUCKET_ALLOCNO (next_allocno) = prev_allocno;
}
/* Splay tree for each cover class. The trees are indexed by the
corresponding cover classes. Splay trees contain uncolorable
allocnos. */
static splay_tree uncolorable_allocnos_splay_tree[N_REG_CLASSES];
/* If the following macro is TRUE, splay tree is used to choose an
allocno of the corresponding cover class for spilling. When the
number uncolorable allocnos of given cover class decreases to some
threshold, linear array search is used to find the best allocno for
spilling. This threshold is actually pretty big because, although
splay trees asymptotically is much faster, each splay tree
operation is sufficiently costly especially taking cache locality
into account. */
#define USE_SPLAY_P(CLASS) (uncolorable_allocnos_num[CLASS] > 4000)
/* Put ALLOCNO onto the coloring stack without removing it from its
bucket. Pushing allocno to the coloring stack can result in moving
conflicting allocnos from the uncolorable bucket to the colorable
one. */
static void
push_ira_allocno_to_stack (ira_allocno_t allocno)
{
int conflicts_num, conflict_size, size;
ira_allocno_t a, conflict_allocno;
enum reg_class cover_class;
ira_allocno_conflict_iterator aci;
ALLOCNO_IN_GRAPH_P (allocno) = false;
VEC_safe_push (ira_allocno_t, heap, allocno_stack_vec, allocno);
cover_class = ALLOCNO_COVER_CLASS (allocno);
if (cover_class == NO_REGS)
return;
size = ira_reg_class_nregs[cover_class][ALLOCNO_MODE (allocno)];
if (allocno_coalesced_p)
bitmap_clear (processed_coalesced_allocno_bitmap);
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
FOR_EACH_ALLOCNO_CONFLICT (a, conflict_allocno, aci)
if (bitmap_bit_p (coloring_allocno_bitmap,
ALLOCNO_NUM (conflict_allocno)))
{
ira_assert (cover_class == ALLOCNO_COVER_CLASS (conflict_allocno));
if (allocno_coalesced_p)
{
if (bitmap_bit_p (processed_coalesced_allocno_bitmap,
ALLOCNO_NUM (conflict_allocno)))
continue;
bitmap_set_bit (processed_coalesced_allocno_bitmap,
ALLOCNO_NUM (conflict_allocno));
}
if (ALLOCNO_IN_GRAPH_P (conflict_allocno)
&& ! ALLOCNO_ASSIGNED_P (conflict_allocno))
{
conflicts_num = ALLOCNO_LEFT_CONFLICTS_NUM (conflict_allocno);
conflict_size
= (ira_reg_class_nregs
[cover_class][ALLOCNO_MODE (conflict_allocno)]);
ira_assert
(ALLOCNO_LEFT_CONFLICTS_NUM (conflict_allocno) >= size);
if (conflicts_num + conflict_size
<= ALLOCNO_AVAILABLE_REGS_NUM (conflict_allocno))
{
ALLOCNO_LEFT_CONFLICTS_NUM (conflict_allocno) -= size;
continue;
}
conflicts_num
= ALLOCNO_LEFT_CONFLICTS_NUM (conflict_allocno) - size;
if (uncolorable_allocnos_splay_tree[cover_class] != NULL
&& !ALLOCNO_SPLAY_REMOVED_P (conflict_allocno)
&& USE_SPLAY_P (cover_class))
{
ira_assert
(splay_tree_lookup
(uncolorable_allocnos_splay_tree[cover_class],
(splay_tree_key) conflict_allocno) != NULL);
splay_tree_remove
(uncolorable_allocnos_splay_tree[cover_class],
(splay_tree_key) conflict_allocno);
ALLOCNO_SPLAY_REMOVED_P (conflict_allocno) = true;
VEC_safe_push (ira_allocno_t, heap,
removed_splay_allocno_vec,
conflict_allocno);
}
ALLOCNO_LEFT_CONFLICTS_NUM (conflict_allocno) = conflicts_num;
if (conflicts_num + conflict_size
<= ALLOCNO_AVAILABLE_REGS_NUM (conflict_allocno))
{
delete_allocno_from_bucket (conflict_allocno,
&uncolorable_allocno_bucket);
add_ira_allocno_to_ordered_bucket (conflict_allocno,
&colorable_allocno_bucket);
}
}
}
if (a == allocno)
break;
}
}
/* Put ALLOCNO onto the coloring stack and remove it from its bucket.
The allocno is in the colorable bucket if COLORABLE_P is TRUE. */
static void
remove_allocno_from_bucket_and_push (ira_allocno_t allocno, bool colorable_p)
{
enum reg_class cover_class;
if (colorable_p)
delete_allocno_from_bucket (allocno, &colorable_allocno_bucket);
else
delete_allocno_from_bucket (allocno, &uncolorable_allocno_bucket);
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
{
fprintf (ira_dump_file, " Pushing");
print_coalesced_allocno (allocno);
fprintf (ira_dump_file, "%s\n", colorable_p ? "" : "(potential spill)");
}
cover_class = ALLOCNO_COVER_CLASS (allocno);
ira_assert ((colorable_p
&& (ALLOCNO_LEFT_CONFLICTS_NUM (allocno)
+ ira_reg_class_nregs[cover_class][ALLOCNO_MODE (allocno)]
<= ALLOCNO_AVAILABLE_REGS_NUM (allocno)))
|| (! colorable_p
&& (ALLOCNO_LEFT_CONFLICTS_NUM (allocno)
+ ira_reg_class_nregs[cover_class][ALLOCNO_MODE
(allocno)]
> ALLOCNO_AVAILABLE_REGS_NUM (allocno))));
if (! colorable_p)
ALLOCNO_MAY_BE_SPILLED_P (allocno) = true;
push_ira_allocno_to_stack (allocno);
}
/* Put all allocnos from colorable bucket onto the coloring stack. */
static void
push_only_colorable (void)
{
sort_bucket (&colorable_allocno_bucket);
for (;colorable_allocno_bucket != NULL;)
remove_allocno_from_bucket_and_push (colorable_allocno_bucket, true);
}
/* Puts ALLOCNO chosen for potential spilling onto the coloring
stack. */
static void
push_ira_allocno_to_spill (ira_allocno_t allocno)
{
delete_allocno_from_bucket (allocno, &uncolorable_allocno_bucket);
ALLOCNO_MAY_BE_SPILLED_P (allocno) = true;
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file, " Pushing p%d(%d) (potential spill)\n",
ALLOCNO_NUM (allocno), ALLOCNO_REGNO (allocno));
push_ira_allocno_to_stack (allocno);
}
/* Return the frequency of exit edges (if EXIT_P) or entry from/to the
loop given by its LOOP_NODE. */
int
ira_loop_edge_freq (ira_loop_tree_node_t loop_node, int regno, bool exit_p)
{
int freq, i;
edge_iterator ei;
edge e;
VEC (edge, heap) *edges;
ira_assert (loop_node->loop != NULL
&& (regno < 0 || regno >= FIRST_PSEUDO_REGISTER));
freq = 0;
if (! exit_p)
{
FOR_EACH_EDGE (e, ei, loop_node->loop->header->preds)
if (e->src != loop_node->loop->latch
&& (regno < 0
|| (bitmap_bit_p (DF_LR_OUT (e->src), regno)
&& bitmap_bit_p (DF_LR_IN (e->dest), regno))))
freq += EDGE_FREQUENCY (e);
}
else
{
edges = get_loop_exit_edges (loop_node->loop);
for (i = 0; VEC_iterate (edge, edges, i, e); i++)
if (regno < 0
|| (bitmap_bit_p (DF_LR_OUT (e->src), regno)
&& bitmap_bit_p (DF_LR_IN (e->dest), regno)))
freq += EDGE_FREQUENCY (e);
VEC_free (edge, heap, edges);
}
return REG_FREQ_FROM_EDGE_FREQ (freq);
}
/* Calculate and return the cost of putting allocno A into memory. */
static int
calculate_allocno_spill_cost (ira_allocno_t a)
{
int regno, cost;
enum machine_mode mode;
enum reg_class rclass;
ira_allocno_t parent_allocno;
ira_loop_tree_node_t parent_node, loop_node;
regno = ALLOCNO_REGNO (a);
cost = ALLOCNO_UPDATED_MEMORY_COST (a) - ALLOCNO_COVER_CLASS_COST (a);
if (ALLOCNO_CAP (a) != NULL)
return cost;
loop_node = ALLOCNO_LOOP_TREE_NODE (a);
if ((parent_node = loop_node->parent) == NULL)
return cost;
if ((parent_allocno = parent_node->regno_allocno_map[regno]) == NULL)
return cost;
mode = ALLOCNO_MODE (a);
rclass = ALLOCNO_COVER_CLASS (a);
if (ALLOCNO_HARD_REGNO (parent_allocno) < 0)
cost -= (ira_memory_move_cost[mode][rclass][0]
* ira_loop_edge_freq (loop_node, regno, true)
+ ira_memory_move_cost[mode][rclass][1]
* ira_loop_edge_freq (loop_node, regno, false));
else
cost += ((ira_memory_move_cost[mode][rclass][1]
* ira_loop_edge_freq (loop_node, regno, true)
+ ira_memory_move_cost[mode][rclass][0]
* ira_loop_edge_freq (loop_node, regno, false))
- (ira_register_move_cost[mode][rclass][rclass]
* (ira_loop_edge_freq (loop_node, regno, false)
+ ira_loop_edge_freq (loop_node, regno, true))));
return cost;
}
/* Compare keys in the splay tree used to choose best allocno for
spilling. The best allocno has the minimal key. */
static int
allocno_spill_priority_compare (splay_tree_key k1, splay_tree_key k2)
{
int pri1, pri2, diff;
ira_allocno_t a1 = (ira_allocno_t) k1, a2 = (ira_allocno_t) k2;
pri1 = (IRA_ALLOCNO_TEMP (a1)
/ (ALLOCNO_LEFT_CONFLICTS_NUM (a1)
* ira_reg_class_nregs[ALLOCNO_COVER_CLASS (a1)][ALLOCNO_MODE (a1)]
+ 1));
pri2 = (IRA_ALLOCNO_TEMP (a2)
/ (ALLOCNO_LEFT_CONFLICTS_NUM (a2)
* ira_reg_class_nregs[ALLOCNO_COVER_CLASS (a2)][ALLOCNO_MODE (a2)]
+ 1));
if ((diff = pri1 - pri2) != 0)
return diff;
if ((diff = IRA_ALLOCNO_TEMP (a1) - IRA_ALLOCNO_TEMP (a2)) != 0)
return diff;
return ALLOCNO_NUM (a1) - ALLOCNO_NUM (a2);
}
/* Allocate data of SIZE for the splay trees. We allocate only spay
tree roots or splay tree nodes. If you change this, please rewrite
the function. */
static void *
splay_tree_allocate (int size, void *data ATTRIBUTE_UNUSED)
{
if (size != sizeof (struct splay_tree_node_s))
return ira_allocate (size);
return pool_alloc (splay_tree_node_pool);
}
/* Free data NODE for the splay trees. We allocate and free only spay
tree roots or splay tree nodes. If you change this, please rewrite
the function. */
static void
splay_tree_free (void *node, void *data ATTRIBUTE_UNUSED)
{
int i;
enum reg_class cover_class;
for (i = 0; i < ira_reg_class_cover_size; i++)
{
cover_class = ira_reg_class_cover[i];
if (node == uncolorable_allocnos_splay_tree[cover_class])
{
ira_free (node);
return;
}
}
pool_free (splay_tree_node_pool, node);
}
/* Push allocnos to the coloring stack. The order of allocnos in the
stack defines the order for the subsequent coloring. */
static void
push_allocnos_to_stack (void)
{
ira_allocno_t allocno, a, i_allocno, *allocno_vec;
enum reg_class cover_class, rclass;
int allocno_pri, i_allocno_pri, allocno_cost, i_allocno_cost;
int i, j, num, cover_class_allocnos_num[N_REG_CLASSES];
ira_allocno_t *cover_class_allocnos[N_REG_CLASSES];
int cost;
/* Initialize. */
VEC_truncate(ira_allocno_t, removed_splay_allocno_vec, 0);
for (i = 0; i < ira_reg_class_cover_size; i++)
{
cover_class = ira_reg_class_cover[i];
cover_class_allocnos_num[cover_class] = 0;
cover_class_allocnos[cover_class] = NULL;
uncolorable_allocnos_splay_tree[cover_class] = NULL;
}
/* Calculate uncolorable allocno spill costs. */
for (allocno = uncolorable_allocno_bucket;
allocno != NULL;
allocno = ALLOCNO_NEXT_BUCKET_ALLOCNO (allocno))
if ((cover_class = ALLOCNO_COVER_CLASS (allocno)) != NO_REGS)
{
cover_class_allocnos_num[cover_class]++;
cost = 0;
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
cost += calculate_allocno_spill_cost (a);
if (a == allocno)
break;
}
/* ??? Remove cost of copies between the coalesced
allocnos. */
IRA_ALLOCNO_TEMP (allocno) = cost;
}
/* Define place where to put uncolorable allocnos of the same cover
class. */
for (num = i = 0; i < ira_reg_class_cover_size; i++)
{
cover_class = ira_reg_class_cover[i];
ira_assert (cover_class_allocnos_num[cover_class]
== uncolorable_allocnos_num[cover_class]);
if (cover_class_allocnos_num[cover_class] != 0)
{
cover_class_allocnos[cover_class] = allocnos_for_spilling + num;
num += cover_class_allocnos_num[cover_class];
cover_class_allocnos_num[cover_class] = 0;
}
if (USE_SPLAY_P (cover_class))
uncolorable_allocnos_splay_tree[cover_class]
= splay_tree_new_with_allocator (allocno_spill_priority_compare,
NULL, NULL, splay_tree_allocate,
splay_tree_free, NULL);
}
ira_assert (num <= ira_allocnos_num);
/* Collect uncolorable allocnos of each cover class. */
for (allocno = uncolorable_allocno_bucket;
allocno != NULL;
allocno = ALLOCNO_NEXT_BUCKET_ALLOCNO (allocno))
if ((cover_class = ALLOCNO_COVER_CLASS (allocno)) != NO_REGS)
{
cover_class_allocnos
[cover_class][cover_class_allocnos_num[cover_class]++] = allocno;
if (uncolorable_allocnos_splay_tree[cover_class] != NULL)
splay_tree_insert (uncolorable_allocnos_splay_tree[cover_class],
(splay_tree_key) allocno,
(splay_tree_value) allocno);
}
for (;;)
{
push_only_colorable ();
allocno = uncolorable_allocno_bucket;
if (allocno == NULL)
break;
cover_class = ALLOCNO_COVER_CLASS (allocno);
if (cover_class == NO_REGS)
{
push_ira_allocno_to_spill (allocno);
continue;
}
/* Potential spilling. */
ira_assert
(ira_reg_class_nregs[cover_class][ALLOCNO_MODE (allocno)] > 0);
if (USE_SPLAY_P (cover_class))
{
for (;VEC_length (ira_allocno_t, removed_splay_allocno_vec) != 0;)
{
allocno = VEC_pop (ira_allocno_t, removed_splay_allocno_vec);
ALLOCNO_SPLAY_REMOVED_P (allocno) = false;
rclass = ALLOCNO_COVER_CLASS (allocno);
if (ALLOCNO_LEFT_CONFLICTS_NUM (allocno)
+ ira_reg_class_nregs [rclass][ALLOCNO_MODE (allocno)]
> ALLOCNO_AVAILABLE_REGS_NUM (allocno))
splay_tree_insert
(uncolorable_allocnos_splay_tree[rclass],
(splay_tree_key) allocno, (splay_tree_value) allocno);
}
allocno = ((ira_allocno_t)
splay_tree_min
(uncolorable_allocnos_splay_tree[cover_class])->key);
splay_tree_remove (uncolorable_allocnos_splay_tree[cover_class],
(splay_tree_key) allocno);
}
else
{
num = cover_class_allocnos_num[cover_class];
ira_assert (num > 0);
allocno_vec = cover_class_allocnos[cover_class];
allocno = NULL;
allocno_pri = allocno_cost = 0;
/* Sort uncolorable allocno to find the one with the lowest
spill cost. */
for (i = 0, j = num - 1; i <= j;)
{
i_allocno = allocno_vec[i];
if (! ALLOCNO_IN_GRAPH_P (i_allocno)
&& ALLOCNO_IN_GRAPH_P (allocno_vec[j]))
{
i_allocno = allocno_vec[j];
allocno_vec[j] = allocno_vec[i];
allocno_vec[i] = i_allocno;
}
if (ALLOCNO_IN_GRAPH_P (i_allocno))
{
i++;
if (IRA_ALLOCNO_TEMP (i_allocno) == INT_MAX)
{
ira_allocno_t a;
int cost = 0;
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (i_allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
cost += calculate_allocno_spill_cost (i_allocno);
if (a == i_allocno)
break;
}
/* ??? Remove cost of copies between the coalesced
allocnos. */
IRA_ALLOCNO_TEMP (i_allocno) = cost;
}
i_allocno_cost = IRA_ALLOCNO_TEMP (i_allocno);
i_allocno_pri
= (i_allocno_cost
/ (ALLOCNO_LEFT_CONFLICTS_NUM (i_allocno)
* ira_reg_class_nregs[ALLOCNO_COVER_CLASS
(i_allocno)]
[ALLOCNO_MODE (i_allocno)] + 1));
if (allocno == NULL || allocno_pri > i_allocno_pri
|| (allocno_pri == i_allocno_pri
&& (allocno_cost > i_allocno_cost
|| (allocno_cost == i_allocno_cost
&& (ALLOCNO_NUM (allocno)
> ALLOCNO_NUM (i_allocno))))))
{
allocno = i_allocno;
allocno_cost = i_allocno_cost;
allocno_pri = i_allocno_pri;
}
}
if (! ALLOCNO_IN_GRAPH_P (allocno_vec[j]))
j--;
}
ira_assert (allocno != NULL && j >= 0);
cover_class_allocnos_num[cover_class] = j + 1;
}
ira_assert (ALLOCNO_IN_GRAPH_P (allocno)
&& ALLOCNO_COVER_CLASS (allocno) == cover_class
&& (ALLOCNO_LEFT_CONFLICTS_NUM (allocno)
+ ira_reg_class_nregs[cover_class][ALLOCNO_MODE
(allocno)]
> ALLOCNO_AVAILABLE_REGS_NUM (allocno)));
remove_allocno_from_bucket_and_push (allocno, false);
}
ira_assert (colorable_allocno_bucket == NULL
&& uncolorable_allocno_bucket == NULL);
for (i = 0; i < ira_reg_class_cover_size; i++)
{
cover_class = ira_reg_class_cover[i];
ira_assert (uncolorable_allocnos_num[cover_class] == 0);
if (uncolorable_allocnos_splay_tree[cover_class] != NULL)
splay_tree_delete (uncolorable_allocnos_splay_tree[cover_class]);
}
}
/* Pop the coloring stack and assign hard registers to the popped
allocnos. */
static void
pop_allocnos_from_stack (void)
{
ira_allocno_t allocno;
enum reg_class cover_class;
for (;VEC_length (ira_allocno_t, allocno_stack_vec) != 0;)
{
allocno = VEC_pop (ira_allocno_t, allocno_stack_vec);
cover_class = ALLOCNO_COVER_CLASS (allocno);
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
{
fprintf (ira_dump_file, " Popping");
print_coalesced_allocno (allocno);
fprintf (ira_dump_file, " -- ");
}
if (cover_class == NO_REGS)
{
ALLOCNO_HARD_REGNO (allocno) = -1;
ALLOCNO_ASSIGNED_P (allocno) = true;
ira_assert (ALLOCNO_UPDATED_HARD_REG_COSTS (allocno) == NULL);
ira_assert
(ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (allocno) == NULL);
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file, "assign memory\n");
}
else if (assign_hard_reg (allocno, false))
{
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file, "assign reg %d\n",
ALLOCNO_HARD_REGNO (allocno));
}
else if (ALLOCNO_ASSIGNED_P (allocno))
{
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file, "spill\n");
}
ALLOCNO_IN_GRAPH_P (allocno) = true;
}
}
/* Set up number of available hard registers for ALLOCNO. */
static void
setup_allocno_available_regs_num (ira_allocno_t allocno)
{
int i, n, hard_regs_num;
enum reg_class cover_class;
ira_allocno_t a;
HARD_REG_SET temp_set;
cover_class = ALLOCNO_COVER_CLASS (allocno);
ALLOCNO_AVAILABLE_REGS_NUM (allocno) = ira_available_class_regs[cover_class];
if (cover_class == NO_REGS)
return;
CLEAR_HARD_REG_SET (temp_set);
ira_assert (ALLOCNO_FIRST_COALESCED_ALLOCNO (allocno) == allocno);
hard_regs_num = ira_class_hard_regs_num[cover_class];
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
IOR_HARD_REG_SET (temp_set, ALLOCNO_TOTAL_CONFLICT_HARD_REGS (a));
if (a == allocno)
break;
}
for (n = 0, i = hard_regs_num - 1; i >= 0; i--)
if (TEST_HARD_REG_BIT (temp_set, ira_class_hard_regs[cover_class][i]))
n++;
if (internal_flag_ira_verbose > 2 && n > 0 && ira_dump_file != NULL)
fprintf (ira_dump_file, " Reg %d of %s has %d regs less\n",
ALLOCNO_REGNO (allocno), reg_class_names[cover_class], n);
ALLOCNO_AVAILABLE_REGS_NUM (allocno) -= n;
}
/* Set up ALLOCNO_LEFT_CONFLICTS_NUM for ALLOCNO. */
static void
setup_allocno_left_conflicts_num (ira_allocno_t allocno)
{
int i, hard_regs_num, hard_regno, conflict_allocnos_size;
ira_allocno_t a, conflict_allocno;
enum reg_class cover_class;
HARD_REG_SET temp_set;
ira_allocno_conflict_iterator aci;
cover_class = ALLOCNO_COVER_CLASS (allocno);
hard_regs_num = ira_class_hard_regs_num[cover_class];
CLEAR_HARD_REG_SET (temp_set);
ira_assert (ALLOCNO_FIRST_COALESCED_ALLOCNO (allocno) == allocno);
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
IOR_HARD_REG_SET (temp_set, ALLOCNO_TOTAL_CONFLICT_HARD_REGS (a));
if (a == allocno)
break;
}
AND_HARD_REG_SET (temp_set, reg_class_contents[cover_class]);
AND_COMPL_HARD_REG_SET (temp_set, ira_no_alloc_regs);
conflict_allocnos_size = 0;
if (! hard_reg_set_empty_p (temp_set))
for (i = 0; i < (int) hard_regs_num; i++)
{
hard_regno = ira_class_hard_regs[cover_class][i];
if (TEST_HARD_REG_BIT (temp_set, hard_regno))
{
conflict_allocnos_size++;
CLEAR_HARD_REG_BIT (temp_set, hard_regno);
if (hard_reg_set_empty_p (temp_set))
break;
}
}
CLEAR_HARD_REG_SET (temp_set);
if (allocno_coalesced_p)
bitmap_clear (processed_coalesced_allocno_bitmap);
if (cover_class != NO_REGS)
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
FOR_EACH_ALLOCNO_CONFLICT (a, conflict_allocno, aci)
if (bitmap_bit_p (consideration_allocno_bitmap,
ALLOCNO_NUM (conflict_allocno)))
{
ira_assert (cover_class
== ALLOCNO_COVER_CLASS (conflict_allocno));
if (allocno_coalesced_p)
{
if (bitmap_bit_p (processed_coalesced_allocno_bitmap,
ALLOCNO_NUM (conflict_allocno)))
continue;
bitmap_set_bit (processed_coalesced_allocno_bitmap,
ALLOCNO_NUM (conflict_allocno));
}
if (! ALLOCNO_ASSIGNED_P (conflict_allocno))
conflict_allocnos_size
+= (ira_reg_class_nregs
[cover_class][ALLOCNO_MODE (conflict_allocno)]);
else if ((hard_regno = ALLOCNO_HARD_REGNO (conflict_allocno))
>= 0)
{
int last = (hard_regno
+ hard_regno_nregs
[hard_regno][ALLOCNO_MODE (conflict_allocno)]);
while (hard_regno < last)
{
if (! TEST_HARD_REG_BIT (temp_set, hard_regno))
{
conflict_allocnos_size++;
SET_HARD_REG_BIT (temp_set, hard_regno);
}
hard_regno++;
}
}
}
if (a == allocno)
break;
}
ALLOCNO_LEFT_CONFLICTS_NUM (allocno) = conflict_allocnos_size;
}
/* Put ALLOCNO in a bucket corresponding to its number and size of its
conflicting allocnos and hard registers. */
static void
put_allocno_into_bucket (ira_allocno_t allocno)
{
int hard_regs_num;
enum reg_class cover_class;
cover_class = ALLOCNO_COVER_CLASS (allocno);
hard_regs_num = ira_class_hard_regs_num[cover_class];
if (ALLOCNO_FIRST_COALESCED_ALLOCNO (allocno) != allocno)
return;
ALLOCNO_IN_GRAPH_P (allocno) = true;
setup_allocno_left_conflicts_num (allocno);
setup_allocno_available_regs_num (allocno);
if (ALLOCNO_LEFT_CONFLICTS_NUM (allocno)
+ ira_reg_class_nregs[cover_class][ALLOCNO_MODE (allocno)]
<= ALLOCNO_AVAILABLE_REGS_NUM (allocno))
add_ira_allocno_to_bucket (allocno, &colorable_allocno_bucket);
else
add_ira_allocno_to_bucket (allocno, &uncolorable_allocno_bucket);
}
/* The function is used to sort allocnos according to their execution
frequencies. */
static int
copy_freq_compare_func (const void *v1p, const void *v2p)
{
ira_copy_t cp1 = *(const ira_copy_t *) v1p, cp2 = *(const ira_copy_t *) v2p;
int pri1, pri2;
pri1 = cp1->freq;
pri2 = cp2->freq;
if (pri2 - pri1)
return pri2 - pri1;
/* If freqencies are equal, sort by copies, so that the results of
qsort leave nothing to chance. */
return cp1->num - cp2->num;
}
/* Merge two sets of coalesced allocnos given correspondingly by
allocnos A1 and A2 (more accurately merging A2 set into A1
set). */
static void
merge_allocnos (ira_allocno_t a1, ira_allocno_t a2)
{
ira_allocno_t a, first, last, next;
first = ALLOCNO_FIRST_COALESCED_ALLOCNO (a1);
if (first == ALLOCNO_FIRST_COALESCED_ALLOCNO (a2))
return;
for (last = a2, a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a2);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
ALLOCNO_FIRST_COALESCED_ALLOCNO (a) = first;
if (a == a2)
break;
last = a;
}
next = ALLOCNO_NEXT_COALESCED_ALLOCNO (first);
ALLOCNO_NEXT_COALESCED_ALLOCNO (first) = a2;
ALLOCNO_NEXT_COALESCED_ALLOCNO (last) = next;
}
/* Return TRUE if there are conflicting allocnos from two sets of
coalesced allocnos given correspondingly by allocnos A1 and A2. If
RELOAD_P is TRUE, we use live ranges to find conflicts because
conflicts are represented only for allocnos of the same cover class
and during the reload pass we coalesce allocnos for sharing stack
memory slots. */
static bool
coalesced_allocno_conflict_p (ira_allocno_t a1, ira_allocno_t a2,
bool reload_p)
{
ira_allocno_t a, conflict_allocno;
ira_allocno_conflict_iterator aci;
if (allocno_coalesced_p)
{
bitmap_clear (processed_coalesced_allocno_bitmap);
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a1);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
bitmap_set_bit (processed_coalesced_allocno_bitmap, ALLOCNO_NUM (a));
if (a == a1)
break;
}
}
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a2);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
if (reload_p)
{
for (conflict_allocno = ALLOCNO_NEXT_COALESCED_ALLOCNO (a1);;
conflict_allocno
= ALLOCNO_NEXT_COALESCED_ALLOCNO (conflict_allocno))
{
if (ira_allocno_live_ranges_intersect_p (a, conflict_allocno))
return true;
if (conflict_allocno == a1)
break;
}
}
else
{
FOR_EACH_ALLOCNO_CONFLICT (a, conflict_allocno, aci)
if (conflict_allocno == a1
|| (allocno_coalesced_p
&& bitmap_bit_p (processed_coalesced_allocno_bitmap,
ALLOCNO_NUM (conflict_allocno))))
return true;
}
if (a == a2)
break;
}
return false;
}
/* The major function for aggressive allocno coalescing. For the
reload pass (RELOAD_P) we coalesce only spilled allocnos. If some
allocnos have been coalesced, we set up flag
allocno_coalesced_p. */
static void
coalesce_allocnos (bool reload_p)
{
ira_allocno_t a;
ira_copy_t cp, next_cp, *sorted_copies;
enum reg_class cover_class;
enum machine_mode mode;
unsigned int j;
int i, n, cp_num, regno;
bitmap_iterator bi;
sorted_copies = (ira_copy_t *) ira_allocate (ira_copies_num
* sizeof (ira_copy_t));
cp_num = 0;
/* Collect copies. */
EXECUTE_IF_SET_IN_BITMAP (coloring_allocno_bitmap, 0, j, bi)
{
a = ira_allocnos[j];
regno = ALLOCNO_REGNO (a);
if ((! reload_p && ALLOCNO_ASSIGNED_P (a))
|| (reload_p
&& (! ALLOCNO_ASSIGNED_P (a) || ALLOCNO_HARD_REGNO (a) >= 0
|| (regno < ira_reg_equiv_len
&& (ira_reg_equiv_const[regno] != NULL_RTX
|| ira_reg_equiv_invariant_p[regno])))))
continue;
cover_class = ALLOCNO_COVER_CLASS (a);
mode = ALLOCNO_MODE (a);
for (cp = ALLOCNO_COPIES (a); cp != NULL; cp = next_cp)
{
if (cp->first == a)
{
next_cp = cp->next_first_allocno_copy;
regno = ALLOCNO_REGNO (cp->second);
if ((reload_p
|| (ALLOCNO_COVER_CLASS (cp->second) == cover_class
&& ALLOCNO_MODE (cp->second) == mode))
&& cp->insn != NULL
&& ((! reload_p && ! ALLOCNO_ASSIGNED_P (cp->second))
|| (reload_p
&& ALLOCNO_ASSIGNED_P (cp->second)
&& ALLOCNO_HARD_REGNO (cp->second) < 0
&& (regno >= ira_reg_equiv_len
|| (! ira_reg_equiv_invariant_p[regno]
&& ira_reg_equiv_const[regno] == NULL_RTX)))))
sorted_copies[cp_num++] = cp;
}
else if (cp->second == a)
next_cp = cp->next_second_allocno_copy;
else
gcc_unreachable ();
}
}
qsort (sorted_copies, cp_num, sizeof (ira_copy_t), copy_freq_compare_func);
/* Coalesced copies, most frequently executed first. */
for (; cp_num != 0;)
{
for (i = 0; i < cp_num; i++)
{
cp = sorted_copies[i];
if (! coalesced_allocno_conflict_p (cp->first, cp->second, reload_p))
{
allocno_coalesced_p = true;
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf
(ira_dump_file,
" Coalescing copy %d:a%dr%d-a%dr%d (freq=%d)\n",
cp->num, ALLOCNO_NUM (cp->first), ALLOCNO_REGNO (cp->first),
ALLOCNO_NUM (cp->second), ALLOCNO_REGNO (cp->second),
cp->freq);
merge_allocnos (cp->first, cp->second);
i++;
break;
}
}
/* Collect the rest of copies. */
for (n = 0; i < cp_num; i++)
{
cp = sorted_copies[i];
if (ALLOCNO_FIRST_COALESCED_ALLOCNO (cp->first)
!= ALLOCNO_FIRST_COALESCED_ALLOCNO (cp->second))
sorted_copies[n++] = cp;
}
cp_num = n;
}
ira_free (sorted_copies);
}
/* Chaitin-Briggs coloring for allocnos in COLORING_ALLOCNO_BITMAP
taking into account allocnos in CONSIDERATION_ALLOCNO_BITMAP. */
static void
color_allocnos (void)
{
unsigned int i;
bitmap_iterator bi;
ira_allocno_t a;
allocno_coalesced_p = false;
processed_coalesced_allocno_bitmap = ira_allocate_bitmap ();
if (flag_ira_coalesce)
coalesce_allocnos (false);
/* Put the allocnos into the corresponding buckets. */
colorable_allocno_bucket = NULL;
uncolorable_allocno_bucket = NULL;
EXECUTE_IF_SET_IN_BITMAP (coloring_allocno_bitmap, 0, i, bi)
{
a = ira_allocnos[i];
if (ALLOCNO_COVER_CLASS (a) == NO_REGS)
{
ALLOCNO_HARD_REGNO (a) = -1;
ALLOCNO_ASSIGNED_P (a) = true;
ira_assert (ALLOCNO_UPDATED_HARD_REG_COSTS (a) == NULL);
ira_assert (ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (a) == NULL);
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
{
fprintf (ira_dump_file, " Spill");
print_coalesced_allocno (a);
fprintf (ira_dump_file, "\n");
}
continue;
}
put_allocno_into_bucket (a);
}
push_allocnos_to_stack ();
pop_allocnos_from_stack ();
if (flag_ira_coalesce)
/* We don't need coalesced allocnos for ira_reassign_pseudos. */
EXECUTE_IF_SET_IN_BITMAP (coloring_allocno_bitmap, 0, i, bi)
{
a = ira_allocnos[i];
ALLOCNO_FIRST_COALESCED_ALLOCNO (a) = a;
ALLOCNO_NEXT_COALESCED_ALLOCNO (a) = a;
}
ira_free_bitmap (processed_coalesced_allocno_bitmap);
allocno_coalesced_p = false;
}
/* Output information about the loop given by its LOOP_TREE_NODE. */
static void
print_loop_title (ira_loop_tree_node_t loop_tree_node)
{
unsigned int j;
bitmap_iterator bi;
ira_assert (loop_tree_node->loop != NULL);
fprintf (ira_dump_file,
"\n Loop %d (parent %d, header bb%d, depth %d)\n all:",
loop_tree_node->loop->num,
(loop_tree_node->parent == NULL
? -1 : loop_tree_node->parent->loop->num),
loop_tree_node->loop->header->index,
loop_depth (loop_tree_node->loop));
EXECUTE_IF_SET_IN_BITMAP (loop_tree_node->all_allocnos, 0, j, bi)
fprintf (ira_dump_file, " %dr%d", j, ALLOCNO_REGNO (ira_allocnos[j]));
fprintf (ira_dump_file, "\n modified regnos:");
EXECUTE_IF_SET_IN_BITMAP (loop_tree_node->modified_regnos, 0, j, bi)
fprintf (ira_dump_file, " %d", j);
fprintf (ira_dump_file, "\n border:");
EXECUTE_IF_SET_IN_BITMAP (loop_tree_node->border_allocnos, 0, j, bi)
fprintf (ira_dump_file, " %dr%d", j, ALLOCNO_REGNO (ira_allocnos[j]));
fprintf (ira_dump_file, "\n Pressure:");
for (j = 0; (int) j < ira_reg_class_cover_size; j++)
{
enum reg_class cover_class;
cover_class = ira_reg_class_cover[j];
if (loop_tree_node->reg_pressure[cover_class] == 0)
continue;
fprintf (ira_dump_file, " %s=%d", reg_class_names[cover_class],
loop_tree_node->reg_pressure[cover_class]);
}
fprintf (ira_dump_file, "\n");
}
/* Color the allocnos inside loop (in the extreme case it can be all
of the function) given the corresponding LOOP_TREE_NODE. The
function is called for each loop during top-down traverse of the
loop tree. */
static void
color_pass (ira_loop_tree_node_t loop_tree_node)
{
int regno, hard_regno, index = -1;
int cost, exit_freq, enter_freq;
unsigned int j;
bitmap_iterator bi;
enum machine_mode mode;
enum reg_class rclass, cover_class;
ira_allocno_t a, subloop_allocno;
ira_loop_tree_node_t subloop_node;
ira_assert (loop_tree_node->bb == NULL);
if (internal_flag_ira_verbose > 1 && ira_dump_file != NULL)
print_loop_title (loop_tree_node);
bitmap_copy (coloring_allocno_bitmap, loop_tree_node->all_allocnos);
bitmap_copy (consideration_allocno_bitmap, coloring_allocno_bitmap);
EXECUTE_IF_SET_IN_BITMAP (consideration_allocno_bitmap, 0, j, bi)
{
a = ira_allocnos[j];
if (! ALLOCNO_ASSIGNED_P (a))
continue;
bitmap_clear_bit (coloring_allocno_bitmap, ALLOCNO_NUM (a));
}
/* Color all mentioned allocnos including transparent ones. */
color_allocnos ();
/* Process caps. They are processed just once. */
if (flag_ira_algorithm == IRA_ALGORITHM_MIXED
|| flag_ira_algorithm == IRA_ALGORITHM_REGIONAL)
EXECUTE_IF_SET_IN_BITMAP (loop_tree_node->all_allocnos, 0, j, bi)
{
a = ira_allocnos[j];
if (ALLOCNO_CAP_MEMBER (a) == NULL)
continue;
/* Remove from processing in the next loop. */
bitmap_clear_bit (consideration_allocno_bitmap, j);
rclass = ALLOCNO_COVER_CLASS (a);
if ((flag_ira_algorithm == IRA_ALGORITHM_MIXED
&& loop_tree_node->reg_pressure[rclass]
<= ira_available_class_regs[rclass]))
{
mode = ALLOCNO_MODE (a);
hard_regno = ALLOCNO_HARD_REGNO (a);
if (hard_regno >= 0)
{
index = ira_class_hard_reg_index[rclass][hard_regno];
ira_assert (index >= 0);
}
regno = ALLOCNO_REGNO (a);
subloop_allocno = ALLOCNO_CAP_MEMBER (a);
subloop_node = ALLOCNO_LOOP_TREE_NODE (subloop_allocno);
ira_assert (!ALLOCNO_ASSIGNED_P (subloop_allocno));
ALLOCNO_HARD_REGNO (subloop_allocno) = hard_regno;
ALLOCNO_ASSIGNED_P (subloop_allocno) = true;
if (hard_regno >= 0)
update_copy_costs (subloop_allocno, true);
/* We don't need updated costs anymore: */
ira_free_allocno_updated_costs (subloop_allocno);
}
}
/* Update costs of the corresponding allocnos (not caps) in the
subloops. */
for (subloop_node = loop_tree_node->subloops;
subloop_node != NULL;
subloop_node = subloop_node->subloop_next)
{
ira_assert (subloop_node->bb == NULL);
EXECUTE_IF_SET_IN_BITMAP (consideration_allocno_bitmap, 0, j, bi)
{
a = ira_allocnos[j];
ira_assert (ALLOCNO_CAP_MEMBER (a) == NULL);
mode = ALLOCNO_MODE (a);
rclass = ALLOCNO_COVER_CLASS (a);
hard_regno = ALLOCNO_HARD_REGNO (a);
if (hard_regno >= 0)
{
index = ira_class_hard_reg_index[rclass][hard_regno];
ira_assert (index >= 0);
}
regno = ALLOCNO_REGNO (a);
/* ??? conflict costs */
subloop_allocno = subloop_node->regno_allocno_map[regno];
if (subloop_allocno == NULL
|| ALLOCNO_CAP (subloop_allocno) != NULL)
continue;
ira_assert (bitmap_bit_p (subloop_node->all_allocnos,
ALLOCNO_NUM (subloop_allocno)));
if (flag_ira_algorithm == IRA_ALGORITHM_MIXED
&& (loop_tree_node->reg_pressure[rclass]
<= ira_available_class_regs[rclass]))
{
if (! ALLOCNO_ASSIGNED_P (subloop_allocno))
{
ALLOCNO_HARD_REGNO (subloop_allocno) = hard_regno;
ALLOCNO_ASSIGNED_P (subloop_allocno) = true;
if (hard_regno >= 0)
update_copy_costs (subloop_allocno, true);
/* We don't need updated costs anymore: */
ira_free_allocno_updated_costs (subloop_allocno);
}
continue;
}
exit_freq = ira_loop_edge_freq (subloop_node, regno, true);
enter_freq = ira_loop_edge_freq (subloop_node, regno, false);
ira_assert (regno < ira_reg_equiv_len);
if (ira_reg_equiv_invariant_p[regno]
|| ira_reg_equiv_const[regno] != NULL_RTX)
{
if (! ALLOCNO_ASSIGNED_P (subloop_allocno))
{
ALLOCNO_HARD_REGNO (subloop_allocno) = hard_regno;
ALLOCNO_ASSIGNED_P (subloop_allocno) = true;
if (hard_regno >= 0)
update_copy_costs (subloop_allocno, true);
/* We don't need updated costs anymore: */
ira_free_allocno_updated_costs (subloop_allocno);
}
}
else if (hard_regno < 0)
{
ALLOCNO_UPDATED_MEMORY_COST (subloop_allocno)
-= ((ira_memory_move_cost[mode][rclass][1] * enter_freq)
+ (ira_memory_move_cost[mode][rclass][0] * exit_freq));
}
else
{
cover_class = ALLOCNO_COVER_CLASS (subloop_allocno);
ira_allocate_and_set_costs
(&ALLOCNO_HARD_REG_COSTS (subloop_allocno), cover_class,
ALLOCNO_COVER_CLASS_COST (subloop_allocno));
ira_allocate_and_set_costs
(&ALLOCNO_CONFLICT_HARD_REG_COSTS (subloop_allocno),
cover_class, 0);
cost = (ira_register_move_cost[mode][rclass][rclass]
* (exit_freq + enter_freq));
ALLOCNO_HARD_REG_COSTS (subloop_allocno)[index] -= cost;
ALLOCNO_CONFLICT_HARD_REG_COSTS (subloop_allocno)[index]
-= cost;
ALLOCNO_UPDATED_MEMORY_COST (subloop_allocno)
+= (ira_memory_move_cost[mode][rclass][0] * enter_freq
+ ira_memory_move_cost[mode][rclass][1] * exit_freq);
if (ALLOCNO_COVER_CLASS_COST (subloop_allocno)
> ALLOCNO_HARD_REG_COSTS (subloop_allocno)[index])
ALLOCNO_COVER_CLASS_COST (subloop_allocno)
= ALLOCNO_HARD_REG_COSTS (subloop_allocno)[index];
}
}
}
}
/* Initialize the common data for coloring and calls functions to do
Chaitin-Briggs and regional coloring. */
static void
do_coloring (void)
{
coloring_allocno_bitmap = ira_allocate_bitmap ();
allocnos_for_spilling
= (ira_allocno_t *) ira_allocate (sizeof (ira_allocno_t)
* ira_allocnos_num);
splay_tree_node_pool = create_alloc_pool ("splay tree nodes",
sizeof (struct splay_tree_node_s),
100);
if (internal_flag_ira_verbose > 0 && ira_dump_file != NULL)
fprintf (ira_dump_file, "\n**** Allocnos coloring:\n\n");
ira_traverse_loop_tree (false, ira_loop_tree_root, color_pass, NULL);
if (internal_flag_ira_verbose > 1 && ira_dump_file != NULL)
ira_print_disposition (ira_dump_file);
free_alloc_pool (splay_tree_node_pool);
ira_free_bitmap (coloring_allocno_bitmap);
ira_free (allocnos_for_spilling);
}
/* Move spill/restore code, which are to be generated in ira-emit.c,
to less frequent points (if it is profitable) by reassigning some
allocnos (in loop with subloops containing in another loop) to
memory which results in longer live-range where the corresponding
pseudo-registers will be in memory. */
static void
move_spill_restore (void)
{
int cost, regno, hard_regno, hard_regno2, index;
bool changed_p;
int enter_freq, exit_freq;
enum machine_mode mode;
enum reg_class rclass;
ira_allocno_t a, parent_allocno, subloop_allocno;
ira_loop_tree_node_t parent, loop_node, subloop_node;
ira_allocno_iterator ai;
for (;;)
{
changed_p = false;
if (internal_flag_ira_verbose > 0 && ira_dump_file != NULL)
fprintf (ira_dump_file, "New iteration of spill/restore move\n");
FOR_EACH_ALLOCNO (a, ai)
{
regno = ALLOCNO_REGNO (a);
loop_node = ALLOCNO_LOOP_TREE_NODE (a);
if (ALLOCNO_CAP_MEMBER (a) != NULL
|| ALLOCNO_CAP (a) != NULL
|| (hard_regno = ALLOCNO_HARD_REGNO (a)) < 0
|| loop_node->children == NULL
/* don't do the optimization because it can create
copies and the reload pass can spill the allocno set
by copy although the allocno will not get memory
slot. */
|| ira_reg_equiv_invariant_p[regno]
|| ira_reg_equiv_const[regno] != NULL_RTX
|| !bitmap_bit_p (loop_node->border_allocnos, ALLOCNO_NUM (a)))
continue;
mode = ALLOCNO_MODE (a);
rclass = ALLOCNO_COVER_CLASS (a);
index = ira_class_hard_reg_index[rclass][hard_regno];
ira_assert (index >= 0);
cost = (ALLOCNO_MEMORY_COST (a)
- (ALLOCNO_HARD_REG_COSTS (a) == NULL
? ALLOCNO_COVER_CLASS_COST (a)
: ALLOCNO_HARD_REG_COSTS (a)[index]));
for (subloop_node = loop_node->subloops;
subloop_node != NULL;
subloop_node = subloop_node->subloop_next)
{
ira_assert (subloop_node->bb == NULL);
subloop_allocno = subloop_node->regno_allocno_map[regno];
if (subloop_allocno == NULL)
continue;
/* We have accumulated cost. To get the real cost of
allocno usage in the loop we should subtract costs of
the subloop allocnos. */
cost -= (ALLOCNO_MEMORY_COST (subloop_allocno)
- (ALLOCNO_HARD_REG_COSTS (subloop_allocno) == NULL
? ALLOCNO_COVER_CLASS_COST (subloop_allocno)
: ALLOCNO_HARD_REG_COSTS (subloop_allocno)[index]));
exit_freq = ira_loop_edge_freq (subloop_node, regno, true);
enter_freq = ira_loop_edge_freq (subloop_node, regno, false);
if ((hard_regno2 = ALLOCNO_HARD_REGNO (subloop_allocno)) < 0)
cost -= (ira_memory_move_cost[mode][rclass][0] * exit_freq
+ ira_memory_move_cost[mode][rclass][1] * enter_freq);
else
{
cost
+= (ira_memory_move_cost[mode][rclass][0] * exit_freq
+ ira_memory_move_cost[mode][rclass][1] * enter_freq);
if (hard_regno2 != hard_regno)
cost -= (ira_register_move_cost[mode][rclass][rclass]
* (exit_freq + enter_freq));
}
}
if ((parent = loop_node->parent) != NULL
&& (parent_allocno = parent->regno_allocno_map[regno]) != NULL)
{
exit_freq = ira_loop_edge_freq (loop_node, regno, true);
enter_freq = ira_loop_edge_freq (loop_node, regno, false);
if ((hard_regno2 = ALLOCNO_HARD_REGNO (parent_allocno)) < 0)
cost -= (ira_memory_move_cost[mode][rclass][0] * exit_freq
+ ira_memory_move_cost[mode][rclass][1] * enter_freq);
else
{
cost
+= (ira_memory_move_cost[mode][rclass][1] * exit_freq
+ ira_memory_move_cost[mode][rclass][0] * enter_freq);
if (hard_regno2 != hard_regno)
cost -= (ira_register_move_cost[mode][rclass][rclass]
* (exit_freq + enter_freq));
}
}
if (cost < 0)
{
ALLOCNO_HARD_REGNO (a) = -1;
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
{
fprintf
(ira_dump_file,
" Moving spill/restore for a%dr%d up from loop %d",
ALLOCNO_NUM (a), regno, loop_node->loop->num);
fprintf (ira_dump_file, " - profit %d\n", -cost);
}
changed_p = true;
}
}
if (! changed_p)
break;
}
}
/* Update current hard reg costs and current conflict hard reg costs
for allocno A. It is done by processing its copies containing
other allocnos already assigned. */
static void
update_curr_costs (ira_allocno_t a)
{
int i, hard_regno, cost;
enum machine_mode mode;
enum reg_class cover_class, rclass;
ira_allocno_t another_a;
ira_copy_t cp, next_cp;
ira_assert (! ALLOCNO_ASSIGNED_P (a));
cover_class = ALLOCNO_COVER_CLASS (a);
if (cover_class == NO_REGS)
return;
mode = ALLOCNO_MODE (a);
for (cp = ALLOCNO_COPIES (a); cp != NULL; cp = next_cp)
{
if (cp->first == a)
{
next_cp = cp->next_first_allocno_copy;
another_a = cp->second;
}
else if (cp->second == a)
{
next_cp = cp->next_second_allocno_copy;
another_a = cp->first;
}
else
gcc_unreachable ();
if (cover_class != ALLOCNO_COVER_CLASS (another_a)
|| ! ALLOCNO_ASSIGNED_P (another_a)
|| (hard_regno = ALLOCNO_HARD_REGNO (another_a)) < 0)
continue;
rclass = REGNO_REG_CLASS (hard_regno);
i = ira_class_hard_reg_index[cover_class][hard_regno];
ira_assert (i >= 0);
cost = (cp->first == a
? ira_register_move_cost[mode][rclass][cover_class]
: ira_register_move_cost[mode][cover_class][rclass]);
ira_allocate_and_set_or_copy_costs
(&ALLOCNO_UPDATED_HARD_REG_COSTS (a),
cover_class, ALLOCNO_COVER_CLASS_COST (a),
ALLOCNO_HARD_REG_COSTS (a));
ira_allocate_and_set_or_copy_costs
(&ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (a),
cover_class, 0, ALLOCNO_CONFLICT_HARD_REG_COSTS (a));
ALLOCNO_UPDATED_HARD_REG_COSTS (a)[i] -= cp->freq * cost;
ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (a)[i] -= cp->freq * cost;
}
}
/* Map: allocno number -> allocno priority. */
static int *allocno_priorities;
/* Allocate array ALLOCNO_PRIORITIES and set up priorities for N allocnos in
array CONSIDERATION_ALLOCNOS. */
static void
start_allocno_priorities (ira_allocno_t *consideration_allocnos, int n)
{
int i, length;
ira_allocno_t a;
allocno_live_range_t r;
for (i = 0; i < n; i++)
{
a = consideration_allocnos[i];
for (length = 0, r = ALLOCNO_LIVE_RANGES (a); r != NULL; r = r->next)
length += r->finish - r->start + 1;
if (length == 0)
{
allocno_priorities[ALLOCNO_NUM (a)] = 0;
continue;
}
ira_assert (length > 0 && ALLOCNO_NREFS (a) >= 0);
allocno_priorities[ALLOCNO_NUM (a)]
= (((double) (floor_log2 (ALLOCNO_NREFS (a)) * ALLOCNO_FREQ (a))
/ length)
* (10000 / REG_FREQ_MAX) * PSEUDO_REGNO_SIZE (ALLOCNO_REGNO (a)));
}
}
/* Sort allocnos according to their priorities which are calculated
analogous to ones in file `global.c'. */
static int
allocno_priority_compare_func (const void *v1p, const void *v2p)
{
ira_allocno_t a1 = *(const ira_allocno_t *) v1p;
ira_allocno_t a2 = *(const ira_allocno_t *) v2p;
int pri1, pri2;
pri1 = allocno_priorities[ALLOCNO_NUM (a1)];
pri2 = allocno_priorities[ALLOCNO_NUM (a2)];
if (pri2 - pri1)
return pri2 - pri1;
/* If regs are equally good, sort by allocnos, so that the results of
qsort leave nothing to chance. */
return ALLOCNO_NUM (a1) - ALLOCNO_NUM (a2);
}
/* Try to assign hard registers to the unassigned allocnos and
allocnos conflicting with them or conflicting with allocnos whose
regno >= START_REGNO. The function is called after ira_flattening,
so more allocnos (including ones created in ira-emit.c) will have a
chance to get a hard register. We use simple assignment algorithm
based on priorities. */
void
ira_reassign_conflict_allocnos (int start_regno)
{
int i, allocnos_to_color_num;
ira_allocno_t a, conflict_a;
ira_allocno_conflict_iterator aci;
enum reg_class cover_class;
bitmap allocnos_to_color;
ira_allocno_iterator ai;
allocnos_to_color = ira_allocate_bitmap ();
allocnos_to_color_num = 0;
FOR_EACH_ALLOCNO (a, ai)
{
if (! ALLOCNO_ASSIGNED_P (a)
&& ! bitmap_bit_p (allocnos_to_color, ALLOCNO_NUM (a)))
{
if (ALLOCNO_COVER_CLASS (a) != NO_REGS)
sorted_allocnos[allocnos_to_color_num++] = a;
else
{
ALLOCNO_ASSIGNED_P (a) = true;
ALLOCNO_HARD_REGNO (a) = -1;
ira_assert (ALLOCNO_UPDATED_HARD_REG_COSTS (a) == NULL);
ira_assert (ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (a) == NULL);
}
bitmap_set_bit (allocnos_to_color, ALLOCNO_NUM (a));
}
if (ALLOCNO_REGNO (a) < start_regno
|| (cover_class = ALLOCNO_COVER_CLASS (a)) == NO_REGS)
continue;
FOR_EACH_ALLOCNO_CONFLICT (a, conflict_a, aci)
{
ira_assert (cover_class == ALLOCNO_COVER_CLASS (conflict_a));
if (bitmap_bit_p (allocnos_to_color, ALLOCNO_NUM (conflict_a)))
continue;
bitmap_set_bit (allocnos_to_color, ALLOCNO_NUM (conflict_a));
sorted_allocnos[allocnos_to_color_num++] = conflict_a;
}
}
ira_free_bitmap (allocnos_to_color);
if (allocnos_to_color_num > 1)
{
start_allocno_priorities (sorted_allocnos, allocnos_to_color_num);
qsort (sorted_allocnos, allocnos_to_color_num, sizeof (ira_allocno_t),
allocno_priority_compare_func);
}
for (i = 0; i < allocnos_to_color_num; i++)
{
a = sorted_allocnos[i];
ALLOCNO_ASSIGNED_P (a) = false;
ira_assert (ALLOCNO_UPDATED_HARD_REG_COSTS (a) == NULL);
ira_assert (ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (a) == NULL);
update_curr_costs (a);
}
for (i = 0; i < allocnos_to_color_num; i++)
{
a = sorted_allocnos[i];
if (assign_hard_reg (a, true))
{
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf
(ira_dump_file,
" Secondary allocation: assign hard reg %d to reg %d\n",
ALLOCNO_HARD_REGNO (a), ALLOCNO_REGNO (a));
}
}
}
/* This page contains code to coalesce memory stack slots used by
spilled allocnos. This results in smaller stack frame, better data
locality, and in smaller code for some architectures like
x86/x86_64 where insn size depends on address displacement value.
On the other hand, it can worsen insn scheduling after the RA but
in practice it is less important than smaller stack frames. */
/* Usage cost and order number of coalesced allocno set to which
given pseudo register belongs to. */
static int *regno_coalesced_allocno_cost;
static int *regno_coalesced_allocno_num;
/* Sort pseudos according frequencies of coalesced allocno sets they
belong to (putting most frequently ones first), and according to
coalesced allocno set order numbers. */
static int
coalesced_pseudo_reg_freq_compare (const void *v1p, const void *v2p)
{
const int regno1 = *(const int *) v1p;
const int regno2 = *(const int *) v2p;
int diff;
if ((diff = (regno_coalesced_allocno_cost[regno2]
- regno_coalesced_allocno_cost[regno1])) != 0)
return diff;
if ((diff = (regno_coalesced_allocno_num[regno1]
- regno_coalesced_allocno_num[regno2])) != 0)
return diff;
return regno1 - regno2;
}
/* Widest width in which each pseudo reg is referred to (via subreg).
It is used for sorting pseudo registers. */
static unsigned int *regno_max_ref_width;
/* Redefine STACK_GROWS_DOWNWARD in terms of 0 or 1. */
#ifdef STACK_GROWS_DOWNWARD
# undef STACK_GROWS_DOWNWARD
# define STACK_GROWS_DOWNWARD 1
#else
# define STACK_GROWS_DOWNWARD 0
#endif
/* Sort pseudos according their slot numbers (putting ones with
smaller numbers first, or last when the frame pointer is not
needed). */
static int
coalesced_pseudo_reg_slot_compare (const void *v1p, const void *v2p)
{
const int regno1 = *(const int *) v1p;
const int regno2 = *(const int *) v2p;
ira_allocno_t a1 = ira_regno_allocno_map[regno1];
ira_allocno_t a2 = ira_regno_allocno_map[regno2];
int diff, slot_num1, slot_num2;
int total_size1, total_size2;
if (a1 == NULL || ALLOCNO_HARD_REGNO (a1) >= 0)
{
if (a2 == NULL || ALLOCNO_HARD_REGNO (a2) >= 0)
return (const int *) v1p - (const int *) v2p; /* Save the order. */
return 1;
}
else if (a2 == NULL || ALLOCNO_HARD_REGNO (a2) >= 0)
return -1;
slot_num1 = -ALLOCNO_HARD_REGNO (a1);
slot_num2 = -ALLOCNO_HARD_REGNO (a2);
if ((diff = slot_num1 - slot_num2) != 0)
return (frame_pointer_needed
|| !FRAME_GROWS_DOWNWARD == STACK_GROWS_DOWNWARD ? diff : -diff);
total_size1 = MAX (PSEUDO_REGNO_BYTES (regno1), regno_max_ref_width[regno1]);
total_size2 = MAX (PSEUDO_REGNO_BYTES (regno2), regno_max_ref_width[regno2]);
if ((diff = total_size2 - total_size1) != 0)
return diff;
return (const int *) v1p - (const int *) v2p; /* Save the order. */
}
/* Setup REGNO_COALESCED_ALLOCNO_COST and REGNO_COALESCED_ALLOCNO_NUM
for coalesced allocno sets containing allocnos with their regnos
given in array PSEUDO_REGNOS of length N. */
static void
setup_coalesced_allocno_costs_and_nums (int *pseudo_regnos, int n)
{
int i, num, regno, cost;
ira_allocno_t allocno, a;
for (num = i = 0; i < n; i++)
{
regno = pseudo_regnos[i];
allocno = ira_regno_allocno_map[regno];
if (allocno == NULL)
{
regno_coalesced_allocno_cost[regno] = 0;
regno_coalesced_allocno_num[regno] = ++num;
continue;
}
if (ALLOCNO_FIRST_COALESCED_ALLOCNO (allocno) != allocno)
continue;
num++;
for (cost = 0, a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
cost += ALLOCNO_FREQ (a);
if (a == allocno)
break;
}
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
regno_coalesced_allocno_num[ALLOCNO_REGNO (a)] = num;
regno_coalesced_allocno_cost[ALLOCNO_REGNO (a)] = cost;
if (a == allocno)
break;
}
}
}
/* Collect spilled allocnos representing coalesced allocno sets (the
first coalesced allocno). The collected allocnos are returned
through array SPILLED_COALESCED_ALLOCNOS. The function returns the
number of the collected allocnos. The allocnos are given by their
regnos in array PSEUDO_REGNOS of length N. */
static int
collect_spilled_coalesced_allocnos (int *pseudo_regnos, int n,
ira_allocno_t *spilled_coalesced_allocnos)
{
int i, num, regno;
ira_allocno_t allocno;
for (num = i = 0; i < n; i++)
{
regno = pseudo_regnos[i];
allocno = ira_regno_allocno_map[regno];
if (allocno == NULL || ALLOCNO_HARD_REGNO (allocno) >= 0
|| ALLOCNO_FIRST_COALESCED_ALLOCNO (allocno) != allocno)
continue;
spilled_coalesced_allocnos[num++] = allocno;
}
return num;
}
/* We have coalesced allocnos involving in copies. Coalesce allocnos
further in order to share the same memory stack slot. Allocnos
representing sets of allocnos coalesced before the call are given
in array SPILLED_COALESCED_ALLOCNOS of length NUM. Return TRUE if
some allocnos were coalesced in the function. */
static bool
coalesce_spill_slots (ira_allocno_t *spilled_coalesced_allocnos, int num)
{
int i, j;
ira_allocno_t allocno, a;
bool merged_p = false;
/* Coalesce non-conflicting spilled allocnos preferring most
frequently used. */
for (i = 0; i < num; i++)
{
allocno = spilled_coalesced_allocnos[i];
if (ALLOCNO_FIRST_COALESCED_ALLOCNO (allocno) != allocno
|| (ALLOCNO_REGNO (allocno) < ira_reg_equiv_len
&& (ira_reg_equiv_invariant_p[ALLOCNO_REGNO (allocno)]
|| ira_reg_equiv_const[ALLOCNO_REGNO (allocno)] != NULL_RTX)))
continue;
for (j = 0; j < i; j++)
{
a = spilled_coalesced_allocnos[j];
if (ALLOCNO_FIRST_COALESCED_ALLOCNO (a) != a
|| (ALLOCNO_REGNO (a) < ira_reg_equiv_len
&& (ira_reg_equiv_invariant_p[ALLOCNO_REGNO (a)]
|| ira_reg_equiv_const[ALLOCNO_REGNO (a)] != NULL_RTX))
|| coalesced_allocno_conflict_p (allocno, a, true))
continue;
allocno_coalesced_p = true;
merged_p = true;
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file,
" Coalescing spilled allocnos a%dr%d->a%dr%d\n",
ALLOCNO_NUM (allocno), ALLOCNO_REGNO (allocno),
ALLOCNO_NUM (a), ALLOCNO_REGNO (a));
merge_allocnos (a, allocno);
ira_assert (ALLOCNO_FIRST_COALESCED_ALLOCNO (a) == a);
}
}
return merged_p;
}
/* Sort pseudo-register numbers in array PSEUDO_REGNOS of length N for
subsequent assigning stack slots to them in the reload pass. To do
this we coalesce spilled allocnos first to decrease the number of
memory-memory move insns. This function is called by the
reload. */
void
ira_sort_regnos_for_alter_reg (int *pseudo_regnos, int n,
unsigned int *reg_max_ref_width)
{
int max_regno = max_reg_num ();
int i, regno, num, slot_num;
ira_allocno_t allocno, a;
ira_allocno_iterator ai;
ira_allocno_t *spilled_coalesced_allocnos;
processed_coalesced_allocno_bitmap = ira_allocate_bitmap ();
/* Set up allocnos can be coalesced. */
coloring_allocno_bitmap = ira_allocate_bitmap ();
for (i = 0; i < n; i++)
{
regno = pseudo_regnos[i];
allocno = ira_regno_allocno_map[regno];
if (allocno != NULL)
bitmap_set_bit (coloring_allocno_bitmap,
ALLOCNO_NUM (allocno));
}
allocno_coalesced_p = false;
coalesce_allocnos (true);
ira_free_bitmap (coloring_allocno_bitmap);
regno_coalesced_allocno_cost
= (int *) ira_allocate (max_regno * sizeof (int));
regno_coalesced_allocno_num
= (int *) ira_allocate (max_regno * sizeof (int));
memset (regno_coalesced_allocno_num, 0, max_regno * sizeof (int));
setup_coalesced_allocno_costs_and_nums (pseudo_regnos, n);
/* Sort regnos according frequencies of the corresponding coalesced
allocno sets. */
qsort (pseudo_regnos, n, sizeof (int), coalesced_pseudo_reg_freq_compare);
spilled_coalesced_allocnos
= (ira_allocno_t *) ira_allocate (ira_allocnos_num
* sizeof (ira_allocno_t));
/* Collect allocnos representing the spilled coalesced allocno
sets. */
num = collect_spilled_coalesced_allocnos (pseudo_regnos, n,
spilled_coalesced_allocnos);
if (flag_ira_share_spill_slots
&& coalesce_spill_slots (spilled_coalesced_allocnos, num))
{
setup_coalesced_allocno_costs_and_nums (pseudo_regnos, n);
qsort (pseudo_regnos, n, sizeof (int),
coalesced_pseudo_reg_freq_compare);
num = collect_spilled_coalesced_allocnos (pseudo_regnos, n,
spilled_coalesced_allocnos);
}
ira_free_bitmap (processed_coalesced_allocno_bitmap);
allocno_coalesced_p = false;
/* Assign stack slot numbers to spilled allocno sets, use smaller
numbers for most frequently used coalesced allocnos. -1 is
reserved for dynamic search of stack slots for pseudos spilled by
the reload. */
slot_num = 1;
for (i = 0; i < num; i++)
{
allocno = spilled_coalesced_allocnos[i];
if (ALLOCNO_FIRST_COALESCED_ALLOCNO (allocno) != allocno
|| ALLOCNO_HARD_REGNO (allocno) >= 0
|| (ALLOCNO_REGNO (allocno) < ira_reg_equiv_len
&& (ira_reg_equiv_invariant_p[ALLOCNO_REGNO (allocno)]
|| ira_reg_equiv_const[ALLOCNO_REGNO (allocno)] != NULL_RTX)))
continue;
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file, " Slot %d (freq,size):", slot_num);
slot_num++;
for (a = ALLOCNO_NEXT_COALESCED_ALLOCNO (allocno);;
a = ALLOCNO_NEXT_COALESCED_ALLOCNO (a))
{
ira_assert (ALLOCNO_HARD_REGNO (a) < 0);
ALLOCNO_HARD_REGNO (a) = -slot_num;
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file, " a%dr%d(%d,%d)",
ALLOCNO_NUM (a), ALLOCNO_REGNO (a), ALLOCNO_FREQ (a),
MAX (PSEUDO_REGNO_BYTES (ALLOCNO_REGNO (a)),
reg_max_ref_width[ALLOCNO_REGNO (a)]));
if (a == allocno)
break;
}
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file, "\n");
}
ira_spilled_reg_stack_slots_num = slot_num - 1;
ira_free (spilled_coalesced_allocnos);
/* Sort regnos according the slot numbers. */
regno_max_ref_width = reg_max_ref_width;
qsort (pseudo_regnos, n, sizeof (int), coalesced_pseudo_reg_slot_compare);
/* Uncoalesce allocnos which is necessary for (re)assigning during
the reload pass. */
FOR_EACH_ALLOCNO (a, ai)
{
ALLOCNO_FIRST_COALESCED_ALLOCNO (a) = a;
ALLOCNO_NEXT_COALESCED_ALLOCNO (a) = a;
}
ira_free (regno_coalesced_allocno_num);
ira_free (regno_coalesced_allocno_cost);
}
/* This page contains code used by the reload pass to improve the
final code. */
/* The function is called from reload to mark changes in the
allocation of REGNO made by the reload. Remember that reg_renumber
reflects the change result. */
void
ira_mark_allocation_change (int regno)
{
ira_allocno_t a = ira_regno_allocno_map[regno];
int old_hard_regno, hard_regno, cost;
enum reg_class cover_class = ALLOCNO_COVER_CLASS (a);
ira_assert (a != NULL);
hard_regno = reg_renumber[regno];
if ((old_hard_regno = ALLOCNO_HARD_REGNO (a)) == hard_regno)
return;
if (old_hard_regno < 0)
cost = -ALLOCNO_MEMORY_COST (a);
else
{
ira_assert (ira_class_hard_reg_index[cover_class][old_hard_regno] >= 0);
cost = -(ALLOCNO_HARD_REG_COSTS (a) == NULL
? ALLOCNO_COVER_CLASS_COST (a)
: ALLOCNO_HARD_REG_COSTS (a)
[ira_class_hard_reg_index[cover_class][old_hard_regno]]);
update_copy_costs (a, false);
}
ira_overall_cost -= cost;
ALLOCNO_HARD_REGNO (a) = hard_regno;
if (hard_regno < 0)
{
ALLOCNO_HARD_REGNO (a) = -1;
cost += ALLOCNO_MEMORY_COST (a);
}
else if (ira_class_hard_reg_index[cover_class][hard_regno] >= 0)
{
cost += (ALLOCNO_HARD_REG_COSTS (a) == NULL
? ALLOCNO_COVER_CLASS_COST (a)
: ALLOCNO_HARD_REG_COSTS (a)
[ira_class_hard_reg_index[cover_class][hard_regno]]);
update_copy_costs (a, true);
}
else
/* Reload changed class of the allocno. */
cost = 0;
ira_overall_cost += cost;
}
/* This function is called when reload deletes memory-memory move. In
this case we marks that the allocation of the corresponding
allocnos should be not changed in future. Otherwise we risk to get
a wrong code. */
void
ira_mark_memory_move_deletion (int dst_regno, int src_regno)
{
ira_allocno_t dst = ira_regno_allocno_map[dst_regno];
ira_allocno_t src = ira_regno_allocno_map[src_regno];
ira_assert (dst != NULL && src != NULL
&& ALLOCNO_HARD_REGNO (dst) < 0
&& ALLOCNO_HARD_REGNO (src) < 0);
ALLOCNO_DONT_REASSIGN_P (dst) = true;
ALLOCNO_DONT_REASSIGN_P (src) = true;
}
/* Try to assign a hard register (except for FORBIDDEN_REGS) to
allocno A and return TRUE in the case of success. That is an
analog of retry_global_alloc for IRA. */
static bool
allocno_reload_assign (ira_allocno_t a, HARD_REG_SET forbidden_regs)
{
int hard_regno;
enum reg_class cover_class;
int regno = ALLOCNO_REGNO (a);
IOR_HARD_REG_SET (ALLOCNO_TOTAL_CONFLICT_HARD_REGS (a), forbidden_regs);
if (! flag_caller_saves && ALLOCNO_CALLS_CROSSED_NUM (a) != 0)
IOR_HARD_REG_SET (ALLOCNO_TOTAL_CONFLICT_HARD_REGS (a), call_used_reg_set);
ALLOCNO_ASSIGNED_P (a) = false;
ira_assert (ALLOCNO_UPDATED_HARD_REG_COSTS (a) == NULL);
ira_assert (ALLOCNO_UPDATED_CONFLICT_HARD_REG_COSTS (a) == NULL);
cover_class = ALLOCNO_COVER_CLASS (a);
update_curr_costs (a);
assign_hard_reg (a, true);
hard_regno = ALLOCNO_HARD_REGNO (a);
reg_renumber[regno] = hard_regno;
if (hard_regno < 0)
ALLOCNO_HARD_REGNO (a) = -1;
else
{
ira_assert (ira_class_hard_reg_index[cover_class][hard_regno] >= 0);
ira_overall_cost -= (ALLOCNO_MEMORY_COST (a)
- (ALLOCNO_HARD_REG_COSTS (a) == NULL
? ALLOCNO_COVER_CLASS_COST (a)
: ALLOCNO_HARD_REG_COSTS (a)
[ira_class_hard_reg_index
[cover_class][hard_regno]]));
if (ALLOCNO_CALLS_CROSSED_NUM (a) != 0
&& ! ira_hard_reg_not_in_set_p (hard_regno, ALLOCNO_MODE (a),
call_used_reg_set))
{
ira_assert (flag_caller_saves);
caller_save_needed = 1;
}
}
/* If we found a hard register, modify the RTL for the pseudo
register to show the hard register, and mark the pseudo register
live. */
if (reg_renumber[regno] >= 0)
{
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file, ": reassign to %d\n", reg_renumber[regno]);
SET_REGNO (regno_reg_rtx[regno], reg_renumber[regno]);
mark_home_live (regno);
}
else if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file, "\n");
return reg_renumber[regno] >= 0;
}
/* Sort pseudos according their usage frequencies (putting most
frequently ones first). */
static int
pseudo_reg_compare (const void *v1p, const void *v2p)
{
int regno1 = *(const int *) v1p;
int regno2 = *(const int *) v2p;
int diff;
if ((diff = REG_FREQ (regno2) - REG_FREQ (regno1)) != 0)
return diff;
return regno1 - regno2;
}
/* Try to allocate hard registers to SPILLED_PSEUDO_REGS (there are
NUM of them) or spilled pseudos conflicting with pseudos in
SPILLED_PSEUDO_REGS. Return TRUE and update SPILLED, if the
allocation has been changed. The function doesn't use
BAD_SPILL_REGS and hard registers in PSEUDO_FORBIDDEN_REGS and
PSEUDO_PREVIOUS_REGS for the corresponding pseudos. The function
is called by the reload pass at the end of each reload
iteration. */
bool
ira_reassign_pseudos (int *spilled_pseudo_regs, int num,
HARD_REG_SET bad_spill_regs,
HARD_REG_SET *pseudo_forbidden_regs,
HARD_REG_SET *pseudo_previous_regs, bitmap spilled)
{
int i, m, n, regno;
bool changed_p;
ira_allocno_t a, conflict_a;
HARD_REG_SET forbidden_regs;
ira_allocno_conflict_iterator aci;
if (num > 1)
qsort (spilled_pseudo_regs, num, sizeof (int), pseudo_reg_compare);
changed_p = false;
/* Try to assign hard registers to pseudos from
SPILLED_PSEUDO_REGS. */
for (m = i = 0; i < num; i++)
{
regno = spilled_pseudo_regs[i];
COPY_HARD_REG_SET (forbidden_regs, bad_spill_regs);
IOR_HARD_REG_SET (forbidden_regs, pseudo_forbidden_regs[regno]);
IOR_HARD_REG_SET (forbidden_regs, pseudo_previous_regs[regno]);
gcc_assert (reg_renumber[regno] < 0);
a = ira_regno_allocno_map[regno];
ira_mark_allocation_change (regno);
ira_assert (reg_renumber[regno] < 0);
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file,
" Spill %d(a%d), cost=%d", regno, ALLOCNO_NUM (a),
ALLOCNO_MEMORY_COST (a)
- ALLOCNO_COVER_CLASS_COST (a));
allocno_reload_assign (a, forbidden_regs);
if (reg_renumber[regno] >= 0)
{
CLEAR_REGNO_REG_SET (spilled, regno);
changed_p = true;
}
else
spilled_pseudo_regs[m++] = regno;
}
if (m == 0)
return changed_p;
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
{
fprintf (ira_dump_file, " Spilled regs");
for (i = 0; i < m; i++)
fprintf (ira_dump_file, " %d", spilled_pseudo_regs[i]);
fprintf (ira_dump_file, "\n");
}
/* Try to assign hard registers to pseudos conflicting with ones
from SPILLED_PSEUDO_REGS. */
for (i = n = 0; i < m; i++)
{
regno = spilled_pseudo_regs[i];
a = ira_regno_allocno_map[regno];
FOR_EACH_ALLOCNO_CONFLICT (a, conflict_a, aci)
if (ALLOCNO_HARD_REGNO (conflict_a) < 0
&& ! ALLOCNO_DONT_REASSIGN_P (conflict_a)
&& ! bitmap_bit_p (consideration_allocno_bitmap,
ALLOCNO_NUM (conflict_a)))
{
sorted_allocnos[n++] = conflict_a;
bitmap_set_bit (consideration_allocno_bitmap,
ALLOCNO_NUM (conflict_a));
}
}
if (n != 0)
{
start_allocno_priorities (sorted_allocnos, n);
qsort (sorted_allocnos, n, sizeof (ira_allocno_t),
allocno_priority_compare_func);
for (i = 0; i < n; i++)
{
a = sorted_allocnos[i];
regno = ALLOCNO_REGNO (a);
COPY_HARD_REG_SET (forbidden_regs, bad_spill_regs);
IOR_HARD_REG_SET (forbidden_regs, pseudo_forbidden_regs[regno]);
IOR_HARD_REG_SET (forbidden_regs, pseudo_previous_regs[regno]);
if (internal_flag_ira_verbose > 3 && ira_dump_file != NULL)
fprintf (ira_dump_file,
" Try assign %d(a%d), cost=%d",
regno, ALLOCNO_NUM (a),
ALLOCNO_MEMORY_COST (a)
- ALLOCNO_COVER_CLASS_COST (a));
if (allocno_reload_assign (a, forbidden_regs))
{
changed_p = true;
bitmap_clear_bit (spilled, regno);
}
}
}
return changed_p;
}
/* The function is called by reload and returns already allocated
stack slot (if any) for REGNO with given INHERENT_SIZE and
TOTAL_SIZE. In the case of failure to find a slot which can be
used for REGNO, the function returns NULL. */
rtx
ira_reuse_stack_slot (int regno, unsigned int inherent_size,
unsigned int total_size)
{
unsigned int i;
int slot_num, best_slot_num;
int cost, best_cost;
ira_copy_t cp, next_cp;
ira_allocno_t another_allocno, allocno = ira_regno_allocno_map[regno];
rtx x;
bitmap_iterator bi;
struct ira_spilled_reg_stack_slot *slot = NULL;
ira_assert (flag_ira && inherent_size == PSEUDO_REGNO_BYTES (regno)
&& inherent_size <= total_size
&& ALLOCNO_HARD_REGNO (allocno) < 0);
if (! flag_ira_share_spill_slots)
return NULL_RTX;
slot_num = -ALLOCNO_HARD_REGNO (allocno) - 2;
if (slot_num != -1)
{
slot = &ira_spilled_reg_stack_slots[slot_num];
x = slot->mem;
}
else
{
best_cost = best_slot_num = -1;
x = NULL_RTX;
/* It means that the pseudo was spilled in the reload pass, try
to reuse a slot. */
for (slot_num = 0;
slot_num < ira_spilled_reg_stack_slots_num;
slot_num++)
{
slot = &ira_spilled_reg_stack_slots[slot_num];
if (slot->mem == NULL_RTX)
continue;
if (slot->width < total_size
|| GET_MODE_SIZE (GET_MODE (slot->mem)) < inherent_size)
continue;
EXECUTE_IF_SET_IN_BITMAP (&slot->spilled_regs,
FIRST_PSEUDO_REGISTER, i, bi)
{
another_allocno = ira_regno_allocno_map[i];
if (ira_allocno_live_ranges_intersect_p (allocno,
another_allocno))
goto cont;
}
for (cost = 0, cp = ALLOCNO_COPIES (allocno);
cp != NULL;
cp = next_cp)
{
if (cp->first == allocno)
{
next_cp = cp->next_first_allocno_copy;
another_allocno = cp->second;
}
else if (cp->second == allocno)
{
next_cp = cp->next_second_allocno_copy;
another_allocno = cp->first;
}
else
gcc_unreachable ();
if (cp->insn == NULL_RTX)
continue;
if (bitmap_bit_p (&slot->spilled_regs,
ALLOCNO_REGNO (another_allocno)))
cost += cp->freq;
}
if (cost > best_cost)
{
best_cost = cost;
best_slot_num = slot_num;
}
cont:
;
}
if (best_cost >= 0)
{
slot = &ira_spilled_reg_stack_slots[best_slot_num];
SET_REGNO_REG_SET (&slot->spilled_regs, regno);
x = slot->mem;
ALLOCNO_HARD_REGNO (allocno) = -best_slot_num - 2;
}
}
if (x != NULL_RTX)
{
ira_assert (slot->width >= total_size);
EXECUTE_IF_SET_IN_BITMAP (&slot->spilled_regs,
FIRST_PSEUDO_REGISTER, i, bi)
{
ira_assert (! ira_pseudo_live_ranges_intersect_p (regno, i));
}
SET_REGNO_REG_SET (&slot->spilled_regs, regno);
if (internal_flag_ira_verbose > 3 && ira_dump_file)
{
fprintf (ira_dump_file, " Assigning %d(freq=%d) slot %d of",
regno, REG_FREQ (regno), slot_num);
EXECUTE_IF_SET_IN_BITMAP (&slot->spilled_regs,
FIRST_PSEUDO_REGISTER, i, bi)
{
if ((unsigned) regno != i)
fprintf (ira_dump_file, " %d", i);
}
fprintf (ira_dump_file, "\n");
}
}
return x;
}
/* This is called by reload every time a new stack slot X with
TOTAL_SIZE was allocated for REGNO. We store this info for
subsequent ira_reuse_stack_slot calls. */
void
ira_mark_new_stack_slot (rtx x, int regno, unsigned int total_size)
{
struct ira_spilled_reg_stack_slot *slot;
int slot_num;
ira_allocno_t allocno;
ira_assert (flag_ira && PSEUDO_REGNO_BYTES (regno) <= total_size);
allocno = ira_regno_allocno_map[regno];
slot_num = -ALLOCNO_HARD_REGNO (allocno) - 2;
if (slot_num == -1)
{
slot_num = ira_spilled_reg_stack_slots_num++;
ALLOCNO_HARD_REGNO (allocno) = -slot_num - 2;
}
slot = &ira_spilled_reg_stack_slots[slot_num];
INIT_REG_SET (&slot->spilled_regs);
SET_REGNO_REG_SET (&slot->spilled_regs, regno);
slot->mem = x;
slot->width = total_size;
if (internal_flag_ira_verbose > 3 && ira_dump_file)
fprintf (ira_dump_file, " Assigning %d(freq=%d) a new slot %d\n",
regno, REG_FREQ (regno), slot_num);
}
/* Return spill cost for pseudo-registers whose numbers are in array
REGNOS (with a negative number as an end marker) for reload with
given IN and OUT for INSN. Return also number points (through
EXCESS_PRESSURE_LIVE_LENGTH) where the pseudo-register lives and
the register pressure is high, number of references of the
pseudo-registers (through NREFS), number of callee-clobbered
hard-registers occupied by the pseudo-registers (through
CALL_USED_COUNT), and the first hard regno occupied by the
pseudo-registers (through FIRST_HARD_REGNO). */
static int
calculate_spill_cost (int *regnos, rtx in, rtx out, rtx insn,
int *excess_pressure_live_length,
int *nrefs, int *call_used_count, int *first_hard_regno)
{
int i, cost, regno, hard_regno, j, count, saved_cost, nregs;
bool in_p, out_p;
int length;
ira_allocno_t a;
*nrefs = 0;
for (length = count = cost = i = 0;; i++)
{
regno = regnos[i];
if (regno < 0)
break;
*nrefs += REG_N_REFS (regno);
hard_regno = reg_renumber[regno];
ira_assert (hard_regno >= 0);
a = ira_regno_allocno_map[regno];
length += ALLOCNO_EXCESS_PRESSURE_POINTS_NUM (a);
cost += ALLOCNO_MEMORY_COST (a) - ALLOCNO_COVER_CLASS_COST (a);
nregs = hard_regno_nregs[hard_regno][ALLOCNO_MODE (a)];
for (j = 0; j < nregs; j++)
if (! TEST_HARD_REG_BIT (call_used_reg_set, hard_regno + j))
break;
if (j == nregs)
count++;
in_p = in && REG_P (in) && (int) REGNO (in) == hard_regno;
out_p = out && REG_P (out) && (int) REGNO (out) == hard_regno;
if ((in_p || out_p)
&& find_regno_note (insn, REG_DEAD, hard_regno) != NULL_RTX)
{
saved_cost = 0;
if (in_p)
saved_cost += ira_memory_move_cost
[ALLOCNO_MODE (a)][ALLOCNO_COVER_CLASS (a)][1];
if (out_p)
saved_cost
+= ira_memory_move_cost
[ALLOCNO_MODE (a)][ALLOCNO_COVER_CLASS (a)][0];
cost -= REG_FREQ_FROM_BB (BLOCK_FOR_INSN (insn)) * saved_cost;
}
}
*excess_pressure_live_length = length;
*call_used_count = count;
hard_regno = -1;
if (regnos[0] >= 0)
{
hard_regno = reg_renumber[regnos[0]];
}
*first_hard_regno = hard_regno;
return cost;
}
/* Return TRUE if spilling pseudo-registers whose numbers are in array
REGNOS is better than spilling pseudo-registers with numbers in
OTHER_REGNOS for reload with given IN and OUT for INSN. The
function used by the reload pass to make better register spilling
decisions. */
bool
ira_better_spill_reload_regno_p (int *regnos, int *other_regnos,
rtx in, rtx out, rtx insn)
{
int cost, other_cost;
int length, other_length;
int nrefs, other_nrefs;
int call_used_count, other_call_used_count;
int hard_regno, other_hard_regno;
cost = calculate_spill_cost (regnos, in, out, insn,
&length, &nrefs, &call_used_count, &hard_regno);
other_cost = calculate_spill_cost (other_regnos, in, out, insn,
&other_length, &other_nrefs,
&other_call_used_count,
&other_hard_regno);
if (nrefs == 0 && other_nrefs != 0)
return true;
if (nrefs != 0 && other_nrefs == 0)
return false;
if (cost != other_cost)
return cost < other_cost;
if (length != other_length)
return length > other_length;
#ifdef REG_ALLOC_ORDER
if (hard_regno >= 0 && other_hard_regno >= 0)
return (inv_reg_alloc_order[hard_regno]
< inv_reg_alloc_order[other_hard_regno]);
#else
if (call_used_count != other_call_used_count)
return call_used_count > other_call_used_count;
#endif
return false;
}
/* Allocate and initialize data necessary for assign_hard_reg. */
void
ira_initiate_assign (void)
{
sorted_allocnos
= (ira_allocno_t *) ira_allocate (sizeof (ira_allocno_t)
* ira_allocnos_num);
consideration_allocno_bitmap = ira_allocate_bitmap ();
initiate_cost_update ();
allocno_priorities = (int *) ira_allocate (sizeof (int) * ira_allocnos_num);
}
/* Deallocate data used by assign_hard_reg. */
void
ira_finish_assign (void)
{
ira_free (sorted_allocnos);
ira_free_bitmap (consideration_allocno_bitmap);
finish_cost_update ();
ira_free (allocno_priorities);
}
/* Entry function doing color-based register allocation. */
void
ira_color (void)
{
allocno_stack_vec = VEC_alloc (ira_allocno_t, heap, ira_allocnos_num);
conflict_allocno_vec = VEC_alloc (ira_allocno_t, heap, ira_allocnos_num);
removed_splay_allocno_vec
= VEC_alloc (ira_allocno_t, heap, ira_allocnos_num);
memset (allocated_hardreg_p, 0, sizeof (allocated_hardreg_p));
ira_initiate_assign ();
do_coloring ();
ira_finish_assign ();
VEC_free (ira_allocno_t, heap, removed_splay_allocno_vec);
VEC_free (ira_allocno_t, heap, conflict_allocno_vec);
VEC_free (ira_allocno_t, heap, allocno_stack_vec);
move_spill_restore ();
}
/* This page contains a simple register allocator without usage of
allocno conflicts. This is used for fast allocation for -O0. */
/* Do register allocation by not using allocno conflicts. It uses
only allocno live ranges. The algorithm is close to Chow's
priority coloring. */
void
ira_fast_allocation (void)
{
int i, j, k, l, num, class_size, hard_regno;
#ifdef STACK_REGS
bool no_stack_reg_p;
#endif
enum reg_class cover_class;
enum machine_mode mode;
ira_allocno_t a;
ira_allocno_iterator ai;
allocno_live_range_t r;
HARD_REG_SET conflict_hard_regs, *used_hard_regs;
allocno_priorities = (int *) ira_allocate (sizeof (int) * ira_allocnos_num);
FOR_EACH_ALLOCNO (a, ai)
{
l = ALLOCNO_EXCESS_PRESSURE_POINTS_NUM (a);
if (l <= 0)
l = 1;
allocno_priorities[ALLOCNO_NUM (a)]
= (((double) (floor_log2 (ALLOCNO_NREFS (a))
* (ALLOCNO_MEMORY_COST (a)
- ALLOCNO_COVER_CLASS_COST (a))) / l)
* (10000 / REG_FREQ_MAX)
* ira_reg_class_nregs[ALLOCNO_COVER_CLASS (a)][ALLOCNO_MODE (a)]);
}
used_hard_regs = (HARD_REG_SET *) ira_allocate (sizeof (HARD_REG_SET)
* ira_max_point);
for (i = 0; i < ira_max_point; i++)
CLEAR_HARD_REG_SET (used_hard_regs[i]);
sorted_allocnos = (ira_allocno_t *) ira_allocate (sizeof (ira_allocno_t)
* ira_allocnos_num);
num = 0;
FOR_EACH_ALLOCNO (a, ai)
sorted_allocnos[num++] = a;
qsort (sorted_allocnos, ira_allocnos_num, sizeof (ira_allocno_t),
allocno_priority_compare_func);
for (i = 0; i < num; i++)
{
a = sorted_allocnos[i];
COPY_HARD_REG_SET (conflict_hard_regs, ALLOCNO_CONFLICT_HARD_REGS (a));
for (r = ALLOCNO_LIVE_RANGES (a); r != NULL; r = r->next)
for (j = r->start; j <= r->finish; j++)
IOR_HARD_REG_SET (conflict_hard_regs, used_hard_regs[j]);
cover_class = ALLOCNO_COVER_CLASS (a);
ALLOCNO_ASSIGNED_P (a) = true;
ALLOCNO_HARD_REGNO (a) = -1;
if (hard_reg_set_subset_p (reg_class_contents[cover_class],
conflict_hard_regs))
continue;
mode = ALLOCNO_MODE (a);
#ifdef STACK_REGS
no_stack_reg_p = ALLOCNO_NO_STACK_REG_P (a);
#endif
class_size = ira_class_hard_regs_num[cover_class];
for (j = 0; j < class_size; j++)
{
hard_regno = ira_class_hard_regs[cover_class][j];
#ifdef STACK_REGS
if (no_stack_reg_p && FIRST_STACK_REG <= hard_regno
&& hard_regno <= LAST_STACK_REG)
continue;
#endif
if (!ira_hard_reg_not_in_set_p (hard_regno, mode, conflict_hard_regs)
|| (TEST_HARD_REG_BIT
(prohibited_class_mode_regs[cover_class][mode], hard_regno)))
continue;
ALLOCNO_HARD_REGNO (a) = hard_regno;
for (r = ALLOCNO_LIVE_RANGES (a); r != NULL; r = r->next)
for (k = r->start; k <= r->finish; k++)
IOR_HARD_REG_SET (used_hard_regs[k],
ira_reg_mode_hard_regset[hard_regno][mode]);
break;
}
}
ira_free (sorted_allocnos);
ira_free (used_hard_regs);
ira_free (allocno_priorities);
if (internal_flag_ira_verbose > 1 && ira_dump_file != NULL)
ira_print_disposition (ira_dump_file);
}
|