llvm.org GIT mirror llvm / 42fc558 docs / tutorial / LangImpl7.html
42fc558

Tree @42fc558 (Download .tar.gz)

LangImpl7.html @42fc558raw · history · blame

   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
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
                      "http://www.w3.org/TR/html4/strict.dtd">

<html>
<head>
  <title>Kaleidoscope: Extending the Language: Mutable Variables / SSA
         construction</title>
  <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
  <meta name="author" content="Chris Lattner">
  <link rel="stylesheet" href="../llvm.css" type="text/css">
</head>

<body>

<div class="doc_title">Kaleidoscope: Extending the Language: Mutable Variables</div>

<ul>
<li><a href="index.html">Up to Tutorial Index</a></li>
<li>Chapter 7
  <ol>
    <li><a href="#intro">Chapter 7 Introduction</a></li>
    <li><a href="#why">Why is this a hard problem?</a></li>
    <li><a href="#memory">Memory in LLVM</a></li>
    <li><a href="#kalvars">Mutable Variables in Kaleidoscope</a></li>
    <li><a href="#adjustments">Adjusting Existing Variables for
     Mutation</a></li>
    <li><a href="#assignment">New Assignment Operator</a></li>
    <li><a href="#localvars">User-defined Local Variables</a></li>
    <li><a href="#code">Full Code Listing</a></li>
  </ol>
</li>
<li><a href="LangImpl8.html">Chapter 8</a>: Conclusion and other useful LLVM
 tidbits</li>
</ul>

<div class="doc_author">
  <p>Written by <a href="mailto:sabre@nondot.org">Chris Lattner</a></p>
</div>

<!-- *********************************************************************** -->
<div class="doc_section"><a name="intro">Chapter 7 Introduction</a></div>
<!-- *********************************************************************** -->

<div class="doc_text">

<p>Welcome to Chapter 7 of the "<a href="index.html">Implementing a language
with LLVM</a>" tutorial.  In chapters 1 through 6, we've built a very
respectable, albeit simple, <a 
href="http://en.wikipedia.org/wiki/Functional_programming">functional
programming language</a>.  In our journey, we learned some parsing techniques,
how to build and represent an AST, how to build LLVM IR, and how to optimize
the resultant code as well as JIT compile it.</p>

<p>While Kaleidoscope is interesting as a functional language, the fact that it
is functional makes it "too easy" to generate LLVM IR for it.  In particular, a 
functional language makes it very easy to build LLVM IR directly in <a 
href="http://en.wikipedia.org/wiki/Static_single_assignment_form">SSA form</a>.
Since LLVM requires that the input code be in SSA form, this is a very nice
property and it is often unclear to newcomers how to generate code for an
imperative language with mutable variables.</p>

<p>The short (and happy) summary of this chapter is that there is no need for
your front-end to build SSA form: LLVM provides highly tuned and well tested
support for this, though the way it works is a bit unexpected for some.</p>

</div>

<!-- *********************************************************************** -->
<div class="doc_section"><a name="why">Why is this a hard problem?</a></div>
<!-- *********************************************************************** -->

<div class="doc_text">

<p>
To understand why mutable variables cause complexities in SSA construction, 
consider this extremely simple C example:
</p>

<div class="doc_code">
<pre>
int G, H;
int test(_Bool Condition) {
  int X;
  if (Condition)
    X = G;
  else
    X = H;
  return X;
}
</pre>
</div>

<p>In this case, we have the variable "X", whose value depends on the path 
executed in the program.  Because there are two different possible values for X
before the return instruction, a PHI node is inserted to merge the two values.
The LLVM IR that we want for this example looks like this:</p>

<div class="doc_code">
<pre>
@G = weak global i32 0   ; type of @G is i32*
@H = weak global i32 0   ; type of @H is i32*

define i32 @test(i1 %Condition) {
entry:
	br i1 %Condition, label %cond_true, label %cond_false

cond_true:
	%X.0 = load i32* @G
	br label %cond_next

cond_false:
	%X.1 = load i32* @H
	br label %cond_next

cond_next:
	%X.2 = phi i32 [ %X.1, %cond_false ], [ %X.0, %cond_true ]
	ret i32 %X.2
}
</pre>
</div>

<p>In this example, the loads from the G and H global variables are explicit in
the LLVM IR, and they live in the then/else branches of the if statement
(cond_true/cond_false).  In order to merge the incoming values, the X.2 phi node
in the cond_next block selects the right value to use based on where control 
flow is coming from: if control flow comes from the cond_false block, X.2 gets
the value of X.1.  Alternatively, if control flow comes from cond_true, it gets
the value of X.0.  The intent of this chapter is not to explain the details of
SSA form.  For more information, see one of the many <a 
href="http://en.wikipedia.org/wiki/Static_single_assignment_form">online 
references</a>.</p>

<p>The question for this article is "who places the phi nodes when lowering 
assignments to mutable variables?".  The issue here is that LLVM 
<em>requires</em> that its IR be in SSA form: there is no "non-ssa" mode for it.
However, SSA construction requires non-trivial algorithms and data structures,
so it is inconvenient and wasteful for every front-end to have to reproduce this
logic.</p>

</div>

<!-- *********************************************************************** -->
<div class="doc_section"><a name="memory">Memory in LLVM</a></div>
<!-- *********************************************************************** -->

<div class="doc_text">

<p>The 'trick' here is that while LLVM does require all register values to be
in SSA form, it does not require (or permit) memory objects to be in SSA form.
In the example above, note that the loads from G and H are direct accesses to
G and H: they are not renamed or versioned.  This differs from some other
compiler systems, which do try to version memory objects.  In LLVM, instead of
encoding dataflow analysis of memory into the LLVM IR, it is handled with <a 
href="../WritingAnLLVMPass.html">Analysis Passes</a> which are computed on
demand.</p>

<p>
With this in mind, the high-level idea is that we want to make a stack variable
(which lives in memory, because it is on the stack) for each mutable object in
a function.  To take advantage of this trick, we need to talk about how LLVM
represents stack variables.
</p>

<p>In LLVM, all memory accesses are explicit with load/store instructions, and
it is carefully designed not to have (or need) an "address-of" operator.  Notice
how the type of the @G/@H global variables is actually "i32*" even though the 
variable is defined as "i32".  What this means is that @G defines <em>space</em>
for an i32 in the global data area, but its <em>name</em> actually refers to the
address for that space.  Stack variables work the same way, except that instead of 
being declared with global variable definitions, they are declared with the 
<a href="../LangRef.html#i_alloca">LLVM alloca instruction</a>:</p>

<div class="doc_code">
<pre>
define i32 @example() {
entry:
	%X = alloca i32           ; type of %X is i32*.
	...
	%tmp = load i32* %X       ; load the stack value %X from the stack.
	%tmp2 = add i32 %tmp, 1   ; increment it
	store i32 %tmp2, i32* %X  ; store it back
	...
</pre>
</div>

<p>This code shows an example of how you can declare and manipulate a stack
variable in the LLVM IR.  Stack memory allocated with the alloca instruction is
fully general: you can pass the address of the stack slot to functions, you can
store it in other variables, etc.  In our example above, we could rewrite the
example to use the alloca technique to avoid using a PHI node:</p>

<div class="doc_code">
<pre>
@G = weak global i32 0   ; type of @G is i32*
@H = weak global i32 0   ; type of @H is i32*

define i32 @test(i1 %Condition) {
entry:
	%X = alloca i32           ; type of %X is i32*.
	br i1 %Condition, label %cond_true, label %cond_false

cond_true:
	%X.0 = load i32* @G
        store i32 %X.0, i32* %X   ; Update X
	br label %cond_next

cond_false:
	%X.1 = load i32* @H
        store i32 %X.1, i32* %X   ; Update X
	br label %cond_next

cond_next:
	%X.2 = load i32* %X       ; Read X
	ret i32 %X.2
}
</pre>
</div>

<p>With this, we have discovered a way to handle arbitrary mutable variables
without the need to create Phi nodes at all:</p>

<ol>
<li>Each mutable variable becomes a stack allocation.</li>
<li>Each read of the variable becomes a load from the stack.</li>
<li>Each update of the variable becomes a store to the stack.</li>
<li>Taking the address of a variable just uses the stack address directly.</li>
</ol>

<p>While this solution has solved our immediate problem, it introduced another
one: we have now apparently introduced a lot of stack traffic for very simple
and common operations, a major performance problem.  Fortunately for us, the
LLVM optimizer has a highly-tuned optimization pass named "mem2reg" that handles
this case, promoting allocas like this into SSA registers, inserting Phi nodes
as appropriate.  If you run this example through the pass, for example, you'll
get:</p>

<div class="doc_code">
<pre>
$ <b>llvm-as &lt; example.ll | opt -mem2reg | llvm-dis</b>
@G = weak global i32 0
@H = weak global i32 0

define i32 @test(i1 %Condition) {
entry:
	br i1 %Condition, label %cond_true, label %cond_false

cond_true:
	%X.0 = load i32* @G
	br label %cond_next

cond_false:
	%X.1 = load i32* @H
	br label %cond_next

cond_next:
	%X.01 = phi i32 [ %X.1, %cond_false ], [ %X.0, %cond_true ]
	ret i32 %X.01
}
</pre>
</div>

<p>The mem2reg pass implements the standard "iterated dominance frontier"
algorithm for constructing SSA form and has a number of optimizations that speed
up (very common) degenerate cases. The mem2reg optimization pass is the answer to dealing 
with mutable variables, and we highly recommend that you depend on it.  Note that
mem2reg only works on variables in certain circumstances:</p>

<ol>
<li>mem2reg is alloca-driven: it looks for allocas and if it can handle them, it
promotes them.  It does not apply to global variables or heap allocations.</li>

<li>mem2reg only looks for alloca instructions in the entry block of the
function.  Being in the entry block guarantees that the alloca is only executed
once, which makes analysis simpler.</li>

<li>mem2reg only promotes allocas whose uses are direct loads and stores.  If
the address of the stack object is passed to a function, or if any funny pointer
arithmetic is involved, the alloca will not be promoted.</li>

<li>mem2reg only works on allocas of <a 
href="../LangRef.html#t_classifications">first class</a> 
values (such as pointers, scalars and vectors), and only if the array size
of the allocation is 1 (or missing in the .ll file).  mem2reg is not capable of
promoting structs or arrays to registers.  Note that the "scalarrepl" pass is
more powerful and can promote structs, "unions", and arrays in many cases.</li>

</ol>

<p>
All of these properties are easy to satisfy for most imperative languages, and
we'll illustrate it below with Kaleidoscope.  The final question you may be
asking is: should I bother with this nonsense for my front-end?  Wouldn't it be
better if I just did SSA construction directly, avoiding use of the mem2reg
optimization pass?  In short, we strongly recommend that you use this technique
for building SSA form, unless there is an extremely good reason not to.  Using
this technique is:</p>

<ul>
<li>Proven and well tested: llvm-gcc and clang both use this technique for local
mutable variables.  As such, the most common clients of LLVM are using this to
handle a bulk of their variables.  You can be sure that bugs are found fast and
fixed early.</li>

<li>Extremely Fast: mem2reg has a number of special cases that make it fast in
common cases as well as fully general.  For example, it has fast-paths for
variables that are only used in a single block, variables that only have one
assignment point, good heuristics to avoid insertion of unneeded phi nodes, etc.
</li>

<li>Needed for debug info generation: <a href="../SourceLevelDebugging.html">
Debug information in LLVM</a> relies on having the address of the variable
exposed so that debug info can be attached to it.  This technique dovetails 
very naturally with this style of debug info.</li>
</ul>

<p>If nothing else, this makes it much easier to get your front-end up and 
running, and is very simple to implement.  Lets extend Kaleidoscope with mutable
variables now!
</p>

</div>

<!-- *********************************************************************** -->
<div class="doc_section"><a name="kalvars">Mutable Variables in 
Kaleidoscope</a></div>
<!-- *********************************************************************** -->

<div class="doc_text">

<p>Now that we know the sort of problem we want to tackle, lets see what this
looks like in the context of our little Kaleidoscope language.  We're going to
add two features:</p>

<ol>
<li>The ability to mutate variables with the '=' operator.</li>
<li>The ability to define new variables.</li>
</ol>

<p>While the first item is really what this is about, we only have variables
for incoming arguments as well as for induction variables, and redefining those only
goes so far :).  Also, the ability to define new variables is a
useful thing regardless of whether you will be mutating them.  Here's a
motivating example that shows how we could use these:</p>

<div class="doc_code">
<pre>
# Define ':' for sequencing: as a low-precedence operator that ignores operands
# and just returns the RHS.
def binary : 1 (x y) y;

# Recursive fib, we could do this before.
def fib(x)
  if (x &lt; 3) then
    1
  else
    fib(x-1)+fib(x-2);

# Iterative fib.
def fibi(x)
  <b>var a = 1, b = 1, c in</b>
  (for i = 3, i &lt; x in 
     <b>c = a + b</b> :
     <b>a = b</b> :
     <b>b = c</b>) :
  b;

# Call it. 
fibi(10);
</pre>
</div>

<p>
In order to mutate variables, we have to change our existing variables to use
the "alloca trick".  Once we have that, we'll add our new operator, then extend
Kaleidoscope to support new variable definitions.
</p>

</div>

<!-- *********************************************************************** -->
<div class="doc_section"><a name="adjustments">Adjusting Existing Variables for
Mutation</a></div>
<!-- *********************************************************************** -->

<div class="doc_text">

<p>
The symbol table in Kaleidoscope is managed at code generation time by the 
'<tt>NamedValues</tt>' map.  This map currently keeps track of the LLVM "Value*"
that holds the double value for the named variable.  In order to support
mutation, we need to change this slightly, so that it <tt>NamedValues</tt> holds
the <em>memory location</em> of the variable in question.  Note that this 
change is a refactoring: it changes the structure of the code, but does not
(by itself) change the behavior of the compiler.  All of these changes are 
isolated in the Kaleidoscope code generator.</p>

<p>
At this point in Kaleidoscope's development, it only supports variables for two
things: incoming arguments to functions and the induction variable of 'for'
loops.  For consistency, we'll allow mutation of these variables in addition to
other user-defined variables.  This means that these will both need memory
locations.
</p>

<p>To start our transformation of Kaleidoscope, we'll change the NamedValues
map so that it maps to AllocaInst* instead of Value*.  Once we do this, the C++ 
compiler will tell us what parts of the code we need to update:</p>

<div class="doc_code">
<pre>
static std::map&lt;std::string, AllocaInst*&gt; NamedValues;
</pre>
</div>

<p>Also, since we will need to create these alloca's, we'll use a helper
function that ensures that the allocas are created in the entry block of the
function:</p>

<div class="doc_code">
<pre>
/// CreateEntryBlockAlloca - Create an alloca instruction in the entry block of
/// the function.  This is used for mutable variables etc.
static AllocaInst *CreateEntryBlockAlloca(Function *TheFunction,
                                          const std::string &amp;VarName) {
  IRBuilder&lt;&gt; TmpB(&amp;TheFunction-&gt;getEntryBlock(),
                 TheFunction-&gt;getEntryBlock().begin());
  return TmpB.CreateAlloca(Type::getDoubleTy(getGlobalContext()), 0,
                           VarName.c_str());
}
</pre>
</div>

<p>This funny looking code creates an IRBuilder object that is pointing at
the first instruction (.begin()) of the entry block.  It then creates an alloca
with the expected name and returns it.  Because all values in Kaleidoscope are
doubles, there is no need to pass in a type to use.</p>

<p>With this in place, the first functionality change we want to make is to
variable references.  In our new scheme, variables live on the stack, so code
generating a reference to them actually needs to produce a load from the stack
slot:</p>

<div class="doc_code">
<pre>
Value *VariableExprAST::Codegen() {
  // Look this variable up in the function.
  Value *V = NamedValues[Name];
  if (V == 0) return ErrorV("Unknown variable name");

  <b>// Load the value.
  return Builder.CreateLoad(V, Name.c_str());</b>
}
</pre>
</div>

<p>As you can see, this is pretty straightforward.  Now we need to update the
things that define the variables to set up the alloca.  We'll start with 
<tt>ForExprAST::Codegen</tt> (see the <a href="#code">full code listing</a> for
the unabridged code):</p>

<div class="doc_code">
<pre>
  Function *TheFunction = Builder.GetInsertBlock()->getParent();

  <b>// Create an alloca for the variable in the entry block.
  AllocaInst *Alloca = CreateEntryBlockAlloca(TheFunction, VarName);</b>
  
    // Emit the start code first, without 'variable' in scope.
  Value *StartVal = Start-&gt;Codegen();
  if (StartVal == 0) return 0;
  
  <b>// Store the value into the alloca.
  Builder.CreateStore(StartVal, Alloca);</b>
  ...

  // Compute the end condition.
  Value *EndCond = End-&gt;Codegen();
  if (EndCond == 0) return EndCond;
  
  <b>// Reload, increment, and restore the alloca.  This handles the case where
  // the body of the loop mutates the variable.
  Value *CurVar = Builder.CreateLoad(Alloca);
  Value *NextVar = Builder.CreateAdd(CurVar, StepVal, "nextvar");
  Builder.CreateStore(NextVar, Alloca);</b>
  ...
</pre>
</div>

<p>This code is virtually identical to the code <a 
href="LangImpl5.html#forcodegen">before we allowed mutable variables</a>.  The
big difference is that we no longer have to construct a PHI node, and we use
load/store to access the variable as needed.</p>

<p>To support mutable argument variables, we need to also make allocas for them.
The code for this is also pretty simple:</p>

<div class="doc_code">
<pre>
/// CreateArgumentAllocas - Create an alloca for each argument and register the
/// argument in the symbol table so that references to it will succeed.
void PrototypeAST::CreateArgumentAllocas(Function *F) {
  Function::arg_iterator AI = F-&gt;arg_begin();
  for (unsigned Idx = 0, e = Args.size(); Idx != e; ++Idx, ++AI) {
    // Create an alloca for this variable.
    AllocaInst *Alloca = CreateEntryBlockAlloca(F, Args[Idx]);

    // Store the initial value into the alloca.
    Builder.CreateStore(AI, Alloca);

    // Add arguments to variable symbol table.
    NamedValues[Args[Idx]] = Alloca;
  }
}
</pre>
</div>

<p>For each argument, we make an alloca, store the input value to the function
into the alloca, and register the alloca as the memory location for the
argument.  This method gets invoked by <tt>FunctionAST::Codegen</tt> right after
it sets up the entry block for the function.</p>

<p>The final missing piece is adding the mem2reg pass, which allows us to get
good codegen once again:</p>

<div class="doc_code">
<pre>
    // Set up the optimizer pipeline.  Start with registering info about how the
    // target lays out data structures.
    OurFPM.add(new TargetData(*TheExecutionEngine-&gt;getTargetData()));
    <b>// Promote allocas to registers.
    OurFPM.add(createPromoteMemoryToRegisterPass());</b>
    // Do simple "peephole" optimizations and bit-twiddling optzns.
    OurFPM.add(createInstructionCombiningPass());
    // Reassociate expressions.
    OurFPM.add(createReassociatePass());
</pre>
</div>

<p>It is interesting to see what the code looks like before and after the
mem2reg optimization runs.  For example, this is the before/after code for our
recursive fib function.  Before the optimization:</p>

<div class="doc_code">
<pre>
define double @fib(double %x) {
entry:
	<b>%x1 = alloca double
	store double %x, double* %x1
	%x2 = load double* %x1</b>
	%cmptmp = fcmp ult double %x2, 3.000000e+00
	%booltmp = uitofp i1 %cmptmp to double
	%ifcond = fcmp one double %booltmp, 0.000000e+00
	br i1 %ifcond, label %then, label %else

then:		; preds = %entry
	br label %ifcont

else:		; preds = %entry
	<b>%x3 = load double* %x1</b>
	%subtmp = sub double %x3, 1.000000e+00
	%calltmp = call double @fib( double %subtmp )
	<b>%x4 = load double* %x1</b>
	%subtmp5 = sub double %x4, 2.000000e+00
	%calltmp6 = call double @fib( double %subtmp5 )
	%addtmp = add double %calltmp, %calltmp6
	br label %ifcont

ifcont:		; preds = %else, %then
	%iftmp = phi double [ 1.000000e+00, %then ], [ %addtmp, %else ]
	ret double %iftmp
}
</pre>
</div>

<p>Here there is only one variable (x, the input argument) but you can still
see the extremely simple-minded code generation strategy we are using.  In the
entry block, an alloca is created, and the initial input value is stored into
it.  Each reference to the variable does a reload from the stack.  Also, note
that we didn't modify the if/then/else expression, so it still inserts a PHI
node.  While we could make an alloca for it, it is actually easier to create a 
PHI node for it, so we still just make the PHI.</p>

<p>Here is the code after the mem2reg pass runs:</p>

<div class="doc_code">
<pre>
define double @fib(double %x) {
entry:
	%cmptmp = fcmp ult double <b>%x</b>, 3.000000e+00
	%booltmp = uitofp i1 %cmptmp to double
	%ifcond = fcmp one double %booltmp, 0.000000e+00
	br i1 %ifcond, label %then, label %else

then:
	br label %ifcont

else:
	%subtmp = sub double <b>%x</b>, 1.000000e+00
	%calltmp = call double @fib( double %subtmp )
	%subtmp5 = sub double <b>%x</b>, 2.000000e+00
	%calltmp6 = call double @fib( double %subtmp5 )
	%addtmp = add double %calltmp, %calltmp6
	br label %ifcont

ifcont:		; preds = %else, %then
	%iftmp = phi double [ 1.000000e+00, %then ], [ %addtmp, %else ]
	ret double %iftmp
}
</pre>
</div>

<p>This is a trivial case for mem2reg, since there are no redefinitions of the
variable.  The point of showing this is to calm your tension about inserting
such blatent inefficiencies :).</p>

<p>After the rest of the optimizers run, we get:</p>

<div class="doc_code">
<pre>
define double @fib(double %x) {
entry:
	%cmptmp = fcmp ult double %x, 3.000000e+00
	%booltmp = uitofp i1 %cmptmp to double
	%ifcond = fcmp ueq double %booltmp, 0.000000e+00
	br i1 %ifcond, label %else, label %ifcont

else:
	%subtmp = sub double %x, 1.000000e+00
	%calltmp = call double @fib( double %subtmp )
	%subtmp5 = sub double %x, 2.000000e+00
	%calltmp6 = call double @fib( double %subtmp5 )
	%addtmp = add double %calltmp, %calltmp6
	ret double %addtmp

ifcont:
	ret double 1.000000e+00
}
</pre>
</div>

<p>Here we see that the simplifycfg pass decided to clone the return instruction
into the end of the 'else' block.  This allowed it to eliminate some branches
and the PHI node.</p>

<p>Now that all symbol table references are updated to use stack variables, 
we'll add the assignment operator.</p>

</div>

<!-- *********************************************************************** -->
<div class="doc_section"><a name="assignment">New Assignment Operator</a></div>
<!-- *********************************************************************** -->

<div class="doc_text">

<p>With our current framework, adding a new assignment operator is really
simple.  We will parse it just like any other binary operator, but handle it
internally (instead of allowing the user to define it).  The first step is to
set a precedence:</p>

<div class="doc_code">
<pre>
 int main() {
   // Install standard binary operators.
   // 1 is lowest precedence.
   <b>BinopPrecedence['='] = 2;</b>
   BinopPrecedence['&lt;'] = 10;
   BinopPrecedence['+'] = 20;
   BinopPrecedence['-'] = 20;
</pre>
</div>

<p>Now that the parser knows the precedence of the binary operator, it takes
care of all the parsing and AST generation.  We just need to implement codegen
for the assignment operator.  This looks like:</p> 

<div class="doc_code">
<pre>
Value *BinaryExprAST::Codegen() {
  // Special case '=' because we don't want to emit the LHS as an expression.
  if (Op == '=') {
    // Assignment requires the LHS to be an identifier.
    VariableExprAST *LHSE = dynamic_cast&lt;VariableExprAST*&gt;(LHS);
    if (!LHSE)
      return ErrorV("destination of '=' must be a variable");
</pre>
</div>

<p>Unlike the rest of the binary operators, our assignment operator doesn't
follow the "emit LHS, emit RHS, do computation" model.  As such, it is handled
as a special case before the other binary operators are handled.  The other 
strange thing is that it requires the LHS to be a variable.  It is invalid to
have "(x+1) = expr" - only things like "x = expr" are allowed.
</p>

<div class="doc_code">
<pre>
    // Codegen the RHS.
    Value *Val = RHS-&gt;Codegen();
    if (Val == 0) return 0;

    // Look up the name.
    Value *Variable = NamedValues[LHSE-&gt;getName()];
    if (Variable == 0) return ErrorV("Unknown variable name");

    Builder.CreateStore(Val, Variable);
    return Val;
  }
  ...  
</pre>
</div>

<p>Once we have the variable, codegen'ing the assignment is straightforward:
we emit the RHS of the assignment, create a store, and return the computed
value.  Returning a value allows for chained assignments like "X = (Y = Z)".</p>

<p>Now that we have an assignment operator, we can mutate loop variables and
arguments.  For example, we can now run code like this:</p>

<div class="doc_code">
<pre>
# Function to print a double.
extern printd(x);

# Define ':' for sequencing: as a low-precedence operator that ignores operands
# and just returns the RHS.
def binary : 1 (x y) y;

def test(x)
  printd(x) :
  x = 4 :
  printd(x);

test(123);
</pre>
</div>

<p>When run, this example prints "123" and then "4", showing that we did
actually mutate the value!  Okay, we have now officially implemented our goal:
getting this to work requires SSA construction in the general case.  However,
to be really useful, we want the ability to define our own local variables, lets
add this next! 
</p>

</div>

<!-- *********************************************************************** -->
<div class="doc_section"><a name="localvars">User-defined Local 
Variables</a></div>
<!-- *********************************************************************** -->

<div class="doc_text">

<p>Adding var/in is just like any other other extensions we made to 
Kaleidoscope: we extend the lexer, the parser, the AST and the code generator.
The first step for adding our new 'var/in' construct is to extend the lexer.
As before, this is pretty trivial, the code looks like this:</p>

<div class="doc_code">
<pre>
enum Token {
  ...
  <b>// var definition
  tok_var = -13</b>
...
}
...
static int gettok() {
...
    if (IdentifierStr == "in") return tok_in;
    if (IdentifierStr == "binary") return tok_binary;
    if (IdentifierStr == "unary") return tok_unary;
    <b>if (IdentifierStr == "var") return tok_var;</b>
    return tok_identifier;
...
</pre>
</div>

<p>The next step is to define the AST node that we will construct.  For var/in,
it looks like this:</p>

<div class="doc_code">
<pre>
/// VarExprAST - Expression class for var/in
class VarExprAST : public ExprAST {
  std::vector&lt;std::pair&lt;std::string, ExprAST*&gt; &gt; VarNames;
  ExprAST *Body;
public:
  VarExprAST(const std::vector&lt;std::pair&lt;std::string, ExprAST*&gt; &gt; &amp;varnames,
             ExprAST *body)
  : VarNames(varnames), Body(body) {}
  
  virtual Value *Codegen();
};
</pre>
</div>

<p>var/in allows a list of names to be defined all at once, and each name can
optionally have an initializer value.  As such, we capture this information in
the VarNames vector.  Also, var/in has a body, this body is allowed to access
the variables defined by the var/in.</p>

<p>With this in place, we can define the parser pieces.  The first thing we do is add
it as a primary expression:</p>

<div class="doc_code">
<pre>
/// primary
///   ::= identifierexpr
///   ::= numberexpr
///   ::= parenexpr
///   ::= ifexpr
///   ::= forexpr
<b>///   ::= varexpr</b>
static ExprAST *ParsePrimary() {
  switch (CurTok) {
  default: return Error("unknown token when expecting an expression");
  case tok_identifier: return ParseIdentifierExpr();
  case tok_number:     return ParseNumberExpr();
  case '(':            return ParseParenExpr();
  case tok_if:         return ParseIfExpr();
  case tok_for:        return ParseForExpr();
  <b>case tok_var:        return ParseVarExpr();</b>
  }
}
</pre>
</div>

<p>Next we define ParseVarExpr:</p>

<div class="doc_code">
<pre>
/// varexpr ::= 'var' identifier ('=' expression)? 
//                    (',' identifier ('=' expression)?)* 'in' expression
static ExprAST *ParseVarExpr() {
  getNextToken();  // eat the var.

  std::vector&lt;std::pair&lt;std::string, ExprAST*&gt; &gt; VarNames;

  // At least one variable name is required.
  if (CurTok != tok_identifier)
    return Error("expected identifier after var");
</pre>
</div>

<p>The first part of this code parses the list of identifier/expr pairs into the
local <tt>VarNames</tt> vector.  

<div class="doc_code">
<pre>
  while (1) {
    std::string Name = IdentifierStr;
    getNextToken();  // eat identifier.

    // Read the optional initializer.
    ExprAST *Init = 0;
    if (CurTok == '=') {
      getNextToken(); // eat the '='.
      
      Init = ParseExpression();
      if (Init == 0) return 0;
    }
    
    VarNames.push_back(std::make_pair(Name, Init));
    
    // End of var list, exit loop.
    if (CurTok != ',') break;
    getNextToken(); // eat the ','.
    
    if (CurTok != tok_identifier)
      return Error("expected identifier list after var");
  }
</pre>
</div>

<p>Once all the variables are parsed, we then parse the body and create the
AST node:</p>

<div class="doc_code">
<pre>
  // At this point, we have to have 'in'.
  if (CurTok != tok_in)
    return Error("expected 'in' keyword after 'var'");
  getNextToken();  // eat 'in'.
  
  ExprAST *Body = ParseExpression();
  if (Body == 0) return 0;
  
  return new VarExprAST(VarNames, Body);
}
</pre>
</div>

<p>Now that we can parse and represent the code, we need to support emission of
LLVM IR for it.  This code starts out with:</p>

<div class="doc_code">
<pre>
Value *VarExprAST::Codegen() {
  std::vector&lt;AllocaInst *&gt; OldBindings;
  
  Function *TheFunction = Builder.GetInsertBlock()-&gt;getParent();

  // Register all variables and emit their initializer.
  for (unsigned i = 0, e = VarNames.size(); i != e; ++i) {
    const std::string &amp;VarName = VarNames[i].first;
    ExprAST *Init = VarNames[i].second;
</pre>
</div>

<p>Basically it loops over all the variables, installing them one at a time.
For each variable we put into the symbol table, we remember the previous value
that we replace in OldBindings.</p>

<div class="doc_code">
<pre>
    // Emit the initializer before adding the variable to scope, this prevents
    // the initializer from referencing the variable itself, and permits stuff
    // like this:
    //  var a = 1 in
    //    var a = a in ...   # refers to outer 'a'.
    Value *InitVal;
    if (Init) {
      InitVal = Init-&gt;Codegen();
      if (InitVal == 0) return 0;
    } else { // If not specified, use 0.0.
      InitVal = ConstantFP::get(getGlobalContext(), APFloat(0.0));
    }
    
    AllocaInst *Alloca = CreateEntryBlockAlloca(TheFunction, VarName);
    Builder.CreateStore(InitVal, Alloca);

    // Remember the old variable binding so that we can restore the binding when
    // we unrecurse.
    OldBindings.push_back(NamedValues[VarName]);
    
    // Remember this binding.
    NamedValues[VarName] = Alloca;
  }
</pre>
</div>

<p>There are more comments here than code.  The basic idea is that we emit the
initializer, create the alloca, then update the symbol table to point to it.
Once all the variables are installed in the symbol table, we evaluate the body
of the var/in expression:</p>

<div class="doc_code">
<pre>
  // Codegen the body, now that all vars are in scope.
  Value *BodyVal = Body-&gt;Codegen();
  if (BodyVal == 0) return 0;
</pre>
</div>

<p>Finally, before returning, we restore the previous variable bindings:</p>

<div class="doc_code">
<pre>
  // Pop all our variables from scope.
  for (unsigned i = 0, e = VarNames.size(); i != e; ++i)
    NamedValues[VarNames[i].first] = OldBindings[i];

  // Return the body computation.
  return BodyVal;
}
</pre>
</div>

<p>The end result of all of this is that we get properly scoped variable 
definitions, and we even (trivially) allow mutation of them :).</p>

<p>With this, we completed what we set out to do.  Our nice iterative fib
example from the intro compiles and runs just fine.  The mem2reg pass optimizes
all of our stack variables into SSA registers, inserting PHI nodes where needed,
and our front-end remains simple: no "iterated dominance frontier" computation
anywhere in sight.</p>

</div>

<!-- *********************************************************************** -->
<div class="doc_section"><a name="code">Full Code Listing</a></div>
<!-- *********************************************************************** -->

<div class="doc_text">

<p>
Here is the complete code listing for our running example, enhanced with mutable
variables and var/in support.  To build this example, use:
</p>

<div class="doc_code">
<pre>
   # Compile
   g++ -g toy.cpp `llvm-config --cppflags --ldflags --libs core jit native` -O3 -o toy
   # Run
   ./toy
</pre>
</div>

<p>Here is the code:</p>

<div class="doc_code">
<pre>
#include "llvm/DerivedTypes.h"
#include "llvm/ExecutionEngine/ExecutionEngine.h"
#include "llvm/ExecutionEngine/JIT.h"
#include "llvm/LLVMContext.h"
#include "llvm/Module.h"
#include "llvm/PassManager.h"
#include "llvm/Analysis/Verifier.h"
#include "llvm/Target/TargetData.h"
#include "llvm/Target/TargetSelect.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Support/IRBuilder.h"
#include &lt;cstdio&gt;
#include &lt;string&gt;
#include &lt;map&gt;
#include &lt;vector&gt;
using namespace llvm;

//===----------------------------------------------------------------------===//
// Lexer
//===----------------------------------------------------------------------===//

// The lexer returns tokens [0-255] if it is an unknown character, otherwise one
// of these for known things.
enum Token {
  tok_eof = -1,

  // commands
  tok_def = -2, tok_extern = -3,

  // primary
  tok_identifier = -4, tok_number = -5,
  
  // control
  tok_if = -6, tok_then = -7, tok_else = -8,
  tok_for = -9, tok_in = -10,
  
  // operators
  tok_binary = -11, tok_unary = -12,
  
  // var definition
  tok_var = -13
};

static std::string IdentifierStr;  // Filled in if tok_identifier
static double NumVal;              // Filled in if tok_number

/// gettok - Return the next token from standard input.
static int gettok() {
  static int LastChar = ' ';

  // Skip any whitespace.
  while (isspace(LastChar))
    LastChar = getchar();

  if (isalpha(LastChar)) { // identifier: [a-zA-Z][a-zA-Z0-9]*
    IdentifierStr = LastChar;
    while (isalnum((LastChar = getchar())))
      IdentifierStr += LastChar;

    if (IdentifierStr == "def") return tok_def;
    if (IdentifierStr == "extern") return tok_extern;
    if (IdentifierStr == "if") return tok_if;
    if (IdentifierStr == "then") return tok_then;
    if (IdentifierStr == "else") return tok_else;
    if (IdentifierStr == "for") return tok_for;
    if (IdentifierStr == "in") return tok_in;
    if (IdentifierStr == "binary") return tok_binary;
    if (IdentifierStr == "unary") return tok_unary;
    if (IdentifierStr == "var") return tok_var;
    return tok_identifier;
  }

  if (isdigit(LastChar) || LastChar == '.') {   // Number: [0-9.]+
    std::string NumStr;
    do {
      NumStr += LastChar;
      LastChar = getchar();
    } while (isdigit(LastChar) || LastChar == '.');

    NumVal = strtod(NumStr.c_str(), 0);
    return tok_number;
  }

  if (LastChar == '#') {
    // Comment until end of line.
    do LastChar = getchar();
    while (LastChar != EOF &amp;&amp; LastChar != '\n' &amp;&amp; LastChar != '\r');
    
    if (LastChar != EOF)
      return gettok();
  }
  
  // Check for end of file.  Don't eat the EOF.
  if (LastChar == EOF)
    return tok_eof;

  // Otherwise, just return the character as its ascii value.
  int ThisChar = LastChar;
  LastChar = getchar();
  return ThisChar;
}

//===----------------------------------------------------------------------===//
// Abstract Syntax Tree (aka Parse Tree)
//===----------------------------------------------------------------------===//

/// ExprAST - Base class for all expression nodes.
class ExprAST {
public:
  virtual ~ExprAST() {}
  virtual Value *Codegen() = 0;
};

/// NumberExprAST - Expression class for numeric literals like "1.0".
class NumberExprAST : public ExprAST {
  double Val;
public:
  NumberExprAST(double val) : Val(val) {}
  virtual Value *Codegen();
};

/// VariableExprAST - Expression class for referencing a variable, like "a".
class VariableExprAST : public ExprAST {
  std::string Name;
public:
  VariableExprAST(const std::string &amp;name) : Name(name) {}
  const std::string &amp;getName() const { return Name; }
  virtual Value *Codegen();
};

/// UnaryExprAST - Expression class for a unary operator.
class UnaryExprAST : public ExprAST {
  char Opcode;
  ExprAST *Operand;
public:
  UnaryExprAST(char opcode, ExprAST *operand) 
    : Opcode(opcode), Operand(operand) {}
  virtual Value *Codegen();
};

/// BinaryExprAST - Expression class for a binary operator.
class BinaryExprAST : public ExprAST {
  char Op;
  ExprAST *LHS, *RHS;
public:
  BinaryExprAST(char op, ExprAST *lhs, ExprAST *rhs) 
    : Op(op), LHS(lhs), RHS(rhs) {}
  virtual Value *Codegen();
};

/// CallExprAST - Expression class for function calls.
class CallExprAST : public ExprAST {
  std::string Callee;
  std::vector&lt;ExprAST*&gt; Args;
public:
  CallExprAST(const std::string &amp;callee, std::vector&lt;ExprAST*&gt; &amp;args)
    : Callee(callee), Args(args) {}
  virtual Value *Codegen();
};

/// IfExprAST - Expression class for if/then/else.
class IfExprAST : public ExprAST {
  ExprAST *Cond, *Then, *Else;
public:
  IfExprAST(ExprAST *cond, ExprAST *then, ExprAST *_else)
  : Cond(cond), Then(then), Else(_else) {}
  virtual Value *Codegen();
};

/// ForExprAST - Expression class for for/in.
class ForExprAST : public ExprAST {
  std::string VarName;
  ExprAST *Start, *End, *Step, *Body;
public:
  ForExprAST(const std::string &amp;varname, ExprAST *start, ExprAST *end,
             ExprAST *step, ExprAST *body)
    : VarName(varname), Start(start), End(end), Step(step), Body(body) {}
  virtual Value *Codegen();
};

/// VarExprAST - Expression class for var/in
class VarExprAST : public ExprAST {
  std::vector&lt;std::pair&lt;std::string, ExprAST*&gt; &gt; VarNames;
  ExprAST *Body;
public:
  VarExprAST(const std::vector&lt;std::pair&lt;std::string, ExprAST*&gt; &gt; &amp;varnames,
             ExprAST *body)
  : VarNames(varnames), Body(body) {}
  
  virtual Value *Codegen();
};

/// PrototypeAST - This class represents the "prototype" for a function,
/// which captures its name, and its argument names (thus implicitly the number
/// of arguments the function takes), as well as if it is an operator.
class PrototypeAST {
  std::string Name;
  std::vector&lt;std::string&gt; Args;
  bool isOperator;
  unsigned Precedence;  // Precedence if a binary op.
public:
  PrototypeAST(const std::string &amp;name, const std::vector&lt;std::string&gt; &amp;args,
               bool isoperator = false, unsigned prec = 0)
  : Name(name), Args(args), isOperator(isoperator), Precedence(prec) {}
  
  bool isUnaryOp() const { return isOperator &amp;&amp; Args.size() == 1; }
  bool isBinaryOp() const { return isOperator &amp;&amp; Args.size() == 2; }
  
  char getOperatorName() const {
    assert(isUnaryOp() || isBinaryOp());
    return Name[Name.size()-1];
  }
  
  unsigned getBinaryPrecedence() const { return Precedence; }
  
  Function *Codegen();
  
  void CreateArgumentAllocas(Function *F);
};

/// FunctionAST - This class represents a function definition itself.
class FunctionAST {
  PrototypeAST *Proto;
  ExprAST *Body;
public:
  FunctionAST(PrototypeAST *proto, ExprAST *body)
    : Proto(proto), Body(body) {}
  
  Function *Codegen();
};

//===----------------------------------------------------------------------===//
// Parser
//===----------------------------------------------------------------------===//

/// CurTok/getNextToken - Provide a simple token buffer.  CurTok is the current
/// token the parser is looking at.  getNextToken reads another token from the
/// lexer and updates CurTok with its results.
static int CurTok;
static int getNextToken() {
  return CurTok = gettok();
}

/// BinopPrecedence - This holds the precedence for each binary operator that is
/// defined.
static std::map&lt;char, int&gt; BinopPrecedence;

/// GetTokPrecedence - Get the precedence of the pending binary operator token.
static int GetTokPrecedence() {
  if (!isascii(CurTok))
    return -1;
  
  // Make sure it's a declared binop.
  int TokPrec = BinopPrecedence[CurTok];
  if (TokPrec &lt;= 0) return -1;
  return TokPrec;
}

/// Error* - These are little helper functions for error handling.
ExprAST *Error(const char *Str) { fprintf(stderr, "Error: %s\n", Str);return 0;}
PrototypeAST *ErrorP(const char *Str) { Error(Str); return 0; }
FunctionAST *ErrorF(const char *Str) { Error(Str); return 0; }

static ExprAST *ParseExpression();

/// identifierexpr
///   ::= identifier
///   ::= identifier '(' expression* ')'
static ExprAST *ParseIdentifierExpr() {
  std::string IdName = IdentifierStr;
  
  getNextToken();  // eat identifier.
  
  if (CurTok != '(') // Simple variable ref.
    return new VariableExprAST(IdName);
  
  // Call.
  getNextToken();  // eat (
  std::vector&lt;ExprAST*&gt; Args;
  if (CurTok != ')') {
    while (1) {
      ExprAST *Arg = ParseExpression();
      if (!Arg) return 0;
      Args.push_back(Arg);

      if (CurTok == ')') break;

      if (CurTok != ',')
        return Error("Expected ')' or ',' in argument list");
      getNextToken();
    }
  }

  // Eat the ')'.
  getNextToken();
  
  return new CallExprAST(IdName, Args);
}

/// numberexpr ::= number
static ExprAST *ParseNumberExpr() {
  ExprAST *Result = new NumberExprAST(NumVal);
  getNextToken(); // consume the number
  return Result;
}

/// parenexpr ::= '(' expression ')'
static ExprAST *ParseParenExpr() {
  getNextToken();  // eat (.
  ExprAST *V = ParseExpression();
  if (!V) return 0;
  
  if (CurTok != ')')
    return Error("expected ')'");
  getNextToken();  // eat ).
  return V;
}

/// ifexpr ::= 'if' expression 'then' expression 'else' expression
static ExprAST *ParseIfExpr() {
  getNextToken();  // eat the if.
  
  // condition.
  ExprAST *Cond = ParseExpression();
  if (!Cond) return 0;
  
  if (CurTok != tok_then)
    return Error("expected then");
  getNextToken();  // eat the then
  
  ExprAST *Then = ParseExpression();
  if (Then == 0) return 0;
  
  if (CurTok != tok_else)
    return Error("expected else");
  
  getNextToken();
  
  ExprAST *Else = ParseExpression();
  if (!Else) return 0;
  
  return new IfExprAST(Cond, Then, Else);
}

/// forexpr ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression
static ExprAST *ParseForExpr() {
  getNextToken();  // eat the for.

  if (CurTok != tok_identifier)
    return Error("expected identifier after for");
  
  std::string IdName = IdentifierStr;
  getNextToken();  // eat identifier.
  
  if (CurTok != '=')
    return Error("expected '=' after for");
  getNextToken();  // eat '='.
  
  
  ExprAST *Start = ParseExpression();
  if (Start == 0) return 0;
  if (CurTok != ',')
    return Error("expected ',' after for start value");
  getNextToken();
  
  ExprAST *End = ParseExpression();
  if (End == 0) return 0;
  
  // The step value is optional.
  ExprAST *Step = 0;
  if (CurTok == ',') {
    getNextToken();
    Step = ParseExpression();
    if (Step == 0) return 0;
  }
  
  if (CurTok != tok_in)
    return Error("expected 'in' after for");
  getNextToken();  // eat 'in'.
  
  ExprAST *Body = ParseExpression();
  if (Body == 0) return 0;

  return new ForExprAST(IdName, Start, End, Step, Body);
}

/// varexpr ::= 'var' identifier ('=' expression)? 
//                    (',' identifier ('=' expression)?)* 'in' expression
static ExprAST *ParseVarExpr() {
  getNextToken();  // eat the var.

  std::vector&lt;std::pair&lt;std::string, ExprAST*&gt; &gt; VarNames;

  // At least one variable name is required.
  if (CurTok != tok_identifier)
    return Error("expected identifier after var");
  
  while (1) {
    std::string Name = IdentifierStr;
    getNextToken();  // eat identifier.

    // Read the optional initializer.
    ExprAST *Init = 0;
    if (CurTok == '=') {
      getNextToken(); // eat the '='.
      
      Init = ParseExpression();
      if (Init == 0) return 0;
    }
    
    VarNames.push_back(std::make_pair(Name, Init));
    
    // End of var list, exit loop.
    if (CurTok != ',') break;
    getNextToken(); // eat the ','.
    
    if (CurTok != tok_identifier)
      return Error("expected identifier list after var");
  }
  
  // At this point, we have to have 'in'.
  if (CurTok != tok_in)
    return Error("expected 'in' keyword after 'var'");
  getNextToken();  // eat 'in'.
  
  ExprAST *Body = ParseExpression();
  if (Body == 0) return 0;
  
  return new VarExprAST(VarNames, Body);
}

/// primary
///   ::= identifierexpr
///   ::= numberexpr
///   ::= parenexpr
///   ::= ifexpr
///   ::= forexpr
///   ::= varexpr
static ExprAST *ParsePrimary() {
  switch (CurTok) {
  default: return Error("unknown token when expecting an expression");
  case tok_identifier: return ParseIdentifierExpr();
  case tok_number:     return ParseNumberExpr();
  case '(':            return ParseParenExpr();
  case tok_if:         return ParseIfExpr();
  case tok_for:        return ParseForExpr();
  case tok_var:        return ParseVarExpr();
  }
}

/// unary
///   ::= primary
///   ::= '!' unary
static ExprAST *ParseUnary() {
  // If the current token is not an operator, it must be a primary expr.
  if (!isascii(CurTok) || CurTok == '(' || CurTok == ',')
    return ParsePrimary();
  
  // If this is a unary operator, read it.
  int Opc = CurTok;
  getNextToken();
  if (ExprAST *Operand = ParseUnary())
    return new UnaryExprAST(Opc, Operand);
  return 0;
}

/// binoprhs
///   ::= ('+' unary)*
static ExprAST *ParseBinOpRHS(int ExprPrec, ExprAST *LHS) {
  // If this is a binop, find its precedence.
  while (1) {
    int TokPrec = GetTokPrecedence();
    
    // If this is a binop that binds at least as tightly as the current binop,
    // consume it, otherwise we are done.
    if (TokPrec &lt; ExprPrec)
      return LHS;
    
    // Okay, we know this is a binop.
    int BinOp = CurTok;
    getNextToken();  // eat binop
    
    // Parse the unary expression after the binary operator.
    ExprAST *RHS = ParseUnary();
    if (!RHS) return 0;
    
    // If BinOp binds less tightly with RHS than the operator after RHS, let
    // the pending operator take RHS as its LHS.
    int NextPrec = GetTokPrecedence();
    if (TokPrec &lt; NextPrec) {
      RHS = ParseBinOpRHS(TokPrec+1, RHS);
      if (RHS == 0) return 0;
    }
    
    // Merge LHS/RHS.
    LHS = new BinaryExprAST(BinOp, LHS, RHS);
  }
}

/// expression
///   ::= unary binoprhs
///
static ExprAST *ParseExpression() {
  ExprAST *LHS = ParseUnary();
  if (!LHS) return 0;
  
  return ParseBinOpRHS(0, LHS);
}

/// prototype
///   ::= id '(' id* ')'
///   ::= binary LETTER number? (id, id)
///   ::= unary LETTER (id)
static PrototypeAST *ParsePrototype() {
  std::string FnName;
  
  unsigned Kind = 0; // 0 = identifier, 1 = unary, 2 = binary.
  unsigned BinaryPrecedence = 30;
  
  switch (CurTok) {
  default:
    return ErrorP("Expected function name in prototype");
  case tok_identifier:
    FnName = IdentifierStr;
    Kind = 0;
    getNextToken();
    break;
  case tok_unary:
    getNextToken();
    if (!isascii(CurTok))
      return ErrorP("Expected unary operator");
    FnName = "unary";
    FnName += (char)CurTok;
    Kind = 1;
    getNextToken();
    break;
  case tok_binary:
    getNextToken();
    if (!isascii(CurTok))
      return ErrorP("Expected binary operator");
    FnName = "binary";
    FnName += (char)CurTok;
    Kind = 2;
    getNextToken();
    
    // Read the precedence if present.
    if (CurTok == tok_number) {
      if (NumVal &lt; 1 || NumVal &gt; 100)
        return ErrorP("Invalid precedecnce: must be 1..100");
      BinaryPrecedence = (unsigned)NumVal;
      getNextToken();
    }
    break;
  }
  
  if (CurTok != '(')
    return ErrorP("Expected '(' in prototype");
  
  std::vector&lt;std::string&gt; ArgNames;
  while (getNextToken() == tok_identifier)
    ArgNames.push_back(IdentifierStr);
  if (CurTok != ')')
    return ErrorP("Expected ')' in prototype");
  
  // success.
  getNextToken();  // eat ')'.
  
  // Verify right number of names for operator.
  if (Kind &amp;&amp; ArgNames.size() != Kind)
    return ErrorP("Invalid number of operands for operator");
  
  return new PrototypeAST(FnName, ArgNames, Kind != 0, BinaryPrecedence);
}

/// definition ::= 'def' prototype expression
static FunctionAST *ParseDefinition() {
  getNextToken();  // eat def.
  PrototypeAST *Proto = ParsePrototype();
  if (Proto == 0) return 0;

  if (ExprAST *E = ParseExpression())
    return new FunctionAST(Proto, E);
  return 0;
}

/// toplevelexpr ::= expression
static FunctionAST *ParseTopLevelExpr() {
  if (ExprAST *E = ParseExpression()) {
    // Make an anonymous proto.
    PrototypeAST *Proto = new PrototypeAST("", std::vector&lt;std::string&gt;());
    return new FunctionAST(Proto, E);
  }
  return 0;
}

/// external ::= 'extern' prototype
static PrototypeAST *ParseExtern() {
  getNextToken();  // eat extern.
  return ParsePrototype();
}

//===----------------------------------------------------------------------===//
// Code Generation
//===----------------------------------------------------------------------===//

static Module *TheModule;
static IRBuilder&lt;&gt; Builder(getGlobalContext());
static std::map&lt;std::string, AllocaInst*&gt; NamedValues;
static FunctionPassManager *TheFPM;

Value *ErrorV(const char *Str) { Error(Str); return 0; }

/// CreateEntryBlockAlloca - Create an alloca instruction in the entry block of
/// the function.  This is used for mutable variables etc.
static AllocaInst *CreateEntryBlockAlloca(Function *TheFunction,
                                          const std::string &amp;VarName) {
  IRBuilder&lt;&gt; TmpB(&amp;TheFunction-&gt;getEntryBlock(),
                 TheFunction-&gt;getEntryBlock().begin());
  return TmpB.CreateAlloca(Type::getDoubleTy(getGlobalContext()), 0,
                           VarName.c_str());
}

Value *NumberExprAST::Codegen() {
  return ConstantFP::get(getGlobalContext(), APFloat(Val));
}

Value *VariableExprAST::Codegen() {
  // Look this variable up in the function.
  Value *V = NamedValues[Name];
  if (V == 0) return ErrorV("Unknown variable name");

  // Load the value.
  return Builder.CreateLoad(V, Name.c_str());
}

Value *UnaryExprAST::Codegen() {
  Value *OperandV = Operand-&gt;Codegen();
  if (OperandV == 0) return 0;
  
  Function *F = TheModule-&gt;getFunction(std::string("unary")+Opcode);
  if (F == 0)
    return ErrorV("Unknown unary operator");
  
  return Builder.CreateCall(F, OperandV, "unop");
}

Value *BinaryExprAST::Codegen() {
  // Special case '=' because we don't want to emit the LHS as an expression.
  if (Op == '=') {
    // Assignment requires the LHS to be an identifier.
    VariableExprAST *LHSE = dynamic_cast&lt;VariableExprAST*&gt;(LHS);
    if (!LHSE)
      return ErrorV("destination of '=' must be a variable");
    // Codegen the RHS.
    Value *Val = RHS-&gt;Codegen();
    if (Val == 0) return 0;

    // Look up the name.
    Value *Variable = NamedValues[LHSE-&gt;getName()];
    if (Variable == 0) return ErrorV("Unknown variable name");

    Builder.CreateStore(Val, Variable);
    return Val;
  }
  
  Value *L = LHS-&gt;Codegen();
  Value *R = RHS-&gt;Codegen();
  if (L == 0 || R == 0) return 0;
  
  switch (Op) {
  case '+': return Builder.CreateAdd(L, R, "addtmp");
  case '-': return Builder.CreateSub(L, R, "subtmp");
  case '*': return Builder.CreateMul(L, R, "multmp");
  case '&lt;':
    L = Builder.CreateFCmpULT(L, R, "cmptmp");
    // Convert bool 0/1 to double 0.0 or 1.0
    return Builder.CreateUIToFP(L, Type::getDoubleTy(getGlobalContext()),
                                "booltmp");
  default: break;
  }
  
  // If it wasn't a builtin binary operator, it must be a user defined one. Emit
  // a call to it.
  Function *F = TheModule-&gt;getFunction(std::string("binary")+Op);
  assert(F &amp;&amp; "binary operator not found!");
  
  Value *Ops[] = { L, R };
  return Builder.CreateCall(F, Ops, Ops+2, "binop");
}

Value *CallExprAST::Codegen() {
  // Look up the name in the global module table.
  Function *CalleeF = TheModule-&gt;getFunction(Callee);
  if (CalleeF == 0)
    return ErrorV("Unknown function referenced");
  
  // If argument mismatch error.
  if (CalleeF-&gt;arg_size() != Args.size())
    return ErrorV("Incorrect # arguments passed");

  std::vector&lt;Value*&gt; ArgsV;
  for (unsigned i = 0, e = Args.size(); i != e; ++i) {
    ArgsV.push_back(Args[i]-&gt;Codegen());
    if (ArgsV.back() == 0) return 0;
  }
  
  return Builder.CreateCall(CalleeF, ArgsV.begin(), ArgsV.end(), "calltmp");
}

Value *IfExprAST::Codegen() {
  Value *CondV = Cond-&gt;Codegen();
  if (CondV == 0) return 0;
  
  // Convert condition to a bool by comparing equal to 0.0.
  CondV = Builder.CreateFCmpONE(CondV, 
                              ConstantFP::get(getGlobalContext(), APFloat(0.0)),
                                "ifcond");
  
  Function *TheFunction = Builder.GetInsertBlock()-&gt;getParent();
  
  // Create blocks for the then and else cases.  Insert the 'then' block at the
  // end of the function.
  BasicBlock *ThenBB = BasicBlock::Create(getGlobalContext(), "then", TheFunction);
  BasicBlock *ElseBB = BasicBlock::Create(getGlobalContext(), "else");
  BasicBlock *MergeBB = BasicBlock::Create(getGlobalContext(), "ifcont");
  
  Builder.CreateCondBr(CondV, ThenBB, ElseBB);
  
  // Emit then value.
  Builder.SetInsertPoint(ThenBB);
  
  Value *ThenV = Then-&gt;Codegen();
  if (ThenV == 0) return 0;
  
  Builder.CreateBr(MergeBB);
  // Codegen of 'Then' can change the current block, update ThenBB for the PHI.
  ThenBB = Builder.GetInsertBlock();
  
  // Emit else block.
  TheFunction-&gt;getBasicBlockList().push_back(ElseBB);
  Builder.SetInsertPoint(ElseBB);
  
  Value *ElseV = Else-&gt;Codegen();
  if (ElseV == 0) return 0;
  
  Builder.CreateBr(MergeBB);
  // Codegen of 'Else' can change the current block, update ElseBB for the PHI.
  ElseBB = Builder.GetInsertBlock();
  
  // Emit merge block.
  TheFunction-&gt;getBasicBlockList().push_back(MergeBB);
  Builder.SetInsertPoint(MergeBB);
  PHINode *PN = Builder.CreatePHI(Type::getDoubleTy(getGlobalContext()),
                                  "iftmp");
  
  PN-&gt;addIncoming(ThenV, ThenBB);
  PN-&gt;addIncoming(ElseV, ElseBB);
  return PN;
}

Value *ForExprAST::Codegen() {
  // Output this as:
  //   var = alloca double
  //   ...
  //   start = startexpr
  //   store start -&gt; var
  //   goto loop
  // loop: 
  //   ...
  //   bodyexpr
  //   ...
  // loopend:
  //   step = stepexpr
  //   endcond = endexpr
  //
  //   curvar = load var
  //   nextvar = curvar + step
  //   store nextvar -&gt; var
  //   br endcond, loop, endloop
  // outloop:
  
  Function *TheFunction = Builder.GetInsertBlock()-&gt;getParent();

  // Create an alloca for the variable in the entry block.
  AllocaInst *Alloca = CreateEntryBlockAlloca(TheFunction, VarName);
  
  // Emit the start code first, without 'variable' in scope.
  Value *StartVal = Start-&gt;Codegen();
  if (StartVal == 0) return 0;
  
  // Store the value into the alloca.
  Builder.CreateStore(StartVal, Alloca);
  
  // Make the new basic block for the loop header, inserting after current
  // block.
  BasicBlock *LoopBB = BasicBlock::Create(getGlobalContext(), "loop", TheFunction);
  
  // Insert an explicit fall through from the current block to the LoopBB.
  Builder.CreateBr(LoopBB);

  // Start insertion in LoopBB.
  Builder.SetInsertPoint(LoopBB);
  
  // Within the loop, the variable is defined equal to the PHI node.  If it
  // shadows an existing variable, we have to restore it, so save it now.
  AllocaInst *OldVal = NamedValues[VarName];
  NamedValues[VarName] = Alloca;
  
  // Emit the body of the loop.  This, like any other expr, can change the
  // current BB.  Note that we ignore the value computed by the body, but don't
  // allow an error.
  if (Body-&gt;Codegen() == 0)
    return 0;
  
  // Emit the step value.
  Value *StepVal;
  if (Step) {
    StepVal = Step-&gt;Codegen();
    if (StepVal == 0) return 0;
  } else {
    // If not specified, use 1.0.
    StepVal = ConstantFP::get(getGlobalContext(), APFloat(1.0));
  }
  
  // Compute the end condition.
  Value *EndCond = End-&gt;Codegen();
  if (EndCond == 0) return EndCond;
  
  // Reload, increment, and restore the alloca.  This handles the case where
  // the body of the loop mutates the variable.
  Value *CurVar = Builder.CreateLoad(Alloca, VarName.c_str());
  Value *NextVar = Builder.CreateAdd(CurVar, StepVal, "nextvar");
  Builder.CreateStore(NextVar, Alloca);
  
  // Convert condition to a bool by comparing equal to 0.0.
  EndCond = Builder.CreateFCmpONE(EndCond, 
                              ConstantFP::get(getGlobalContext(), APFloat(0.0)),
                                  "loopcond");
  
  // Create the "after loop" block and insert it.
  BasicBlock *AfterBB = BasicBlock::Create(getGlobalContext(), "afterloop", TheFunction);
  
  // Insert the conditional branch into the end of LoopEndBB.
  Builder.CreateCondBr(EndCond, LoopBB, AfterBB);
  
  // Any new code will be inserted in AfterBB.
  Builder.SetInsertPoint(AfterBB);
  
  // Restore the unshadowed variable.
  if (OldVal)
    NamedValues[VarName] = OldVal;
  else
    NamedValues.erase(VarName);

  
  // for expr always returns 0.0.
  return Constant::getNullValue(Type::getDoubleTy(getGlobalContext()));
}

Value *VarExprAST::Codegen() {
  std::vector&lt;AllocaInst *&gt; OldBindings;
  
  Function *TheFunction = Builder.GetInsertBlock()-&gt;getParent();

  // Register all variables and emit their initializer.
  for (unsigned i = 0, e = VarNames.size(); i != e; ++i) {
    const std::string &amp;VarName = VarNames[i].first;
    ExprAST *Init = VarNames[i].second;
    
    // Emit the initializer before adding the variable to scope, this prevents
    // the initializer from referencing the variable itself, and permits stuff
    // like this:
    //  var a = 1 in
    //    var a = a in ...   # refers to outer 'a'.
    Value *InitVal;
    if (Init) {
      InitVal = Init-&gt;Codegen();
      if (InitVal == 0) return 0;
    } else { // If not specified, use 0.0.
      InitVal = ConstantFP::get(getGlobalContext(), APFloat(0.0));
    }
    
    AllocaInst *Alloca = CreateEntryBlockAlloca(TheFunction, VarName);
    Builder.CreateStore(InitVal, Alloca);

    // Remember the old variable binding so that we can restore the binding when
    // we unrecurse.
    OldBindings.push_back(NamedValues[VarName]);
    
    // Remember this binding.
    NamedValues[VarName] = Alloca;
  }
  
  // Codegen the body, now that all vars are in scope.
  Value *BodyVal = Body-&gt;Codegen();
  if (BodyVal == 0) return 0;
  
  // Pop all our variables from scope.
  for (unsigned i = 0, e = VarNames.size(); i != e; ++i)
    NamedValues[VarNames[i].first] = OldBindings[i];

  // Return the body computation.
  return BodyVal;
}

Function *PrototypeAST::Codegen() {
  // Make the function type:  double(double,double) etc.
  std::vector&lt;const Type*&gt; Doubles(Args.size(),
                                   Type::getDoubleTy(getGlobalContext()));
  FunctionType *FT = FunctionType::get(Type::getDoubleTy(getGlobalContext()),
                                       Doubles, false);
  
  Function *F = Function::Create(FT, Function::ExternalLinkage, Name, TheModule);
  
  // If F conflicted, there was already something named 'Name'.  If it has a
  // body, don't allow redefinition or reextern.
  if (F-&gt;getName() != Name) {
    // Delete the one we just made and get the existing one.
    F-&gt;eraseFromParent();
    F = TheModule-&gt;getFunction(Name);
    
    // If F already has a body, reject this.
    if (!F-&gt;empty()) {
      ErrorF("redefinition of function");
      return 0;
    }
    
    // If F took a different number of args, reject.
    if (F-&gt;arg_size() != Args.size()) {
      ErrorF("redefinition of function with different # args");
      return 0;
    }
  }
  
  // Set names for all arguments.
  unsigned Idx = 0;
  for (Function::arg_iterator AI = F-&gt;arg_begin(); Idx != Args.size();
       ++AI, ++Idx)
    AI-&gt;setName(Args[Idx]);
    
  return F;
}

/// CreateArgumentAllocas - Create an alloca for each argument and register the
/// argument in the symbol table so that references to it will succeed.
void PrototypeAST::CreateArgumentAllocas(Function *F) {
  Function::arg_iterator AI = F-&gt;arg_begin();
  for (unsigned Idx = 0, e = Args.size(); Idx != e; ++Idx, ++AI) {
    // Create an alloca for this variable.
    AllocaInst *Alloca = CreateEntryBlockAlloca(F, Args[Idx]);

    // Store the initial value into the alloca.
    Builder.CreateStore(AI, Alloca);

    // Add arguments to variable symbol table.
    NamedValues[Args[Idx]] = Alloca;
  }
}

Function *FunctionAST::Codegen() {
  NamedValues.clear();
  
  Function *TheFunction = Proto-&gt;Codegen();
  if (TheFunction == 0)
    return 0;
  
  // If this is an operator, install it.
  if (Proto-&gt;isBinaryOp())
    BinopPrecedence[Proto-&gt;getOperatorName()] = Proto-&gt;getBinaryPrecedence();
  
  // Create a new basic block to start insertion into.
  BasicBlock *BB = BasicBlock::Create(getGlobalContext(), "entry", TheFunction);
  Builder.SetInsertPoint(BB);
  
  // Add all arguments to the symbol table and create their allocas.
  Proto-&gt;CreateArgumentAllocas(TheFunction);

  if (Value *RetVal = Body-&gt;Codegen()) {
    // Finish off the function.
    Builder.CreateRet(RetVal);

    // Validate the generated code, checking for consistency.
    verifyFunction(*TheFunction);

    // Optimize the function.
    TheFPM-&gt;run(*TheFunction);
    
    return TheFunction;
  }
  
  // Error reading body, remove function.
  TheFunction-&gt;eraseFromParent();

  if (Proto-&gt;isBinaryOp())
    BinopPrecedence.erase(Proto-&gt;getOperatorName());
  return 0;
}

//===----------------------------------------------------------------------===//
// Top-Level parsing and JIT Driver
//===----------------------------------------------------------------------===//

static ExecutionEngine *TheExecutionEngine;

static void HandleDefinition() {
  if (FunctionAST *F = ParseDefinition()) {
    if (Function *LF = F-&gt;Codegen()) {
      fprintf(stderr, "Read function definition:");
      LF-&gt;dump();
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

static void HandleExtern() {
  if (PrototypeAST *P = ParseExtern()) {
    if (Function *F = P-&gt;Codegen()) {
      fprintf(stderr, "Read extern: ");
      F-&gt;dump();
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

static void HandleTopLevelExpression() {
  // Evaluate a top-level expression into an anonymous function.
  if (FunctionAST *F = ParseTopLevelExpr()) {
    if (Function *LF = F-&gt;Codegen()) {
      // JIT the function, returning a function pointer.
      void *FPtr = TheExecutionEngine-&gt;getPointerToFunction(LF);
      
      // Cast it to the right type (takes no arguments, returns a double) so we
      // can call it as a native function.
      double (*FP)() = (double (*)())(intptr_t)FPtr;
      fprintf(stderr, "Evaluated to %f\n", FP());
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

/// top ::= definition | external | expression | ';'
static void MainLoop() {
  while (1) {
    fprintf(stderr, "ready&gt; ");
    switch (CurTok) {
    case tok_eof:    return;
    case ';':        getNextToken(); break;  // ignore top-level semicolons.
    case tok_def:    HandleDefinition(); break;
    case tok_extern: HandleExtern(); break;
    default:         HandleTopLevelExpression(); break;
    }
  }
}

//===----------------------------------------------------------------------===//
// "Library" functions that can be "extern'd" from user code.
//===----------------------------------------------------------------------===//

/// putchard - putchar that takes a double and returns 0.
extern "C" 
double putchard(double X) {
  putchar((char)X);
  return 0;
}

/// printd - printf that takes a double prints it as "%f\n", returning 0.
extern "C" 
double printd(double X) {
  printf("%f\n", X);
  return 0;
}

//===----------------------------------------------------------------------===//
// Main driver code.
//===----------------------------------------------------------------------===//

int main() {
  InitializeNativeTarget();
  LLVMContext &amp;Context = getGlobalContext();

  // Install standard binary operators.
  // 1 is lowest precedence.
  BinopPrecedence['='] = 2;
  BinopPrecedence['&lt;'] = 10;
  BinopPrecedence['+'] = 20;
  BinopPrecedence['-'] = 20;
  BinopPrecedence['*'] = 40;  // highest.

  // Prime the first token.
  fprintf(stderr, "ready&gt; ");
  getNextToken();

  // Make the module, which holds all the code.
  TheModule = new Module("my cool jit", Context);

  // Create the JIT.  This takes ownership of the module.
  std::string ErrStr;
  TheExecutionEngine = EngineBuilder(TheModule).setErrorStr(&amp;ErrStr).create();
  if (!TheExecutionEngine) {
    fprintf(stderr, "Could not create ExecutionEngine: %s\n", ErrStr.c_str());
    exit(1);
  }

  FunctionPassManager OurFPM(TheModule);

  // Set up the optimizer pipeline.  Start with registering info about how the
  // target lays out data structures.
  OurFPM.add(new TargetData(*TheExecutionEngine-&gt;getTargetData()));
  // Promote allocas to registers.
  OurFPM.add(createPromoteMemoryToRegisterPass());
  // Do simple "peephole" optimizations and bit-twiddling optzns.
  OurFPM.add(createInstructionCombiningPass());
  // Reassociate expressions.
  OurFPM.add(createReassociatePass());
  // Eliminate Common SubExpressions.
  OurFPM.add(createGVNPass());
  // Simplify the control flow graph (deleting unreachable blocks, etc).
  OurFPM.add(createCFGSimplificationPass());

  OurFPM.doInitialization();

  // Set the global so the code gen can use this.
  TheFPM = &amp;OurFPM;

  // Run the main "interpreter loop" now.
  MainLoop();

  TheFPM = 0;

  // Print out all of the generated code.
  TheModule-&gt;dump();

  return 0;
}
</pre>
</div>

<a href="LangImpl8.html">Next: Conclusion and other useful LLVM tidbits</a>
</div>

<!-- *********************************************************************** -->
<hr>
<address>
  <a href="http://jigsaw.w3.org/css-validator/check/referer"><img
  src="http://jigsaw.w3.org/css-validator/images/vcss" alt="Valid CSS!"></a>
  <a href="http://validator.w3.org/check/referer"><img
  src="http://www.w3.org/Icons/valid-html401" alt="Valid HTML 4.01!"></a>

  <a href="mailto:sabre@nondot.org">Chris Lattner</a><br>
  <a href="http://llvm.org">The LLVM Compiler Infrastructure</a><br>
  Last modified: $Date$
</address>
</body>
</html>