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
|
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<title>Kaleidoscope: Extending the Language: Control Flow</title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<meta name="author" content="Chris Lattner">
<link rel="stylesheet" href="../_static/llvm.css" type="text/css">
</head>
<body>
<h1>Kaleidoscope: Extending the Language: Control Flow</h1>
<ul>
<li><a href="index.html">Up to Tutorial Index</a></li>
<li>Chapter 5
<ol>
<li><a href="#intro">Chapter 5 Introduction</a></li>
<li><a href="#ifthen">If/Then/Else</a>
<ol>
<li><a href="#iflexer">Lexer Extensions</a></li>
<li><a href="#ifast">AST Extensions</a></li>
<li><a href="#ifparser">Parser Extensions</a></li>
<li><a href="#ifir">LLVM IR</a></li>
<li><a href="#ifcodegen">Code Generation</a></li>
</ol>
</li>
<li><a href="#for">'for' Loop Expression</a>
<ol>
<li><a href="#forlexer">Lexer Extensions</a></li>
<li><a href="#forast">AST Extensions</a></li>
<li><a href="#forparser">Parser Extensions</a></li>
<li><a href="#forir">LLVM IR</a></li>
<li><a href="#forcodegen">Code Generation</a></li>
</ol>
</li>
<li><a href="#code">Full Code Listing</a></li>
</ol>
</li>
<li><a href="LangImpl6.html">Chapter 6</a>: Extending the Language:
User-defined Operators</li>
</ul>
<div class="doc_author">
<p>Written by <a href="mailto:sabre@nondot.org">Chris Lattner</a></p>
</div>
<!-- *********************************************************************** -->
<h2><a name="intro">Chapter 5 Introduction</a></h2>
<!-- *********************************************************************** -->
<div>
<p>Welcome to Chapter 5 of the "<a href="index.html">Implementing a language
with LLVM</a>" tutorial. Parts 1-4 described the implementation of the simple
Kaleidoscope language and included support for generating LLVM IR, followed by
optimizations and a JIT compiler. Unfortunately, as presented, Kaleidoscope is
mostly useless: it has no control flow other than call and return. This means
that you can't have conditional branches in the code, significantly limiting its
power. In this episode of "build that compiler", we'll extend Kaleidoscope to
have an if/then/else expression plus a simple 'for' loop.</p>
</div>
<!-- *********************************************************************** -->
<h2><a name="ifthen">If/Then/Else</a></h2>
<!-- *********************************************************************** -->
<div>
<p>
Extending Kaleidoscope to support if/then/else is quite straightforward. It
basically requires adding support for this "new" concept to the lexer,
parser, AST, and LLVM code emitter. This example is nice, because it shows how
easy it is to "grow" a language over time, incrementally extending it as new
ideas are discovered.</p>
<p>Before we get going on "how" we add this extension, lets talk about "what" we
want. The basic idea is that we want to be able to write this sort of thing:
</p>
<div class="doc_code">
<pre>
def fib(x)
if x < 3 then
1
else
fib(x-1)+fib(x-2);
</pre>
</div>
<p>In Kaleidoscope, every construct is an expression: there are no statements.
As such, the if/then/else expression needs to return a value like any other.
Since we're using a mostly functional form, we'll have it evaluate its
conditional, then return the 'then' or 'else' value based on how the condition
was resolved. This is very similar to the C "?:" expression.</p>
<p>The semantics of the if/then/else expression is that it evaluates the
condition to a boolean equality value: 0.0 is considered to be false and
everything else is considered to be true.
If the condition is true, the first subexpression is evaluated and returned, if
the condition is false, the second subexpression is evaluated and returned.
Since Kaleidoscope allows side-effects, this behavior is important to nail down.
</p>
<p>Now that we know what we "want", lets break this down into its constituent
pieces.</p>
<!-- ======================================================================= -->
<h4><a name="iflexer">Lexer Extensions for If/Then/Else</a></h4>
<!-- ======================================================================= -->
<div>
<p>The lexer extensions are straightforward. First we add new enum values
for the relevant tokens:</p>
<div class="doc_code">
<pre>
// control
tok_if = -6, tok_then = -7, tok_else = -8,
</pre>
</div>
<p>Once we have that, we recognize the new keywords in the lexer. This is pretty simple
stuff:</p>
<div class="doc_code">
<pre>
...
if (IdentifierStr == "def") return tok_def;
if (IdentifierStr == "extern") return tok_extern;
<b>if (IdentifierStr == "if") return tok_if;
if (IdentifierStr == "then") return tok_then;
if (IdentifierStr == "else") return tok_else;</b>
return tok_identifier;
</pre>
</div>
</div>
<!-- ======================================================================= -->
<h4><a name="ifast">AST Extensions for If/Then/Else</a></h4>
<!-- ======================================================================= -->
<div>
<p>To represent the new expression we add a new AST node for it:</p>
<div class="doc_code">
<pre>
/// 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();
};
</pre>
</div>
<p>The AST node just has pointers to the various subexpressions.</p>
</div>
<!-- ======================================================================= -->
<h4><a name="ifparser">Parser Extensions for If/Then/Else</a></h4>
<!-- ======================================================================= -->
<div>
<p>Now that we have the relevant tokens coming from the lexer and we have the
AST node to build, our parsing logic is relatively straightforward. First we
define a new parsing function:</p>
<div class="doc_code">
<pre>
/// 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);
}
</pre>
</div>
<p>Next we hook it up as a primary expression:</p>
<div class="doc_code">
<pre>
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();
<b>case tok_if: return ParseIfExpr();</b>
}
}
</pre>
</div>
</div>
<!-- ======================================================================= -->
<h4><a name="ifir">LLVM IR for If/Then/Else</a></h4>
<!-- ======================================================================= -->
<div>
<p>Now that we have it parsing and building the AST, the final piece is adding
LLVM code generation support. This is the most interesting part of the
if/then/else example, because this is where it starts to introduce new concepts.
All of the code above has been thoroughly described in previous chapters.
</p>
<p>To motivate the code we want to produce, lets take a look at a simple
example. Consider:</p>
<div class="doc_code">
<pre>
extern foo();
extern bar();
def baz(x) if x then foo() else bar();
</pre>
</div>
<p>If you disable optimizations, the code you'll (soon) get from Kaleidoscope
looks like this:</p>
<div class="doc_code">
<pre>
declare double @foo()
declare double @bar()
define double @baz(double %x) {
entry:
%ifcond = fcmp one double %x, 0.000000e+00
br i1 %ifcond, label %then, label %else
then: ; preds = %entry
%calltmp = call double @foo()
br label %ifcont
else: ; preds = %entry
%calltmp1 = call double @bar()
br label %ifcont
ifcont: ; preds = %else, %then
%iftmp = phi double [ %calltmp, %then ], [ %calltmp1, %else ]
ret double %iftmp
}
</pre>
</div>
<p>To visualize the control flow graph, you can use a nifty feature of the LLVM
'<a href="http://llvm.org/cmds/opt.html">opt</a>' tool. If you put this LLVM IR
into "t.ll" and run "<tt>llvm-as < t.ll | opt -analyze -view-cfg</tt>", <a
href="../ProgrammersManual.html#ViewGraph">a window will pop up</a> and you'll
see this graph:</p>
<div style="text-align: center"><img src="LangImpl5-cfg.png" alt="Example CFG" width="423"
height="315"></div>
<p>Another way to get this is to call "<tt>F->viewCFG()</tt>" or
"<tt>F->viewCFGOnly()</tt>" (where F is a "<tt>Function*</tt>") either by
inserting actual calls into the code and recompiling or by calling these in the
debugger. LLVM has many nice features for visualizing various graphs.</p>
<p>Getting back to the generated code, it is fairly simple: the entry block
evaluates the conditional expression ("x" in our case here) and compares the
result to 0.0 with the "<tt><a href="../LangRef.html#i_fcmp">fcmp</a> one</tt>"
instruction ('one' is "Ordered and Not Equal"). Based on the result of this
expression, the code jumps to either the "then" or "else" blocks, which contain
the expressions for the true/false cases.</p>
<p>Once the then/else blocks are finished executing, they both branch back to the
'ifcont' block to execute the code that happens after the if/then/else. In this
case the only thing left to do is to return to the caller of the function. The
question then becomes: how does the code know which expression to return?</p>
<p>The answer to this question involves an important SSA operation: the
<a href="http://en.wikipedia.org/wiki/Static_single_assignment_form">Phi
operation</a>. If you're not familiar with SSA, <a
href="http://en.wikipedia.org/wiki/Static_single_assignment_form">the wikipedia
article</a> is a good introduction and there are various other introductions to
it available on your favorite search engine. The short version is that
"execution" of the Phi operation requires "remembering" which block control came
from. The Phi operation takes on the value corresponding to the input control
block. In this case, if control comes in from the "then" block, it gets the
value of "calltmp". If control comes from the "else" block, it gets the value
of "calltmp1".</p>
<p>At this point, you are probably starting to think "Oh no! This means my
simple and elegant front-end will have to start generating SSA form in order to
use LLVM!". Fortunately, this is not the case, and we strongly advise
<em>not</em> implementing an SSA construction algorithm in your front-end
unless there is an amazingly good reason to do so. In practice, there are two
sorts of values that float around in code written for your average imperative
programming language that might need Phi nodes:</p>
<ol>
<li>Code that involves user variables: <tt>x = 1; x = x + 1; </tt></li>
<li>Values that are implicit in the structure of your AST, such as the Phi node
in this case.</li>
</ol>
<p>In <a href="LangImpl7.html">Chapter 7</a> of this tutorial ("mutable
variables"), we'll talk about #1
in depth. For now, just believe me that you don't need SSA construction to
handle this case. For #2, you have the choice of using the techniques that we will
describe for #1, or you can insert Phi nodes directly, if convenient. In this
case, it is really really easy to generate the Phi node, so we choose to do it
directly.</p>
<p>Okay, enough of the motivation and overview, lets generate code!</p>
</div>
<!-- ======================================================================= -->
<h4><a name="ifcodegen">Code Generation for If/Then/Else</a></h4>
<!-- ======================================================================= -->
<div>
<p>In order to generate code for this, we implement the <tt>Codegen</tt> method
for <tt>IfExprAST</tt>:</p>
<div class="doc_code">
<pre>
Value *IfExprAST::Codegen() {
Value *CondV = Cond->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");
</pre>
</div>
<p>This code is straightforward and similar to what we saw before. We emit the
expression for the condition, then compare that value to zero to get a truth
value as a 1-bit (bool) value.</p>
<div class="doc_code">
<pre>
Function *TheFunction = Builder.GetInsertBlock()->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);
</pre>
</div>
<p>This code creates the basic blocks that are related to the if/then/else
statement, and correspond directly to the blocks in the example above. The
first line gets the current Function object that is being built. It
gets this by asking the builder for the current BasicBlock, and asking that
block for its "parent" (the function it is currently embedded into).</p>
<p>Once it has that, it creates three blocks. Note that it passes "TheFunction"
into the constructor for the "then" block. This causes the constructor to
automatically insert the new block into the end of the specified function. The
other two blocks are created, but aren't yet inserted into the function.</p>
<p>Once the blocks are created, we can emit the conditional branch that chooses
between them. Note that creating new blocks does not implicitly affect the
IRBuilder, so it is still inserting into the block that the condition
went into. Also note that it is creating a branch to the "then" block and the
"else" block, even though the "else" block isn't inserted into the function yet.
This is all ok: it is the standard way that LLVM supports forward
references.</p>
<div class="doc_code">
<pre>
// Emit then value.
Builder.SetInsertPoint(ThenBB);
Value *ThenV = Then->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();
</pre>
</div>
<p>After the conditional branch is inserted, we move the builder to start
inserting into the "then" block. Strictly speaking, this call moves the
insertion point to be at the end of the specified block. However, since the
"then" block is empty, it also starts out by inserting at the beginning of the
block. :)</p>
<p>Once the insertion point is set, we recursively codegen the "then" expression
from the AST. To finish off the "then" block, we create an unconditional branch
to the merge block. One interesting (and very important) aspect of the LLVM IR
is that it <a href="../LangRef.html#functionstructure">requires all basic blocks
to be "terminated"</a> with a <a href="../LangRef.html#terminators">control flow
instruction</a> such as return or branch. This means that all control flow,
<em>including fall throughs</em> must be made explicit in the LLVM IR. If you
violate this rule, the verifier will emit an error.</p>
<p>The final line here is quite subtle, but is very important. The basic issue
is that when we create the Phi node in the merge block, we need to set up the
block/value pairs that indicate how the Phi will work. Importantly, the Phi
node expects to have an entry for each predecessor of the block in the CFG. Why
then, are we getting the current block when we just set it to ThenBB 5 lines
above? The problem is that the "Then" expression may actually itself change the
block that the Builder is emitting into if, for example, it contains a nested
"if/then/else" expression. Because calling Codegen recursively could
arbitrarily change the notion of the current block, we are required to get an
up-to-date value for code that will set up the Phi node.</p>
<div class="doc_code">
<pre>
// Emit else block.
TheFunction->getBasicBlockList().push_back(ElseBB);
Builder.SetInsertPoint(ElseBB);
Value *ElseV = Else->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();
</pre>
</div>
<p>Code generation for the 'else' block is basically identical to codegen for
the 'then' block. The only significant difference is the first line, which adds
the 'else' block to the function. Recall previously that the 'else' block was
created, but not added to the function. Now that the 'then' and 'else' blocks
are emitted, we can finish up with the merge code:</p>
<div class="doc_code">
<pre>
// Emit merge block.
TheFunction->getBasicBlockList().push_back(MergeBB);
Builder.SetInsertPoint(MergeBB);
PHINode *PN = Builder.CreatePHI(Type::getDoubleTy(getGlobalContext()), 2,
"iftmp");
PN->addIncoming(ThenV, ThenBB);
PN->addIncoming(ElseV, ElseBB);
return PN;
}
</pre>
</div>
<p>The first two lines here are now familiar: the first adds the "merge" block
to the Function object (it was previously floating, like the else block above).
The second block changes the insertion point so that newly created code will go
into the "merge" block. Once that is done, we need to create the PHI node and
set up the block/value pairs for the PHI.</p>
<p>Finally, the CodeGen function returns the phi node as the value computed by
the if/then/else expression. In our example above, this returned value will
feed into the code for the top-level function, which will create the return
instruction.</p>
<p>Overall, we now have the ability to execute conditional code in
Kaleidoscope. With this extension, Kaleidoscope is a fairly complete language
that can calculate a wide variety of numeric functions. Next up we'll add
another useful expression that is familiar from non-functional languages...</p>
</div>
</div>
<!-- *********************************************************************** -->
<h2><a name="for">'for' Loop Expression</a></h2>
<!-- *********************************************************************** -->
<div>
<p>Now that we know how to add basic control flow constructs to the language,
we have the tools to add more powerful things. Lets add something more
aggressive, a 'for' expression:</p>
<div class="doc_code">
<pre>
extern putchard(char)
def printstar(n)
for i = 1, i < n, 1.0 in
putchard(42); # ascii 42 = '*'
# print 100 '*' characters
printstar(100);
</pre>
</div>
<p>This expression defines a new variable ("i" in this case) which iterates from
a starting value, while the condition ("i < n" in this case) is true,
incrementing by an optional step value ("1.0" in this case). If the step value
is omitted, it defaults to 1.0. While the loop is true, it executes its
body expression. Because we don't have anything better to return, we'll just
define the loop as always returning 0.0. In the future when we have mutable
variables, it will get more useful.</p>
<p>As before, lets talk about the changes that we need to Kaleidoscope to
support this.</p>
<!-- ======================================================================= -->
<h4><a name="forlexer">Lexer Extensions for the 'for' Loop</a></h4>
<!-- ======================================================================= -->
<div>
<p>The lexer extensions are the same sort of thing as for if/then/else:</p>
<div class="doc_code">
<pre>
... in enum Token ...
// control
tok_if = -6, tok_then = -7, tok_else = -8,
<b> tok_for = -9, tok_in = -10</b>
... in gettok ...
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;
<b>if (IdentifierStr == "for") return tok_for;
if (IdentifierStr == "in") return tok_in;</b>
return tok_identifier;
</pre>
</div>
</div>
<!-- ======================================================================= -->
<h4><a name="forast">AST Extensions for the 'for' Loop</a></h4>
<!-- ======================================================================= -->
<div>
<p>The AST node is just as simple. It basically boils down to capturing
the variable name and the constituent expressions in the node.</p>
<div class="doc_code">
<pre>
/// ForExprAST - Expression class for for/in.
class ForExprAST : public ExprAST {
std::string VarName;
ExprAST *Start, *End, *Step, *Body;
public:
ForExprAST(const std::string &varname, ExprAST *start, ExprAST *end,
ExprAST *step, ExprAST *body)
: VarName(varname), Start(start), End(end), Step(step), Body(body) {}
virtual Value *Codegen();
};
</pre>
</div>
</div>
<!-- ======================================================================= -->
<h4><a name="forparser">Parser Extensions for the 'for' Loop</a></h4>
<!-- ======================================================================= -->
<div>
<p>The parser code is also fairly standard. The only interesting thing here is
handling of the optional step value. The parser code handles it by checking to
see if the second comma is present. If not, it sets the step value to null in
the AST node:</p>
<div class="doc_code">
<pre>
/// 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);
}
</pre>
</div>
</div>
<!-- ======================================================================= -->
<h4><a name="forir">LLVM IR for the 'for' Loop</a></h4>
<!-- ======================================================================= -->
<div>
<p>Now we get to the good part: the LLVM IR we want to generate for this thing.
With the simple example above, we get this LLVM IR (note that this dump is
generated with optimizations disabled for clarity):
</p>
<div class="doc_code">
<pre>
declare double @putchard(double)
define double @printstar(double %n) {
entry:
; initial value = 1.0 (inlined into phi)
br label %loop
loop: ; preds = %loop, %entry
%i = phi double [ 1.000000e+00, %entry ], [ %nextvar, %loop ]
; body
%calltmp = call double @putchard(double 4.200000e+01)
; increment
%nextvar = fadd double %i, 1.000000e+00
; termination test
%cmptmp = fcmp ult double %i, %n
%booltmp = uitofp i1 %cmptmp to double
%loopcond = fcmp one double %booltmp, 0.000000e+00
br i1 %loopcond, label %loop, label %afterloop
afterloop: ; preds = %loop
; loop always returns 0.0
ret double 0.000000e+00
}
</pre>
</div>
<p>This loop contains all the same constructs we saw before: a phi node, several
expressions, and some basic blocks. Lets see how this fits together.</p>
</div>
<!-- ======================================================================= -->
<h4><a name="forcodegen">Code Generation for the 'for' Loop</a></h4>
<!-- ======================================================================= -->
<div>
<p>The first part of Codegen is very simple: we just output the start expression
for the loop value:</p>
<div class="doc_code">
<pre>
Value *ForExprAST::Codegen() {
// Emit the start code first, without 'variable' in scope.
Value *StartVal = Start->Codegen();
if (StartVal == 0) return 0;
</pre>
</div>
<p>With this out of the way, the next step is to set up the LLVM basic block
for the start of the loop body. In the case above, the whole loop body is one
block, but remember that the body code itself could consist of multiple blocks
(e.g. if it contains an if/then/else or a for/in expression).</p>
<div class="doc_code">
<pre>
// Make the new basic block for the loop header, inserting after current
// block.
Function *TheFunction = Builder.GetInsertBlock()->getParent();
BasicBlock *PreheaderBB = Builder.GetInsertBlock();
BasicBlock *LoopBB = BasicBlock::Create(getGlobalContext(), "loop", TheFunction);
// Insert an explicit fall through from the current block to the LoopBB.
Builder.CreateBr(LoopBB);
</pre>
</div>
<p>This code is similar to what we saw for if/then/else. Because we will need
it to create the Phi node, we remember the block that falls through into the
loop. Once we have that, we create the actual block that starts the loop and
create an unconditional branch for the fall-through between the two blocks.</p>
<div class="doc_code">
<pre>
// Start insertion in LoopBB.
Builder.SetInsertPoint(LoopBB);
// Start the PHI node with an entry for Start.
PHINode *Variable = Builder.CreatePHI(Type::getDoubleTy(getGlobalContext()), 2, VarName.c_str());
Variable->addIncoming(StartVal, PreheaderBB);
</pre>
</div>
<p>Now that the "preheader" for the loop is set up, we switch to emitting code
for the loop body. To begin with, we move the insertion point and create the
PHI node for the loop induction variable. Since we already know the incoming
value for the starting value, we add it to the Phi node. Note that the Phi will
eventually get a second value for the backedge, but we can't set it up yet
(because it doesn't exist!).</p>
<div class="doc_code">
<pre>
// 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.
Value *OldVal = NamedValues[VarName];
NamedValues[VarName] = Variable;
// 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->Codegen() == 0)
return 0;
</pre>
</div>
<p>Now the code starts to get more interesting. Our 'for' loop introduces a new
variable to the symbol table. This means that our symbol table can now contain
either function arguments or loop variables. To handle this, before we codegen
the body of the loop, we add the loop variable as the current value for its
name. Note that it is possible that there is a variable of the same name in the
outer scope. It would be easy to make this an error (emit an error and return
null if there is already an entry for VarName) but we choose to allow shadowing
of variables. In order to handle this correctly, we remember the Value that
we are potentially shadowing in <tt>OldVal</tt> (which will be null if there is
no shadowed variable).</p>
<p>Once the loop variable is set into the symbol table, the code recursively
codegen's the body. This allows the body to use the loop variable: any
references to it will naturally find it in the symbol table.</p>
<div class="doc_code">
<pre>
// Emit the step value.
Value *StepVal;
if (Step) {
StepVal = Step->Codegen();
if (StepVal == 0) return 0;
} else {
// If not specified, use 1.0.
StepVal = ConstantFP::get(getGlobalContext(), APFloat(1.0));
}
Value *NextVar = Builder.CreateFAdd(Variable, StepVal, "nextvar");
</pre>
</div>
<p>Now that the body is emitted, we compute the next value of the iteration
variable by adding the step value, or 1.0 if it isn't present. '<tt>NextVar</tt>'
will be the value of the loop variable on the next iteration of the loop.</p>
<div class="doc_code">
<pre>
// Compute the end condition.
Value *EndCond = End->Codegen();
if (EndCond == 0) return EndCond;
// Convert condition to a bool by comparing equal to 0.0.
EndCond = Builder.CreateFCmpONE(EndCond,
ConstantFP::get(getGlobalContext(), APFloat(0.0)),
"loopcond");
</pre>
</div>
<p>Finally, we evaluate the exit value of the loop, to determine whether the
loop should exit. This mirrors the condition evaluation for the if/then/else
statement.</p>
<div class="doc_code">
<pre>
// Create the "after loop" block and insert it.
BasicBlock *LoopEndBB = Builder.GetInsertBlock();
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);
</pre>
</div>
<p>With the code for the body of the loop complete, we just need to finish up
the control flow for it. This code remembers the end block (for the phi node),
then creates the block for the loop exit ("afterloop"). Based on the value of
the exit condition, it creates a conditional branch that chooses between
executing the loop again and exiting the loop. Any future code is emitted in
the "afterloop" block, so it sets the insertion position to it.</p>
<div class="doc_code">
<pre>
// Add a new entry to the PHI node for the backedge.
Variable->addIncoming(NextVar, LoopEndBB);
// 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()));
}
</pre>
</div>
<p>The final code handles various cleanups: now that we have the "NextVar"
value, we can add the incoming value to the loop PHI node. After that, we
remove the loop variable from the symbol table, so that it isn't in scope after
the for loop. Finally, code generation of the for loop always returns 0.0, so
that is what we return from <tt>ForExprAST::Codegen</tt>.</p>
<p>With this, we conclude the "adding control flow to Kaleidoscope" chapter of
the tutorial. In this chapter we added two control flow constructs, and used them to motivate a couple of aspects of the LLVM IR that are important for front-end implementors
to know. In the next chapter of our saga, we will get a bit crazier and add
<a href="LangImpl6.html">user-defined operators</a> to our poor innocent
language.</p>
</div>
</div>
<!-- *********************************************************************** -->
<h2><a name="code">Full Code Listing</a></h2>
<!-- *********************************************************************** -->
<div>
<p>
Here is the complete code listing for our running example, enhanced with the
if/then/else and for expressions.. To build this example, use:
</p>
<div class="doc_code">
<pre>
# Compile
clang++ -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/IRBuilder.h"
#include "llvm/LLVMContext.h"
#include "llvm/Module.h"
#include "llvm/PassManager.h"
#include "llvm/Analysis/Verifier.h"
#include "llvm/Analysis/Passes.h"
#include "llvm/Target/TargetData.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Support/TargetSelect.h"
#include <cstdio>
#include <string>
#include <map>
#include <vector>
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
};
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;
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 && LastChar != '\n' && 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 &name) : Name(name) {}
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<ExprAST*> Args;
public:
CallExprAST(const std::string &callee, std::vector<ExprAST*> &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 &varname, ExprAST *start, ExprAST *end,
ExprAST *step, ExprAST *body)
: VarName(varname), Start(start), End(end), Step(step), 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).
class PrototypeAST {
std::string Name;
std::vector<std::string> Args;
public:
PrototypeAST(const std::string &name, const std::vector<std::string> &args)
: Name(name), Args(args) {}
Function *Codegen();
};
/// 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<char, int> 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 <= 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<ExprAST*> 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);
}
/// primary
/// ::= identifierexpr
/// ::= numberexpr
/// ::= parenexpr
/// ::= ifexpr
/// ::= forexpr
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();
}
}
/// binoprhs
/// ::= ('+' primary)*
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 < ExprPrec)
return LHS;
// Okay, we know this is a binop.
int BinOp = CurTok;
getNextToken(); // eat binop
// Parse the primary expression after the binary operator.
ExprAST *RHS = ParsePrimary();
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 < NextPrec) {
RHS = ParseBinOpRHS(TokPrec+1, RHS);
if (RHS == 0) return 0;
}
// Merge LHS/RHS.
LHS = new BinaryExprAST(BinOp, LHS, RHS);
}
}
/// expression
/// ::= primary binoprhs
///
static ExprAST *ParseExpression() {
ExprAST *LHS = ParsePrimary();
if (!LHS) return 0;
return ParseBinOpRHS(0, LHS);
}
/// prototype
/// ::= id '(' id* ')'
static PrototypeAST *ParsePrototype() {
if (CurTok != tok_identifier)
return ErrorP("Expected function name in prototype");
std::string FnName = IdentifierStr;
getNextToken();
if (CurTok != '(')
return ErrorP("Expected '(' in prototype");
std::vector<std::string> ArgNames;
while (getNextToken() == tok_identifier)
ArgNames.push_back(IdentifierStr);
if (CurTok != ')')
return ErrorP("Expected ')' in prototype");
// success.
getNextToken(); // eat ')'.
return new PrototypeAST(FnName, ArgNames);
}
/// 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<std::string>());
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<> Builder(getGlobalContext());
static std::map<std::string, Value*> NamedValues;
static FunctionPassManager *TheFPM;
Value *ErrorV(const char *Str) { Error(Str); return 0; }
Value *NumberExprAST::Codegen() {
return ConstantFP::get(getGlobalContext(), APFloat(Val));
}
Value *VariableExprAST::Codegen() {
// Look this variable up in the function.
Value *V = NamedValues[Name];
return V ? V : ErrorV("Unknown variable name");
}
Value *BinaryExprAST::Codegen() {
Value *L = LHS->Codegen();
Value *R = RHS->Codegen();
if (L == 0 || R == 0) return 0;
switch (Op) {
case '+': return Builder.CreateFAdd(L, R, "addtmp");
case '-': return Builder.CreateFSub(L, R, "subtmp");
case '*': return Builder.CreateFMul(L, R, "multmp");
case '<':
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: return ErrorV("invalid binary operator");
}
}
Value *CallExprAST::Codegen() {
// Look up the name in the global module table.
Function *CalleeF = TheModule->getFunction(Callee);
if (CalleeF == 0)
return ErrorV("Unknown function referenced");
// If argument mismatch error.
if (CalleeF->arg_size() != Args.size())
return ErrorV("Incorrect # arguments passed");
std::vector<Value*> ArgsV;
for (unsigned i = 0, e = Args.size(); i != e; ++i) {
ArgsV.push_back(Args[i]->Codegen());
if (ArgsV.back() == 0) return 0;
}
return Builder.CreateCall(CalleeF, ArgsV, "calltmp");
}
Value *IfExprAST::Codegen() {
Value *CondV = Cond->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()->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->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->getBasicBlockList().push_back(ElseBB);
Builder.SetInsertPoint(ElseBB);
Value *ElseV = Else->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->getBasicBlockList().push_back(MergeBB);
Builder.SetInsertPoint(MergeBB);
PHINode *PN = Builder.CreatePHI(Type::getDoubleTy(getGlobalContext()), 2,
"iftmp");
PN->addIncoming(ThenV, ThenBB);
PN->addIncoming(ElseV, ElseBB);
return PN;
}
Value *ForExprAST::Codegen() {
// Output this as:
// ...
// start = startexpr
// goto loop
// loop:
// variable = phi [start, loopheader], [nextvariable, loopend]
// ...
// bodyexpr
// ...
// loopend:
// step = stepexpr
// nextvariable = variable + step
// endcond = endexpr
// br endcond, loop, endloop
// outloop:
// Emit the start code first, without 'variable' in scope.
Value *StartVal = Start->Codegen();
if (StartVal == 0) return 0;
// Make the new basic block for the loop header, inserting after current
// block.
Function *TheFunction = Builder.GetInsertBlock()->getParent();
BasicBlock *PreheaderBB = Builder.GetInsertBlock();
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);
// Start the PHI node with an entry for Start.
PHINode *Variable = Builder.CreatePHI(Type::getDoubleTy(getGlobalContext()), 2, VarName.c_str());
Variable->addIncoming(StartVal, PreheaderBB);
// 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.
Value *OldVal = NamedValues[VarName];
NamedValues[VarName] = Variable;
// 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->Codegen() == 0)
return 0;
// Emit the step value.
Value *StepVal;
if (Step) {
StepVal = Step->Codegen();
if (StepVal == 0) return 0;
} else {
// If not specified, use 1.0.
StepVal = ConstantFP::get(getGlobalContext(), APFloat(1.0));
}
Value *NextVar = Builder.CreateFAdd(Variable, StepVal, "nextvar");
// Compute the end condition.
Value *EndCond = End->Codegen();
if (EndCond == 0) return EndCond;
// 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 *LoopEndBB = Builder.GetInsertBlock();
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);
// Add a new entry to the PHI node for the backedge.
Variable->addIncoming(NextVar, LoopEndBB);
// 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()));
}
Function *PrototypeAST::Codegen() {
// Make the function type: double(double,double) etc.
std::vector<Type*> 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->getName() != Name) {
// Delete the one we just made and get the existing one.
F->eraseFromParent();
F = TheModule->getFunction(Name);
// If F already has a body, reject this.
if (!F->empty()) {
ErrorF("redefinition of function");
return 0;
}
// If F took a different number of args, reject.
if (F->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->arg_begin(); Idx != Args.size();
++AI, ++Idx) {
AI->setName(Args[Idx]);
// Add arguments to variable symbol table.
NamedValues[Args[Idx]] = AI;
}
return F;
}
Function *FunctionAST::Codegen() {
NamedValues.clear();
Function *TheFunction = Proto->Codegen();
if (TheFunction == 0)
return 0;
// Create a new basic block to start insertion into.
BasicBlock *BB = BasicBlock::Create(getGlobalContext(), "entry", TheFunction);
Builder.SetInsertPoint(BB);
if (Value *RetVal = Body->Codegen()) {
// Finish off the function.
Builder.CreateRet(RetVal);
// Validate the generated code, checking for consistency.
verifyFunction(*TheFunction);
// Optimize the function.
TheFPM->run(*TheFunction);
return TheFunction;
}
// Error reading body, remove function.
TheFunction->eraseFromParent();
return 0;
}
//===----------------------------------------------------------------------===//
// Top-Level parsing and JIT Driver
//===----------------------------------------------------------------------===//
static ExecutionEngine *TheExecutionEngine;
static void HandleDefinition() {
if (FunctionAST *F = ParseDefinition()) {
if (Function *LF = F->Codegen()) {
fprintf(stderr, "Read function definition:");
LF->dump();
}
} else {
// Skip token for error recovery.
getNextToken();
}
}
static void HandleExtern() {
if (PrototypeAST *P = ParseExtern()) {
if (Function *F = P->Codegen()) {
fprintf(stderr, "Read extern: ");
F->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->Codegen()) {
// JIT the function, returning a function pointer.
void *FPtr = TheExecutionEngine->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> ");
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;
}
//===----------------------------------------------------------------------===//
// Main driver code.
//===----------------------------------------------------------------------===//
int main() {
InitializeNativeTarget();
LLVMContext &Context = getGlobalContext();
// Install standard binary operators.
// 1 is lowest precedence.
BinopPrecedence['<'] = 10;
BinopPrecedence['+'] = 20;
BinopPrecedence['-'] = 20;
BinopPrecedence['*'] = 40; // highest.
// Prime the first token.
fprintf(stderr, "ready> ");
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(&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->getTargetData()));
// Provide basic AliasAnalysis support for GVN.
OurFPM.add(createBasicAliasAnalysisPass());
// 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 = &OurFPM;
// Run the main "interpreter loop" now.
MainLoop();
TheFPM = 0;
// Print out all of the generated code.
TheModule->dump();
return 0;
}
</pre>
</div>
<a href="LangImpl6.html">Next: Extending the language: user-defined operators</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>
|
