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
|
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<title>Kaleidoscope: Implementing code generation to LLVM IR</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: Code generation to LLVM IR</div>
<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">Part 3 Introduction</a></div>
<!-- *********************************************************************** -->
<div class="doc_text">
<p>Welcome to part 3 of the "<a href="index.html">Implementing a language with
LLVM</a>" tutorial. This chapter shows you how to transform the <a
href="LangImpl2.html">Abstract Syntax Tree built in Chapter 2</a> into LLVM IR.
This will teach you a little bit about how LLVM does things, as well as
demonstrate how easy it is to use. It's much more work to build a lexer and
parser than it is to generate LLVM IR code.
</p>
</div>
<!-- *********************************************************************** -->
<div class="doc_section"><a name="basics">Code Generation setup</a></div>
<!-- *********************************************************************** -->
<div class="doc_text">
<p>
In order to generate LLVM IR, we want some simple setup to get started. First,
we define virtual codegen methods in each AST class:</p>
<div class="doc_code">
<pre>
/// 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:
explicit NumberExprAST(double val) : Val(val) {}
virtual Value *Codegen();
};
...
</pre>
</div>
<p>The Codegen() method says to emit IR for that AST node and all things it
depends on, and they all return an LLVM Value object.
"Value" is the class used to represent a "<a
href="http://en.wikipedia.org/wiki/Static_single_assignment_form">Static Single
Assignment (SSA)</a> register" or "SSA value" in LLVM. The most distinct aspect
of SSA values is that their value is computed as the related instruction
executes, and it does not get a new value until (and if) the instruction
re-executes. In order words, there is no way to "change" an SSA value. For
more information, please read up on <a
href="http://en.wikipedia.org/wiki/Static_single_assignment_form">Static Single
Assignment</a> - the concepts are really quite natural once you grok them.</p>
<p>The
second thing we want is an "Error" method like we used for parser, which will
be used to report errors found during code generation (for example, use of an
undeclared parameter):</p>
<div class="doc_code">
<pre>
Value *ErrorV(const char *Str) { Error(Str); return 0; }
static Module *TheModule;
static LLVMBuilder Builder;
static std::map<std::string, Value*> NamedValues;
</pre>
</div>
<p>The static variables will be used during code generation. <tt>TheModule</tt>
is the LLVM construct that contains all of the functions and global variables in
a chunk of code. In many ways, it is the top-level structure that the LLVM IR
uses to contain code.</p>
<p>The <tt>Builder</tt> object is a helper object that makes it easy to generate
LLVM instructions. The <tt>Builder</tt> keeps track of the current place to
insert instructions and has methods to create new instructions.</p>
<p>The <tt>NamedValues</tt> map keeps track of which values are defined in the
current scope and what their LLVM representation is. In this form of
Kaleidoscope, the only things that can be referenced are function parameters.
As such, function parameters will be in this map when generating code for their
function body.</p>
<p>
With these basics in place, we can start talking about how to generate code for
each expression. Note that this assumes that the <tt>Builder</tt> has been set
up to generate code <em>into</em> something. For now, we'll assume that this
has already been done, and we'll just use it to emit code.
</p>
</div>
<!-- *********************************************************************** -->
<div class="doc_section"><a name="exprs">Expression Code Generation</a></div>
<!-- *********************************************************************** -->
<div class="doc_text">
<p>Generating LLVM code for expression nodes is very straight-forward: less
than 45 lines of commented code for all four of our expression nodes. First,
we'll do numeric literals:</p>
<div class="doc_code">
<pre>
Value *NumberExprAST::Codegen() {
return ConstantFP::get(Type::DoubleTy, APFloat(Val));
}
</pre>
</div>
<p>In the LLVM IR, numeric constants are represented with the
<tt>ConstantFP</tt> class, which holds the numeric value in an <tt>APFloat</tt>
internally (<tt>APFloat</tt> has the capability of holding floating point
constants of <em>A</em>rbitrary <em>P</em>recision). This code basically just
creates and returns a <tt>ConstantFP</tt>. Note that in the LLVM IR
that constants are all uniqued together and shared. For this reason, the API
uses "the foo::get(..)" idiom instead of "new foo(..)" or "foo::create(..).</p>
<div class="doc_code">
<pre>
Value *VariableExprAST::Codegen() {
// Look this variable up in the function.
Value *V = NamedValues[Name];
return V ? V : ErrorV("Unknown variable name");
}
</pre>
</div>
<p>References to variables is also quite simple here. In the simple version
of Kaleidoscope, we assume that the variable has already been emited somewhere
and its value is available. In practice, the only values that can be in the
<tt>NamedValues</tt> map are function arguments. This
code simply checks to see that the specified name is in the map (if not, an
unknown variable is being referenced) and returns the value for it.</p>
<div class="doc_code">
<pre>
Value *BinaryExprAST::Codegen() {
Value *L = LHS->Codegen();
Value *R = RHS->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 '<':
L = Builder.CreateFCmpULT(L, R, "multmp");
// Convert bool 0/1 to double 0.0 or 1.0
return Builder.CreateUIToFP(L, Type::DoubleTy, "booltmp");
default: return ErrorV("invalid binary operator");
}
}
</pre>
</div>
<p>Binary operators start to get more interesting. The basic idea here is that
we recursively emit code for the left-hand side of the expression, then the
right-hand side, then we compute the result of the binary expression. In this
code, we do a simple switch on the opcode to create the right LLVM instruction.
</p>
<p>In this example, the LLVM builder class is starting to show its value.
Because it knows where to insert the newly created instruction, you just have to
specificy what instruction to create (e.g. with <tt>CreateAdd</tt>), which
operands to use (<tt>L</tt> and <tt>R</tt> here) and optionally provide a name
for the generated instruction. One nice thing about LLVM is that the name is
just a hint: if there are multiple additions in a single function, the first
will be named "addtmp" and the second will be "autorenamed" by adding a suffix,
giving it a name like "addtmp42". Local value names for instructions are purely
optional, but it makes it much easier to read the IR dumps.</p>
<p><a href="../LangRef.html#instref">LLVM instructions</a> are constrained to
have very strict type properties: for example, the Left and Right operators of
an <a href="../LangRef.html#i_add">add instruction</a> have to have the same
type, and that the result of the add matches the operands. Because all values
in Kaleidoscope are doubles, this makes for very simple code for add, sub and
mul.</p>
<p>On the other hand, LLVM specifies that the <a
href="../LangRef.html#i_fcmp">fcmp instruction</a> always returns an 'i1' value
(a one bit integer). However, Kaleidoscope wants the value to be a 0.0 or 1.0
value. In order to get these semantics, we combine the fcmp instruction with
a <a href="../LangRef.html#i_uitofp">uitofp instruction</a>. This instruction
converts its input integer into a floating point value by treating the input
as an unsigned value. In contrast, if we used the <a
href="../LangRef.html#i_sitofp">sitofp instruction</a>, the Kaleidoscope '<'
operator would return 0.0 and -1.0, depending on the input value.</p>
<div class="doc_code">
<pre>
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.begin(), ArgsV.end(), "calltmp");
}
</pre>
</div>
<p>Code generation for function calls is quite straight-forward with LLVM. The
code above first looks the name of the function up in the LLVM Module's symbol
table. Recall that the LLVM Module is the container that holds all of the
functions we are JIT'ing. By giving each function the same name as what the
user specifies, we can use the LLVM symbol table to resolve function names for
us.</p>
<p>Once we have the function to call, we recursively codegen each argument that
is to be passed in, and create an LLVM <a href="../LangRef.html#i_call">call
instruction</a>. Note that LLVM uses the native C calling conventions by
default, allowing these calls to call into standard library functions like
"sin" and "cos" with no additional effort.</p>
<p>This wraps up our handling of the four basic expressions that we have so far
in Kaleidoscope. Feel free to go in and add some more. For example, by
browsing the <a href="../LangRef.html">LLVM language reference</a> you'll find
several other interesting instructions that are really easy to plug into our
basic framework.</p>
</div>
<!-- *********************************************************************** -->
<div class="doc_section"><a name="funcs">Function Code Generation</a></div>
<!-- *********************************************************************** -->
<div class="doc_text">
<p>Code generation for prototypes and functions has to handle a number of
details, which make their code less beautiful and elegant than expression code
generation, but they illustrate some important points. First, lets talk about
code generation for prototypes: this is used both for function bodies as well
as external function declarations. The code starts with:</p>
<div class="doc_code">
<pre>
Function *PrototypeAST::Codegen() {
// Make the function type: double(double,double) etc.
std::vector<const Type*> Doubles(Args.size(), Type::DoubleTy);
FunctionType *FT = FunctionType::get(Type::DoubleTy, Doubles, false);
Function *F = new Function(FT, Function::ExternalLinkage, Name, TheModule);
</pre>
</div>
<p>This code packs a lot of power into a few lines. The first step is to create
the <tt>FunctionType</tt> that should be used for a given Prototype. Since all
function arguments in Kaleidoscope are of type double, the first line creates
a vector of "N" LLVM Double types. It then uses the <tt>FunctionType::get</tt>
method to create a function type that takes "N" doubles as arguments, returns
one double as a result, and that is not vararg (the false parameter indicates
this). Note that Types in LLVM are uniqued just like Constants are, so you
don't "new" a type, you "get" it.</p>
<p>The final line above actually creates the function that the prototype will
correspond to. This indicates which type, linkage, and name to use, and which
module to insert into. "<a href="LangRef.html#linkage">external linkage</a>"
means that the function may be defined outside the current module and/or that it
is callable by functions outside the module. The Name passed in is the name the
user specified: since "<tt>TheModule</tt>" is specified, this name is registered
in "<tt>TheModule</tt>"s symbol table, which is used by the function call code
above.</p>
<div class="doc_code">
<pre>
// 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);
</pre>
</div>
<p>The Module symbol table works just like the Function symbol table when it
comes to name conflicts: if a new function is created with a name was previously
added to the symbol table, it will get implicitly renamed when added to the
Module. The code above exploits this fact to tell if there was a previous
definition of this function.</p>
<p>In Kaleidoscope, I choose to allow redefinitions of functions in two cases:
first, we want to allow 'extern'ing a function more than once, so long as the
prototypes for the externs match (since all arguments have the same type, we
just have to check that the number of arguments match). Second, we want to
allow 'extern'ing a function and then definining a body for it. This is useful
when defining mutually recursive functions.</p>
<p>In order to implement this, the code above first checks to see if there is
a collision on the name of the function. If so, it deletes the function we just
created (by calling <tt>eraseFromParent</tt>) and then calling
<tt>getFunction</tt> to get the existing function with the specified name. Note
that many APIs in LLVM have "erase" forms and "remove" forms. The "remove" form
unlinks the object from its parent (e.g. a Function from a Module) and returns
it. The "erase" form unlinks the object and then deletes it.</p>
<div class="doc_code">
<pre>
// 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;
}
}
</pre>
</div>
<p>In order to verify the logic above, we first check to see if the preexisting
function is "empty". In this case, empty means that it has no basic blocks in
it, which means it has no body. If it has no body, this means its a forward
declaration. Since we don't allow anything after a full definition of the
function, the code rejects this case. If the previous reference to a function
was an 'extern', we simply verify that the number of arguments for that
definition and this one match up. If not, we emit an error.</p>
<div class="doc_code">
<pre>
// 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;
}
</pre>
</div>
<p>The last bit of code for prototypes loops over all of the arguments in the
function, setting the name of the LLVM Argument objects to match and registering
the arguments in the <tt>NamedValues</tt> map for future use by the
<tt>VariableExprAST</tt> AST node. Once this is set up, it returns the Function
object to the caller. Note that we don't check for conflicting
argument names here (e.g. "extern foo(a b a)"). Doing so would be very
straight-forward.</p>
<div class="doc_code">
<pre>
Function *FunctionAST::Codegen() {
NamedValues.clear();
Function *TheFunction = Proto->Codegen();
if (TheFunction == 0)
return 0;
</pre>
</div>
<p>Code generation for function definitions starts out simply enough: first we
codegen the prototype and verify that it is ok. We also clear out the
<tt>NamedValues</tt> map to make sure that there isn't anything in it from the
last function we compiled.</p>
<div class="doc_code">
<pre>
// Create a new basic block to start insertion into.
BasicBlock *BB = new BasicBlock("entry", TheFunction);
Builder.SetInsertPoint(BB);
if (Value *RetVal = Body->Codegen()) {
</pre>
</div>
<p>Now we get to the point where the <tt>Builder</tt> is set up. The first
line creates a new <a href="http://en.wikipedia.org/wiki/Basic_block">basic
block</a> (named "entry"), which is inserted into <tt>TheFunction</tt>. The
second line then tells the builder that new instructions should be inserted into
the end of the new basic block. Basic blocks in LLVM are an important part
of functions that define the <a
href="http://en.wikipedia.org/wiki/Control_flow_graph">Control Flow Graph</a>.
Since we don't have any control flow, our functions will only contain one
block so far. We'll fix this in a future installment :).</p>
<div class="doc_code">
<pre>
if (Value *RetVal = Body->Codegen()) {
// Finish off the function.
Builder.CreateRet(RetVal);
// Validate the generated code, checking for consistency.
verifyFunction(*TheFunction);
return TheFunction;
}
</pre>
</div>
<p>Once the insertion point is set up, we call the <tt>CodeGen()</tt> method for
the root expression of the function. If no error happens, this emits code to
compute the expression into the entry block and returns the value that was
computed. Assuming no error, we then create an LLVM <a
href="../LangRef.html#i_ret">ret instruction</a>, which completes the function.
Once the function is built, we call the <tt>verifyFunction</tt> function, which
is provided by LLVM. This function does a variety of consistency checks on the
generated code, to determine if our compiler is doing everything right. Using
this is important: it can catch a lot of bugs. Once the function is finished
and validated, we return it.</p>
<div class="doc_code">
<pre>
// Error reading body, remove function.
TheFunction->eraseFromParent();
return 0;
}
</pre>
</div>
<p>The only piece left here is handling of the error case. For simplicity, we
simply handle this by deleting the function we produced with the
<tt>eraseFromParent</tt> method. This allows the user to redefine a function
that they incorrectly typed in before: if we didn't delete it, it would live in
the symbol table, with a body, preventing future redefinition.</p>
<p>This code does have a bug though. Since the <tt>PrototypeAST::Codegen</tt>
can return a previously defined forward declaration, this can actually delete
a forward declaration. There are a number of ways to fix this bug, see what you
can come up with! Here is a testcase:</p>
<div class="doc_code">
<pre>
extern foo(a b); # ok, defines foo.
def foo(a b) c; # error, 'c' is invalid.
def bar() foo(1, 2); # error, unknown function "foo"
</pre>
</div>
</div>
<!-- *********************************************************************** -->
<div class="doc_section"><a name="driver">Driver Changes and
Closing Thoughts</a></div>
<!-- *********************************************************************** -->
<div class="doc_text">
<p>
For now, code generation to LLVM doesn't really get us much, except that we can
look at the pretty IR calls. The sample code inserts calls to Codegen into the
"<tt>HandleDefinition</tt>", "<tt>HandleExtern</tt>" etc functions, and then
dumps out the LLVM IR. This gives a nice way to look at the LLVM IR for simple
functions. For example:
</p>
<div class="doc_code">
<pre>
ready> <b>4+5</b>;
ready> Read top-level expression:
define double @""() {
entry:
%addtmp = add double 4.000000e+00, 5.000000e+00
ret double %addtmp
}
</pre>
</div>
<p>Note how the parser turns the top-level expression into anonymous functions
for us. This will be handy when we add JIT support in the next chapter. Also
note that the code is very literally transcribed, no optimizations are being
performed. We will add optimizations explicitly in the next chapter.</p>
<div class="doc_code">
<pre>
ready> <b>def foo(a b) a*a + 2*a*b + b*b;</b>
ready> Read function definition:
define double @foo(double %a, double %b) {
entry:
%multmp = mul double %a, %a
%multmp1 = mul double 2.000000e+00, %a
%multmp2 = mul double %multmp1, %b
%addtmp = add double %multmp, %multmp2
%multmp3 = mul double %b, %b
%addtmp4 = add double %addtmp, %multmp3
ret double %addtmp4
}
</pre>
</div>
<p>This shows some simple arithmetic. Notice the striking similarity to the
LLVM builder calls that we use to create the instructions.</p>
<div class="doc_code">
<pre>
ready> <b>def bar(a) foo(a, 4.0) + bar(31337);</b>
ready> Read function definition:
define double @bar(double %a) {
entry:
%calltmp = call double @foo( double %a, double 4.000000e+00 )
%calltmp1 = call double @bar( double 3.133700e+04 )
%addtmp = add double %calltmp, %calltmp1
ret double %addtmp
}
</pre>
</div>
<p>This shows some function calls. Note that the runtime of this function might
be fairly high. In the future we'll add conditional control flow to make
recursion actually be useful :).</p>
<div class="doc_code">
<pre>
ready> <b>extern cos(x);</b>
ready> Read extern:
declare double @cos(double)
ready> <b>cos(1.234);</b>
ready> Read top-level expression:
define double @""() {
entry:
%calltmp = call double @cos( double 1.234000e+00 )
ret double %calltmp
}
</pre>
</div>
<p>This shows an extern for the libm "cos" function, and a call to it.</p>
<div class="doc_code">
<pre>
ready> <b>^D</b>
; ModuleID = 'my cool jit'
define double @""() {
entry:
%addtmp = add double 4.000000e+00, 5.000000e+00
ret double %addtmp
}
define double @foo(double %a, double %b) {
entry:
%multmp = mul double %a, %a
%multmp1 = mul double 2.000000e+00, %a
%multmp2 = mul double %multmp1, %b
%addtmp = add double %multmp, %multmp2
%multmp3 = mul double %b, %b
%addtmp4 = add double %addtmp, %multmp3
ret double %addtmp4
}
define double @bar(double %a) {
entry:
%calltmp = call double @foo( double %a, double 4.000000e+00 )
%calltmp1 = call double @bar( double 3.133700e+04 )
%addtmp = add double %calltmp, %calltmp1
ret double %addtmp
}
declare double @cos(double)
define double @""() {
entry:
%calltmp = call double @cos( double 1.234000e+00 )
ret double %calltmp
}
</pre>
</div>
<p>When you quit the current demo, it dumps out the IR for the entire module
generated. Here you can see the big picture with all the functions referencing
each other.</p>
<p>This wraps up this chapter of the Kaleidoscope tutorial. Up next we'll
describe how to <a href="LangImpl4.html">add JIT codegen and optimizer
support</a> to this so we can actually start running code!</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 the
LLVM code generator. Because this uses the LLVM libraries, we need to link
them in. To do this, we use the <a
href="http://llvm.org/cmds/llvm-config.html">llvm-config</a> tool to inform
our makefile/command line about which options to use:</p>
<div class="doc_code">
<pre>
# Compile
g++ -g toy.cpp `llvm-config --cppflags --ldflags --libs core` -o toy
# Run
./toy
</pre>
</div>
<p>Here is the code:</p>
<div class="doc_code">
<pre>
// To build this:
// See example below.
#include "llvm/DerivedTypes.h"
#include "llvm/Module.h"
#include "llvm/Analysis/Verifier.h"
#include "llvm/Support/LLVMBuilder.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,
};
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;
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:
explicit 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:
explicit 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();
};
/// PrototypeAST - This class represents the "prototype" for a function,
/// which captures its argument names as well as if it is an operator.
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 it 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
/// ::= identifer
/// ::= identifer '(' expression* ')'
static ExprAST *ParseIdentifierExpr() {
std::string IdName = IdentifierStr;
getNextToken(); // eat identifer.
if (CurTok != '(') // Simple variable ref.
return new VariableExprAST(IdName);
// Call.
getNextToken(); // eat (
std::vector<ExprAST*> Args;
while (1) {
ExprAST *Arg = ParseExpression();
if (!Arg) return 0;
Args.push_back(Arg);
if (CurTok == ')') break;
if (CurTok != ',')
return Error("Expected ')'");
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;
}
/// primary
/// ::= identifierexpr
/// ::= numberexpr
/// ::= parenexpr
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();
}
}
/// 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 LLVMBuilder Builder;
static std::map<std::string, Value*> NamedValues;
Value *ErrorV(const char *Str) { Error(Str); return 0; }
Value *NumberExprAST::Codegen() {
return ConstantFP::get(Type::DoubleTy, 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.CreateAdd(L, R, "addtmp");
case '-': return Builder.CreateSub(L, R, "subtmp");
case '*': return Builder.CreateMul(L, R, "multmp");
case '<':
L = Builder.CreateFCmpULT(L, R, "multmp");
// Convert bool 0/1 to double 0.0 or 1.0
return Builder.CreateUIToFP(L, Type::DoubleTy, "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.begin(), ArgsV.end(), "calltmp");
}
Function *PrototypeAST::Codegen() {
// Make the function type: double(double,double) etc.
std::vector<const Type*> Doubles(Args.size(), Type::DoubleTy);
FunctionType *FT = FunctionType::get(Type::DoubleTy, Doubles, false);
Function *F = new Function(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 = new BasicBlock("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);
return TheFunction;
}
// Error reading body, remove function.
TheFunction->eraseFromParent();
return 0;
}
//===----------------------------------------------------------------------===//
// Top-Level parsing and JIT Driver
//===----------------------------------------------------------------------===//
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()) {
fprintf(stderr, "Read top-level expression:");
LF->dump();
}
} 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() {
TheModule = new Module("my cool jit");
// 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();
MainLoop();
TheModule->dump();
return 0;
}
</pre>
</div>
</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: 2007-10-17 11:05:13 -0700 (Wed, 17 Oct 2007) $
</address>
</body>
</html>
|
