llvm.org GIT mirror llvm / release_31 docs / tutorial / OCamlLangImpl4.html
release_31

Tree @release_31 (Download .tar.gz)

OCamlLangImpl4.html @release_31raw · history · blame

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
                      "http://www.w3.org/TR/html4/strict.dtd">

<html>
<head>
  <title>Kaleidoscope: Adding JIT and Optimizer Support</title>
  <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
  <meta name="author" content="Chris Lattner">
  <meta name="author" content="Erick Tryzelaar">
  <link rel="stylesheet" href="../llvm.css" type="text/css">
</head>

<body>

<h1>Kaleidoscope: Adding JIT and Optimizer Support</h1>

<ul>
<li><a href="index.html">Up to Tutorial Index</a></li>
<li>Chapter 4
  <ol>
    <li><a href="#intro">Chapter 4 Introduction</a></li>
    <li><a href="#trivialconstfold">Trivial Constant Folding</a></li>
    <li><a href="#optimizerpasses">LLVM Optimization Passes</a></li>
    <li><a href="#jit">Adding a JIT Compiler</a></li>
    <li><a href="#code">Full Code Listing</a></li>
  </ol>
</li>
<li><a href="OCamlLangImpl5.html">Chapter 5</a>: Extending the Language: Control
Flow</li>
</ul>

<div class="doc_author">
	<p>
		Written by <a href="mailto:sabre@nondot.org">Chris Lattner</a>
		and <a href="mailto:idadesub@users.sourceforge.net">Erick Tryzelaar</a>
	</p>
</div>

<!-- *********************************************************************** -->
<h2><a name="intro">Chapter 4 Introduction</a></h2>
<!-- *********************************************************************** -->

<div>

<p>Welcome to Chapter 4 of the "<a href="index.html">Implementing a language
with LLVM</a>" tutorial.  Chapters 1-3 described the implementation of a simple
language and added support for generating LLVM IR.  This chapter describes
two new techniques: adding optimizer support to your language, and adding JIT
compiler support.  These additions will demonstrate how to get nice, efficient code
for the Kaleidoscope language.</p>

</div>

<!-- *********************************************************************** -->
<h2><a name="trivialconstfold">Trivial Constant Folding</a></h2>
<!-- *********************************************************************** -->

<div>

<p><b>Note:</b> the default <tt>IRBuilder</tt> now always includes the constant 
folding optimisations below.<p>

<p>
Our demonstration for Chapter 3 is elegant and easy to extend.  Unfortunately,
it does not produce wonderful code.  For example, when compiling simple code,
we don't get obvious optimizations:</p>

<div class="doc_code">
<pre>
ready&gt; <b>def test(x) 1+2+x;</b>
Read function definition:
define double @test(double %x) {
entry:
        %addtmp = fadd double 1.000000e+00, 2.000000e+00
        %addtmp1 = fadd double %addtmp, %x
        ret double %addtmp1
}
</pre>
</div>

<p>This code is a very, very literal transcription of the AST built by parsing
the input. As such, this transcription lacks optimizations like constant folding
(we'd like to get "<tt>add x, 3.0</tt>" in the example above) as well as other
more important optimizations.  Constant folding, in particular, is a very common
and very important optimization: so much so that many language implementors
implement constant folding support in their AST representation.</p>

<p>With LLVM, you don't need this support in the AST.  Since all calls to build
LLVM IR go through the LLVM builder, it would be nice if the builder itself
checked to see if there was a constant folding opportunity when you call it.
If so, it could just do the constant fold and return the constant instead of
creating an instruction.  This is exactly what the <tt>LLVMFoldingBuilder</tt>
class does.

<p>All we did was switch from <tt>LLVMBuilder</tt> to
<tt>LLVMFoldingBuilder</tt>.  Though we change no other code, we now have all of our
instructions implicitly constant folded without us having to do anything
about it.  For example, the input above now compiles to:</p>

<div class="doc_code">
<pre>
ready&gt; <b>def test(x) 1+2+x;</b>
Read function definition:
define double @test(double %x) {
entry:
        %addtmp = fadd double 3.000000e+00, %x
        ret double %addtmp
}
</pre>
</div>

<p>Well, that was easy :).  In practice, we recommend always using
<tt>LLVMFoldingBuilder</tt> when generating code like this.  It has no
"syntactic overhead" for its use (you don't have to uglify your compiler with
constant checks everywhere) and it can dramatically reduce the amount of
LLVM IR that is generated in some cases (particular for languages with a macro
preprocessor or that use a lot of constants).</p>

<p>On the other hand, the <tt>LLVMFoldingBuilder</tt> is limited by the fact
that it does all of its analysis inline with the code as it is built.  If you
take a slightly more complex example:</p>

<div class="doc_code">
<pre>
ready&gt; <b>def test(x) (1+2+x)*(x+(1+2));</b>
ready&gt; Read function definition:
define double @test(double %x) {
entry:
        %addtmp = fadd double 3.000000e+00, %x
        %addtmp1 = fadd double %x, 3.000000e+00
        %multmp = fmul double %addtmp, %addtmp1
        ret double %multmp
}
</pre>
</div>

<p>In this case, the LHS and RHS of the multiplication are the same value.  We'd
really like to see this generate "<tt>tmp = x+3; result = tmp*tmp;</tt>" instead
of computing "<tt>x*3</tt>" twice.</p>

<p>Unfortunately, no amount of local analysis will be able to detect and correct
this.  This requires two transformations: reassociation of expressions (to
make the add's lexically identical) and Common Subexpression Elimination (CSE)
to  delete the redundant add instruction.  Fortunately, LLVM provides a broad
range of optimizations that you can use, in the form of "passes".</p>

</div>

<!-- *********************************************************************** -->
<h2><a name="optimizerpasses">LLVM Optimization Passes</a></h2>
<!-- *********************************************************************** -->

<div>

<p>LLVM provides many optimization passes, which do many different sorts of
things and have different tradeoffs.  Unlike other systems, LLVM doesn't hold
to the mistaken notion that one set of optimizations is right for all languages
and for all situations.  LLVM allows a compiler implementor to make complete
decisions about what optimizations to use, in which order, and in what
situation.</p>

<p>As a concrete example, LLVM supports both "whole module" passes, which look
across as large of body of code as they can (often a whole file, but if run
at link time, this can be a substantial portion of the whole program).  It also
supports and includes "per-function" passes which just operate on a single
function at a time, without looking at other functions.  For more information
on passes and how they are run, see the <a href="../WritingAnLLVMPass.html">How
to Write a Pass</a> document and the <a href="../Passes.html">List of LLVM
Passes</a>.</p>

<p>For Kaleidoscope, we are currently generating functions on the fly, one at
a time, as the user types them in.  We aren't shooting for the ultimate
optimization experience in this setting, but we also want to catch the easy and
quick stuff where possible.  As such, we will choose to run a few per-function
optimizations as the user types the function in.  If we wanted to make a "static
Kaleidoscope compiler", we would use exactly the code we have now, except that
we would defer running the optimizer until the entire file has been parsed.</p>

<p>In order to get per-function optimizations going, we need to set up a
<a href="../WritingAnLLVMPass.html#passmanager">Llvm.PassManager</a> to hold and
organize the LLVM optimizations that we want to run.  Once we have that, we can
add a set of optimizations to run.  The code looks like this:</p>

<div class="doc_code">
<pre>
  (* Create the JIT. *)
  let the_execution_engine = ExecutionEngine.create Codegen.the_module in
  let the_fpm = PassManager.create_function Codegen.the_module in

  (* Set up the optimizer pipeline.  Start with registering info about how the
   * target lays out data structures. *)
  TargetData.add (ExecutionEngine.target_data the_execution_engine) the_fpm;

  (* Do simple "peephole" optimizations and bit-twiddling optzn. *)
  add_instruction_combining the_fpm;

  (* reassociate expressions. *)
  add_reassociation the_fpm;

  (* Eliminate Common SubExpressions. *)
  add_gvn the_fpm;

  (* Simplify the control flow graph (deleting unreachable blocks, etc). *)
  add_cfg_simplification the_fpm;

  ignore (PassManager.initialize the_fpm);

  (* Run the main "interpreter loop" now. *)
  Toplevel.main_loop the_fpm the_execution_engine stream;
</pre>
</div>

<p>The meat of the matter here, is the definition of "<tt>the_fpm</tt>".  It
requires a pointer to the <tt>the_module</tt> to construct itself.  Once it is
set up, we use a series of "add" calls to add a bunch of LLVM passes.  The
first pass is basically boilerplate, it adds a pass so that later optimizations
know how the data structures in the program are laid out.  The
"<tt>the_execution_engine</tt>" variable is related to the JIT, which we will
get to in the next section.</p>

<p>In this case, we choose to add 4 optimization passes.  The passes we chose
here are a pretty standard set of "cleanup" optimizations that are useful for
a wide variety of code.  I won't delve into what they do but, believe me,
they are a good starting place :).</p>

<p>Once the <tt>Llvm.PassManager.</tt> is set up, we need to make use of it.
We do this by running it after our newly created function is constructed (in
<tt>Codegen.codegen_func</tt>), but before it is returned to the client:</p>

<div class="doc_code">
<pre>
let codegen_func the_fpm = function
      ...
      try
        let ret_val = codegen_expr body in

        (* Finish off the function. *)
        let _ = build_ret ret_val builder in

        (* Validate the generated code, checking for consistency. *)
        Llvm_analysis.assert_valid_function the_function;

        (* Optimize the function. *)
        let _ = PassManager.run_function the_function the_fpm in

        the_function
</pre>
</div>

<p>As you can see, this is pretty straightforward.  The <tt>the_fpm</tt>
optimizes and updates the LLVM Function* in place, improving (hopefully) its
body.  With this in place, we can try our test above again:</p>

<div class="doc_code">
<pre>
ready&gt; <b>def test(x) (1+2+x)*(x+(1+2));</b>
ready&gt; Read function definition:
define double @test(double %x) {
entry:
        %addtmp = fadd double %x, 3.000000e+00
        %multmp = fmul double %addtmp, %addtmp
        ret double %multmp
}
</pre>
</div>

<p>As expected, we now get our nicely optimized code, saving a floating point
add instruction from every execution of this function.</p>

<p>LLVM provides a wide variety of optimizations that can be used in certain
circumstances.  Some <a href="../Passes.html">documentation about the various
passes</a> is available, but it isn't very complete.  Another good source of
ideas can come from looking at the passes that <tt>llvm-gcc</tt> or
<tt>llvm-ld</tt> run to get started.  The "<tt>opt</tt>" tool allows you to
experiment with passes from the command line, so you can see if they do
anything.</p>

<p>Now that we have reasonable code coming out of our front-end, lets talk about
executing it!</p>

</div>

<!-- *********************************************************************** -->
<h2><a name="jit">Adding a JIT Compiler</a></h2>
<!-- *********************************************************************** -->

<div>

<p>Code that is available in LLVM IR can have a wide variety of tools
applied to it.  For example, you can run optimizations on it (as we did above),
you can dump it out in textual or binary forms, you can compile the code to an
assembly file (.s) for some target, or you can JIT compile it.  The nice thing
about the LLVM IR representation is that it is the "common currency" between
many different parts of the compiler.
</p>

<p>In this section, we'll add JIT compiler support to our interpreter.  The
basic idea that we want for Kaleidoscope is to have the user enter function
bodies as they do now, but immediately evaluate the top-level expressions they
type in.  For example, if they type in "1 + 2;", we should evaluate and print
out 3.  If they define a function, they should be able to call it from the
command line.</p>

<p>In order to do this, we first declare and initialize the JIT.  This is done
by adding a global variable and a call in <tt>main</tt>:</p>

<div class="doc_code">
<pre>
...
let main () =
  ...
  <b>(* Create the JIT. *)
  let the_execution_engine = ExecutionEngine.create Codegen.the_module in</b>
  ...
</pre>
</div>

<p>This creates an abstract "Execution Engine" which can be either a JIT
compiler or the LLVM interpreter.  LLVM will automatically pick a JIT compiler
for you if one is available for your platform, otherwise it will fall back to
the interpreter.</p>

<p>Once the <tt>Llvm_executionengine.ExecutionEngine.t</tt> is created, the JIT
is ready to be used.  There are a variety of APIs that are useful, but the
simplest one is the "<tt>Llvm_executionengine.ExecutionEngine.run_function</tt>"
function.  This method JIT compiles the specified LLVM Function and returns a
function pointer to the generated machine code.  In our case, this means that we
can change the code that parses a top-level expression to look like this:</p>

<div class="doc_code">
<pre>
            (* Evaluate a top-level expression into an anonymous function. *)
            let e = Parser.parse_toplevel stream in
            print_endline "parsed a top-level expr";
            let the_function = Codegen.codegen_func the_fpm e in
            dump_value the_function;

            (* JIT the function, returning a function pointer. *)
            let result = ExecutionEngine.run_function the_function [||]
              the_execution_engine in

            print_string "Evaluated to ";
            print_float (GenericValue.as_float Codegen.double_type result);
            print_newline ();
</pre>
</div>

<p>Recall that we compile top-level expressions into a self-contained LLVM
function that takes no arguments and returns the computed double.  Because the
LLVM JIT compiler matches the native platform ABI, this means that you can just
cast the result pointer to a function pointer of that type and call it directly.
This means, there is no difference between JIT compiled code and native machine
code that is statically linked into your application.</p>

<p>With just these two changes, lets see how Kaleidoscope works now!</p>

<div class="doc_code">
<pre>
ready&gt; <b>4+5;</b>
define double @""() {
entry:
        ret double 9.000000e+00
}

<em>Evaluated to 9.000000</em>
</pre>
</div>

<p>Well this looks like it is basically working.  The dump of the function
shows the "no argument function that always returns double" that we synthesize
for each top level expression that is typed in.  This demonstrates very basic
functionality, but can we do more?</p>

<div class="doc_code">
<pre>
ready&gt; <b>def testfunc(x y) x + y*2; </b>
Read function definition:
define double @testfunc(double %x, double %y) {
entry:
        %multmp = fmul double %y, 2.000000e+00
        %addtmp = fadd double %multmp, %x
        ret double %addtmp
}

ready&gt; <b>testfunc(4, 10);</b>
define double @""() {
entry:
        %calltmp = call double @testfunc(double 4.000000e+00, double 1.000000e+01)
        ret double %calltmp
}

<em>Evaluated to 24.000000</em>
</pre>
</div>

<p>This illustrates that we can now call user code, but there is something a bit
subtle going on here.  Note that we only invoke the JIT on the anonymous
functions that <em>call testfunc</em>, but we never invoked it
on <em>testfunc</em> itself.  What actually happened here is that the JIT
scanned for all non-JIT'd functions transitively called from the anonymous
function and compiled all of them before returning
from <tt>run_function</tt>.</p>

<p>The JIT provides a number of other more advanced interfaces for things like
freeing allocated machine code, rejit'ing functions to update them, etc.
However, even with this simple code, we get some surprisingly powerful
capabilities - check this out (I removed the dump of the anonymous functions,
you should get the idea by now :) :</p>

<div class="doc_code">
<pre>
ready&gt; <b>extern sin(x);</b>
Read extern:
declare double @sin(double)

ready&gt; <b>extern cos(x);</b>
Read extern:
declare double @cos(double)

ready&gt; <b>sin(1.0);</b>
<em>Evaluated to 0.841471</em>

ready&gt; <b>def foo(x) sin(x)*sin(x) + cos(x)*cos(x);</b>
Read function definition:
define double @foo(double %x) {
entry:
        %calltmp = call double @sin(double %x)
        %multmp = fmul double %calltmp, %calltmp
        %calltmp2 = call double @cos(double %x)
        %multmp4 = fmul double %calltmp2, %calltmp2
        %addtmp = fadd double %multmp, %multmp4
        ret double %addtmp
}

ready&gt; <b>foo(4.0);</b>
<em>Evaluated to 1.000000</em>
</pre>
</div>

<p>Whoa, how does the JIT know about sin and cos?  The answer is surprisingly
simple: in this example, the JIT started execution of a function and got to a
function call.  It realized that the function was not yet JIT compiled and
invoked the standard set of routines to resolve the function.  In this case,
there is no body defined for the function, so the JIT ended up calling
"<tt>dlsym("sin")</tt>" on the Kaleidoscope process itself.  Since
"<tt>sin</tt>" is defined within the JIT's address space, it simply patches up
calls in the module to call the libm version of <tt>sin</tt> directly.</p>

<p>The LLVM JIT provides a number of interfaces (look in the
<tt>llvm_executionengine.mli</tt> file) for controlling how unknown functions
get resolved.  It allows you to establish explicit mappings between IR objects
and addresses (useful for LLVM global variables that you want to map to static
tables, for example), allows you to dynamically decide on the fly based on the
function name, and even allows you to have the JIT compile functions lazily the
first time they're called.</p>

<p>One interesting application of this is that we can now extend the language
by writing arbitrary C code to implement operations.  For example, if we add:
</p>

<div class="doc_code">
<pre>
/* putchard - putchar that takes a double and returns 0. */
extern "C"
double putchard(double X) {
  putchar((char)X);
  return 0;
}
</pre>
</div>

<p>Now we can produce simple output to the console by using things like:
"<tt>extern putchard(x); putchard(120);</tt>", which prints a lowercase 'x' on
the console (120 is the ASCII code for 'x').  Similar code could be used to
implement file I/O, console input, and many other capabilities in
Kaleidoscope.</p>

<p>This completes the JIT and optimizer chapter of the Kaleidoscope tutorial. At
this point, we can compile a non-Turing-complete programming language, optimize
and JIT compile it in a user-driven way.  Next up we'll look into <a
href="OCamlLangImpl5.html">extending the language with control flow
constructs</a>, tackling some interesting LLVM IR issues along the way.</p>

</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
LLVM JIT and optimizer.  To build this example, use:
</p>

<div class="doc_code">
<pre>
# Compile
ocamlbuild toy.byte
# Run
./toy.byte
</pre>
</div>

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

<dl>
<dt>_tags:</dt>
<dd class="doc_code">
<pre>
&lt;{lexer,parser}.ml&gt;: use_camlp4, pp(camlp4of)
&lt;*.{byte,native}&gt;: g++, use_llvm, use_llvm_analysis
&lt;*.{byte,native}&gt;: use_llvm_executionengine, use_llvm_target
&lt;*.{byte,native}&gt;: use_llvm_scalar_opts, use_bindings
</pre>
</dd>

<dt>myocamlbuild.ml:</dt>
<dd class="doc_code">
<pre>
open Ocamlbuild_plugin;;

ocaml_lib ~extern:true "llvm";;
ocaml_lib ~extern:true "llvm_analysis";;
ocaml_lib ~extern:true "llvm_executionengine";;
ocaml_lib ~extern:true "llvm_target";;
ocaml_lib ~extern:true "llvm_scalar_opts";;

flag ["link"; "ocaml"; "g++"] (S[A"-cc"; A"g++"]);;
dep ["link"; "ocaml"; "use_bindings"] ["bindings.o"];;
</pre>
</dd>

<dt>token.ml:</dt>
<dd class="doc_code">
<pre>
(*===----------------------------------------------------------------------===
 * Lexer Tokens
 *===----------------------------------------------------------------------===*)

(* The lexer returns these 'Kwd' if it is an unknown character, otherwise one of
 * these others for known things. *)
type token =
  (* commands *)
  | Def | Extern

  (* primary *)
  | Ident of string | Number of float

  (* unknown *)
  | Kwd of char
</pre>
</dd>

<dt>lexer.ml:</dt>
<dd class="doc_code">
<pre>
(*===----------------------------------------------------------------------===
 * Lexer
 *===----------------------------------------------------------------------===*)

let rec lex = parser
  (* Skip any whitespace. *)
  | [&lt; ' (' ' | '\n' | '\r' | '\t'); stream &gt;] -&gt; lex stream

  (* identifier: [a-zA-Z][a-zA-Z0-9] *)
  | [&lt; ' ('A' .. 'Z' | 'a' .. 'z' as c); stream &gt;] -&gt;
      let buffer = Buffer.create 1 in
      Buffer.add_char buffer c;
      lex_ident buffer stream

  (* number: [0-9.]+ *)
  | [&lt; ' ('0' .. '9' as c); stream &gt;] -&gt;
      let buffer = Buffer.create 1 in
      Buffer.add_char buffer c;
      lex_number buffer stream

  (* Comment until end of line. *)
  | [&lt; ' ('#'); stream &gt;] -&gt;
      lex_comment stream

  (* Otherwise, just return the character as its ascii value. *)
  | [&lt; 'c; stream &gt;] -&gt;
      [&lt; 'Token.Kwd c; lex stream &gt;]

  (* end of stream. *)
  | [&lt; &gt;] -&gt; [&lt; &gt;]

and lex_number buffer = parser
  | [&lt; ' ('0' .. '9' | '.' as c); stream &gt;] -&gt;
      Buffer.add_char buffer c;
      lex_number buffer stream
  | [&lt; stream=lex &gt;] -&gt;
      [&lt; 'Token.Number (float_of_string (Buffer.contents buffer)); stream &gt;]

and lex_ident buffer = parser
  | [&lt; ' ('A' .. 'Z' | 'a' .. 'z' | '0' .. '9' as c); stream &gt;] -&gt;
      Buffer.add_char buffer c;
      lex_ident buffer stream
  | [&lt; stream=lex &gt;] -&gt;
      match Buffer.contents buffer with
      | "def" -&gt; [&lt; 'Token.Def; stream &gt;]
      | "extern" -&gt; [&lt; 'Token.Extern; stream &gt;]
      | id -&gt; [&lt; 'Token.Ident id; stream &gt;]

and lex_comment = parser
  | [&lt; ' ('\n'); stream=lex &gt;] -&gt; stream
  | [&lt; 'c; e=lex_comment &gt;] -&gt; e
  | [&lt; &gt;] -&gt; [&lt; &gt;]
</pre>
</dd>

<dt>ast.ml:</dt>
<dd class="doc_code">
<pre>
(*===----------------------------------------------------------------------===
 * Abstract Syntax Tree (aka Parse Tree)
 *===----------------------------------------------------------------------===*)

(* expr - Base type for all expression nodes. *)
type expr =
  (* variant for numeric literals like "1.0". *)
  | Number of float

  (* variant for referencing a variable, like "a". *)
  | Variable of string

  (* variant for a binary operator. *)
  | Binary of char * expr * expr

  (* variant for function calls. *)
  | Call of string * expr array

(* proto - This type represents the "prototype" for a function, which captures
 * its name, and its argument names (thus implicitly the number of arguments the
 * function takes). *)
type proto = Prototype of string * string array

(* func - This type represents a function definition itself. *)
type func = Function of proto * expr
</pre>
</dd>

<dt>parser.ml:</dt>
<dd class="doc_code">
<pre>
(*===---------------------------------------------------------------------===
 * Parser
 *===---------------------------------------------------------------------===*)

(* binop_precedence - This holds the precedence for each binary operator that is
 * defined *)
let binop_precedence:(char, int) Hashtbl.t = Hashtbl.create 10

(* precedence - Get the precedence of the pending binary operator token. *)
let precedence c = try Hashtbl.find binop_precedence c with Not_found -&gt; -1

(* primary
 *   ::= identifier
 *   ::= numberexpr
 *   ::= parenexpr *)
let rec parse_primary = parser
  (* numberexpr ::= number *)
  | [&lt; 'Token.Number n &gt;] -&gt; Ast.Number n

  (* parenexpr ::= '(' expression ')' *)
  | [&lt; 'Token.Kwd '('; e=parse_expr; 'Token.Kwd ')' ?? "expected ')'" &gt;] -&gt; e

  (* identifierexpr
   *   ::= identifier
   *   ::= identifier '(' argumentexpr ')' *)
  | [&lt; 'Token.Ident id; stream &gt;] -&gt;
      let rec parse_args accumulator = parser
        | [&lt; e=parse_expr; stream &gt;] -&gt;
            begin parser
              | [&lt; 'Token.Kwd ','; e=parse_args (e :: accumulator) &gt;] -&gt; e
              | [&lt; &gt;] -&gt; e :: accumulator
            end stream
        | [&lt; &gt;] -&gt; accumulator
      in
      let rec parse_ident id = parser
        (* Call. *)
        | [&lt; 'Token.Kwd '(';
             args=parse_args [];
             'Token.Kwd ')' ?? "expected ')'"&gt;] -&gt;
            Ast.Call (id, Array.of_list (List.rev args))

        (* Simple variable ref. *)
        | [&lt; &gt;] -&gt; Ast.Variable id
      in
      parse_ident id stream

  | [&lt; &gt;] -&gt; raise (Stream.Error "unknown token when expecting an expression.")

(* binoprhs
 *   ::= ('+' primary)* *)
and parse_bin_rhs expr_prec lhs stream =
  match Stream.peek stream with
  (* If this is a binop, find its precedence. *)
  | Some (Token.Kwd c) when Hashtbl.mem binop_precedence c -&gt;
      let token_prec = precedence c in

      (* If this is a binop that binds at least as tightly as the current binop,
       * consume it, otherwise we are done. *)
      if token_prec &lt; expr_prec then lhs else begin
        (* Eat the binop. *)
        Stream.junk stream;

        (* Parse the primary expression after the binary operator. *)
        let rhs = parse_primary stream in

        (* Okay, we know this is a binop. *)
        let rhs =
          match Stream.peek stream with
          | Some (Token.Kwd c2) -&gt;
              (* If BinOp binds less tightly with rhs than the operator after
               * rhs, let the pending operator take rhs as its lhs. *)
              let next_prec = precedence c2 in
              if token_prec &lt; next_prec
              then parse_bin_rhs (token_prec + 1) rhs stream
              else rhs
          | _ -&gt; rhs
        in

        (* Merge lhs/rhs. *)
        let lhs = Ast.Binary (c, lhs, rhs) in
        parse_bin_rhs expr_prec lhs stream
      end
  | _ -&gt; lhs

(* expression
 *   ::= primary binoprhs *)
and parse_expr = parser
  | [&lt; lhs=parse_primary; stream &gt;] -&gt; parse_bin_rhs 0 lhs stream

(* prototype
 *   ::= id '(' id* ')' *)
let parse_prototype =
  let rec parse_args accumulator = parser
    | [&lt; 'Token.Ident id; e=parse_args (id::accumulator) &gt;] -&gt; e
    | [&lt; &gt;] -&gt; accumulator
  in

  parser
  | [&lt; 'Token.Ident id;
       'Token.Kwd '(' ?? "expected '(' in prototype";
       args=parse_args [];
       'Token.Kwd ')' ?? "expected ')' in prototype" &gt;] -&gt;
      (* success. *)
      Ast.Prototype (id, Array.of_list (List.rev args))

  | [&lt; &gt;] -&gt;
      raise (Stream.Error "expected function name in prototype")

(* definition ::= 'def' prototype expression *)
let parse_definition = parser
  | [&lt; 'Token.Def; p=parse_prototype; e=parse_expr &gt;] -&gt;
      Ast.Function (p, e)

(* toplevelexpr ::= expression *)
let parse_toplevel = parser
  | [&lt; e=parse_expr &gt;] -&gt;
      (* Make an anonymous proto. *)
      Ast.Function (Ast.Prototype ("", [||]), e)

(*  external ::= 'extern' prototype *)
let parse_extern = parser
  | [&lt; 'Token.Extern; e=parse_prototype &gt;] -&gt; e
</pre>
</dd>

<dt>codegen.ml:</dt>
<dd class="doc_code">
<pre>
(*===----------------------------------------------------------------------===
 * Code Generation
 *===----------------------------------------------------------------------===*)

open Llvm

exception Error of string

let context = global_context ()
let the_module = create_module context "my cool jit"
let builder = builder context
let named_values:(string, llvalue) Hashtbl.t = Hashtbl.create 10
let double_type = double_type context

let rec codegen_expr = function
  | Ast.Number n -&gt; const_float double_type n
  | Ast.Variable name -&gt;
      (try Hashtbl.find named_values name with
        | Not_found -&gt; raise (Error "unknown variable name"))
  | Ast.Binary (op, lhs, rhs) -&gt;
      let lhs_val = codegen_expr lhs in
      let rhs_val = codegen_expr rhs in
      begin
        match op with
        | '+' -&gt; build_add lhs_val rhs_val "addtmp" builder
        | '-' -&gt; build_sub lhs_val rhs_val "subtmp" builder
        | '*' -&gt; build_mul lhs_val rhs_val "multmp" builder
        | '&lt;' -&gt;
            (* Convert bool 0/1 to double 0.0 or 1.0 *)
            let i = build_fcmp Fcmp.Ult lhs_val rhs_val "cmptmp" builder in
            build_uitofp i double_type "booltmp" builder
        | _ -&gt; raise (Error "invalid binary operator")
      end
  | Ast.Call (callee, args) -&gt;
      (* Look up the name in the module table. *)
      let callee =
        match lookup_function callee the_module with
        | Some callee -&gt; callee
        | None -&gt; raise (Error "unknown function referenced")
      in
      let params = params callee in

      (* If argument mismatch error. *)
      if Array.length params == Array.length args then () else
        raise (Error "incorrect # arguments passed");
      let args = Array.map codegen_expr args in
      build_call callee args "calltmp" builder

let codegen_proto = function
  | Ast.Prototype (name, args) -&gt;
      (* Make the function type: double(double,double) etc. *)
      let doubles = Array.make (Array.length args) double_type in
      let ft = function_type double_type doubles in
      let f =
        match lookup_function name the_module with
        | None -&gt; declare_function name ft the_module

        (* If 'f' conflicted, there was already something named 'name'. If it
         * has a body, don't allow redefinition or reextern. *)
        | Some f -&gt;
            (* If 'f' already has a body, reject this. *)
            if block_begin f &lt;&gt; At_end f then
              raise (Error "redefinition of function");

            (* If 'f' took a different number of arguments, reject. *)
            if element_type (type_of f) &lt;&gt; ft then
              raise (Error "redefinition of function with different # args");
            f
      in

      (* Set names for all arguments. *)
      Array.iteri (fun i a -&gt;
        let n = args.(i) in
        set_value_name n a;
        Hashtbl.add named_values n a;
      ) (params f);
      f

let codegen_func the_fpm = function
  | Ast.Function (proto, body) -&gt;
      Hashtbl.clear named_values;
      let the_function = codegen_proto proto in

      (* Create a new basic block to start insertion into. *)
      let bb = append_block context "entry" the_function in
      position_at_end bb builder;

      try
        let ret_val = codegen_expr body in

        (* Finish off the function. *)
        let _ = build_ret ret_val builder in

        (* Validate the generated code, checking for consistency. *)
        Llvm_analysis.assert_valid_function the_function;

        (* Optimize the function. *)
        let _ = PassManager.run_function the_function the_fpm in

        the_function
      with e -&gt;
        delete_function the_function;
        raise e
</pre>
</dd>

<dt>toplevel.ml:</dt>
<dd class="doc_code">
<pre>
(*===----------------------------------------------------------------------===
 * Top-Level parsing and JIT Driver
 *===----------------------------------------------------------------------===*)

open Llvm
open Llvm_executionengine

(* top ::= definition | external | expression | ';' *)
let rec main_loop the_fpm the_execution_engine stream =
  match Stream.peek stream with
  | None -&gt; ()

  (* ignore top-level semicolons. *)
  | Some (Token.Kwd ';') -&gt;
      Stream.junk stream;
      main_loop the_fpm the_execution_engine stream

  | Some token -&gt;
      begin
        try match token with
        | Token.Def -&gt;
            let e = Parser.parse_definition stream in
            print_endline "parsed a function definition.";
            dump_value (Codegen.codegen_func the_fpm e);
        | Token.Extern -&gt;
            let e = Parser.parse_extern stream in
            print_endline "parsed an extern.";
            dump_value (Codegen.codegen_proto e);
        | _ -&gt;
            (* Evaluate a top-level expression into an anonymous function. *)
            let e = Parser.parse_toplevel stream in
            print_endline "parsed a top-level expr";
            let the_function = Codegen.codegen_func the_fpm e in
            dump_value the_function;

            (* JIT the function, returning a function pointer. *)
            let result = ExecutionEngine.run_function the_function [||]
              the_execution_engine in

            print_string "Evaluated to ";
            print_float (GenericValue.as_float Codegen.double_type result);
            print_newline ();
        with Stream.Error s | Codegen.Error s -&gt;
          (* Skip token for error recovery. *)
          Stream.junk stream;
          print_endline s;
      end;
      print_string "ready&gt; "; flush stdout;
      main_loop the_fpm the_execution_engine stream
</pre>
</dd>

<dt>toy.ml:</dt>
<dd class="doc_code">
<pre>
(*===----------------------------------------------------------------------===
 * Main driver code.
 *===----------------------------------------------------------------------===*)

open Llvm
open Llvm_executionengine
open Llvm_target
open Llvm_scalar_opts

let main () =
  ignore (initialize_native_target ());

  (* Install standard binary operators.
   * 1 is the lowest precedence. *)
  Hashtbl.add Parser.binop_precedence '&lt;' 10;
  Hashtbl.add Parser.binop_precedence '+' 20;
  Hashtbl.add Parser.binop_precedence '-' 20;
  Hashtbl.add Parser.binop_precedence '*' 40;    (* highest. *)

  (* Prime the first token. *)
  print_string "ready&gt; "; flush stdout;
  let stream = Lexer.lex (Stream.of_channel stdin) in

  (* Create the JIT. *)
  let the_execution_engine = ExecutionEngine.create Codegen.the_module in
  let the_fpm = PassManager.create_function Codegen.the_module in

  (* Set up the optimizer pipeline.  Start with registering info about how the
   * target lays out data structures. *)
  TargetData.add (ExecutionEngine.target_data the_execution_engine) the_fpm;

  (* Do simple "peephole" optimizations and bit-twiddling optzn. *)
  add_instruction_combination the_fpm;

  (* reassociate expressions. *)
  add_reassociation the_fpm;

  (* Eliminate Common SubExpressions. *)
  add_gvn the_fpm;

  (* Simplify the control flow graph (deleting unreachable blocks, etc). *)
  add_cfg_simplification the_fpm;

  ignore (PassManager.initialize the_fpm);

  (* Run the main "interpreter loop" now. *)
  Toplevel.main_loop the_fpm the_execution_engine stream;

  (* Print out all the generated code. *)
  dump_module Codegen.the_module
;;

main ()
</pre>
</dd>

<dt>bindings.c</dt>
<dd class="doc_code">
<pre>
#include &lt;stdio.h&gt;

/* putchard - putchar that takes a double and returns 0. */
extern double putchard(double X) {
  putchar((char)X);
  return 0;
}
</pre>
</dd>
</dl>

<a href="OCamlLangImpl5.html">Next: Extending the language: control flow</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="mailto:idadesub@users.sourceforge.net">Erick Tryzelaar</a><br>
  <a href="http://llvm.org/">The LLVM Compiler Infrastructure</a><br>
  Last modified: $Date$
</address>
</body>
</html>