Home | History | Annotate | Download | only in docs
      1 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
      2                       "http://www.w3.org/TR/html4/strict.dtd">
      3 <html>
      4 <head>
      5   <meta http-equiv="Content-type" content="text/html;charset=UTF-8">
      6   <title>LLVM Programmer's Manual</title>
      7   <link rel="stylesheet" href="llvm.css" type="text/css">
      8 </head>
      9 <body>
     10 
     11 <h1>
     12   LLVM Programmer's Manual
     13 </h1>
     14 
     15 <ol>
     16   <li><a href="#introduction">Introduction</a></li>
     17   <li><a href="#general">General Information</a>
     18     <ul>
     19       <li><a href="#stl">The C++ Standard Template Library</a></li>
     20 <!--
     21       <li>The <tt>-time-passes</tt> option</li>
     22       <li>How to use the LLVM Makefile system</li>
     23       <li>How to write a regression test</li>
     24 
     25 --> 
     26     </ul>
     27   </li>
     28   <li><a href="#apis">Important and useful LLVM APIs</a>
     29     <ul>
     30       <li><a href="#isa">The <tt>isa&lt;&gt;</tt>, <tt>cast&lt;&gt;</tt>
     31 and <tt>dyn_cast&lt;&gt;</tt> templates</a> </li>
     32       <li><a href="#string_apis">Passing strings (the <tt>StringRef</tt>
     33 and <tt>Twine</tt> classes)</a>
     34         <ul>
     35           <li><a href="#StringRef">The <tt>StringRef</tt> class</a> </li>
     36           <li><a href="#Twine">The <tt>Twine</tt> class</a> </li>
     37         </ul>
     38       </li>
     39       <li><a href="#DEBUG">The <tt>DEBUG()</tt> macro and <tt>-debug</tt>
     40 option</a>
     41         <ul>
     42           <li><a href="#DEBUG_TYPE">Fine grained debug info with <tt>DEBUG_TYPE</tt>
     43 and the <tt>-debug-only</tt> option</a> </li>
     44         </ul>
     45       </li>
     46       <li><a href="#Statistic">The <tt>Statistic</tt> class &amp; <tt>-stats</tt>
     47 option</a></li>
     48 <!--
     49       <li>The <tt>InstVisitor</tt> template
     50       <li>The general graph API
     51 --> 
     52       <li><a href="#ViewGraph">Viewing graphs while debugging code</a></li>
     53     </ul>
     54   </li>
     55   <li><a href="#datastructure">Picking the Right Data Structure for a Task</a>
     56     <ul>
     57     <li><a href="#ds_sequential">Sequential Containers (std::vector, std::list, etc)</a>
     58     <ul>
     59       <li><a href="#dss_arrayref">llvm/ADT/ArrayRef.h</a></li>
     60       <li><a href="#dss_fixedarrays">Fixed Size Arrays</a></li>
     61       <li><a href="#dss_heaparrays">Heap Allocated Arrays</a></li>
     62       <li><a href="#dss_tinyptrvector">"llvm/ADT/TinyPtrVector.h"</a></li>
     63       <li><a href="#dss_smallvector">"llvm/ADT/SmallVector.h"</a></li>
     64       <li><a href="#dss_vector">&lt;vector&gt;</a></li>
     65       <li><a href="#dss_deque">&lt;deque&gt;</a></li>
     66       <li><a href="#dss_list">&lt;list&gt;</a></li>
     67       <li><a href="#dss_ilist">llvm/ADT/ilist.h</a></li>
     68       <li><a href="#dss_packedvector">llvm/ADT/PackedVector.h</a></li>
     69       <li><a href="#dss_other">Other Sequential Container Options</a></li>
     70     </ul></li>
     71     <li><a href="#ds_string">String-like containers</a>
     72     <ul>
     73       <li><a href="#dss_stringref">llvm/ADT/StringRef.h</a></li>
     74       <li><a href="#dss_twine">llvm/ADT/Twine.h</a></li>
     75       <li><a href="#dss_smallstring">llvm/ADT/SmallString.h</a></li>
     76       <li><a href="#dss_stdstring">std::string</a></li>
     77     </ul></li>
     78     <li><a href="#ds_set">Set-Like Containers (std::set, SmallSet, SetVector, etc)</a>
     79     <ul>
     80       <li><a href="#dss_sortedvectorset">A sorted 'vector'</a></li>
     81       <li><a href="#dss_smallset">"llvm/ADT/SmallSet.h"</a></li>
     82       <li><a href="#dss_smallptrset">"llvm/ADT/SmallPtrSet.h"</a></li>
     83       <li><a href="#dss_denseset">"llvm/ADT/DenseSet.h"</a></li>
     84       <li><a href="#dss_sparseset">"llvm/ADT/SparseSet.h"</a></li>
     85       <li><a href="#dss_FoldingSet">"llvm/ADT/FoldingSet.h"</a></li>
     86       <li><a href="#dss_set">&lt;set&gt;</a></li>
     87       <li><a href="#dss_setvector">"llvm/ADT/SetVector.h"</a></li>
     88       <li><a href="#dss_uniquevector">"llvm/ADT/UniqueVector.h"</a></li>
     89       <li><a href="#dss_immutableset">"llvm/ADT/ImmutableSet.h"</a></li>
     90       <li><a href="#dss_otherset">Other Set-Like Container Options</a></li>
     91     </ul></li>
     92     <li><a href="#ds_map">Map-Like Containers (std::map, DenseMap, etc)</a>
     93     <ul>
     94       <li><a href="#dss_sortedvectormap">A sorted 'vector'</a></li>
     95       <li><a href="#dss_stringmap">"llvm/ADT/StringMap.h"</a></li>
     96       <li><a href="#dss_indexedmap">"llvm/ADT/IndexedMap.h"</a></li>
     97       <li><a href="#dss_densemap">"llvm/ADT/DenseMap.h"</a></li>
     98       <li><a href="#dss_valuemap">"llvm/ADT/ValueMap.h"</a></li>
     99       <li><a href="#dss_intervalmap">"llvm/ADT/IntervalMap.h"</a></li>
    100       <li><a href="#dss_map">&lt;map&gt;</a></li>
    101       <li><a href="#dss_inteqclasses">"llvm/ADT/IntEqClasses.h"</a></li>
    102       <li><a href="#dss_immutablemap">"llvm/ADT/ImmutableMap.h"</a></li>
    103       <li><a href="#dss_othermap">Other Map-Like Container Options</a></li>
    104     </ul></li>
    105     <li><a href="#ds_bit">BitVector-like containers</a>
    106     <ul>
    107       <li><a href="#dss_bitvector">A dense bitvector</a></li>
    108       <li><a href="#dss_smallbitvector">A "small" dense bitvector</a></li>
    109       <li><a href="#dss_sparsebitvector">A sparse bitvector</a></li>
    110     </ul></li>
    111   </ul>
    112   </li>
    113   <li><a href="#common">Helpful Hints for Common Operations</a>
    114     <ul>
    115       <li><a href="#inspection">Basic Inspection and Traversal Routines</a>
    116         <ul>
    117           <li><a href="#iterate_function">Iterating over the <tt>BasicBlock</tt>s
    118 in a <tt>Function</tt></a> </li>
    119           <li><a href="#iterate_basicblock">Iterating over the <tt>Instruction</tt>s
    120 in a <tt>BasicBlock</tt></a> </li>
    121           <li><a href="#iterate_institer">Iterating over the <tt>Instruction</tt>s
    122 in a <tt>Function</tt></a> </li>
    123           <li><a href="#iterate_convert">Turning an iterator into a
    124 class pointer</a> </li>
    125           <li><a href="#iterate_complex">Finding call sites: a more
    126 complex example</a> </li>
    127           <li><a href="#calls_and_invokes">Treating calls and invokes
    128 the same way</a> </li>
    129           <li><a href="#iterate_chains">Iterating over def-use &amp;
    130 use-def chains</a> </li>
    131           <li><a href="#iterate_preds">Iterating over predecessors &amp;
    132 successors of blocks</a></li>
    133         </ul>
    134       </li>
    135       <li><a href="#simplechanges">Making simple changes</a>
    136         <ul>
    137           <li><a href="#schanges_creating">Creating and inserting new
    138 		 <tt>Instruction</tt>s</a> </li>
    139           <li><a href="#schanges_deleting">Deleting 		 <tt>Instruction</tt>s</a> </li>
    140           <li><a href="#schanges_replacing">Replacing an 		 <tt>Instruction</tt>
    141 with another <tt>Value</tt></a> </li>
    142           <li><a href="#schanges_deletingGV">Deleting <tt>GlobalVariable</tt>s</a> </li>  
    143         </ul>
    144       </li>
    145       <li><a href="#create_types">How to Create Types</a></li>
    146 <!--
    147     <li>Working with the Control Flow Graph
    148     <ul>
    149       <li>Accessing predecessors and successors of a <tt>BasicBlock</tt>
    150       <li>
    151       <li>
    152     </ul>
    153 --> 
    154     </ul>
    155   </li>
    156 
    157   <li><a href="#threading">Threads and LLVM</a>
    158   <ul>
    159     <li><a href="#startmultithreaded">Entering and Exiting Multithreaded Mode
    160         </a></li>
    161     <li><a href="#shutdown">Ending execution with <tt>llvm_shutdown()</tt></a></li>
    162     <li><a href="#managedstatic">Lazy initialization with <tt>ManagedStatic</tt></a></li>
    163     <li><a href="#llvmcontext">Achieving Isolation with <tt>LLVMContext</tt></a></li>
    164     <li><a href="#jitthreading">Threads and the JIT</a></li>
    165   </ul>
    166   </li>
    167 
    168   <li><a href="#advanced">Advanced Topics</a>
    169   <ul>
    170 
    171   <li><a href="#SymbolTable">The <tt>ValueSymbolTable</tt> class</a></li>
    172   <li><a href="#UserLayout">The <tt>User</tt> and owned <tt>Use</tt> classes' memory layout</a></li>
    173   </ul></li>
    174 
    175   <li><a href="#coreclasses">The Core LLVM Class Hierarchy Reference</a>
    176     <ul>
    177       <li><a href="#Type">The <tt>Type</tt> class</a> </li>
    178       <li><a href="#Module">The <tt>Module</tt> class</a></li>
    179       <li><a href="#Value">The <tt>Value</tt> class</a>
    180       <ul>
    181         <li><a href="#User">The <tt>User</tt> class</a>
    182         <ul>
    183           <li><a href="#Instruction">The <tt>Instruction</tt> class</a></li>
    184           <li><a href="#Constant">The <tt>Constant</tt> class</a>
    185           <ul>
    186             <li><a href="#GlobalValue">The <tt>GlobalValue</tt> class</a>
    187             <ul>
    188               <li><a href="#Function">The <tt>Function</tt> class</a></li>
    189               <li><a href="#GlobalVariable">The <tt>GlobalVariable</tt> class</a></li>
    190             </ul>
    191             </li>
    192           </ul>
    193           </li>
    194         </ul>
    195         </li>
    196         <li><a href="#BasicBlock">The <tt>BasicBlock</tt> class</a></li>
    197         <li><a href="#Argument">The <tt>Argument</tt> class</a></li>
    198       </ul>
    199       </li>
    200     </ul>
    201   </li>
    202 </ol>
    203 
    204 <div class="doc_author">    
    205   <p>Written by <a href="mailto:sabre (a] nondot.org">Chris Lattner</a>, 
    206                 <a href="mailto:dhurjati (a] cs.uiuc.edu">Dinakar Dhurjati</a>, 
    207                 <a href="mailto:ggreif (a] gmail.com">Gabor Greif</a>, 
    208                 <a href="mailto:jstanley (a] cs.uiuc.edu">Joel Stanley</a>,
    209                 <a href="mailto:rspencer (a] x10sys.com">Reid Spencer</a> and
    210                 <a href="mailto:owen (a] apple.com">Owen Anderson</a></p>
    211 </div>
    212 
    213 <!-- *********************************************************************** -->
    214 <h2>
    215   <a name="introduction">Introduction </a>
    216 </h2>
    217 <!-- *********************************************************************** -->
    218 
    219 <div>
    220 
    221 <p>This document is meant to highlight some of the important classes and
    222 interfaces available in the LLVM source-base.  This manual is not
    223 intended to explain what LLVM is, how it works, and what LLVM code looks
    224 like.  It assumes that you know the basics of LLVM and are interested
    225 in writing transformations or otherwise analyzing or manipulating the
    226 code.</p>
    227 
    228 <p>This document should get you oriented so that you can find your
    229 way in the continuously growing source code that makes up the LLVM
    230 infrastructure. Note that this manual is not intended to serve as a
    231 replacement for reading the source code, so if you think there should be
    232 a method in one of these classes to do something, but it's not listed,
    233 check the source.  Links to the <a href="/doxygen/">doxygen</a> sources
    234 are provided to make this as easy as possible.</p>
    235 
    236 <p>The first section of this document describes general information that is
    237 useful to know when working in the LLVM infrastructure, and the second describes
    238 the Core LLVM classes.  In the future this manual will be extended with
    239 information describing how to use extension libraries, such as dominator
    240 information, CFG traversal routines, and useful utilities like the <tt><a
    241 href="/doxygen/InstVisitor_8h-source.html">InstVisitor</a></tt> template.</p>
    242 
    243 </div>
    244 
    245 <!-- *********************************************************************** -->
    246 <h2>
    247   <a name="general">General Information</a>
    248 </h2>
    249 <!-- *********************************************************************** -->
    250 
    251 <div>
    252 
    253 <p>This section contains general information that is useful if you are working
    254 in the LLVM source-base, but that isn't specific to any particular API.</p>
    255 
    256 <!-- ======================================================================= -->
    257 <h3>
    258   <a name="stl">The C++ Standard Template Library</a>
    259 </h3>
    260 
    261 <div>
    262 
    263 <p>LLVM makes heavy use of the C++ Standard Template Library (STL),
    264 perhaps much more than you are used to, or have seen before.  Because of
    265 this, you might want to do a little background reading in the
    266 techniques used and capabilities of the library.  There are many good
    267 pages that discuss the STL, and several books on the subject that you
    268 can get, so it will not be discussed in this document.</p>
    269 
    270 <p>Here are some useful links:</p>
    271 
    272 <ol>
    273 
    274 <li><a href="http://www.dinkumware.com/manuals/#Standard C++ Library">Dinkumware
    275 C++ Library reference</a> - an excellent reference for the STL and other parts
    276 of the standard C++ library.</li>
    277 
    278 <li><a href="http://www.tempest-sw.com/cpp/">C++ In a Nutshell</a> - This is an
    279 O'Reilly book in the making.  It has a decent Standard Library
    280 Reference that rivals Dinkumware's, and is unfortunately no longer free since the
    281 book has been published.</li>
    282 
    283 <li><a href="http://www.parashift.com/c++-faq-lite/">C++ Frequently Asked
    284 Questions</a></li>
    285 
    286 <li><a href="http://www.sgi.com/tech/stl/">SGI's STL Programmer's Guide</a> -
    287 Contains a useful <a
    288 href="http://www.sgi.com/tech/stl/stl_introduction.html">Introduction to the
    289 STL</a>.</li>
    290 
    291 <li><a href="http://www.research.att.com/%7Ebs/C++.html">Bjarne Stroustrup's C++
    292 Page</a></li>
    293 
    294 <li><a href="http://64.78.49.204/">
    295 Bruce Eckel's Thinking in C++, 2nd ed. Volume 2 Revision 4.0 (even better, get
    296 the book).</a></li>
    297 
    298 </ol>
    299   
    300 <p>You are also encouraged to take a look at the <a
    301 href="CodingStandards.html">LLVM Coding Standards</a> guide which focuses on how
    302 to write maintainable code more than where to put your curly braces.</p>
    303 
    304 </div>
    305 
    306 <!-- ======================================================================= -->
    307 <h3>
    308   <a name="stl">Other useful references</a>
    309 </h3>
    310 
    311 <div>
    312 
    313 <ol>
    314 <li><a href="http://www.fortran-2000.com/ArnaudRecipes/sharedlib.html">Using
    315 static and shared libraries across platforms</a></li>
    316 </ol>
    317 
    318 </div>
    319 
    320 </div>
    321 
    322 <!-- *********************************************************************** -->
    323 <h2>
    324   <a name="apis">Important and useful LLVM APIs</a>
    325 </h2>
    326 <!-- *********************************************************************** -->
    327 
    328 <div>
    329 
    330 <p>Here we highlight some LLVM APIs that are generally useful and good to
    331 know about when writing transformations.</p>
    332 
    333 <!-- ======================================================================= -->
    334 <h3>
    335   <a name="isa">The <tt>isa&lt;&gt;</tt>, <tt>cast&lt;&gt;</tt> and
    336   <tt>dyn_cast&lt;&gt;</tt> templates</a>
    337 </h3>
    338 
    339 <div>
    340 
    341 <p>The LLVM source-base makes extensive use of a custom form of RTTI.
    342 These templates have many similarities to the C++ <tt>dynamic_cast&lt;&gt;</tt>
    343 operator, but they don't have some drawbacks (primarily stemming from
    344 the fact that <tt>dynamic_cast&lt;&gt;</tt> only works on classes that
    345 have a v-table). Because they are used so often, you must know what they
    346 do and how they work. All of these templates are defined in the <a
    347  href="/doxygen/Casting_8h-source.html"><tt>llvm/Support/Casting.h</tt></a>
    348 file (note that you very rarely have to include this file directly).</p>
    349 
    350 <dl>
    351   <dt><tt>isa&lt;&gt;</tt>: </dt>
    352 
    353   <dd><p>The <tt>isa&lt;&gt;</tt> operator works exactly like the Java
    354   "<tt>instanceof</tt>" operator.  It returns true or false depending on whether
    355   a reference or pointer points to an instance of the specified class.  This can
    356   be very useful for constraint checking of various sorts (example below).</p>
    357   </dd>
    358 
    359   <dt><tt>cast&lt;&gt;</tt>: </dt>
    360 
    361   <dd><p>The <tt>cast&lt;&gt;</tt> operator is a "checked cast" operation. It
    362   converts a pointer or reference from a base class to a derived class, causing
    363   an assertion failure if it is not really an instance of the right type.  This
    364   should be used in cases where you have some information that makes you believe
    365   that something is of the right type.  An example of the <tt>isa&lt;&gt;</tt>
    366   and <tt>cast&lt;&gt;</tt> template is:</p>
    367 
    368 <div class="doc_code">
    369 <pre>
    370 static bool isLoopInvariant(const <a href="#Value">Value</a> *V, const Loop *L) {
    371   if (isa&lt;<a href="#Constant">Constant</a>&gt;(V) || isa&lt;<a href="#Argument">Argument</a>&gt;(V) || isa&lt;<a href="#GlobalValue">GlobalValue</a>&gt;(V))
    372     return true;
    373 
    374   // <i>Otherwise, it must be an instruction...</i>
    375   return !L-&gt;contains(cast&lt;<a href="#Instruction">Instruction</a>&gt;(V)-&gt;getParent());
    376 }
    377 </pre>
    378 </div>
    379 
    380   <p>Note that you should <b>not</b> use an <tt>isa&lt;&gt;</tt> test followed
    381   by a <tt>cast&lt;&gt;</tt>, for that use the <tt>dyn_cast&lt;&gt;</tt>
    382   operator.</p>
    383 
    384   </dd>
    385 
    386   <dt><tt>dyn_cast&lt;&gt;</tt>:</dt>
    387 
    388   <dd><p>The <tt>dyn_cast&lt;&gt;</tt> operator is a "checking cast" operation.
    389   It checks to see if the operand is of the specified type, and if so, returns a
    390   pointer to it (this operator does not work with references). If the operand is
    391   not of the correct type, a null pointer is returned.  Thus, this works very
    392   much like the <tt>dynamic_cast&lt;&gt;</tt> operator in C++, and should be
    393   used in the same circumstances.  Typically, the <tt>dyn_cast&lt;&gt;</tt>
    394   operator is used in an <tt>if</tt> statement or some other flow control
    395   statement like this:</p>
    396 
    397 <div class="doc_code">
    398 <pre>
    399 if (<a href="#AllocationInst">AllocationInst</a> *AI = dyn_cast&lt;<a href="#AllocationInst">AllocationInst</a>&gt;(Val)) {
    400   // <i>...</i>
    401 }
    402 </pre>
    403 </div>
    404    
    405   <p>This form of the <tt>if</tt> statement effectively combines together a call
    406   to <tt>isa&lt;&gt;</tt> and a call to <tt>cast&lt;&gt;</tt> into one
    407   statement, which is very convenient.</p>
    408 
    409   <p>Note that the <tt>dyn_cast&lt;&gt;</tt> operator, like C++'s
    410   <tt>dynamic_cast&lt;&gt;</tt> or Java's <tt>instanceof</tt> operator, can be
    411   abused.  In particular, you should not use big chained <tt>if/then/else</tt>
    412   blocks to check for lots of different variants of classes.  If you find
    413   yourself wanting to do this, it is much cleaner and more efficient to use the
    414   <tt>InstVisitor</tt> class to dispatch over the instruction type directly.</p>
    415 
    416   </dd>
    417 
    418   <dt><tt>cast_or_null&lt;&gt;</tt>: </dt>
    419   
    420   <dd><p>The <tt>cast_or_null&lt;&gt;</tt> operator works just like the
    421   <tt>cast&lt;&gt;</tt> operator, except that it allows for a null pointer as an
    422   argument (which it then propagates).  This can sometimes be useful, allowing
    423   you to combine several null checks into one.</p></dd>
    424 
    425   <dt><tt>dyn_cast_or_null&lt;&gt;</tt>: </dt>
    426 
    427   <dd><p>The <tt>dyn_cast_or_null&lt;&gt;</tt> operator works just like the
    428   <tt>dyn_cast&lt;&gt;</tt> operator, except that it allows for a null pointer
    429   as an argument (which it then propagates).  This can sometimes be useful,
    430   allowing you to combine several null checks into one.</p></dd>
    431 
    432 </dl>
    433 
    434 <p>These five templates can be used with any classes, whether they have a
    435 v-table or not.  To add support for these templates, you simply need to add
    436 <tt>classof</tt> static methods to the class you are interested casting
    437 to. Describing this is currently outside the scope of this document, but there
    438 are lots of examples in the LLVM source base.</p>
    439 
    440 </div>
    441 
    442 
    443 <!-- ======================================================================= -->
    444 <h3>
    445   <a name="string_apis">Passing strings (the <tt>StringRef</tt>
    446 and <tt>Twine</tt> classes)</a>
    447 </h3>
    448 
    449 <div>
    450 
    451 <p>Although LLVM generally does not do much string manipulation, we do have
    452 several important APIs which take strings.  Two important examples are the
    453 Value class -- which has names for instructions, functions, etc. -- and the
    454 StringMap class which is used extensively in LLVM and Clang.</p>
    455 
    456 <p>These are generic classes, and they need to be able to accept strings which
    457 may have embedded null characters.  Therefore, they cannot simply take
    458 a <tt>const char *</tt>, and taking a <tt>const std::string&amp;</tt> requires
    459 clients to perform a heap allocation which is usually unnecessary.  Instead,
    460 many LLVM APIs use a <tt>StringRef</tt> or a <tt>const Twine&amp;</tt> for
    461 passing strings efficiently.</p>
    462 
    463 <!-- _______________________________________________________________________ -->
    464 <h4>
    465   <a name="StringRef">The <tt>StringRef</tt> class</a>
    466 </h4>
    467 
    468 <div>
    469 
    470 <p>The <tt>StringRef</tt> data type represents a reference to a constant string
    471 (a character array and a length) and supports the common operations available
    472 on <tt>std:string</tt>, but does not require heap allocation.</p>
    473 
    474 <p>It can be implicitly constructed using a C style null-terminated string,
    475 an <tt>std::string</tt>, or explicitly with a character pointer and length.
    476 For example, the <tt>StringRef</tt> find function is declared as:</p>
    477 
    478 <pre class="doc_code">
    479   iterator find(StringRef Key);
    480 </pre>
    481 
    482 <p>and clients can call it using any one of:</p>
    483 
    484 <pre class="doc_code">
    485   Map.find("foo");                 <i>// Lookup "foo"</i>
    486   Map.find(std::string("bar"));    <i>// Lookup "bar"</i>
    487   Map.find(StringRef("\0baz", 4)); <i>// Lookup "\0baz"</i>
    488 </pre>
    489 
    490 <p>Similarly, APIs which need to return a string may return a <tt>StringRef</tt>
    491 instance, which can be used directly or converted to an <tt>std::string</tt>
    492 using the <tt>str</tt> member function.  See 
    493 "<tt><a href="/doxygen/classllvm_1_1StringRef_8h-source.html">llvm/ADT/StringRef.h</a></tt>"
    494 for more information.</p>
    495 
    496 <p>You should rarely use the <tt>StringRef</tt> class directly, because it contains
    497 pointers to external memory it is not generally safe to store an instance of the
    498 class (unless you know that the external storage will not be freed). StringRef is
    499 small and pervasive enough in LLVM that it should always be passed by value.</p>
    500 
    501 </div>
    502 
    503 <!-- _______________________________________________________________________ -->
    504 <h4>
    505   <a name="Twine">The <tt>Twine</tt> class</a>
    506 </h4>
    507 
    508 <div>
    509 
    510 <p>The <tt>Twine</tt> class is an efficient way for APIs to accept concatenated
    511 strings.  For example, a common LLVM paradigm is to name one instruction based on
    512 the name of another instruction with a suffix, for example:</p>
    513 
    514 <div class="doc_code">
    515 <pre>
    516     New = CmpInst::Create(<i>...</i>, SO->getName() + ".cmp");
    517 </pre>
    518 </div>
    519 
    520 <p>The <tt>Twine</tt> class is effectively a
    521 lightweight <a href="http://en.wikipedia.org/wiki/Rope_(computer_science)">rope</a>
    522 which points to temporary (stack allocated) objects.  Twines can be implicitly
    523 constructed as the result of the plus operator applied to strings (i.e., a C
    524 strings, an <tt>std::string</tt>, or a <tt>StringRef</tt>).  The twine delays the
    525 actual concatenation of strings until it is actually required, at which point
    526 it can be efficiently rendered directly into a character array.  This avoids
    527 unnecessary heap allocation involved in constructing the temporary results of
    528 string concatenation. See
    529 "<tt><a href="/doxygen/classllvm_1_1Twine_8h-source.html">llvm/ADT/Twine.h</a></tt>"
    530 for more information.</p>
    531 
    532 <p>As with a <tt>StringRef</tt>, <tt>Twine</tt> objects point to external memory
    533 and should almost never be stored or mentioned directly.  They are intended
    534 solely for use when defining a function which should be able to efficiently
    535 accept concatenated strings.</p>
    536 
    537 </div>
    538 
    539 </div>
    540 
    541 <!-- ======================================================================= -->
    542 <h3>
    543   <a name="DEBUG">The <tt>DEBUG()</tt> macro and <tt>-debug</tt> option</a>
    544 </h3>
    545 
    546 <div>
    547 
    548 <p>Often when working on your pass you will put a bunch of debugging printouts
    549 and other code into your pass.  After you get it working, you want to remove
    550 it, but you may need it again in the future (to work out new bugs that you run
    551 across).</p>
    552 
    553 <p> Naturally, because of this, you don't want to delete the debug printouts,
    554 but you don't want them to always be noisy.  A standard compromise is to comment
    555 them out, allowing you to enable them if you need them in the future.</p>
    556 
    557 <p>The "<tt><a href="/doxygen/Debug_8h-source.html">llvm/Support/Debug.h</a></tt>"
    558 file provides a macro named <tt>DEBUG()</tt> that is a much nicer solution to
    559 this problem.  Basically, you can put arbitrary code into the argument of the
    560 <tt>DEBUG</tt> macro, and it is only executed if '<tt>opt</tt>' (or any other
    561 tool) is run with the '<tt>-debug</tt>' command line argument:</p>
    562 
    563 <div class="doc_code">
    564 <pre>
    565 DEBUG(errs() &lt;&lt; "I am here!\n");
    566 </pre>
    567 </div>
    568 
    569 <p>Then you can run your pass like this:</p>
    570 
    571 <div class="doc_code">
    572 <pre>
    573 $ opt &lt; a.bc &gt; /dev/null -mypass
    574 <i>&lt;no output&gt;</i>
    575 $ opt &lt; a.bc &gt; /dev/null -mypass -debug
    576 I am here!
    577 </pre>
    578 </div>
    579 
    580 <p>Using the <tt>DEBUG()</tt> macro instead of a home-brewed solution allows you
    581 to not have to create "yet another" command line option for the debug output for
    582 your pass.  Note that <tt>DEBUG()</tt> macros are disabled for optimized builds,
    583 so they do not cause a performance impact at all (for the same reason, they
    584 should also not contain side-effects!).</p>
    585 
    586 <p>One additional nice thing about the <tt>DEBUG()</tt> macro is that you can
    587 enable or disable it directly in gdb.  Just use "<tt>set DebugFlag=0</tt>" or
    588 "<tt>set DebugFlag=1</tt>" from the gdb if the program is running.  If the
    589 program hasn't been started yet, you can always just run it with
    590 <tt>-debug</tt>.</p>
    591 
    592 <!-- _______________________________________________________________________ -->
    593 <h4>
    594   <a name="DEBUG_TYPE">Fine grained debug info with <tt>DEBUG_TYPE</tt> and
    595   the <tt>-debug-only</tt> option</a>
    596 </h4>
    597 
    598 <div>
    599 
    600 <p>Sometimes you may find yourself in a situation where enabling <tt>-debug</tt>
    601 just turns on <b>too much</b> information (such as when working on the code
    602 generator).  If you want to enable debug information with more fine-grained
    603 control, you define the <tt>DEBUG_TYPE</tt> macro and the <tt>-debug</tt> only
    604 option as follows:</p>
    605 
    606 <div class="doc_code">
    607 <pre>
    608 #undef  DEBUG_TYPE
    609 DEBUG(errs() &lt;&lt; "No debug type\n");
    610 #define DEBUG_TYPE "foo"
    611 DEBUG(errs() &lt;&lt; "'foo' debug type\n");
    612 #undef  DEBUG_TYPE
    613 #define DEBUG_TYPE "bar"
    614 DEBUG(errs() &lt;&lt; "'bar' debug type\n"));
    615 #undef  DEBUG_TYPE
    616 #define DEBUG_TYPE ""
    617 DEBUG(errs() &lt;&lt; "No debug type (2)\n");
    618 </pre>
    619 </div>
    620 
    621 <p>Then you can run your pass like this:</p>
    622 
    623 <div class="doc_code">
    624 <pre>
    625 $ opt &lt; a.bc &gt; /dev/null -mypass
    626 <i>&lt;no output&gt;</i>
    627 $ opt &lt; a.bc &gt; /dev/null -mypass -debug
    628 No debug type
    629 'foo' debug type
    630 'bar' debug type
    631 No debug type (2)
    632 $ opt &lt; a.bc &gt; /dev/null -mypass -debug-only=foo
    633 'foo' debug type
    634 $ opt &lt; a.bc &gt; /dev/null -mypass -debug-only=bar
    635 'bar' debug type
    636 </pre>
    637 </div>
    638 
    639 <p>Of course, in practice, you should only set <tt>DEBUG_TYPE</tt> at the top of
    640 a file, to specify the debug type for the entire module (if you do this before
    641 you <tt>#include "llvm/Support/Debug.h"</tt>, you don't have to insert the ugly
    642 <tt>#undef</tt>'s).  Also, you should use names more meaningful than "foo" and
    643 "bar", because there is no system in place to ensure that names do not
    644 conflict. If two different modules use the same string, they will all be turned
    645 on when the name is specified. This allows, for example, all debug information
    646 for instruction scheduling to be enabled with <tt>-debug-type=InstrSched</tt>,
    647 even if the source lives in multiple files.</p>
    648 
    649 <p>The <tt>DEBUG_WITH_TYPE</tt> macro is also available for situations where you
    650 would like to set <tt>DEBUG_TYPE</tt>, but only for one specific <tt>DEBUG</tt>
    651 statement. It takes an additional first parameter, which is the type to use. For
    652 example, the preceding example could be written as:</p>
    653 
    654 
    655 <div class="doc_code">
    656 <pre>
    657 DEBUG_WITH_TYPE("", errs() &lt;&lt; "No debug type\n");
    658 DEBUG_WITH_TYPE("foo", errs() &lt;&lt; "'foo' debug type\n");
    659 DEBUG_WITH_TYPE("bar", errs() &lt;&lt; "'bar' debug type\n"));
    660 DEBUG_WITH_TYPE("", errs() &lt;&lt; "No debug type (2)\n");
    661 </pre>
    662 </div>
    663 
    664 </div>
    665 
    666 </div>
    667 
    668 <!-- ======================================================================= -->
    669 <h3>
    670   <a name="Statistic">The <tt>Statistic</tt> class &amp; <tt>-stats</tt>
    671   option</a>
    672 </h3>
    673 
    674 <div>
    675 
    676 <p>The "<tt><a
    677 href="/doxygen/Statistic_8h-source.html">llvm/ADT/Statistic.h</a></tt>" file
    678 provides a class named <tt>Statistic</tt> that is used as a unified way to
    679 keep track of what the LLVM compiler is doing and how effective various
    680 optimizations are.  It is useful to see what optimizations are contributing to
    681 making a particular program run faster.</p>
    682 
    683 <p>Often you may run your pass on some big program, and you're interested to see
    684 how many times it makes a certain transformation.  Although you can do this with
    685 hand inspection, or some ad-hoc method, this is a real pain and not very useful
    686 for big programs.  Using the <tt>Statistic</tt> class makes it very easy to
    687 keep track of this information, and the calculated information is presented in a
    688 uniform manner with the rest of the passes being executed.</p>
    689 
    690 <p>There are many examples of <tt>Statistic</tt> uses, but the basics of using
    691 it are as follows:</p>
    692 
    693 <ol>
    694     <li><p>Define your statistic like this:</p>
    695 
    696 <div class="doc_code">
    697 <pre>
    698 #define <a href="#DEBUG_TYPE">DEBUG_TYPE</a> "mypassname"   <i>// This goes before any #includes.</i>
    699 STATISTIC(NumXForms, "The # of times I did stuff");
    700 </pre>
    701 </div>
    702 
    703   <p>The <tt>STATISTIC</tt> macro defines a static variable, whose name is
    704     specified by the first argument.  The pass name is taken from the DEBUG_TYPE
    705     macro, and the description is taken from the second argument.  The variable
    706     defined ("NumXForms" in this case) acts like an unsigned integer.</p></li>
    707 
    708     <li><p>Whenever you make a transformation, bump the counter:</p>
    709 
    710 <div class="doc_code">
    711 <pre>
    712 ++NumXForms;   // <i>I did stuff!</i>
    713 </pre>
    714 </div>
    715 
    716     </li>
    717   </ol>
    718 
    719   <p>That's all you have to do.  To get '<tt>opt</tt>' to print out the
    720   statistics gathered, use the '<tt>-stats</tt>' option:</p>
    721 
    722 <div class="doc_code">
    723 <pre>
    724 $ opt -stats -mypassname &lt; program.bc &gt; /dev/null
    725 <i>... statistics output ...</i>
    726 </pre>
    727 </div>
    728 
    729   <p> When running <tt>opt</tt> on a C file from the SPEC benchmark
    730 suite, it gives a report that looks like this:</p>
    731 
    732 <div class="doc_code">
    733 <pre>
    734    7646 bitcodewriter   - Number of normal instructions
    735     725 bitcodewriter   - Number of oversized instructions
    736  129996 bitcodewriter   - Number of bitcode bytes written
    737    2817 raise           - Number of insts DCEd or constprop'd
    738    3213 raise           - Number of cast-of-self removed
    739    5046 raise           - Number of expression trees converted
    740      75 raise           - Number of other getelementptr's formed
    741     138 raise           - Number of load/store peepholes
    742      42 deadtypeelim    - Number of unused typenames removed from symtab
    743     392 funcresolve     - Number of varargs functions resolved
    744      27 globaldce       - Number of global variables removed
    745       2 adce            - Number of basic blocks removed
    746     134 cee             - Number of branches revectored
    747      49 cee             - Number of setcc instruction eliminated
    748     532 gcse            - Number of loads removed
    749    2919 gcse            - Number of instructions removed
    750      86 indvars         - Number of canonical indvars added
    751      87 indvars         - Number of aux indvars removed
    752      25 instcombine     - Number of dead inst eliminate
    753     434 instcombine     - Number of insts combined
    754     248 licm            - Number of load insts hoisted
    755    1298 licm            - Number of insts hoisted to a loop pre-header
    756       3 licm            - Number of insts hoisted to multiple loop preds (bad, no loop pre-header)
    757      75 mem2reg         - Number of alloca's promoted
    758    1444 cfgsimplify     - Number of blocks simplified
    759 </pre>
    760 </div>
    761 
    762 <p>Obviously, with so many optimizations, having a unified framework for this
    763 stuff is very nice.  Making your pass fit well into the framework makes it more
    764 maintainable and useful.</p>
    765 
    766 </div>
    767 
    768 <!-- ======================================================================= -->
    769 <h3>
    770   <a name="ViewGraph">Viewing graphs while debugging code</a>
    771 </h3>
    772 
    773 <div>
    774 
    775 <p>Several of the important data structures in LLVM are graphs: for example
    776 CFGs made out of LLVM <a href="#BasicBlock">BasicBlock</a>s, CFGs made out of
    777 LLVM <a href="CodeGenerator.html#machinebasicblock">MachineBasicBlock</a>s, and
    778 <a href="CodeGenerator.html#selectiondag_intro">Instruction Selection
    779 DAGs</a>.  In many cases, while debugging various parts of the compiler, it is
    780 nice to instantly visualize these graphs.</p>
    781 
    782 <p>LLVM provides several callbacks that are available in a debug build to do
    783 exactly that.  If you call the <tt>Function::viewCFG()</tt> method, for example,
    784 the current LLVM tool will pop up a window containing the CFG for the function
    785 where each basic block is a node in the graph, and each node contains the
    786 instructions in the block.  Similarly, there also exists 
    787 <tt>Function::viewCFGOnly()</tt> (does not include the instructions), the
    788 <tt>MachineFunction::viewCFG()</tt> and <tt>MachineFunction::viewCFGOnly()</tt>,
    789 and the <tt>SelectionDAG::viewGraph()</tt> methods.  Within GDB, for example,
    790 you can usually use something like <tt>call DAG.viewGraph()</tt> to pop
    791 up a window.  Alternatively, you can sprinkle calls to these functions in your
    792 code in places you want to debug.</p>
    793 
    794 <p>Getting this to work requires a small amount of configuration.  On Unix
    795 systems with X11, install the <a href="http://www.graphviz.org">graphviz</a>
    796 toolkit, and make sure 'dot' and 'gv' are in your path.  If you are running on
    797 Mac OS/X, download and install the Mac OS/X <a 
    798 href="http://www.pixelglow.com/graphviz/">Graphviz program</a>, and add
    799 <tt>/Applications/Graphviz.app/Contents/MacOS/</tt> (or wherever you install
    800 it) to your path.  Once in your system and path are set up, rerun the LLVM
    801 configure script and rebuild LLVM to enable this functionality.</p>
    802 
    803 <p><tt>SelectionDAG</tt> has been extended to make it easier to locate
    804 <i>interesting</i> nodes in large complex graphs.  From gdb, if you
    805 <tt>call DAG.setGraphColor(<i>node</i>, "<i>color</i>")</tt>, then the
    806 next <tt>call DAG.viewGraph()</tt> would highlight the node in the
    807 specified color (choices of colors can be found at <a
    808 href="http://www.graphviz.org/doc/info/colors.html">colors</a>.) More
    809 complex node attributes can be provided with <tt>call
    810 DAG.setGraphAttrs(<i>node</i>, "<i>attributes</i>")</tt> (choices can be
    811 found at <a href="http://www.graphviz.org/doc/info/attrs.html">Graph
    812 Attributes</a>.)  If you want to restart and clear all the current graph
    813 attributes, then you can <tt>call DAG.clearGraphAttrs()</tt>. </p>
    814 
    815 <p>Note that graph visualization features are compiled out of Release builds
    816 to reduce file size.  This means that you need a Debug+Asserts or 
    817 Release+Asserts build to use these features.</p>
    818 
    819 </div>
    820 
    821 </div>
    822 
    823 <!-- *********************************************************************** -->
    824 <h2>
    825   <a name="datastructure">Picking the Right Data Structure for a Task</a>
    826 </h2>
    827 <!-- *********************************************************************** -->
    828 
    829 <div>
    830 
    831 <p>LLVM has a plethora of data structures in the <tt>llvm/ADT/</tt> directory,
    832  and we commonly use STL data structures.  This section describes the trade-offs
    833  you should consider when you pick one.</p>
    834 
    835 <p>
    836 The first step is a choose your own adventure: do you want a sequential
    837 container, a set-like container, or a map-like container?  The most important
    838 thing when choosing a container is the algorithmic properties of how you plan to
    839 access the container.  Based on that, you should use:</p>
    840 
    841 <ul>
    842 <li>a <a href="#ds_map">map-like</a> container if you need efficient look-up
    843     of an value based on another value.  Map-like containers also support
    844     efficient queries for containment (whether a key is in the map).  Map-like
    845     containers generally do not support efficient reverse mapping (values to
    846     keys).  If you need that, use two maps.  Some map-like containers also
    847     support efficient iteration through the keys in sorted order.  Map-like
    848     containers are the most expensive sort, only use them if you need one of
    849     these capabilities.</li>
    850 
    851 <li>a <a href="#ds_set">set-like</a> container if you need to put a bunch of
    852     stuff into a container that automatically eliminates duplicates.  Some
    853     set-like containers support efficient iteration through the elements in
    854     sorted order.  Set-like containers are more expensive than sequential
    855     containers.
    856 </li>
    857 
    858 <li>a <a href="#ds_sequential">sequential</a> container provides
    859     the most efficient way to add elements and keeps track of the order they are
    860     added to the collection.  They permit duplicates and support efficient
    861     iteration, but do not support efficient look-up based on a key.
    862 </li>
    863 
    864 <li>a <a href="#ds_string">string</a> container is a specialized sequential
    865     container or reference structure that is used for character or byte
    866     arrays.</li>
    867 
    868 <li>a <a href="#ds_bit">bit</a> container provides an efficient way to store and
    869     perform set operations on sets of numeric id's, while automatically
    870     eliminating duplicates.  Bit containers require a maximum of 1 bit for each
    871     identifier you want to store.
    872 </li>
    873 </ul>
    874 
    875 <p>
    876 Once the proper category of container is determined, you can fine tune the
    877 memory use, constant factors, and cache behaviors of access by intelligently
    878 picking a member of the category.  Note that constant factors and cache behavior
    879 can be a big deal.  If you have a vector that usually only contains a few
    880 elements (but could contain many), for example, it's much better to use
    881 <a href="#dss_smallvector">SmallVector</a> than <a href="#dss_vector">vector</a>
    882 .  Doing so avoids (relatively) expensive malloc/free calls, which dwarf the
    883 cost of adding the elements to the container. </p>
    884 
    885 <!-- ======================================================================= -->
    886 <h3>
    887   <a name="ds_sequential">Sequential Containers (std::vector, std::list, etc)</a>
    888 </h3>
    889 
    890 <div>
    891 There are a variety of sequential containers available for you, based on your
    892 needs.  Pick the first in this section that will do what you want.
    893   
    894 <!-- _______________________________________________________________________ -->
    895 <h4>
    896   <a name="dss_arrayref">llvm/ADT/ArrayRef.h</a>
    897 </h4>
    898 
    899 <div>
    900 <p>The llvm::ArrayRef class is the preferred class to use in an interface that
    901    accepts a sequential list of elements in memory and just reads from them.  By
    902    taking an ArrayRef, the API can be passed a fixed size array, an std::vector,
    903    an llvm::SmallVector and anything else that is contiguous in memory.
    904 </p>
    905 </div>
    906 
    907 
    908   
    909 <!-- _______________________________________________________________________ -->
    910 <h4>
    911   <a name="dss_fixedarrays">Fixed Size Arrays</a>
    912 </h4>
    913 
    914 <div>
    915 <p>Fixed size arrays are very simple and very fast.  They are good if you know
    916 exactly how many elements you have, or you have a (low) upper bound on how many
    917 you have.</p>
    918 </div>
    919 
    920 <!-- _______________________________________________________________________ -->
    921 <h4>
    922   <a name="dss_heaparrays">Heap Allocated Arrays</a>
    923 </h4>
    924 
    925 <div>
    926 <p>Heap allocated arrays (new[] + delete[]) are also simple.  They are good if
    927 the number of elements is variable, if you know how many elements you will need
    928 before the array is allocated, and if the array is usually large (if not,
    929 consider a <a href="#dss_smallvector">SmallVector</a>).  The cost of a heap
    930 allocated array is the cost of the new/delete (aka malloc/free).  Also note that
    931 if you are allocating an array of a type with a constructor, the constructor and
    932 destructors will be run for every element in the array (re-sizable vectors only
    933 construct those elements actually used).</p>
    934 </div>
    935 
    936 <!-- _______________________________________________________________________ -->
    937 <h4>
    938   <a name="dss_tinyptrvector">"llvm/ADT/TinyPtrVector.h"</a>
    939 </h4>
    940 
    941 
    942 <div>
    943 <p><tt>TinyPtrVector&lt;Type&gt;</tt> is a highly specialized collection class
    944 that is optimized to avoid allocation in the case when a vector has zero or one
    945 elements.  It has two major restrictions: 1) it can only hold values of pointer
    946 type, and 2) it cannot hold a null pointer.</p>
    947   
    948 <p>Since this container is highly specialized, it is rarely used.</p>
    949   
    950 </div>
    951     
    952 <!-- _______________________________________________________________________ -->
    953 <h4>
    954   <a name="dss_smallvector">"llvm/ADT/SmallVector.h"</a>
    955 </h4>
    956 
    957 <div>
    958 <p><tt>SmallVector&lt;Type, N&gt;</tt> is a simple class that looks and smells
    959 just like <tt>vector&lt;Type&gt;</tt>:
    960 it supports efficient iteration, lays out elements in memory order (so you can
    961 do pointer arithmetic between elements), supports efficient push_back/pop_back
    962 operations, supports efficient random access to its elements, etc.</p>
    963 
    964 <p>The advantage of SmallVector is that it allocates space for
    965 some number of elements (N) <b>in the object itself</b>.  Because of this, if
    966 the SmallVector is dynamically smaller than N, no malloc is performed.  This can
    967 be a big win in cases where the malloc/free call is far more expensive than the
    968 code that fiddles around with the elements.</p>
    969 
    970 <p>This is good for vectors that are "usually small" (e.g. the number of
    971 predecessors/successors of a block is usually less than 8).  On the other hand,
    972 this makes the size of the SmallVector itself large, so you don't want to
    973 allocate lots of them (doing so will waste a lot of space).  As such,
    974 SmallVectors are most useful when on the stack.</p>
    975 
    976 <p>SmallVector also provides a nice portable and efficient replacement for
    977 <tt>alloca</tt>.</p>
    978 
    979 </div>
    980 
    981 <!-- _______________________________________________________________________ -->
    982 <h4>
    983   <a name="dss_vector">&lt;vector&gt;</a>
    984 </h4>
    985 
    986 <div>
    987 <p>
    988 std::vector is well loved and respected.  It is useful when SmallVector isn't:
    989 when the size of the vector is often large (thus the small optimization will
    990 rarely be a benefit) or if you will be allocating many instances of the vector
    991 itself (which would waste space for elements that aren't in the container).
    992 vector is also useful when interfacing with code that expects vectors :).
    993 </p>
    994 
    995 <p>One worthwhile note about std::vector: avoid code like this:</p>
    996 
    997 <div class="doc_code">
    998 <pre>
    999 for ( ... ) {
   1000    std::vector&lt;foo&gt; V;
   1001    // make use of V.
   1002 }
   1003 </pre>
   1004 </div>
   1005 
   1006 <p>Instead, write this as:</p>
   1007 
   1008 <div class="doc_code">
   1009 <pre>
   1010 std::vector&lt;foo&gt; V;
   1011 for ( ... ) {
   1012    // make use of V.
   1013    V.clear();
   1014 }
   1015 </pre>
   1016 </div>
   1017 
   1018 <p>Doing so will save (at least) one heap allocation and free per iteration of
   1019 the loop.</p>
   1020 
   1021 </div>
   1022 
   1023 <!-- _______________________________________________________________________ -->
   1024 <h4>
   1025   <a name="dss_deque">&lt;deque&gt;</a>
   1026 </h4>
   1027 
   1028 <div>
   1029 <p>std::deque is, in some senses, a generalized version of std::vector.  Like
   1030 std::vector, it provides constant time random access and other similar
   1031 properties, but it also provides efficient access to the front of the list.  It
   1032 does not guarantee continuity of elements within memory.</p>
   1033 
   1034 <p>In exchange for this extra flexibility, std::deque has significantly higher
   1035 constant factor costs than std::vector.  If possible, use std::vector or
   1036 something cheaper.</p>
   1037 </div>
   1038 
   1039 <!-- _______________________________________________________________________ -->
   1040 <h4>
   1041   <a name="dss_list">&lt;list&gt;</a>
   1042 </h4>
   1043 
   1044 <div>
   1045 <p>std::list is an extremely inefficient class that is rarely useful.
   1046 It performs a heap allocation for every element inserted into it, thus having an
   1047 extremely high constant factor, particularly for small data types.  std::list
   1048 also only supports bidirectional iteration, not random access iteration.</p>
   1049 
   1050 <p>In exchange for this high cost, std::list supports efficient access to both
   1051 ends of the list (like std::deque, but unlike std::vector or SmallVector).  In
   1052 addition, the iterator invalidation characteristics of std::list are stronger
   1053 than that of a vector class: inserting or removing an element into the list does
   1054 not invalidate iterator or pointers to other elements in the list.</p>
   1055 </div>
   1056 
   1057 <!-- _______________________________________________________________________ -->
   1058 <h4>
   1059   <a name="dss_ilist">llvm/ADT/ilist.h</a>
   1060 </h4>
   1061 
   1062 <div>
   1063 <p><tt>ilist&lt;T&gt;</tt> implements an 'intrusive' doubly-linked list.  It is
   1064 intrusive, because it requires the element to store and provide access to the
   1065 prev/next pointers for the list.</p>
   1066 
   1067 <p><tt>ilist</tt> has the same drawbacks as <tt>std::list</tt>, and additionally
   1068 requires an <tt>ilist_traits</tt> implementation for the element type, but it
   1069 provides some novel characteristics.  In particular, it can efficiently store
   1070 polymorphic objects, the traits class is informed when an element is inserted or
   1071 removed from the list, and <tt>ilist</tt>s are guaranteed to support a
   1072 constant-time splice operation.</p>
   1073 
   1074 <p>These properties are exactly what we want for things like
   1075 <tt>Instruction</tt>s and basic blocks, which is why these are implemented with
   1076 <tt>ilist</tt>s.</p>
   1077 
   1078 Related classes of interest are explained in the following subsections:
   1079     <ul>
   1080       <li><a href="#dss_ilist_traits">ilist_traits</a></li>
   1081       <li><a href="#dss_iplist">iplist</a></li>
   1082       <li><a href="#dss_ilist_node">llvm/ADT/ilist_node.h</a></li>
   1083       <li><a href="#dss_ilist_sentinel">Sentinels</a></li>
   1084     </ul>
   1085 </div>
   1086 
   1087 <!-- _______________________________________________________________________ -->
   1088 <h4>
   1089   <a name="dss_packedvector">llvm/ADT/PackedVector.h</a>
   1090 </h4>
   1091 
   1092 <div>
   1093 <p>
   1094 Useful for storing a vector of values using only a few number of bits for each
   1095 value. Apart from the standard operations of a vector-like container, it can
   1096 also perform an 'or' set operation. 
   1097 </p>
   1098 
   1099 <p>For example:</p>
   1100 
   1101 <div class="doc_code">
   1102 <pre>
   1103 enum State {
   1104     None = 0x0,
   1105     FirstCondition = 0x1,
   1106     SecondCondition = 0x2,
   1107     Both = 0x3
   1108 };
   1109 
   1110 State get() {
   1111     PackedVector&lt;State, 2&gt; Vec1;
   1112     Vec1.push_back(FirstCondition);
   1113 
   1114     PackedVector&lt;State, 2&gt; Vec2;
   1115     Vec2.push_back(SecondCondition);
   1116 
   1117     Vec1 |= Vec2;
   1118     return Vec1[0]; // returns 'Both'.
   1119 }
   1120 </pre>
   1121 </div>
   1122 
   1123 </div>
   1124 
   1125 <!-- _______________________________________________________________________ -->
   1126 <h4>
   1127   <a name="dss_ilist_traits">ilist_traits</a>
   1128 </h4>
   1129 
   1130 <div>
   1131 <p><tt>ilist_traits&lt;T&gt;</tt> is <tt>ilist&lt;T&gt;</tt>'s customization
   1132 mechanism. <tt>iplist&lt;T&gt;</tt> (and consequently <tt>ilist&lt;T&gt;</tt>)
   1133 publicly derive from this traits class.</p>
   1134 </div>
   1135 
   1136 <!-- _______________________________________________________________________ -->
   1137 <h4>
   1138   <a name="dss_iplist">iplist</a>
   1139 </h4>
   1140 
   1141 <div>
   1142 <p><tt>iplist&lt;T&gt;</tt> is <tt>ilist&lt;T&gt;</tt>'s base and as such
   1143 supports a slightly narrower interface. Notably, inserters from
   1144 <tt>T&amp;</tt> are absent.</p>
   1145 
   1146 <p><tt>ilist_traits&lt;T&gt;</tt> is a public base of this class and can be
   1147 used for a wide variety of customizations.</p>
   1148 </div>
   1149 
   1150 <!-- _______________________________________________________________________ -->
   1151 <h4>
   1152   <a name="dss_ilist_node">llvm/ADT/ilist_node.h</a>
   1153 </h4>
   1154 
   1155 <div>
   1156 <p><tt>ilist_node&lt;T&gt;</tt> implements a the forward and backward links
   1157 that are expected by the <tt>ilist&lt;T&gt;</tt> (and analogous containers)
   1158 in the default manner.</p>
   1159 
   1160 <p><tt>ilist_node&lt;T&gt;</tt>s are meant to be embedded in the node type
   1161 <tt>T</tt>, usually <tt>T</tt> publicly derives from
   1162 <tt>ilist_node&lt;T&gt;</tt>.</p>
   1163 </div>
   1164 
   1165 <!-- _______________________________________________________________________ -->
   1166 <h4>
   1167   <a name="dss_ilist_sentinel">Sentinels</a>
   1168 </h4>
   1169 
   1170 <div>
   1171 <p><tt>ilist</tt>s have another specialty that must be considered. To be a good
   1172 citizen in the C++ ecosystem, it needs to support the standard container
   1173 operations, such as <tt>begin</tt> and <tt>end</tt> iterators, etc. Also, the
   1174 <tt>operator--</tt> must work correctly on the <tt>end</tt> iterator in the
   1175 case of non-empty <tt>ilist</tt>s.</p>
   1176 
   1177 <p>The only sensible solution to this problem is to allocate a so-called
   1178 <i>sentinel</i> along with the intrusive list, which serves as the <tt>end</tt>
   1179 iterator, providing the back-link to the last element. However conforming to the
   1180 C++ convention it is illegal to <tt>operator++</tt> beyond the sentinel and it
   1181 also must not be dereferenced.</p>
   1182 
   1183 <p>These constraints allow for some implementation freedom to the <tt>ilist</tt>
   1184 how to allocate and store the sentinel. The corresponding policy is dictated
   1185 by <tt>ilist_traits&lt;T&gt;</tt>. By default a <tt>T</tt> gets heap-allocated
   1186 whenever the need for a sentinel arises.</p>
   1187 
   1188 <p>While the default policy is sufficient in most cases, it may break down when
   1189 <tt>T</tt> does not provide a default constructor. Also, in the case of many
   1190 instances of <tt>ilist</tt>s, the memory overhead of the associated sentinels
   1191 is wasted. To alleviate the situation with numerous and voluminous
   1192 <tt>T</tt>-sentinels, sometimes a trick is employed, leading to <i>ghostly
   1193 sentinels</i>.</p>
   1194 
   1195 <p>Ghostly sentinels are obtained by specially-crafted <tt>ilist_traits&lt;T&gt;</tt>
   1196 which superpose the sentinel with the <tt>ilist</tt> instance in memory. Pointer
   1197 arithmetic is used to obtain the sentinel, which is relative to the
   1198 <tt>ilist</tt>'s <tt>this</tt> pointer. The <tt>ilist</tt> is augmented by an
   1199 extra pointer, which serves as the back-link of the sentinel. This is the only
   1200 field in the ghostly sentinel which can be legally accessed.</p>
   1201 </div>
   1202 
   1203 <!-- _______________________________________________________________________ -->
   1204 <h4>
   1205   <a name="dss_other">Other Sequential Container options</a>
   1206 </h4>
   1207 
   1208 <div>
   1209 <p>Other STL containers are available, such as std::string.</p>
   1210 
   1211 <p>There are also various STL adapter classes such as std::queue,
   1212 std::priority_queue, std::stack, etc.  These provide simplified access to an
   1213 underlying container but don't affect the cost of the container itself.</p>
   1214 
   1215 </div>
   1216 </div>
   1217 
   1218 <!-- ======================================================================= -->
   1219 <h3>
   1220   <a name="ds_string">String-like containers</a>
   1221 </h3>
   1222 
   1223 <div>
   1224 
   1225 <p>
   1226 There are a variety of ways to pass around and use strings in C and C++, and
   1227 LLVM adds a few new options to choose from.  Pick the first option on this list
   1228 that will do what you need, they are ordered according to their relative cost.
   1229 </p>
   1230 <p>
   1231 Note that is is generally preferred to <em>not</em> pass strings around as 
   1232 "<tt>const char*</tt>"'s.  These have a number of problems, including the fact
   1233 that they cannot represent embedded nul ("\0") characters, and do not have a
   1234 length available efficiently.  The general replacement for '<tt>const 
   1235 char*</tt>' is StringRef.
   1236 </p>
   1237   
   1238 <p>For more information on choosing string containers for APIs, please see
   1239 <a href="#string_apis">Passing strings</a>.</p>
   1240   
   1241   
   1242 <!-- _______________________________________________________________________ -->
   1243 <h4>
   1244   <a name="dss_stringref">llvm/ADT/StringRef.h</a>
   1245 </h4>
   1246 
   1247 <div>
   1248 <p>
   1249 The StringRef class is a simple value class that contains a pointer to a
   1250 character and a length, and is quite related to the <a 
   1251 href="#dss_arrayref">ArrayRef</a> class (but specialized for arrays of
   1252 characters).  Because StringRef carries a length with it, it safely handles
   1253 strings with embedded nul characters in it, getting the length does not require
   1254 a strlen call, and it even has very convenient APIs for slicing and dicing the
   1255 character range that it represents.
   1256 </p>
   1257   
   1258 <p>
   1259 StringRef is ideal for passing simple strings around that are known to be live,
   1260 either because they are C string literals, std::string, a C array, or a
   1261 SmallVector.  Each of these cases has an efficient implicit conversion to
   1262 StringRef, which doesn't result in a dynamic strlen being executed.
   1263 </p>
   1264   
   1265 <p>StringRef has a few major limitations which make more powerful string
   1266 containers useful:</p>
   1267   
   1268 <ol>
   1269 <li>You cannot directly convert a StringRef to a 'const char*' because there is
   1270 no way to add a trailing nul (unlike the .c_str() method on various stronger
   1271 classes).</li>
   1272 
   1273   
   1274 <li>StringRef doesn't own or keep alive the underlying string bytes.
   1275 As such it can easily lead to dangling pointers, and is not suitable for
   1276 embedding in datastructures in most cases (instead, use an std::string or
   1277 something like that).</li>
   1278   
   1279 <li>For the same reason, StringRef cannot be used as the return value of a
   1280 method if the method "computes" the result string.  Instead, use
   1281 std::string.</li>
   1282     
   1283 <li>StringRef's do not allow you to mutate the pointed-to string bytes and it
   1284 doesn't allow you to insert or remove bytes from the range.  For editing 
   1285 operations like this, it interoperates with the <a 
   1286 href="#dss_twine">Twine</a> class.</li>
   1287 </ol>
   1288   
   1289 <p>Because of its strengths and limitations, it is very common for a function to
   1290 take a StringRef and for a method on an object to return a StringRef that
   1291 points into some string that it owns.</p>
   1292   
   1293 </div>
   1294   
   1295 <!-- _______________________________________________________________________ -->
   1296 <h4>
   1297   <a name="dss_twine">llvm/ADT/Twine.h</a>
   1298 </h4>
   1299 
   1300 <div>
   1301   <p>
   1302   The Twine class is used as an intermediary datatype for APIs that want to take
   1303   a string that can be constructed inline with a series of concatenations.
   1304   Twine works by forming recursive instances of the Twine datatype (a simple
   1305   value object) on the stack as temporary objects, linking them together into a
   1306   tree which is then linearized when the Twine is consumed.  Twine is only safe
   1307   to use as the argument to a function, and should always be a const reference,
   1308   e.g.:
   1309   </p>
   1310   
   1311   <pre>
   1312     void foo(const Twine &amp;T);
   1313     ...
   1314     StringRef X = ...
   1315     unsigned i = ...
   1316     foo(X + "." + Twine(i));
   1317   </pre>
   1318   
   1319   <p>This example forms a string like "blarg.42" by concatenating the values
   1320   together, and does not form intermediate strings containing "blarg" or
   1321   "blarg.".
   1322   </p>
   1323   
   1324   <p>Because Twine is constructed with temporary objects on the stack, and
   1325   because these instances are destroyed at the end of the current statement,
   1326   it is an inherently dangerous API.  For example, this simple variant contains
   1327   undefined behavior and will probably crash:</p>
   1328   
   1329   <pre>
   1330     void foo(const Twine &amp;T);
   1331     ...
   1332     StringRef X = ...
   1333     unsigned i = ...
   1334     const Twine &amp;Tmp = X + "." + Twine(i);
   1335     foo(Tmp);
   1336   </pre>
   1337 
   1338   <p>... because the temporaries are destroyed before the call.  That said,
   1339   Twine's are much more efficient than intermediate std::string temporaries, and
   1340   they work really well with StringRef.  Just be aware of their limitations.</p>
   1341   
   1342 </div>
   1343 
   1344   
   1345 <!-- _______________________________________________________________________ -->
   1346 <h4>
   1347   <a name="dss_smallstring">llvm/ADT/SmallString.h</a>
   1348 </h4>
   1349 
   1350 <div>
   1351   
   1352 <p>SmallString is a subclass of <a href="#dss_smallvector">SmallVector</a> that
   1353 adds some convenience APIs like += that takes StringRef's.  SmallString avoids
   1354 allocating memory in the case when the preallocated space is enough to hold its
   1355 data, and it calls back to general heap allocation when required.  Since it owns
   1356 its data, it is very safe to use and supports full mutation of the string.</p>
   1357   
   1358 <p>Like SmallVector's, the big downside to SmallString is their sizeof.  While
   1359 they are optimized for small strings, they themselves are not particularly
   1360 small.  This means that they work great for temporary scratch buffers on the
   1361 stack, but should not generally be put into the heap: it is very rare to 
   1362 see a SmallString as the member of a frequently-allocated heap data structure
   1363 or returned by-value.
   1364 </p>
   1365 
   1366 </div>
   1367   
   1368 <!-- _______________________________________________________________________ -->
   1369 <h4>
   1370   <a name="dss_stdstring">std::string</a>
   1371 </h4>
   1372 
   1373 <div>
   1374   
   1375   <p>The standard C++ std::string class is a very general class that (like
   1376   SmallString) owns its underlying data.  sizeof(std::string) is very reasonable
   1377   so it can be embedded into heap data structures and returned by-value.
   1378   On the other hand, std::string is highly inefficient for inline editing (e.g.
   1379   concatenating a bunch of stuff together) and because it is provided by the
   1380   standard library, its performance characteristics depend a lot of the host
   1381   standard library (e.g. libc++ and MSVC provide a highly optimized string
   1382   class, GCC contains a really slow implementation).
   1383   </p>
   1384 
   1385   <p>The major disadvantage of std::string is that almost every operation that
   1386   makes them larger can allocate memory, which is slow.  As such, it is better
   1387   to use SmallVector or Twine as a scratch buffer, but then use std::string to
   1388   persist the result.</p>
   1389 
   1390   
   1391 </div>
   1392   
   1393 <!-- end of strings -->
   1394 </div>
   1395 
   1396   
   1397 <!-- ======================================================================= -->
   1398 <h3>
   1399   <a name="ds_set">Set-Like Containers (std::set, SmallSet, SetVector, etc)</a>
   1400 </h3>
   1401 
   1402 <div>
   1403 
   1404 <p>Set-like containers are useful when you need to canonicalize multiple values
   1405 into a single representation.  There are several different choices for how to do
   1406 this, providing various trade-offs.</p>
   1407 
   1408 <!-- _______________________________________________________________________ -->
   1409 <h4>
   1410   <a name="dss_sortedvectorset">A sorted 'vector'</a>
   1411 </h4>
   1412 
   1413 <div>
   1414 
   1415 <p>If you intend to insert a lot of elements, then do a lot of queries, a
   1416 great approach is to use a vector (or other sequential container) with
   1417 std::sort+std::unique to remove duplicates.  This approach works really well if
   1418 your usage pattern has these two distinct phases (insert then query), and can be
   1419 coupled with a good choice of <a href="#ds_sequential">sequential container</a>.
   1420 </p>
   1421 
   1422 <p>
   1423 This combination provides the several nice properties: the result data is
   1424 contiguous in memory (good for cache locality), has few allocations, is easy to
   1425 address (iterators in the final vector are just indices or pointers), and can be
   1426 efficiently queried with a standard binary or radix search.</p>
   1427 
   1428 </div>
   1429 
   1430 <!-- _______________________________________________________________________ -->
   1431 <h4>
   1432   <a name="dss_smallset">"llvm/ADT/SmallSet.h"</a>
   1433 </h4>
   1434 
   1435 <div>
   1436 
   1437 <p>If you have a set-like data structure that is usually small and whose elements
   1438 are reasonably small, a <tt>SmallSet&lt;Type, N&gt;</tt> is a good choice.  This set
   1439 has space for N elements in place (thus, if the set is dynamically smaller than
   1440 N, no malloc traffic is required) and accesses them with a simple linear search.
   1441 When the set grows beyond 'N' elements, it allocates a more expensive representation that
   1442 guarantees efficient access (for most types, it falls back to std::set, but for
   1443 pointers it uses something far better, <a
   1444 href="#dss_smallptrset">SmallPtrSet</a>).</p>
   1445 
   1446 <p>The magic of this class is that it handles small sets extremely efficiently,
   1447 but gracefully handles extremely large sets without loss of efficiency.  The
   1448 drawback is that the interface is quite small: it supports insertion, queries
   1449 and erasing, but does not support iteration.</p>
   1450 
   1451 </div>
   1452 
   1453 <!-- _______________________________________________________________________ -->
   1454 <h4>
   1455   <a name="dss_smallptrset">"llvm/ADT/SmallPtrSet.h"</a>
   1456 </h4>
   1457 
   1458 <div>
   1459 
   1460 <p>SmallPtrSet has all the advantages of <tt>SmallSet</tt> (and a <tt>SmallSet</tt> of pointers is 
   1461 transparently implemented with a <tt>SmallPtrSet</tt>), but also supports iterators.  If
   1462 more than 'N' insertions are performed, a single quadratically
   1463 probed hash table is allocated and grows as needed, providing extremely
   1464 efficient access (constant time insertion/deleting/queries with low constant
   1465 factors) and is very stingy with malloc traffic.</p>
   1466 
   1467 <p>Note that, unlike <tt>std::set</tt>, the iterators of <tt>SmallPtrSet</tt> are invalidated
   1468 whenever an insertion occurs.  Also, the values visited by the iterators are not
   1469 visited in sorted order.</p>
   1470 
   1471 </div>
   1472 
   1473 <!-- _______________________________________________________________________ -->
   1474 <h4>
   1475   <a name="dss_denseset">"llvm/ADT/DenseSet.h"</a>
   1476 </h4>
   1477 
   1478 <div>
   1479 
   1480 <p>
   1481 DenseSet is a simple quadratically probed hash table.  It excels at supporting
   1482 small values: it uses a single allocation to hold all of the pairs that
   1483 are currently inserted in the set.  DenseSet is a great way to unique small
   1484 values that are not simple pointers (use <a 
   1485 href="#dss_smallptrset">SmallPtrSet</a> for pointers).  Note that DenseSet has
   1486 the same requirements for the value type that <a 
   1487 href="#dss_densemap">DenseMap</a> has.
   1488 </p>
   1489 
   1490 </div>
   1491 
   1492 <!-- _______________________________________________________________________ -->
   1493 <h4>
   1494   <a name="dss_sparseset">"llvm/ADT/SparseSet.h"</a>
   1495 </h4>
   1496 
   1497 <div>
   1498 
   1499 <p>SparseSet holds a small number of objects identified by unsigned keys of
   1500 moderate size. It uses a lot of memory, but provides operations that are
   1501 almost as fast as a vector. Typical keys are physical registers, virtual
   1502 registers, or numbered basic blocks.</p>
   1503 
   1504 <p>SparseSet is useful for algorithms that need very fast clear/find/insert/erase
   1505 and fast iteration over small sets.  It is not intended for building composite
   1506 data structures.</p>
   1507 
   1508 </div>
   1509 
   1510 <!-- _______________________________________________________________________ -->
   1511 <h4>
   1512   <a name="dss_FoldingSet">"llvm/ADT/FoldingSet.h"</a>
   1513 </h4>
   1514 
   1515 <div>
   1516 
   1517 <p>
   1518 FoldingSet is an aggregate class that is really good at uniquing
   1519 expensive-to-create or polymorphic objects.  It is a combination of a chained
   1520 hash table with intrusive links (uniqued objects are required to inherit from
   1521 FoldingSetNode) that uses <a href="#dss_smallvector">SmallVector</a> as part of
   1522 its ID process.</p>
   1523 
   1524 <p>Consider a case where you want to implement a "getOrCreateFoo" method for
   1525 a complex object (for example, a node in the code generator).  The client has a
   1526 description of *what* it wants to generate (it knows the opcode and all the
   1527 operands), but we don't want to 'new' a node, then try inserting it into a set
   1528 only to find out it already exists, at which point we would have to delete it
   1529 and return the node that already exists.
   1530 </p>
   1531 
   1532 <p>To support this style of client, FoldingSet perform a query with a
   1533 FoldingSetNodeID (which wraps SmallVector) that can be used to describe the
   1534 element that we want to query for.  The query either returns the element
   1535 matching the ID or it returns an opaque ID that indicates where insertion should
   1536 take place.  Construction of the ID usually does not require heap traffic.</p>
   1537 
   1538 <p>Because FoldingSet uses intrusive links, it can support polymorphic objects
   1539 in the set (for example, you can have SDNode instances mixed with LoadSDNodes).
   1540 Because the elements are individually allocated, pointers to the elements are
   1541 stable: inserting or removing elements does not invalidate any pointers to other
   1542 elements.
   1543 </p>
   1544 
   1545 </div>
   1546 
   1547 <!-- _______________________________________________________________________ -->
   1548 <h4>
   1549   <a name="dss_set">&lt;set&gt;</a>
   1550 </h4>
   1551 
   1552 <div>
   1553 
   1554 <p><tt>std::set</tt> is a reasonable all-around set class, which is decent at
   1555 many things but great at nothing.  std::set allocates memory for each element
   1556 inserted (thus it is very malloc intensive) and typically stores three pointers
   1557 per element in the set (thus adding a large amount of per-element space
   1558 overhead).  It offers guaranteed log(n) performance, which is not particularly
   1559 fast from a complexity standpoint (particularly if the elements of the set are
   1560 expensive to compare, like strings), and has extremely high constant factors for
   1561 lookup, insertion and removal.</p>
   1562 
   1563 <p>The advantages of std::set are that its iterators are stable (deleting or
   1564 inserting an element from the set does not affect iterators or pointers to other
   1565 elements) and that iteration over the set is guaranteed to be in sorted order.
   1566 If the elements in the set are large, then the relative overhead of the pointers
   1567 and malloc traffic is not a big deal, but if the elements of the set are small,
   1568 std::set is almost never a good choice.</p>
   1569 
   1570 </div>
   1571 
   1572 <!-- _______________________________________________________________________ -->
   1573 <h4>
   1574   <a name="dss_setvector">"llvm/ADT/SetVector.h"</a>
   1575 </h4>
   1576 
   1577 <div>
   1578 <p>LLVM's SetVector&lt;Type&gt; is an adapter class that combines your choice of
   1579 a set-like container along with a <a href="#ds_sequential">Sequential 
   1580 Container</a>.  The important property
   1581 that this provides is efficient insertion with uniquing (duplicate elements are
   1582 ignored) with iteration support.  It implements this by inserting elements into
   1583 both a set-like container and the sequential container, using the set-like
   1584 container for uniquing and the sequential container for iteration.
   1585 </p>
   1586 
   1587 <p>The difference between SetVector and other sets is that the order of
   1588 iteration is guaranteed to match the order of insertion into the SetVector.
   1589 This property is really important for things like sets of pointers.  Because
   1590 pointer values are non-deterministic (e.g. vary across runs of the program on
   1591 different machines), iterating over the pointers in the set will
   1592 not be in a well-defined order.</p>
   1593 
   1594 <p>
   1595 The drawback of SetVector is that it requires twice as much space as a normal
   1596 set and has the sum of constant factors from the set-like container and the 
   1597 sequential container that it uses.  Use it *only* if you need to iterate over 
   1598 the elements in a deterministic order.  SetVector is also expensive to delete
   1599 elements out of (linear time), unless you use it's "pop_back" method, which is
   1600 faster.
   1601 </p>
   1602 
   1603 <p><tt>SetVector</tt> is an adapter class that defaults to
   1604    using <tt>std::vector</tt> and a size 16 <tt>SmallSet</tt> for the underlying
   1605    containers, so it is quite expensive. However,
   1606    <tt>"llvm/ADT/SetVector.h"</tt> also provides a <tt>SmallSetVector</tt>
   1607    class, which defaults to using a <tt>SmallVector</tt> and <tt>SmallSet</tt>
   1608    of a specified size. If you use this, and if your sets are dynamically
   1609    smaller than <tt>N</tt>, you will save a lot of heap traffic.</p>
   1610 
   1611 </div>
   1612 
   1613 <!-- _______________________________________________________________________ -->
   1614 <h4>
   1615   <a name="dss_uniquevector">"llvm/ADT/UniqueVector.h"</a>
   1616 </h4>
   1617 
   1618 <div>
   1619 
   1620 <p>
   1621 UniqueVector is similar to <a href="#dss_setvector">SetVector</a>, but it
   1622 retains a unique ID for each element inserted into the set.  It internally
   1623 contains a map and a vector, and it assigns a unique ID for each value inserted
   1624 into the set.</p>
   1625 
   1626 <p>UniqueVector is very expensive: its cost is the sum of the cost of
   1627 maintaining both the map and vector, it has high complexity, high constant
   1628 factors, and produces a lot of malloc traffic.  It should be avoided.</p>
   1629 
   1630 </div>
   1631 
   1632 <!-- _______________________________________________________________________ -->
   1633 <h4>
   1634   <a name="dss_immutableset">"llvm/ADT/ImmutableSet.h"</a>
   1635 </h4>
   1636 
   1637 <div>
   1638 
   1639 <p>
   1640 ImmutableSet is an immutable (functional) set implementation based on an AVL
   1641 tree.
   1642 Adding or removing elements is done through a Factory object and results in the
   1643 creation of a new ImmutableSet object.
   1644 If an ImmutableSet already exists with the given contents, then the existing one
   1645 is returned; equality is compared with a FoldingSetNodeID.
   1646 The time and space complexity of add or remove operations is logarithmic in the
   1647 size of the original set.
   1648 
   1649 <p>
   1650 There is no method for returning an element of the set, you can only check for
   1651 membership.
   1652 
   1653 </div>
   1654 
   1655 
   1656 <!-- _______________________________________________________________________ -->
   1657 <h4>
   1658   <a name="dss_otherset">Other Set-Like Container Options</a>
   1659 </h4>
   1660 
   1661 <div>
   1662 
   1663 <p>
   1664 The STL provides several other options, such as std::multiset and the various 
   1665 "hash_set" like containers (whether from C++ TR1 or from the SGI library). We
   1666 never use hash_set and unordered_set because they are generally very expensive 
   1667 (each insertion requires a malloc) and very non-portable.
   1668 </p>
   1669 
   1670 <p>std::multiset is useful if you're not interested in elimination of
   1671 duplicates, but has all the drawbacks of std::set.  A sorted vector (where you 
   1672 don't delete duplicate entries) or some other approach is almost always
   1673 better.</p>
   1674 
   1675 </div>
   1676 
   1677 </div>
   1678 
   1679 <!-- ======================================================================= -->
   1680 <h3>
   1681   <a name="ds_map">Map-Like Containers (std::map, DenseMap, etc)</a>
   1682 </h3>
   1683 
   1684 <div>
   1685 Map-like containers are useful when you want to associate data to a key.  As
   1686 usual, there are a lot of different ways to do this. :)
   1687 
   1688 <!-- _______________________________________________________________________ -->
   1689 <h4>
   1690   <a name="dss_sortedvectormap">A sorted 'vector'</a>
   1691 </h4>
   1692 
   1693 <div>
   1694 
   1695 <p>
   1696 If your usage pattern follows a strict insert-then-query approach, you can
   1697 trivially use the same approach as <a href="#dss_sortedvectorset">sorted vectors
   1698 for set-like containers</a>.  The only difference is that your query function
   1699 (which uses std::lower_bound to get efficient log(n) lookup) should only compare
   1700 the key, not both the key and value.  This yields the same advantages as sorted
   1701 vectors for sets.
   1702 </p>
   1703 </div>
   1704 
   1705 <!-- _______________________________________________________________________ -->
   1706 <h4>
   1707   <a name="dss_stringmap">"llvm/ADT/StringMap.h"</a>
   1708 </h4>
   1709 
   1710 <div>
   1711 
   1712 <p>
   1713 Strings are commonly used as keys in maps, and they are difficult to support
   1714 efficiently: they are variable length, inefficient to hash and compare when
   1715 long, expensive to copy, etc.  StringMap is a specialized container designed to
   1716 cope with these issues.  It supports mapping an arbitrary range of bytes to an
   1717 arbitrary other object.</p>
   1718 
   1719 <p>The StringMap implementation uses a quadratically-probed hash table, where
   1720 the buckets store a pointer to the heap allocated entries (and some other
   1721 stuff).  The entries in the map must be heap allocated because the strings are
   1722 variable length.  The string data (key) and the element object (value) are
   1723 stored in the same allocation with the string data immediately after the element
   1724 object.  This container guarantees the "<tt>(char*)(&amp;Value+1)</tt>" points
   1725 to the key string for a value.</p>
   1726 
   1727 <p>The StringMap is very fast for several reasons: quadratic probing is very
   1728 cache efficient for lookups, the hash value of strings in buckets is not
   1729 recomputed when looking up an element, StringMap rarely has to touch the
   1730 memory for unrelated objects when looking up a value (even when hash collisions
   1731 happen), hash table growth does not recompute the hash values for strings
   1732 already in the table, and each pair in the map is store in a single allocation
   1733 (the string data is stored in the same allocation as the Value of a pair).</p>
   1734 
   1735 <p>StringMap also provides query methods that take byte ranges, so it only ever
   1736 copies a string if a value is inserted into the table.</p>
   1737 
   1738 <p>StringMap iteratation order, however, is not guaranteed to be deterministic,
   1739 so any uses which require that should instead use a std::map.</p>
   1740 </div>
   1741 
   1742 <!-- _______________________________________________________________________ -->
   1743 <h4>
   1744   <a name="dss_indexedmap">"llvm/ADT/IndexedMap.h"</a>
   1745 </h4>
   1746 
   1747 <div>
   1748 <p>
   1749 IndexedMap is a specialized container for mapping small dense integers (or
   1750 values that can be mapped to small dense integers) to some other type.  It is
   1751 internally implemented as a vector with a mapping function that maps the keys to
   1752 the dense integer range.
   1753 </p>
   1754 
   1755 <p>
   1756 This is useful for cases like virtual registers in the LLVM code generator: they
   1757 have a dense mapping that is offset by a compile-time constant (the first
   1758 virtual register ID).</p>
   1759 
   1760 </div>
   1761 
   1762 <!-- _______________________________________________________________________ -->
   1763 <h4>
   1764   <a name="dss_densemap">"llvm/ADT/DenseMap.h"</a>
   1765 </h4>
   1766 
   1767 <div>
   1768 
   1769 <p>
   1770 DenseMap is a simple quadratically probed hash table.  It excels at supporting
   1771 small keys and values: it uses a single allocation to hold all of the pairs that
   1772 are currently inserted in the map.  DenseMap is a great way to map pointers to
   1773 pointers, or map other small types to each other.
   1774 </p>
   1775 
   1776 <p>
   1777 There are several aspects of DenseMap that you should be aware of, however.  The
   1778 iterators in a DenseMap are invalidated whenever an insertion occurs, unlike
   1779 map.  Also, because DenseMap allocates space for a large number of key/value
   1780 pairs (it starts with 64 by default), it will waste a lot of space if your keys
   1781 or values are large.  Finally, you must implement a partial specialization of
   1782 DenseMapInfo for the key that you want, if it isn't already supported.  This
   1783 is required to tell DenseMap about two special marker values (which can never be
   1784 inserted into the map) that it needs internally.</p>
   1785 
   1786 <p>
   1787 DenseMap's find_as() method supports lookup operations using an alternate key
   1788 type. This is useful in cases where the normal key type is expensive to
   1789 construct, but cheap to compare against. The DenseMapInfo is responsible for
   1790 defining the appropriate comparison and hashing methods for each alternate
   1791 key type used.
   1792 </p>
   1793 
   1794 </div>
   1795 
   1796 <!-- _______________________________________________________________________ -->
   1797 <h4>
   1798   <a name="dss_valuemap">"llvm/ADT/ValueMap.h"</a>
   1799 </h4>
   1800 
   1801 <div>
   1802 
   1803 <p>
   1804 ValueMap is a wrapper around a <a href="#dss_densemap">DenseMap</a> mapping
   1805 Value*s (or subclasses) to another type.  When a Value is deleted or RAUW'ed,
   1806 ValueMap will update itself so the new version of the key is mapped to the same
   1807 value, just as if the key were a WeakVH.  You can configure exactly how this
   1808 happens, and what else happens on these two events, by passing
   1809 a <code>Config</code> parameter to the ValueMap template.</p>
   1810 
   1811 </div>
   1812 
   1813 <!-- _______________________________________________________________________ -->
   1814 <h4>
   1815   <a name="dss_intervalmap">"llvm/ADT/IntervalMap.h"</a>
   1816 </h4>
   1817 
   1818 <div>
   1819 
   1820 <p> IntervalMap is a compact map for small keys and values. It maps key
   1821 intervals instead of single keys, and it will automatically coalesce adjacent
   1822 intervals. When then map only contains a few intervals, they are stored in the
   1823 map object itself to avoid allocations.</p>
   1824 
   1825 <p> The IntervalMap iterators are quite big, so they should not be passed around
   1826 as STL iterators. The heavyweight iterators allow a smaller data structure.</p>
   1827 
   1828 </div>
   1829 
   1830 <!-- _______________________________________________________________________ -->
   1831 <h4>
   1832   <a name="dss_map">&lt;map&gt;</a>
   1833 </h4>
   1834 
   1835 <div>
   1836 
   1837 <p>
   1838 std::map has similar characteristics to <a href="#dss_set">std::set</a>: it uses
   1839 a single allocation per pair inserted into the map, it offers log(n) lookup with
   1840 an extremely large constant factor, imposes a space penalty of 3 pointers per
   1841 pair in the map, etc.</p>
   1842 
   1843 <p>std::map is most useful when your keys or values are very large, if you need
   1844 to iterate over the collection in sorted order, or if you need stable iterators
   1845 into the map (i.e. they don't get invalidated if an insertion or deletion of
   1846 another element takes place).</p>
   1847 
   1848 </div>
   1849 
   1850 <!-- _______________________________________________________________________ -->
   1851 <h4>
   1852   <a name="dss_inteqclasses">"llvm/ADT/IntEqClasses.h"</a>
   1853 </h4>
   1854 
   1855 <div>
   1856 
   1857 <p>IntEqClasses provides a compact representation of equivalence classes of
   1858 small integers. Initially, each integer in the range 0..n-1 has its own
   1859 equivalence class. Classes can be joined by passing two class representatives to
   1860 the join(a, b) method. Two integers are in the same class when findLeader()
   1861 returns the same representative.</p>
   1862 
   1863 <p>Once all equivalence classes are formed, the map can be compressed so each
   1864 integer 0..n-1 maps to an equivalence class number in the range 0..m-1, where m
   1865 is the total number of equivalence classes. The map must be uncompressed before
   1866 it can be edited again.</p>
   1867 
   1868 </div>
   1869 
   1870 <!-- _______________________________________________________________________ -->
   1871 <h4>
   1872   <a name="dss_immutablemap">"llvm/ADT/ImmutableMap.h"</a>
   1873 </h4>
   1874 
   1875 <div>
   1876 
   1877 <p>
   1878 ImmutableMap is an immutable (functional) map implementation based on an AVL
   1879 tree.
   1880 Adding or removing elements is done through a Factory object and results in the
   1881 creation of a new ImmutableMap object.
   1882 If an ImmutableMap already exists with the given key set, then the existing one
   1883 is returned; equality is compared with a FoldingSetNodeID.
   1884 The time and space complexity of add or remove operations is logarithmic in the
   1885 size of the original map.
   1886 
   1887 </div>
   1888 
   1889 <!-- _______________________________________________________________________ -->
   1890 <h4>
   1891   <a name="dss_othermap">Other Map-Like Container Options</a>
   1892 </h4>
   1893 
   1894 <div>
   1895 
   1896 <p>
   1897 The STL provides several other options, such as std::multimap and the various 
   1898 "hash_map" like containers (whether from C++ TR1 or from the SGI library). We
   1899 never use hash_set and unordered_set because they are generally very expensive 
   1900 (each insertion requires a malloc) and very non-portable.</p>
   1901 
   1902 <p>std::multimap is useful if you want to map a key to multiple values, but has
   1903 all the drawbacks of std::map.  A sorted vector or some other approach is almost
   1904 always better.</p>
   1905 
   1906 </div>
   1907 
   1908 </div>
   1909 
   1910 <!-- ======================================================================= -->
   1911 <h3>
   1912   <a name="ds_bit">Bit storage containers (BitVector, SparseBitVector)</a>
   1913 </h3>
   1914 
   1915 <div>
   1916 <p>Unlike the other containers, there are only two bit storage containers, and 
   1917 choosing when to use each is relatively straightforward.</p>
   1918 
   1919 <p>One additional option is 
   1920 <tt>std::vector&lt;bool&gt;</tt>: we discourage its use for two reasons 1) the
   1921 implementation in many common compilers (e.g. commonly available versions of 
   1922 GCC) is extremely inefficient and 2) the C++ standards committee is likely to
   1923 deprecate this container and/or change it significantly somehow.  In any case,
   1924 please don't use it.</p>
   1925 
   1926 <!-- _______________________________________________________________________ -->
   1927 <h4>
   1928   <a name="dss_bitvector">BitVector</a>
   1929 </h4>
   1930 
   1931 <div>
   1932 <p> The BitVector container provides a dynamic size set of bits for manipulation.
   1933 It supports individual bit setting/testing, as well as set operations.  The set
   1934 operations take time O(size of bitvector), but operations are performed one word
   1935 at a time, instead of one bit at a time.  This makes the BitVector very fast for
   1936 set operations compared to other containers.  Use the BitVector when you expect
   1937 the number of set bits to be high (IE a dense set).
   1938 </p>
   1939 </div>
   1940 
   1941 <!-- _______________________________________________________________________ -->
   1942 <h4>
   1943   <a name="dss_smallbitvector">SmallBitVector</a>
   1944 </h4>
   1945 
   1946 <div>
   1947 <p> The SmallBitVector container provides the same interface as BitVector, but
   1948 it is optimized for the case where only a small number of bits, less than
   1949 25 or so, are needed. It also transparently supports larger bit counts, but
   1950 slightly less efficiently than a plain BitVector, so SmallBitVector should
   1951 only be used when larger counts are rare.
   1952 </p>
   1953 
   1954 <p>
   1955 At this time, SmallBitVector does not support set operations (and, or, xor),
   1956 and its operator[] does not provide an assignable lvalue.
   1957 </p>
   1958 </div>
   1959 
   1960 <!-- _______________________________________________________________________ -->
   1961 <h4>
   1962   <a name="dss_sparsebitvector">SparseBitVector</a>
   1963 </h4>
   1964 
   1965 <div>
   1966 <p> The SparseBitVector container is much like BitVector, with one major
   1967 difference: Only the bits that are set, are stored.  This makes the
   1968 SparseBitVector much more space efficient than BitVector when the set is sparse,
   1969 as well as making set operations O(number of set bits) instead of O(size of
   1970 universe).  The downside to the SparseBitVector is that setting and testing of random bits is O(N), and on large SparseBitVectors, this can be slower than BitVector. In our implementation, setting or testing bits in sorted order
   1971 (either forwards or reverse) is O(1) worst case.  Testing and setting bits within 128 bits (depends on size) of the current bit is also O(1).  As a general statement, testing/setting bits in a SparseBitVector is O(distance away from last set bit).
   1972 </p>
   1973 </div>
   1974 
   1975 </div>
   1976 
   1977 </div>
   1978 
   1979 <!-- *********************************************************************** -->
   1980 <h2>
   1981   <a name="common">Helpful Hints for Common Operations</a>
   1982 </h2>
   1983 <!-- *********************************************************************** -->
   1984 
   1985 <div>
   1986 
   1987 <p>This section describes how to perform some very simple transformations of
   1988 LLVM code.  This is meant to give examples of common idioms used, showing the
   1989 practical side of LLVM transformations.  <p> Because this is a "how-to" section,
   1990 you should also read about the main classes that you will be working with.  The
   1991 <a href="#coreclasses">Core LLVM Class Hierarchy Reference</a> contains details
   1992 and descriptions of the main classes that you should know about.</p>
   1993 
   1994 <!-- NOTE: this section should be heavy on example code -->
   1995 <!-- ======================================================================= -->
   1996 <h3>
   1997   <a name="inspection">Basic Inspection and Traversal Routines</a>
   1998 </h3>
   1999 
   2000 <div>
   2001 
   2002 <p>The LLVM compiler infrastructure have many different data structures that may
   2003 be traversed.  Following the example of the C++ standard template library, the
   2004 techniques used to traverse these various data structures are all basically the
   2005 same.  For a enumerable sequence of values, the <tt>XXXbegin()</tt> function (or
   2006 method) returns an iterator to the start of the sequence, the <tt>XXXend()</tt>
   2007 function returns an iterator pointing to one past the last valid element of the
   2008 sequence, and there is some <tt>XXXiterator</tt> data type that is common
   2009 between the two operations.</p>
   2010 
   2011 <p>Because the pattern for iteration is common across many different aspects of
   2012 the program representation, the standard template library algorithms may be used
   2013 on them, and it is easier to remember how to iterate. First we show a few common
   2014 examples of the data structures that need to be traversed.  Other data
   2015 structures are traversed in very similar ways.</p>
   2016 
   2017 <!-- _______________________________________________________________________ -->
   2018 <h4>
   2019   <a name="iterate_function">Iterating over the </a><a
   2020   href="#BasicBlock"><tt>BasicBlock</tt></a>s in a <a
   2021   href="#Function"><tt>Function</tt></a>
   2022 </h4>
   2023 
   2024 <div>
   2025 
   2026 <p>It's quite common to have a <tt>Function</tt> instance that you'd like to
   2027 transform in some way; in particular, you'd like to manipulate its
   2028 <tt>BasicBlock</tt>s.  To facilitate this, you'll need to iterate over all of
   2029 the <tt>BasicBlock</tt>s that constitute the <tt>Function</tt>. The following is
   2030 an example that prints the name of a <tt>BasicBlock</tt> and the number of
   2031 <tt>Instruction</tt>s it contains:</p>
   2032 
   2033 <div class="doc_code">
   2034 <pre>
   2035 // <i>func is a pointer to a Function instance</i>
   2036 for (Function::iterator i = func-&gt;begin(), e = func-&gt;end(); i != e; ++i)
   2037   // <i>Print out the name of the basic block if it has one, and then the</i>
   2038   // <i>number of instructions that it contains</i>
   2039   errs() &lt;&lt; "Basic block (name=" &lt;&lt; i-&gt;getName() &lt;&lt; ") has "
   2040              &lt;&lt; i-&gt;size() &lt;&lt; " instructions.\n";
   2041 </pre>
   2042 </div>
   2043 
   2044 <p>Note that i can be used as if it were a pointer for the purposes of
   2045 invoking member functions of the <tt>Instruction</tt> class.  This is
   2046 because the indirection operator is overloaded for the iterator
   2047 classes.  In the above code, the expression <tt>i-&gt;size()</tt> is
   2048 exactly equivalent to <tt>(*i).size()</tt> just like you'd expect.</p>
   2049 
   2050 </div>
   2051 
   2052 <!-- _______________________________________________________________________ -->
   2053 <h4>
   2054   <a name="iterate_basicblock">Iterating over the </a><a
   2055   href="#Instruction"><tt>Instruction</tt></a>s in a <a
   2056   href="#BasicBlock"><tt>BasicBlock</tt></a>
   2057 </h4>
   2058 
   2059 <div>
   2060 
   2061 <p>Just like when dealing with <tt>BasicBlock</tt>s in <tt>Function</tt>s, it's
   2062 easy to iterate over the individual instructions that make up
   2063 <tt>BasicBlock</tt>s. Here's a code snippet that prints out each instruction in
   2064 a <tt>BasicBlock</tt>:</p>
   2065 
   2066 <div class="doc_code">
   2067 <pre>
   2068 // <i>blk is a pointer to a BasicBlock instance</i>
   2069 for (BasicBlock::iterator i = blk-&gt;begin(), e = blk-&gt;end(); i != e; ++i)
   2070    // <i>The next statement works since operator&lt;&lt;(ostream&amp;,...)</i>
   2071    // <i>is overloaded for Instruction&amp;</i>
   2072    errs() &lt;&lt; *i &lt;&lt; "\n";
   2073 </pre>
   2074 </div>
   2075 
   2076 <p>However, this isn't really the best way to print out the contents of a
   2077 <tt>BasicBlock</tt>!  Since the ostream operators are overloaded for virtually
   2078 anything you'll care about, you could have just invoked the print routine on the
   2079 basic block itself: <tt>errs() &lt;&lt; *blk &lt;&lt; "\n";</tt>.</p>
   2080 
   2081 </div>
   2082 
   2083 <!-- _______________________________________________________________________ -->
   2084 <h4>
   2085   <a name="iterate_institer">Iterating over the </a><a
   2086   href="#Instruction"><tt>Instruction</tt></a>s in a <a
   2087   href="#Function"><tt>Function</tt></a>
   2088 </h4>
   2089 
   2090 <div>
   2091 
   2092 <p>If you're finding that you commonly iterate over a <tt>Function</tt>'s
   2093 <tt>BasicBlock</tt>s and then that <tt>BasicBlock</tt>'s <tt>Instruction</tt>s,
   2094 <tt>InstIterator</tt> should be used instead. You'll need to include <a
   2095 href="/doxygen/InstIterator_8h-source.html"><tt>llvm/Support/InstIterator.h</tt></a>,
   2096 and then instantiate <tt>InstIterator</tt>s explicitly in your code.  Here's a
   2097 small example that shows how to dump all instructions in a function to the standard error stream:<p>
   2098 
   2099 <div class="doc_code">
   2100 <pre>
   2101 #include "<a href="/doxygen/InstIterator_8h-source.html">llvm/Support/InstIterator.h</a>"
   2102 
   2103 // <i>F is a pointer to a Function instance</i>
   2104 for (inst_iterator I = inst_begin(F), E = inst_end(F); I != E; ++I)
   2105   errs() &lt;&lt; *I &lt;&lt; "\n";
   2106 </pre>
   2107 </div>
   2108 
   2109 <p>Easy, isn't it?  You can also use <tt>InstIterator</tt>s to fill a
   2110 work list with its initial contents.  For example, if you wanted to
   2111 initialize a work list to contain all instructions in a <tt>Function</tt>
   2112 F, all you would need to do is something like:</p>
   2113 
   2114 <div class="doc_code">
   2115 <pre>
   2116 std::set&lt;Instruction*&gt; worklist;
   2117 // or better yet, SmallPtrSet&lt;Instruction*, 64&gt; worklist;
   2118 
   2119 for (inst_iterator I = inst_begin(F), E = inst_end(F); I != E; ++I)
   2120    worklist.insert(&amp;*I);
   2121 </pre>
   2122 </div>
   2123 
   2124 <p>The STL set <tt>worklist</tt> would now contain all instructions in the
   2125 <tt>Function</tt> pointed to by F.</p>
   2126 
   2127 </div>
   2128 
   2129 <!-- _______________________________________________________________________ -->
   2130 <h4>
   2131   <a name="iterate_convert">Turning an iterator into a class pointer (and
   2132   vice-versa)</a>
   2133 </h4>
   2134 
   2135 <div>
   2136 
   2137 <p>Sometimes, it'll be useful to grab a reference (or pointer) to a class
   2138 instance when all you've got at hand is an iterator.  Well, extracting
   2139 a reference or a pointer from an iterator is very straight-forward.
   2140 Assuming that <tt>i</tt> is a <tt>BasicBlock::iterator</tt> and <tt>j</tt>
   2141 is a <tt>BasicBlock::const_iterator</tt>:</p>
   2142 
   2143 <div class="doc_code">
   2144 <pre>
   2145 Instruction&amp; inst = *i;   // <i>Grab reference to instruction reference</i>
   2146 Instruction* pinst = &amp;*i; // <i>Grab pointer to instruction reference</i>
   2147 const Instruction&amp; inst = *j;
   2148 </pre>
   2149 </div>
   2150 
   2151 <p>However, the iterators you'll be working with in the LLVM framework are
   2152 special: they will automatically convert to a ptr-to-instance type whenever they
   2153 need to.  Instead of dereferencing the iterator and then taking the address of
   2154 the result, you can simply assign the iterator to the proper pointer type and
   2155 you get the dereference and address-of operation as a result of the assignment
   2156 (behind the scenes, this is a result of overloading casting mechanisms).  Thus
   2157 the last line of the last example,</p>
   2158 
   2159 <div class="doc_code">
   2160 <pre>
   2161 Instruction *pinst = &amp;*i;
   2162 </pre>
   2163 </div>
   2164 
   2165 <p>is semantically equivalent to</p>
   2166 
   2167 <div class="doc_code">
   2168 <pre>
   2169 Instruction *pinst = i;
   2170 </pre>
   2171 </div>
   2172 
   2173 <p>It's also possible to turn a class pointer into the corresponding iterator,
   2174 and this is a constant time operation (very efficient).  The following code
   2175 snippet illustrates use of the conversion constructors provided by LLVM
   2176 iterators.  By using these, you can explicitly grab the iterator of something
   2177 without actually obtaining it via iteration over some structure:</p>
   2178 
   2179 <div class="doc_code">
   2180 <pre>
   2181 void printNextInstruction(Instruction* inst) {
   2182   BasicBlock::iterator it(inst);
   2183   ++it; // <i>After this line, it refers to the instruction after *inst</i>
   2184   if (it != inst-&gt;getParent()-&gt;end()) errs() &lt;&lt; *it &lt;&lt; "\n";
   2185 }
   2186 </pre>
   2187 </div>
   2188 
   2189 <p>Unfortunately, these implicit conversions come at a cost; they prevent
   2190 these iterators from conforming to standard iterator conventions, and thus
   2191 from being usable with standard algorithms and containers. For example, they
   2192 prevent the following code, where <tt>B</tt> is a <tt>BasicBlock</tt>,
   2193 from compiling:</p>
   2194 
   2195 <div class="doc_code">
   2196 <pre>
   2197   llvm::SmallVector&lt;llvm::Instruction *, 16&gt;(B-&gt;begin(), B-&gt;end());
   2198 </pre>
   2199 </div>
   2200 
   2201 <p>Because of this, these implicit conversions may be removed some day,
   2202 and <tt>operator*</tt> changed to return a pointer instead of a reference.</p>
   2203 
   2204 </div>
   2205 
   2206 <!--_______________________________________________________________________-->
   2207 <h4>
   2208   <a name="iterate_complex">Finding call sites: a slightly more complex
   2209   example</a>
   2210 </h4>
   2211 
   2212 <div>
   2213 
   2214 <p>Say that you're writing a FunctionPass and would like to count all the
   2215 locations in the entire module (that is, across every <tt>Function</tt>) where a
   2216 certain function (i.e., some <tt>Function</tt>*) is already in scope.  As you'll
   2217 learn later, you may want to use an <tt>InstVisitor</tt> to accomplish this in a
   2218 much more straight-forward manner, but this example will allow us to explore how
   2219 you'd do it if you didn't have <tt>InstVisitor</tt> around. In pseudo-code, this
   2220 is what we want to do:</p>
   2221 
   2222 <div class="doc_code">
   2223 <pre>
   2224 initialize callCounter to zero
   2225 for each Function f in the Module
   2226   for each BasicBlock b in f
   2227     for each Instruction i in b
   2228       if (i is a CallInst and calls the given function)
   2229         increment callCounter
   2230 </pre>
   2231 </div>
   2232 
   2233 <p>And the actual code is (remember, because we're writing a
   2234 <tt>FunctionPass</tt>, our <tt>FunctionPass</tt>-derived class simply has to
   2235 override the <tt>runOnFunction</tt> method):</p>
   2236 
   2237 <div class="doc_code">
   2238 <pre>
   2239 Function* targetFunc = ...;
   2240 
   2241 class OurFunctionPass : public FunctionPass {
   2242   public:
   2243     OurFunctionPass(): callCounter(0) { }
   2244 
   2245     virtual runOnFunction(Function&amp; F) {
   2246       for (Function::iterator b = F.begin(), be = F.end(); b != be; ++b) {
   2247         for (BasicBlock::iterator i = b-&gt;begin(), ie = b-&gt;end(); i != ie; ++i) {
   2248           if (<a href="#CallInst">CallInst</a>* callInst = <a href="#isa">dyn_cast</a>&lt;<a
   2249  href="#CallInst">CallInst</a>&gt;(&amp;*i)) {
   2250             // <i>We know we've encountered a call instruction, so we</i>
   2251             // <i>need to determine if it's a call to the</i>
   2252             // <i>function pointed to by m_func or not.</i>
   2253             if (callInst-&gt;getCalledFunction() == targetFunc)
   2254               ++callCounter;
   2255           }
   2256         }
   2257       }
   2258     }
   2259 
   2260   private:
   2261     unsigned callCounter;
   2262 };
   2263 </pre>
   2264 </div>
   2265 
   2266 </div>
   2267 
   2268 <!--_______________________________________________________________________-->
   2269 <h4>
   2270   <a name="calls_and_invokes">Treating calls and invokes the same way</a>
   2271 </h4>
   2272 
   2273 <div>
   2274 
   2275 <p>You may have noticed that the previous example was a bit oversimplified in
   2276 that it did not deal with call sites generated by 'invoke' instructions. In
   2277 this, and in other situations, you may find that you want to treat
   2278 <tt>CallInst</tt>s and <tt>InvokeInst</tt>s the same way, even though their
   2279 most-specific common base class is <tt>Instruction</tt>, which includes lots of
   2280 less closely-related things. For these cases, LLVM provides a handy wrapper
   2281 class called <a
   2282 href="http://llvm.org/doxygen/classllvm_1_1CallSite.html"><tt>CallSite</tt></a>.
   2283 It is essentially a wrapper around an <tt>Instruction</tt> pointer, with some
   2284 methods that provide functionality common to <tt>CallInst</tt>s and
   2285 <tt>InvokeInst</tt>s.</p>
   2286 
   2287 <p>This class has "value semantics": it should be passed by value, not by
   2288 reference and it should not be dynamically allocated or deallocated using
   2289 <tt>operator new</tt> or <tt>operator delete</tt>. It is efficiently copyable,
   2290 assignable and constructable, with costs equivalents to that of a bare pointer.
   2291 If you look at its definition, it has only a single pointer member.</p>
   2292 
   2293 </div>
   2294 
   2295 <!--_______________________________________________________________________-->
   2296 <h4>
   2297   <a name="iterate_chains">Iterating over def-use &amp; use-def chains</a>
   2298 </h4>
   2299 
   2300 <div>
   2301 
   2302 <p>Frequently, we might have an instance of the <a
   2303 href="/doxygen/classllvm_1_1Value.html">Value Class</a> and we want to
   2304 determine which <tt>User</tt>s use the <tt>Value</tt>.  The list of all
   2305 <tt>User</tt>s of a particular <tt>Value</tt> is called a <i>def-use</i> chain.
   2306 For example, let's say we have a <tt>Function*</tt> named <tt>F</tt> to a
   2307 particular function <tt>foo</tt>. Finding all of the instructions that
   2308 <i>use</i> <tt>foo</tt> is as simple as iterating over the <i>def-use</i> chain
   2309 of <tt>F</tt>:</p>
   2310 
   2311 <div class="doc_code">
   2312 <pre>
   2313 Function *F = ...;
   2314 
   2315 for (Value::use_iterator i = F-&gt;use_begin(), e = F-&gt;use_end(); i != e; ++i)
   2316   if (Instruction *Inst = dyn_cast&lt;Instruction&gt;(*i)) {
   2317     errs() &lt;&lt; "F is used in instruction:\n";
   2318     errs() &lt;&lt; *Inst &lt;&lt; "\n";
   2319   }
   2320 </pre>
   2321 </div>
   2322 
   2323 <p>Note that dereferencing a <tt>Value::use_iterator</tt> is not a very cheap
   2324 operation. Instead of performing <tt>*i</tt> above several times, consider
   2325 doing it only once in the loop body and reusing its result.</p>
   2326 
   2327 <p>Alternatively, it's common to have an instance of the <a
   2328 href="/doxygen/classllvm_1_1User.html">User Class</a> and need to know what
   2329 <tt>Value</tt>s are used by it.  The list of all <tt>Value</tt>s used by a
   2330 <tt>User</tt> is known as a <i>use-def</i> chain.  Instances of class
   2331 <tt>Instruction</tt> are common <tt>User</tt>s, so we might want to iterate over
   2332 all of the values that a particular instruction uses (that is, the operands of
   2333 the particular <tt>Instruction</tt>):</p>
   2334 
   2335 <div class="doc_code">
   2336 <pre>
   2337 Instruction *pi = ...;
   2338 
   2339 for (User::op_iterator i = pi-&gt;op_begin(), e = pi-&gt;op_end(); i != e; ++i) {
   2340   Value *v = *i;
   2341   // <i>...</i>
   2342 }
   2343 </pre>
   2344 </div>
   2345 
   2346 <p>Declaring objects as <tt>const</tt> is an important tool of enforcing
   2347 mutation free algorithms (such as analyses, etc.). For this purpose above
   2348 iterators come in constant flavors as <tt>Value::const_use_iterator</tt>
   2349 and <tt>Value::const_op_iterator</tt>.  They automatically arise when
   2350 calling <tt>use/op_begin()</tt> on <tt>const Value*</tt>s or
   2351 <tt>const User*</tt>s respectively.  Upon dereferencing, they return
   2352 <tt>const Use*</tt>s. Otherwise the above patterns remain unchanged.</p>
   2353 
   2354 </div>
   2355 
   2356 <!--_______________________________________________________________________-->
   2357 <h4>
   2358   <a name="iterate_preds">Iterating over predecessors &amp;
   2359 successors of blocks</a>
   2360 </h4>
   2361 
   2362 <div>
   2363 
   2364 <p>Iterating over the predecessors and successors of a block is quite easy
   2365 with the routines defined in <tt>"llvm/Support/CFG.h"</tt>.  Just use code like
   2366 this to iterate over all predecessors of BB:</p>
   2367 
   2368 <div class="doc_code">
   2369 <pre>
   2370 #include "llvm/Support/CFG.h"
   2371 BasicBlock *BB = ...;
   2372 
   2373 for (pred_iterator PI = pred_begin(BB), E = pred_end(BB); PI != E; ++PI) {
   2374   BasicBlock *Pred = *PI;
   2375   // <i>...</i>
   2376 }
   2377 </pre>
   2378 </div>
   2379 
   2380 <p>Similarly, to iterate over successors use
   2381 succ_iterator/succ_begin/succ_end.</p>
   2382 
   2383 </div>
   2384 
   2385 </div>
   2386 
   2387 <!-- ======================================================================= -->
   2388 <h3>
   2389   <a name="simplechanges">Making simple changes</a>
   2390 </h3>
   2391 
   2392 <div>
   2393 
   2394 <p>There are some primitive transformation operations present in the LLVM
   2395 infrastructure that are worth knowing about.  When performing
   2396 transformations, it's fairly common to manipulate the contents of basic
   2397 blocks. This section describes some of the common methods for doing so
   2398 and gives example code.</p>
   2399 
   2400 <!--_______________________________________________________________________-->
   2401 <h4>
   2402   <a name="schanges_creating">Creating and inserting new
   2403   <tt>Instruction</tt>s</a>
   2404 </h4>
   2405 
   2406 <div>
   2407 
   2408 <p><i>Instantiating Instructions</i></p>
   2409 
   2410 <p>Creation of <tt>Instruction</tt>s is straight-forward: simply call the
   2411 constructor for the kind of instruction to instantiate and provide the necessary
   2412 parameters. For example, an <tt>AllocaInst</tt> only <i>requires</i> a
   2413 (const-ptr-to) <tt>Type</tt>. Thus:</p> 
   2414 
   2415 <div class="doc_code">
   2416 <pre>
   2417 AllocaInst* ai = new AllocaInst(Type::Int32Ty);
   2418 </pre>
   2419 </div>
   2420 
   2421 <p>will create an <tt>AllocaInst</tt> instance that represents the allocation of
   2422 one integer in the current stack frame, at run time. Each <tt>Instruction</tt>
   2423 subclass is likely to have varying default parameters which change the semantics
   2424 of the instruction, so refer to the <a
   2425 href="/doxygen/classllvm_1_1Instruction.html">doxygen documentation for the subclass of
   2426 Instruction</a> that you're interested in instantiating.</p>
   2427 
   2428 <p><i>Naming values</i></p>
   2429 
   2430 <p>It is very useful to name the values of instructions when you're able to, as
   2431 this facilitates the debugging of your transformations.  If you end up looking
   2432 at generated LLVM machine code, you definitely want to have logical names
   2433 associated with the results of instructions!  By supplying a value for the
   2434 <tt>Name</tt> (default) parameter of the <tt>Instruction</tt> constructor, you
   2435 associate a logical name with the result of the instruction's execution at
   2436 run time.  For example, say that I'm writing a transformation that dynamically
   2437 allocates space for an integer on the stack, and that integer is going to be
   2438 used as some kind of index by some other code.  To accomplish this, I place an
   2439 <tt>AllocaInst</tt> at the first point in the first <tt>BasicBlock</tt> of some
   2440 <tt>Function</tt>, and I'm intending to use it within the same
   2441 <tt>Function</tt>. I might do:</p>
   2442 
   2443 <div class="doc_code">
   2444 <pre>
   2445 AllocaInst* pa = new AllocaInst(Type::Int32Ty, 0, "indexLoc");
   2446 </pre>
   2447 </div>
   2448 
   2449 <p>where <tt>indexLoc</tt> is now the logical name of the instruction's
   2450 execution value, which is a pointer to an integer on the run time stack.</p>
   2451 
   2452 <p><i>Inserting instructions</i></p>
   2453 
   2454 <p>There are essentially two ways to insert an <tt>Instruction</tt>
   2455 into an existing sequence of instructions that form a <tt>BasicBlock</tt>:</p>
   2456 
   2457 <ul>
   2458   <li>Insertion into an explicit instruction list
   2459 
   2460     <p>Given a <tt>BasicBlock* pb</tt>, an <tt>Instruction* pi</tt> within that
   2461     <tt>BasicBlock</tt>, and a newly-created instruction we wish to insert
   2462     before <tt>*pi</tt>, we do the following: </p>
   2463 
   2464 <div class="doc_code">
   2465 <pre>
   2466 BasicBlock *pb = ...;
   2467 Instruction *pi = ...;
   2468 Instruction *newInst = new Instruction(...);
   2469 
   2470 pb-&gt;getInstList().insert(pi, newInst); // <i>Inserts newInst before pi in pb</i>
   2471 </pre>
   2472 </div>
   2473 
   2474     <p>Appending to the end of a <tt>BasicBlock</tt> is so common that
   2475     the <tt>Instruction</tt> class and <tt>Instruction</tt>-derived
   2476     classes provide constructors which take a pointer to a
   2477     <tt>BasicBlock</tt> to be appended to. For example code that
   2478     looked like: </p>
   2479 
   2480 <div class="doc_code">
   2481 <pre>
   2482 BasicBlock *pb = ...;
   2483 Instruction *newInst = new Instruction(...);
   2484 
   2485 pb-&gt;getInstList().push_back(newInst); // <i>Appends newInst to pb</i>
   2486 </pre>
   2487 </div>
   2488 
   2489     <p>becomes: </p>
   2490 
   2491 <div class="doc_code">
   2492 <pre>
   2493 BasicBlock *pb = ...;
   2494 Instruction *newInst = new Instruction(..., pb);
   2495 </pre>
   2496 </div>
   2497 
   2498     <p>which is much cleaner, especially if you are creating
   2499     long instruction streams.</p></li>
   2500 
   2501   <li>Insertion into an implicit instruction list
   2502 
   2503     <p><tt>Instruction</tt> instances that are already in <tt>BasicBlock</tt>s
   2504     are implicitly associated with an existing instruction list: the instruction
   2505     list of the enclosing basic block. Thus, we could have accomplished the same
   2506     thing as the above code without being given a <tt>BasicBlock</tt> by doing:
   2507     </p>
   2508 
   2509 <div class="doc_code">
   2510 <pre>
   2511 Instruction *pi = ...;
   2512 Instruction *newInst = new Instruction(...);
   2513 
   2514 pi-&gt;getParent()-&gt;getInstList().insert(pi, newInst);
   2515 </pre>
   2516 </div>
   2517 
   2518     <p>In fact, this sequence of steps occurs so frequently that the
   2519     <tt>Instruction</tt> class and <tt>Instruction</tt>-derived classes provide
   2520     constructors which take (as a default parameter) a pointer to an
   2521     <tt>Instruction</tt> which the newly-created <tt>Instruction</tt> should
   2522     precede.  That is, <tt>Instruction</tt> constructors are capable of
   2523     inserting the newly-created instance into the <tt>BasicBlock</tt> of a
   2524     provided instruction, immediately before that instruction.  Using an
   2525     <tt>Instruction</tt> constructor with a <tt>insertBefore</tt> (default)
   2526     parameter, the above code becomes:</p>
   2527 
   2528 <div class="doc_code">
   2529 <pre>
   2530 Instruction* pi = ...;
   2531 Instruction* newInst = new Instruction(..., pi);
   2532 </pre>
   2533 </div>
   2534 
   2535     <p>which is much cleaner, especially if you're creating a lot of
   2536     instructions and adding them to <tt>BasicBlock</tt>s.</p></li>
   2537 </ul>
   2538 
   2539 </div>
   2540 
   2541 <!--_______________________________________________________________________-->
   2542 <h4>
   2543   <a name="schanges_deleting">Deleting <tt>Instruction</tt>s</a>
   2544 </h4>
   2545 
   2546 <div>
   2547 
   2548 <p>Deleting an instruction from an existing sequence of instructions that form a
   2549 <a href="#BasicBlock"><tt>BasicBlock</tt></a> is very straight-forward: just
   2550 call the instruction's eraseFromParent() method.  For example:</p>
   2551 
   2552 <div class="doc_code">
   2553 <pre>
   2554 <a href="#Instruction">Instruction</a> *I = .. ;
   2555 I-&gt;eraseFromParent();
   2556 </pre>
   2557 </div>
   2558 
   2559 <p>This unlinks the instruction from its containing basic block and deletes 
   2560 it.  If you'd just like to unlink the instruction from its containing basic
   2561 block but not delete it, you can use the <tt>removeFromParent()</tt> method.</p>
   2562 
   2563 </div>
   2564 
   2565 <!--_______________________________________________________________________-->
   2566 <h4>
   2567   <a name="schanges_replacing">Replacing an <tt>Instruction</tt> with another
   2568   <tt>Value</tt></a>
   2569 </h4>
   2570 
   2571 <div>
   2572 
   2573 <h5><i>Replacing individual instructions</i></h5>
   2574 
   2575 <p>Including "<a href="/doxygen/BasicBlockUtils_8h-source.html">llvm/Transforms/Utils/BasicBlockUtils.h</a>"
   2576 permits use of two very useful replace functions: <tt>ReplaceInstWithValue</tt>
   2577 and <tt>ReplaceInstWithInst</tt>.</p>
   2578 
   2579 <h5><a name="schanges_deleting">Deleting <tt>Instruction</tt>s</a></h5>
   2580 
   2581 <div>
   2582 <ul>
   2583   <li><tt>ReplaceInstWithValue</tt>
   2584 
   2585     <p>This function replaces all uses of a given instruction with a value,
   2586     and then removes the original instruction. The following example
   2587     illustrates the replacement of the result of a particular
   2588     <tt>AllocaInst</tt> that allocates memory for a single integer with a null
   2589     pointer to an integer.</p>
   2590 
   2591 <div class="doc_code">
   2592 <pre>
   2593 AllocaInst* instToReplace = ...;
   2594 BasicBlock::iterator ii(instToReplace);
   2595 
   2596 ReplaceInstWithValue(instToReplace-&gt;getParent()-&gt;getInstList(), ii,
   2597                      Constant::getNullValue(PointerType::getUnqual(Type::Int32Ty)));
   2598 </pre></div></li>
   2599 
   2600   <li><tt>ReplaceInstWithInst</tt> 
   2601 
   2602     <p>This function replaces a particular instruction with another
   2603     instruction, inserting the new instruction into the basic block at the
   2604     location where the old instruction was, and replacing any uses of the old
   2605     instruction with the new instruction. The following example illustrates
   2606     the replacement of one <tt>AllocaInst</tt> with another.</p>
   2607 
   2608 <div class="doc_code">
   2609 <pre>
   2610 AllocaInst* instToReplace = ...;
   2611 BasicBlock::iterator ii(instToReplace);
   2612 
   2613 ReplaceInstWithInst(instToReplace-&gt;getParent()-&gt;getInstList(), ii,
   2614                     new AllocaInst(Type::Int32Ty, 0, "ptrToReplacedInt"));
   2615 </pre></div></li>
   2616 </ul>
   2617 
   2618 </div>
   2619 
   2620 <h5><i>Replacing multiple uses of <tt>User</tt>s and <tt>Value</tt>s</i></h5>
   2621 
   2622 <p>You can use <tt>Value::replaceAllUsesWith</tt> and
   2623 <tt>User::replaceUsesOfWith</tt> to change more than one use at a time.  See the
   2624 doxygen documentation for the <a href="/doxygen/classllvm_1_1Value.html">Value Class</a>
   2625 and <a href="/doxygen/classllvm_1_1User.html">User Class</a>, respectively, for more
   2626 information.</p>
   2627 
   2628 <!-- Value::replaceAllUsesWith User::replaceUsesOfWith Point out:
   2629 include/llvm/Transforms/Utils/ especially BasicBlockUtils.h with:
   2630 ReplaceInstWithValue, ReplaceInstWithInst -->
   2631 
   2632 </div>
   2633 
   2634 <!--_______________________________________________________________________-->
   2635 <h4>
   2636   <a name="schanges_deletingGV">Deleting <tt>GlobalVariable</tt>s</a>
   2637 </h4>
   2638 
   2639 <div>
   2640 
   2641 <p>Deleting a global variable from a module is just as easy as deleting an 
   2642 Instruction. First, you must have a pointer to the global variable that you wish
   2643  to delete.  You use this pointer to erase it from its parent, the module.
   2644  For example:</p>
   2645 
   2646 <div class="doc_code">
   2647 <pre>
   2648 <a href="#GlobalVariable">GlobalVariable</a> *GV = .. ;
   2649 
   2650 GV-&gt;eraseFromParent();
   2651 </pre>
   2652 </div>
   2653 
   2654 </div>
   2655 
   2656 </div>
   2657 
   2658 <!-- ======================================================================= -->
   2659 <h3>
   2660   <a name="create_types">How to Create Types</a>
   2661 </h3>
   2662 
   2663 <div>
   2664 
   2665 <p>In generating IR, you may need some complex types.  If you know these types
   2666 statically, you can use <tt>TypeBuilder&lt;...&gt;::get()</tt>, defined
   2667 in <tt>llvm/Support/TypeBuilder.h</tt>, to retrieve them.  <tt>TypeBuilder</tt>
   2668 has two forms depending on whether you're building types for cross-compilation
   2669 or native library use.  <tt>TypeBuilder&lt;T, true&gt;</tt> requires
   2670 that <tt>T</tt> be independent of the host environment, meaning that it's built
   2671 out of types from
   2672 the <a href="/doxygen/namespacellvm_1_1types.html"><tt>llvm::types</tt></a>
   2673 namespace and pointers, functions, arrays, etc. built of
   2674 those.  <tt>TypeBuilder&lt;T, false&gt;</tt> additionally allows native C types
   2675 whose size may depend on the host compiler.  For example,</p>
   2676 
   2677 <div class="doc_code">
   2678 <pre>
   2679 FunctionType *ft = TypeBuilder&lt;types::i&lt;8&gt;(types::i&lt;32&gt;*), true&gt;::get();
   2680 </pre>
   2681 </div>
   2682 
   2683 <p>is easier to read and write than the equivalent</p>
   2684 
   2685 <div class="doc_code">
   2686 <pre>
   2687 std::vector&lt;const Type*&gt; params;
   2688 params.push_back(PointerType::getUnqual(Type::Int32Ty));
   2689 FunctionType *ft = FunctionType::get(Type::Int8Ty, params, false);
   2690 </pre>
   2691 </div>
   2692 
   2693 <p>See the <a href="/doxygen/TypeBuilder_8h-source.html#l00001">class
   2694 comment</a> for more details.</p>
   2695 
   2696 </div>
   2697 
   2698 </div>
   2699 
   2700 <!-- *********************************************************************** -->
   2701 <h2>
   2702   <a name="threading">Threads and LLVM</a>
   2703 </h2>
   2704 <!-- *********************************************************************** -->
   2705 
   2706 <div>
   2707 <p>
   2708 This section describes the interaction of the LLVM APIs with multithreading,
   2709 both on the part of client applications, and in the JIT, in the hosted
   2710 application.
   2711 </p>
   2712 
   2713 <p>
   2714 Note that LLVM's support for multithreading is still relatively young.  Up 
   2715 through version 2.5, the execution of threaded hosted applications was
   2716 supported, but not threaded client access to the APIs.  While this use case is
   2717 now supported, clients <em>must</em> adhere to the guidelines specified below to
   2718 ensure proper operation in multithreaded mode.
   2719 </p>
   2720 
   2721 <p>
   2722 Note that, on Unix-like platforms, LLVM requires the presence of GCC's atomic
   2723 intrinsics in order to support threaded operation.  If you need a
   2724 multhreading-capable LLVM on a platform without a suitably modern system
   2725 compiler, consider compiling LLVM and LLVM-GCC in single-threaded mode, and 
   2726 using the resultant compiler to build a copy of LLVM with multithreading
   2727 support.
   2728 </p>
   2729 
   2730 <!-- ======================================================================= -->
   2731 <h3>
   2732   <a name="startmultithreaded">Entering and Exiting Multithreaded Mode</a>
   2733 </h3>
   2734 
   2735 <div>
   2736 
   2737 <p>
   2738 In order to properly protect its internal data structures while avoiding 
   2739 excessive locking overhead in the single-threaded case, the LLVM must intialize
   2740 certain data structures necessary to provide guards around its internals.  To do
   2741 so, the client program must invoke <tt>llvm_start_multithreaded()</tt> before
   2742 making any concurrent LLVM API calls.  To subsequently tear down these
   2743 structures, use the <tt>llvm_stop_multithreaded()</tt> call.  You can also use
   2744 the <tt>llvm_is_multithreaded()</tt> call to check the status of multithreaded
   2745 mode.
   2746 </p>
   2747 
   2748 <p>
   2749 Note that both of these calls must be made <em>in isolation</em>.  That is to
   2750 say that no other LLVM API calls may be executing at any time during the 
   2751 execution of <tt>llvm_start_multithreaded()</tt> or <tt>llvm_stop_multithreaded
   2752 </tt>.  It's is the client's responsibility to enforce this isolation.
   2753 </p>
   2754 
   2755 <p>
   2756 The return value of <tt>llvm_start_multithreaded()</tt> indicates the success or
   2757 failure of the initialization.  Failure typically indicates that your copy of
   2758 LLVM was built without multithreading support, typically because GCC atomic
   2759 intrinsics were not found in your system compiler.  In this case, the LLVM API
   2760 will not be safe for concurrent calls.  However, it <em>will</em> be safe for
   2761 hosting threaded applications in the JIT, though <a href="#jitthreading">care
   2762 must be taken</a> to ensure that side exits and the like do not accidentally
   2763 result in concurrent LLVM API calls.
   2764 </p>
   2765 </div>
   2766 
   2767 <!-- ======================================================================= -->
   2768 <h3>
   2769   <a name="shutdown">Ending Execution with <tt>llvm_shutdown()</tt></a>
   2770 </h3>
   2771 
   2772 <div>
   2773 <p>
   2774 When you are done using the LLVM APIs, you should call <tt>llvm_shutdown()</tt>
   2775 to deallocate memory used for internal structures.  This will also invoke 
   2776 <tt>llvm_stop_multithreaded()</tt> if LLVM is operating in multithreaded mode.
   2777 As such, <tt>llvm_shutdown()</tt> requires the same isolation guarantees as
   2778 <tt>llvm_stop_multithreaded()</tt>.
   2779 </p>
   2780 
   2781 <p>
   2782 Note that, if you use scope-based shutdown, you can use the
   2783 <tt>llvm_shutdown_obj</tt> class, which calls <tt>llvm_shutdown()</tt> in its
   2784 destructor.
   2785 </div>
   2786 
   2787 <!-- ======================================================================= -->
   2788 <h3>
   2789   <a name="managedstatic">Lazy Initialization with <tt>ManagedStatic</tt></a>
   2790 </h3>
   2791 
   2792 <div>
   2793 <p>
   2794 <tt>ManagedStatic</tt> is a utility class in LLVM used to implement static
   2795 initialization of static resources, such as the global type tables.  Before the
   2796 invocation of <tt>llvm_shutdown()</tt>, it implements a simple lazy 
   2797 initialization scheme.  Once <tt>llvm_start_multithreaded()</tt> returns,
   2798 however, it uses double-checked locking to implement thread-safe lazy
   2799 initialization.
   2800 </p>
   2801 
   2802 <p>
   2803 Note that, because no other threads are allowed to issue LLVM API calls before
   2804 <tt>llvm_start_multithreaded()</tt> returns, it is possible to have 
   2805 <tt>ManagedStatic</tt>s of <tt>llvm::sys::Mutex</tt>s.
   2806 </p>
   2807 
   2808 <p>
   2809 The <tt>llvm_acquire_global_lock()</tt> and <tt>llvm_release_global_lock</tt> 
   2810 APIs provide access to the global lock used to implement the double-checked
   2811 locking for lazy initialization.  These should only be used internally to LLVM,
   2812 and only if you know what you're doing!
   2813 </p>
   2814 </div>
   2815 
   2816 <!-- ======================================================================= -->
   2817 <h3>
   2818   <a name="llvmcontext">Achieving Isolation with <tt>LLVMContext</tt></a>
   2819 </h3>
   2820 
   2821 <div>
   2822 <p>
   2823 <tt>LLVMContext</tt> is an opaque class in the LLVM API which clients can use
   2824 to operate multiple, isolated instances of LLVM concurrently within the same
   2825 address space.  For instance, in a hypothetical compile-server, the compilation
   2826 of an individual translation unit is conceptually independent from all the 
   2827 others, and it would be desirable to be able to compile incoming translation 
   2828 units concurrently on independent server threads.  Fortunately, 
   2829 <tt>LLVMContext</tt> exists to enable just this kind of scenario!
   2830 </p>
   2831 
   2832 <p>
   2833 Conceptually, <tt>LLVMContext</tt> provides isolation.  Every LLVM entity 
   2834 (<tt>Module</tt>s, <tt>Value</tt>s, <tt>Type</tt>s, <tt>Constant</tt>s, etc.)
   2835 in LLVM's in-memory IR belongs to an <tt>LLVMContext</tt>.  Entities in 
   2836 different contexts <em>cannot</em> interact with each other: <tt>Module</tt>s in
   2837 different contexts cannot be linked together, <tt>Function</tt>s cannot be added
   2838 to <tt>Module</tt>s in different contexts, etc.  What this means is that is is
   2839 safe to compile on multiple threads simultaneously, as long as no two threads
   2840 operate on entities within the same context.
   2841 </p>
   2842 
   2843 <p>
   2844 In practice, very few places in the API require the explicit specification of a
   2845 <tt>LLVMContext</tt>, other than the <tt>Type</tt> creation/lookup APIs.
   2846 Because every <tt>Type</tt> carries a reference to its owning context, most
   2847 other entities can determine what context they belong to by looking at their
   2848 own <tt>Type</tt>.  If you are adding new entities to LLVM IR, please try to
   2849 maintain this interface design.
   2850 </p>
   2851 
   2852 <p>
   2853 For clients that do <em>not</em> require the benefits of isolation, LLVM 
   2854 provides a convenience API <tt>getGlobalContext()</tt>.  This returns a global,
   2855 lazily initialized <tt>LLVMContext</tt> that may be used in situations where
   2856 isolation is not a concern.
   2857 </p>
   2858 </div>
   2859 
   2860 <!-- ======================================================================= -->
   2861 <h3>
   2862   <a name="jitthreading">Threads and the JIT</a>
   2863 </h3>
   2864 
   2865 <div>
   2866 <p>
   2867 LLVM's "eager" JIT compiler is safe to use in threaded programs.  Multiple
   2868 threads can call <tt>ExecutionEngine::getPointerToFunction()</tt> or
   2869 <tt>ExecutionEngine::runFunction()</tt> concurrently, and multiple threads can
   2870 run code output by the JIT concurrently.  The user must still ensure that only
   2871 one thread accesses IR in a given <tt>LLVMContext</tt> while another thread
   2872 might be modifying it.  One way to do that is to always hold the JIT lock while
   2873 accessing IR outside the JIT (the JIT <em>modifies</em> the IR by adding
   2874 <tt>CallbackVH</tt>s).  Another way is to only
   2875 call <tt>getPointerToFunction()</tt> from the <tt>LLVMContext</tt>'s thread.
   2876 </p>
   2877 
   2878 <p>When the JIT is configured to compile lazily (using
   2879 <tt>ExecutionEngine::DisableLazyCompilation(false)</tt>), there is currently a
   2880 <a href="http://llvm.org/bugs/show_bug.cgi?id=5184">race condition</a> in
   2881 updating call sites after a function is lazily-jitted.  It's still possible to
   2882 use the lazy JIT in a threaded program if you ensure that only one thread at a
   2883 time can call any particular lazy stub and that the JIT lock guards any IR
   2884 access, but we suggest using only the eager JIT in threaded programs.
   2885 </p>
   2886 </div>
   2887 
   2888 </div>
   2889 
   2890 <!-- *********************************************************************** -->
   2891 <h2>
   2892   <a name="advanced">Advanced Topics</a>
   2893 </h2>
   2894 <!-- *********************************************************************** -->
   2895 
   2896 <div>
   2897 <p>
   2898 This section describes some of the advanced or obscure API's that most clients
   2899 do not need to be aware of.  These API's tend manage the inner workings of the
   2900 LLVM system, and only need to be accessed in unusual circumstances.
   2901 </p>
   2902 
   2903   
   2904 <!-- ======================================================================= -->
   2905 <h3>
   2906   <a name="SymbolTable">The <tt>ValueSymbolTable</tt> class</a>
   2907 </h3>
   2908 
   2909 <div>
   2910 <p>The <tt><a href="http://llvm.org/doxygen/classllvm_1_1ValueSymbolTable.html">
   2911 ValueSymbolTable</a></tt> class provides a symbol table that the <a
   2912 href="#Function"><tt>Function</tt></a> and <a href="#Module">
   2913 <tt>Module</tt></a> classes use for naming value definitions. The symbol table
   2914 can provide a name for any <a href="#Value"><tt>Value</tt></a>. 
   2915 </p>
   2916 
   2917 <p>Note that the <tt>SymbolTable</tt> class should not be directly accessed 
   2918 by most clients.  It should only be used when iteration over the symbol table 
   2919 names themselves are required, which is very special purpose.  Note that not 
   2920 all LLVM
   2921 <tt><a href="#Value">Value</a></tt>s have names, and those without names (i.e. they have
   2922 an empty name) do not exist in the symbol table.
   2923 </p>
   2924 
   2925 <p>Symbol tables support iteration over the values in the symbol
   2926 table with <tt>begin/end/iterator</tt> and supports querying to see if a
   2927 specific name is in the symbol table (with <tt>lookup</tt>).  The
   2928 <tt>ValueSymbolTable</tt> class exposes no public mutator methods, instead,
   2929 simply call <tt>setName</tt> on a value, which will autoinsert it into the
   2930 appropriate symbol table.</p>
   2931 
   2932 </div>
   2933 
   2934 
   2935 
   2936 <!-- ======================================================================= -->
   2937 <h3>
   2938   <a name="UserLayout">The <tt>User</tt> and owned <tt>Use</tt> classes' memory layout</a>
   2939 </h3>
   2940 
   2941 <div>
   2942 <p>The <tt><a href="http://llvm.org/doxygen/classllvm_1_1User.html">
   2943 User</a></tt> class provides a basis for expressing the ownership of <tt>User</tt>
   2944 towards other <tt><a href="http://llvm.org/doxygen/classllvm_1_1Value.html">
   2945 Value</a></tt>s. The <tt><a href="http://llvm.org/doxygen/classllvm_1_1Use.html">
   2946 Use</a></tt> helper class is employed to do the bookkeeping and to facilitate <i>O(1)</i>
   2947 addition and removal.</p>
   2948 
   2949 <!-- ______________________________________________________________________ -->
   2950 <h4>
   2951   <a name="Use2User">
   2952     Interaction and relationship between <tt>User</tt> and <tt>Use</tt> objects
   2953   </a>
   2954 </h4>
   2955 
   2956 <div>
   2957 <p>
   2958 A subclass of <tt>User</tt> can choose between incorporating its <tt>Use</tt> objects
   2959 or refer to them out-of-line by means of a pointer. A mixed variant
   2960 (some <tt>Use</tt>s inline others hung off) is impractical and breaks the invariant
   2961 that the <tt>Use</tt> objects belonging to the same <tt>User</tt> form a contiguous array.
   2962 </p>
   2963 
   2964 <p>
   2965 We have 2 different layouts in the <tt>User</tt> (sub)classes:
   2966 <ul>
   2967 <li><p>Layout a)
   2968 The <tt>Use</tt> object(s) are inside (resp. at fixed offset) of the <tt>User</tt>
   2969 object and there are a fixed number of them.</p>
   2970 
   2971 <li><p>Layout b)
   2972 The <tt>Use</tt> object(s) are referenced by a pointer to an
   2973 array from the <tt>User</tt> object and there may be a variable
   2974 number of them.</p>
   2975 </ul>
   2976 <p>
   2977 As of v2.4 each layout still possesses a direct pointer to the
   2978 start of the array of <tt>Use</tt>s. Though not mandatory for layout a),
   2979 we stick to this redundancy for the sake of simplicity.
   2980 The <tt>User</tt> object also stores the number of <tt>Use</tt> objects it
   2981 has. (Theoretically this information can also be calculated
   2982 given the scheme presented below.)</p>
   2983 <p>
   2984 Special forms of allocation operators (<tt>operator new</tt>)
   2985 enforce the following memory layouts:</p>
   2986 
   2987 <ul>
   2988 <li><p>Layout a) is modelled by prepending the <tt>User</tt> object by the <tt>Use[]</tt> array.</p>
   2989 
   2990 <pre>
   2991 ...---.---.---.---.-------...
   2992   | P | P | P | P | User
   2993 '''---'---'---'---'-------'''
   2994 </pre>
   2995 
   2996 <li><p>Layout b) is modelled by pointing at the <tt>Use[]</tt> array.</p>
   2997 <pre>
   2998 .-------...
   2999 | User
   3000 '-------'''
   3001     |
   3002     v
   3003     .---.---.---.---...
   3004     | P | P | P | P |
   3005     '---'---'---'---'''
   3006 </pre>
   3007 </ul>
   3008 <i>(In the above figures '<tt>P</tt>' stands for the <tt>Use**</tt> that
   3009     is stored in each <tt>Use</tt> object in the member <tt>Use::Prev</tt>)</i>
   3010 
   3011 </div>
   3012 
   3013 <!-- ______________________________________________________________________ -->
   3014 <h4>
   3015   <a name="Waymarking">The waymarking algorithm</a>
   3016 </h4>
   3017 
   3018 <div>
   3019 <p>
   3020 Since the <tt>Use</tt> objects are deprived of the direct (back)pointer to
   3021 their <tt>User</tt> objects, there must be a fast and exact method to
   3022 recover it. This is accomplished by the following scheme:</p>
   3023 
   3024 A bit-encoding in the 2 LSBits (least significant bits) of the <tt>Use::Prev</tt> allows to find the
   3025 start of the <tt>User</tt> object:
   3026 <ul>
   3027 <li><tt>00</tt> &mdash;&gt; binary digit 0</li>
   3028 <li><tt>01</tt> &mdash;&gt; binary digit 1</li>
   3029 <li><tt>10</tt> &mdash;&gt; stop and calculate (<tt>s</tt>)</li>
   3030 <li><tt>11</tt> &mdash;&gt; full stop (<tt>S</tt>)</li>
   3031 </ul>
   3032 <p>
   3033 Given a <tt>Use*</tt>, all we have to do is to walk till we get
   3034 a stop and we either have a <tt>User</tt> immediately behind or
   3035 we have to walk to the next stop picking up digits
   3036 and calculating the offset:</p>
   3037 <pre>
   3038 .---.---.---.---.---.---.---.---.---.---.---.---.---.---.---.---.----------------
   3039 | 1 | s | 1 | 0 | 1 | 0 | s | 1 | 1 | 0 | s | 1 | 1 | s | 1 | S | User (or User*)
   3040 '---'---'---'---'---'---'---'---'---'---'---'---'---'---'---'---'----------------
   3041     |+15                |+10            |+6         |+3     |+1
   3042     |                   |               |           |       |__>
   3043     |                   |               |           |__________>
   3044     |                   |               |______________________>
   3045     |                   |______________________________________>
   3046     |__________________________________________________________>
   3047 </pre>
   3048 <p>
   3049 Only the significant number of bits need to be stored between the
   3050 stops, so that the <i>worst case is 20 memory accesses</i> when there are
   3051 1000 <tt>Use</tt> objects associated with a <tt>User</tt>.</p>
   3052 
   3053 </div>
   3054 
   3055 <!-- ______________________________________________________________________ -->
   3056 <h4>
   3057   <a name="ReferenceImpl">Reference implementation</a>
   3058 </h4>
   3059 
   3060 <div>
   3061 <p>
   3062 The following literate Haskell fragment demonstrates the concept:</p>
   3063 
   3064 <div class="doc_code">
   3065 <pre>
   3066 > import Test.QuickCheck
   3067 > 
   3068 > digits :: Int -> [Char] -> [Char]
   3069 > digits 0 acc = '0' : acc
   3070 > digits 1 acc = '1' : acc
   3071 > digits n acc = digits (n `div` 2) $ digits (n `mod` 2) acc
   3072 > 
   3073 > dist :: Int -> [Char] -> [Char]
   3074 > dist 0 [] = ['S']
   3075 > dist 0 acc = acc
   3076 > dist 1 acc = let r = dist 0 acc in 's' : digits (length r) r
   3077 > dist n acc = dist (n - 1) $ dist 1 acc
   3078 > 
   3079 > takeLast n ss = reverse $ take n $ reverse ss
   3080 > 
   3081 > test = takeLast 40 $ dist 20 []
   3082 > 
   3083 </pre>
   3084 </div>
   3085 <p>
   3086 Printing &lt;test&gt; gives: <tt>"1s100000s11010s10100s1111s1010s110s11s1S"</tt></p>
   3087 <p>
   3088 The reverse algorithm computes the length of the string just by examining
   3089 a certain prefix:</p>
   3090 
   3091 <div class="doc_code">
   3092 <pre>
   3093 > pref :: [Char] -> Int
   3094 > pref "S" = 1
   3095 > pref ('s':'1':rest) = decode 2 1 rest
   3096 > pref (_:rest) = 1 + pref rest
   3097 > 
   3098 > decode walk acc ('0':rest) = decode (walk + 1) (acc * 2) rest
   3099 > decode walk acc ('1':rest) = decode (walk + 1) (acc * 2 + 1) rest
   3100 > decode walk acc _ = walk + acc
   3101 > 
   3102 </pre>
   3103 </div>
   3104 <p>
   3105 Now, as expected, printing &lt;pref test&gt; gives <tt>40</tt>.</p>
   3106 <p>
   3107 We can <i>quickCheck</i> this with following property:</p>
   3108 
   3109 <div class="doc_code">
   3110 <pre>
   3111 > testcase = dist 2000 []
   3112 > testcaseLength = length testcase
   3113 > 
   3114 > identityProp n = n > 0 && n <= testcaseLength ==> length arr == pref arr
   3115 >     where arr = takeLast n testcase
   3116 > 
   3117 </pre>
   3118 </div>
   3119 <p>
   3120 As expected &lt;quickCheck identityProp&gt; gives:</p>
   3121 
   3122 <pre>
   3123 *Main> quickCheck identityProp
   3124 OK, passed 100 tests.
   3125 </pre>
   3126 <p>
   3127 Let's be a bit more exhaustive:</p>
   3128 
   3129 <div class="doc_code">
   3130 <pre>
   3131 > 
   3132 > deepCheck p = check (defaultConfig { configMaxTest = 500 }) p
   3133 > 
   3134 </pre>
   3135 </div>
   3136 <p>
   3137 And here is the result of &lt;deepCheck identityProp&gt;:</p>
   3138 
   3139 <pre>
   3140 *Main> deepCheck identityProp
   3141 OK, passed 500 tests.
   3142 </pre>
   3143 
   3144 </div>
   3145 
   3146 <!-- ______________________________________________________________________ -->
   3147 <h4>
   3148   <a name="Tagging">Tagging considerations</a>
   3149 </h4>
   3150 
   3151 <div>
   3152 
   3153 <p>
   3154 To maintain the invariant that the 2 LSBits of each <tt>Use**</tt> in <tt>Use</tt>
   3155 never change after being set up, setters of <tt>Use::Prev</tt> must re-tag the
   3156 new <tt>Use**</tt> on every modification. Accordingly getters must strip the
   3157 tag bits.</p>
   3158 <p>
   3159 For layout b) instead of the <tt>User</tt> we find a pointer (<tt>User*</tt> with LSBit set).
   3160 Following this pointer brings us to the <tt>User</tt>. A portable trick ensures
   3161 that the first bytes of <tt>User</tt> (if interpreted as a pointer) never has
   3162 the LSBit set. (Portability is relying on the fact that all known compilers place the
   3163 <tt>vptr</tt> in the first word of the instances.)</p>
   3164 
   3165 </div>
   3166 
   3167 </div>
   3168 
   3169 </div>
   3170 
   3171 <!-- *********************************************************************** -->
   3172 <h2>
   3173   <a name="coreclasses">The Core LLVM Class Hierarchy Reference </a>
   3174 </h2>
   3175 <!-- *********************************************************************** -->
   3176 
   3177 <div>
   3178 <p><tt>#include "<a href="/doxygen/Type_8h-source.html">llvm/Type.h</a>"</tt>
   3179 <br>doxygen info: <a href="/doxygen/classllvm_1_1Type.html">Type Class</a></p>
   3180 
   3181 <p>The Core LLVM classes are the primary means of representing the program
   3182 being inspected or transformed.  The core LLVM classes are defined in
   3183 header files in the <tt>include/llvm/</tt> directory, and implemented in
   3184 the <tt>lib/VMCore</tt> directory.</p>
   3185 
   3186 <!-- ======================================================================= -->
   3187 <h3>
   3188   <a name="Type">The <tt>Type</tt> class and Derived Types</a>
   3189 </h3>
   3190 
   3191 <div>
   3192 
   3193   <p><tt>Type</tt> is a superclass of all type classes. Every <tt>Value</tt> has
   3194   a <tt>Type</tt>. <tt>Type</tt> cannot be instantiated directly but only
   3195   through its subclasses. Certain primitive types (<tt>VoidType</tt>,
   3196   <tt>LabelType</tt>, <tt>FloatType</tt> and <tt>DoubleType</tt>) have hidden 
   3197   subclasses. They are hidden because they offer no useful functionality beyond
   3198   what the <tt>Type</tt> class offers except to distinguish themselves from 
   3199   other subclasses of <tt>Type</tt>.</p>
   3200   <p>All other types are subclasses of <tt>DerivedType</tt>.  Types can be 
   3201   named, but this is not a requirement. There exists exactly 
   3202   one instance of a given shape at any one time.  This allows type equality to
   3203   be performed with address equality of the Type Instance. That is, given two 
   3204   <tt>Type*</tt> values, the types are identical if the pointers are identical.
   3205   </p>
   3206 
   3207 <!-- _______________________________________________________________________ -->
   3208 <h4>
   3209   <a name="m_Type">Important Public Methods</a>
   3210 </h4>
   3211 
   3212 <div>
   3213 
   3214 <ul>
   3215   <li><tt>bool isIntegerTy() const</tt>: Returns true for any integer type.</li>
   3216 
   3217   <li><tt>bool isFloatingPointTy()</tt>: Return true if this is one of the five
   3218   floating point types.</li>
   3219 
   3220   <li><tt>bool isSized()</tt>: Return true if the type has known size. Things
   3221   that don't have a size are abstract types, labels and void.</li>
   3222 
   3223 </ul>
   3224 </div>
   3225 
   3226 <!-- _______________________________________________________________________ -->
   3227 <h4>
   3228   <a name="derivedtypes">Important Derived Types</a>
   3229 </h4>
   3230 <div>
   3231 <dl>
   3232   <dt><tt>IntegerType</tt></dt>
   3233   <dd>Subclass of DerivedType that represents integer types of any bit width. 
   3234   Any bit width between <tt>IntegerType::MIN_INT_BITS</tt> (1) and 
   3235   <tt>IntegerType::MAX_INT_BITS</tt> (~8 million) can be represented.
   3236   <ul>
   3237     <li><tt>static const IntegerType* get(unsigned NumBits)</tt>: get an integer
   3238     type of a specific bit width.</li>
   3239     <li><tt>unsigned getBitWidth() const</tt>: Get the bit width of an integer
   3240     type.</li>
   3241   </ul>
   3242   </dd>
   3243   <dt><tt>SequentialType</tt></dt>
   3244   <dd>This is subclassed by ArrayType, PointerType and VectorType.
   3245     <ul>
   3246       <li><tt>const Type * getElementType() const</tt>: Returns the type of each
   3247       of the elements in the sequential type. </li>
   3248     </ul>
   3249   </dd>
   3250   <dt><tt>ArrayType</tt></dt>
   3251   <dd>This is a subclass of SequentialType and defines the interface for array 
   3252   types.
   3253     <ul>
   3254       <li><tt>unsigned getNumElements() const</tt>: Returns the number of 
   3255       elements in the array. </li>
   3256     </ul>
   3257   </dd>
   3258   <dt><tt>PointerType</tt></dt>
   3259   <dd>Subclass of SequentialType for pointer types.</dd>
   3260   <dt><tt>VectorType</tt></dt>
   3261   <dd>Subclass of SequentialType for vector types. A 
   3262   vector type is similar to an ArrayType but is distinguished because it is 
   3263   a first class type whereas ArrayType is not. Vector types are used for 
   3264   vector operations and are usually small vectors of of an integer or floating 
   3265   point type.</dd>
   3266   <dt><tt>StructType</tt></dt>
   3267   <dd>Subclass of DerivedTypes for struct types.</dd>
   3268   <dt><tt><a name="FunctionType">FunctionType</a></tt></dt>
   3269   <dd>Subclass of DerivedTypes for function types.
   3270     <ul>
   3271       <li><tt>bool isVarArg() const</tt>: Returns true if it's a vararg
   3272       function</li>
   3273       <li><tt> const Type * getReturnType() const</tt>: Returns the
   3274       return type of the function.</li>
   3275       <li><tt>const Type * getParamType (unsigned i)</tt>: Returns
   3276       the type of the ith parameter.</li>
   3277       <li><tt> const unsigned getNumParams() const</tt>: Returns the
   3278       number of formal parameters.</li>
   3279     </ul>
   3280   </dd>
   3281 </dl>
   3282 </div>
   3283 
   3284 </div>
   3285 
   3286 <!-- ======================================================================= -->
   3287 <h3>
   3288   <a name="Module">The <tt>Module</tt> class</a>
   3289 </h3>
   3290 
   3291 <div>
   3292 
   3293 <p><tt>#include "<a
   3294 href="/doxygen/Module_8h-source.html">llvm/Module.h</a>"</tt><br> doxygen info:
   3295 <a href="/doxygen/classllvm_1_1Module.html">Module Class</a></p>
   3296 
   3297 <p>The <tt>Module</tt> class represents the top level structure present in LLVM
   3298 programs.  An LLVM module is effectively either a translation unit of the
   3299 original program or a combination of several translation units merged by the
   3300 linker.  The <tt>Module</tt> class keeps track of a list of <a
   3301 href="#Function"><tt>Function</tt></a>s, a list of <a
   3302 href="#GlobalVariable"><tt>GlobalVariable</tt></a>s, and a <a
   3303 href="#SymbolTable"><tt>SymbolTable</tt></a>.  Additionally, it contains a few
   3304 helpful member functions that try to make common operations easy.</p>
   3305 
   3306 <!-- _______________________________________________________________________ -->
   3307 <h4>
   3308   <a name="m_Module">Important Public Members of the <tt>Module</tt> class</a>
   3309 </h4>
   3310 
   3311 <div>
   3312 
   3313 <ul>
   3314   <li><tt>Module::Module(std::string name = "")</tt>
   3315 
   3316   <p>Constructing a <a href="#Module">Module</a> is easy. You can optionally
   3317 provide a name for it (probably based on the name of the translation unit).</p>
   3318   </li>
   3319 
   3320   <li><tt>Module::iterator</tt> - Typedef for function list iterator<br>
   3321     <tt>Module::const_iterator</tt> - Typedef for const_iterator.<br>
   3322 
   3323     <tt>begin()</tt>, <tt>end()</tt>
   3324     <tt>size()</tt>, <tt>empty()</tt>
   3325 
   3326     <p>These are forwarding methods that make it easy to access the contents of
   3327     a <tt>Module</tt> object's <a href="#Function"><tt>Function</tt></a>
   3328     list.</p></li>
   3329 
   3330   <li><tt>Module::FunctionListType &amp;getFunctionList()</tt>
   3331 
   3332     <p> Returns the list of <a href="#Function"><tt>Function</tt></a>s.  This is
   3333     necessary to use when you need to update the list or perform a complex
   3334     action that doesn't have a forwarding method.</p>
   3335 
   3336     <p><!--  Global Variable --></p></li> 
   3337 </ul>
   3338 
   3339 <hr>
   3340 
   3341 <ul>
   3342   <li><tt>Module::global_iterator</tt> - Typedef for global variable list iterator<br>
   3343 
   3344     <tt>Module::const_global_iterator</tt> - Typedef for const_iterator.<br>
   3345 
   3346     <tt>global_begin()</tt>, <tt>global_end()</tt>
   3347     <tt>global_size()</tt>, <tt>global_empty()</tt>
   3348 
   3349     <p> These are forwarding methods that make it easy to access the contents of
   3350     a <tt>Module</tt> object's <a
   3351     href="#GlobalVariable"><tt>GlobalVariable</tt></a> list.</p></li>
   3352 
   3353   <li><tt>Module::GlobalListType &amp;getGlobalList()</tt>
   3354 
   3355     <p>Returns the list of <a
   3356     href="#GlobalVariable"><tt>GlobalVariable</tt></a>s.  This is necessary to
   3357     use when you need to update the list or perform a complex action that
   3358     doesn't have a forwarding method.</p>
   3359 
   3360     <p><!--  Symbol table stuff --> </p></li>
   3361 </ul>
   3362 
   3363 <hr>
   3364 
   3365 <ul>
   3366   <li><tt><a href="#SymbolTable">SymbolTable</a> *getSymbolTable()</tt>
   3367 
   3368     <p>Return a reference to the <a href="#SymbolTable"><tt>SymbolTable</tt></a>
   3369     for this <tt>Module</tt>.</p>
   3370 
   3371     <p><!--  Convenience methods --></p></li>
   3372 </ul>
   3373 
   3374 <hr>
   3375 
   3376 <ul>
   3377   <li><tt><a href="#Function">Function</a> *getFunction(const std::string
   3378   &amp;Name, const <a href="#FunctionType">FunctionType</a> *Ty)</tt>
   3379 
   3380     <p>Look up the specified function in the <tt>Module</tt> <a
   3381     href="#SymbolTable"><tt>SymbolTable</tt></a>. If it does not exist, return
   3382     <tt>null</tt>.</p></li>
   3383 
   3384   <li><tt><a href="#Function">Function</a> *getOrInsertFunction(const
   3385   std::string &amp;Name, const <a href="#FunctionType">FunctionType</a> *T)</tt>
   3386 
   3387     <p>Look up the specified function in the <tt>Module</tt> <a
   3388     href="#SymbolTable"><tt>SymbolTable</tt></a>. If it does not exist, add an
   3389     external declaration for the function and return it.</p></li>
   3390 
   3391   <li><tt>std::string getTypeName(const <a href="#Type">Type</a> *Ty)</tt>
   3392 
   3393     <p>If there is at least one entry in the <a
   3394     href="#SymbolTable"><tt>SymbolTable</tt></a> for the specified <a
   3395     href="#Type"><tt>Type</tt></a>, return it.  Otherwise return the empty
   3396     string.</p></li>
   3397 
   3398   <li><tt>bool addTypeName(const std::string &amp;Name, const <a
   3399   href="#Type">Type</a> *Ty)</tt>
   3400 
   3401     <p>Insert an entry in the <a href="#SymbolTable"><tt>SymbolTable</tt></a>
   3402     mapping <tt>Name</tt> to <tt>Ty</tt>. If there is already an entry for this
   3403     name, true is returned and the <a
   3404     href="#SymbolTable"><tt>SymbolTable</tt></a> is not modified.</p></li>
   3405 </ul>
   3406 
   3407 </div>
   3408 
   3409 </div>
   3410 
   3411 <!-- ======================================================================= -->
   3412 <h3>
   3413   <a name="Value">The <tt>Value</tt> class</a>
   3414 </h3>
   3415 
   3416 <div>
   3417 
   3418 <p><tt>#include "<a href="/doxygen/Value_8h-source.html">llvm/Value.h</a>"</tt>
   3419 <br> 
   3420 doxygen info: <a href="/doxygen/classllvm_1_1Value.html">Value Class</a></p>
   3421 
   3422 <p>The <tt>Value</tt> class is the most important class in the LLVM Source
   3423 base.  It represents a typed value that may be used (among other things) as an
   3424 operand to an instruction.  There are many different types of <tt>Value</tt>s,
   3425 such as <a href="#Constant"><tt>Constant</tt></a>s,<a
   3426 href="#Argument"><tt>Argument</tt></a>s. Even <a
   3427 href="#Instruction"><tt>Instruction</tt></a>s and <a
   3428 href="#Function"><tt>Function</tt></a>s are <tt>Value</tt>s.</p>
   3429 
   3430 <p>A particular <tt>Value</tt> may be used many times in the LLVM representation
   3431 for a program.  For example, an incoming argument to a function (represented
   3432 with an instance of the <a href="#Argument">Argument</a> class) is "used" by
   3433 every instruction in the function that references the argument.  To keep track
   3434 of this relationship, the <tt>Value</tt> class keeps a list of all of the <a
   3435 href="#User"><tt>User</tt></a>s that is using it (the <a
   3436 href="#User"><tt>User</tt></a> class is a base class for all nodes in the LLVM
   3437 graph that can refer to <tt>Value</tt>s).  This use list is how LLVM represents
   3438 def-use information in the program, and is accessible through the <tt>use_</tt>*
   3439 methods, shown below.</p>
   3440 
   3441 <p>Because LLVM is a typed representation, every LLVM <tt>Value</tt> is typed,
   3442 and this <a href="#Type">Type</a> is available through the <tt>getType()</tt>
   3443 method. In addition, all LLVM values can be named.  The "name" of the
   3444 <tt>Value</tt> is a symbolic string printed in the LLVM code:</p>
   3445 
   3446 <div class="doc_code">
   3447 <pre>
   3448 %<b>foo</b> = add i32 1, 2
   3449 </pre>
   3450 </div>
   3451 
   3452 <p><a name="nameWarning">The name of this instruction is "foo".</a> <b>NOTE</b>
   3453 that the name of any value may be missing (an empty string), so names should
   3454 <b>ONLY</b> be used for debugging (making the source code easier to read,
   3455 debugging printouts), they should not be used to keep track of values or map
   3456 between them.  For this purpose, use a <tt>std::map</tt> of pointers to the
   3457 <tt>Value</tt> itself instead.</p>
   3458 
   3459 <p>One important aspect of LLVM is that there is no distinction between an SSA
   3460 variable and the operation that produces it.  Because of this, any reference to
   3461 the value produced by an instruction (or the value available as an incoming
   3462 argument, for example) is represented as a direct pointer to the instance of
   3463 the class that
   3464 represents this value.  Although this may take some getting used to, it
   3465 simplifies the representation and makes it easier to manipulate.</p>
   3466 
   3467 <!-- _______________________________________________________________________ -->
   3468 <h4>
   3469   <a name="m_Value">Important Public Members of the <tt>Value</tt> class</a>
   3470 </h4>
   3471 
   3472 <div>
   3473 
   3474 <ul>
   3475   <li><tt>Value::use_iterator</tt> - Typedef for iterator over the
   3476 use-list<br>
   3477     <tt>Value::const_use_iterator</tt> - Typedef for const_iterator over
   3478 the use-list<br>
   3479     <tt>unsigned use_size()</tt> - Returns the number of users of the
   3480 value.<br>
   3481     <tt>bool use_empty()</tt> - Returns true if there are no users.<br>
   3482     <tt>use_iterator use_begin()</tt> - Get an iterator to the start of
   3483 the use-list.<br>
   3484     <tt>use_iterator use_end()</tt> - Get an iterator to the end of the
   3485 use-list.<br>
   3486     <tt><a href="#User">User</a> *use_back()</tt> - Returns the last
   3487 element in the list.
   3488     <p> These methods are the interface to access the def-use
   3489 information in LLVM.  As with all other iterators in LLVM, the naming
   3490 conventions follow the conventions defined by the <a href="#stl">STL</a>.</p>
   3491   </li>
   3492   <li><tt><a href="#Type">Type</a> *getType() const</tt>
   3493     <p>This method returns the Type of the Value.</p>
   3494   </li>
   3495   <li><tt>bool hasName() const</tt><br>
   3496     <tt>std::string getName() const</tt><br>
   3497     <tt>void setName(const std::string &amp;Name)</tt>
   3498     <p> This family of methods is used to access and assign a name to a <tt>Value</tt>,
   3499 be aware of the <a href="#nameWarning">precaution above</a>.</p>
   3500   </li>
   3501   <li><tt>void replaceAllUsesWith(Value *V)</tt>
   3502 
   3503     <p>This method traverses the use list of a <tt>Value</tt> changing all <a
   3504     href="#User"><tt>User</tt>s</a> of the current value to refer to
   3505     "<tt>V</tt>" instead.  For example, if you detect that an instruction always
   3506     produces a constant value (for example through constant folding), you can
   3507     replace all uses of the instruction with the constant like this:</p>
   3508 
   3509 <div class="doc_code">
   3510 <pre>
   3511 Inst-&gt;replaceAllUsesWith(ConstVal);
   3512 </pre>
   3513 </div>
   3514 
   3515 </ul>
   3516 
   3517 </div>
   3518 
   3519 </div>
   3520 
   3521 <!-- ======================================================================= -->
   3522 <h3>
   3523   <a name="User">The <tt>User</tt> class</a>
   3524 </h3>
   3525 
   3526 <div>
   3527   
   3528 <p>
   3529 <tt>#include "<a href="/doxygen/User_8h-source.html">llvm/User.h</a>"</tt><br>
   3530 doxygen info: <a href="/doxygen/classllvm_1_1User.html">User Class</a><br>
   3531 Superclass: <a href="#Value"><tt>Value</tt></a></p>
   3532 
   3533 <p>The <tt>User</tt> class is the common base class of all LLVM nodes that may
   3534 refer to <a href="#Value"><tt>Value</tt></a>s.  It exposes a list of "Operands"
   3535 that are all of the <a href="#Value"><tt>Value</tt></a>s that the User is
   3536 referring to.  The <tt>User</tt> class itself is a subclass of
   3537 <tt>Value</tt>.</p>
   3538 
   3539 <p>The operands of a <tt>User</tt> point directly to the LLVM <a
   3540 href="#Value"><tt>Value</tt></a> that it refers to.  Because LLVM uses Static
   3541 Single Assignment (SSA) form, there can only be one definition referred to,
   3542 allowing this direct connection.  This connection provides the use-def
   3543 information in LLVM.</p>
   3544 
   3545 <!-- _______________________________________________________________________ -->
   3546 <h4>
   3547   <a name="m_User">Important Public Members of the <tt>User</tt> class</a>
   3548 </h4>
   3549 
   3550 <div>
   3551 
   3552 <p>The <tt>User</tt> class exposes the operand list in two ways: through
   3553 an index access interface and through an iterator based interface.</p>
   3554 
   3555 <ul>
   3556   <li><tt>Value *getOperand(unsigned i)</tt><br>
   3557     <tt>unsigned getNumOperands()</tt>
   3558     <p> These two methods expose the operands of the <tt>User</tt> in a
   3559 convenient form for direct access.</p></li>
   3560 
   3561   <li><tt>User::op_iterator</tt> - Typedef for iterator over the operand
   3562 list<br>
   3563     <tt>op_iterator op_begin()</tt> - Get an iterator to the start of 
   3564 the operand list.<br>
   3565     <tt>op_iterator op_end()</tt> - Get an iterator to the end of the
   3566 operand list.
   3567     <p> Together, these methods make up the iterator based interface to
   3568 the operands of a <tt>User</tt>.</p></li>
   3569 </ul>
   3570 
   3571 </div>    
   3572 
   3573 </div>
   3574 
   3575 <!-- ======================================================================= -->
   3576 <h3>
   3577   <a name="Instruction">The <tt>Instruction</tt> class</a>
   3578 </h3>
   3579 
   3580 <div>
   3581 
   3582 <p><tt>#include "</tt><tt><a
   3583 href="/doxygen/Instruction_8h-source.html">llvm/Instruction.h</a>"</tt><br>
   3584 doxygen info: <a href="/doxygen/classllvm_1_1Instruction.html">Instruction Class</a><br>
   3585 Superclasses: <a href="#User"><tt>User</tt></a>, <a
   3586 href="#Value"><tt>Value</tt></a></p>
   3587 
   3588 <p>The <tt>Instruction</tt> class is the common base class for all LLVM
   3589 instructions.  It provides only a few methods, but is a very commonly used
   3590 class.  The primary data tracked by the <tt>Instruction</tt> class itself is the
   3591 opcode (instruction type) and the parent <a
   3592 href="#BasicBlock"><tt>BasicBlock</tt></a> the <tt>Instruction</tt> is embedded
   3593 into.  To represent a specific type of instruction, one of many subclasses of
   3594 <tt>Instruction</tt> are used.</p>
   3595 
   3596 <p> Because the <tt>Instruction</tt> class subclasses the <a
   3597 href="#User"><tt>User</tt></a> class, its operands can be accessed in the same
   3598 way as for other <a href="#User"><tt>User</tt></a>s (with the
   3599 <tt>getOperand()</tt>/<tt>getNumOperands()</tt> and
   3600 <tt>op_begin()</tt>/<tt>op_end()</tt> methods).</p> <p> An important file for
   3601 the <tt>Instruction</tt> class is the <tt>llvm/Instruction.def</tt> file. This
   3602 file contains some meta-data about the various different types of instructions
   3603 in LLVM.  It describes the enum values that are used as opcodes (for example
   3604 <tt>Instruction::Add</tt> and <tt>Instruction::ICmp</tt>), as well as the
   3605 concrete sub-classes of <tt>Instruction</tt> that implement the instruction (for
   3606 example <tt><a href="#BinaryOperator">BinaryOperator</a></tt> and <tt><a
   3607 href="#CmpInst">CmpInst</a></tt>).  Unfortunately, the use of macros in
   3608 this file confuses doxygen, so these enum values don't show up correctly in the
   3609 <a href="/doxygen/classllvm_1_1Instruction.html">doxygen output</a>.</p>
   3610 
   3611 <!-- _______________________________________________________________________ -->
   3612 <h4>
   3613   <a name="s_Instruction">
   3614     Important Subclasses of the <tt>Instruction</tt> class
   3615   </a>
   3616 </h4>
   3617 <div>
   3618   <ul>
   3619     <li><tt><a name="BinaryOperator">BinaryOperator</a></tt>
   3620     <p>This subclasses represents all two operand instructions whose operands
   3621     must be the same type, except for the comparison instructions.</p></li>
   3622     <li><tt><a name="CastInst">CastInst</a></tt>
   3623     <p>This subclass is the parent of the 12 casting instructions. It provides
   3624     common operations on cast instructions.</p>
   3625     <li><tt><a name="CmpInst">CmpInst</a></tt>
   3626     <p>This subclass respresents the two comparison instructions, 
   3627     <a href="LangRef.html#i_icmp">ICmpInst</a> (integer opreands), and
   3628     <a href="LangRef.html#i_fcmp">FCmpInst</a> (floating point operands).</p>
   3629     <li><tt><a name="TerminatorInst">TerminatorInst</a></tt>
   3630     <p>This subclass is the parent of all terminator instructions (those which
   3631     can terminate a block).</p>
   3632   </ul>
   3633   </div>
   3634 
   3635 <!-- _______________________________________________________________________ -->
   3636 <h4>
   3637   <a name="m_Instruction">
   3638     Important Public Members of the <tt>Instruction</tt> class
   3639   </a>
   3640 </h4>
   3641 
   3642 <div>
   3643 
   3644 <ul>
   3645   <li><tt><a href="#BasicBlock">BasicBlock</a> *getParent()</tt>
   3646     <p>Returns the <a href="#BasicBlock"><tt>BasicBlock</tt></a> that
   3647 this  <tt>Instruction</tt> is embedded into.</p></li>
   3648   <li><tt>bool mayWriteToMemory()</tt>
   3649     <p>Returns true if the instruction writes to memory, i.e. it is a
   3650       <tt>call</tt>,<tt>free</tt>,<tt>invoke</tt>, or <tt>store</tt>.</p></li>
   3651   <li><tt>unsigned getOpcode()</tt>
   3652     <p>Returns the opcode for the <tt>Instruction</tt>.</p></li>
   3653   <li><tt><a href="#Instruction">Instruction</a> *clone() const</tt>
   3654     <p>Returns another instance of the specified instruction, identical
   3655 in all ways to the original except that the instruction has no parent
   3656 (ie it's not embedded into a <a href="#BasicBlock"><tt>BasicBlock</tt></a>),
   3657 and it has no name</p></li>
   3658 </ul>
   3659 
   3660 </div>
   3661 
   3662 </div>
   3663 
   3664 <!-- ======================================================================= -->
   3665 <h3>
   3666   <a name="Constant">The <tt>Constant</tt> class and subclasses</a>
   3667 </h3>
   3668 
   3669 <div>
   3670 
   3671 <p>Constant represents a base class for different types of constants. It
   3672 is subclassed by ConstantInt, ConstantArray, etc. for representing 
   3673 the various types of Constants.  <a href="#GlobalValue">GlobalValue</a> is also
   3674 a subclass, which represents the address of a global variable or function.
   3675 </p>
   3676 
   3677 <!-- _______________________________________________________________________ -->
   3678 <h4>Important Subclasses of Constant</h4>
   3679 <div>
   3680 <ul>
   3681   <li>ConstantInt : This subclass of Constant represents an integer constant of
   3682   any width.
   3683     <ul>
   3684       <li><tt>const APInt&amp; getValue() const</tt>: Returns the underlying
   3685       value of this constant, an APInt value.</li>
   3686       <li><tt>int64_t getSExtValue() const</tt>: Converts the underlying APInt
   3687       value to an int64_t via sign extension. If the value (not the bit width)
   3688       of the APInt is too large to fit in an int64_t, an assertion will result.
   3689       For this reason, use of this method is discouraged.</li>
   3690       <li><tt>uint64_t getZExtValue() const</tt>: Converts the underlying APInt
   3691       value to a uint64_t via zero extension. IF the value (not the bit width)
   3692       of the APInt is too large to fit in a uint64_t, an assertion will result.
   3693       For this reason, use of this method is discouraged.</li>
   3694       <li><tt>static ConstantInt* get(const APInt&amp; Val)</tt>: Returns the
   3695       ConstantInt object that represents the value provided by <tt>Val</tt>.
   3696       The type is implied as the IntegerType that corresponds to the bit width
   3697       of <tt>Val</tt>.</li>
   3698       <li><tt>static ConstantInt* get(const Type *Ty, uint64_t Val)</tt>: 
   3699       Returns the ConstantInt object that represents the value provided by 
   3700       <tt>Val</tt> for integer type <tt>Ty</tt>.</li>
   3701     </ul>
   3702   </li>
   3703   <li>ConstantFP : This class represents a floating point constant.
   3704     <ul>
   3705       <li><tt>double getValue() const</tt>: Returns the underlying value of 
   3706       this constant. </li>
   3707     </ul>
   3708   </li>
   3709   <li>ConstantArray : This represents a constant array.
   3710     <ul>
   3711       <li><tt>const std::vector&lt;Use&gt; &amp;getValues() const</tt>: Returns 
   3712       a vector of component constants that makeup this array. </li>
   3713     </ul>
   3714   </li>
   3715   <li>ConstantStruct : This represents a constant struct.
   3716     <ul>
   3717       <li><tt>const std::vector&lt;Use&gt; &amp;getValues() const</tt>: Returns 
   3718       a vector of component constants that makeup this array. </li>
   3719     </ul>
   3720   </li>
   3721   <li>GlobalValue : This represents either a global variable or a function. In 
   3722   either case, the value is a constant fixed address (after linking). 
   3723   </li>
   3724 </ul>
   3725 </div>
   3726 
   3727 </div>
   3728 
   3729 <!-- ======================================================================= -->
   3730 <h3>
   3731   <a name="GlobalValue">The <tt>GlobalValue</tt> class</a>
   3732 </h3>
   3733 
   3734 <div>
   3735 
   3736 <p><tt>#include "<a
   3737 href="/doxygen/GlobalValue_8h-source.html">llvm/GlobalValue.h</a>"</tt><br>
   3738 doxygen info: <a href="/doxygen/classllvm_1_1GlobalValue.html">GlobalValue
   3739 Class</a><br>
   3740 Superclasses: <a href="#Constant"><tt>Constant</tt></a>, 
   3741 <a href="#User"><tt>User</tt></a>, <a href="#Value"><tt>Value</tt></a></p>
   3742 
   3743 <p>Global values (<a href="#GlobalVariable"><tt>GlobalVariable</tt></a>s or <a
   3744 href="#Function"><tt>Function</tt></a>s) are the only LLVM values that are
   3745 visible in the bodies of all <a href="#Function"><tt>Function</tt></a>s.
   3746 Because they are visible at global scope, they are also subject to linking with
   3747 other globals defined in different translation units.  To control the linking
   3748 process, <tt>GlobalValue</tt>s know their linkage rules. Specifically,
   3749 <tt>GlobalValue</tt>s know whether they have internal or external linkage, as
   3750 defined by the <tt>LinkageTypes</tt> enumeration.</p>
   3751 
   3752 <p>If a <tt>GlobalValue</tt> has internal linkage (equivalent to being
   3753 <tt>static</tt> in C), it is not visible to code outside the current translation
   3754 unit, and does not participate in linking.  If it has external linkage, it is
   3755 visible to external code, and does participate in linking.  In addition to
   3756 linkage information, <tt>GlobalValue</tt>s keep track of which <a
   3757 href="#Module"><tt>Module</tt></a> they are currently part of.</p>
   3758 
   3759 <p>Because <tt>GlobalValue</tt>s are memory objects, they are always referred to
   3760 by their <b>address</b>. As such, the <a href="#Type"><tt>Type</tt></a> of a
   3761 global is always a pointer to its contents. It is important to remember this
   3762 when using the <tt>GetElementPtrInst</tt> instruction because this pointer must
   3763 be dereferenced first. For example, if you have a <tt>GlobalVariable</tt> (a
   3764 subclass of <tt>GlobalValue)</tt> that is an array of 24 ints, type <tt>[24 x
   3765 i32]</tt>, then the <tt>GlobalVariable</tt> is a pointer to that array. Although
   3766 the address of the first element of this array and the value of the
   3767 <tt>GlobalVariable</tt> are the same, they have different types. The
   3768 <tt>GlobalVariable</tt>'s type is <tt>[24 x i32]</tt>. The first element's type
   3769 is <tt>i32.</tt> Because of this, accessing a global value requires you to
   3770 dereference the pointer with <tt>GetElementPtrInst</tt> first, then its elements
   3771 can be accessed. This is explained in the <a href="LangRef.html#globalvars">LLVM
   3772 Language Reference Manual</a>.</p>
   3773 
   3774 <!-- _______________________________________________________________________ -->
   3775 <h4>
   3776   <a name="m_GlobalValue">
   3777     Important Public Members of the <tt>GlobalValue</tt> class
   3778   </a>
   3779 </h4>
   3780 
   3781 <div>
   3782 
   3783 <ul>
   3784   <li><tt>bool hasInternalLinkage() const</tt><br>
   3785     <tt>bool hasExternalLinkage() const</tt><br>
   3786     <tt>void setInternalLinkage(bool HasInternalLinkage)</tt>
   3787     <p> These methods manipulate the linkage characteristics of the <tt>GlobalValue</tt>.</p>
   3788     <p> </p>
   3789   </li>
   3790   <li><tt><a href="#Module">Module</a> *getParent()</tt>
   3791     <p> This returns the <a href="#Module"><tt>Module</tt></a> that the
   3792 GlobalValue is currently embedded into.</p></li>
   3793 </ul>
   3794 
   3795 </div>
   3796 
   3797 </div>
   3798 
   3799 <!-- ======================================================================= -->
   3800 <h3>
   3801   <a name="Function">The <tt>Function</tt> class</a>
   3802 </h3>
   3803 
   3804 <div>
   3805 
   3806 <p><tt>#include "<a
   3807 href="/doxygen/Function_8h-source.html">llvm/Function.h</a>"</tt><br> doxygen
   3808 info: <a href="/doxygen/classllvm_1_1Function.html">Function Class</a><br>
   3809 Superclasses: <a href="#GlobalValue"><tt>GlobalValue</tt></a>, 
   3810 <a href="#Constant"><tt>Constant</tt></a>, 
   3811 <a href="#User"><tt>User</tt></a>, 
   3812 <a href="#Value"><tt>Value</tt></a></p>
   3813 
   3814 <p>The <tt>Function</tt> class represents a single procedure in LLVM.  It is
   3815 actually one of the more complex classes in the LLVM hierarchy because it must
   3816 keep track of a large amount of data.  The <tt>Function</tt> class keeps track
   3817 of a list of <a href="#BasicBlock"><tt>BasicBlock</tt></a>s, a list of formal 
   3818 <a href="#Argument"><tt>Argument</tt></a>s, and a 
   3819 <a href="#SymbolTable"><tt>SymbolTable</tt></a>.</p>
   3820 
   3821 <p>The list of <a href="#BasicBlock"><tt>BasicBlock</tt></a>s is the most
   3822 commonly used part of <tt>Function</tt> objects.  The list imposes an implicit
   3823 ordering of the blocks in the function, which indicate how the code will be
   3824 laid out by the backend.  Additionally, the first <a
   3825 href="#BasicBlock"><tt>BasicBlock</tt></a> is the implicit entry node for the
   3826 <tt>Function</tt>.  It is not legal in LLVM to explicitly branch to this initial
   3827 block.  There are no implicit exit nodes, and in fact there may be multiple exit
   3828 nodes from a single <tt>Function</tt>.  If the <a
   3829 href="#BasicBlock"><tt>BasicBlock</tt></a> list is empty, this indicates that
   3830 the <tt>Function</tt> is actually a function declaration: the actual body of the
   3831 function hasn't been linked in yet.</p>
   3832 
   3833 <p>In addition to a list of <a href="#BasicBlock"><tt>BasicBlock</tt></a>s, the
   3834 <tt>Function</tt> class also keeps track of the list of formal <a
   3835 href="#Argument"><tt>Argument</tt></a>s that the function receives.  This
   3836 container manages the lifetime of the <a href="#Argument"><tt>Argument</tt></a>
   3837 nodes, just like the <a href="#BasicBlock"><tt>BasicBlock</tt></a> list does for
   3838 the <a href="#BasicBlock"><tt>BasicBlock</tt></a>s.</p>
   3839 
   3840 <p>The <a href="#SymbolTable"><tt>SymbolTable</tt></a> is a very rarely used
   3841 LLVM feature that is only used when you have to look up a value by name.  Aside
   3842 from that, the <a href="#SymbolTable"><tt>SymbolTable</tt></a> is used
   3843 internally to make sure that there are not conflicts between the names of <a
   3844 href="#Instruction"><tt>Instruction</tt></a>s, <a
   3845 href="#BasicBlock"><tt>BasicBlock</tt></a>s, or <a
   3846 href="#Argument"><tt>Argument</tt></a>s in the function body.</p>
   3847 
   3848 <p>Note that <tt>Function</tt> is a <a href="#GlobalValue">GlobalValue</a>
   3849 and therefore also a <a href="#Constant">Constant</a>. The value of the function
   3850 is its address (after linking) which is guaranteed to be constant.</p>
   3851 
   3852 <!-- _______________________________________________________________________ -->
   3853 <h4>
   3854   <a name="m_Function">
   3855     Important Public Members of the <tt>Function</tt> class
   3856   </a>
   3857 </h4>
   3858 
   3859 <div>
   3860 
   3861 <ul>
   3862   <li><tt>Function(const </tt><tt><a href="#FunctionType">FunctionType</a>
   3863   *Ty, LinkageTypes Linkage, const std::string &amp;N = "", Module* Parent = 0)</tt>
   3864 
   3865     <p>Constructor used when you need to create new <tt>Function</tt>s to add
   3866     the the program.  The constructor must specify the type of the function to
   3867     create and what type of linkage the function should have. The <a 
   3868     href="#FunctionType"><tt>FunctionType</tt></a> argument
   3869     specifies the formal arguments and return value for the function. The same
   3870     <a href="#FunctionType"><tt>FunctionType</tt></a> value can be used to
   3871     create multiple functions. The <tt>Parent</tt> argument specifies the Module
   3872     in which the function is defined. If this argument is provided, the function
   3873     will automatically be inserted into that module's list of
   3874     functions.</p></li>
   3875 
   3876   <li><tt>bool isDeclaration()</tt>
   3877 
   3878     <p>Return whether or not the <tt>Function</tt> has a body defined.  If the
   3879     function is "external", it does not have a body, and thus must be resolved
   3880     by linking with a function defined in a different translation unit.</p></li>
   3881 
   3882   <li><tt>Function::iterator</tt> - Typedef for basic block list iterator<br>
   3883     <tt>Function::const_iterator</tt> - Typedef for const_iterator.<br>
   3884 
   3885     <tt>begin()</tt>, <tt>end()</tt>
   3886     <tt>size()</tt>, <tt>empty()</tt>
   3887 
   3888     <p>These are forwarding methods that make it easy to access the contents of
   3889     a <tt>Function</tt> object's <a href="#BasicBlock"><tt>BasicBlock</tt></a>
   3890     list.</p></li>
   3891 
   3892   <li><tt>Function::BasicBlockListType &amp;getBasicBlockList()</tt>
   3893 
   3894     <p>Returns the list of <a href="#BasicBlock"><tt>BasicBlock</tt></a>s.  This
   3895     is necessary to use when you need to update the list or perform a complex
   3896     action that doesn't have a forwarding method.</p></li>
   3897 
   3898   <li><tt>Function::arg_iterator</tt> - Typedef for the argument list
   3899 iterator<br>
   3900     <tt>Function::const_arg_iterator</tt> - Typedef for const_iterator.<br>
   3901 
   3902     <tt>arg_begin()</tt>, <tt>arg_end()</tt>
   3903     <tt>arg_size()</tt>, <tt>arg_empty()</tt>
   3904 
   3905     <p>These are forwarding methods that make it easy to access the contents of
   3906     a <tt>Function</tt> object's <a href="#Argument"><tt>Argument</tt></a>
   3907     list.</p></li>
   3908 
   3909   <li><tt>Function::ArgumentListType &amp;getArgumentList()</tt>
   3910 
   3911     <p>Returns the list of <a href="#Argument"><tt>Argument</tt></a>s.  This is
   3912     necessary to use when you need to update the list or perform a complex
   3913     action that doesn't have a forwarding method.</p></li>
   3914 
   3915   <li><tt><a href="#BasicBlock">BasicBlock</a> &amp;getEntryBlock()</tt>
   3916 
   3917     <p>Returns the entry <a href="#BasicBlock"><tt>BasicBlock</tt></a> for the
   3918     function.  Because the entry block for the function is always the first
   3919     block, this returns the first block of the <tt>Function</tt>.</p></li>
   3920 
   3921   <li><tt><a href="#Type">Type</a> *getReturnType()</tt><br>
   3922     <tt><a href="#FunctionType">FunctionType</a> *getFunctionType()</tt>
   3923 
   3924     <p>This traverses the <a href="#Type"><tt>Type</tt></a> of the
   3925     <tt>Function</tt> and returns the return type of the function, or the <a
   3926     href="#FunctionType"><tt>FunctionType</tt></a> of the actual
   3927     function.</p></li>
   3928 
   3929   <li><tt><a href="#SymbolTable">SymbolTable</a> *getSymbolTable()</tt>
   3930 
   3931     <p> Return a pointer to the <a href="#SymbolTable"><tt>SymbolTable</tt></a>
   3932     for this <tt>Function</tt>.</p></li>
   3933 </ul>
   3934 
   3935 </div>
   3936 
   3937 </div>
   3938 
   3939 <!-- ======================================================================= -->
   3940 <h3>
   3941   <a name="GlobalVariable">The <tt>GlobalVariable</tt> class</a>
   3942 </h3>
   3943 
   3944 <div>
   3945 
   3946 <p><tt>#include "<a
   3947 href="/doxygen/GlobalVariable_8h-source.html">llvm/GlobalVariable.h</a>"</tt>
   3948 <br>
   3949 doxygen info: <a href="/doxygen/classllvm_1_1GlobalVariable.html">GlobalVariable
   3950  Class</a><br>
   3951 Superclasses: <a href="#GlobalValue"><tt>GlobalValue</tt></a>, 
   3952 <a href="#Constant"><tt>Constant</tt></a>,
   3953 <a href="#User"><tt>User</tt></a>,
   3954 <a href="#Value"><tt>Value</tt></a></p>
   3955 
   3956 <p>Global variables are represented with the (surprise surprise)
   3957 <tt>GlobalVariable</tt> class. Like functions, <tt>GlobalVariable</tt>s are also
   3958 subclasses of <a href="#GlobalValue"><tt>GlobalValue</tt></a>, and as such are
   3959 always referenced by their address (global values must live in memory, so their
   3960 "name" refers to their constant address). See 
   3961 <a href="#GlobalValue"><tt>GlobalValue</tt></a> for more on this.  Global 
   3962 variables may have an initial value (which must be a 
   3963 <a href="#Constant"><tt>Constant</tt></a>), and if they have an initializer, 
   3964 they may be marked as "constant" themselves (indicating that their contents 
   3965 never change at runtime).</p>
   3966 
   3967 <!-- _______________________________________________________________________ -->
   3968 <h4>
   3969   <a name="m_GlobalVariable">
   3970     Important Public Members of the <tt>GlobalVariable</tt> class
   3971   </a>
   3972 </h4>
   3973 
   3974 <div>
   3975 
   3976 <ul>
   3977   <li><tt>GlobalVariable(const </tt><tt><a href="#Type">Type</a> *Ty, bool
   3978   isConstant, LinkageTypes&amp; Linkage, <a href="#Constant">Constant</a>
   3979   *Initializer = 0, const std::string &amp;Name = "", Module* Parent = 0)</tt>
   3980 
   3981     <p>Create a new global variable of the specified type. If
   3982     <tt>isConstant</tt> is true then the global variable will be marked as
   3983     unchanging for the program. The Linkage parameter specifies the type of
   3984     linkage (internal, external, weak, linkonce, appending) for the variable.
   3985     If the linkage is InternalLinkage, WeakAnyLinkage, WeakODRLinkage,
   3986     LinkOnceAnyLinkage or LinkOnceODRLinkage,&nbsp; then the resultant
   3987     global variable will have internal linkage.  AppendingLinkage concatenates
   3988     together all instances (in different translation units) of the variable
   3989     into a single variable but is only applicable to arrays.  &nbsp;See
   3990     the <a href="LangRef.html#modulestructure">LLVM Language Reference</a> for
   3991     further details on linkage types. Optionally an initializer, a name, and the
   3992     module to put the variable into may be specified for the global variable as
   3993     well.</p></li>
   3994 
   3995   <li><tt>bool isConstant() const</tt>
   3996 
   3997     <p>Returns true if this is a global variable that is known not to
   3998     be modified at runtime.</p></li>
   3999 
   4000   <li><tt>bool hasInitializer()</tt>
   4001 
   4002     <p>Returns true if this <tt>GlobalVariable</tt> has an intializer.</p></li>
   4003 
   4004   <li><tt><a href="#Constant">Constant</a> *getInitializer()</tt>
   4005 
   4006     <p>Returns the initial value for a <tt>GlobalVariable</tt>.  It is not legal
   4007     to call this method if there is no initializer.</p></li>
   4008 </ul>
   4009 
   4010 </div>
   4011 
   4012 </div>
   4013 
   4014 <!-- ======================================================================= -->
   4015 <h3>
   4016   <a name="BasicBlock">The <tt>BasicBlock</tt> class</a>
   4017 </h3>
   4018 
   4019 <div>
   4020 
   4021 <p><tt>#include "<a
   4022 href="/doxygen/BasicBlock_8h-source.html">llvm/BasicBlock.h</a>"</tt><br>
   4023 doxygen info: <a href="/doxygen/classllvm_1_1BasicBlock.html">BasicBlock
   4024 Class</a><br>
   4025 Superclass: <a href="#Value"><tt>Value</tt></a></p>
   4026 
   4027 <p>This class represents a single entry single exit section of the code,
   4028 commonly known as a basic block by the compiler community.  The
   4029 <tt>BasicBlock</tt> class maintains a list of <a
   4030 href="#Instruction"><tt>Instruction</tt></a>s, which form the body of the block.
   4031 Matching the language definition, the last element of this list of instructions
   4032 is always a terminator instruction (a subclass of the <a
   4033 href="#TerminatorInst"><tt>TerminatorInst</tt></a> class).</p>
   4034 
   4035 <p>In addition to tracking the list of instructions that make up the block, the
   4036 <tt>BasicBlock</tt> class also keeps track of the <a
   4037 href="#Function"><tt>Function</tt></a> that it is embedded into.</p>
   4038 
   4039 <p>Note that <tt>BasicBlock</tt>s themselves are <a
   4040 href="#Value"><tt>Value</tt></a>s, because they are referenced by instructions
   4041 like branches and can go in the switch tables. <tt>BasicBlock</tt>s have type
   4042 <tt>label</tt>.</p>
   4043 
   4044 <!-- _______________________________________________________________________ -->
   4045 <h4>
   4046   <a name="m_BasicBlock">
   4047     Important Public Members of the <tt>BasicBlock</tt> class
   4048   </a>
   4049 </h4>
   4050 
   4051 <div>
   4052 <ul>
   4053 
   4054 <li><tt>BasicBlock(const std::string &amp;Name = "", </tt><tt><a
   4055  href="#Function">Function</a> *Parent = 0)</tt>
   4056 
   4057 <p>The <tt>BasicBlock</tt> constructor is used to create new basic blocks for
   4058 insertion into a function.  The constructor optionally takes a name for the new
   4059 block, and a <a href="#Function"><tt>Function</tt></a> to insert it into.  If
   4060 the <tt>Parent</tt> parameter is specified, the new <tt>BasicBlock</tt> is
   4061 automatically inserted at the end of the specified <a
   4062 href="#Function"><tt>Function</tt></a>, if not specified, the BasicBlock must be
   4063 manually inserted into the <a href="#Function"><tt>Function</tt></a>.</p></li>
   4064 
   4065 <li><tt>BasicBlock::iterator</tt> - Typedef for instruction list iterator<br>
   4066 <tt>BasicBlock::const_iterator</tt> - Typedef for const_iterator.<br>
   4067 <tt>begin()</tt>, <tt>end()</tt>, <tt>front()</tt>, <tt>back()</tt>,
   4068 <tt>size()</tt>, <tt>empty()</tt>
   4069 STL-style functions for accessing the instruction list.
   4070 
   4071 <p>These methods and typedefs are forwarding functions that have the same
   4072 semantics as the standard library methods of the same names.  These methods
   4073 expose the underlying instruction list of a basic block in a way that is easy to
   4074 manipulate.  To get the full complement of container operations (including
   4075 operations to update the list), you must use the <tt>getInstList()</tt>
   4076 method.</p></li>
   4077 
   4078 <li><tt>BasicBlock::InstListType &amp;getInstList()</tt>
   4079 
   4080 <p>This method is used to get access to the underlying container that actually
   4081 holds the Instructions.  This method must be used when there isn't a forwarding
   4082 function in the <tt>BasicBlock</tt> class for the operation that you would like
   4083 to perform.  Because there are no forwarding functions for "updating"
   4084 operations, you need to use this if you want to update the contents of a
   4085 <tt>BasicBlock</tt>.</p></li>
   4086 
   4087 <li><tt><a href="#Function">Function</a> *getParent()</tt>
   4088 
   4089 <p> Returns a pointer to <a href="#Function"><tt>Function</tt></a> the block is
   4090 embedded into, or a null pointer if it is homeless.</p></li>
   4091 
   4092 <li><tt><a href="#TerminatorInst">TerminatorInst</a> *getTerminator()</tt>
   4093 
   4094 <p> Returns a pointer to the terminator instruction that appears at the end of
   4095 the <tt>BasicBlock</tt>.  If there is no terminator instruction, or if the last
   4096 instruction in the block is not a terminator, then a null pointer is
   4097 returned.</p></li>
   4098 
   4099 </ul>
   4100 
   4101 </div>
   4102 
   4103 </div>
   4104 
   4105 <!-- ======================================================================= -->
   4106 <h3>
   4107   <a name="Argument">The <tt>Argument</tt> class</a>
   4108 </h3>
   4109 
   4110 <div>
   4111 
   4112 <p>This subclass of Value defines the interface for incoming formal
   4113 arguments to a function. A Function maintains a list of its formal
   4114 arguments. An argument has a pointer to the parent Function.</p>
   4115 
   4116 </div>
   4117 
   4118 </div>
   4119 
   4120 <!-- *********************************************************************** -->
   4121 <hr>
   4122 <address>
   4123   <a href="http://jigsaw.w3.org/css-validator/check/referer"><img
   4124   src="http://jigsaw.w3.org/css-validator/images/vcss-blue" alt="Valid CSS"></a>
   4125   <a href="http://validator.w3.org/check/referer"><img
   4126   src="http://www.w3.org/Icons/valid-html401" alt="Valid HTML 4.01 Strict"></a>
   4127 
   4128   <a href="mailto:dhurjati (a] cs.uiuc.edu">Dinakar Dhurjati</a> and
   4129   <a href="mailto:sabre (a] nondot.org">Chris Lattner</a><br>
   4130   <a href="http://llvm.org/">The LLVM Compiler Infrastructure</a><br>
   4131   Last modified: $Date$
   4132 </address>
   4133 
   4134 </body>
   4135 </html>
   4136