• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
2                      "http://www.w3.org/TR/html4/strict.dtd">
3<html>
4<head>
5  <title>LLVM Assembly Language Reference Manual</title>
6  <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
7  <meta name="author" content="Chris Lattner">
8  <meta name="description"
9  content="LLVM Assembly Language Reference Manual.">
10  <link rel="stylesheet" href="llvm.css" type="text/css">
11</head>
12
13<body>
14
15<h1>LLVM Language Reference Manual</h1>
16<ol>
17  <li><a href="#abstract">Abstract</a></li>
18  <li><a href="#introduction">Introduction</a></li>
19  <li><a href="#identifiers">Identifiers</a></li>
20  <li><a href="#highlevel">High Level Structure</a>
21    <ol>
22      <li><a href="#modulestructure">Module Structure</a></li>
23      <li><a href="#linkage">Linkage Types</a>
24        <ol>
25          <li><a href="#linkage_private">'<tt>private</tt>' Linkage</a></li>
26          <li><a href="#linkage_linker_private">'<tt>linker_private</tt>' Linkage</a></li>
27          <li><a href="#linkage_linker_private_weak">'<tt>linker_private_weak</tt>' Linkage</a></li>
28          <li><a href="#linkage_linker_private_weak_def_auto">'<tt>linker_private_weak_def_auto</tt>' Linkage</a></li>
29          <li><a href="#linkage_internal">'<tt>internal</tt>' Linkage</a></li>
30          <li><a href="#linkage_available_externally">'<tt>available_externally</tt>' Linkage</a></li>
31          <li><a href="#linkage_linkonce">'<tt>linkonce</tt>' Linkage</a></li>
32          <li><a href="#linkage_common">'<tt>common</tt>' Linkage</a></li>
33          <li><a href="#linkage_weak">'<tt>weak</tt>' Linkage</a></li>
34          <li><a href="#linkage_appending">'<tt>appending</tt>' Linkage</a></li>
35          <li><a href="#linkage_externweak">'<tt>extern_weak</tt>' Linkage</a></li>
36          <li><a href="#linkage_linkonce_odr">'<tt>linkonce_odr</tt>' Linkage</a></li>
37          <li><a href="#linkage_weak">'<tt>weak_odr</tt>' Linkage</a></li>
38          <li><a href="#linkage_external">'<tt>external</tt>' Linkage</a></li>
39          <li><a href="#linkage_dllimport">'<tt>dllimport</tt>' Linkage</a></li>
40          <li><a href="#linkage_dllexport">'<tt>dllexport</tt>' Linkage</a></li>
41        </ol>
42      </li>
43      <li><a href="#callingconv">Calling Conventions</a></li>
44      <li><a href="#namedtypes">Named Types</a></li>
45      <li><a href="#globalvars">Global Variables</a></li>
46      <li><a href="#functionstructure">Functions</a></li>
47      <li><a href="#aliasstructure">Aliases</a></li>
48      <li><a href="#namedmetadatastructure">Named Metadata</a></li>
49      <li><a href="#paramattrs">Parameter Attributes</a></li>
50      <li><a href="#fnattrs">Function Attributes</a></li>
51      <li><a href="#gc">Garbage Collector Names</a></li>
52      <li><a href="#moduleasm">Module-Level Inline Assembly</a></li>
53      <li><a href="#datalayout">Data Layout</a></li>
54      <li><a href="#pointeraliasing">Pointer Aliasing Rules</a></li>
55      <li><a href="#volatile">Volatile Memory Accesses</a></li>
56      <li><a href="#memmodel">Memory Model for Concurrent Operations</a></li>
57      <li><a href="#ordering">Atomic Memory Ordering Constraints</a></li>
58    </ol>
59  </li>
60  <li><a href="#typesystem">Type System</a>
61    <ol>
62      <li><a href="#t_classifications">Type Classifications</a></li>
63      <li><a href="#t_primitive">Primitive Types</a>
64        <ol>
65          <li><a href="#t_integer">Integer Type</a></li>
66          <li><a href="#t_floating">Floating Point Types</a></li>
67          <li><a href="#t_x86mmx">X86mmx Type</a></li>
68          <li><a href="#t_void">Void Type</a></li>
69          <li><a href="#t_label">Label Type</a></li>
70          <li><a href="#t_metadata">Metadata Type</a></li>
71        </ol>
72      </li>
73      <li><a href="#t_derived">Derived Types</a>
74        <ol>
75          <li><a href="#t_aggregate">Aggregate Types</a>
76            <ol>
77              <li><a href="#t_array">Array Type</a></li>
78              <li><a href="#t_struct">Structure Type</a></li>
79              <li><a href="#t_opaque">Opaque Structure Types</a></li>
80              <li><a href="#t_vector">Vector Type</a></li>
81            </ol>
82          </li>
83          <li><a href="#t_function">Function Type</a></li>
84          <li><a href="#t_pointer">Pointer Type</a></li>
85        </ol>
86      </li>
87    </ol>
88  </li>
89  <li><a href="#constants">Constants</a>
90    <ol>
91      <li><a href="#simpleconstants">Simple Constants</a></li>
92      <li><a href="#complexconstants">Complex Constants</a></li>
93      <li><a href="#globalconstants">Global Variable and Function Addresses</a></li>
94      <li><a href="#undefvalues">Undefined Values</a></li>
95      <li><a href="#trapvalues">Trap Values</a></li>
96      <li><a href="#blockaddress">Addresses of Basic Blocks</a></li>
97      <li><a href="#constantexprs">Constant Expressions</a></li>
98    </ol>
99  </li>
100  <li><a href="#othervalues">Other Values</a>
101    <ol>
102      <li><a href="#inlineasm">Inline Assembler Expressions</a></li>
103      <li><a href="#metadata">Metadata Nodes and Metadata Strings</a></li>
104    </ol>
105  </li>
106  <li><a href="#intrinsic_globals">Intrinsic Global Variables</a>
107    <ol>
108      <li><a href="#intg_used">The '<tt>llvm.used</tt>' Global Variable</a></li>
109      <li><a href="#intg_compiler_used">The '<tt>llvm.compiler.used</tt>'
110          Global Variable</a></li>
111      <li><a href="#intg_global_ctors">The '<tt>llvm.global_ctors</tt>'
112         Global Variable</a></li>
113      <li><a href="#intg_global_dtors">The '<tt>llvm.global_dtors</tt>'
114         Global Variable</a></li>
115    </ol>
116  </li>
117  <li><a href="#instref">Instruction Reference</a>
118    <ol>
119      <li><a href="#terminators">Terminator Instructions</a>
120        <ol>
121          <li><a href="#i_ret">'<tt>ret</tt>' Instruction</a></li>
122          <li><a href="#i_br">'<tt>br</tt>' Instruction</a></li>
123          <li><a href="#i_switch">'<tt>switch</tt>' Instruction</a></li>
124          <li><a href="#i_indirectbr">'<tt>indirectbr</tt>' Instruction</a></li>
125          <li><a href="#i_invoke">'<tt>invoke</tt>' Instruction</a></li>
126          <li><a href="#i_unwind">'<tt>unwind</tt>'  Instruction</a></li>
127          <li><a href="#i_resume">'<tt>resume</tt>'  Instruction</a></li>
128          <li><a href="#i_unreachable">'<tt>unreachable</tt>' Instruction</a></li>
129        </ol>
130      </li>
131      <li><a href="#binaryops">Binary Operations</a>
132        <ol>
133          <li><a href="#i_add">'<tt>add</tt>' Instruction</a></li>
134          <li><a href="#i_fadd">'<tt>fadd</tt>' Instruction</a></li>
135          <li><a href="#i_sub">'<tt>sub</tt>' Instruction</a></li>
136          <li><a href="#i_fsub">'<tt>fsub</tt>' Instruction</a></li>
137          <li><a href="#i_mul">'<tt>mul</tt>' Instruction</a></li>
138          <li><a href="#i_fmul">'<tt>fmul</tt>' Instruction</a></li>
139          <li><a href="#i_udiv">'<tt>udiv</tt>' Instruction</a></li>
140          <li><a href="#i_sdiv">'<tt>sdiv</tt>' Instruction</a></li>
141          <li><a href="#i_fdiv">'<tt>fdiv</tt>' Instruction</a></li>
142          <li><a href="#i_urem">'<tt>urem</tt>' Instruction</a></li>
143          <li><a href="#i_srem">'<tt>srem</tt>' Instruction</a></li>
144          <li><a href="#i_frem">'<tt>frem</tt>' Instruction</a></li>
145        </ol>
146      </li>
147      <li><a href="#bitwiseops">Bitwise Binary Operations</a>
148        <ol>
149          <li><a href="#i_shl">'<tt>shl</tt>' Instruction</a></li>
150          <li><a href="#i_lshr">'<tt>lshr</tt>' Instruction</a></li>
151          <li><a href="#i_ashr">'<tt>ashr</tt>' Instruction</a></li>
152          <li><a href="#i_and">'<tt>and</tt>' Instruction</a></li>
153          <li><a href="#i_or">'<tt>or</tt>'  Instruction</a></li>
154          <li><a href="#i_xor">'<tt>xor</tt>' Instruction</a></li>
155        </ol>
156      </li>
157      <li><a href="#vectorops">Vector Operations</a>
158        <ol>
159          <li><a href="#i_extractelement">'<tt>extractelement</tt>' Instruction</a></li>
160          <li><a href="#i_insertelement">'<tt>insertelement</tt>' Instruction</a></li>
161          <li><a href="#i_shufflevector">'<tt>shufflevector</tt>' Instruction</a></li>
162        </ol>
163      </li>
164      <li><a href="#aggregateops">Aggregate Operations</a>
165        <ol>
166          <li><a href="#i_extractvalue">'<tt>extractvalue</tt>' Instruction</a></li>
167          <li><a href="#i_insertvalue">'<tt>insertvalue</tt>' Instruction</a></li>
168        </ol>
169      </li>
170      <li><a href="#memoryops">Memory Access and Addressing Operations</a>
171        <ol>
172          <li><a href="#i_alloca">'<tt>alloca</tt>' Instruction</a></li>
173         <li><a href="#i_load">'<tt>load</tt>' Instruction</a></li>
174         <li><a href="#i_store">'<tt>store</tt>' Instruction</a></li>
175         <li><a href="#i_fence">'<tt>fence</tt>' Instruction</a></li>
176         <li><a href="#i_cmpxchg">'<tt>cmpxchg</tt>' Instruction</a></li>
177         <li><a href="#i_atomicrmw">'<tt>atomicrmw</tt>' Instruction</a></li>
178         <li><a href="#i_getelementptr">'<tt>getelementptr</tt>' Instruction</a></li>
179        </ol>
180      </li>
181      <li><a href="#convertops">Conversion Operations</a>
182        <ol>
183          <li><a href="#i_trunc">'<tt>trunc .. to</tt>' Instruction</a></li>
184          <li><a href="#i_zext">'<tt>zext .. to</tt>' Instruction</a></li>
185          <li><a href="#i_sext">'<tt>sext .. to</tt>' Instruction</a></li>
186          <li><a href="#i_fptrunc">'<tt>fptrunc .. to</tt>' Instruction</a></li>
187          <li><a href="#i_fpext">'<tt>fpext .. to</tt>' Instruction</a></li>
188          <li><a href="#i_fptoui">'<tt>fptoui .. to</tt>' Instruction</a></li>
189          <li><a href="#i_fptosi">'<tt>fptosi .. to</tt>' Instruction</a></li>
190          <li><a href="#i_uitofp">'<tt>uitofp .. to</tt>' Instruction</a></li>
191          <li><a href="#i_sitofp">'<tt>sitofp .. to</tt>' Instruction</a></li>
192          <li><a href="#i_ptrtoint">'<tt>ptrtoint .. to</tt>' Instruction</a></li>
193          <li><a href="#i_inttoptr">'<tt>inttoptr .. to</tt>' Instruction</a></li>
194          <li><a href="#i_bitcast">'<tt>bitcast .. to</tt>' Instruction</a></li>
195        </ol>
196      </li>
197      <li><a href="#otherops">Other Operations</a>
198        <ol>
199          <li><a href="#i_icmp">'<tt>icmp</tt>' Instruction</a></li>
200          <li><a href="#i_fcmp">'<tt>fcmp</tt>' Instruction</a></li>
201          <li><a href="#i_phi">'<tt>phi</tt>'   Instruction</a></li>
202          <li><a href="#i_select">'<tt>select</tt>' Instruction</a></li>
203          <li><a href="#i_call">'<tt>call</tt>'  Instruction</a></li>
204          <li><a href="#i_va_arg">'<tt>va_arg</tt>'  Instruction</a></li>
205          <li><a href="#i_landingpad">'<tt>landingpad</tt>' Instruction</a></li>
206        </ol>
207      </li>
208    </ol>
209  </li>
210  <li><a href="#intrinsics">Intrinsic Functions</a>
211    <ol>
212      <li><a href="#int_varargs">Variable Argument Handling Intrinsics</a>
213        <ol>
214          <li><a href="#int_va_start">'<tt>llvm.va_start</tt>' Intrinsic</a></li>
215          <li><a href="#int_va_end">'<tt>llvm.va_end</tt>'   Intrinsic</a></li>
216          <li><a href="#int_va_copy">'<tt>llvm.va_copy</tt>'  Intrinsic</a></li>
217        </ol>
218      </li>
219      <li><a href="#int_gc">Accurate Garbage Collection Intrinsics</a>
220        <ol>
221          <li><a href="#int_gcroot">'<tt>llvm.gcroot</tt>' Intrinsic</a></li>
222          <li><a href="#int_gcread">'<tt>llvm.gcread</tt>' Intrinsic</a></li>
223          <li><a href="#int_gcwrite">'<tt>llvm.gcwrite</tt>' Intrinsic</a></li>
224        </ol>
225      </li>
226      <li><a href="#int_codegen">Code Generator Intrinsics</a>
227        <ol>
228          <li><a href="#int_returnaddress">'<tt>llvm.returnaddress</tt>' Intrinsic</a></li>
229          <li><a href="#int_frameaddress">'<tt>llvm.frameaddress</tt>'   Intrinsic</a></li>
230          <li><a href="#int_stacksave">'<tt>llvm.stacksave</tt>' Intrinsic</a></li>
231          <li><a href="#int_stackrestore">'<tt>llvm.stackrestore</tt>' Intrinsic</a></li>
232          <li><a href="#int_prefetch">'<tt>llvm.prefetch</tt>' Intrinsic</a></li>
233          <li><a href="#int_pcmarker">'<tt>llvm.pcmarker</tt>' Intrinsic</a></li>
234          <li><a href="#int_readcyclecounter">'<tt>llvm.readcyclecounter</tt>' Intrinsic</a></li>
235        </ol>
236      </li>
237      <li><a href="#int_libc">Standard C Library Intrinsics</a>
238        <ol>
239          <li><a href="#int_memcpy">'<tt>llvm.memcpy.*</tt>' Intrinsic</a></li>
240          <li><a href="#int_memmove">'<tt>llvm.memmove.*</tt>' Intrinsic</a></li>
241          <li><a href="#int_memset">'<tt>llvm.memset.*</tt>' Intrinsic</a></li>
242          <li><a href="#int_sqrt">'<tt>llvm.sqrt.*</tt>' Intrinsic</a></li>
243          <li><a href="#int_powi">'<tt>llvm.powi.*</tt>' Intrinsic</a></li>
244          <li><a href="#int_sin">'<tt>llvm.sin.*</tt>' Intrinsic</a></li>
245          <li><a href="#int_cos">'<tt>llvm.cos.*</tt>' Intrinsic</a></li>
246          <li><a href="#int_pow">'<tt>llvm.pow.*</tt>' Intrinsic</a></li>
247          <li><a href="#int_exp">'<tt>llvm.exp.*</tt>' Intrinsic</a></li>
248          <li><a href="#int_log">'<tt>llvm.log.*</tt>' Intrinsic</a></li>
249          <li><a href="#int_fma">'<tt>llvm.fma.*</tt>' Intrinsic</a></li>
250        </ol>
251      </li>
252      <li><a href="#int_manip">Bit Manipulation Intrinsics</a>
253        <ol>
254          <li><a href="#int_bswap">'<tt>llvm.bswap.*</tt>' Intrinsics</a></li>
255          <li><a href="#int_ctpop">'<tt>llvm.ctpop.*</tt>' Intrinsic </a></li>
256          <li><a href="#int_ctlz">'<tt>llvm.ctlz.*</tt>' Intrinsic </a></li>
257          <li><a href="#int_cttz">'<tt>llvm.cttz.*</tt>' Intrinsic </a></li>
258        </ol>
259      </li>
260      <li><a href="#int_overflow">Arithmetic with Overflow Intrinsics</a>
261        <ol>
262          <li><a href="#int_sadd_overflow">'<tt>llvm.sadd.with.overflow.*</tt> Intrinsics</a></li>
263          <li><a href="#int_uadd_overflow">'<tt>llvm.uadd.with.overflow.*</tt> Intrinsics</a></li>
264          <li><a href="#int_ssub_overflow">'<tt>llvm.ssub.with.overflow.*</tt> Intrinsics</a></li>
265          <li><a href="#int_usub_overflow">'<tt>llvm.usub.with.overflow.*</tt> Intrinsics</a></li>
266          <li><a href="#int_smul_overflow">'<tt>llvm.smul.with.overflow.*</tt> Intrinsics</a></li>
267          <li><a href="#int_umul_overflow">'<tt>llvm.umul.with.overflow.*</tt> Intrinsics</a></li>
268        </ol>
269      </li>
270      <li><a href="#int_fp16">Half Precision Floating Point Intrinsics</a>
271        <ol>
272          <li><a href="#int_convert_to_fp16">'<tt>llvm.convert.to.fp16</tt>' Intrinsic</a></li>
273          <li><a href="#int_convert_from_fp16">'<tt>llvm.convert.from.fp16</tt>' Intrinsic</a></li>
274        </ol>
275      </li>
276      <li><a href="#int_debugger">Debugger intrinsics</a></li>
277      <li><a href="#int_eh">Exception Handling intrinsics</a></li>
278      <li><a href="#int_trampoline">Trampoline Intrinsics</a>
279        <ol>
280          <li><a href="#int_it">'<tt>llvm.init.trampoline</tt>' Intrinsic</a></li>
281          <li><a href="#int_at">'<tt>llvm.adjust.trampoline</tt>' Intrinsic</a></li>
282        </ol>
283      </li>
284      <li><a href="#int_memorymarkers">Memory Use Markers</a>
285        <ol>
286          <li><a href="#int_lifetime_start"><tt>llvm.lifetime.start</tt></a></li>
287          <li><a href="#int_lifetime_end"><tt>llvm.lifetime.end</tt></a></li>
288          <li><a href="#int_invariant_start"><tt>llvm.invariant.start</tt></a></li>
289          <li><a href="#int_invariant_end"><tt>llvm.invariant.end</tt></a></li>
290        </ol>
291      </li>
292      <li><a href="#int_general">General intrinsics</a>
293        <ol>
294          <li><a href="#int_var_annotation">
295            '<tt>llvm.var.annotation</tt>' Intrinsic</a></li>
296          <li><a href="#int_annotation">
297            '<tt>llvm.annotation.*</tt>' Intrinsic</a></li>
298          <li><a href="#int_trap">
299            '<tt>llvm.trap</tt>' Intrinsic</a></li>
300          <li><a href="#int_stackprotector">
301            '<tt>llvm.stackprotector</tt>' Intrinsic</a></li>
302	  <li><a href="#int_objectsize">
303            '<tt>llvm.objectsize</tt>' Intrinsic</a></li>
304        </ol>
305      </li>
306    </ol>
307  </li>
308</ol>
309
310<div class="doc_author">
311  <p>Written by <a href="mailto:sabre@nondot.org">Chris Lattner</a>
312            and <a href="mailto:vadve@cs.uiuc.edu">Vikram Adve</a></p>
313</div>
314
315<!-- *********************************************************************** -->
316<h2><a name="abstract">Abstract</a></h2>
317<!-- *********************************************************************** -->
318
319<div>
320
321<p>This document is a reference manual for the LLVM assembly language. LLVM is
322   a Static Single Assignment (SSA) based representation that provides type
323   safety, low-level operations, flexibility, and the capability of representing
324   'all' high-level languages cleanly.  It is the common code representation
325   used throughout all phases of the LLVM compilation strategy.</p>
326
327</div>
328
329<!-- *********************************************************************** -->
330<h2><a name="introduction">Introduction</a></h2>
331<!-- *********************************************************************** -->
332
333<div>
334
335<p>The LLVM code representation is designed to be used in three different forms:
336   as an in-memory compiler IR, as an on-disk bitcode representation (suitable
337   for fast loading by a Just-In-Time compiler), and as a human readable
338   assembly language representation.  This allows LLVM to provide a powerful
339   intermediate representation for efficient compiler transformations and
340   analysis, while providing a natural means to debug and visualize the
341   transformations.  The three different forms of LLVM are all equivalent.  This
342   document describes the human readable representation and notation.</p>
343
344<p>The LLVM representation aims to be light-weight and low-level while being
345   expressive, typed, and extensible at the same time.  It aims to be a
346   "universal IR" of sorts, by being at a low enough level that high-level ideas
347   may be cleanly mapped to it (similar to how microprocessors are "universal
348   IR's", allowing many source languages to be mapped to them).  By providing
349   type information, LLVM can be used as the target of optimizations: for
350   example, through pointer analysis, it can be proven that a C automatic
351   variable is never accessed outside of the current function, allowing it to
352   be promoted to a simple SSA value instead of a memory location.</p>
353
354<!-- _______________________________________________________________________ -->
355<h4>
356  <a name="wellformed">Well-Formedness</a>
357</h4>
358
359<div>
360
361<p>It is important to note that this document describes 'well formed' LLVM
362   assembly language.  There is a difference between what the parser accepts and
363   what is considered 'well formed'.  For example, the following instruction is
364   syntactically okay, but not well formed:</p>
365
366<pre class="doc_code">
367%x = <a href="#i_add">add</a> i32 1, %x
368</pre>
369
370<p>because the definition of <tt>%x</tt> does not dominate all of its uses. The
371   LLVM infrastructure provides a verification pass that may be used to verify
372   that an LLVM module is well formed.  This pass is automatically run by the
373   parser after parsing input assembly and by the optimizer before it outputs
374   bitcode.  The violations pointed out by the verifier pass indicate bugs in
375   transformation passes or input to the parser.</p>
376
377</div>
378
379</div>
380
381<!-- Describe the typesetting conventions here. -->
382
383<!-- *********************************************************************** -->
384<h2><a name="identifiers">Identifiers</a></h2>
385<!-- *********************************************************************** -->
386
387<div>
388
389<p>LLVM identifiers come in two basic types: global and local. Global
390   identifiers (functions, global variables) begin with the <tt>'@'</tt>
391   character. Local identifiers (register names, types) begin with
392   the <tt>'%'</tt> character. Additionally, there are three different formats
393   for identifiers, for different purposes:</p>
394
395<ol>
396  <li>Named values are represented as a string of characters with their prefix.
397      For example, <tt>%foo</tt>, <tt>@DivisionByZero</tt>,
398      <tt>%a.really.long.identifier</tt>. The actual regular expression used is
399      '<tt>[%@][a-zA-Z$._][a-zA-Z$._0-9]*</tt>'.  Identifiers which require
400      other characters in their names can be surrounded with quotes. Special
401      characters may be escaped using <tt>"\xx"</tt> where <tt>xx</tt> is the
402      ASCII code for the character in hexadecimal.  In this way, any character
403      can be used in a name value, even quotes themselves.</li>
404
405  <li>Unnamed values are represented as an unsigned numeric value with their
406      prefix.  For example, <tt>%12</tt>, <tt>@2</tt>, <tt>%44</tt>.</li>
407
408  <li>Constants, which are described in a <a href="#constants">section about
409      constants</a>, below.</li>
410</ol>
411
412<p>LLVM requires that values start with a prefix for two reasons: Compilers
413   don't need to worry about name clashes with reserved words, and the set of
414   reserved words may be expanded in the future without penalty.  Additionally,
415   unnamed identifiers allow a compiler to quickly come up with a temporary
416   variable without having to avoid symbol table conflicts.</p>
417
418<p>Reserved words in LLVM are very similar to reserved words in other
419   languages. There are keywords for different opcodes
420   ('<tt><a href="#i_add">add</a></tt>',
421   '<tt><a href="#i_bitcast">bitcast</a></tt>',
422   '<tt><a href="#i_ret">ret</a></tt>', etc...), for primitive type names
423   ('<tt><a href="#t_void">void</a></tt>',
424   '<tt><a href="#t_primitive">i32</a></tt>', etc...), and others.  These
425   reserved words cannot conflict with variable names, because none of them
426   start with a prefix character (<tt>'%'</tt> or <tt>'@'</tt>).</p>
427
428<p>Here is an example of LLVM code to multiply the integer variable
429   '<tt>%X</tt>' by 8:</p>
430
431<p>The easy way:</p>
432
433<pre class="doc_code">
434%result = <a href="#i_mul">mul</a> i32 %X, 8
435</pre>
436
437<p>After strength reduction:</p>
438
439<pre class="doc_code">
440%result = <a href="#i_shl">shl</a> i32 %X, i8 3
441</pre>
442
443<p>And the hard way:</p>
444
445<pre class="doc_code">
446%0 = <a href="#i_add">add</a> i32 %X, %X           <i>; yields {i32}:%0</i>
447%1 = <a href="#i_add">add</a> i32 %0, %0           <i>; yields {i32}:%1</i>
448%result = <a href="#i_add">add</a> i32 %1, %1
449</pre>
450
451<p>This last way of multiplying <tt>%X</tt> by 8 illustrates several important
452   lexical features of LLVM:</p>
453
454<ol>
455  <li>Comments are delimited with a '<tt>;</tt>' and go until the end of
456      line.</li>
457
458  <li>Unnamed temporaries are created when the result of a computation is not
459      assigned to a named value.</li>
460
461  <li>Unnamed temporaries are numbered sequentially</li>
462</ol>
463
464<p>It also shows a convention that we follow in this document.  When
465   demonstrating instructions, we will follow an instruction with a comment that
466   defines the type and name of value produced.  Comments are shown in italic
467   text.</p>
468
469</div>
470
471<!-- *********************************************************************** -->
472<h2><a name="highlevel">High Level Structure</a></h2>
473<!-- *********************************************************************** -->
474<div>
475<!-- ======================================================================= -->
476<h3>
477  <a name="modulestructure">Module Structure</a>
478</h3>
479
480<div>
481
482<p>LLVM programs are composed of "Module"s, each of which is a translation unit
483   of the input programs.  Each module consists of functions, global variables,
484   and symbol table entries.  Modules may be combined together with the LLVM
485   linker, which merges function (and global variable) definitions, resolves
486   forward declarations, and merges symbol table entries. Here is an example of
487   the "hello world" module:</p>
488
489<pre class="doc_code">
490<i>; Declare the string constant as a global constant.</i>&nbsp;
491<a href="#identifiers">@.LC0</a> = <a href="#linkage_internal">internal</a>&nbsp;<a href="#globalvars">constant</a>&nbsp;<a href="#t_array">[13 x i8]</a> c"hello world\0A\00"      <i>; [13 x i8]*</i>&nbsp;
492
493<i>; External declaration of the puts function</i>&nbsp;
494<a href="#functionstructure">declare</a> i32 @puts(i8*)                                      <i>; i32 (i8*)* </i>&nbsp;
495
496<i>; Definition of main function</i>
497define i32 @main() {   <i>; i32()* </i>&nbsp;
498  <i>; Convert [13 x i8]* to i8  *...</i>&nbsp;
499  %cast210 = <a href="#i_getelementptr">getelementptr</a> [13 x i8]* @.LC0, i64 0, i64 0   <i>; i8*</i>&nbsp;
500
501  <i>; Call puts function to write out the string to stdout.</i>&nbsp;
502  <a href="#i_call">call</a> i32 @puts(i8* %cast210)           <i>; i32</i>&nbsp;
503  <a href="#i_ret">ret</a> i32 0&nbsp;
504}
505
506<i>; Named metadata</i>
507!1 = metadata !{i32 41}
508!foo = !{!1, null}
509</pre>
510
511<p>This example is made up of a <a href="#globalvars">global variable</a> named
512   "<tt>.LC0</tt>", an external declaration of the "<tt>puts</tt>" function,
513   a <a href="#functionstructure">function definition</a> for
514   "<tt>main</tt>" and <a href="#namedmetadatastructure">named metadata</a>
515   "<tt>foo"</tt>.</p>
516
517<p>In general, a module is made up of a list of global values, where both
518   functions and global variables are global values.  Global values are
519   represented by a pointer to a memory location (in this case, a pointer to an
520   array of char, and a pointer to a function), and have one of the
521   following <a href="#linkage">linkage types</a>.</p>
522
523</div>
524
525<!-- ======================================================================= -->
526<h3>
527  <a name="linkage">Linkage Types</a>
528</h3>
529
530<div>
531
532<p>All Global Variables and Functions have one of the following types of
533   linkage:</p>
534
535<dl>
536  <dt><tt><b><a name="linkage_private">private</a></b></tt></dt>
537  <dd>Global values with "<tt>private</tt>" linkage are only directly accessible
538      by objects in the current module. In particular, linking code into a
539      module with an private global value may cause the private to be renamed as
540      necessary to avoid collisions.  Because the symbol is private to the
541      module, all references can be updated. This doesn't show up in any symbol
542      table in the object file.</dd>
543
544  <dt><tt><b><a name="linkage_linker_private">linker_private</a></b></tt></dt>
545  <dd>Similar to <tt>private</tt>, but the symbol is passed through the
546      assembler and evaluated by the linker. Unlike normal strong symbols, they
547      are removed by the linker from the final linked image (executable or
548      dynamic library).</dd>
549
550  <dt><tt><b><a name="linkage_linker_private_weak">linker_private_weak</a></b></tt></dt>
551  <dd>Similar to "<tt>linker_private</tt>", but the symbol is weak. Note that
552      <tt>linker_private_weak</tt> symbols are subject to coalescing by the
553      linker. The symbols are removed by the linker from the final linked image
554      (executable or dynamic library).</dd>
555
556  <dt><tt><b><a name="linkage_linker_private_weak_def_auto">linker_private_weak_def_auto</a></b></tt></dt>
557  <dd>Similar to "<tt>linker_private_weak</tt>", but it's known that the address
558      of the object is not taken. For instance, functions that had an inline
559      definition, but the compiler decided not to inline it. Note,
560      unlike <tt>linker_private</tt> and <tt>linker_private_weak</tt>,
561      <tt>linker_private_weak_def_auto</tt> may have only <tt>default</tt>
562      visibility.  The symbols are removed by the linker from the final linked
563      image (executable or dynamic library).</dd>
564
565  <dt><tt><b><a name="linkage_internal">internal</a></b></tt></dt>
566  <dd>Similar to private, but the value shows as a local symbol
567      (<tt>STB_LOCAL</tt> in the case of ELF) in the object file. This
568      corresponds to the notion of the '<tt>static</tt>' keyword in C.</dd>
569
570  <dt><tt><b><a name="linkage_available_externally">available_externally</a></b></tt></dt>
571  <dd>Globals with "<tt>available_externally</tt>" linkage are never emitted
572      into the object file corresponding to the LLVM module.  They exist to
573      allow inlining and other optimizations to take place given knowledge of
574      the definition of the global, which is known to be somewhere outside the
575      module.  Globals with <tt>available_externally</tt> linkage are allowed to
576      be discarded at will, and are otherwise the same as <tt>linkonce_odr</tt>.
577      This linkage type is only allowed on definitions, not declarations.</dd>
578
579  <dt><tt><b><a name="linkage_linkonce">linkonce</a></b></tt></dt>
580  <dd>Globals with "<tt>linkonce</tt>" linkage are merged with other globals of
581      the same name when linkage occurs.  This can be used to implement
582      some forms of inline functions, templates, or other code which must be
583      generated in each translation unit that uses it, but where the body may
584      be overridden with a more definitive definition later.  Unreferenced
585      <tt>linkonce</tt> globals are allowed to be discarded.  Note that
586      <tt>linkonce</tt> linkage does not actually allow the optimizer to
587      inline the body of this function into callers because it doesn't know if
588      this definition of the function is the definitive definition within the
589      program or whether it will be overridden by a stronger definition.
590      To enable inlining and other optimizations, use "<tt>linkonce_odr</tt>"
591      linkage.</dd>
592
593  <dt><tt><b><a name="linkage_weak">weak</a></b></tt></dt>
594  <dd>"<tt>weak</tt>" linkage has the same merging semantics as
595      <tt>linkonce</tt> linkage, except that unreferenced globals with
596      <tt>weak</tt> linkage may not be discarded.  This is used for globals that
597      are declared "weak" in C source code.</dd>
598
599  <dt><tt><b><a name="linkage_common">common</a></b></tt></dt>
600  <dd>"<tt>common</tt>" linkage is most similar to "<tt>weak</tt>" linkage, but
601      they are used for tentative definitions in C, such as "<tt>int X;</tt>" at
602      global scope.
603      Symbols with "<tt>common</tt>" linkage are merged in the same way as
604      <tt>weak symbols</tt>, and they may not be deleted if unreferenced.
605      <tt>common</tt> symbols may not have an explicit section,
606      must have a zero initializer, and may not be marked '<a
607      href="#globalvars"><tt>constant</tt></a>'.  Functions and aliases may not
608      have common linkage.</dd>
609
610
611  <dt><tt><b><a name="linkage_appending">appending</a></b></tt></dt>
612  <dd>"<tt>appending</tt>" linkage may only be applied to global variables of
613      pointer to array type.  When two global variables with appending linkage
614      are linked together, the two global arrays are appended together.  This is
615      the LLVM, typesafe, equivalent of having the system linker append together
616      "sections" with identical names when .o files are linked.</dd>
617
618  <dt><tt><b><a name="linkage_externweak">extern_weak</a></b></tt></dt>
619  <dd>The semantics of this linkage follow the ELF object file model: the symbol
620      is weak until linked, if not linked, the symbol becomes null instead of
621      being an undefined reference.</dd>
622
623  <dt><tt><b><a name="linkage_linkonce_odr">linkonce_odr</a></b></tt></dt>
624  <dt><tt><b><a name="linkage_weak_odr">weak_odr</a></b></tt></dt>
625  <dd>Some languages allow differing globals to be merged, such as two functions
626      with different semantics.  Other languages, such as <tt>C++</tt>, ensure
627      that only equivalent globals are ever merged (the "one definition rule"
628      &mdash; "ODR").  Such languages can use the <tt>linkonce_odr</tt>
629      and <tt>weak_odr</tt> linkage types to indicate that the global will only
630      be merged with equivalent globals.  These linkage types are otherwise the
631      same as their non-<tt>odr</tt> versions.</dd>
632
633  <dt><tt><b><a name="linkage_external">external</a></b></tt>:</dt>
634  <dd>If none of the above identifiers are used, the global is externally
635      visible, meaning that it participates in linkage and can be used to
636      resolve external symbol references.</dd>
637</dl>
638
639<p>The next two types of linkage are targeted for Microsoft Windows platform
640   only. They are designed to support importing (exporting) symbols from (to)
641   DLLs (Dynamic Link Libraries).</p>
642
643<dl>
644  <dt><tt><b><a name="linkage_dllimport">dllimport</a></b></tt></dt>
645  <dd>"<tt>dllimport</tt>" linkage causes the compiler to reference a function
646      or variable via a global pointer to a pointer that is set up by the DLL
647      exporting the symbol. On Microsoft Windows targets, the pointer name is
648      formed by combining <code>__imp_</code> and the function or variable
649      name.</dd>
650
651  <dt><tt><b><a name="linkage_dllexport">dllexport</a></b></tt></dt>
652  <dd>"<tt>dllexport</tt>" linkage causes the compiler to provide a global
653      pointer to a pointer in a DLL, so that it can be referenced with the
654      <tt>dllimport</tt> attribute. On Microsoft Windows targets, the pointer
655      name is formed by combining <code>__imp_</code> and the function or
656      variable name.</dd>
657</dl>
658
659<p>For example, since the "<tt>.LC0</tt>" variable is defined to be internal, if
660   another module defined a "<tt>.LC0</tt>" variable and was linked with this
661   one, one of the two would be renamed, preventing a collision.  Since
662   "<tt>main</tt>" and "<tt>puts</tt>" are external (i.e., lacking any linkage
663   declarations), they are accessible outside of the current module.</p>
664
665<p>It is illegal for a function <i>declaration</i> to have any linkage type
666   other than <tt>external</tt>, <tt>dllimport</tt>
667  or <tt>extern_weak</tt>.</p>
668
669<p>Aliases can have only <tt>external</tt>, <tt>internal</tt>, <tt>weak</tt>
670   or <tt>weak_odr</tt> linkages.</p>
671
672</div>
673
674<!-- ======================================================================= -->
675<h3>
676  <a name="callingconv">Calling Conventions</a>
677</h3>
678
679<div>
680
681<p>LLVM <a href="#functionstructure">functions</a>, <a href="#i_call">calls</a>
682   and <a href="#i_invoke">invokes</a> can all have an optional calling
683   convention specified for the call.  The calling convention of any pair of
684   dynamic caller/callee must match, or the behavior of the program is
685   undefined.  The following calling conventions are supported by LLVM, and more
686   may be added in the future:</p>
687
688<dl>
689  <dt><b>"<tt>ccc</tt>" - The C calling convention</b>:</dt>
690  <dd>This calling convention (the default if no other calling convention is
691      specified) matches the target C calling conventions.  This calling
692      convention supports varargs function calls and tolerates some mismatch in
693      the declared prototype and implemented declaration of the function (as
694      does normal C).</dd>
695
696  <dt><b>"<tt>fastcc</tt>" - The fast calling convention</b>:</dt>
697  <dd>This calling convention attempts to make calls as fast as possible
698      (e.g. by passing things in registers).  This calling convention allows the
699      target to use whatever tricks it wants to produce fast code for the
700      target, without having to conform to an externally specified ABI
701      (Application Binary Interface).
702      <a href="CodeGenerator.html#tailcallopt">Tail calls can only be optimized
703      when this or the GHC convention is used.</a>  This calling convention
704      does not support varargs and requires the prototype of all callees to
705      exactly match the prototype of the function definition.</dd>
706
707  <dt><b>"<tt>coldcc</tt>" - The cold calling convention</b>:</dt>
708  <dd>This calling convention attempts to make code in the caller as efficient
709      as possible under the assumption that the call is not commonly executed.
710      As such, these calls often preserve all registers so that the call does
711      not break any live ranges in the caller side.  This calling convention
712      does not support varargs and requires the prototype of all callees to
713      exactly match the prototype of the function definition.</dd>
714
715  <dt><b>"<tt>cc <em>10</em></tt>" - GHC convention</b>:</dt>
716  <dd>This calling convention has been implemented specifically for use by the
717      <a href="http://www.haskell.org/ghc">Glasgow Haskell Compiler (GHC)</a>.
718      It passes everything in registers, going to extremes to achieve this by
719      disabling callee save registers. This calling convention should not be
720      used lightly but only for specific situations such as an alternative to
721      the <em>register pinning</em> performance technique often used when
722      implementing functional programming languages.At the moment only X86
723      supports this convention and it has the following limitations:
724      <ul>
725        <li>On <em>X86-32</em> only supports up to 4 bit type parameters. No
726            floating point types are supported.</li>
727        <li>On <em>X86-64</em> only supports up to 10 bit type parameters and
728            6 floating point parameters.</li>
729      </ul>
730      This calling convention supports
731      <a href="CodeGenerator.html#tailcallopt">tail call optimization</a> but
732      requires both the caller and callee are using it.
733  </dd>
734
735  <dt><b>"<tt>cc &lt;<em>n</em>&gt;</tt>" - Numbered convention</b>:</dt>
736  <dd>Any calling convention may be specified by number, allowing
737      target-specific calling conventions to be used.  Target specific calling
738      conventions start at 64.</dd>
739</dl>
740
741<p>More calling conventions can be added/defined on an as-needed basis, to
742   support Pascal conventions or any other well-known target-independent
743   convention.</p>
744
745</div>
746
747<!-- ======================================================================= -->
748<h3>
749  <a name="visibility">Visibility Styles</a>
750</h3>
751
752<div>
753
754<p>All Global Variables and Functions have one of the following visibility
755   styles:</p>
756
757<dl>
758  <dt><b>"<tt>default</tt>" - Default style</b>:</dt>
759  <dd>On targets that use the ELF object file format, default visibility means
760      that the declaration is visible to other modules and, in shared libraries,
761      means that the declared entity may be overridden. On Darwin, default
762      visibility means that the declaration is visible to other modules. Default
763      visibility corresponds to "external linkage" in the language.</dd>
764
765  <dt><b>"<tt>hidden</tt>" - Hidden style</b>:</dt>
766  <dd>Two declarations of an object with hidden visibility refer to the same
767      object if they are in the same shared object. Usually, hidden visibility
768      indicates that the symbol will not be placed into the dynamic symbol
769      table, so no other module (executable or shared library) can reference it
770      directly.</dd>
771
772  <dt><b>"<tt>protected</tt>" - Protected style</b>:</dt>
773  <dd>On ELF, protected visibility indicates that the symbol will be placed in
774      the dynamic symbol table, but that references within the defining module
775      will bind to the local symbol. That is, the symbol cannot be overridden by
776      another module.</dd>
777</dl>
778
779</div>
780
781<!-- ======================================================================= -->
782<h3>
783  <a name="namedtypes">Named Types</a>
784</h3>
785
786<div>
787
788<p>LLVM IR allows you to specify name aliases for certain types.  This can make
789   it easier to read the IR and make the IR more condensed (particularly when
790   recursive types are involved).  An example of a name specification is:</p>
791
792<pre class="doc_code">
793%mytype = type { %mytype*, i32 }
794</pre>
795
796<p>You may give a name to any <a href="#typesystem">type</a> except
797   "<a href="#t_void">void</a>".  Type name aliases may be used anywhere a type
798   is expected with the syntax "%mytype".</p>
799
800<p>Note that type names are aliases for the structural type that they indicate,
801   and that you can therefore specify multiple names for the same type.  This
802   often leads to confusing behavior when dumping out a .ll file.  Since LLVM IR
803   uses structural typing, the name is not part of the type.  When printing out
804   LLVM IR, the printer will pick <em>one name</em> to render all types of a
805   particular shape.  This means that if you have code where two different
806   source types end up having the same LLVM type, that the dumper will sometimes
807   print the "wrong" or unexpected type.  This is an important design point and
808   isn't going to change.</p>
809
810</div>
811
812<!-- ======================================================================= -->
813<h3>
814  <a name="globalvars">Global Variables</a>
815</h3>
816
817<div>
818
819<p>Global variables define regions of memory allocated at compilation time
820   instead of run-time.  Global variables may optionally be initialized, may
821   have an explicit section to be placed in, and may have an optional explicit
822   alignment specified.  A variable may be defined as "thread_local", which
823   means that it will not be shared by threads (each thread will have a
824   separated copy of the variable).  A variable may be defined as a global
825   "constant," which indicates that the contents of the variable
826   will <b>never</b> be modified (enabling better optimization, allowing the
827   global data to be placed in the read-only section of an executable, etc).
828   Note that variables that need runtime initialization cannot be marked
829   "constant" as there is a store to the variable.</p>
830
831<p>LLVM explicitly allows <em>declarations</em> of global variables to be marked
832   constant, even if the final definition of the global is not.  This capability
833   can be used to enable slightly better optimization of the program, but
834   requires the language definition to guarantee that optimizations based on the
835   'constantness' are valid for the translation units that do not include the
836   definition.</p>
837
838<p>As SSA values, global variables define pointer values that are in scope
839   (i.e. they dominate) all basic blocks in the program.  Global variables
840   always define a pointer to their "content" type because they describe a
841   region of memory, and all memory objects in LLVM are accessed through
842   pointers.</p>
843
844<p>Global variables can be marked with <tt>unnamed_addr</tt> which indicates
845  that the address is not significant, only the content. Constants marked
846  like this can be merged with other constants if they have the same
847  initializer. Note that a constant with significant address <em>can</em>
848  be merged with a <tt>unnamed_addr</tt> constant, the result being a
849  constant whose address is significant.</p>
850
851<p>A global variable may be declared to reside in a target-specific numbered
852   address space. For targets that support them, address spaces may affect how
853   optimizations are performed and/or what target instructions are used to
854   access the variable. The default address space is zero. The address space
855   qualifier must precede any other attributes.</p>
856
857<p>LLVM allows an explicit section to be specified for globals.  If the target
858   supports it, it will emit globals to the section specified.</p>
859
860<p>An explicit alignment may be specified for a global, which must be a power
861   of 2.  If not present, or if the alignment is set to zero, the alignment of
862   the global is set by the target to whatever it feels convenient.  If an
863   explicit alignment is specified, the global is forced to have exactly that
864   alignment.  Targets and optimizers are not allowed to over-align the global
865   if the global has an assigned section.  In this case, the extra alignment
866   could be observable: for example, code could assume that the globals are
867   densely packed in their section and try to iterate over them as an array,
868   alignment padding would break this iteration.</p>
869
870<p>For example, the following defines a global in a numbered address space with
871   an initializer, section, and alignment:</p>
872
873<pre class="doc_code">
874@G = addrspace(5) constant float 1.0, section "foo", align 4
875</pre>
876
877</div>
878
879
880<!-- ======================================================================= -->
881<h3>
882  <a name="functionstructure">Functions</a>
883</h3>
884
885<div>
886
887<p>LLVM function definitions consist of the "<tt>define</tt>" keyword, an
888   optional <a href="#linkage">linkage type</a>, an optional
889   <a href="#visibility">visibility style</a>, an optional
890   <a href="#callingconv">calling convention</a>,
891   an optional <tt>unnamed_addr</tt> attribute, a return type, an optional
892   <a href="#paramattrs">parameter attribute</a> for the return type, a function
893   name, a (possibly empty) argument list (each with optional
894   <a href="#paramattrs">parameter attributes</a>), optional
895   <a href="#fnattrs">function attributes</a>, an optional section, an optional
896   alignment, an optional <a href="#gc">garbage collector name</a>, an opening
897   curly brace, a list of basic blocks, and a closing curly brace.</p>
898
899<p>LLVM function declarations consist of the "<tt>declare</tt>" keyword, an
900   optional <a href="#linkage">linkage type</a>, an optional
901   <a href="#visibility">visibility style</a>, an optional
902   <a href="#callingconv">calling convention</a>,
903   an optional <tt>unnamed_addr</tt> attribute, a return type, an optional
904   <a href="#paramattrs">parameter attribute</a> for the return type, a function
905   name, a possibly empty list of arguments, an optional alignment, and an
906   optional <a href="#gc">garbage collector name</a>.</p>
907
908<p>A function definition contains a list of basic blocks, forming the CFG
909   (Control Flow Graph) for the function.  Each basic block may optionally start
910   with a label (giving the basic block a symbol table entry), contains a list
911   of instructions, and ends with a <a href="#terminators">terminator</a>
912   instruction (such as a branch or function return).</p>
913
914<p>The first basic block in a function is special in two ways: it is immediately
915   executed on entrance to the function, and it is not allowed to have
916   predecessor basic blocks (i.e. there can not be any branches to the entry
917   block of a function).  Because the block can have no predecessors, it also
918   cannot have any <a href="#i_phi">PHI nodes</a>.</p>
919
920<p>LLVM allows an explicit section to be specified for functions.  If the target
921   supports it, it will emit functions to the section specified.</p>
922
923<p>An explicit alignment may be specified for a function.  If not present, or if
924   the alignment is set to zero, the alignment of the function is set by the
925   target to whatever it feels convenient.  If an explicit alignment is
926   specified, the function is forced to have at least that much alignment.  All
927   alignments must be a power of 2.</p>
928
929<p>If the <tt>unnamed_addr</tt> attribute is given, the address is know to not
930  be significant and two identical functions can be merged</p>.
931
932<h5>Syntax:</h5>
933<pre class="doc_code">
934define [<a href="#linkage">linkage</a>] [<a href="#visibility">visibility</a>]
935       [<a href="#callingconv">cconv</a>] [<a href="#paramattrs">ret attrs</a>]
936       &lt;ResultType&gt; @&lt;FunctionName&gt; ([argument list])
937       [<a href="#fnattrs">fn Attrs</a>] [section "name"] [align N]
938       [<a href="#gc">gc</a>] { ... }
939</pre>
940
941</div>
942
943<!-- ======================================================================= -->
944<h3>
945  <a name="aliasstructure">Aliases</a>
946</h3>
947
948<div>
949
950<p>Aliases act as "second name" for the aliasee value (which can be either
951   function, global variable, another alias or bitcast of global value). Aliases
952   may have an optional <a href="#linkage">linkage type</a>, and an
953   optional <a href="#visibility">visibility style</a>.</p>
954
955<h5>Syntax:</h5>
956<pre class="doc_code">
957@&lt;Name&gt; = alias [Linkage] [Visibility] &lt;AliaseeTy&gt; @&lt;Aliasee&gt;
958</pre>
959
960</div>
961
962<!-- ======================================================================= -->
963<h3>
964  <a name="namedmetadatastructure">Named Metadata</a>
965</h3>
966
967<div>
968
969<p>Named metadata is a collection of metadata. <a href="#metadata">Metadata
970   nodes</a> (but not metadata strings) are the only valid operands for
971   a named metadata.</p>
972
973<h5>Syntax:</h5>
974<pre class="doc_code">
975; Some unnamed metadata nodes, which are referenced by the named metadata.
976!0 = metadata !{metadata !"zero"}
977!1 = metadata !{metadata !"one"}
978!2 = metadata !{metadata !"two"}
979; A named metadata.
980!name = !{!0, !1, !2}
981</pre>
982
983</div>
984
985<!-- ======================================================================= -->
986<h3>
987  <a name="paramattrs">Parameter Attributes</a>
988</h3>
989
990<div>
991
992<p>The return type and each parameter of a function type may have a set of
993   <i>parameter attributes</i> associated with them. Parameter attributes are
994   used to communicate additional information about the result or parameters of
995   a function. Parameter attributes are considered to be part of the function,
996   not of the function type, so functions with different parameter attributes
997   can have the same function type.</p>
998
999<p>Parameter attributes are simple keywords that follow the type specified. If
1000   multiple parameter attributes are needed, they are space separated. For
1001   example:</p>
1002
1003<pre class="doc_code">
1004declare i32 @printf(i8* noalias nocapture, ...)
1005declare i32 @atoi(i8 zeroext)
1006declare signext i8 @returns_signed_char()
1007</pre>
1008
1009<p>Note that any attributes for the function result (<tt>nounwind</tt>,
1010   <tt>readonly</tt>) come immediately after the argument list.</p>
1011
1012<p>Currently, only the following parameter attributes are defined:</p>
1013
1014<dl>
1015  <dt><tt><b>zeroext</b></tt></dt>
1016  <dd>This indicates to the code generator that the parameter or return value
1017      should be zero-extended to the extent required by the target's ABI (which
1018      is usually 32-bits, but is 8-bits for a i1 on x86-64) by the caller (for a
1019      parameter) or the callee (for a return value).</dd>
1020
1021  <dt><tt><b>signext</b></tt></dt>
1022  <dd>This indicates to the code generator that the parameter or return value
1023      should be sign-extended to the extent required by the target's ABI (which
1024      is usually 32-bits) by the caller (for a parameter) or the callee (for a
1025      return value).</dd>
1026
1027  <dt><tt><b>inreg</b></tt></dt>
1028  <dd>This indicates that this parameter or return value should be treated in a
1029      special target-dependent fashion during while emitting code for a function
1030      call or return (usually, by putting it in a register as opposed to memory,
1031      though some targets use it to distinguish between two different kinds of
1032      registers).  Use of this attribute is target-specific.</dd>
1033
1034  <dt><tt><b><a name="byval">byval</a></b></tt></dt>
1035  <dd><p>This indicates that the pointer parameter should really be passed by
1036      value to the function.  The attribute implies that a hidden copy of the
1037      pointee
1038      is made between the caller and the callee, so the callee is unable to
1039      modify the value in the callee.  This attribute is only valid on LLVM
1040      pointer arguments.  It is generally used to pass structs and arrays by
1041      value, but is also valid on pointers to scalars.  The copy is considered
1042      to belong to the caller not the callee (for example,
1043      <tt><a href="#readonly">readonly</a></tt> functions should not write to
1044      <tt>byval</tt> parameters). This is not a valid attribute for return
1045      values.</p>
1046
1047      <p>The byval attribute also supports specifying an alignment with
1048      the align attribute.  It indicates the alignment of the stack slot to
1049      form and the known alignment of the pointer specified to the call site. If
1050      the alignment is not specified, then the code generator makes a
1051      target-specific assumption.</p></dd>
1052
1053  <dt><tt><b><a name="sret">sret</a></b></tt></dt>
1054  <dd>This indicates that the pointer parameter specifies the address of a
1055      structure that is the return value of the function in the source program.
1056      This pointer must be guaranteed by the caller to be valid: loads and
1057      stores to the structure may be assumed by the callee to not to trap.  This
1058      may only be applied to the first parameter. This is not a valid attribute
1059      for return values. </dd>
1060
1061  <dt><tt><b><a name="noalias">noalias</a></b></tt></dt>
1062  <dd>This indicates that pointer values
1063      <a href="#pointeraliasing"><i>based</i></a> on the argument or return
1064      value do not alias pointer values which are not <i>based</i> on it,
1065      ignoring certain "irrelevant" dependencies.
1066      For a call to the parent function, dependencies between memory
1067      references from before or after the call and from those during the call
1068      are "irrelevant" to the <tt>noalias</tt> keyword for the arguments and
1069      return value used in that call.
1070      The caller shares the responsibility with the callee for ensuring that
1071      these requirements are met.
1072      For further details, please see the discussion of the NoAlias response in
1073      <a href="AliasAnalysis.html#MustMayNo">alias analysis</a>.<br>
1074<br>
1075      Note that this definition of <tt>noalias</tt> is intentionally
1076      similar to the definition of <tt>restrict</tt> in C99 for function
1077      arguments, though it is slightly weaker.
1078<br>
1079      For function return values, C99's <tt>restrict</tt> is not meaningful,
1080      while LLVM's <tt>noalias</tt> is.
1081      </dd>
1082
1083  <dt><tt><b><a name="nocapture">nocapture</a></b></tt></dt>
1084  <dd>This indicates that the callee does not make any copies of the pointer
1085      that outlive the callee itself. This is not a valid attribute for return
1086      values.</dd>
1087
1088  <dt><tt><b><a name="nest">nest</a></b></tt></dt>
1089  <dd>This indicates that the pointer parameter can be excised using the
1090      <a href="#int_trampoline">trampoline intrinsics</a>. This is not a valid
1091      attribute for return values.</dd>
1092</dl>
1093
1094</div>
1095
1096<!-- ======================================================================= -->
1097<h3>
1098  <a name="gc">Garbage Collector Names</a>
1099</h3>
1100
1101<div>
1102
1103<p>Each function may specify a garbage collector name, which is simply a
1104   string:</p>
1105
1106<pre class="doc_code">
1107define void @f() gc "name" { ... }
1108</pre>
1109
1110<p>The compiler declares the supported values of <i>name</i>. Specifying a
1111   collector which will cause the compiler to alter its output in order to
1112   support the named garbage collection algorithm.</p>
1113
1114</div>
1115
1116<!-- ======================================================================= -->
1117<h3>
1118  <a name="fnattrs">Function Attributes</a>
1119</h3>
1120
1121<div>
1122
1123<p>Function attributes are set to communicate additional information about a
1124   function. Function attributes are considered to be part of the function, not
1125   of the function type, so functions with different parameter attributes can
1126   have the same function type.</p>
1127
1128<p>Function attributes are simple keywords that follow the type specified. If
1129   multiple attributes are needed, they are space separated. For example:</p>
1130
1131<pre class="doc_code">
1132define void @f() noinline { ... }
1133define void @f() alwaysinline { ... }
1134define void @f() alwaysinline optsize { ... }
1135define void @f() optsize { ... }
1136</pre>
1137
1138<dl>
1139  <dt><tt><b>alignstack(&lt;<em>n</em>&gt;)</b></tt></dt>
1140  <dd>This attribute indicates that, when emitting the prologue and epilogue,
1141      the backend should forcibly align the stack pointer. Specify the
1142      desired alignment, which must be a power of two, in parentheses.
1143
1144  <dt><tt><b>alwaysinline</b></tt></dt>
1145  <dd>This attribute indicates that the inliner should attempt to inline this
1146      function into callers whenever possible, ignoring any active inlining size
1147      threshold for this caller.</dd>
1148
1149  <dt><tt><b>nonlazybind</b></tt></dt>
1150  <dd>This attribute suppresses lazy symbol binding for the function. This
1151      may make calls to the function faster, at the cost of extra program
1152      startup time if the function is not called during program startup.</dd>
1153
1154  <dt><tt><b>inlinehint</b></tt></dt>
1155  <dd>This attribute indicates that the source code contained a hint that inlining
1156      this function is desirable (such as the "inline" keyword in C/C++).  It
1157      is just a hint; it imposes no requirements on the inliner.</dd>
1158
1159  <dt><tt><b>naked</b></tt></dt>
1160  <dd>This attribute disables prologue / epilogue emission for the function.
1161      This can have very system-specific consequences.</dd>
1162
1163  <dt><tt><b>noimplicitfloat</b></tt></dt>
1164  <dd>This attributes disables implicit floating point instructions.</dd>
1165
1166  <dt><tt><b>noinline</b></tt></dt>
1167  <dd>This attribute indicates that the inliner should never inline this
1168      function in any situation. This attribute may not be used together with
1169      the <tt>alwaysinline</tt> attribute.</dd>
1170
1171  <dt><tt><b>noredzone</b></tt></dt>
1172  <dd>This attribute indicates that the code generator should not use a red
1173      zone, even if the target-specific ABI normally permits it.</dd>
1174
1175  <dt><tt><b>noreturn</b></tt></dt>
1176  <dd>This function attribute indicates that the function never returns
1177      normally.  This produces undefined behavior at runtime if the function
1178      ever does dynamically return.</dd>
1179
1180  <dt><tt><b>nounwind</b></tt></dt>
1181  <dd>This function attribute indicates that the function never returns with an
1182      unwind or exceptional control flow.  If the function does unwind, its
1183      runtime behavior is undefined.</dd>
1184
1185  <dt><tt><b>optsize</b></tt></dt>
1186  <dd>This attribute suggests that optimization passes and code generator passes
1187      make choices that keep the code size of this function low, and otherwise
1188      do optimizations specifically to reduce code size.</dd>
1189
1190  <dt><tt><b>readnone</b></tt></dt>
1191  <dd>This attribute indicates that the function computes its result (or decides
1192      to unwind an exception) based strictly on its arguments, without
1193      dereferencing any pointer arguments or otherwise accessing any mutable
1194      state (e.g. memory, control registers, etc) visible to caller functions.
1195      It does not write through any pointer arguments
1196      (including <tt><a href="#byval">byval</a></tt> arguments) and never
1197      changes any state visible to callers.  This means that it cannot unwind
1198      exceptions by calling the <tt>C++</tt> exception throwing methods, but
1199      could use the <tt>unwind</tt> instruction.</dd>
1200
1201  <dt><tt><b><a name="readonly">readonly</a></b></tt></dt>
1202  <dd>This attribute indicates that the function does not write through any
1203      pointer arguments (including <tt><a href="#byval">byval</a></tt>
1204      arguments) or otherwise modify any state (e.g. memory, control registers,
1205      etc) visible to caller functions.  It may dereference pointer arguments
1206      and read state that may be set in the caller.  A readonly function always
1207      returns the same value (or unwinds an exception identically) when called
1208      with the same set of arguments and global state.  It cannot unwind an
1209      exception by calling the <tt>C++</tt> exception throwing methods, but may
1210      use the <tt>unwind</tt> instruction.</dd>
1211
1212  <dt><tt><b><a name="ssp">ssp</a></b></tt></dt>
1213  <dd>This attribute indicates that the function should emit a stack smashing
1214      protector. It is in the form of a "canary"&mdash;a random value placed on
1215      the stack before the local variables that's checked upon return from the
1216      function to see if it has been overwritten. A heuristic is used to
1217      determine if a function needs stack protectors or not.<br>
1218<br>
1219      If a function that has an <tt>ssp</tt> attribute is inlined into a
1220      function that doesn't have an <tt>ssp</tt> attribute, then the resulting
1221      function will have an <tt>ssp</tt> attribute.</dd>
1222
1223  <dt><tt><b>sspreq</b></tt></dt>
1224  <dd>This attribute indicates that the function should <em>always</em> emit a
1225      stack smashing protector. This overrides
1226      the <tt><a href="#ssp">ssp</a></tt> function attribute.<br>
1227<br>
1228      If a function that has an <tt>sspreq</tt> attribute is inlined into a
1229      function that doesn't have an <tt>sspreq</tt> attribute or which has
1230      an <tt>ssp</tt> attribute, then the resulting function will have
1231      an <tt>sspreq</tt> attribute.</dd>
1232
1233  <dt><tt><b><a name="uwtable">uwtable</a></b></tt></dt>
1234  <dd>This attribute indicates that the ABI being targeted requires that
1235      an unwind table entry be produce for this function even if we can
1236      show that no exceptions passes by it. This is normally the case for
1237      the ELF x86-64 abi, but it can be disabled for some compilation
1238      units.</dd>
1239
1240  <dt><tt><b><a name="returns_twice">returns_twice</a></b></tt></dt>
1241  <dd>This attribute indicates that this function can return
1242  twice. The C <code>setjmp</code> is an example of such a function.
1243  The compiler disables some optimizations (like tail calls) in the caller of
1244  these functions.</dd>
1245</dl>
1246
1247</div>
1248
1249<!-- ======================================================================= -->
1250<h3>
1251  <a name="moduleasm">Module-Level Inline Assembly</a>
1252</h3>
1253
1254<div>
1255
1256<p>Modules may contain "module-level inline asm" blocks, which corresponds to
1257   the GCC "file scope inline asm" blocks.  These blocks are internally
1258   concatenated by LLVM and treated as a single unit, but may be separated in
1259   the <tt>.ll</tt> file if desired.  The syntax is very simple:</p>
1260
1261<pre class="doc_code">
1262module asm "inline asm code goes here"
1263module asm "more can go here"
1264</pre>
1265
1266<p>The strings can contain any character by escaping non-printable characters.
1267   The escape sequence used is simply "\xx" where "xx" is the two digit hex code
1268   for the number.</p>
1269
1270<p>The inline asm code is simply printed to the machine code .s file when
1271   assembly code is generated.</p>
1272
1273</div>
1274
1275<!-- ======================================================================= -->
1276<h3>
1277  <a name="datalayout">Data Layout</a>
1278</h3>
1279
1280<div>
1281
1282<p>A module may specify a target specific data layout string that specifies how
1283   data is to be laid out in memory. The syntax for the data layout is
1284   simply:</p>
1285
1286<pre class="doc_code">
1287target datalayout = "<i>layout specification</i>"
1288</pre>
1289
1290<p>The <i>layout specification</i> consists of a list of specifications
1291   separated by the minus sign character ('-').  Each specification starts with
1292   a letter and may include other information after the letter to define some
1293   aspect of the data layout.  The specifications accepted are as follows:</p>
1294
1295<dl>
1296  <dt><tt>E</tt></dt>
1297  <dd>Specifies that the target lays out data in big-endian form. That is, the
1298      bits with the most significance have the lowest address location.</dd>
1299
1300  <dt><tt>e</tt></dt>
1301  <dd>Specifies that the target lays out data in little-endian form. That is,
1302      the bits with the least significance have the lowest address
1303      location.</dd>
1304
1305  <dt><tt>S<i>size</i></tt></dt>
1306  <dd>Specifies the natural alignment of the stack in bits. Alignment promotion
1307      of stack variables is limited to the natural stack alignment to avoid
1308      dynamic stack realignment. The stack alignment must be a multiple of
1309      8-bits. If omitted, the natural stack alignment defaults to "unspecified",
1310      which does not prevent any alignment promotions.</dd>
1311
1312  <dt><tt>p:<i>size</i>:<i>abi</i>:<i>pref</i></tt></dt>
1313  <dd>This specifies the <i>size</i> of a pointer and its <i>abi</i> and
1314      <i>preferred</i> alignments. All sizes are in bits. Specifying
1315      the <i>pref</i> alignment is optional. If omitted, the
1316      preceding <tt>:</tt> should be omitted too.</dd>
1317
1318  <dt><tt>i<i>size</i>:<i>abi</i>:<i>pref</i></tt></dt>
1319  <dd>This specifies the alignment for an integer type of a given bit
1320      <i>size</i>. The value of <i>size</i> must be in the range [1,2^23).</dd>
1321
1322  <dt><tt>v<i>size</i>:<i>abi</i>:<i>pref</i></tt></dt>
1323  <dd>This specifies the alignment for a vector type of a given bit
1324      <i>size</i>.</dd>
1325
1326  <dt><tt>f<i>size</i>:<i>abi</i>:<i>pref</i></tt></dt>
1327  <dd>This specifies the alignment for a floating point type of a given bit
1328      <i>size</i>. Only values of <i>size</i> that are supported by the target
1329      will work.  32 (float) and 64 (double) are supported on all targets;
1330      80 or 128 (different flavors of long double) are also supported on some
1331      targets.
1332
1333  <dt><tt>a<i>size</i>:<i>abi</i>:<i>pref</i></tt></dt>
1334  <dd>This specifies the alignment for an aggregate type of a given bit
1335      <i>size</i>.</dd>
1336
1337  <dt><tt>s<i>size</i>:<i>abi</i>:<i>pref</i></tt></dt>
1338  <dd>This specifies the alignment for a stack object of a given bit
1339      <i>size</i>.</dd>
1340
1341  <dt><tt>n<i>size1</i>:<i>size2</i>:<i>size3</i>...</tt></dt>
1342  <dd>This specifies a set of native integer widths for the target CPU
1343      in bits.  For example, it might contain "n32" for 32-bit PowerPC,
1344      "n32:64" for PowerPC 64, or "n8:16:32:64" for X86-64.  Elements of
1345      this set are considered to support most general arithmetic
1346      operations efficiently.</dd>
1347</dl>
1348
1349<p>When constructing the data layout for a given target, LLVM starts with a
1350   default set of specifications which are then (possibly) overridden by the
1351   specifications in the <tt>datalayout</tt> keyword. The default specifications
1352   are given in this list:</p>
1353
1354<ul>
1355  <li><tt>E</tt> - big endian</li>
1356  <li><tt>p:64:64:64</tt> - 64-bit pointers with 64-bit alignment</li>
1357  <li><tt>i1:8:8</tt> - i1 is 8-bit (byte) aligned</li>
1358  <li><tt>i8:8:8</tt> - i8 is 8-bit (byte) aligned</li>
1359  <li><tt>i16:16:16</tt> - i16 is 16-bit aligned</li>
1360  <li><tt>i32:32:32</tt> - i32 is 32-bit aligned</li>
1361  <li><tt>i64:32:64</tt> - i64 has ABI alignment of 32-bits but preferred
1362  alignment of 64-bits</li>
1363  <li><tt>f32:32:32</tt> - float is 32-bit aligned</li>
1364  <li><tt>f64:64:64</tt> - double is 64-bit aligned</li>
1365  <li><tt>v64:64:64</tt> - 64-bit vector is 64-bit aligned</li>
1366  <li><tt>v128:128:128</tt> - 128-bit vector is 128-bit aligned</li>
1367  <li><tt>a0:0:1</tt> - aggregates are 8-bit aligned</li>
1368  <li><tt>s0:64:64</tt> - stack objects are 64-bit aligned</li>
1369</ul>
1370
1371<p>When LLVM is determining the alignment for a given type, it uses the
1372   following rules:</p>
1373
1374<ol>
1375  <li>If the type sought is an exact match for one of the specifications, that
1376      specification is used.</li>
1377
1378  <li>If no match is found, and the type sought is an integer type, then the
1379      smallest integer type that is larger than the bitwidth of the sought type
1380      is used. If none of the specifications are larger than the bitwidth then
1381      the the largest integer type is used. For example, given the default
1382      specifications above, the i7 type will use the alignment of i8 (next
1383      largest) while both i65 and i256 will use the alignment of i64 (largest
1384      specified).</li>
1385
1386  <li>If no match is found, and the type sought is a vector type, then the
1387      largest vector type that is smaller than the sought vector type will be
1388      used as a fall back.  This happens because &lt;128 x double&gt; can be
1389      implemented in terms of 64 &lt;2 x double&gt;, for example.</li>
1390</ol>
1391
1392<p>The function of the data layout string may not be what you expect.  Notably,
1393   this is not a specification from the frontend of what alignment the code
1394   generator should use.</p>
1395
1396<p>Instead, if specified, the target data layout is required to match what the
1397   ultimate <em>code generator</em> expects.  This string is used by the
1398   mid-level optimizers to
1399   improve code, and this only works if it matches what the ultimate code
1400   generator uses.  If you would like to generate IR that does not embed this
1401   target-specific detail into the IR, then you don't have to specify the
1402   string.  This will disable some optimizations that require precise layout
1403   information, but this also prevents those optimizations from introducing
1404   target specificity into the IR.</p>
1405
1406
1407
1408</div>
1409
1410<!-- ======================================================================= -->
1411<h3>
1412  <a name="pointeraliasing">Pointer Aliasing Rules</a>
1413</h3>
1414
1415<div>
1416
1417<p>Any memory access must be done through a pointer value associated
1418with an address range of the memory access, otherwise the behavior
1419is undefined. Pointer values are associated with address ranges
1420according to the following rules:</p>
1421
1422<ul>
1423  <li>A pointer value is associated with the addresses associated with
1424      any value it is <i>based</i> on.
1425  <li>An address of a global variable is associated with the address
1426      range of the variable's storage.</li>
1427  <li>The result value of an allocation instruction is associated with
1428      the address range of the allocated storage.</li>
1429  <li>A null pointer in the default address-space is associated with
1430      no address.</li>
1431  <li>An integer constant other than zero or a pointer value returned
1432      from a function not defined within LLVM may be associated with address
1433      ranges allocated through mechanisms other than those provided by
1434      LLVM. Such ranges shall not overlap with any ranges of addresses
1435      allocated by mechanisms provided by LLVM.</li>
1436</ul>
1437
1438<p>A pointer value is <i>based</i> on another pointer value according
1439   to the following rules:</p>
1440
1441<ul>
1442  <li>A pointer value formed from a
1443      <tt><a href="#i_getelementptr">getelementptr</a></tt> operation
1444      is <i>based</i> on the first operand of the <tt>getelementptr</tt>.</li>
1445  <li>The result value of a
1446      <tt><a href="#i_bitcast">bitcast</a></tt> is <i>based</i> on the operand
1447      of the <tt>bitcast</tt>.</li>
1448  <li>A pointer value formed by an
1449      <tt><a href="#i_inttoptr">inttoptr</a></tt> is <i>based</i> on all
1450      pointer values that contribute (directly or indirectly) to the
1451      computation of the pointer's value.</li>
1452  <li>The "<i>based</i> on" relationship is transitive.</li>
1453</ul>
1454
1455<p>Note that this definition of <i>"based"</i> is intentionally
1456   similar to the definition of <i>"based"</i> in C99, though it is
1457   slightly weaker.</p>
1458
1459<p>LLVM IR does not associate types with memory. The result type of a
1460<tt><a href="#i_load">load</a></tt> merely indicates the size and
1461alignment of the memory from which to load, as well as the
1462interpretation of the value. The first operand type of a
1463<tt><a href="#i_store">store</a></tt> similarly only indicates the size
1464and alignment of the store.</p>
1465
1466<p>Consequently, type-based alias analysis, aka TBAA, aka
1467<tt>-fstrict-aliasing</tt>, is not applicable to general unadorned
1468LLVM IR. <a href="#metadata">Metadata</a> may be used to encode
1469additional information which specialized optimization passes may use
1470to implement type-based alias analysis.</p>
1471
1472</div>
1473
1474<!-- ======================================================================= -->
1475<h3>
1476  <a name="volatile">Volatile Memory Accesses</a>
1477</h3>
1478
1479<div>
1480
1481<p>Certain memory accesses, such as <a href="#i_load"><tt>load</tt></a>s, <a
1482href="#i_store"><tt>store</tt></a>s, and <a
1483href="#int_memcpy"><tt>llvm.memcpy</tt></a>s may be marked <tt>volatile</tt>.
1484The optimizers must not change the number of volatile operations or change their
1485order of execution relative to other volatile operations.  The optimizers
1486<i>may</i> change the order of volatile operations relative to non-volatile
1487operations.  This is not Java's "volatile" and has no cross-thread
1488synchronization behavior.</p>
1489
1490</div>
1491
1492<!-- ======================================================================= -->
1493<h3>
1494  <a name="memmodel">Memory Model for Concurrent Operations</a>
1495</h3>
1496
1497<div>
1498
1499<p>The LLVM IR does not define any way to start parallel threads of execution
1500or to register signal handlers. Nonetheless, there are platform-specific
1501ways to create them, and we define LLVM IR's behavior in their presence. This
1502model is inspired by the C++0x memory model.</p>
1503
1504<p>For a more informal introduction to this model, see the
1505<a href="Atomics.html">LLVM Atomic Instructions and Concurrency Guide</a>.
1506
1507<p>We define a <i>happens-before</i> partial order as the least partial order
1508that</p>
1509<ul>
1510  <li>Is a superset of single-thread program order, and</li>
1511  <li>When a <i>synchronizes-with</i> <tt>b</tt>, includes an edge from
1512      <tt>a</tt> to <tt>b</tt>. <i>Synchronizes-with</i> pairs are introduced
1513      by platform-specific techniques, like pthread locks, thread
1514      creation, thread joining, etc., and by atomic instructions.
1515      (See also <a href="#ordering">Atomic Memory Ordering Constraints</a>).
1516      </li>
1517</ul>
1518
1519<p>Note that program order does not introduce <i>happens-before</i> edges
1520between a thread and signals executing inside that thread.</p>
1521
1522<p>Every (defined) read operation (load instructions, memcpy, atomic
1523loads/read-modify-writes, etc.) <var>R</var> reads a series of bytes written by
1524(defined) write operations (store instructions, atomic
1525stores/read-modify-writes, memcpy, etc.). For the purposes of this section,
1526initialized globals are considered to have a write of the initializer which is
1527atomic and happens before any other read or write of the memory in question.
1528For each byte of a read <var>R</var>, <var>R<sub>byte</sub></var> may see
1529any write to the same byte, except:</p>
1530
1531<ul>
1532  <li>If <var>write<sub>1</sub></var> happens before
1533      <var>write<sub>2</sub></var>, and <var>write<sub>2</sub></var> happens
1534      before <var>R<sub>byte</sub></var>, then <var>R<sub>byte</sub></var>
1535      does not see <var>write<sub>1</sub></var>.
1536  <li>If <var>R<sub>byte</sub></var> happens before
1537      <var>write<sub>3</sub></var>, then <var>R<sub>byte</sub></var> does not
1538      see <var>write<sub>3</sub></var>.
1539</ul>
1540
1541<p>Given that definition, <var>R<sub>byte</sub></var> is defined as follows:
1542<ul>
1543  <li>If <var>R</var> is volatile, the result is target-dependent. (Volatile
1544      is supposed to give guarantees which can support
1545      <code>sig_atomic_t</code> in C/C++, and may be used for accesses to
1546      addresses which do not behave like normal memory.  It does not generally
1547      provide cross-thread synchronization.)
1548  <li>Otherwise, if there is no write to the same byte that happens before
1549    <var>R<sub>byte</sub></var>, <var>R<sub>byte</sub></var> returns
1550    <tt>undef</tt> for that byte.
1551  <li>Otherwise, if <var>R<sub>byte</sub></var> may see exactly one write,
1552      <var>R<sub>byte</sub></var> returns the value written by that
1553      write.</li>
1554  <li>Otherwise, if <var>R</var> is atomic, and all the writes
1555      <var>R<sub>byte</sub></var> may see are atomic, it chooses one of the
1556      values written.  See the <a href="#ordering">Atomic Memory Ordering
1557      Constraints</a> section for additional constraints on how the choice
1558      is made.
1559  <li>Otherwise <var>R<sub>byte</sub></var> returns <tt>undef</tt>.</li>
1560</ul>
1561
1562<p><var>R</var> returns the value composed of the series of bytes it read.
1563This implies that some bytes within the value may be <tt>undef</tt>
1564<b>without</b> the entire value being <tt>undef</tt>. Note that this only
1565defines the semantics of the operation; it doesn't mean that targets will
1566emit more than one instruction to read the series of bytes.</p>
1567
1568<p>Note that in cases where none of the atomic intrinsics are used, this model
1569places only one restriction on IR transformations on top of what is required
1570for single-threaded execution: introducing a store to a byte which might not
1571otherwise be stored is not allowed in general.  (Specifically, in the case
1572where another thread might write to and read from an address, introducing a
1573store can change a load that may see exactly one write into a load that may
1574see multiple writes.)</p>
1575
1576<!-- FIXME: This model assumes all targets where concurrency is relevant have
1577a byte-size store which doesn't affect adjacent bytes.  As far as I can tell,
1578none of the backends currently in the tree fall into this category; however,
1579there might be targets which care.  If there are, we want a paragraph
1580like the following:
1581
1582Targets may specify that stores narrower than a certain width are not
1583available; on such a target, for the purposes of this model, treat any
1584non-atomic write with an alignment or width less than the minimum width
1585as if it writes to the relevant surrounding bytes.
1586-->
1587
1588</div>
1589
1590<!-- ======================================================================= -->
1591<h3>
1592      <a name="ordering">Atomic Memory Ordering Constraints</a>
1593</h3>
1594
1595<div>
1596
1597<p>Atomic instructions (<a href="#i_cmpxchg"><code>cmpxchg</code></a>,
1598<a href="#i_atomicrmw"><code>atomicrmw</code></a>,
1599<a href="#i_fence"><code>fence</code></a>,
1600<a href="#i_load"><code>atomic load</code></a>, and
1601<a href="#i_store"><code>atomic store</code></a>) take an ordering parameter
1602that determines which other atomic instructions on the same address they
1603<i>synchronize with</i>.  These semantics are borrowed from Java and C++0x,
1604but are somewhat more colloquial. If these descriptions aren't precise enough,
1605check those specs (see spec references in the
1606<a href="Atomic.html#introduction">atomics guide</a>).
1607<a href="#i_fence"><code>fence</code></a> instructions
1608treat these orderings somewhat differently since they don't take an address.
1609See that instruction's documentation for details.</p>
1610
1611<p>For a simpler introduction to the ordering constraints, see the
1612<a href="Atomics.html">LLVM Atomic Instructions and Concurrency Guide</a>.</p>
1613
1614<dl>
1615<dt><code>unordered</code></dt>
1616<dd>The set of values that can be read is governed by the happens-before
1617partial order. A value cannot be read unless some operation wrote it.
1618This is intended to provide a guarantee strong enough to model Java's
1619non-volatile shared variables.  This ordering cannot be specified for
1620read-modify-write operations; it is not strong enough to make them atomic
1621in any interesting way.</dd>
1622<dt><code>monotonic</code></dt>
1623<dd>In addition to the guarantees of <code>unordered</code>, there is a single
1624total order for modifications by <code>monotonic</code> operations on each
1625address. All modification orders must be compatible with the happens-before
1626order. There is no guarantee that the modification orders can be combined to
1627a global total order for the whole program (and this often will not be
1628possible). The read in an atomic read-modify-write operation
1629(<a href="#i_cmpxchg"><code>cmpxchg</code></a> and
1630<a href="#i_atomicrmw"><code>atomicrmw</code></a>)
1631reads the value in the modification order immediately before the value it
1632writes. If one atomic read happens before another atomic read of the same
1633address, the later read must see the same value or a later value in the
1634address's modification order. This disallows reordering of
1635<code>monotonic</code> (or stronger) operations on the same address. If an
1636address is written <code>monotonic</code>ally by one thread, and other threads
1637<code>monotonic</code>ally read that address repeatedly, the other threads must
1638eventually see the write. This corresponds to the C++0x/C1x
1639<code>memory_order_relaxed</code>.</dd>
1640<dt><code>acquire</code></dt>
1641<dd>In addition to the guarantees of <code>monotonic</code>,
1642a <i>synchronizes-with</i> edge may be formed with a <code>release</code>
1643operation. This is intended to model C++'s <code>memory_order_acquire</code>.</dd>
1644<dt><code>release</code></dt>
1645<dd>In addition to the guarantees of <code>monotonic</code>, if this operation
1646writes a value which is subsequently read by an <code>acquire</code> operation,
1647it <i>synchronizes-with</i> that operation.  (This isn't a complete
1648description; see the C++0x definition of a release sequence.) This corresponds
1649to the C++0x/C1x <code>memory_order_release</code>.</dd>
1650<dt><code>acq_rel</code> (acquire+release)</dt><dd>Acts as both an
1651<code>acquire</code> and <code>release</code> operation on its address.
1652This corresponds to the C++0x/C1x <code>memory_order_acq_rel</code>.</dd>
1653<dt><code>seq_cst</code> (sequentially consistent)</dt><dd>
1654<dd>In addition to the guarantees of <code>acq_rel</code>
1655(<code>acquire</code> for an operation which only reads, <code>release</code>
1656for an operation which only writes), there is a global total order on all
1657sequentially-consistent operations on all addresses, which is consistent with
1658the <i>happens-before</i> partial order and with the modification orders of
1659all the affected addresses. Each sequentially-consistent read sees the last
1660preceding write to the same address in this global order. This corresponds
1661to the C++0x/C1x <code>memory_order_seq_cst</code> and Java volatile.</dd>
1662</dl>
1663
1664<p id="singlethread">If an atomic operation is marked <code>singlethread</code>,
1665it only <i>synchronizes with</i> or participates in modification and seq_cst
1666total orderings with other operations running in the same thread (for example,
1667in signal handlers).</p>
1668
1669</div>
1670
1671</div>
1672
1673<!-- *********************************************************************** -->
1674<h2><a name="typesystem">Type System</a></h2>
1675<!-- *********************************************************************** -->
1676
1677<div>
1678
1679<p>The LLVM type system is one of the most important features of the
1680   intermediate representation.  Being typed enables a number of optimizations
1681   to be performed on the intermediate representation directly, without having
1682   to do extra analyses on the side before the transformation.  A strong type
1683   system makes it easier to read the generated code and enables novel analyses
1684   and transformations that are not feasible to perform on normal three address
1685   code representations.</p>
1686
1687<!-- ======================================================================= -->
1688<h3>
1689  <a name="t_classifications">Type Classifications</a>
1690</h3>
1691
1692<div>
1693
1694<p>The types fall into a few useful classifications:</p>
1695
1696<table border="1" cellspacing="0" cellpadding="4">
1697  <tbody>
1698    <tr><th>Classification</th><th>Types</th></tr>
1699    <tr>
1700      <td><a href="#t_integer">integer</a></td>
1701      <td><tt>i1, i2, i3, ... i8, ... i16, ... i32, ... i64, ... </tt></td>
1702    </tr>
1703    <tr>
1704      <td><a href="#t_floating">floating point</a></td>
1705      <td><tt>float, double, x86_fp80, fp128, ppc_fp128</tt></td>
1706    </tr>
1707    <tr>
1708      <td><a name="t_firstclass">first class</a></td>
1709      <td><a href="#t_integer">integer</a>,
1710          <a href="#t_floating">floating point</a>,
1711          <a href="#t_pointer">pointer</a>,
1712          <a href="#t_vector">vector</a>,
1713          <a href="#t_struct">structure</a>,
1714          <a href="#t_array">array</a>,
1715          <a href="#t_label">label</a>,
1716          <a href="#t_metadata">metadata</a>.
1717      </td>
1718    </tr>
1719    <tr>
1720      <td><a href="#t_primitive">primitive</a></td>
1721      <td><a href="#t_label">label</a>,
1722          <a href="#t_void">void</a>,
1723          <a href="#t_integer">integer</a>,
1724          <a href="#t_floating">floating point</a>,
1725          <a href="#t_x86mmx">x86mmx</a>,
1726          <a href="#t_metadata">metadata</a>.</td>
1727    </tr>
1728    <tr>
1729      <td><a href="#t_derived">derived</a></td>
1730      <td><a href="#t_array">array</a>,
1731          <a href="#t_function">function</a>,
1732          <a href="#t_pointer">pointer</a>,
1733          <a href="#t_struct">structure</a>,
1734          <a href="#t_vector">vector</a>,
1735          <a href="#t_opaque">opaque</a>.
1736      </td>
1737    </tr>
1738  </tbody>
1739</table>
1740
1741<p>The <a href="#t_firstclass">first class</a> types are perhaps the most
1742   important.  Values of these types are the only ones which can be produced by
1743   instructions.</p>
1744
1745</div>
1746
1747<!-- ======================================================================= -->
1748<h3>
1749  <a name="t_primitive">Primitive Types</a>
1750</h3>
1751
1752<div>
1753
1754<p>The primitive types are the fundamental building blocks of the LLVM
1755   system.</p>
1756
1757<!-- _______________________________________________________________________ -->
1758<h4>
1759  <a name="t_integer">Integer Type</a>
1760</h4>
1761
1762<div>
1763
1764<h5>Overview:</h5>
1765<p>The integer type is a very simple type that simply specifies an arbitrary
1766   bit width for the integer type desired. Any bit width from 1 bit to
1767   2<sup>23</sup>-1 (about 8 million) can be specified.</p>
1768
1769<h5>Syntax:</h5>
1770<pre>
1771  iN
1772</pre>
1773
1774<p>The number of bits the integer will occupy is specified by the <tt>N</tt>
1775   value.</p>
1776
1777<h5>Examples:</h5>
1778<table class="layout">
1779  <tr class="layout">
1780    <td class="left"><tt>i1</tt></td>
1781    <td class="left">a single-bit integer.</td>
1782  </tr>
1783  <tr class="layout">
1784    <td class="left"><tt>i32</tt></td>
1785    <td class="left">a 32-bit integer.</td>
1786  </tr>
1787  <tr class="layout">
1788    <td class="left"><tt>i1942652</tt></td>
1789    <td class="left">a really big integer of over 1 million bits.</td>
1790  </tr>
1791</table>
1792
1793</div>
1794
1795<!-- _______________________________________________________________________ -->
1796<h4>
1797  <a name="t_floating">Floating Point Types</a>
1798</h4>
1799
1800<div>
1801
1802<table>
1803  <tbody>
1804    <tr><th>Type</th><th>Description</th></tr>
1805    <tr><td><tt>float</tt></td><td>32-bit floating point value</td></tr>
1806    <tr><td><tt>double</tt></td><td>64-bit floating point value</td></tr>
1807    <tr><td><tt>fp128</tt></td><td>128-bit floating point value (112-bit mantissa)</td></tr>
1808    <tr><td><tt>x86_fp80</tt></td><td>80-bit floating point value (X87)</td></tr>
1809    <tr><td><tt>ppc_fp128</tt></td><td>128-bit floating point value (two 64-bits)</td></tr>
1810  </tbody>
1811</table>
1812
1813</div>
1814
1815<!-- _______________________________________________________________________ -->
1816<h4>
1817  <a name="t_x86mmx">X86mmx Type</a>
1818</h4>
1819
1820<div>
1821
1822<h5>Overview:</h5>
1823<p>The x86mmx type represents a value held in an MMX register on an x86 machine.  The operations allowed on it are quite limited:  parameters and return values, load and store, and bitcast.  User-specified MMX instructions are represented as intrinsic or asm calls with arguments and/or results of this type.  There are no arrays, vectors or constants of this type.</p>
1824
1825<h5>Syntax:</h5>
1826<pre>
1827  x86mmx
1828</pre>
1829
1830</div>
1831
1832<!-- _______________________________________________________________________ -->
1833<h4>
1834  <a name="t_void">Void Type</a>
1835</h4>
1836
1837<div>
1838
1839<h5>Overview:</h5>
1840<p>The void type does not represent any value and has no size.</p>
1841
1842<h5>Syntax:</h5>
1843<pre>
1844  void
1845</pre>
1846
1847</div>
1848
1849<!-- _______________________________________________________________________ -->
1850<h4>
1851  <a name="t_label">Label Type</a>
1852</h4>
1853
1854<div>
1855
1856<h5>Overview:</h5>
1857<p>The label type represents code labels.</p>
1858
1859<h5>Syntax:</h5>
1860<pre>
1861  label
1862</pre>
1863
1864</div>
1865
1866<!-- _______________________________________________________________________ -->
1867<h4>
1868  <a name="t_metadata">Metadata Type</a>
1869</h4>
1870
1871<div>
1872
1873<h5>Overview:</h5>
1874<p>The metadata type represents embedded metadata. No derived types may be
1875   created from metadata except for <a href="#t_function">function</a>
1876   arguments.
1877
1878<h5>Syntax:</h5>
1879<pre>
1880  metadata
1881</pre>
1882
1883</div>
1884
1885</div>
1886
1887<!-- ======================================================================= -->
1888<h3>
1889  <a name="t_derived">Derived Types</a>
1890</h3>
1891
1892<div>
1893
1894<p>The real power in LLVM comes from the derived types in the system.  This is
1895   what allows a programmer to represent arrays, functions, pointers, and other
1896   useful types.  Each of these types contain one or more element types which
1897   may be a primitive type, or another derived type.  For example, it is
1898   possible to have a two dimensional array, using an array as the element type
1899   of another array.</p>
1900
1901</div>
1902
1903
1904<!-- _______________________________________________________________________ -->
1905<h4>
1906  <a name="t_aggregate">Aggregate Types</a>
1907</h4>
1908
1909<div>
1910
1911<p>Aggregate Types are a subset of derived types that can contain multiple
1912  member types. <a href="#t_array">Arrays</a>,
1913  <a href="#t_struct">structs</a>, and <a href="#t_vector">vectors</a> are
1914  aggregate types.</p>
1915
1916</div>
1917
1918<!-- _______________________________________________________________________ -->
1919<h4>
1920  <a name="t_array">Array Type</a>
1921</h4>
1922
1923<div>
1924
1925<h5>Overview:</h5>
1926<p>The array type is a very simple derived type that arranges elements
1927   sequentially in memory.  The array type requires a size (number of elements)
1928   and an underlying data type.</p>
1929
1930<h5>Syntax:</h5>
1931<pre>
1932  [&lt;# elements&gt; x &lt;elementtype&gt;]
1933</pre>
1934
1935<p>The number of elements is a constant integer value; <tt>elementtype</tt> may
1936   be any type with a size.</p>
1937
1938<h5>Examples:</h5>
1939<table class="layout">
1940  <tr class="layout">
1941    <td class="left"><tt>[40 x i32]</tt></td>
1942    <td class="left">Array of 40 32-bit integer values.</td>
1943  </tr>
1944  <tr class="layout">
1945    <td class="left"><tt>[41 x i32]</tt></td>
1946    <td class="left">Array of 41 32-bit integer values.</td>
1947  </tr>
1948  <tr class="layout">
1949    <td class="left"><tt>[4 x i8]</tt></td>
1950    <td class="left">Array of 4 8-bit integer values.</td>
1951  </tr>
1952</table>
1953<p>Here are some examples of multidimensional arrays:</p>
1954<table class="layout">
1955  <tr class="layout">
1956    <td class="left"><tt>[3 x [4 x i32]]</tt></td>
1957    <td class="left">3x4 array of 32-bit integer values.</td>
1958  </tr>
1959  <tr class="layout">
1960    <td class="left"><tt>[12 x [10 x float]]</tt></td>
1961    <td class="left">12x10 array of single precision floating point values.</td>
1962  </tr>
1963  <tr class="layout">
1964    <td class="left"><tt>[2 x [3 x [4 x i16]]]</tt></td>
1965    <td class="left">2x3x4 array of 16-bit integer  values.</td>
1966  </tr>
1967</table>
1968
1969<p>There is no restriction on indexing beyond the end of the array implied by
1970   a static type (though there are restrictions on indexing beyond the bounds
1971   of an allocated object in some cases). This means that single-dimension
1972   'variable sized array' addressing can be implemented in LLVM with a zero
1973   length array type. An implementation of 'pascal style arrays' in LLVM could
1974   use the type "<tt>{ i32, [0 x float]}</tt>", for example.</p>
1975
1976</div>
1977
1978<!-- _______________________________________________________________________ -->
1979<h4>
1980  <a name="t_function">Function Type</a>
1981</h4>
1982
1983<div>
1984
1985<h5>Overview:</h5>
1986<p>The function type can be thought of as a function signature.  It consists of
1987   a return type and a list of formal parameter types. The return type of a
1988   function type is a first class type or a void type.</p>
1989
1990<h5>Syntax:</h5>
1991<pre>
1992  &lt;returntype&gt; (&lt;parameter list&gt;)
1993</pre>
1994
1995<p>...where '<tt>&lt;parameter list&gt;</tt>' is a comma-separated list of type
1996   specifiers.  Optionally, the parameter list may include a type <tt>...</tt>,
1997   which indicates that the function takes a variable number of arguments.
1998   Variable argument functions can access their arguments with
1999   the <a href="#int_varargs">variable argument handling intrinsic</a>
2000   functions.  '<tt>&lt;returntype&gt;</tt>' is any type except
2001   <a href="#t_label">label</a>.</p>
2002
2003<h5>Examples:</h5>
2004<table class="layout">
2005  <tr class="layout">
2006    <td class="left"><tt>i32 (i32)</tt></td>
2007    <td class="left">function taking an <tt>i32</tt>, returning an <tt>i32</tt>
2008    </td>
2009  </tr><tr class="layout">
2010    <td class="left"><tt>float&nbsp;(i16,&nbsp;i32&nbsp;*)&nbsp;*
2011    </tt></td>
2012    <td class="left"><a href="#t_pointer">Pointer</a> to a function that takes
2013      an <tt>i16</tt> and a <a href="#t_pointer">pointer</a> to <tt>i32</tt>,
2014      returning <tt>float</tt>.
2015    </td>
2016  </tr><tr class="layout">
2017    <td class="left"><tt>i32 (i8*, ...)</tt></td>
2018    <td class="left">A vararg function that takes at least one
2019      <a href="#t_pointer">pointer</a> to <tt>i8 </tt> (char in C),
2020      which returns an integer.  This is the signature for <tt>printf</tt> in
2021      LLVM.
2022    </td>
2023  </tr><tr class="layout">
2024    <td class="left"><tt>{i32, i32} (i32)</tt></td>
2025    <td class="left">A function taking an <tt>i32</tt>, returning a
2026        <a href="#t_struct">structure</a> containing two <tt>i32</tt> values
2027    </td>
2028  </tr>
2029</table>
2030
2031</div>
2032
2033<!-- _______________________________________________________________________ -->
2034<h4>
2035  <a name="t_struct">Structure Type</a>
2036</h4>
2037
2038<div>
2039
2040<h5>Overview:</h5>
2041<p>The structure type is used to represent a collection of data members together
2042  in memory.  The elements of a structure may be any type that has a size.</p>
2043
2044<p>Structures in memory are accessed using '<tt><a href="#i_load">load</a></tt>'
2045   and '<tt><a href="#i_store">store</a></tt>' by getting a pointer to a field
2046   with the '<tt><a href="#i_getelementptr">getelementptr</a></tt>' instruction.
2047   Structures in registers are accessed using the
2048   '<tt><a href="#i_extractvalue">extractvalue</a></tt>' and
2049   '<tt><a href="#i_insertvalue">insertvalue</a></tt>' instructions.</p>
2050
2051<p>Structures may optionally be "packed" structures, which indicate that the
2052  alignment of the struct is one byte, and that there is no padding between
2053  the elements.  In non-packed structs, padding between field types is inserted
2054  as defined by the TargetData string in the module, which is required to match
2055  what the underlying code generator expects.</p>
2056
2057<p>Structures can either be "literal" or "identified".  A literal structure is
2058  defined inline with other types (e.g. <tt>{i32, i32}*</tt>) whereas identified
2059  types are always defined at the top level with a name.  Literal types are
2060  uniqued by their contents and can never be recursive or opaque since there is
2061  no way to write one.  Identified types can be recursive, can be opaqued, and are
2062  never uniqued.
2063</p>
2064
2065<h5>Syntax:</h5>
2066<pre>
2067  %T1 = type { &lt;type list&gt; }     <i>; Identified normal struct type</i>
2068  %T2 = type &lt;{ &lt;type list&gt; }&gt;   <i>; Identified packed struct type</i>
2069</pre>
2070
2071<h5>Examples:</h5>
2072<table class="layout">
2073  <tr class="layout">
2074    <td class="left"><tt>{ i32, i32, i32 }</tt></td>
2075    <td class="left">A triple of three <tt>i32</tt> values</td>
2076  </tr>
2077  <tr class="layout">
2078    <td class="left"><tt>{&nbsp;float,&nbsp;i32&nbsp;(i32)&nbsp;*&nbsp;}</tt></td>
2079    <td class="left">A pair, where the first element is a <tt>float</tt> and the
2080      second element is a <a href="#t_pointer">pointer</a> to a
2081      <a href="#t_function">function</a> that takes an <tt>i32</tt>, returning
2082      an <tt>i32</tt>.</td>
2083  </tr>
2084  <tr class="layout">
2085    <td class="left"><tt>&lt;{ i8, i32 }&gt;</tt></td>
2086    <td class="left">A packed struct known to be 5 bytes in size.</td>
2087  </tr>
2088</table>
2089
2090</div>
2091
2092<!-- _______________________________________________________________________ -->
2093<h4>
2094  <a name="t_opaque">Opaque Structure Types</a>
2095</h4>
2096
2097<div>
2098
2099<h5>Overview:</h5>
2100<p>Opaque structure types are used to represent named structure types that do
2101   not have a body specified.  This corresponds (for example) to the C notion of
2102   a forward declared structure.</p>
2103
2104<h5>Syntax:</h5>
2105<pre>
2106  %X = type opaque
2107  %52 = type opaque
2108</pre>
2109
2110<h5>Examples:</h5>
2111<table class="layout">
2112  <tr class="layout">
2113    <td class="left"><tt>opaque</tt></td>
2114    <td class="left">An opaque type.</td>
2115  </tr>
2116</table>
2117
2118</div>
2119
2120
2121
2122<!-- _______________________________________________________________________ -->
2123<h4>
2124  <a name="t_pointer">Pointer Type</a>
2125</h4>
2126
2127<div>
2128
2129<h5>Overview:</h5>
2130<p>The pointer type is used to specify memory locations.
2131   Pointers are commonly used to reference objects in memory.</p>
2132
2133<p>Pointer types may have an optional address space attribute defining the
2134   numbered address space where the pointed-to object resides. The default
2135   address space is number zero. The semantics of non-zero address
2136   spaces are target-specific.</p>
2137
2138<p>Note that LLVM does not permit pointers to void (<tt>void*</tt>) nor does it
2139   permit pointers to labels (<tt>label*</tt>).  Use <tt>i8*</tt> instead.</p>
2140
2141<h5>Syntax:</h5>
2142<pre>
2143  &lt;type&gt; *
2144</pre>
2145
2146<h5>Examples:</h5>
2147<table class="layout">
2148  <tr class="layout">
2149    <td class="left"><tt>[4 x i32]*</tt></td>
2150    <td class="left">A <a href="#t_pointer">pointer</a> to <a
2151                    href="#t_array">array</a> of four <tt>i32</tt> values.</td>
2152  </tr>
2153  <tr class="layout">
2154    <td class="left"><tt>i32 (i32*) *</tt></td>
2155    <td class="left"> A <a href="#t_pointer">pointer</a> to a <a
2156      href="#t_function">function</a> that takes an <tt>i32*</tt>, returning an
2157      <tt>i32</tt>.</td>
2158  </tr>
2159  <tr class="layout">
2160    <td class="left"><tt>i32 addrspace(5)*</tt></td>
2161    <td class="left">A <a href="#t_pointer">pointer</a> to an <tt>i32</tt> value
2162     that resides in address space #5.</td>
2163  </tr>
2164</table>
2165
2166</div>
2167
2168<!-- _______________________________________________________________________ -->
2169<h4>
2170  <a name="t_vector">Vector Type</a>
2171</h4>
2172
2173<div>
2174
2175<h5>Overview:</h5>
2176<p>A vector type is a simple derived type that represents a vector of elements.
2177   Vector types are used when multiple primitive data are operated in parallel
2178   using a single instruction (SIMD).  A vector type requires a size (number of
2179   elements) and an underlying primitive data type.  Vector types are considered
2180   <a href="#t_firstclass">first class</a>.</p>
2181
2182<h5>Syntax:</h5>
2183<pre>
2184  &lt; &lt;# elements&gt; x &lt;elementtype&gt; &gt;
2185</pre>
2186
2187<p>The number of elements is a constant integer value larger than 0; elementtype
2188   may be any integer or floating point type.  Vectors of size zero are not
2189   allowed, and pointers are not allowed as the element type.</p>
2190
2191<h5>Examples:</h5>
2192<table class="layout">
2193  <tr class="layout">
2194    <td class="left"><tt>&lt;4 x i32&gt;</tt></td>
2195    <td class="left">Vector of 4 32-bit integer values.</td>
2196  </tr>
2197  <tr class="layout">
2198    <td class="left"><tt>&lt;8 x float&gt;</tt></td>
2199    <td class="left">Vector of 8 32-bit floating-point values.</td>
2200  </tr>
2201  <tr class="layout">
2202    <td class="left"><tt>&lt;2 x i64&gt;</tt></td>
2203    <td class="left">Vector of 2 64-bit integer values.</td>
2204  </tr>
2205</table>
2206
2207</div>
2208
2209</div>
2210
2211<!-- *********************************************************************** -->
2212<h2><a name="constants">Constants</a></h2>
2213<!-- *********************************************************************** -->
2214
2215<div>
2216
2217<p>LLVM has several different basic types of constants.  This section describes
2218   them all and their syntax.</p>
2219
2220<!-- ======================================================================= -->
2221<h3>
2222  <a name="simpleconstants">Simple Constants</a>
2223</h3>
2224
2225<div>
2226
2227<dl>
2228  <dt><b>Boolean constants</b></dt>
2229  <dd>The two strings '<tt>true</tt>' and '<tt>false</tt>' are both valid
2230      constants of the <tt><a href="#t_integer">i1</a></tt> type.</dd>
2231
2232  <dt><b>Integer constants</b></dt>
2233  <dd>Standard integers (such as '4') are constants of
2234      the <a href="#t_integer">integer</a> type.  Negative numbers may be used
2235      with integer types.</dd>
2236
2237  <dt><b>Floating point constants</b></dt>
2238  <dd>Floating point constants use standard decimal notation (e.g. 123.421),
2239      exponential notation (e.g. 1.23421e+2), or a more precise hexadecimal
2240      notation (see below).  The assembler requires the exact decimal value of a
2241      floating-point constant.  For example, the assembler accepts 1.25 but
2242      rejects 1.3 because 1.3 is a repeating decimal in binary.  Floating point
2243      constants must have a <a href="#t_floating">floating point</a> type. </dd>
2244
2245  <dt><b>Null pointer constants</b></dt>
2246  <dd>The identifier '<tt>null</tt>' is recognized as a null pointer constant
2247      and must be of <a href="#t_pointer">pointer type</a>.</dd>
2248</dl>
2249
2250<p>The one non-intuitive notation for constants is the hexadecimal form of
2251   floating point constants.  For example, the form '<tt>double
2252   0x432ff973cafa8000</tt>' is equivalent to (but harder to read than)
2253   '<tt>double 4.5e+15</tt>'.  The only time hexadecimal floating point
2254   constants are required (and the only time that they are generated by the
2255   disassembler) is when a floating point constant must be emitted but it cannot
2256   be represented as a decimal floating point number in a reasonable number of
2257   digits.  For example, NaN's, infinities, and other special values are
2258   represented in their IEEE hexadecimal format so that assembly and disassembly
2259   do not cause any bits to change in the constants.</p>
2260
2261<p>When using the hexadecimal form, constants of types float and double are
2262   represented using the 16-digit form shown above (which matches the IEEE754
2263   representation for double); float values must, however, be exactly
2264   representable as IEE754 single precision.  Hexadecimal format is always used
2265   for long double, and there are three forms of long double.  The 80-bit format
2266   used by x86 is represented as <tt>0xK</tt> followed by 20 hexadecimal digits.
2267   The 128-bit format used by PowerPC (two adjacent doubles) is represented
2268   by <tt>0xM</tt> followed by 32 hexadecimal digits.  The IEEE 128-bit format
2269   is represented by <tt>0xL</tt> followed by 32 hexadecimal digits; no
2270   currently supported target uses this format.  Long doubles will only work if
2271   they match the long double format on your target.  All hexadecimal formats
2272   are big-endian (sign bit at the left).</p>
2273
2274<p>There are no constants of type x86mmx.</p>
2275</div>
2276
2277<!-- ======================================================================= -->
2278<h3>
2279<a name="aggregateconstants"></a> <!-- old anchor -->
2280<a name="complexconstants">Complex Constants</a>
2281</h3>
2282
2283<div>
2284
2285<p>Complex constants are a (potentially recursive) combination of simple
2286   constants and smaller complex constants.</p>
2287
2288<dl>
2289  <dt><b>Structure constants</b></dt>
2290  <dd>Structure constants are represented with notation similar to structure
2291      type definitions (a comma separated list of elements, surrounded by braces
2292      (<tt>{}</tt>)).  For example: "<tt>{ i32 4, float 17.0, i32* @G }</tt>",
2293      where "<tt>@G</tt>" is declared as "<tt>@G = external global i32</tt>".
2294      Structure constants must have <a href="#t_struct">structure type</a>, and
2295      the number and types of elements must match those specified by the
2296      type.</dd>
2297
2298  <dt><b>Array constants</b></dt>
2299  <dd>Array constants are represented with notation similar to array type
2300     definitions (a comma separated list of elements, surrounded by square
2301     brackets (<tt>[]</tt>)).  For example: "<tt>[ i32 42, i32 11, i32 74
2302     ]</tt>".  Array constants must have <a href="#t_array">array type</a>, and
2303     the number and types of elements must match those specified by the
2304     type.</dd>
2305
2306  <dt><b>Vector constants</b></dt>
2307  <dd>Vector constants are represented with notation similar to vector type
2308      definitions (a comma separated list of elements, surrounded by
2309      less-than/greater-than's (<tt>&lt;&gt;</tt>)).  For example: "<tt>&lt; i32
2310      42, i32 11, i32 74, i32 100 &gt;</tt>".  Vector constants must
2311      have <a href="#t_vector">vector type</a>, and the number and types of
2312      elements must match those specified by the type.</dd>
2313
2314  <dt><b>Zero initialization</b></dt>
2315  <dd>The string '<tt>zeroinitializer</tt>' can be used to zero initialize a
2316      value to zero of <em>any</em> type, including scalar and
2317      <a href="#t_aggregate">aggregate</a> types.
2318      This is often used to avoid having to print large zero initializers
2319      (e.g. for large arrays) and is always exactly equivalent to using explicit
2320      zero initializers.</dd>
2321
2322  <dt><b>Metadata node</b></dt>
2323  <dd>A metadata node is a structure-like constant with
2324      <a href="#t_metadata">metadata type</a>.  For example: "<tt>metadata !{
2325      i32 0, metadata !"test" }</tt>".  Unlike other constants that are meant to
2326      be interpreted as part of the instruction stream, metadata is a place to
2327      attach additional information such as debug info.</dd>
2328</dl>
2329
2330</div>
2331
2332<!-- ======================================================================= -->
2333<h3>
2334  <a name="globalconstants">Global Variable and Function Addresses</a>
2335</h3>
2336
2337<div>
2338
2339<p>The addresses of <a href="#globalvars">global variables</a>
2340   and <a href="#functionstructure">functions</a> are always implicitly valid
2341   (link-time) constants.  These constants are explicitly referenced when
2342   the <a href="#identifiers">identifier for the global</a> is used and always
2343   have <a href="#t_pointer">pointer</a> type. For example, the following is a
2344   legal LLVM file:</p>
2345
2346<pre class="doc_code">
2347@X = global i32 17
2348@Y = global i32 42
2349@Z = global [2 x i32*] [ i32* @X, i32* @Y ]
2350</pre>
2351
2352</div>
2353
2354<!-- ======================================================================= -->
2355<h3>
2356  <a name="undefvalues">Undefined Values</a>
2357</h3>
2358
2359<div>
2360
2361<p>The string '<tt>undef</tt>' can be used anywhere a constant is expected, and
2362   indicates that the user of the value may receive an unspecified bit-pattern.
2363   Undefined values may be of any type (other than '<tt>label</tt>'
2364   or '<tt>void</tt>') and be used anywhere a constant is permitted.</p>
2365
2366<p>Undefined values are useful because they indicate to the compiler that the
2367   program is well defined no matter what value is used.  This gives the
2368   compiler more freedom to optimize.  Here are some examples of (potentially
2369   surprising) transformations that are valid (in pseudo IR):</p>
2370
2371
2372<pre class="doc_code">
2373  %A = add %X, undef
2374  %B = sub %X, undef
2375  %C = xor %X, undef
2376Safe:
2377  %A = undef
2378  %B = undef
2379  %C = undef
2380</pre>
2381
2382<p>This is safe because all of the output bits are affected by the undef bits.
2383   Any output bit can have a zero or one depending on the input bits.</p>
2384
2385<pre class="doc_code">
2386  %A = or %X, undef
2387  %B = and %X, undef
2388Safe:
2389  %A = -1
2390  %B = 0
2391Unsafe:
2392  %A = undef
2393  %B = undef
2394</pre>
2395
2396<p>These logical operations have bits that are not always affected by the input.
2397   For example, if <tt>%X</tt> has a zero bit, then the output of the
2398   '<tt>and</tt>' operation will always be a zero for that bit, no matter what
2399   the corresponding bit from the '<tt>undef</tt>' is. As such, it is unsafe to
2400   optimize or assume that the result of the '<tt>and</tt>' is '<tt>undef</tt>'.
2401   However, it is safe to assume that all bits of the '<tt>undef</tt>' could be
2402   0, and optimize the '<tt>and</tt>' to 0. Likewise, it is safe to assume that
2403   all the bits of the '<tt>undef</tt>' operand to the '<tt>or</tt>' could be
2404   set, allowing the '<tt>or</tt>' to be folded to -1.</p>
2405
2406<pre class="doc_code">
2407  %A = select undef, %X, %Y
2408  %B = select undef, 42, %Y
2409  %C = select %X, %Y, undef
2410Safe:
2411  %A = %X     (or %Y)
2412  %B = 42     (or %Y)
2413  %C = %Y
2414Unsafe:
2415  %A = undef
2416  %B = undef
2417  %C = undef
2418</pre>
2419
2420<p>This set of examples shows that undefined '<tt>select</tt>' (and conditional
2421   branch) conditions can go <em>either way</em>, but they have to come from one
2422   of the two operands.  In the <tt>%A</tt> example, if <tt>%X</tt> and
2423   <tt>%Y</tt> were both known to have a clear low bit, then <tt>%A</tt> would
2424   have to have a cleared low bit. However, in the <tt>%C</tt> example, the
2425   optimizer is allowed to assume that the '<tt>undef</tt>' operand could be the
2426   same as <tt>%Y</tt>, allowing the whole '<tt>select</tt>' to be
2427   eliminated.</p>
2428
2429<pre class="doc_code">
2430  %A = xor undef, undef
2431
2432  %B = undef
2433  %C = xor %B, %B
2434
2435  %D = undef
2436  %E = icmp lt %D, 4
2437  %F = icmp gte %D, 4
2438
2439Safe:
2440  %A = undef
2441  %B = undef
2442  %C = undef
2443  %D = undef
2444  %E = undef
2445  %F = undef
2446</pre>
2447
2448<p>This example points out that two '<tt>undef</tt>' operands are not
2449   necessarily the same. This can be surprising to people (and also matches C
2450   semantics) where they assume that "<tt>X^X</tt>" is always zero, even
2451   if <tt>X</tt> is undefined. This isn't true for a number of reasons, but the
2452   short answer is that an '<tt>undef</tt>' "variable" can arbitrarily change
2453   its value over its "live range".  This is true because the variable doesn't
2454   actually <em>have a live range</em>. Instead, the value is logically read
2455   from arbitrary registers that happen to be around when needed, so the value
2456   is not necessarily consistent over time. In fact, <tt>%A</tt> and <tt>%C</tt>
2457   need to have the same semantics or the core LLVM "replace all uses with"
2458   concept would not hold.</p>
2459
2460<pre class="doc_code">
2461  %A = fdiv undef, %X
2462  %B = fdiv %X, undef
2463Safe:
2464  %A = undef
2465b: unreachable
2466</pre>
2467
2468<p>These examples show the crucial difference between an <em>undefined
2469  value</em> and <em>undefined behavior</em>. An undefined value (like
2470  '<tt>undef</tt>') is allowed to have an arbitrary bit-pattern. This means that
2471  the <tt>%A</tt> operation can be constant folded to '<tt>undef</tt>', because
2472  the '<tt>undef</tt>' could be an SNaN, and <tt>fdiv</tt> is not (currently)
2473  defined on SNaN's. However, in the second example, we can make a more
2474  aggressive assumption: because the <tt>undef</tt> is allowed to be an
2475  arbitrary value, we are allowed to assume that it could be zero. Since a
2476  divide by zero has <em>undefined behavior</em>, we are allowed to assume that
2477  the operation does not execute at all. This allows us to delete the divide and
2478  all code after it. Because the undefined operation "can't happen", the
2479  optimizer can assume that it occurs in dead code.</p>
2480
2481<pre class="doc_code">
2482a:  store undef -> %X
2483b:  store %X -> undef
2484Safe:
2485a: &lt;deleted&gt;
2486b: unreachable
2487</pre>
2488
2489<p>These examples reiterate the <tt>fdiv</tt> example: a store <em>of</em> an
2490   undefined value can be assumed to not have any effect; we can assume that the
2491   value is overwritten with bits that happen to match what was already there.
2492   However, a store <em>to</em> an undefined location could clobber arbitrary
2493   memory, therefore, it has undefined behavior.</p>
2494
2495</div>
2496
2497<!-- ======================================================================= -->
2498<h3>
2499  <a name="trapvalues">Trap Values</a>
2500</h3>
2501
2502<div>
2503
2504<p>Trap values are similar to <a href="#undefvalues">undef values</a>, however
2505   instead of representing an unspecified bit pattern, they represent the
2506   fact that an instruction or constant expression which cannot evoke side
2507   effects has nevertheless detected a condition which results in undefined
2508   behavior.</p>
2509
2510<p>There is currently no way of representing a trap value in the IR; they
2511   only exist when produced by operations such as
2512   <a href="#i_add"><tt>add</tt></a> with the <tt>nsw</tt> flag.</p>
2513
2514<p>Trap value behavior is defined in terms of value <i>dependence</i>:</p>
2515
2516<ul>
2517<li>Values other than <a href="#i_phi"><tt>phi</tt></a> nodes depend on
2518    their operands.</li>
2519
2520<li><a href="#i_phi"><tt>Phi</tt></a> nodes depend on the operand corresponding
2521    to their dynamic predecessor basic block.</li>
2522
2523<li>Function arguments depend on the corresponding actual argument values in
2524    the dynamic callers of their functions.</li>
2525
2526<li><a href="#i_call"><tt>Call</tt></a> instructions depend on the
2527    <a href="#i_ret"><tt>ret</tt></a> instructions that dynamically transfer
2528    control back to them.</li>
2529
2530<li><a href="#i_invoke"><tt>Invoke</tt></a> instructions depend on the
2531    <a href="#i_ret"><tt>ret</tt></a>, <a href="#i_unwind"><tt>unwind</tt></a>,
2532    or exception-throwing call instructions that dynamically transfer control
2533    back to them.</li>
2534
2535<li>Non-volatile loads and stores depend on the most recent stores to all of the
2536    referenced memory addresses, following the order in the IR
2537    (including loads and stores implied by intrinsics such as
2538    <a href="#int_memcpy"><tt>@llvm.memcpy</tt></a>.)</li>
2539
2540<!-- TODO: In the case of multiple threads, this only applies if the store
2541     "happens-before" the load or store. -->
2542
2543<!-- TODO: floating-point exception state -->
2544
2545<li>An instruction with externally visible side effects depends on the most
2546    recent preceding instruction with externally visible side effects, following
2547    the order in the IR. (This includes
2548    <a href="#volatile">volatile operations</a>.)</li>
2549
2550<li>An instruction <i>control-depends</i> on a
2551    <a href="#terminators">terminator instruction</a>
2552    if the terminator instruction has multiple successors and the instruction
2553    is always executed when control transfers to one of the successors, and
2554    may not be executed when control is transferred to another.</li>
2555
2556<li>Additionally, an instruction also <i>control-depends</i> on a terminator
2557    instruction if the set of instructions it otherwise depends on would be
2558    different if the terminator had transferred control to a different
2559    successor.</li>
2560
2561<li>Dependence is transitive.</li>
2562
2563</ul>
2564
2565<p>Whenever a trap value is generated, all values which depend on it evaluate
2566   to trap. If they have side effects, they evoke their side effects as if each
2567   operand with a trap value were undef. If they have externally-visible side
2568   effects, the behavior is undefined.</p>
2569
2570<p>Here are some examples:</p>
2571
2572<pre class="doc_code">
2573entry:
2574  %trap = sub nuw i32 0, 1           ; Results in a trap value.
2575  %still_trap = and i32 %trap, 0     ; Whereas (and i32 undef, 0) would return 0.
2576  %trap_yet_again = getelementptr i32* @h, i32 %still_trap
2577  store i32 0, i32* %trap_yet_again  ; undefined behavior
2578
2579  store i32 %trap, i32* @g           ; Trap value conceptually stored to memory.
2580  %trap2 = load i32* @g              ; Returns a trap value, not just undef.
2581
2582  volatile store i32 %trap, i32* @g  ; External observation; undefined behavior.
2583
2584  %narrowaddr = bitcast i32* @g to i16*
2585  %wideaddr = bitcast i32* @g to i64*
2586  %trap3 = load i16* %narrowaddr     ; Returns a trap value.
2587  %trap4 = load i64* %wideaddr       ; Returns a trap value.
2588
2589  %cmp = icmp slt i32 %trap, 0       ; Returns a trap value.
2590  br i1 %cmp, label %true, label %end ; Branch to either destination.
2591
2592true:
2593  volatile store i32 0, i32* @g      ; This is control-dependent on %cmp, so
2594                                     ; it has undefined behavior.
2595  br label %end
2596
2597end:
2598  %p = phi i32 [ 0, %entry ], [ 1, %true ]
2599                                     ; Both edges into this PHI are
2600                                     ; control-dependent on %cmp, so this
2601                                     ; always results in a trap value.
2602
2603  volatile store i32 0, i32* @g      ; This would depend on the store in %true
2604                                     ; if %cmp is true, or the store in %entry
2605                                     ; otherwise, so this is undefined behavior.
2606
2607  br i1 %cmp, label %second_true, label %second_end
2608                                     ; The same branch again, but this time the
2609                                     ; true block doesn't have side effects.
2610
2611second_true:
2612  ; No side effects!
2613  ret void
2614
2615second_end:
2616  volatile store i32 0, i32* @g      ; This time, the instruction always depends
2617                                     ; on the store in %end. Also, it is
2618                                     ; control-equivalent to %end, so this is
2619                                     ; well-defined (again, ignoring earlier
2620                                     ; undefined behavior in this example).
2621</pre>
2622
2623</div>
2624
2625<!-- ======================================================================= -->
2626<h3>
2627  <a name="blockaddress">Addresses of Basic Blocks</a>
2628</h3>
2629
2630<div>
2631
2632<p><b><tt>blockaddress(@function, %block)</tt></b></p>
2633
2634<p>The '<tt>blockaddress</tt>' constant computes the address of the specified
2635   basic block in the specified function, and always has an i8* type.  Taking
2636   the address of the entry block is illegal.</p>
2637
2638<p>This value only has defined behavior when used as an operand to the
2639   '<a href="#i_indirectbr"><tt>indirectbr</tt></a>' instruction, or for
2640   comparisons against null. Pointer equality tests between labels addresses
2641   results in undefined behavior &mdash; though, again, comparison against null
2642   is ok, and no label is equal to the null pointer. This may be passed around
2643   as an opaque pointer sized value as long as the bits are not inspected. This
2644   allows <tt>ptrtoint</tt> and arithmetic to be performed on these values so
2645   long as the original value is reconstituted before the <tt>indirectbr</tt>
2646   instruction.</p>
2647
2648<p>Finally, some targets may provide defined semantics when using the value as
2649   the operand to an inline assembly, but that is target specific.</p>
2650
2651</div>
2652
2653
2654<!-- ======================================================================= -->
2655<h3>
2656  <a name="constantexprs">Constant Expressions</a>
2657</h3>
2658
2659<div>
2660
2661<p>Constant expressions are used to allow expressions involving other constants
2662   to be used as constants.  Constant expressions may be of
2663   any <a href="#t_firstclass">first class</a> type and may involve any LLVM
2664   operation that does not have side effects (e.g. load and call are not
2665   supported). The following is the syntax for constant expressions:</p>
2666
2667<dl>
2668  <dt><b><tt>trunc (CST to TYPE)</tt></b></dt>
2669  <dd>Truncate a constant to another type. The bit size of CST must be larger
2670      than the bit size of TYPE. Both types must be integers.</dd>
2671
2672  <dt><b><tt>zext (CST to TYPE)</tt></b></dt>
2673  <dd>Zero extend a constant to another type. The bit size of CST must be
2674      smaller than the bit size of TYPE.  Both types must be integers.</dd>
2675
2676  <dt><b><tt>sext (CST to TYPE)</tt></b></dt>
2677  <dd>Sign extend a constant to another type. The bit size of CST must be
2678      smaller than the bit size of TYPE.  Both types must be integers.</dd>
2679
2680  <dt><b><tt>fptrunc (CST to TYPE)</tt></b></dt>
2681  <dd>Truncate a floating point constant to another floating point type. The
2682      size of CST must be larger than the size of TYPE. Both types must be
2683      floating point.</dd>
2684
2685  <dt><b><tt>fpext (CST to TYPE)</tt></b></dt>
2686  <dd>Floating point extend a constant to another type. The size of CST must be
2687      smaller or equal to the size of TYPE. Both types must be floating
2688      point.</dd>
2689
2690  <dt><b><tt>fptoui (CST to TYPE)</tt></b></dt>
2691  <dd>Convert a floating point constant to the corresponding unsigned integer
2692      constant. TYPE must be a scalar or vector integer type. CST must be of
2693      scalar or vector floating point type. Both CST and TYPE must be scalars,
2694      or vectors of the same number of elements. If the value won't fit in the
2695      integer type, the results are undefined.</dd>
2696
2697  <dt><b><tt>fptosi (CST to TYPE)</tt></b></dt>
2698  <dd>Convert a floating point constant to the corresponding signed integer
2699      constant.  TYPE must be a scalar or vector integer type. CST must be of
2700      scalar or vector floating point type. Both CST and TYPE must be scalars,
2701      or vectors of the same number of elements. If the value won't fit in the
2702      integer type, the results are undefined.</dd>
2703
2704  <dt><b><tt>uitofp (CST to TYPE)</tt></b></dt>
2705  <dd>Convert an unsigned integer constant to the corresponding floating point
2706      constant. TYPE must be a scalar or vector floating point type. CST must be
2707      of scalar or vector integer type. Both CST and TYPE must be scalars, or
2708      vectors of the same number of elements. If the value won't fit in the
2709      floating point type, the results are undefined.</dd>
2710
2711  <dt><b><tt>sitofp (CST to TYPE)</tt></b></dt>
2712  <dd>Convert a signed integer constant to the corresponding floating point
2713      constant. TYPE must be a scalar or vector floating point type. CST must be
2714      of scalar or vector integer type. Both CST and TYPE must be scalars, or
2715      vectors of the same number of elements. If the value won't fit in the
2716      floating point type, the results are undefined.</dd>
2717
2718  <dt><b><tt>ptrtoint (CST to TYPE)</tt></b></dt>
2719  <dd>Convert a pointer typed constant to the corresponding integer constant
2720      <tt>TYPE</tt> must be an integer type. <tt>CST</tt> must be of pointer
2721      type. The <tt>CST</tt> value is zero extended, truncated, or unchanged to
2722      make it fit in <tt>TYPE</tt>.</dd>
2723
2724  <dt><b><tt>inttoptr (CST to TYPE)</tt></b></dt>
2725  <dd>Convert a integer constant to a pointer constant.  TYPE must be a pointer
2726      type.  CST must be of integer type. The CST value is zero extended,
2727      truncated, or unchanged to make it fit in a pointer size. This one is
2728      <i>really</i> dangerous!</dd>
2729
2730  <dt><b><tt>bitcast (CST to TYPE)</tt></b></dt>
2731  <dd>Convert a constant, CST, to another TYPE. The constraints of the operands
2732      are the same as those for the <a href="#i_bitcast">bitcast
2733      instruction</a>.</dd>
2734
2735  <dt><b><tt>getelementptr (CSTPTR, IDX0, IDX1, ...)</tt></b></dt>
2736  <dt><b><tt>getelementptr inbounds (CSTPTR, IDX0, IDX1, ...)</tt></b></dt>
2737  <dd>Perform the <a href="#i_getelementptr">getelementptr operation</a> on
2738      constants.  As with the <a href="#i_getelementptr">getelementptr</a>
2739      instruction, the index list may have zero or more indexes, which are
2740      required to make sense for the type of "CSTPTR".</dd>
2741
2742  <dt><b><tt>select (COND, VAL1, VAL2)</tt></b></dt>
2743  <dd>Perform the <a href="#i_select">select operation</a> on constants.</dd>
2744
2745  <dt><b><tt>icmp COND (VAL1, VAL2)</tt></b></dt>
2746  <dd>Performs the <a href="#i_icmp">icmp operation</a> on constants.</dd>
2747
2748  <dt><b><tt>fcmp COND (VAL1, VAL2)</tt></b></dt>
2749  <dd>Performs the <a href="#i_fcmp">fcmp operation</a> on constants.</dd>
2750
2751  <dt><b><tt>extractelement (VAL, IDX)</tt></b></dt>
2752  <dd>Perform the <a href="#i_extractelement">extractelement operation</a> on
2753      constants.</dd>
2754
2755  <dt><b><tt>insertelement (VAL, ELT, IDX)</tt></b></dt>
2756  <dd>Perform the <a href="#i_insertelement">insertelement operation</a> on
2757    constants.</dd>
2758
2759  <dt><b><tt>shufflevector (VEC1, VEC2, IDXMASK)</tt></b></dt>
2760  <dd>Perform the <a href="#i_shufflevector">shufflevector operation</a> on
2761      constants.</dd>
2762
2763  <dt><b><tt>extractvalue (VAL, IDX0, IDX1, ...)</tt></b></dt>
2764  <dd>Perform the <a href="#i_extractvalue">extractvalue operation</a> on
2765    constants. The index list is interpreted in a similar manner as indices in
2766    a '<a href="#i_getelementptr">getelementptr</a>' operation. At least one
2767    index value must be specified.</dd>
2768
2769  <dt><b><tt>insertvalue (VAL, ELT, IDX0, IDX1, ...)</tt></b></dt>
2770  <dd>Perform the <a href="#i_insertvalue">insertvalue operation</a> on
2771    constants. The index list is interpreted in a similar manner as indices in
2772    a '<a href="#i_getelementptr">getelementptr</a>' operation. At least one
2773    index value must be specified.</dd>
2774
2775  <dt><b><tt>OPCODE (LHS, RHS)</tt></b></dt>
2776  <dd>Perform the specified operation of the LHS and RHS constants. OPCODE may
2777      be any of the <a href="#binaryops">binary</a>
2778      or <a href="#bitwiseops">bitwise binary</a> operations.  The constraints
2779      on operands are the same as those for the corresponding instruction
2780      (e.g. no bitwise operations on floating point values are allowed).</dd>
2781</dl>
2782
2783</div>
2784
2785</div>
2786
2787<!-- *********************************************************************** -->
2788<h2><a name="othervalues">Other Values</a></h2>
2789<!-- *********************************************************************** -->
2790<div>
2791<!-- ======================================================================= -->
2792<h3>
2793<a name="inlineasm">Inline Assembler Expressions</a>
2794</h3>
2795
2796<div>
2797
2798<p>LLVM supports inline assembler expressions (as opposed
2799   to <a href="#moduleasm"> Module-Level Inline Assembly</a>) through the use of
2800   a special value.  This value represents the inline assembler as a string
2801   (containing the instructions to emit), a list of operand constraints (stored
2802   as a string), a flag that indicates whether or not the inline asm
2803   expression has side effects, and a flag indicating whether the function
2804   containing the asm needs to align its stack conservatively.  An example
2805   inline assembler expression is:</p>
2806
2807<pre class="doc_code">
2808i32 (i32) asm "bswap $0", "=r,r"
2809</pre>
2810
2811<p>Inline assembler expressions may <b>only</b> be used as the callee operand of
2812   a <a href="#i_call"><tt>call</tt> instruction</a>.  Thus, typically we
2813   have:</p>
2814
2815<pre class="doc_code">
2816%X = call i32 asm "<a href="#int_bswap">bswap</a> $0", "=r,r"(i32 %Y)
2817</pre>
2818
2819<p>Inline asms with side effects not visible in the constraint list must be
2820   marked as having side effects.  This is done through the use of the
2821   '<tt>sideeffect</tt>' keyword, like so:</p>
2822
2823<pre class="doc_code">
2824call void asm sideeffect "eieio", ""()
2825</pre>
2826
2827<p>In some cases inline asms will contain code that will not work unless the
2828   stack is aligned in some way, such as calls or SSE instructions on x86,
2829   yet will not contain code that does that alignment within the asm.
2830   The compiler should make conservative assumptions about what the asm might
2831   contain and should generate its usual stack alignment code in the prologue
2832   if the '<tt>alignstack</tt>' keyword is present:</p>
2833
2834<pre class="doc_code">
2835call void asm alignstack "eieio", ""()
2836</pre>
2837
2838<p>If both keywords appear the '<tt>sideeffect</tt>' keyword must come
2839   first.</p>
2840
2841<p>TODO: The format of the asm and constraints string still need to be
2842   documented here.  Constraints on what can be done (e.g. duplication, moving,
2843   etc need to be documented).  This is probably best done by reference to
2844   another document that covers inline asm from a holistic perspective.</p>
2845
2846<h4>
2847<a name="inlineasm_md">Inline Asm Metadata</a>
2848</h4>
2849
2850<div>
2851
2852<p>The call instructions that wrap inline asm nodes may have a "!srcloc" MDNode
2853   attached to it that contains a list of constant integers.  If present, the
2854  code generator will use the integer as the location cookie value when report
2855   errors through the LLVMContext error reporting mechanisms.  This allows a
2856   front-end to correlate backend errors that occur with inline asm back to the
2857   source code that produced it.  For example:</p>
2858
2859<pre class="doc_code">
2860call void asm sideeffect "something bad", ""()<b>, !srcloc !42</b>
2861...
2862!42 = !{ i32 1234567 }
2863</pre>
2864
2865<p>It is up to the front-end to make sense of the magic numbers it places in the
2866   IR.  If the MDNode contains multiple constants, the code generator will use
2867   the one that corresponds to the line of the asm that the error occurs on.</p>
2868
2869</div>
2870
2871</div>
2872
2873<!-- ======================================================================= -->
2874<h3>
2875  <a name="metadata">Metadata Nodes and Metadata Strings</a>
2876</h3>
2877
2878<div>
2879
2880<p>LLVM IR allows metadata to be attached to instructions in the program that
2881   can convey extra information about the code to the optimizers and code
2882   generator.  One example application of metadata is source-level debug
2883   information.  There are two metadata primitives: strings and nodes. All
2884   metadata has the <tt>metadata</tt> type and is identified in syntax by a
2885   preceding exclamation point ('<tt>!</tt>').</p>
2886
2887<p>A metadata string is a string surrounded by double quotes.  It can contain
2888   any character by escaping non-printable characters with "\xx" where "xx" is
2889   the two digit hex code.  For example: "<tt>!"test\00"</tt>".</p>
2890
2891<p>Metadata nodes are represented with notation similar to structure constants
2892   (a comma separated list of elements, surrounded by braces and preceded by an
2893   exclamation point).  For example: "<tt>!{ metadata !"test\00", i32
2894   10}</tt>".  Metadata nodes can have any values as their operand.</p>
2895
2896<p>A <a href="#namedmetadatastructure">named metadata</a> is a collection of
2897   metadata nodes, which can be looked up in the module symbol table. For
2898   example: "<tt>!foo =  metadata !{!4, !3}</tt>".
2899
2900<p>Metadata can be used as function arguments. Here <tt>llvm.dbg.value</tt>
2901   function is using two metadata arguments.</p>
2902
2903<div class="doc_code">
2904<pre>
2905call void @llvm.dbg.value(metadata !24, i64 0, metadata !25)
2906</pre>
2907</div>
2908
2909<p>Metadata can be attached with an instruction. Here metadata <tt>!21</tt> is
2910   attached with <tt>add</tt> instruction using <tt>!dbg</tt> identifier.</p>
2911
2912<div class="doc_code">
2913<pre>
2914%indvar.next = add i64 %indvar, 1, !dbg !21
2915</pre>
2916</div>
2917
2918</div>
2919
2920</div>
2921
2922<!-- *********************************************************************** -->
2923<h2>
2924  <a name="intrinsic_globals">Intrinsic Global Variables</a>
2925</h2>
2926<!-- *********************************************************************** -->
2927<div>
2928<p>LLVM has a number of "magic" global variables that contain data that affect
2929code generation or other IR semantics.  These are documented here.  All globals
2930of this sort should have a section specified as "<tt>llvm.metadata</tt>".  This
2931section and all globals that start with "<tt>llvm.</tt>" are reserved for use
2932by LLVM.</p>
2933
2934<!-- ======================================================================= -->
2935<h3>
2936<a name="intg_used">The '<tt>llvm.used</tt>' Global Variable</a>
2937</h3>
2938
2939<div>
2940
2941<p>The <tt>@llvm.used</tt> global is an array with i8* element type which has <a
2942href="#linkage_appending">appending linkage</a>.  This array contains a list of
2943pointers to global variables and functions which may optionally have a pointer
2944cast formed of bitcast or getelementptr.  For example, a legal use of it is:</p>
2945
2946<pre>
2947  @X = global i8 4
2948  @Y = global i32 123
2949
2950  @llvm.used = appending global [2 x i8*] [
2951     i8* @X,
2952     i8* bitcast (i32* @Y to i8*)
2953  ], section "llvm.metadata"
2954</pre>
2955
2956<p>If a global variable appears in the <tt>@llvm.used</tt> list, then the
2957compiler, assembler, and linker are required to treat the symbol as if there is
2958a reference to the global that it cannot see.  For example, if a variable has
2959internal linkage and no references other than that from the <tt>@llvm.used</tt>
2960list, it cannot be deleted.  This is commonly used to represent references from
2961inline asms and other things the compiler cannot "see", and corresponds to
2962"attribute((used))" in GNU C.</p>
2963
2964<p>On some targets, the code generator must emit a directive to the assembler or
2965object file to prevent the assembler and linker from molesting the symbol.</p>
2966
2967</div>
2968
2969<!-- ======================================================================= -->
2970<h3>
2971  <a name="intg_compiler_used">
2972    The '<tt>llvm.compiler.used</tt>' Global Variable
2973  </a>
2974</h3>
2975
2976<div>
2977
2978<p>The <tt>@llvm.compiler.used</tt> directive is the same as the
2979<tt>@llvm.used</tt> directive, except that it only prevents the compiler from
2980touching the symbol.  On targets that support it, this allows an intelligent
2981linker to optimize references to the symbol without being impeded as it would be
2982by <tt>@llvm.used</tt>.</p>
2983
2984<p>This is a rare construct that should only be used in rare circumstances, and
2985should not be exposed to source languages.</p>
2986
2987</div>
2988
2989<!-- ======================================================================= -->
2990<h3>
2991<a name="intg_global_ctors">The '<tt>llvm.global_ctors</tt>' Global Variable</a>
2992</h3>
2993
2994<div>
2995<pre>
2996%0 = type { i32, void ()* }
2997@llvm.global_ctors = appending global [1 x %0] [%0 { i32 65535, void ()* @ctor }]
2998</pre>
2999<p>The <tt>@llvm.global_ctors</tt> array contains a list of constructor functions and associated priorities.  The functions referenced by this array will be called in ascending order of priority (i.e. lowest first) when the module is loaded.  The order of functions with the same priority is not defined.
3000</p>
3001
3002</div>
3003
3004<!-- ======================================================================= -->
3005<h3>
3006<a name="intg_global_dtors">The '<tt>llvm.global_dtors</tt>' Global Variable</a>
3007</h3>
3008
3009<div>
3010<pre>
3011%0 = type { i32, void ()* }
3012@llvm.global_dtors = appending global [1 x %0] [%0 { i32 65535, void ()* @dtor }]
3013</pre>
3014
3015<p>The <tt>@llvm.global_dtors</tt> array contains a list of destructor functions and associated priorities.  The functions referenced by this array will be called in descending order of priority (i.e. highest first) when the module is loaded.  The order of functions with the same priority is not defined.
3016</p>
3017
3018</div>
3019
3020</div>
3021
3022<!-- *********************************************************************** -->
3023<h2><a name="instref">Instruction Reference</a></h2>
3024<!-- *********************************************************************** -->
3025
3026<div>
3027
3028<p>The LLVM instruction set consists of several different classifications of
3029   instructions: <a href="#terminators">terminator
3030   instructions</a>, <a href="#binaryops">binary instructions</a>,
3031   <a href="#bitwiseops">bitwise binary instructions</a>,
3032   <a href="#memoryops">memory instructions</a>, and
3033   <a href="#otherops">other instructions</a>.</p>
3034
3035<!-- ======================================================================= -->
3036<h3>
3037  <a name="terminators">Terminator Instructions</a>
3038</h3>
3039
3040<div>
3041
3042<p>As mentioned <a href="#functionstructure">previously</a>, every basic block
3043   in a program ends with a "Terminator" instruction, which indicates which
3044   block should be executed after the current block is finished. These
3045   terminator instructions typically yield a '<tt>void</tt>' value: they produce
3046   control flow, not values (the one exception being the
3047   '<a href="#i_invoke"><tt>invoke</tt></a>' instruction).</p>
3048
3049<p>The terminator instructions are:
3050   '<a href="#i_ret"><tt>ret</tt></a>',
3051   '<a href="#i_br"><tt>br</tt></a>',
3052   '<a href="#i_switch"><tt>switch</tt></a>',
3053   '<a href="#i_indirectbr"><tt>indirectbr</tt></a>',
3054   '<a href="#i_invoke"><tt>invoke</tt></a>',
3055   '<a href="#i_unwind"><tt>unwind</tt></a>',
3056   '<a href="#i_resume"><tt>resume</tt></a>', and
3057   '<a href="#i_unreachable"><tt>unreachable</tt></a>'.</p>
3058
3059<!-- _______________________________________________________________________ -->
3060<h4>
3061  <a name="i_ret">'<tt>ret</tt>' Instruction</a>
3062</h4>
3063
3064<div>
3065
3066<h5>Syntax:</h5>
3067<pre>
3068  ret &lt;type&gt; &lt;value&gt;       <i>; Return a value from a non-void function</i>
3069  ret void                 <i>; Return from void function</i>
3070</pre>
3071
3072<h5>Overview:</h5>
3073<p>The '<tt>ret</tt>' instruction is used to return control flow (and optionally
3074   a value) from a function back to the caller.</p>
3075
3076<p>There are two forms of the '<tt>ret</tt>' instruction: one that returns a
3077   value and then causes control flow, and one that just causes control flow to
3078   occur.</p>
3079
3080<h5>Arguments:</h5>
3081<p>The '<tt>ret</tt>' instruction optionally accepts a single argument, the
3082   return value. The type of the return value must be a
3083   '<a href="#t_firstclass">first class</a>' type.</p>
3084
3085<p>A function is not <a href="#wellformed">well formed</a> if it it has a
3086   non-void return type and contains a '<tt>ret</tt>' instruction with no return
3087   value or a return value with a type that does not match its type, or if it
3088   has a void return type and contains a '<tt>ret</tt>' instruction with a
3089   return value.</p>
3090
3091<h5>Semantics:</h5>
3092<p>When the '<tt>ret</tt>' instruction is executed, control flow returns back to
3093   the calling function's context.  If the caller is a
3094   "<a href="#i_call"><tt>call</tt></a>" instruction, execution continues at the
3095   instruction after the call.  If the caller was an
3096   "<a href="#i_invoke"><tt>invoke</tt></a>" instruction, execution continues at
3097   the beginning of the "normal" destination block.  If the instruction returns
3098   a value, that value shall set the call or invoke instruction's return
3099   value.</p>
3100
3101<h5>Example:</h5>
3102<pre>
3103  ret i32 5                       <i>; Return an integer value of 5</i>
3104  ret void                        <i>; Return from a void function</i>
3105  ret { i32, i8 } { i32 4, i8 2 } <i>; Return a struct of values 4 and 2</i>
3106</pre>
3107
3108</div>
3109<!-- _______________________________________________________________________ -->
3110<h4>
3111  <a name="i_br">'<tt>br</tt>' Instruction</a>
3112</h4>
3113
3114<div>
3115
3116<h5>Syntax:</h5>
3117<pre>
3118  br i1 &lt;cond&gt;, label &lt;iftrue&gt;, label &lt;iffalse&gt;
3119  br label &lt;dest&gt;          <i>; Unconditional branch</i>
3120</pre>
3121
3122<h5>Overview:</h5>
3123<p>The '<tt>br</tt>' instruction is used to cause control flow to transfer to a
3124   different basic block in the current function.  There are two forms of this
3125   instruction, corresponding to a conditional branch and an unconditional
3126   branch.</p>
3127
3128<h5>Arguments:</h5>
3129<p>The conditional branch form of the '<tt>br</tt>' instruction takes a single
3130   '<tt>i1</tt>' value and two '<tt>label</tt>' values.  The unconditional form
3131   of the '<tt>br</tt>' instruction takes a single '<tt>label</tt>' value as a
3132   target.</p>
3133
3134<h5>Semantics:</h5>
3135<p>Upon execution of a conditional '<tt>br</tt>' instruction, the '<tt>i1</tt>'
3136   argument is evaluated.  If the value is <tt>true</tt>, control flows to the
3137   '<tt>iftrue</tt>' <tt>label</tt> argument.  If "cond" is <tt>false</tt>,
3138   control flows to the '<tt>iffalse</tt>' <tt>label</tt> argument.</p>
3139
3140<h5>Example:</h5>
3141<pre>
3142Test:
3143  %cond = <a href="#i_icmp">icmp</a> eq i32 %a, %b
3144  br i1 %cond, label %IfEqual, label %IfUnequal
3145IfEqual:
3146  <a href="#i_ret">ret</a> i32 1
3147IfUnequal:
3148  <a href="#i_ret">ret</a> i32 0
3149</pre>
3150
3151</div>
3152
3153<!-- _______________________________________________________________________ -->
3154<h4>
3155   <a name="i_switch">'<tt>switch</tt>' Instruction</a>
3156</h4>
3157
3158<div>
3159
3160<h5>Syntax:</h5>
3161<pre>
3162  switch &lt;intty&gt; &lt;value&gt;, label &lt;defaultdest&gt; [ &lt;intty&gt; &lt;val&gt;, label &lt;dest&gt; ... ]
3163</pre>
3164
3165<h5>Overview:</h5>
3166<p>The '<tt>switch</tt>' instruction is used to transfer control flow to one of
3167   several different places.  It is a generalization of the '<tt>br</tt>'
3168   instruction, allowing a branch to occur to one of many possible
3169   destinations.</p>
3170
3171<h5>Arguments:</h5>
3172<p>The '<tt>switch</tt>' instruction uses three parameters: an integer
3173   comparison value '<tt>value</tt>', a default '<tt>label</tt>' destination,
3174   and an array of pairs of comparison value constants and '<tt>label</tt>'s.
3175   The table is not allowed to contain duplicate constant entries.</p>
3176
3177<h5>Semantics:</h5>
3178<p>The <tt>switch</tt> instruction specifies a table of values and
3179   destinations. When the '<tt>switch</tt>' instruction is executed, this table
3180   is searched for the given value.  If the value is found, control flow is
3181   transferred to the corresponding destination; otherwise, control flow is
3182   transferred to the default destination.</p>
3183
3184<h5>Implementation:</h5>
3185<p>Depending on properties of the target machine and the particular
3186   <tt>switch</tt> instruction, this instruction may be code generated in
3187   different ways.  For example, it could be generated as a series of chained
3188   conditional branches or with a lookup table.</p>
3189
3190<h5>Example:</h5>
3191<pre>
3192 <i>; Emulate a conditional br instruction</i>
3193 %Val = <a href="#i_zext">zext</a> i1 %value to i32
3194 switch i32 %Val, label %truedest [ i32 0, label %falsedest ]
3195
3196 <i>; Emulate an unconditional br instruction</i>
3197 switch i32 0, label %dest [ ]
3198
3199 <i>; Implement a jump table:</i>
3200 switch i32 %val, label %otherwise [ i32 0, label %onzero
3201                                     i32 1, label %onone
3202                                     i32 2, label %ontwo ]
3203</pre>
3204
3205</div>
3206
3207
3208<!-- _______________________________________________________________________ -->
3209<h4>
3210   <a name="i_indirectbr">'<tt>indirectbr</tt>' Instruction</a>
3211</h4>
3212
3213<div>
3214
3215<h5>Syntax:</h5>
3216<pre>
3217  indirectbr &lt;somety&gt;* &lt;address&gt;, [ label &lt;dest1&gt;, label &lt;dest2&gt;, ... ]
3218</pre>
3219
3220<h5>Overview:</h5>
3221
3222<p>The '<tt>indirectbr</tt>' instruction implements an indirect branch to a label
3223   within the current function, whose address is specified by
3224   "<tt>address</tt>".  Address must be derived from a <a
3225   href="#blockaddress">blockaddress</a> constant.</p>
3226
3227<h5>Arguments:</h5>
3228
3229<p>The '<tt>address</tt>' argument is the address of the label to jump to.  The
3230   rest of the arguments indicate the full set of possible destinations that the
3231   address may point to.  Blocks are allowed to occur multiple times in the
3232   destination list, though this isn't particularly useful.</p>
3233
3234<p>This destination list is required so that dataflow analysis has an accurate
3235   understanding of the CFG.</p>
3236
3237<h5>Semantics:</h5>
3238
3239<p>Control transfers to the block specified in the address argument.  All
3240   possible destination blocks must be listed in the label list, otherwise this
3241   instruction has undefined behavior.  This implies that jumps to labels
3242   defined in other functions have undefined behavior as well.</p>
3243
3244<h5>Implementation:</h5>
3245
3246<p>This is typically implemented with a jump through a register.</p>
3247
3248<h5>Example:</h5>
3249<pre>
3250 indirectbr i8* %Addr, [ label %bb1, label %bb2, label %bb3 ]
3251</pre>
3252
3253</div>
3254
3255
3256<!-- _______________________________________________________________________ -->
3257<h4>
3258  <a name="i_invoke">'<tt>invoke</tt>' Instruction</a>
3259</h4>
3260
3261<div>
3262
3263<h5>Syntax:</h5>
3264<pre>
3265  &lt;result&gt; = invoke [<a href="#callingconv">cconv</a>] [<a href="#paramattrs">ret attrs</a>] &lt;ptr to function ty&gt; &lt;function ptr val&gt;(&lt;function args&gt;) [<a href="#fnattrs">fn attrs</a>]
3266                to label &lt;normal label&gt; unwind label &lt;exception label&gt;
3267</pre>
3268
3269<h5>Overview:</h5>
3270<p>The '<tt>invoke</tt>' instruction causes control to transfer to a specified
3271   function, with the possibility of control flow transfer to either the
3272   '<tt>normal</tt>' label or the '<tt>exception</tt>' label.  If the callee
3273   function returns with the "<tt><a href="#i_ret">ret</a></tt>" instruction,
3274   control flow will return to the "normal" label.  If the callee (or any
3275   indirect callees) returns with the "<a href="#i_unwind"><tt>unwind</tt></a>"
3276   instruction, control is interrupted and continued at the dynamically nearest
3277   "exception" label.</p>
3278
3279<p>The '<tt>exception</tt>' label is a
3280   <i><a href="ExceptionHandling.html#overview">landing pad</a></i> for the
3281   exception. As such, '<tt>exception</tt>' label is required to have the
3282   "<a href="#i_landingpad"><tt>landingpad</tt></a>" instruction, which contains
3283   the information about about the behavior of the program after unwinding
3284   happens, as its first non-PHI instruction. The restrictions on the
3285   "<tt>landingpad</tt>" instruction's tightly couples it to the
3286   "<tt>invoke</tt>" instruction, so that the important information contained
3287   within the "<tt>landingpad</tt>" instruction can't be lost through normal
3288   code motion.</p>
3289
3290<h5>Arguments:</h5>
3291<p>This instruction requires several arguments:</p>
3292
3293<ol>
3294  <li>The optional "cconv" marker indicates which <a href="#callingconv">calling
3295      convention</a> the call should use.  If none is specified, the call
3296      defaults to using C calling conventions.</li>
3297
3298  <li>The optional <a href="#paramattrs">Parameter Attributes</a> list for
3299      return values. Only '<tt>zeroext</tt>', '<tt>signext</tt>', and
3300      '<tt>inreg</tt>' attributes are valid here.</li>
3301
3302  <li>'<tt>ptr to function ty</tt>': shall be the signature of the pointer to
3303      function value being invoked.  In most cases, this is a direct function
3304      invocation, but indirect <tt>invoke</tt>s are just as possible, branching
3305      off an arbitrary pointer to function value.</li>
3306
3307  <li>'<tt>function ptr val</tt>': An LLVM value containing a pointer to a
3308      function to be invoked. </li>
3309
3310  <li>'<tt>function args</tt>': argument list whose types match the function
3311      signature argument types and parameter attributes. All arguments must be
3312      of <a href="#t_firstclass">first class</a> type. If the function
3313      signature indicates the function accepts a variable number of arguments,
3314      the extra arguments can be specified.</li>
3315
3316  <li>'<tt>normal label</tt>': the label reached when the called function
3317      executes a '<tt><a href="#i_ret">ret</a></tt>' instruction. </li>
3318
3319  <li>'<tt>exception label</tt>': the label reached when a callee returns with
3320      the <a href="#i_unwind"><tt>unwind</tt></a> instruction. </li>
3321
3322  <li>The optional <a href="#fnattrs">function attributes</a> list. Only
3323      '<tt>noreturn</tt>', '<tt>nounwind</tt>', '<tt>readonly</tt>' and
3324      '<tt>readnone</tt>' attributes are valid here.</li>
3325</ol>
3326
3327<h5>Semantics:</h5>
3328<p>This instruction is designed to operate as a standard
3329   '<tt><a href="#i_call">call</a></tt>' instruction in most regards.  The
3330   primary difference is that it establishes an association with a label, which
3331   is used by the runtime library to unwind the stack.</p>
3332
3333<p>This instruction is used in languages with destructors to ensure that proper
3334   cleanup is performed in the case of either a <tt>longjmp</tt> or a thrown
3335   exception.  Additionally, this is important for implementation of
3336   '<tt>catch</tt>' clauses in high-level languages that support them.</p>
3337
3338<p>For the purposes of the SSA form, the definition of the value returned by the
3339   '<tt>invoke</tt>' instruction is deemed to occur on the edge from the current
3340   block to the "normal" label. If the callee unwinds then no return value is
3341   available.</p>
3342
3343<p>Note that the code generator does not yet completely support unwind, and
3344that the invoke/unwind semantics are likely to change in future versions.</p>
3345
3346<h5>Example:</h5>
3347<pre>
3348  %retval = invoke i32 @Test(i32 15) to label %Continue
3349              unwind label %TestCleanup              <i>; {i32}:retval set</i>
3350  %retval = invoke <a href="#callingconv">coldcc</a> i32 %Testfnptr(i32 15) to label %Continue
3351              unwind label %TestCleanup              <i>; {i32}:retval set</i>
3352</pre>
3353
3354</div>
3355
3356<!-- _______________________________________________________________________ -->
3357
3358<h4>
3359  <a name="i_unwind">'<tt>unwind</tt>' Instruction</a>
3360</h4>
3361
3362<div>
3363
3364<h5>Syntax:</h5>
3365<pre>
3366  unwind
3367</pre>
3368
3369<h5>Overview:</h5>
3370<p>The '<tt>unwind</tt>' instruction unwinds the stack, continuing control flow
3371   at the first callee in the dynamic call stack which used
3372   an <a href="#i_invoke"><tt>invoke</tt></a> instruction to perform the call.
3373   This is primarily used to implement exception handling.</p>
3374
3375<h5>Semantics:</h5>
3376<p>The '<tt>unwind</tt>' instruction causes execution of the current function to
3377   immediately halt.  The dynamic call stack is then searched for the
3378   first <a href="#i_invoke"><tt>invoke</tt></a> instruction on the call stack.
3379   Once found, execution continues at the "exceptional" destination block
3380   specified by the <tt>invoke</tt> instruction.  If there is no <tt>invoke</tt>
3381   instruction in the dynamic call chain, undefined behavior results.</p>
3382
3383<p>Note that the code generator does not yet completely support unwind, and
3384that the invoke/unwind semantics are likely to change in future versions.</p>
3385
3386</div>
3387
3388 <!-- _______________________________________________________________________ -->
3389
3390<h4>
3391  <a name="i_resume">'<tt>resume</tt>' Instruction</a>
3392</h4>
3393
3394<div>
3395
3396<h5>Syntax:</h5>
3397<pre>
3398  resume &lt;type&gt; &lt;value&gt;
3399</pre>
3400
3401<h5>Overview:</h5>
3402<p>The '<tt>resume</tt>' instruction is a terminator instruction that has no
3403   successors.</p>
3404
3405<h5>Arguments:</h5>
3406<p>The '<tt>resume</tt>' instruction requires one argument, which must have the
3407   same type as the result of any '<tt>landingpad</tt>' instruction in the same
3408   function.</p>
3409
3410<h5>Semantics:</h5>
3411<p>The '<tt>resume</tt>' instruction resumes propagation of an existing
3412   (in-flight) exception whose unwinding was interrupted with
3413   a <a href="#i_landingpad"><tt>landingpad</tt></a> instruction.</p>
3414
3415<h5>Example:</h5>
3416<pre>
3417  resume { i8*, i32 } %exn
3418</pre>
3419
3420</div>
3421
3422<!-- _______________________________________________________________________ -->
3423
3424<h4>
3425  <a name="i_unreachable">'<tt>unreachable</tt>' Instruction</a>
3426</h4>
3427
3428<div>
3429
3430<h5>Syntax:</h5>
3431<pre>
3432  unreachable
3433</pre>
3434
3435<h5>Overview:</h5>
3436<p>The '<tt>unreachable</tt>' instruction has no defined semantics.  This
3437   instruction is used to inform the optimizer that a particular portion of the
3438   code is not reachable.  This can be used to indicate that the code after a
3439   no-return function cannot be reached, and other facts.</p>
3440
3441<h5>Semantics:</h5>
3442<p>The '<tt>unreachable</tt>' instruction has no defined semantics.</p>
3443
3444</div>
3445
3446</div>
3447
3448<!-- ======================================================================= -->
3449<h3>
3450  <a name="binaryops">Binary Operations</a>
3451</h3>
3452
3453<div>
3454
3455<p>Binary operators are used to do most of the computation in a program.  They
3456   require two operands of the same type, execute an operation on them, and
3457   produce a single value.  The operands might represent multiple data, as is
3458   the case with the <a href="#t_vector">vector</a> data type.  The result value
3459   has the same type as its operands.</p>
3460
3461<p>There are several different binary operators:</p>
3462
3463<!-- _______________________________________________________________________ -->
3464<h4>
3465  <a name="i_add">'<tt>add</tt>' Instruction</a>
3466</h4>
3467
3468<div>
3469
3470<h5>Syntax:</h5>
3471<pre>
3472  &lt;result&gt; = add &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;          <i>; yields {ty}:result</i>
3473  &lt;result&gt; = add nuw &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;      <i>; yields {ty}:result</i>
3474  &lt;result&gt; = add nsw &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;      <i>; yields {ty}:result</i>
3475  &lt;result&gt; = add nuw nsw &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;  <i>; yields {ty}:result</i>
3476</pre>
3477
3478<h5>Overview:</h5>
3479<p>The '<tt>add</tt>' instruction returns the sum of its two operands.</p>
3480
3481<h5>Arguments:</h5>
3482<p>The two arguments to the '<tt>add</tt>' instruction must
3483   be <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of
3484   integer values. Both arguments must have identical types.</p>
3485
3486<h5>Semantics:</h5>
3487<p>The value produced is the integer sum of the two operands.</p>
3488
3489<p>If the sum has unsigned overflow, the result returned is the mathematical
3490   result modulo 2<sup>n</sup>, where n is the bit width of the result.</p>
3491
3492<p>Because LLVM integers use a two's complement representation, this instruction
3493   is appropriate for both signed and unsigned integers.</p>
3494
3495<p><tt>nuw</tt> and <tt>nsw</tt> stand for &quot;No Unsigned Wrap&quot;
3496   and &quot;No Signed Wrap&quot;, respectively. If the <tt>nuw</tt> and/or
3497   <tt>nsw</tt> keywords are present, the result value of the <tt>add</tt>
3498   is a <a href="#trapvalues">trap value</a> if unsigned and/or signed overflow,
3499   respectively, occurs.</p>
3500
3501<h5>Example:</h5>
3502<pre>
3503  &lt;result&gt; = add i32 4, %var          <i>; yields {i32}:result = 4 + %var</i>
3504</pre>
3505
3506</div>
3507
3508<!-- _______________________________________________________________________ -->
3509<h4>
3510  <a name="i_fadd">'<tt>fadd</tt>' Instruction</a>
3511</h4>
3512
3513<div>
3514
3515<h5>Syntax:</h5>
3516<pre>
3517  &lt;result&gt; = fadd &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
3518</pre>
3519
3520<h5>Overview:</h5>
3521<p>The '<tt>fadd</tt>' instruction returns the sum of its two operands.</p>
3522
3523<h5>Arguments:</h5>
3524<p>The two arguments to the '<tt>fadd</tt>' instruction must be
3525   <a href="#t_floating">floating point</a> or <a href="#t_vector">vector</a> of
3526   floating point values. Both arguments must have identical types.</p>
3527
3528<h5>Semantics:</h5>
3529<p>The value produced is the floating point sum of the two operands.</p>
3530
3531<h5>Example:</h5>
3532<pre>
3533  &lt;result&gt; = fadd float 4.0, %var          <i>; yields {float}:result = 4.0 + %var</i>
3534</pre>
3535
3536</div>
3537
3538<!-- _______________________________________________________________________ -->
3539<h4>
3540   <a name="i_sub">'<tt>sub</tt>' Instruction</a>
3541</h4>
3542
3543<div>
3544
3545<h5>Syntax:</h5>
3546<pre>
3547  &lt;result&gt; = sub &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;          <i>; yields {ty}:result</i>
3548  &lt;result&gt; = sub nuw &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;      <i>; yields {ty}:result</i>
3549  &lt;result&gt; = sub nsw &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;      <i>; yields {ty}:result</i>
3550  &lt;result&gt; = sub nuw nsw &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;  <i>; yields {ty}:result</i>
3551</pre>
3552
3553<h5>Overview:</h5>
3554<p>The '<tt>sub</tt>' instruction returns the difference of its two
3555   operands.</p>
3556
3557<p>Note that the '<tt>sub</tt>' instruction is used to represent the
3558   '<tt>neg</tt>' instruction present in most other intermediate
3559   representations.</p>
3560
3561<h5>Arguments:</h5>
3562<p>The two arguments to the '<tt>sub</tt>' instruction must
3563   be <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of
3564   integer values.  Both arguments must have identical types.</p>
3565
3566<h5>Semantics:</h5>
3567<p>The value produced is the integer difference of the two operands.</p>
3568
3569<p>If the difference has unsigned overflow, the result returned is the
3570   mathematical result modulo 2<sup>n</sup>, where n is the bit width of the
3571   result.</p>
3572
3573<p>Because LLVM integers use a two's complement representation, this instruction
3574   is appropriate for both signed and unsigned integers.</p>
3575
3576<p><tt>nuw</tt> and <tt>nsw</tt> stand for &quot;No Unsigned Wrap&quot;
3577   and &quot;No Signed Wrap&quot;, respectively. If the <tt>nuw</tt> and/or
3578   <tt>nsw</tt> keywords are present, the result value of the <tt>sub</tt>
3579   is a <a href="#trapvalues">trap value</a> if unsigned and/or signed overflow,
3580   respectively, occurs.</p>
3581
3582<h5>Example:</h5>
3583<pre>
3584  &lt;result&gt; = sub i32 4, %var          <i>; yields {i32}:result = 4 - %var</i>
3585  &lt;result&gt; = sub i32 0, %val          <i>; yields {i32}:result = -%var</i>
3586</pre>
3587
3588</div>
3589
3590<!-- _______________________________________________________________________ -->
3591<h4>
3592   <a name="i_fsub">'<tt>fsub</tt>' Instruction</a>
3593</h4>
3594
3595<div>
3596
3597<h5>Syntax:</h5>
3598<pre>
3599  &lt;result&gt; = fsub &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
3600</pre>
3601
3602<h5>Overview:</h5>
3603<p>The '<tt>fsub</tt>' instruction returns the difference of its two
3604   operands.</p>
3605
3606<p>Note that the '<tt>fsub</tt>' instruction is used to represent the
3607   '<tt>fneg</tt>' instruction present in most other intermediate
3608   representations.</p>
3609
3610<h5>Arguments:</h5>
3611<p>The two arguments to the '<tt>fsub</tt>' instruction must be
3612   <a href="#t_floating">floating point</a> or <a href="#t_vector">vector</a> of
3613   floating point values.  Both arguments must have identical types.</p>
3614
3615<h5>Semantics:</h5>
3616<p>The value produced is the floating point difference of the two operands.</p>
3617
3618<h5>Example:</h5>
3619<pre>
3620  &lt;result&gt; = fsub float 4.0, %var           <i>; yields {float}:result = 4.0 - %var</i>
3621  &lt;result&gt; = fsub float -0.0, %val          <i>; yields {float}:result = -%var</i>
3622</pre>
3623
3624</div>
3625
3626<!-- _______________________________________________________________________ -->
3627<h4>
3628  <a name="i_mul">'<tt>mul</tt>' Instruction</a>
3629</h4>
3630
3631<div>
3632
3633<h5>Syntax:</h5>
3634<pre>
3635  &lt;result&gt; = mul &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;          <i>; yields {ty}:result</i>
3636  &lt;result&gt; = mul nuw &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;      <i>; yields {ty}:result</i>
3637  &lt;result&gt; = mul nsw &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;      <i>; yields {ty}:result</i>
3638  &lt;result&gt; = mul nuw nsw &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;  <i>; yields {ty}:result</i>
3639</pre>
3640
3641<h5>Overview:</h5>
3642<p>The '<tt>mul</tt>' instruction returns the product of its two operands.</p>
3643
3644<h5>Arguments:</h5>
3645<p>The two arguments to the '<tt>mul</tt>' instruction must
3646   be <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of
3647   integer values.  Both arguments must have identical types.</p>
3648
3649<h5>Semantics:</h5>
3650<p>The value produced is the integer product of the two operands.</p>
3651
3652<p>If the result of the multiplication has unsigned overflow, the result
3653   returned is the mathematical result modulo 2<sup>n</sup>, where n is the bit
3654   width of the result.</p>
3655
3656<p>Because LLVM integers use a two's complement representation, and the result
3657   is the same width as the operands, this instruction returns the correct
3658   result for both signed and unsigned integers.  If a full product
3659   (e.g. <tt>i32</tt>x<tt>i32</tt>-><tt>i64</tt>) is needed, the operands should
3660   be sign-extended or zero-extended as appropriate to the width of the full
3661   product.</p>
3662
3663<p><tt>nuw</tt> and <tt>nsw</tt> stand for &quot;No Unsigned Wrap&quot;
3664   and &quot;No Signed Wrap&quot;, respectively. If the <tt>nuw</tt> and/or
3665   <tt>nsw</tt> keywords are present, the result value of the <tt>mul</tt>
3666   is a <a href="#trapvalues">trap value</a> if unsigned and/or signed overflow,
3667   respectively, occurs.</p>
3668
3669<h5>Example:</h5>
3670<pre>
3671  &lt;result&gt; = mul i32 4, %var          <i>; yields {i32}:result = 4 * %var</i>
3672</pre>
3673
3674</div>
3675
3676<!-- _______________________________________________________________________ -->
3677<h4>
3678  <a name="i_fmul">'<tt>fmul</tt>' Instruction</a>
3679</h4>
3680
3681<div>
3682
3683<h5>Syntax:</h5>
3684<pre>
3685  &lt;result&gt; = fmul &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
3686</pre>
3687
3688<h5>Overview:</h5>
3689<p>The '<tt>fmul</tt>' instruction returns the product of its two operands.</p>
3690
3691<h5>Arguments:</h5>
3692<p>The two arguments to the '<tt>fmul</tt>' instruction must be
3693   <a href="#t_floating">floating point</a> or <a href="#t_vector">vector</a> of
3694   floating point values.  Both arguments must have identical types.</p>
3695
3696<h5>Semantics:</h5>
3697<p>The value produced is the floating point product of the two operands.</p>
3698
3699<h5>Example:</h5>
3700<pre>
3701  &lt;result&gt; = fmul float 4.0, %var          <i>; yields {float}:result = 4.0 * %var</i>
3702</pre>
3703
3704</div>
3705
3706<!-- _______________________________________________________________________ -->
3707<h4>
3708  <a name="i_udiv">'<tt>udiv</tt>' Instruction</a>
3709</h4>
3710
3711<div>
3712
3713<h5>Syntax:</h5>
3714<pre>
3715  &lt;result&gt; = udiv &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;         <i>; yields {ty}:result</i>
3716  &lt;result&gt; = udiv exact &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
3717</pre>
3718
3719<h5>Overview:</h5>
3720<p>The '<tt>udiv</tt>' instruction returns the quotient of its two operands.</p>
3721
3722<h5>Arguments:</h5>
3723<p>The two arguments to the '<tt>udiv</tt>' instruction must be
3724   <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of integer
3725   values.  Both arguments must have identical types.</p>
3726
3727<h5>Semantics:</h5>
3728<p>The value produced is the unsigned integer quotient of the two operands.</p>
3729
3730<p>Note that unsigned integer division and signed integer division are distinct
3731   operations; for signed integer division, use '<tt>sdiv</tt>'.</p>
3732
3733<p>Division by zero leads to undefined behavior.</p>
3734
3735<p>If the <tt>exact</tt> keyword is present, the result value of the
3736   <tt>udiv</tt> is a <a href="#trapvalues">trap value</a> if %op1 is not a
3737  multiple of %op2 (as such, "((a udiv exact b) mul b) == a").</p>
3738
3739
3740<h5>Example:</h5>
3741<pre>
3742  &lt;result&gt; = udiv i32 4, %var          <i>; yields {i32}:result = 4 / %var</i>
3743</pre>
3744
3745</div>
3746
3747<!-- _______________________________________________________________________ -->
3748<h4>
3749  <a name="i_sdiv">'<tt>sdiv</tt>' Instruction</a>
3750</h4>
3751
3752<div>
3753
3754<h5>Syntax:</h5>
3755<pre>
3756  &lt;result&gt; = sdiv &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;         <i>; yields {ty}:result</i>
3757  &lt;result&gt; = sdiv exact &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
3758</pre>
3759
3760<h5>Overview:</h5>
3761<p>The '<tt>sdiv</tt>' instruction returns the quotient of its two operands.</p>
3762
3763<h5>Arguments:</h5>
3764<p>The two arguments to the '<tt>sdiv</tt>' instruction must be
3765   <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of integer
3766   values.  Both arguments must have identical types.</p>
3767
3768<h5>Semantics:</h5>
3769<p>The value produced is the signed integer quotient of the two operands rounded
3770   towards zero.</p>
3771
3772<p>Note that signed integer division and unsigned integer division are distinct
3773   operations; for unsigned integer division, use '<tt>udiv</tt>'.</p>
3774
3775<p>Division by zero leads to undefined behavior. Overflow also leads to
3776   undefined behavior; this is a rare case, but can occur, for example, by doing
3777   a 32-bit division of -2147483648 by -1.</p>
3778
3779<p>If the <tt>exact</tt> keyword is present, the result value of the
3780   <tt>sdiv</tt> is a <a href="#trapvalues">trap value</a> if the result would
3781   be rounded.</p>
3782
3783<h5>Example:</h5>
3784<pre>
3785  &lt;result&gt; = sdiv i32 4, %var          <i>; yields {i32}:result = 4 / %var</i>
3786</pre>
3787
3788</div>
3789
3790<!-- _______________________________________________________________________ -->
3791<h4>
3792  <a name="i_fdiv">'<tt>fdiv</tt>' Instruction</a>
3793</h4>
3794
3795<div>
3796
3797<h5>Syntax:</h5>
3798<pre>
3799  &lt;result&gt; = fdiv &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
3800</pre>
3801
3802<h5>Overview:</h5>
3803<p>The '<tt>fdiv</tt>' instruction returns the quotient of its two operands.</p>
3804
3805<h5>Arguments:</h5>
3806<p>The two arguments to the '<tt>fdiv</tt>' instruction must be
3807   <a href="#t_floating">floating point</a> or <a href="#t_vector">vector</a> of
3808   floating point values.  Both arguments must have identical types.</p>
3809
3810<h5>Semantics:</h5>
3811<p>The value produced is the floating point quotient of the two operands.</p>
3812
3813<h5>Example:</h5>
3814<pre>
3815  &lt;result&gt; = fdiv float 4.0, %var          <i>; yields {float}:result = 4.0 / %var</i>
3816</pre>
3817
3818</div>
3819
3820<!-- _______________________________________________________________________ -->
3821<h4>
3822  <a name="i_urem">'<tt>urem</tt>' Instruction</a>
3823</h4>
3824
3825<div>
3826
3827<h5>Syntax:</h5>
3828<pre>
3829  &lt;result&gt; = urem &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
3830</pre>
3831
3832<h5>Overview:</h5>
3833<p>The '<tt>urem</tt>' instruction returns the remainder from the unsigned
3834   division of its two arguments.</p>
3835
3836<h5>Arguments:</h5>
3837<p>The two arguments to the '<tt>urem</tt>' instruction must be
3838   <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of integer
3839   values.  Both arguments must have identical types.</p>
3840
3841<h5>Semantics:</h5>
3842<p>This instruction returns the unsigned integer <i>remainder</i> of a division.
3843   This instruction always performs an unsigned division to get the
3844   remainder.</p>
3845
3846<p>Note that unsigned integer remainder and signed integer remainder are
3847   distinct operations; for signed integer remainder, use '<tt>srem</tt>'.</p>
3848
3849<p>Taking the remainder of a division by zero leads to undefined behavior.</p>
3850
3851<h5>Example:</h5>
3852<pre>
3853  &lt;result&gt; = urem i32 4, %var          <i>; yields {i32}:result = 4 % %var</i>
3854</pre>
3855
3856</div>
3857
3858<!-- _______________________________________________________________________ -->
3859<h4>
3860  <a name="i_srem">'<tt>srem</tt>' Instruction</a>
3861</h4>
3862
3863<div>
3864
3865<h5>Syntax:</h5>
3866<pre>
3867  &lt;result&gt; = srem &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
3868</pre>
3869
3870<h5>Overview:</h5>
3871<p>The '<tt>srem</tt>' instruction returns the remainder from the signed
3872   division of its two operands. This instruction can also take
3873   <a href="#t_vector">vector</a> versions of the values in which case the
3874   elements must be integers.</p>
3875
3876<h5>Arguments:</h5>
3877<p>The two arguments to the '<tt>srem</tt>' instruction must be
3878   <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of integer
3879   values.  Both arguments must have identical types.</p>
3880
3881<h5>Semantics:</h5>
3882<p>This instruction returns the <i>remainder</i> of a division (where the result
3883   is either zero or has the same sign as the dividend, <tt>op1</tt>), not the
3884   <i>modulo</i> operator (where the result is either zero or has the same sign
3885   as the divisor, <tt>op2</tt>) of a value.
3886   For more information about the difference,
3887   see <a href="http://mathforum.org/dr.math/problems/anne.4.28.99.html">The
3888   Math Forum</a>. For a table of how this is implemented in various languages,
3889   please see <a href="http://en.wikipedia.org/wiki/Modulo_operation">
3890   Wikipedia: modulo operation</a>.</p>
3891
3892<p>Note that signed integer remainder and unsigned integer remainder are
3893   distinct operations; for unsigned integer remainder, use '<tt>urem</tt>'.</p>
3894
3895<p>Taking the remainder of a division by zero leads to undefined behavior.
3896   Overflow also leads to undefined behavior; this is a rare case, but can
3897   occur, for example, by taking the remainder of a 32-bit division of
3898   -2147483648 by -1.  (The remainder doesn't actually overflow, but this rule
3899   lets srem be implemented using instructions that return both the result of
3900   the division and the remainder.)</p>
3901
3902<h5>Example:</h5>
3903<pre>
3904  &lt;result&gt; = srem i32 4, %var          <i>; yields {i32}:result = 4 % %var</i>
3905</pre>
3906
3907</div>
3908
3909<!-- _______________________________________________________________________ -->
3910<h4>
3911  <a name="i_frem">'<tt>frem</tt>' Instruction</a>
3912</h4>
3913
3914<div>
3915
3916<h5>Syntax:</h5>
3917<pre>
3918  &lt;result&gt; = frem &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
3919</pre>
3920
3921<h5>Overview:</h5>
3922<p>The '<tt>frem</tt>' instruction returns the remainder from the division of
3923   its two operands.</p>
3924
3925<h5>Arguments:</h5>
3926<p>The two arguments to the '<tt>frem</tt>' instruction must be
3927   <a href="#t_floating">floating point</a> or <a href="#t_vector">vector</a> of
3928   floating point values.  Both arguments must have identical types.</p>
3929
3930<h5>Semantics:</h5>
3931<p>This instruction returns the <i>remainder</i> of a division.  The remainder
3932   has the same sign as the dividend.</p>
3933
3934<h5>Example:</h5>
3935<pre>
3936  &lt;result&gt; = frem float 4.0, %var          <i>; yields {float}:result = 4.0 % %var</i>
3937</pre>
3938
3939</div>
3940
3941</div>
3942
3943<!-- ======================================================================= -->
3944<h3>
3945  <a name="bitwiseops">Bitwise Binary Operations</a>
3946</h3>
3947
3948<div>
3949
3950<p>Bitwise binary operators are used to do various forms of bit-twiddling in a
3951   program.  They are generally very efficient instructions and can commonly be
3952   strength reduced from other instructions.  They require two operands of the
3953   same type, execute an operation on them, and produce a single value.  The
3954   resulting value is the same type as its operands.</p>
3955
3956<!-- _______________________________________________________________________ -->
3957<h4>
3958  <a name="i_shl">'<tt>shl</tt>' Instruction</a>
3959</h4>
3960
3961<div>
3962
3963<h5>Syntax:</h5>
3964<pre>
3965  &lt;result&gt; = shl &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;           <i>; yields {ty}:result</i>
3966  &lt;result&gt; = shl nuw &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;       <i>; yields {ty}:result</i>
3967  &lt;result&gt; = shl nsw &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;       <i>; yields {ty}:result</i>
3968  &lt;result&gt; = shl nuw nsw &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
3969</pre>
3970
3971<h5>Overview:</h5>
3972<p>The '<tt>shl</tt>' instruction returns the first operand shifted to the left
3973   a specified number of bits.</p>
3974
3975<h5>Arguments:</h5>
3976<p>Both arguments to the '<tt>shl</tt>' instruction must be the
3977    same <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of
3978    integer type.  '<tt>op2</tt>' is treated as an unsigned value.</p>
3979
3980<h5>Semantics:</h5>
3981<p>The value produced is <tt>op1</tt> * 2<sup><tt>op2</tt></sup> mod
3982   2<sup>n</sup>, where <tt>n</tt> is the width of the result.  If <tt>op2</tt>
3983   is (statically or dynamically) negative or equal to or larger than the number
3984   of bits in <tt>op1</tt>, the result is undefined.  If the arguments are
3985   vectors, each vector element of <tt>op1</tt> is shifted by the corresponding
3986   shift amount in <tt>op2</tt>.</p>
3987
3988<p>If the <tt>nuw</tt> keyword is present, then the shift produces a
3989   <a href="#trapvalues">trap value</a> if it shifts out any non-zero bits.  If
3990   the <tt>nsw</tt> keyword is present, then the shift produces a
3991   <a href="#trapvalues">trap value</a> if it shifts out any bits that disagree
3992   with the resultant sign bit.  As such, NUW/NSW have the same semantics as
3993   they would if the shift were expressed as a mul instruction with the same
3994   nsw/nuw bits in (mul %op1, (shl 1, %op2)).</p>
3995
3996<h5>Example:</h5>
3997<pre>
3998  &lt;result&gt; = shl i32 4, %var   <i>; yields {i32}: 4 &lt;&lt; %var</i>
3999  &lt;result&gt; = shl i32 4, 2      <i>; yields {i32}: 16</i>
4000  &lt;result&gt; = shl i32 1, 10     <i>; yields {i32}: 1024</i>
4001  &lt;result&gt; = shl i32 1, 32     <i>; undefined</i>
4002  &lt;result&gt; = shl &lt;2 x i32&gt; &lt; i32 1, i32 1&gt;, &lt; i32 1, i32 2&gt;   <i>; yields: result=&lt;2 x i32&gt; &lt; i32 2, i32 4&gt;</i>
4003</pre>
4004
4005</div>
4006
4007<!-- _______________________________________________________________________ -->
4008<h4>
4009  <a name="i_lshr">'<tt>lshr</tt>' Instruction</a>
4010</h4>
4011
4012<div>
4013
4014<h5>Syntax:</h5>
4015<pre>
4016  &lt;result&gt; = lshr &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;         <i>; yields {ty}:result</i>
4017  &lt;result&gt; = lshr exact &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
4018</pre>
4019
4020<h5>Overview:</h5>
4021<p>The '<tt>lshr</tt>' instruction (logical shift right) returns the first
4022   operand shifted to the right a specified number of bits with zero fill.</p>
4023
4024<h5>Arguments:</h5>
4025<p>Both arguments to the '<tt>lshr</tt>' instruction must be the same
4026   <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of integer
4027   type. '<tt>op2</tt>' is treated as an unsigned value.</p>
4028
4029<h5>Semantics:</h5>
4030<p>This instruction always performs a logical shift right operation. The most
4031   significant bits of the result will be filled with zero bits after the shift.
4032   If <tt>op2</tt> is (statically or dynamically) equal to or larger than the
4033   number of bits in <tt>op1</tt>, the result is undefined. If the arguments are
4034   vectors, each vector element of <tt>op1</tt> is shifted by the corresponding
4035   shift amount in <tt>op2</tt>.</p>
4036
4037<p>If the <tt>exact</tt> keyword is present, the result value of the
4038   <tt>lshr</tt> is a <a href="#trapvalues">trap value</a> if any of the bits
4039   shifted out are non-zero.</p>
4040
4041
4042<h5>Example:</h5>
4043<pre>
4044  &lt;result&gt; = lshr i32 4, 1   <i>; yields {i32}:result = 2</i>
4045  &lt;result&gt; = lshr i32 4, 2   <i>; yields {i32}:result = 1</i>
4046  &lt;result&gt; = lshr i8  4, 3   <i>; yields {i8}:result = 0</i>
4047  &lt;result&gt; = lshr i8 -2, 1   <i>; yields {i8}:result = 0x7FFFFFFF </i>
4048  &lt;result&gt; = lshr i32 1, 32  <i>; undefined</i>
4049  &lt;result&gt; = lshr &lt;2 x i32&gt; &lt; i32 -2, i32 4&gt;, &lt; i32 1, i32 2&gt;   <i>; yields: result=&lt;2 x i32&gt; &lt; i32 0x7FFFFFFF, i32 1&gt;</i>
4050</pre>
4051
4052</div>
4053
4054<!-- _______________________________________________________________________ -->
4055<h4>
4056  <a name="i_ashr">'<tt>ashr</tt>' Instruction</a>
4057</h4>
4058
4059<div>
4060
4061<h5>Syntax:</h5>
4062<pre>
4063  &lt;result&gt; = ashr &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;         <i>; yields {ty}:result</i>
4064  &lt;result&gt; = ashr exact &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
4065</pre>
4066
4067<h5>Overview:</h5>
4068<p>The '<tt>ashr</tt>' instruction (arithmetic shift right) returns the first
4069   operand shifted to the right a specified number of bits with sign
4070   extension.</p>
4071
4072<h5>Arguments:</h5>
4073<p>Both arguments to the '<tt>ashr</tt>' instruction must be the same
4074   <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of integer
4075   type.  '<tt>op2</tt>' is treated as an unsigned value.</p>
4076
4077<h5>Semantics:</h5>
4078<p>This instruction always performs an arithmetic shift right operation, The
4079   most significant bits of the result will be filled with the sign bit
4080   of <tt>op1</tt>.  If <tt>op2</tt> is (statically or dynamically) equal to or
4081   larger than the number of bits in <tt>op1</tt>, the result is undefined. If
4082   the arguments are vectors, each vector element of <tt>op1</tt> is shifted by
4083   the corresponding shift amount in <tt>op2</tt>.</p>
4084
4085<p>If the <tt>exact</tt> keyword is present, the result value of the
4086   <tt>ashr</tt> is a <a href="#trapvalues">trap value</a> if any of the bits
4087   shifted out are non-zero.</p>
4088
4089<h5>Example:</h5>
4090<pre>
4091  &lt;result&gt; = ashr i32 4, 1   <i>; yields {i32}:result = 2</i>
4092  &lt;result&gt; = ashr i32 4, 2   <i>; yields {i32}:result = 1</i>
4093  &lt;result&gt; = ashr i8  4, 3   <i>; yields {i8}:result = 0</i>
4094  &lt;result&gt; = ashr i8 -2, 1   <i>; yields {i8}:result = -1</i>
4095  &lt;result&gt; = ashr i32 1, 32  <i>; undefined</i>
4096  &lt;result&gt; = ashr &lt;2 x i32&gt; &lt; i32 -2, i32 4&gt;, &lt; i32 1, i32 3&gt;   <i>; yields: result=&lt;2 x i32&gt; &lt; i32 -1, i32 0&gt;</i>
4097</pre>
4098
4099</div>
4100
4101<!-- _______________________________________________________________________ -->
4102<h4>
4103  <a name="i_and">'<tt>and</tt>' Instruction</a>
4104</h4>
4105
4106<div>
4107
4108<h5>Syntax:</h5>
4109<pre>
4110  &lt;result&gt; = and &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
4111</pre>
4112
4113<h5>Overview:</h5>
4114<p>The '<tt>and</tt>' instruction returns the bitwise logical and of its two
4115   operands.</p>
4116
4117<h5>Arguments:</h5>
4118<p>The two arguments to the '<tt>and</tt>' instruction must be
4119   <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of integer
4120   values.  Both arguments must have identical types.</p>
4121
4122<h5>Semantics:</h5>
4123<p>The truth table used for the '<tt>and</tt>' instruction is:</p>
4124
4125<table border="1" cellspacing="0" cellpadding="4">
4126  <tbody>
4127    <tr>
4128      <td>In0</td>
4129      <td>In1</td>
4130      <td>Out</td>
4131    </tr>
4132    <tr>
4133      <td>0</td>
4134      <td>0</td>
4135      <td>0</td>
4136    </tr>
4137    <tr>
4138      <td>0</td>
4139      <td>1</td>
4140      <td>0</td>
4141    </tr>
4142    <tr>
4143      <td>1</td>
4144      <td>0</td>
4145      <td>0</td>
4146    </tr>
4147    <tr>
4148      <td>1</td>
4149      <td>1</td>
4150      <td>1</td>
4151    </tr>
4152  </tbody>
4153</table>
4154
4155<h5>Example:</h5>
4156<pre>
4157  &lt;result&gt; = and i32 4, %var         <i>; yields {i32}:result = 4 &amp; %var</i>
4158  &lt;result&gt; = and i32 15, 40          <i>; yields {i32}:result = 8</i>
4159  &lt;result&gt; = and i32 4, 8            <i>; yields {i32}:result = 0</i>
4160</pre>
4161</div>
4162<!-- _______________________________________________________________________ -->
4163<h4>
4164  <a name="i_or">'<tt>or</tt>' Instruction</a>
4165</h4>
4166
4167<div>
4168
4169<h5>Syntax:</h5>
4170<pre>
4171  &lt;result&gt; = or &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
4172</pre>
4173
4174<h5>Overview:</h5>
4175<p>The '<tt>or</tt>' instruction returns the bitwise logical inclusive or of its
4176   two operands.</p>
4177
4178<h5>Arguments:</h5>
4179<p>The two arguments to the '<tt>or</tt>' instruction must be
4180   <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of integer
4181   values.  Both arguments must have identical types.</p>
4182
4183<h5>Semantics:</h5>
4184<p>The truth table used for the '<tt>or</tt>' instruction is:</p>
4185
4186<table border="1" cellspacing="0" cellpadding="4">
4187  <tbody>
4188    <tr>
4189      <td>In0</td>
4190      <td>In1</td>
4191      <td>Out</td>
4192    </tr>
4193    <tr>
4194      <td>0</td>
4195      <td>0</td>
4196      <td>0</td>
4197    </tr>
4198    <tr>
4199      <td>0</td>
4200      <td>1</td>
4201      <td>1</td>
4202    </tr>
4203    <tr>
4204      <td>1</td>
4205      <td>0</td>
4206      <td>1</td>
4207    </tr>
4208    <tr>
4209      <td>1</td>
4210      <td>1</td>
4211      <td>1</td>
4212    </tr>
4213  </tbody>
4214</table>
4215
4216<h5>Example:</h5>
4217<pre>
4218  &lt;result&gt; = or i32 4, %var         <i>; yields {i32}:result = 4 | %var</i>
4219  &lt;result&gt; = or i32 15, 40          <i>; yields {i32}:result = 47</i>
4220  &lt;result&gt; = or i32 4, 8            <i>; yields {i32}:result = 12</i>
4221</pre>
4222
4223</div>
4224
4225<!-- _______________________________________________________________________ -->
4226<h4>
4227  <a name="i_xor">'<tt>xor</tt>' Instruction</a>
4228</h4>
4229
4230<div>
4231
4232<h5>Syntax:</h5>
4233<pre>
4234  &lt;result&gt; = xor &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {ty}:result</i>
4235</pre>
4236
4237<h5>Overview:</h5>
4238<p>The '<tt>xor</tt>' instruction returns the bitwise logical exclusive or of
4239   its two operands.  The <tt>xor</tt> is used to implement the "one's
4240   complement" operation, which is the "~" operator in C.</p>
4241
4242<h5>Arguments:</h5>
4243<p>The two arguments to the '<tt>xor</tt>' instruction must be
4244   <a href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of integer
4245   values.  Both arguments must have identical types.</p>
4246
4247<h5>Semantics:</h5>
4248<p>The truth table used for the '<tt>xor</tt>' instruction is:</p>
4249
4250<table border="1" cellspacing="0" cellpadding="4">
4251  <tbody>
4252    <tr>
4253      <td>In0</td>
4254      <td>In1</td>
4255      <td>Out</td>
4256    </tr>
4257    <tr>
4258      <td>0</td>
4259      <td>0</td>
4260      <td>0</td>
4261    </tr>
4262    <tr>
4263      <td>0</td>
4264      <td>1</td>
4265      <td>1</td>
4266    </tr>
4267    <tr>
4268      <td>1</td>
4269      <td>0</td>
4270      <td>1</td>
4271    </tr>
4272    <tr>
4273      <td>1</td>
4274      <td>1</td>
4275      <td>0</td>
4276    </tr>
4277  </tbody>
4278</table>
4279
4280<h5>Example:</h5>
4281<pre>
4282  &lt;result&gt; = xor i32 4, %var         <i>; yields {i32}:result = 4 ^ %var</i>
4283  &lt;result&gt; = xor i32 15, 40          <i>; yields {i32}:result = 39</i>
4284  &lt;result&gt; = xor i32 4, 8            <i>; yields {i32}:result = 12</i>
4285  &lt;result&gt; = xor i32 %V, -1          <i>; yields {i32}:result = ~%V</i>
4286</pre>
4287
4288</div>
4289
4290</div>
4291
4292<!-- ======================================================================= -->
4293<h3>
4294  <a name="vectorops">Vector Operations</a>
4295</h3>
4296
4297<div>
4298
4299<p>LLVM supports several instructions to represent vector operations in a
4300   target-independent manner.  These instructions cover the element-access and
4301   vector-specific operations needed to process vectors effectively.  While LLVM
4302   does directly support these vector operations, many sophisticated algorithms
4303   will want to use target-specific intrinsics to take full advantage of a
4304   specific target.</p>
4305
4306<!-- _______________________________________________________________________ -->
4307<h4>
4308   <a name="i_extractelement">'<tt>extractelement</tt>' Instruction</a>
4309</h4>
4310
4311<div>
4312
4313<h5>Syntax:</h5>
4314<pre>
4315  &lt;result&gt; = extractelement &lt;n x &lt;ty&gt;&gt; &lt;val&gt;, i32 &lt;idx&gt;    <i>; yields &lt;ty&gt;</i>
4316</pre>
4317
4318<h5>Overview:</h5>
4319<p>The '<tt>extractelement</tt>' instruction extracts a single scalar element
4320   from a vector at a specified index.</p>
4321
4322
4323<h5>Arguments:</h5>
4324<p>The first operand of an '<tt>extractelement</tt>' instruction is a value
4325   of <a href="#t_vector">vector</a> type.  The second operand is an index
4326   indicating the position from which to extract the element.  The index may be
4327   a variable.</p>
4328
4329<h5>Semantics:</h5>
4330<p>The result is a scalar of the same type as the element type of
4331   <tt>val</tt>.  Its value is the value at position <tt>idx</tt> of
4332   <tt>val</tt>.  If <tt>idx</tt> exceeds the length of <tt>val</tt>, the
4333   results are undefined.</p>
4334
4335<h5>Example:</h5>
4336<pre>
4337  &lt;result&gt; = extractelement &lt;4 x i32&gt; %vec, i32 0    <i>; yields i32</i>
4338</pre>
4339
4340</div>
4341
4342<!-- _______________________________________________________________________ -->
4343<h4>
4344   <a name="i_insertelement">'<tt>insertelement</tt>' Instruction</a>
4345</h4>
4346
4347<div>
4348
4349<h5>Syntax:</h5>
4350<pre>
4351  &lt;result&gt; = insertelement &lt;n x &lt;ty&gt;&gt; &lt;val&gt;, &lt;ty&gt; &lt;elt&gt;, i32 &lt;idx&gt;    <i>; yields &lt;n x &lt;ty&gt;&gt;</i>
4352</pre>
4353
4354<h5>Overview:</h5>
4355<p>The '<tt>insertelement</tt>' instruction inserts a scalar element into a
4356   vector at a specified index.</p>
4357
4358<h5>Arguments:</h5>
4359<p>The first operand of an '<tt>insertelement</tt>' instruction is a value
4360   of <a href="#t_vector">vector</a> type.  The second operand is a scalar value
4361   whose type must equal the element type of the first operand.  The third
4362   operand is an index indicating the position at which to insert the value.
4363   The index may be a variable.</p>
4364
4365<h5>Semantics:</h5>
4366<p>The result is a vector of the same type as <tt>val</tt>.  Its element values
4367   are those of <tt>val</tt> except at position <tt>idx</tt>, where it gets the
4368   value <tt>elt</tt>.  If <tt>idx</tt> exceeds the length of <tt>val</tt>, the
4369   results are undefined.</p>
4370
4371<h5>Example:</h5>
4372<pre>
4373  &lt;result&gt; = insertelement &lt;4 x i32&gt; %vec, i32 1, i32 0    <i>; yields &lt;4 x i32&gt;</i>
4374</pre>
4375
4376</div>
4377
4378<!-- _______________________________________________________________________ -->
4379<h4>
4380   <a name="i_shufflevector">'<tt>shufflevector</tt>' Instruction</a>
4381</h4>
4382
4383<div>
4384
4385<h5>Syntax:</h5>
4386<pre>
4387  &lt;result&gt; = shufflevector &lt;n x &lt;ty&gt;&gt; &lt;v1&gt;, &lt;n x &lt;ty&gt;&gt; &lt;v2&gt;, &lt;m x i32&gt; &lt;mask&gt;    <i>; yields &lt;m x &lt;ty&gt;&gt;</i>
4388</pre>
4389
4390<h5>Overview:</h5>
4391<p>The '<tt>shufflevector</tt>' instruction constructs a permutation of elements
4392   from two input vectors, returning a vector with the same element type as the
4393   input and length that is the same as the shuffle mask.</p>
4394
4395<h5>Arguments:</h5>
4396<p>The first two operands of a '<tt>shufflevector</tt>' instruction are vectors
4397   with types that match each other. The third argument is a shuffle mask whose
4398   element type is always 'i32'.  The result of the instruction is a vector
4399   whose length is the same as the shuffle mask and whose element type is the
4400   same as the element type of the first two operands.</p>
4401
4402<p>The shuffle mask operand is required to be a constant vector with either
4403   constant integer or undef values.</p>
4404
4405<h5>Semantics:</h5>
4406<p>The elements of the two input vectors are numbered from left to right across
4407   both of the vectors.  The shuffle mask operand specifies, for each element of
4408   the result vector, which element of the two input vectors the result element
4409   gets.  The element selector may be undef (meaning "don't care") and the
4410   second operand may be undef if performing a shuffle from only one vector.</p>
4411
4412<h5>Example:</h5>
4413<pre>
4414  &lt;result&gt; = shufflevector &lt;4 x i32&gt; %v1, &lt;4 x i32&gt; %v2,
4415                          &lt;4 x i32&gt; &lt;i32 0, i32 4, i32 1, i32 5&gt;  <i>; yields &lt;4 x i32&gt;</i>
4416  &lt;result&gt; = shufflevector &lt;4 x i32&gt; %v1, &lt;4 x i32&gt; undef,
4417                          &lt;4 x i32&gt; &lt;i32 0, i32 1, i32 2, i32 3&gt;  <i>; yields &lt;4 x i32&gt;</i> - Identity shuffle.
4418  &lt;result&gt; = shufflevector &lt;8 x i32&gt; %v1, &lt;8 x i32&gt; undef,
4419                          &lt;4 x i32&gt; &lt;i32 0, i32 1, i32 2, i32 3&gt;  <i>; yields &lt;4 x i32&gt;</i>
4420  &lt;result&gt; = shufflevector &lt;4 x i32&gt; %v1, &lt;4 x i32&gt; %v2,
4421                          &lt;8 x i32&gt; &lt;i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7 &gt;  <i>; yields &lt;8 x i32&gt;</i>
4422</pre>
4423
4424</div>
4425
4426</div>
4427
4428<!-- ======================================================================= -->
4429<h3>
4430  <a name="aggregateops">Aggregate Operations</a>
4431</h3>
4432
4433<div>
4434
4435<p>LLVM supports several instructions for working with
4436  <a href="#t_aggregate">aggregate</a> values.</p>
4437
4438<!-- _______________________________________________________________________ -->
4439<h4>
4440   <a name="i_extractvalue">'<tt>extractvalue</tt>' Instruction</a>
4441</h4>
4442
4443<div>
4444
4445<h5>Syntax:</h5>
4446<pre>
4447  &lt;result&gt; = extractvalue &lt;aggregate type&gt; &lt;val&gt;, &lt;idx&gt;{, &lt;idx&gt;}*
4448</pre>
4449
4450<h5>Overview:</h5>
4451<p>The '<tt>extractvalue</tt>' instruction extracts the value of a member field
4452   from an <a href="#t_aggregate">aggregate</a> value.</p>
4453
4454<h5>Arguments:</h5>
4455<p>The first operand of an '<tt>extractvalue</tt>' instruction is a value
4456   of <a href="#t_struct">struct</a> or
4457   <a href="#t_array">array</a> type.  The operands are constant indices to
4458   specify which value to extract in a similar manner as indices in a
4459   '<tt><a href="#i_getelementptr">getelementptr</a></tt>' instruction.</p>
4460   <p>The major differences to <tt>getelementptr</tt> indexing are:</p>
4461     <ul>
4462       <li>Since the value being indexed is not a pointer, the first index is
4463           omitted and assumed to be zero.</li>
4464       <li>At least one index must be specified.</li>
4465       <li>Not only struct indices but also array indices must be in
4466           bounds.</li>
4467     </ul>
4468
4469<h5>Semantics:</h5>
4470<p>The result is the value at the position in the aggregate specified by the
4471   index operands.</p>
4472
4473<h5>Example:</h5>
4474<pre>
4475  &lt;result&gt; = extractvalue {i32, float} %agg, 0    <i>; yields i32</i>
4476</pre>
4477
4478</div>
4479
4480<!-- _______________________________________________________________________ -->
4481<h4>
4482   <a name="i_insertvalue">'<tt>insertvalue</tt>' Instruction</a>
4483</h4>
4484
4485<div>
4486
4487<h5>Syntax:</h5>
4488<pre>
4489  &lt;result&gt; = insertvalue &lt;aggregate type&gt; &lt;val&gt;, &lt;ty&gt; &lt;elt&gt;, &lt;idx&gt;{, &lt;idx&gt;}*    <i>; yields &lt;aggregate type&gt;</i>
4490</pre>
4491
4492<h5>Overview:</h5>
4493<p>The '<tt>insertvalue</tt>' instruction inserts a value into a member field
4494   in an <a href="#t_aggregate">aggregate</a> value.</p>
4495
4496<h5>Arguments:</h5>
4497<p>The first operand of an '<tt>insertvalue</tt>' instruction is a value
4498   of <a href="#t_struct">struct</a> or
4499   <a href="#t_array">array</a> type.  The second operand is a first-class
4500   value to insert.  The following operands are constant indices indicating
4501   the position at which to insert the value in a similar manner as indices in a
4502   '<tt><a href="#i_extractvalue">extractvalue</a></tt>' instruction.  The
4503   value to insert must have the same type as the value identified by the
4504   indices.</p>
4505
4506<h5>Semantics:</h5>
4507<p>The result is an aggregate of the same type as <tt>val</tt>.  Its value is
4508   that of <tt>val</tt> except that the value at the position specified by the
4509   indices is that of <tt>elt</tt>.</p>
4510
4511<h5>Example:</h5>
4512<pre>
4513  %agg1 = insertvalue {i32, float} undef, i32 1, 0              <i>; yields {i32 1, float undef}</i>
4514  %agg2 = insertvalue {i32, float} %agg1, float %val, 1         <i>; yields {i32 1, float %val}</i>
4515  %agg3 = insertvalue {i32, {float}} %agg1, float %val, 1, 0    <i>; yields {i32 1, float %val}</i>
4516</pre>
4517
4518</div>
4519
4520</div>
4521
4522<!-- ======================================================================= -->
4523<h3>
4524  <a name="memoryops">Memory Access and Addressing Operations</a>
4525</h3>
4526
4527<div>
4528
4529<p>A key design point of an SSA-based representation is how it represents
4530   memory.  In LLVM, no memory locations are in SSA form, which makes things
4531   very simple.  This section describes how to read, write, and allocate
4532   memory in LLVM.</p>
4533
4534<!-- _______________________________________________________________________ -->
4535<h4>
4536  <a name="i_alloca">'<tt>alloca</tt>' Instruction</a>
4537</h4>
4538
4539<div>
4540
4541<h5>Syntax:</h5>
4542<pre>
4543  &lt;result&gt; = alloca &lt;type&gt;[, &lt;ty&gt; &lt;NumElements&gt;][, align &lt;alignment&gt;]     <i>; yields {type*}:result</i>
4544</pre>
4545
4546<h5>Overview:</h5>
4547<p>The '<tt>alloca</tt>' instruction allocates memory on the stack frame of the
4548   currently executing function, to be automatically released when this function
4549   returns to its caller. The object is always allocated in the generic address
4550   space (address space zero).</p>
4551
4552<h5>Arguments:</h5>
4553<p>The '<tt>alloca</tt>' instruction
4554   allocates <tt>sizeof(&lt;type&gt;)*NumElements</tt> bytes of memory on the
4555   runtime stack, returning a pointer of the appropriate type to the program.
4556   If "NumElements" is specified, it is the number of elements allocated,
4557   otherwise "NumElements" is defaulted to be one.  If a constant alignment is
4558   specified, the value result of the allocation is guaranteed to be aligned to
4559   at least that boundary.  If not specified, or if zero, the target can choose
4560   to align the allocation on any convenient boundary compatible with the
4561   type.</p>
4562
4563<p>'<tt>type</tt>' may be any sized type.</p>
4564
4565<h5>Semantics:</h5>
4566<p>Memory is allocated; a pointer is returned.  The operation is undefined if
4567   there is insufficient stack space for the allocation.  '<tt>alloca</tt>'d
4568   memory is automatically released when the function returns.  The
4569   '<tt>alloca</tt>' instruction is commonly used to represent automatic
4570   variables that must have an address available.  When the function returns
4571   (either with the <tt><a href="#i_ret">ret</a></tt>
4572   or <tt><a href="#i_unwind">unwind</a></tt> instructions), the memory is
4573   reclaimed.  Allocating zero bytes is legal, but the result is undefined.</p>
4574
4575<h5>Example:</h5>
4576<pre>
4577  %ptr = alloca i32                             <i>; yields {i32*}:ptr</i>
4578  %ptr = alloca i32, i32 4                      <i>; yields {i32*}:ptr</i>
4579  %ptr = alloca i32, i32 4, align 1024          <i>; yields {i32*}:ptr</i>
4580  %ptr = alloca i32, align 1024                 <i>; yields {i32*}:ptr</i>
4581</pre>
4582
4583</div>
4584
4585<!-- _______________________________________________________________________ -->
4586<h4>
4587  <a name="i_load">'<tt>load</tt>' Instruction</a>
4588</h4>
4589
4590<div>
4591
4592<h5>Syntax:</h5>
4593<pre>
4594  &lt;result&gt; = load [volatile] &lt;ty&gt;* &lt;pointer&gt;[, align &lt;alignment&gt;][, !nontemporal !&lt;index&gt;]
4595  &lt;result&gt; = load atomic [volatile] &lt;ty&gt;* &lt;pointer&gt; [singlethread] &lt;ordering&gt;, align &lt;alignment&gt;
4596  !&lt;index&gt; = !{ i32 1 }
4597</pre>
4598
4599<h5>Overview:</h5>
4600<p>The '<tt>load</tt>' instruction is used to read from memory.</p>
4601
4602<h5>Arguments:</h5>
4603<p>The argument to the '<tt>load</tt>' instruction specifies the memory address
4604   from which to load.  The pointer must point to
4605   a <a href="#t_firstclass">first class</a> type.  If the <tt>load</tt> is
4606   marked as <tt>volatile</tt>, then the optimizer is not allowed to modify the
4607   number or order of execution of this <tt>load</tt> with other <a
4608   href="#volatile">volatile operations</a>.</p>
4609
4610<p>If the <code>load</code> is marked as <code>atomic</code>, it takes an extra
4611   <a href="#ordering">ordering</a> and optional <code>singlethread</code>
4612   argument.  The <code>release</code> and <code>acq_rel</code> orderings are
4613   not valid on <code>load</code> instructions.  Atomic loads produce <a
4614   href="#memorymodel">defined</a> results when they may see multiple atomic
4615   stores.  The type of the pointee must be an integer type whose bit width
4616   is a power of two greater than or equal to eight and less than or equal
4617   to a target-specific size limit. <code>align</code> must be explicitly
4618   specified on atomic loads, and the load has undefined behavior if the
4619   alignment is not set to a value which is at least the size in bytes of
4620   the pointee. <code>!nontemporal</code> does not have any defined semantics
4621   for atomic loads.</p>
4622
4623<p>The optional constant <tt>align</tt> argument specifies the alignment of the
4624   operation (that is, the alignment of the memory address). A value of 0 or an
4625   omitted <tt>align</tt> argument means that the operation has the preferential
4626   alignment for the target. It is the responsibility of the code emitter to
4627   ensure that the alignment information is correct. Overestimating the
4628   alignment results in undefined behavior. Underestimating the alignment may
4629   produce less efficient code. An alignment of 1 is always safe.</p>
4630
4631<p>The optional <tt>!nontemporal</tt> metadata must reference a single
4632   metatadata name &lt;index&gt; corresponding to a metadata node with
4633   one <tt>i32</tt> entry of value 1.  The existence of
4634   the <tt>!nontemporal</tt> metatadata on the instruction tells the optimizer
4635   and code generator that this load is not expected to be reused in the cache.
4636   The code generator may select special instructions to save cache bandwidth,
4637   such as the <tt>MOVNT</tt> instruction on x86.</p>
4638
4639<h5>Semantics:</h5>
4640<p>The location of memory pointed to is loaded.  If the value being loaded is of
4641   scalar type then the number of bytes read does not exceed the minimum number
4642   of bytes needed to hold all bits of the type.  For example, loading an
4643   <tt>i24</tt> reads at most three bytes.  When loading a value of a type like
4644   <tt>i20</tt> with a size that is not an integral number of bytes, the result
4645   is undefined if the value was not originally written using a store of the
4646   same type.</p>
4647
4648<h5>Examples:</h5>
4649<pre>
4650  %ptr = <a href="#i_alloca">alloca</a> i32                               <i>; yields {i32*}:ptr</i>
4651  <a href="#i_store">store</a> i32 3, i32* %ptr                          <i>; yields {void}</i>
4652  %val = load i32* %ptr                           <i>; yields {i32}:val = i32 3</i>
4653</pre>
4654
4655</div>
4656
4657<!-- _______________________________________________________________________ -->
4658<h4>
4659  <a name="i_store">'<tt>store</tt>' Instruction</a>
4660</h4>
4661
4662<div>
4663
4664<h5>Syntax:</h5>
4665<pre>
4666  store [volatile] &lt;ty&gt; &lt;value&gt;, &lt;ty&gt;* &lt;pointer&gt;[, align &lt;alignment&gt;][, !nontemporal !&lt;index&gt;]                   <i>; yields {void}</i>
4667  store atomic [volatile] &lt;ty&gt; &lt;value&gt;, &lt;ty&gt;* &lt;pointer&gt; [singlethread] &lt;ordering&gt;, align &lt;alignment&gt;             <i>; yields {void}</i>
4668</pre>
4669
4670<h5>Overview:</h5>
4671<p>The '<tt>store</tt>' instruction is used to write to memory.</p>
4672
4673<h5>Arguments:</h5>
4674<p>There are two arguments to the '<tt>store</tt>' instruction: a value to store
4675   and an address at which to store it.  The type of the
4676   '<tt>&lt;pointer&gt;</tt>' operand must be a pointer to
4677   the <a href="#t_firstclass">first class</a> type of the
4678   '<tt>&lt;value&gt;</tt>' operand. If the <tt>store</tt> is marked as
4679   <tt>volatile</tt>, then the optimizer is not allowed to modify the number or
4680   order of execution of this <tt>store</tt> with other <a
4681   href="#volatile">volatile operations</a>.</p>
4682
4683<p>If the <code>store</code> is marked as <code>atomic</code>, it takes an extra
4684   <a href="#ordering">ordering</a> and optional <code>singlethread</code>
4685   argument.  The <code>acquire</code> and <code>acq_rel</code> orderings aren't
4686   valid on <code>store</code> instructions.  Atomic loads produce <a
4687   href="#memorymodel">defined</a> results when they may see multiple atomic
4688   stores. The type of the pointee must be an integer type whose bit width
4689   is a power of two greater than or equal to eight and less than or equal
4690   to a target-specific size limit. <code>align</code> must be explicitly
4691   specified on atomic stores, and the store has undefined behavior if the
4692   alignment is not set to a value which is at least the size in bytes of
4693   the pointee. <code>!nontemporal</code> does not have any defined semantics
4694   for atomic stores.</p>
4695
4696<p>The optional constant "align" argument specifies the alignment of the
4697   operation (that is, the alignment of the memory address). A value of 0 or an
4698   omitted "align" argument means that the operation has the preferential
4699   alignment for the target. It is the responsibility of the code emitter to
4700   ensure that the alignment information is correct. Overestimating the
4701   alignment results in an undefined behavior. Underestimating the alignment may
4702   produce less efficient code. An alignment of 1 is always safe.</p>
4703
4704<p>The optional !nontemporal metadata must reference a single metatadata
4705   name &lt;index&gt; corresponding to a metadata node with one i32 entry of
4706   value 1.  The existence of the !nontemporal metatadata on the
4707   instruction tells the optimizer and code generator that this load is
4708   not expected to be reused in the cache.  The code generator may
4709   select special instructions to save cache bandwidth, such as the
4710   MOVNT instruction on x86.</p>
4711
4712
4713<h5>Semantics:</h5>
4714<p>The contents of memory are updated to contain '<tt>&lt;value&gt;</tt>' at the
4715   location specified by the '<tt>&lt;pointer&gt;</tt>' operand.  If
4716   '<tt>&lt;value&gt;</tt>' is of scalar type then the number of bytes written
4717   does not exceed the minimum number of bytes needed to hold all bits of the
4718   type.  For example, storing an <tt>i24</tt> writes at most three bytes.  When
4719   writing a value of a type like <tt>i20</tt> with a size that is not an
4720   integral number of bytes, it is unspecified what happens to the extra bits
4721   that do not belong to the type, but they will typically be overwritten.</p>
4722
4723<h5>Example:</h5>
4724<pre>
4725  %ptr = <a href="#i_alloca">alloca</a> i32                               <i>; yields {i32*}:ptr</i>
4726  store i32 3, i32* %ptr                          <i>; yields {void}</i>
4727  %val = <a href="#i_load">load</a> i32* %ptr                           <i>; yields {i32}:val = i32 3</i>
4728</pre>
4729
4730</div>
4731
4732<!-- _______________________________________________________________________ -->
4733<h4>
4734<a name="i_fence">'<tt>fence</tt>' Instruction</a>
4735</h4>
4736
4737<div>
4738
4739<h5>Syntax:</h5>
4740<pre>
4741  fence [singlethread] &lt;ordering&gt;                   <i>; yields {void}</i>
4742</pre>
4743
4744<h5>Overview:</h5>
4745<p>The '<tt>fence</tt>' instruction is used to introduce happens-before edges
4746between operations.</p>
4747
4748<h5>Arguments:</h5> <p>'<code>fence</code>' instructions take an <a
4749href="#ordering">ordering</a> argument which defines what
4750<i>synchronizes-with</i> edges they add.  They can only be given
4751<code>acquire</code>, <code>release</code>, <code>acq_rel</code>, and
4752<code>seq_cst</code> orderings.</p>
4753
4754<h5>Semantics:</h5>
4755<p>A fence <var>A</var> which has (at least) <code>release</code> ordering
4756semantics <i>synchronizes with</i> a fence <var>B</var> with (at least)
4757<code>acquire</code> ordering semantics if and only if there exist atomic
4758operations <var>X</var> and <var>Y</var>, both operating on some atomic object
4759<var>M</var>, such that <var>A</var> is sequenced before <var>X</var>,
4760<var>X</var> modifies <var>M</var> (either directly or through some side effect
4761of a sequence headed by <var>X</var>), <var>Y</var> is sequenced before
4762<var>B</var>, and <var>Y</var> observes <var>M</var>. This provides a
4763<i>happens-before</i> dependency between <var>A</var> and <var>B</var>. Rather
4764than an explicit <code>fence</code>, one (but not both) of the atomic operations
4765<var>X</var> or <var>Y</var> might provide a <code>release</code> or
4766<code>acquire</code> (resp.) ordering constraint and still
4767<i>synchronize-with</i> the explicit <code>fence</code> and establish the
4768<i>happens-before</i> edge.</p>
4769
4770<p>A <code>fence</code> which has <code>seq_cst</code> ordering, in addition to
4771having both <code>acquire</code> and <code>release</code> semantics specified
4772above, participates in the global program order of other <code>seq_cst</code>
4773operations and/or fences.</p>
4774
4775<p>The optional "<a href="#singlethread"><code>singlethread</code></a>" argument
4776specifies that the fence only synchronizes with other fences in the same
4777thread.  (This is useful for interacting with signal handlers.)</p>
4778
4779<h5>Example:</h5>
4780<pre>
4781  fence acquire                          <i>; yields {void}</i>
4782  fence singlethread seq_cst             <i>; yields {void}</i>
4783</pre>
4784
4785</div>
4786
4787<!-- _______________________________________________________________________ -->
4788<h4>
4789<a name="i_cmpxchg">'<tt>cmpxchg</tt>' Instruction</a>
4790</h4>
4791
4792<div>
4793
4794<h5>Syntax:</h5>
4795<pre>
4796  cmpxchg [volatile] &lt;ty&gt;* &lt;pointer&gt;, &lt;ty&gt; &lt;cmp&gt;, &lt;ty&gt; &lt;new&gt; [singlethread] &lt;ordering&gt;                   <i>; yields {ty}</i>
4797</pre>
4798
4799<h5>Overview:</h5>
4800<p>The '<tt>cmpxchg</tt>' instruction is used to atomically modify memory.
4801It loads a value in memory and compares it to a given value. If they are
4802equal, it stores a new value into the memory.</p>
4803
4804<h5>Arguments:</h5>
4805<p>There are three arguments to the '<code>cmpxchg</code>' instruction: an
4806address to operate on, a value to compare to the value currently be at that
4807address, and a new value to place at that address if the compared values are
4808equal.  The type of '<var>&lt;cmp&gt;</var>' must be an integer type whose
4809bit width is a power of two greater than or equal to eight and less than
4810or equal to a target-specific size limit. '<var>&lt;cmp&gt;</var>' and
4811'<var>&lt;new&gt;</var>' must have the same type, and the type of
4812'<var>&lt;pointer&gt;</var>' must be a pointer to that type. If the
4813<code>cmpxchg</code> is marked as <code>volatile</code>, then the
4814optimizer is not allowed to modify the number or order of execution
4815of this <code>cmpxchg</code> with other <a href="#volatile">volatile
4816operations</a>.</p>
4817
4818<!-- FIXME: Extend allowed types. -->
4819
4820<p>The <a href="#ordering"><var>ordering</var></a> argument specifies how this
4821<code>cmpxchg</code> synchronizes with other atomic operations.</p>
4822
4823<p>The optional "<code>singlethread</code>" argument declares that the
4824<code>cmpxchg</code> is only atomic with respect to code (usually signal
4825handlers) running in the same thread as the <code>cmpxchg</code>.  Otherwise the
4826cmpxchg is atomic with respect to all other code in the system.</p>
4827
4828<p>The pointer passed into cmpxchg must have alignment greater than or equal to
4829the size in memory of the operand.
4830
4831<h5>Semantics:</h5>
4832<p>The contents of memory at the location specified by the
4833'<tt>&lt;pointer&gt;</tt>' operand is read and compared to
4834'<tt>&lt;cmp&gt;</tt>'; if the read value is the equal,
4835'<tt>&lt;new&gt;</tt>' is written.  The original value at the location
4836is returned.
4837
4838<p>A successful <code>cmpxchg</code> is a read-modify-write instruction for the
4839purpose of identifying <a href="#release_sequence">release sequences</a>.  A
4840failed <code>cmpxchg</code> is equivalent to an atomic load with an ordering
4841parameter determined by dropping any <code>release</code> part of the
4842<code>cmpxchg</code>'s ordering.</p>
4843
4844<!--
4845FIXME: Is compare_exchange_weak() necessary?  (Consider after we've done
4846optimization work on ARM.)
4847
4848FIXME: Is a weaker ordering constraint on failure helpful in practice?
4849-->
4850
4851<h5>Example:</h5>
4852<pre>
4853entry:
4854  %orig = atomic <a href="#i_load">load</a> i32* %ptr unordered                       <i>; yields {i32}</i>
4855  <a href="#i_br">br</a> label %loop
4856
4857loop:
4858  %cmp = <a href="#i_phi">phi</a> i32 [ %orig, %entry ], [%old, %loop]
4859  %squared = <a href="#i_mul">mul</a> i32 %cmp, %cmp
4860  %old = cmpxchg i32* %ptr, i32 %cmp, i32 %squared                       <i>; yields {i32}</i>
4861  %success = <a href="#i_icmp">icmp</a> eq i32 %cmp, %old
4862  <a href="#i_br">br</a> i1 %success, label %done, label %loop
4863
4864done:
4865  ...
4866</pre>
4867
4868</div>
4869
4870<!-- _______________________________________________________________________ -->
4871<h4>
4872<a name="i_atomicrmw">'<tt>atomicrmw</tt>' Instruction</a>
4873</h4>
4874
4875<div>
4876
4877<h5>Syntax:</h5>
4878<pre>
4879  atomicrmw [volatile] &lt;operation&gt; &lt;ty&gt;* &lt;pointer&gt;, &lt;ty&gt; &lt;value&gt; [singlethread] &lt;ordering&gt;                   <i>; yields {ty}</i>
4880</pre>
4881
4882<h5>Overview:</h5>
4883<p>The '<tt>atomicrmw</tt>' instruction is used to atomically modify memory.</p>
4884
4885<h5>Arguments:</h5>
4886<p>There are three arguments to the '<code>atomicrmw</code>' instruction: an
4887operation to apply, an address whose value to modify, an argument to the
4888operation.  The operation must be one of the following keywords:</p>
4889<ul>
4890  <li>xchg</li>
4891  <li>add</li>
4892  <li>sub</li>
4893  <li>and</li>
4894  <li>nand</li>
4895  <li>or</li>
4896  <li>xor</li>
4897  <li>max</li>
4898  <li>min</li>
4899  <li>umax</li>
4900  <li>umin</li>
4901</ul>
4902
4903<p>The type of '<var>&lt;value&gt;</var>' must be an integer type whose
4904bit width is a power of two greater than or equal to eight and less than
4905or equal to a target-specific size limit.  The type of the
4906'<code>&lt;pointer&gt;</code>' operand must be a pointer to that type.
4907If the <code>atomicrmw</code> is marked as <code>volatile</code>, then the
4908optimizer is not allowed to modify the number or order of execution of this
4909<code>atomicrmw</code> with other <a href="#volatile">volatile
4910  operations</a>.</p>
4911
4912<!-- FIXME: Extend allowed types. -->
4913
4914<h5>Semantics:</h5>
4915<p>The contents of memory at the location specified by the
4916'<tt>&lt;pointer&gt;</tt>' operand are atomically read, modified, and written
4917back.  The original value at the location is returned.  The modification is
4918specified by the <var>operation</var> argument:</p>
4919
4920<ul>
4921  <li>xchg: <code>*ptr = val</code></li>
4922  <li>add: <code>*ptr = *ptr + val</code></li>
4923  <li>sub: <code>*ptr = *ptr - val</code></li>
4924  <li>and: <code>*ptr = *ptr &amp; val</code></li>
4925  <li>nand: <code>*ptr = ~(*ptr &amp; val)</code></li>
4926  <li>or: <code>*ptr = *ptr | val</code></li>
4927  <li>xor: <code>*ptr = *ptr ^ val</code></li>
4928  <li>max: <code>*ptr = *ptr &gt; val ? *ptr : val</code> (using a signed comparison)</li>
4929  <li>min: <code>*ptr = *ptr &lt; val ? *ptr : val</code> (using a signed comparison)</li>
4930  <li>umax: <code>*ptr = *ptr &gt; val ? *ptr : val</code> (using an unsigned comparison)</li>
4931  <li>umin: <code>*ptr = *ptr &lt; val ? *ptr : val</code> (using an unsigned comparison)</li>
4932</ul>
4933
4934<h5>Example:</h5>
4935<pre>
4936  %old = atomicrmw add i32* %ptr, i32 1 acquire                        <i>; yields {i32}</i>
4937</pre>
4938
4939</div>
4940
4941<!-- _______________________________________________________________________ -->
4942<h4>
4943   <a name="i_getelementptr">'<tt>getelementptr</tt>' Instruction</a>
4944</h4>
4945
4946<div>
4947
4948<h5>Syntax:</h5>
4949<pre>
4950  &lt;result&gt; = getelementptr &lt;pty&gt;* &lt;ptrval&gt;{, &lt;ty&gt; &lt;idx&gt;}*
4951  &lt;result&gt; = getelementptr inbounds &lt;pty&gt;* &lt;ptrval&gt;{, &lt;ty&gt; &lt;idx&gt;}*
4952</pre>
4953
4954<h5>Overview:</h5>
4955<p>The '<tt>getelementptr</tt>' instruction is used to get the address of a
4956   subelement of an <a href="#t_aggregate">aggregate</a> data structure.
4957   It performs address calculation only and does not access memory.</p>
4958
4959<h5>Arguments:</h5>
4960<p>The first argument is always a pointer, and forms the basis of the
4961   calculation. The remaining arguments are indices that indicate which of the
4962   elements of the aggregate object are indexed. The interpretation of each
4963   index is dependent on the type being indexed into. The first index always
4964   indexes the pointer value given as the first argument, the second index
4965   indexes a value of the type pointed to (not necessarily the value directly
4966   pointed to, since the first index can be non-zero), etc. The first type
4967   indexed into must be a pointer value, subsequent types can be arrays,
4968   vectors, and structs. Note that subsequent types being indexed into
4969   can never be pointers, since that would require loading the pointer before
4970   continuing calculation.</p>
4971
4972<p>The type of each index argument depends on the type it is indexing into.
4973   When indexing into a (optionally packed) structure, only <tt>i32</tt>
4974   integer <b>constants</b> are allowed.  When indexing into an array, pointer
4975   or vector, integers of any width are allowed, and they are not required to be
4976   constant.  These integers are treated as signed values where relevant.</p>
4977
4978<p>For example, let's consider a C code fragment and how it gets compiled to
4979   LLVM:</p>
4980
4981<pre class="doc_code">
4982struct RT {
4983  char A;
4984  int B[10][20];
4985  char C;
4986};
4987struct ST {
4988  int X;
4989  double Y;
4990  struct RT Z;
4991};
4992
4993int *foo(struct ST *s) {
4994  return &amp;s[1].Z.B[5][13];
4995}
4996</pre>
4997
4998<p>The LLVM code generated by the GCC frontend is:</p>
4999
5000<pre class="doc_code">
5001%RT = <a href="#namedtypes">type</a> { i8 , [10 x [20 x i32]], i8  }
5002%ST = <a href="#namedtypes">type</a> { i32, double, %RT }
5003
5004define i32* @foo(%ST* %s) {
5005entry:
5006  %reg = getelementptr %ST* %s, i32 1, i32 2, i32 1, i32 5, i32 13
5007  ret i32* %reg
5008}
5009</pre>
5010
5011<h5>Semantics:</h5>
5012<p>In the example above, the first index is indexing into the '<tt>%ST*</tt>'
5013   type, which is a pointer, yielding a '<tt>%ST</tt>' = '<tt>{ i32, double, %RT
5014   }</tt>' type, a structure.  The second index indexes into the third element
5015   of the structure, yielding a '<tt>%RT</tt>' = '<tt>{ i8 , [10 x [20 x i32]],
5016   i8 }</tt>' type, another structure.  The third index indexes into the second
5017   element of the structure, yielding a '<tt>[10 x [20 x i32]]</tt>' type, an
5018   array.  The two dimensions of the array are subscripted into, yielding an
5019   '<tt>i32</tt>' type.  The '<tt>getelementptr</tt>' instruction returns a
5020   pointer to this element, thus computing a value of '<tt>i32*</tt>' type.</p>
5021
5022<p>Note that it is perfectly legal to index partially through a structure,
5023   returning a pointer to an inner element.  Because of this, the LLVM code for
5024   the given testcase is equivalent to:</p>
5025
5026<pre>
5027  define i32* @foo(%ST* %s) {
5028    %t1 = getelementptr %ST* %s, i32 1                        <i>; yields %ST*:%t1</i>
5029    %t2 = getelementptr %ST* %t1, i32 0, i32 2                <i>; yields %RT*:%t2</i>
5030    %t3 = getelementptr %RT* %t2, i32 0, i32 1                <i>; yields [10 x [20 x i32]]*:%t3</i>
5031    %t4 = getelementptr [10 x [20 x i32]]* %t3, i32 0, i32 5  <i>; yields [20 x i32]*:%t4</i>
5032    %t5 = getelementptr [20 x i32]* %t4, i32 0, i32 13        <i>; yields i32*:%t5</i>
5033    ret i32* %t5
5034  }
5035</pre>
5036
5037<p>If the <tt>inbounds</tt> keyword is present, the result value of the
5038   <tt>getelementptr</tt> is a <a href="#trapvalues">trap value</a> if the
5039   base pointer is not an <i>in bounds</i> address of an allocated object,
5040   or if any of the addresses that would be formed by successive addition of
5041   the offsets implied by the indices to the base address with infinitely
5042   precise signed arithmetic are not an <i>in bounds</i> address of that
5043   allocated object. The <i>in bounds</i> addresses for an allocated object
5044   are all the addresses that point into the object, plus the address one
5045   byte past the end.</p>
5046
5047<p>If the <tt>inbounds</tt> keyword is not present, the offsets are added to
5048   the base address with silently-wrapping two's complement arithmetic. If the
5049   offsets have a different width from the pointer, they are sign-extended or
5050   truncated to the width of the pointer. The result value of the
5051   <tt>getelementptr</tt> may be outside the object pointed to by the base
5052   pointer. The result value may not necessarily be used to access memory
5053   though, even if it happens to point into allocated storage. See the
5054   <a href="#pointeraliasing">Pointer Aliasing Rules</a> section for more
5055   information.</p>
5056
5057<p>The getelementptr instruction is often confusing.  For some more insight into
5058   how it works, see <a href="GetElementPtr.html">the getelementptr FAQ</a>.</p>
5059
5060<h5>Example:</h5>
5061<pre>
5062    <i>; yields [12 x i8]*:aptr</i>
5063    %aptr = getelementptr {i32, [12 x i8]}* %saptr, i64 0, i32 1
5064    <i>; yields i8*:vptr</i>
5065    %vptr = getelementptr {i32, &lt;2 x i8&gt;}* %svptr, i64 0, i32 1, i32 1
5066    <i>; yields i8*:eptr</i>
5067    %eptr = getelementptr [12 x i8]* %aptr, i64 0, i32 1
5068    <i>; yields i32*:iptr</i>
5069    %iptr = getelementptr [10 x i32]* @arr, i16 0, i16 0
5070</pre>
5071
5072</div>
5073
5074</div>
5075
5076<!-- ======================================================================= -->
5077<h3>
5078  <a name="convertops">Conversion Operations</a>
5079</h3>
5080
5081<div>
5082
5083<p>The instructions in this category are the conversion instructions (casting)
5084   which all take a single operand and a type. They perform various bit
5085   conversions on the operand.</p>
5086
5087<!-- _______________________________________________________________________ -->
5088<h4>
5089   <a name="i_trunc">'<tt>trunc .. to</tt>' Instruction</a>
5090</h4>
5091
5092<div>
5093
5094<h5>Syntax:</h5>
5095<pre>
5096  &lt;result&gt; = trunc &lt;ty&gt; &lt;value&gt; to &lt;ty2&gt;             <i>; yields ty2</i>
5097</pre>
5098
5099<h5>Overview:</h5>
5100<p>The '<tt>trunc</tt>' instruction truncates its operand to the
5101   type <tt>ty2</tt>.</p>
5102
5103<h5>Arguments:</h5>
5104<p>The '<tt>trunc</tt>' instruction takes a value to trunc, and a type to trunc it to.
5105   Both types must be of <a href="#t_integer">integer</a> types, or vectors
5106   of the same number of integers.
5107   The bit size of the <tt>value</tt> must be larger than
5108   the bit size of the destination type, <tt>ty2</tt>.
5109   Equal sized types are not allowed.</p>
5110
5111<h5>Semantics:</h5>
5112<p>The '<tt>trunc</tt>' instruction truncates the high order bits
5113   in <tt>value</tt> and converts the remaining bits to <tt>ty2</tt>. Since the
5114   source size must be larger than the destination size, <tt>trunc</tt> cannot
5115   be a <i>no-op cast</i>.  It will always truncate bits.</p>
5116
5117<h5>Example:</h5>
5118<pre>
5119  %X = trunc i32 257 to i8                        <i>; yields i8:1</i>
5120  %Y = trunc i32 123 to i1                        <i>; yields i1:true</i>
5121  %Z = trunc i32 122 to i1                        <i>; yields i1:false</i>
5122  %W = trunc &lt;2 x i16&gt; &lt;i16 8, i16 7&gt; to &lt;2 x i8&gt; <i>; yields &lt;i8 8, i8 7&gt;</i>
5123</pre>
5124
5125</div>
5126
5127<!-- _______________________________________________________________________ -->
5128<h4>
5129   <a name="i_zext">'<tt>zext .. to</tt>' Instruction</a>
5130</h4>
5131
5132<div>
5133
5134<h5>Syntax:</h5>
5135<pre>
5136  &lt;result&gt; = zext &lt;ty&gt; &lt;value&gt; to &lt;ty2&gt;             <i>; yields ty2</i>
5137</pre>
5138
5139<h5>Overview:</h5>
5140<p>The '<tt>zext</tt>' instruction zero extends its operand to type
5141   <tt>ty2</tt>.</p>
5142
5143
5144<h5>Arguments:</h5>
5145<p>The '<tt>zext</tt>' instruction takes a value to cast, and a type to cast it to.
5146   Both types must be of <a href="#t_integer">integer</a> types, or vectors
5147   of the same number of integers.
5148   The bit size of the <tt>value</tt> must be smaller than
5149   the bit size of the destination type,
5150   <tt>ty2</tt>.</p>
5151
5152<h5>Semantics:</h5>
5153<p>The <tt>zext</tt> fills the high order bits of the <tt>value</tt> with zero
5154   bits until it reaches the size of the destination type, <tt>ty2</tt>.</p>
5155
5156<p>When zero extending from i1, the result will always be either 0 or 1.</p>
5157
5158<h5>Example:</h5>
5159<pre>
5160  %X = zext i32 257 to i64              <i>; yields i64:257</i>
5161  %Y = zext i1 true to i32              <i>; yields i32:1</i>
5162  %Z = zext &lt;2 x i16&gt; &lt;i16 8, i16 7&gt; to &lt;2 x i32&gt; <i>; yields &lt;i32 8, i32 7&gt;</i>
5163</pre>
5164
5165</div>
5166
5167<!-- _______________________________________________________________________ -->
5168<h4>
5169   <a name="i_sext">'<tt>sext .. to</tt>' Instruction</a>
5170</h4>
5171
5172<div>
5173
5174<h5>Syntax:</h5>
5175<pre>
5176  &lt;result&gt; = sext &lt;ty&gt; &lt;value&gt; to &lt;ty2&gt;             <i>; yields ty2</i>
5177</pre>
5178
5179<h5>Overview:</h5>
5180<p>The '<tt>sext</tt>' sign extends <tt>value</tt> to the type <tt>ty2</tt>.</p>
5181
5182<h5>Arguments:</h5>
5183<p>The '<tt>sext</tt>' instruction takes a value to cast, and a type to cast it to.
5184   Both types must be of <a href="#t_integer">integer</a> types, or vectors
5185   of the same number of integers.
5186   The bit size of the <tt>value</tt> must be smaller than
5187   the bit size of the destination type,
5188   <tt>ty2</tt>.</p>
5189
5190<h5>Semantics:</h5>
5191<p>The '<tt>sext</tt>' instruction performs a sign extension by copying the sign
5192   bit (highest order bit) of the <tt>value</tt> until it reaches the bit size
5193   of the type <tt>ty2</tt>.</p>
5194
5195<p>When sign extending from i1, the extension always results in -1 or 0.</p>
5196
5197<h5>Example:</h5>
5198<pre>
5199  %X = sext i8  -1 to i16              <i>; yields i16   :65535</i>
5200  %Y = sext i1 true to i32             <i>; yields i32:-1</i>
5201  %Z = sext &lt;2 x i16&gt; &lt;i16 8, i16 7&gt; to &lt;2 x i32&gt; <i>; yields &lt;i32 8, i32 7&gt;</i>
5202</pre>
5203
5204</div>
5205
5206<!-- _______________________________________________________________________ -->
5207<h4>
5208   <a name="i_fptrunc">'<tt>fptrunc .. to</tt>' Instruction</a>
5209</h4>
5210
5211<div>
5212
5213<h5>Syntax:</h5>
5214<pre>
5215  &lt;result&gt; = fptrunc &lt;ty&gt; &lt;value&gt; to &lt;ty2&gt;             <i>; yields ty2</i>
5216</pre>
5217
5218<h5>Overview:</h5>
5219<p>The '<tt>fptrunc</tt>' instruction truncates <tt>value</tt> to type
5220   <tt>ty2</tt>.</p>
5221
5222<h5>Arguments:</h5>
5223<p>The '<tt>fptrunc</tt>' instruction takes a <a href="#t_floating">floating
5224   point</a> value to cast and a <a href="#t_floating">floating point</a> type
5225   to cast it to. The size of <tt>value</tt> must be larger than the size of
5226   <tt>ty2</tt>. This implies that <tt>fptrunc</tt> cannot be used to make a
5227   <i>no-op cast</i>.</p>
5228
5229<h5>Semantics:</h5>
5230<p>The '<tt>fptrunc</tt>' instruction truncates a <tt>value</tt> from a larger
5231   <a href="#t_floating">floating point</a> type to a smaller
5232   <a href="#t_floating">floating point</a> type.  If the value cannot fit
5233   within the destination type, <tt>ty2</tt>, then the results are
5234   undefined.</p>
5235
5236<h5>Example:</h5>
5237<pre>
5238  %X = fptrunc double 123.0 to float         <i>; yields float:123.0</i>
5239  %Y = fptrunc double 1.0E+300 to float      <i>; yields undefined</i>
5240</pre>
5241
5242</div>
5243
5244<!-- _______________________________________________________________________ -->
5245<h4>
5246   <a name="i_fpext">'<tt>fpext .. to</tt>' Instruction</a>
5247</h4>
5248
5249<div>
5250
5251<h5>Syntax:</h5>
5252<pre>
5253  &lt;result&gt; = fpext &lt;ty&gt; &lt;value&gt; to &lt;ty2&gt;             <i>; yields ty2</i>
5254</pre>
5255
5256<h5>Overview:</h5>
5257<p>The '<tt>fpext</tt>' extends a floating point <tt>value</tt> to a larger
5258   floating point value.</p>
5259
5260<h5>Arguments:</h5>
5261<p>The '<tt>fpext</tt>' instruction takes a
5262   <a href="#t_floating">floating point</a> <tt>value</tt> to cast, and
5263   a <a href="#t_floating">floating point</a> type to cast it to. The source
5264   type must be smaller than the destination type.</p>
5265
5266<h5>Semantics:</h5>
5267<p>The '<tt>fpext</tt>' instruction extends the <tt>value</tt> from a smaller
5268   <a href="#t_floating">floating point</a> type to a larger
5269   <a href="#t_floating">floating point</a> type. The <tt>fpext</tt> cannot be
5270   used to make a <i>no-op cast</i> because it always changes bits. Use
5271   <tt>bitcast</tt> to make a <i>no-op cast</i> for a floating point cast.</p>
5272
5273<h5>Example:</h5>
5274<pre>
5275  %X = fpext float 3.125 to double         <i>; yields double:3.125000e+00</i>
5276  %Y = fpext double %X to fp128            <i>; yields fp128:0xL00000000000000004000900000000000</i>
5277</pre>
5278
5279</div>
5280
5281<!-- _______________________________________________________________________ -->
5282<h4>
5283   <a name="i_fptoui">'<tt>fptoui .. to</tt>' Instruction</a>
5284</h4>
5285
5286<div>
5287
5288<h5>Syntax:</h5>
5289<pre>
5290  &lt;result&gt; = fptoui &lt;ty&gt; &lt;value&gt; to &lt;ty2&gt;             <i>; yields ty2</i>
5291</pre>
5292
5293<h5>Overview:</h5>
5294<p>The '<tt>fptoui</tt>' converts a floating point <tt>value</tt> to its
5295   unsigned integer equivalent of type <tt>ty2</tt>.</p>
5296
5297<h5>Arguments:</h5>
5298<p>The '<tt>fptoui</tt>' instruction takes a value to cast, which must be a
5299   scalar or vector <a href="#t_floating">floating point</a> value, and a type
5300   to cast it to <tt>ty2</tt>, which must be an <a href="#t_integer">integer</a>
5301   type. If <tt>ty</tt> is a vector floating point type, <tt>ty2</tt> must be a
5302   vector integer type with the same number of elements as <tt>ty</tt></p>
5303
5304<h5>Semantics:</h5>
5305<p>The '<tt>fptoui</tt>' instruction converts its
5306   <a href="#t_floating">floating point</a> operand into the nearest (rounding
5307   towards zero) unsigned integer value. If the value cannot fit
5308   in <tt>ty2</tt>, the results are undefined.</p>
5309
5310<h5>Example:</h5>
5311<pre>
5312  %X = fptoui double 123.0 to i32      <i>; yields i32:123</i>
5313  %Y = fptoui float 1.0E+300 to i1     <i>; yields undefined:1</i>
5314  %Z = fptoui float 1.04E+17 to i8     <i>; yields undefined:1</i>
5315</pre>
5316
5317</div>
5318
5319<!-- _______________________________________________________________________ -->
5320<h4>
5321   <a name="i_fptosi">'<tt>fptosi .. to</tt>' Instruction</a>
5322</h4>
5323
5324<div>
5325
5326<h5>Syntax:</h5>
5327<pre>
5328  &lt;result&gt; = fptosi &lt;ty&gt; &lt;value&gt; to &lt;ty2&gt;             <i>; yields ty2</i>
5329</pre>
5330
5331<h5>Overview:</h5>
5332<p>The '<tt>fptosi</tt>' instruction converts
5333   <a href="#t_floating">floating point</a> <tt>value</tt> to
5334   type <tt>ty2</tt>.</p>
5335
5336<h5>Arguments:</h5>
5337<p>The '<tt>fptosi</tt>' instruction takes a value to cast, which must be a
5338   scalar or vector <a href="#t_floating">floating point</a> value, and a type
5339   to cast it to <tt>ty2</tt>, which must be an <a href="#t_integer">integer</a>
5340   type. If <tt>ty</tt> is a vector floating point type, <tt>ty2</tt> must be a
5341   vector integer type with the same number of elements as <tt>ty</tt></p>
5342
5343<h5>Semantics:</h5>
5344<p>The '<tt>fptosi</tt>' instruction converts its
5345   <a href="#t_floating">floating point</a> operand into the nearest (rounding
5346   towards zero) signed integer value. If the value cannot fit in <tt>ty2</tt>,
5347   the results are undefined.</p>
5348
5349<h5>Example:</h5>
5350<pre>
5351  %X = fptosi double -123.0 to i32      <i>; yields i32:-123</i>
5352  %Y = fptosi float 1.0E-247 to i1      <i>; yields undefined:1</i>
5353  %Z = fptosi float 1.04E+17 to i8      <i>; yields undefined:1</i>
5354</pre>
5355
5356</div>
5357
5358<!-- _______________________________________________________________________ -->
5359<h4>
5360   <a name="i_uitofp">'<tt>uitofp .. to</tt>' Instruction</a>
5361</h4>
5362
5363<div>
5364
5365<h5>Syntax:</h5>
5366<pre>
5367  &lt;result&gt; = uitofp &lt;ty&gt; &lt;value&gt; to &lt;ty2&gt;             <i>; yields ty2</i>
5368</pre>
5369
5370<h5>Overview:</h5>
5371<p>The '<tt>uitofp</tt>' instruction regards <tt>value</tt> as an unsigned
5372   integer and converts that value to the <tt>ty2</tt> type.</p>
5373
5374<h5>Arguments:</h5>
5375<p>The '<tt>uitofp</tt>' instruction takes a value to cast, which must be a
5376   scalar or vector <a href="#t_integer">integer</a> value, and a type to cast
5377   it to <tt>ty2</tt>, which must be an <a href="#t_floating">floating point</a>
5378   type. If <tt>ty</tt> is a vector integer type, <tt>ty2</tt> must be a vector
5379   floating point type with the same number of elements as <tt>ty</tt></p>
5380
5381<h5>Semantics:</h5>
5382<p>The '<tt>uitofp</tt>' instruction interprets its operand as an unsigned
5383   integer quantity and converts it to the corresponding floating point
5384   value. If the value cannot fit in the floating point value, the results are
5385   undefined.</p>
5386
5387<h5>Example:</h5>
5388<pre>
5389  %X = uitofp i32 257 to float         <i>; yields float:257.0</i>
5390  %Y = uitofp i8 -1 to double          <i>; yields double:255.0</i>
5391</pre>
5392
5393</div>
5394
5395<!-- _______________________________________________________________________ -->
5396<h4>
5397   <a name="i_sitofp">'<tt>sitofp .. to</tt>' Instruction</a>
5398</h4>
5399
5400<div>
5401
5402<h5>Syntax:</h5>
5403<pre>
5404  &lt;result&gt; = sitofp &lt;ty&gt; &lt;value&gt; to &lt;ty2&gt;             <i>; yields ty2</i>
5405</pre>
5406
5407<h5>Overview:</h5>
5408<p>The '<tt>sitofp</tt>' instruction regards <tt>value</tt> as a signed integer
5409   and converts that value to the <tt>ty2</tt> type.</p>
5410
5411<h5>Arguments:</h5>
5412<p>The '<tt>sitofp</tt>' instruction takes a value to cast, which must be a
5413   scalar or vector <a href="#t_integer">integer</a> value, and a type to cast
5414   it to <tt>ty2</tt>, which must be an <a href="#t_floating">floating point</a>
5415   type. If <tt>ty</tt> is a vector integer type, <tt>ty2</tt> must be a vector
5416   floating point type with the same number of elements as <tt>ty</tt></p>
5417
5418<h5>Semantics:</h5>
5419<p>The '<tt>sitofp</tt>' instruction interprets its operand as a signed integer
5420   quantity and converts it to the corresponding floating point value. If the
5421   value cannot fit in the floating point value, the results are undefined.</p>
5422
5423<h5>Example:</h5>
5424<pre>
5425  %X = sitofp i32 257 to float         <i>; yields float:257.0</i>
5426  %Y = sitofp i8 -1 to double          <i>; yields double:-1.0</i>
5427</pre>
5428
5429</div>
5430
5431<!-- _______________________________________________________________________ -->
5432<h4>
5433   <a name="i_ptrtoint">'<tt>ptrtoint .. to</tt>' Instruction</a>
5434</h4>
5435
5436<div>
5437
5438<h5>Syntax:</h5>
5439<pre>
5440  &lt;result&gt; = ptrtoint &lt;ty&gt; &lt;value&gt; to &lt;ty2&gt;             <i>; yields ty2</i>
5441</pre>
5442
5443<h5>Overview:</h5>
5444<p>The '<tt>ptrtoint</tt>' instruction converts the pointer <tt>value</tt> to
5445   the integer type <tt>ty2</tt>.</p>
5446
5447<h5>Arguments:</h5>
5448<p>The '<tt>ptrtoint</tt>' instruction takes a <tt>value</tt> to cast, which
5449   must be a <a href="#t_pointer">pointer</a> value, and a type to cast it to
5450   <tt>ty2</tt>, which must be an <a href="#t_integer">integer</a> type.</p>
5451
5452<h5>Semantics:</h5>
5453<p>The '<tt>ptrtoint</tt>' instruction converts <tt>value</tt> to integer type
5454   <tt>ty2</tt> by interpreting the pointer value as an integer and either
5455   truncating or zero extending that value to the size of the integer type. If
5456   <tt>value</tt> is smaller than <tt>ty2</tt> then a zero extension is done. If
5457   <tt>value</tt> is larger than <tt>ty2</tt> then a truncation is done. If they
5458   are the same size, then nothing is done (<i>no-op cast</i>) other than a type
5459   change.</p>
5460
5461<h5>Example:</h5>
5462<pre>
5463  %X = ptrtoint i32* %X to i8           <i>; yields truncation on 32-bit architecture</i>
5464  %Y = ptrtoint i32* %x to i64          <i>; yields zero extension on 32-bit architecture</i>
5465</pre>
5466
5467</div>
5468
5469<!-- _______________________________________________________________________ -->
5470<h4>
5471   <a name="i_inttoptr">'<tt>inttoptr .. to</tt>' Instruction</a>
5472</h4>
5473
5474<div>
5475
5476<h5>Syntax:</h5>
5477<pre>
5478  &lt;result&gt; = inttoptr &lt;ty&gt; &lt;value&gt; to &lt;ty2&gt;             <i>; yields ty2</i>
5479</pre>
5480
5481<h5>Overview:</h5>
5482<p>The '<tt>inttoptr</tt>' instruction converts an integer <tt>value</tt> to a
5483   pointer type, <tt>ty2</tt>.</p>
5484
5485<h5>Arguments:</h5>
5486<p>The '<tt>inttoptr</tt>' instruction takes an <a href="#t_integer">integer</a>
5487   value to cast, and a type to cast it to, which must be a
5488   <a href="#t_pointer">pointer</a> type.</p>
5489
5490<h5>Semantics:</h5>
5491<p>The '<tt>inttoptr</tt>' instruction converts <tt>value</tt> to type
5492   <tt>ty2</tt> by applying either a zero extension or a truncation depending on
5493   the size of the integer <tt>value</tt>. If <tt>value</tt> is larger than the
5494   size of a pointer then a truncation is done. If <tt>value</tt> is smaller
5495   than the size of a pointer then a zero extension is done. If they are the
5496   same size, nothing is done (<i>no-op cast</i>).</p>
5497
5498<h5>Example:</h5>
5499<pre>
5500  %X = inttoptr i32 255 to i32*          <i>; yields zero extension on 64-bit architecture</i>
5501  %Y = inttoptr i32 255 to i32*          <i>; yields no-op on 32-bit architecture</i>
5502  %Z = inttoptr i64 0 to i32*            <i>; yields truncation on 32-bit architecture</i>
5503</pre>
5504
5505</div>
5506
5507<!-- _______________________________________________________________________ -->
5508<h4>
5509   <a name="i_bitcast">'<tt>bitcast .. to</tt>' Instruction</a>
5510</h4>
5511
5512<div>
5513
5514<h5>Syntax:</h5>
5515<pre>
5516  &lt;result&gt; = bitcast &lt;ty&gt; &lt;value&gt; to &lt;ty2&gt;             <i>; yields ty2</i>
5517</pre>
5518
5519<h5>Overview:</h5>
5520<p>The '<tt>bitcast</tt>' instruction converts <tt>value</tt> to type
5521   <tt>ty2</tt> without changing any bits.</p>
5522
5523<h5>Arguments:</h5>
5524<p>The '<tt>bitcast</tt>' instruction takes a value to cast, which must be a
5525   non-aggregate first class value, and a type to cast it to, which must also be
5526   a non-aggregate <a href="#t_firstclass">first class</a> type. The bit sizes
5527   of <tt>value</tt> and the destination type, <tt>ty2</tt>, must be
5528   identical. If the source type is a pointer, the destination type must also be
5529   a pointer.  This instruction supports bitwise conversion of vectors to
5530   integers and to vectors of other types (as long as they have the same
5531   size).</p>
5532
5533<h5>Semantics:</h5>
5534<p>The '<tt>bitcast</tt>' instruction converts <tt>value</tt> to type
5535   <tt>ty2</tt>. It is always a <i>no-op cast</i> because no bits change with
5536   this conversion.  The conversion is done as if the <tt>value</tt> had been
5537   stored to memory and read back as type <tt>ty2</tt>. Pointer types may only
5538   be converted to other pointer types with this instruction. To convert
5539   pointers to other types, use the <a href="#i_inttoptr">inttoptr</a> or
5540   <a href="#i_ptrtoint">ptrtoint</a> instructions first.</p>
5541
5542<h5>Example:</h5>
5543<pre>
5544  %X = bitcast i8 255 to i8              <i>; yields i8 :-1</i>
5545  %Y = bitcast i32* %x to sint*          <i>; yields sint*:%x</i>
5546  %Z = bitcast &lt;2 x int&gt; %V to i64;      <i>; yields i64: %V</i>
5547</pre>
5548
5549</div>
5550
5551</div>
5552
5553<!-- ======================================================================= -->
5554<h3>
5555  <a name="otherops">Other Operations</a>
5556</h3>
5557
5558<div>
5559
5560<p>The instructions in this category are the "miscellaneous" instructions, which
5561   defy better classification.</p>
5562
5563<!-- _______________________________________________________________________ -->
5564<h4>
5565  <a name="i_icmp">'<tt>icmp</tt>' Instruction</a>
5566</h4>
5567
5568<div>
5569
5570<h5>Syntax:</h5>
5571<pre>
5572  &lt;result&gt; = icmp &lt;cond&gt; &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;   <i>; yields {i1} or {&lt;N x i1&gt;}:result</i>
5573</pre>
5574
5575<h5>Overview:</h5>
5576<p>The '<tt>icmp</tt>' instruction returns a boolean value or a vector of
5577   boolean values based on comparison of its two integer, integer vector, or
5578   pointer operands.</p>
5579
5580<h5>Arguments:</h5>
5581<p>The '<tt>icmp</tt>' instruction takes three operands. The first operand is
5582   the condition code indicating the kind of comparison to perform. It is not a
5583   value, just a keyword. The possible condition code are:</p>
5584
5585<ol>
5586  <li><tt>eq</tt>: equal</li>
5587  <li><tt>ne</tt>: not equal </li>
5588  <li><tt>ugt</tt>: unsigned greater than</li>
5589  <li><tt>uge</tt>: unsigned greater or equal</li>
5590  <li><tt>ult</tt>: unsigned less than</li>
5591  <li><tt>ule</tt>: unsigned less or equal</li>
5592  <li><tt>sgt</tt>: signed greater than</li>
5593  <li><tt>sge</tt>: signed greater or equal</li>
5594  <li><tt>slt</tt>: signed less than</li>
5595  <li><tt>sle</tt>: signed less or equal</li>
5596</ol>
5597
5598<p>The remaining two arguments must be <a href="#t_integer">integer</a> or
5599   <a href="#t_pointer">pointer</a> or integer <a href="#t_vector">vector</a>
5600   typed.  They must also be identical types.</p>
5601
5602<h5>Semantics:</h5>
5603<p>The '<tt>icmp</tt>' compares <tt>op1</tt> and <tt>op2</tt> according to the
5604   condition code given as <tt>cond</tt>. The comparison performed always yields
5605   either an <a href="#t_integer"><tt>i1</tt></a> or vector of <tt>i1</tt>
5606   result, as follows:</p>
5607
5608<ol>
5609  <li><tt>eq</tt>: yields <tt>true</tt> if the operands are equal,
5610      <tt>false</tt> otherwise. No sign interpretation is necessary or
5611      performed.</li>
5612
5613  <li><tt>ne</tt>: yields <tt>true</tt> if the operands are unequal,
5614      <tt>false</tt> otherwise. No sign interpretation is necessary or
5615      performed.</li>
5616
5617  <li><tt>ugt</tt>: interprets the operands as unsigned values and yields
5618      <tt>true</tt> if <tt>op1</tt> is greater than <tt>op2</tt>.</li>
5619
5620  <li><tt>uge</tt>: interprets the operands as unsigned values and yields
5621      <tt>true</tt> if <tt>op1</tt> is greater than or equal
5622      to <tt>op2</tt>.</li>
5623
5624  <li><tt>ult</tt>: interprets the operands as unsigned values and yields
5625      <tt>true</tt> if <tt>op1</tt> is less than <tt>op2</tt>.</li>
5626
5627  <li><tt>ule</tt>: interprets the operands as unsigned values and yields
5628      <tt>true</tt> if <tt>op1</tt> is less than or equal to <tt>op2</tt>.</li>
5629
5630  <li><tt>sgt</tt>: interprets the operands as signed values and yields
5631      <tt>true</tt> if <tt>op1</tt> is greater than <tt>op2</tt>.</li>
5632
5633  <li><tt>sge</tt>: interprets the operands as signed values and yields
5634      <tt>true</tt> if <tt>op1</tt> is greater than or equal
5635      to <tt>op2</tt>.</li>
5636
5637  <li><tt>slt</tt>: interprets the operands as signed values and yields
5638      <tt>true</tt> if <tt>op1</tt> is less than <tt>op2</tt>.</li>
5639
5640  <li><tt>sle</tt>: interprets the operands as signed values and yields
5641      <tt>true</tt> if <tt>op1</tt> is less than or equal to <tt>op2</tt>.</li>
5642</ol>
5643
5644<p>If the operands are <a href="#t_pointer">pointer</a> typed, the pointer
5645   values are compared as if they were integers.</p>
5646
5647<p>If the operands are integer vectors, then they are compared element by
5648   element. The result is an <tt>i1</tt> vector with the same number of elements
5649   as the values being compared.  Otherwise, the result is an <tt>i1</tt>.</p>
5650
5651<h5>Example:</h5>
5652<pre>
5653  &lt;result&gt; = icmp eq i32 4, 5          <i>; yields: result=false</i>
5654  &lt;result&gt; = icmp ne float* %X, %X     <i>; yields: result=false</i>
5655  &lt;result&gt; = icmp ult i16  4, 5        <i>; yields: result=true</i>
5656  &lt;result&gt; = icmp sgt i16  4, 5        <i>; yields: result=false</i>
5657  &lt;result&gt; = icmp ule i16 -4, 5        <i>; yields: result=false</i>
5658  &lt;result&gt; = icmp sge i16  4, 5        <i>; yields: result=false</i>
5659</pre>
5660
5661<p>Note that the code generator does not yet support vector types with
5662   the <tt>icmp</tt> instruction.</p>
5663
5664</div>
5665
5666<!-- _______________________________________________________________________ -->
5667<h4>
5668  <a name="i_fcmp">'<tt>fcmp</tt>' Instruction</a>
5669</h4>
5670
5671<div>
5672
5673<h5>Syntax:</h5>
5674<pre>
5675  &lt;result&gt; = fcmp &lt;cond&gt; &lt;ty&gt; &lt;op1&gt;, &lt;op2&gt;     <i>; yields {i1} or {&lt;N x i1&gt;}:result</i>
5676</pre>
5677
5678<h5>Overview:</h5>
5679<p>The '<tt>fcmp</tt>' instruction returns a boolean value or vector of boolean
5680   values based on comparison of its operands.</p>
5681
5682<p>If the operands are floating point scalars, then the result type is a boolean
5683(<a href="#t_integer"><tt>i1</tt></a>).</p>
5684
5685<p>If the operands are floating point vectors, then the result type is a vector
5686   of boolean with the same number of elements as the operands being
5687   compared.</p>
5688
5689<h5>Arguments:</h5>
5690<p>The '<tt>fcmp</tt>' instruction takes three operands. The first operand is
5691   the condition code indicating the kind of comparison to perform. It is not a
5692   value, just a keyword. The possible condition code are:</p>
5693
5694<ol>
5695  <li><tt>false</tt>: no comparison, always returns false</li>
5696  <li><tt>oeq</tt>: ordered and equal</li>
5697  <li><tt>ogt</tt>: ordered and greater than </li>
5698  <li><tt>oge</tt>: ordered and greater than or equal</li>
5699  <li><tt>olt</tt>: ordered and less than </li>
5700  <li><tt>ole</tt>: ordered and less than or equal</li>
5701  <li><tt>one</tt>: ordered and not equal</li>
5702  <li><tt>ord</tt>: ordered (no nans)</li>
5703  <li><tt>ueq</tt>: unordered or equal</li>
5704  <li><tt>ugt</tt>: unordered or greater than </li>
5705  <li><tt>uge</tt>: unordered or greater than or equal</li>
5706  <li><tt>ult</tt>: unordered or less than </li>
5707  <li><tt>ule</tt>: unordered or less than or equal</li>
5708  <li><tt>une</tt>: unordered or not equal</li>
5709  <li><tt>uno</tt>: unordered (either nans)</li>
5710  <li><tt>true</tt>: no comparison, always returns true</li>
5711</ol>
5712
5713<p><i>Ordered</i> means that neither operand is a QNAN while
5714   <i>unordered</i> means that either operand may be a QNAN.</p>
5715
5716<p>Each of <tt>val1</tt> and <tt>val2</tt> arguments must be either
5717   a <a href="#t_floating">floating point</a> type or
5718   a <a href="#t_vector">vector</a> of floating point type.  They must have
5719   identical types.</p>
5720
5721<h5>Semantics:</h5>
5722<p>The '<tt>fcmp</tt>' instruction compares <tt>op1</tt> and <tt>op2</tt>
5723   according to the condition code given as <tt>cond</tt>.  If the operands are
5724   vectors, then the vectors are compared element by element.  Each comparison
5725   performed always yields an <a href="#t_integer">i1</a> result, as
5726   follows:</p>
5727
5728<ol>
5729  <li><tt>false</tt>: always yields <tt>false</tt>, regardless of operands.</li>
5730
5731  <li><tt>oeq</tt>: yields <tt>true</tt> if both operands are not a QNAN and
5732      <tt>op1</tt> is equal to <tt>op2</tt>.</li>
5733
5734  <li><tt>ogt</tt>: yields <tt>true</tt> if both operands are not a QNAN and
5735      <tt>op1</tt> is greater than <tt>op2</tt>.</li>
5736
5737  <li><tt>oge</tt>: yields <tt>true</tt> if both operands are not a QNAN and
5738      <tt>op1</tt> is greater than or equal to <tt>op2</tt>.</li>
5739
5740  <li><tt>olt</tt>: yields <tt>true</tt> if both operands are not a QNAN and
5741      <tt>op1</tt> is less than <tt>op2</tt>.</li>
5742
5743  <li><tt>ole</tt>: yields <tt>true</tt> if both operands are not a QNAN and
5744      <tt>op1</tt> is less than or equal to <tt>op2</tt>.</li>
5745
5746  <li><tt>one</tt>: yields <tt>true</tt> if both operands are not a QNAN and
5747      <tt>op1</tt> is not equal to <tt>op2</tt>.</li>
5748
5749  <li><tt>ord</tt>: yields <tt>true</tt> if both operands are not a QNAN.</li>
5750
5751  <li><tt>ueq</tt>: yields <tt>true</tt> if either operand is a QNAN or
5752      <tt>op1</tt> is equal to <tt>op2</tt>.</li>
5753
5754  <li><tt>ugt</tt>: yields <tt>true</tt> if either operand is a QNAN or
5755      <tt>op1</tt> is greater than <tt>op2</tt>.</li>
5756
5757  <li><tt>uge</tt>: yields <tt>true</tt> if either operand is a QNAN or
5758      <tt>op1</tt> is greater than or equal to <tt>op2</tt>.</li>
5759
5760  <li><tt>ult</tt>: yields <tt>true</tt> if either operand is a QNAN or
5761      <tt>op1</tt> is less than <tt>op2</tt>.</li>
5762
5763  <li><tt>ule</tt>: yields <tt>true</tt> if either operand is a QNAN or
5764      <tt>op1</tt> is less than or equal to <tt>op2</tt>.</li>
5765
5766  <li><tt>une</tt>: yields <tt>true</tt> if either operand is a QNAN or
5767      <tt>op1</tt> is not equal to <tt>op2</tt>.</li>
5768
5769  <li><tt>uno</tt>: yields <tt>true</tt> if either operand is a QNAN.</li>
5770
5771  <li><tt>true</tt>: always yields <tt>true</tt>, regardless of operands.</li>
5772</ol>
5773
5774<h5>Example:</h5>
5775<pre>
5776  &lt;result&gt; = fcmp oeq float 4.0, 5.0    <i>; yields: result=false</i>
5777  &lt;result&gt; = fcmp one float 4.0, 5.0    <i>; yields: result=true</i>
5778  &lt;result&gt; = fcmp olt float 4.0, 5.0    <i>; yields: result=true</i>
5779  &lt;result&gt; = fcmp ueq double 1.0, 2.0   <i>; yields: result=false</i>
5780</pre>
5781
5782<p>Note that the code generator does not yet support vector types with
5783   the <tt>fcmp</tt> instruction.</p>
5784
5785</div>
5786
5787<!-- _______________________________________________________________________ -->
5788<h4>
5789  <a name="i_phi">'<tt>phi</tt>' Instruction</a>
5790</h4>
5791
5792<div>
5793
5794<h5>Syntax:</h5>
5795<pre>
5796  &lt;result&gt; = phi &lt;ty&gt; [ &lt;val0&gt;, &lt;label0&gt;], ...
5797</pre>
5798
5799<h5>Overview:</h5>
5800<p>The '<tt>phi</tt>' instruction is used to implement the &#966; node in the
5801   SSA graph representing the function.</p>
5802
5803<h5>Arguments:</h5>
5804<p>The type of the incoming values is specified with the first type field. After
5805   this, the '<tt>phi</tt>' instruction takes a list of pairs as arguments, with
5806   one pair for each predecessor basic block of the current block.  Only values
5807   of <a href="#t_firstclass">first class</a> type may be used as the value
5808   arguments to the PHI node.  Only labels may be used as the label
5809   arguments.</p>
5810
5811<p>There must be no non-phi instructions between the start of a basic block and
5812   the PHI instructions: i.e. PHI instructions must be first in a basic
5813   block.</p>
5814
5815<p>For the purposes of the SSA form, the use of each incoming value is deemed to
5816   occur on the edge from the corresponding predecessor block to the current
5817   block (but after any definition of an '<tt>invoke</tt>' instruction's return
5818   value on the same edge).</p>
5819
5820<h5>Semantics:</h5>
5821<p>At runtime, the '<tt>phi</tt>' instruction logically takes on the value
5822   specified by the pair corresponding to the predecessor basic block that
5823   executed just prior to the current block.</p>
5824
5825<h5>Example:</h5>
5826<pre>
5827Loop:       ; Infinite loop that counts from 0 on up...
5828  %indvar = phi i32 [ 0, %LoopHeader ], [ %nextindvar, %Loop ]
5829  %nextindvar = add i32 %indvar, 1
5830  br label %Loop
5831</pre>
5832
5833</div>
5834
5835<!-- _______________________________________________________________________ -->
5836<h4>
5837   <a name="i_select">'<tt>select</tt>' Instruction</a>
5838</h4>
5839
5840<div>
5841
5842<h5>Syntax:</h5>
5843<pre>
5844  &lt;result&gt; = select <i>selty</i> &lt;cond&gt;, &lt;ty&gt; &lt;val1&gt;, &lt;ty&gt; &lt;val2&gt;             <i>; yields ty</i>
5845
5846  <i>selty</i> is either i1 or {&lt;N x i1&gt;}
5847</pre>
5848
5849<h5>Overview:</h5>
5850<p>The '<tt>select</tt>' instruction is used to choose one value based on a
5851   condition, without branching.</p>
5852
5853
5854<h5>Arguments:</h5>
5855<p>The '<tt>select</tt>' instruction requires an 'i1' value or a vector of 'i1'
5856   values indicating the condition, and two values of the
5857   same <a href="#t_firstclass">first class</a> type.  If the val1/val2 are
5858   vectors and the condition is a scalar, then entire vectors are selected, not
5859   individual elements.</p>
5860
5861<h5>Semantics:</h5>
5862<p>If the condition is an i1 and it evaluates to 1, the instruction returns the
5863   first value argument; otherwise, it returns the second value argument.</p>
5864
5865<p>If the condition is a vector of i1, then the value arguments must be vectors
5866   of the same size, and the selection is done element by element.</p>
5867
5868<h5>Example:</h5>
5869<pre>
5870  %X = select i1 true, i8 17, i8 42          <i>; yields i8:17</i>
5871</pre>
5872
5873<p>Note that the code generator does not yet support conditions
5874   with vector type.</p>
5875
5876</div>
5877
5878<!-- _______________________________________________________________________ -->
5879<h4>
5880  <a name="i_call">'<tt>call</tt>' Instruction</a>
5881</h4>
5882
5883<div>
5884
5885<h5>Syntax:</h5>
5886<pre>
5887  &lt;result&gt; = [tail] call [<a href="#callingconv">cconv</a>] [<a href="#paramattrs">ret attrs</a>] &lt;ty&gt; [&lt;fnty&gt;*] &lt;fnptrval&gt;(&lt;function args&gt;) [<a href="#fnattrs">fn attrs</a>]
5888</pre>
5889
5890<h5>Overview:</h5>
5891<p>The '<tt>call</tt>' instruction represents a simple function call.</p>
5892
5893<h5>Arguments:</h5>
5894<p>This instruction requires several arguments:</p>
5895
5896<ol>
5897  <li>The optional "tail" marker indicates that the callee function does not
5898      access any allocas or varargs in the caller.  Note that calls may be
5899      marked "tail" even if they do not occur before
5900      a <a href="#i_ret"><tt>ret</tt></a> instruction.  If the "tail" marker is
5901      present, the function call is eligible for tail call optimization,
5902      but <a href="CodeGenerator.html#tailcallopt">might not in fact be
5903      optimized into a jump</a>.  The code generator may optimize calls marked
5904      "tail" with either 1) automatic <a href="CodeGenerator.html#sibcallopt">
5905      sibling call optimization</a> when the caller and callee have
5906      matching signatures, or 2) forced tail call optimization when the
5907      following extra requirements are met:
5908      <ul>
5909        <li>Caller and callee both have the calling
5910            convention <tt>fastcc</tt>.</li>
5911        <li>The call is in tail position (ret immediately follows call and ret
5912            uses value of call or is void).</li>
5913        <li>Option <tt>-tailcallopt</tt> is enabled,
5914            or <code>llvm::GuaranteedTailCallOpt</code> is <code>true</code>.</li>
5915        <li><a href="CodeGenerator.html#tailcallopt">Platform specific
5916            constraints are met.</a></li>
5917      </ul>
5918  </li>
5919
5920  <li>The optional "cconv" marker indicates which <a href="#callingconv">calling
5921      convention</a> the call should use.  If none is specified, the call
5922      defaults to using C calling conventions.  The calling convention of the
5923      call must match the calling convention of the target function, or else the
5924      behavior is undefined.</li>
5925
5926  <li>The optional <a href="#paramattrs">Parameter Attributes</a> list for
5927      return values. Only '<tt>zeroext</tt>', '<tt>signext</tt>', and
5928      '<tt>inreg</tt>' attributes are valid here.</li>
5929
5930  <li>'<tt>ty</tt>': the type of the call instruction itself which is also the
5931      type of the return value.  Functions that return no value are marked
5932      <tt><a href="#t_void">void</a></tt>.</li>
5933
5934  <li>'<tt>fnty</tt>': shall be the signature of the pointer to function value
5935      being invoked.  The argument types must match the types implied by this
5936      signature.  This type can be omitted if the function is not varargs and if
5937      the function type does not return a pointer to a function.</li>
5938
5939  <li>'<tt>fnptrval</tt>': An LLVM value containing a pointer to a function to
5940      be invoked. In most cases, this is a direct function invocation, but
5941      indirect <tt>call</tt>s are just as possible, calling an arbitrary pointer
5942      to function value.</li>
5943
5944  <li>'<tt>function args</tt>': argument list whose types match the function
5945      signature argument types and parameter attributes. All arguments must be
5946      of <a href="#t_firstclass">first class</a> type. If the function
5947      signature indicates the function accepts a variable number of arguments,
5948      the extra arguments can be specified.</li>
5949
5950  <li>The optional <a href="#fnattrs">function attributes</a> list. Only
5951      '<tt>noreturn</tt>', '<tt>nounwind</tt>', '<tt>readonly</tt>' and
5952      '<tt>readnone</tt>' attributes are valid here.</li>
5953</ol>
5954
5955<h5>Semantics:</h5>
5956<p>The '<tt>call</tt>' instruction is used to cause control flow to transfer to
5957   a specified function, with its incoming arguments bound to the specified
5958   values. Upon a '<tt><a href="#i_ret">ret</a></tt>' instruction in the called
5959   function, control flow continues with the instruction after the function
5960   call, and the return value of the function is bound to the result
5961   argument.</p>
5962
5963<h5>Example:</h5>
5964<pre>
5965  %retval = call i32 @test(i32 %argc)
5966  call i32 (i8*, ...)* @printf(i8* %msg, i32 12, i8 42)        <i>; yields i32</i>
5967  %X = tail call i32 @foo()                                    <i>; yields i32</i>
5968  %Y = tail call <a href="#callingconv">fastcc</a> i32 @foo()  <i>; yields i32</i>
5969  call void %foo(i8 97 signext)
5970
5971  %struct.A = type { i32, i8 }
5972  %r = call %struct.A @foo()                        <i>; yields { 32, i8 }</i>
5973  %gr = extractvalue %struct.A %r, 0                <i>; yields i32</i>
5974  %gr1 = extractvalue %struct.A %r, 1               <i>; yields i8</i>
5975  %Z = call void @foo() noreturn                    <i>; indicates that %foo never returns normally</i>
5976  %ZZ = call zeroext i32 @bar()                     <i>; Return value is %zero extended</i>
5977</pre>
5978
5979<p>llvm treats calls to some functions with names and arguments that match the
5980standard C99 library as being the C99 library functions, and may perform
5981optimizations or generate code for them under that assumption.  This is
5982something we'd like to change in the future to provide better support for
5983freestanding environments and non-C-based languages.</p>
5984
5985</div>
5986
5987<!-- _______________________________________________________________________ -->
5988<h4>
5989  <a name="i_va_arg">'<tt>va_arg</tt>' Instruction</a>
5990</h4>
5991
5992<div>
5993
5994<h5>Syntax:</h5>
5995<pre>
5996  &lt;resultval&gt; = va_arg &lt;va_list*&gt; &lt;arglist&gt;, &lt;argty&gt;
5997</pre>
5998
5999<h5>Overview:</h5>
6000<p>The '<tt>va_arg</tt>' instruction is used to access arguments passed through
6001   the "variable argument" area of a function call.  It is used to implement the
6002   <tt>va_arg</tt> macro in C.</p>
6003
6004<h5>Arguments:</h5>
6005<p>This instruction takes a <tt>va_list*</tt> value and the type of the
6006   argument. It returns a value of the specified argument type and increments
6007   the <tt>va_list</tt> to point to the next argument.  The actual type
6008   of <tt>va_list</tt> is target specific.</p>
6009
6010<h5>Semantics:</h5>
6011<p>The '<tt>va_arg</tt>' instruction loads an argument of the specified type
6012   from the specified <tt>va_list</tt> and causes the <tt>va_list</tt> to point
6013   to the next argument.  For more information, see the variable argument
6014   handling <a href="#int_varargs">Intrinsic Functions</a>.</p>
6015
6016<p>It is legal for this instruction to be called in a function which does not
6017   take a variable number of arguments, for example, the <tt>vfprintf</tt>
6018   function.</p>
6019
6020<p><tt>va_arg</tt> is an LLVM instruction instead of
6021   an <a href="#intrinsics">intrinsic function</a> because it takes a type as an
6022   argument.</p>
6023
6024<h5>Example:</h5>
6025<p>See the <a href="#int_varargs">variable argument processing</a> section.</p>
6026
6027<p>Note that the code generator does not yet fully support va_arg on many
6028   targets. Also, it does not currently support va_arg with aggregate types on
6029   any target.</p>
6030
6031</div>
6032
6033<!-- _______________________________________________________________________ -->
6034<h4>
6035  <a name="i_landingpad">'<tt>landingpad</tt>' Instruction</a>
6036</h4>
6037
6038<div>
6039
6040<h5>Syntax:</h5>
6041<pre>
6042  &lt;resultval&gt; = landingpad &lt;somety&gt; personality &lt;type&gt; &lt;pers_fn&gt; &lt;clause&gt;+
6043  &lt;resultval&gt; = landingpad &lt;somety&gt; personality &lt;type&gt; &lt;pers_fn&gt; cleanup &lt;clause&gt;*
6044
6045  &lt;clause&gt; := catch &lt;type&gt; &lt;value&gt;
6046  &lt;clause&gt; := filter &lt;array constant type&gt; &lt;array constant&gt;
6047</pre>
6048
6049<h5>Overview:</h5>
6050<p>The '<tt>landingpad</tt>' instruction is used by
6051   <a href="ExceptionHandling.html#overview">LLVM's exception handling
6052   system</a> to specify that a basic block is a landing pad &mdash; one where
6053   the exception lands, and corresponds to the code found in the
6054   <i><tt>catch</tt></i> portion of a <i><tt>try/catch</tt></i> sequence. It
6055   defines values supplied by the personality function (<tt>pers_fn</tt>) upon
6056   re-entry to the function. The <tt>resultval</tt> has the
6057   type <tt>somety</tt>.</p>
6058
6059<h5>Arguments:</h5>
6060<p>This instruction takes a <tt>pers_fn</tt> value. This is the personality
6061   function associated with the unwinding mechanism. The optional
6062   <tt>cleanup</tt> flag indicates that the landing pad block is a cleanup.</p>
6063
6064<p>A <tt>clause</tt> begins with the clause type &mdash; <tt>catch</tt>
6065   or <tt>filter</tt> &mdash; and contains the global variable representing the
6066   "type" that may be caught or filtered respectively. Unlike the
6067   <tt>catch</tt> clause, the <tt>filter</tt> clause takes an array constant as
6068   its argument. Use "<tt>[0 x i8**] undef</tt>" for a filter which cannot
6069   throw. The '<tt>landingpad</tt>' instruction must contain <em>at least</em>
6070   one <tt>clause</tt> or the <tt>cleanup</tt> flag.</p>
6071
6072<h5>Semantics:</h5>
6073<p>The '<tt>landingpad</tt>' instruction defines the values which are set by the
6074   personality function (<tt>pers_fn</tt>) upon re-entry to the function, and
6075   therefore the "result type" of the <tt>landingpad</tt> instruction. As with
6076   calling conventions, how the personality function results are represented in
6077   LLVM IR is target specific.</p>
6078
6079<p>The clauses are applied in order from top to bottom. If two
6080   <tt>landingpad</tt> instructions are merged together through inlining, the
6081   clauses from the calling function are appended to the list of clauses.</p>
6082
6083<p>The <tt>landingpad</tt> instruction has several restrictions:</p>
6084
6085<ul>
6086  <li>A landing pad block is a basic block which is the unwind destination of an
6087      '<tt>invoke</tt>' instruction.</li>
6088  <li>A landing pad block must have a '<tt>landingpad</tt>' instruction as its
6089      first non-PHI instruction.</li>
6090  <li>There can be only one '<tt>landingpad</tt>' instruction within the landing
6091      pad block.</li>
6092  <li>A basic block that is not a landing pad block may not include a
6093      '<tt>landingpad</tt>' instruction.</li>
6094  <li>All '<tt>landingpad</tt>' instructions in a function must have the same
6095      personality function.</li>
6096</ul>
6097
6098<h5>Example:</h5>
6099<pre>
6100  ;; A landing pad which can catch an integer.
6101  %res = landingpad { i8*, i32 } personality i32 (...)* @__gxx_personality_v0
6102           catch i8** @_ZTIi
6103  ;; A landing pad that is a cleanup.
6104  %res = landingpad { i8*, i32 } personality i32 (...)* @__gxx_personality_v0
6105           cleanup
6106  ;; A landing pad which can catch an integer and can only throw a double.
6107  %res = landingpad { i8*, i32 } personality i32 (...)* @__gxx_personality_v0
6108           catch i8** @_ZTIi
6109           filter [1 x i8**] [@_ZTId]
6110</pre>
6111
6112</div>
6113
6114</div>
6115
6116</div>
6117
6118<!-- *********************************************************************** -->
6119<h2><a name="intrinsics">Intrinsic Functions</a></h2>
6120<!-- *********************************************************************** -->
6121
6122<div>
6123
6124<p>LLVM supports the notion of an "intrinsic function".  These functions have
6125   well known names and semantics and are required to follow certain
6126   restrictions.  Overall, these intrinsics represent an extension mechanism for
6127   the LLVM language that does not require changing all of the transformations
6128   in LLVM when adding to the language (or the bitcode reader/writer, the
6129   parser, etc...).</p>
6130
6131<p>Intrinsic function names must all start with an "<tt>llvm.</tt>" prefix. This
6132   prefix is reserved in LLVM for intrinsic names; thus, function names may not
6133   begin with this prefix.  Intrinsic functions must always be external
6134   functions: you cannot define the body of intrinsic functions.  Intrinsic
6135   functions may only be used in call or invoke instructions: it is illegal to
6136   take the address of an intrinsic function.  Additionally, because intrinsic
6137   functions are part of the LLVM language, it is required if any are added that
6138   they be documented here.</p>
6139
6140<p>Some intrinsic functions can be overloaded, i.e., the intrinsic represents a
6141   family of functions that perform the same operation but on different data
6142   types. Because LLVM can represent over 8 million different integer types,
6143   overloading is used commonly to allow an intrinsic function to operate on any
6144   integer type. One or more of the argument types or the result type can be
6145   overloaded to accept any integer type. Argument types may also be defined as
6146   exactly matching a previous argument's type or the result type. This allows
6147   an intrinsic function which accepts multiple arguments, but needs all of them
6148   to be of the same type, to only be overloaded with respect to a single
6149   argument or the result.</p>
6150
6151<p>Overloaded intrinsics will have the names of its overloaded argument types
6152   encoded into its function name, each preceded by a period. Only those types
6153   which are overloaded result in a name suffix. Arguments whose type is matched
6154   against another type do not. For example, the <tt>llvm.ctpop</tt> function
6155   can take an integer of any width and returns an integer of exactly the same
6156   integer width. This leads to a family of functions such as
6157   <tt>i8 @llvm.ctpop.i8(i8 %val)</tt> and <tt>i29 @llvm.ctpop.i29(i29
6158   %val)</tt>.  Only one type, the return type, is overloaded, and only one type
6159   suffix is required. Because the argument's type is matched against the return
6160   type, it does not require its own name suffix.</p>
6161
6162<p>To learn how to add an intrinsic function, please see the
6163   <a href="ExtendingLLVM.html">Extending LLVM Guide</a>.</p>
6164
6165<!-- ======================================================================= -->
6166<h3>
6167  <a name="int_varargs">Variable Argument Handling Intrinsics</a>
6168</h3>
6169
6170<div>
6171
6172<p>Variable argument support is defined in LLVM with
6173   the <a href="#i_va_arg"><tt>va_arg</tt></a> instruction and these three
6174   intrinsic functions.  These functions are related to the similarly named
6175   macros defined in the <tt>&lt;stdarg.h&gt;</tt> header file.</p>
6176
6177<p>All of these functions operate on arguments that use a target-specific value
6178   type "<tt>va_list</tt>".  The LLVM assembly language reference manual does
6179   not define what this type is, so all transformations should be prepared to
6180   handle these functions regardless of the type used.</p>
6181
6182<p>This example shows how the <a href="#i_va_arg"><tt>va_arg</tt></a>
6183   instruction and the variable argument handling intrinsic functions are
6184   used.</p>
6185
6186<pre class="doc_code">
6187define i32 @test(i32 %X, ...) {
6188  ; Initialize variable argument processing
6189  %ap = alloca i8*
6190  %ap2 = bitcast i8** %ap to i8*
6191  call void @llvm.va_start(i8* %ap2)
6192
6193  ; Read a single integer argument
6194  %tmp = va_arg i8** %ap, i32
6195
6196  ; Demonstrate usage of llvm.va_copy and llvm.va_end
6197  %aq = alloca i8*
6198  %aq2 = bitcast i8** %aq to i8*
6199  call void @llvm.va_copy(i8* %aq2, i8* %ap2)
6200  call void @llvm.va_end(i8* %aq2)
6201
6202  ; Stop processing of arguments.
6203  call void @llvm.va_end(i8* %ap2)
6204  ret i32 %tmp
6205}
6206
6207declare void @llvm.va_start(i8*)
6208declare void @llvm.va_copy(i8*, i8*)
6209declare void @llvm.va_end(i8*)
6210</pre>
6211
6212<!-- _______________________________________________________________________ -->
6213<h4>
6214  <a name="int_va_start">'<tt>llvm.va_start</tt>' Intrinsic</a>
6215</h4>
6216
6217
6218<div>
6219
6220<h5>Syntax:</h5>
6221<pre>
6222  declare void %llvm.va_start(i8* &lt;arglist&gt;)
6223</pre>
6224
6225<h5>Overview:</h5>
6226<p>The '<tt>llvm.va_start</tt>' intrinsic initializes <tt>*&lt;arglist&gt;</tt>
6227   for subsequent use by <tt><a href="#i_va_arg">va_arg</a></tt>.</p>
6228
6229<h5>Arguments:</h5>
6230<p>The argument is a pointer to a <tt>va_list</tt> element to initialize.</p>
6231
6232<h5>Semantics:</h5>
6233<p>The '<tt>llvm.va_start</tt>' intrinsic works just like the <tt>va_start</tt>
6234   macro available in C.  In a target-dependent way, it initializes
6235   the <tt>va_list</tt> element to which the argument points, so that the next
6236   call to <tt>va_arg</tt> will produce the first variable argument passed to
6237   the function.  Unlike the C <tt>va_start</tt> macro, this intrinsic does not
6238   need to know the last argument of the function as the compiler can figure
6239   that out.</p>
6240
6241</div>
6242
6243<!-- _______________________________________________________________________ -->
6244<h4>
6245 <a name="int_va_end">'<tt>llvm.va_end</tt>' Intrinsic</a>
6246</h4>
6247
6248<div>
6249
6250<h5>Syntax:</h5>
6251<pre>
6252  declare void @llvm.va_end(i8* &lt;arglist&gt;)
6253</pre>
6254
6255<h5>Overview:</h5>
6256<p>The '<tt>llvm.va_end</tt>' intrinsic destroys <tt>*&lt;arglist&gt;</tt>,
6257   which has been initialized previously
6258   with <tt><a href="#int_va_start">llvm.va_start</a></tt>
6259   or <tt><a href="#i_va_copy">llvm.va_copy</a></tt>.</p>
6260
6261<h5>Arguments:</h5>
6262<p>The argument is a pointer to a <tt>va_list</tt> to destroy.</p>
6263
6264<h5>Semantics:</h5>
6265<p>The '<tt>llvm.va_end</tt>' intrinsic works just like the <tt>va_end</tt>
6266   macro available in C.  In a target-dependent way, it destroys
6267   the <tt>va_list</tt> element to which the argument points.  Calls
6268   to <a href="#int_va_start"><tt>llvm.va_start</tt></a>
6269   and <a href="#int_va_copy"> <tt>llvm.va_copy</tt></a> must be matched exactly
6270   with calls to <tt>llvm.va_end</tt>.</p>
6271
6272</div>
6273
6274<!-- _______________________________________________________________________ -->
6275<h4>
6276  <a name="int_va_copy">'<tt>llvm.va_copy</tt>' Intrinsic</a>
6277</h4>
6278
6279<div>
6280
6281<h5>Syntax:</h5>
6282<pre>
6283  declare void @llvm.va_copy(i8* &lt;destarglist&gt;, i8* &lt;srcarglist&gt;)
6284</pre>
6285
6286<h5>Overview:</h5>
6287<p>The '<tt>llvm.va_copy</tt>' intrinsic copies the current argument position
6288   from the source argument list to the destination argument list.</p>
6289
6290<h5>Arguments:</h5>
6291<p>The first argument is a pointer to a <tt>va_list</tt> element to initialize.
6292   The second argument is a pointer to a <tt>va_list</tt> element to copy
6293   from.</p>
6294
6295<h5>Semantics:</h5>
6296<p>The '<tt>llvm.va_copy</tt>' intrinsic works just like the <tt>va_copy</tt>
6297   macro available in C.  In a target-dependent way, it copies the
6298   source <tt>va_list</tt> element into the destination <tt>va_list</tt>
6299   element.  This intrinsic is necessary because
6300   the <tt><a href="#int_va_start"> llvm.va_start</a></tt> intrinsic may be
6301   arbitrarily complex and require, for example, memory allocation.</p>
6302
6303</div>
6304
6305</div>
6306
6307</div>
6308
6309<!-- ======================================================================= -->
6310<h3>
6311  <a name="int_gc">Accurate Garbage Collection Intrinsics</a>
6312</h3>
6313
6314<div>
6315
6316<p>LLVM support for <a href="GarbageCollection.html">Accurate Garbage
6317Collection</a> (GC) requires the implementation and generation of these
6318intrinsics. These intrinsics allow identification of <a href="#int_gcroot">GC
6319roots on the stack</a>, as well as garbage collector implementations that
6320require <a href="#int_gcread">read</a> and <a href="#int_gcwrite">write</a>
6321barriers.  Front-ends for type-safe garbage collected languages should generate
6322these intrinsics to make use of the LLVM garbage collectors.  For more details,
6323see <a href="GarbageCollection.html">Accurate Garbage Collection with
6324LLVM</a>.</p>
6325
6326<p>The garbage collection intrinsics only operate on objects in the generic
6327   address space (address space zero).</p>
6328
6329<!-- _______________________________________________________________________ -->
6330<h4>
6331  <a name="int_gcroot">'<tt>llvm.gcroot</tt>' Intrinsic</a>
6332</h4>
6333
6334<div>
6335
6336<h5>Syntax:</h5>
6337<pre>
6338  declare void @llvm.gcroot(i8** %ptrloc, i8* %metadata)
6339</pre>
6340
6341<h5>Overview:</h5>
6342<p>The '<tt>llvm.gcroot</tt>' intrinsic declares the existence of a GC root to
6343   the code generator, and allows some metadata to be associated with it.</p>
6344
6345<h5>Arguments:</h5>
6346<p>The first argument specifies the address of a stack object that contains the
6347   root pointer.  The second pointer (which must be either a constant or a
6348   global value address) contains the meta-data to be associated with the
6349   root.</p>
6350
6351<h5>Semantics:</h5>
6352<p>At runtime, a call to this intrinsic stores a null pointer into the "ptrloc"
6353   location.  At compile-time, the code generator generates information to allow
6354   the runtime to find the pointer at GC safe points. The '<tt>llvm.gcroot</tt>'
6355   intrinsic may only be used in a function which <a href="#gc">specifies a GC
6356   algorithm</a>.</p>
6357
6358</div>
6359
6360<!-- _______________________________________________________________________ -->
6361<h4>
6362  <a name="int_gcread">'<tt>llvm.gcread</tt>' Intrinsic</a>
6363</h4>
6364
6365<div>
6366
6367<h5>Syntax:</h5>
6368<pre>
6369  declare i8* @llvm.gcread(i8* %ObjPtr, i8** %Ptr)
6370</pre>
6371
6372<h5>Overview:</h5>
6373<p>The '<tt>llvm.gcread</tt>' intrinsic identifies reads of references from heap
6374   locations, allowing garbage collector implementations that require read
6375   barriers.</p>
6376
6377<h5>Arguments:</h5>
6378<p>The second argument is the address to read from, which should be an address
6379   allocated from the garbage collector.  The first object is a pointer to the
6380   start of the referenced object, if needed by the language runtime (otherwise
6381   null).</p>
6382
6383<h5>Semantics:</h5>
6384<p>The '<tt>llvm.gcread</tt>' intrinsic has the same semantics as a load
6385   instruction, but may be replaced with substantially more complex code by the
6386   garbage collector runtime, as needed. The '<tt>llvm.gcread</tt>' intrinsic
6387   may only be used in a function which <a href="#gc">specifies a GC
6388   algorithm</a>.</p>
6389
6390</div>
6391
6392<!-- _______________________________________________________________________ -->
6393<h4>
6394  <a name="int_gcwrite">'<tt>llvm.gcwrite</tt>' Intrinsic</a>
6395</h4>
6396
6397<div>
6398
6399<h5>Syntax:</h5>
6400<pre>
6401  declare void @llvm.gcwrite(i8* %P1, i8* %Obj, i8** %P2)
6402</pre>
6403
6404<h5>Overview:</h5>
6405<p>The '<tt>llvm.gcwrite</tt>' intrinsic identifies writes of references to heap
6406   locations, allowing garbage collector implementations that require write
6407   barriers (such as generational or reference counting collectors).</p>
6408
6409<h5>Arguments:</h5>
6410<p>The first argument is the reference to store, the second is the start of the
6411   object to store it to, and the third is the address of the field of Obj to
6412   store to.  If the runtime does not require a pointer to the object, Obj may
6413   be null.</p>
6414
6415<h5>Semantics:</h5>
6416<p>The '<tt>llvm.gcwrite</tt>' intrinsic has the same semantics as a store
6417   instruction, but may be replaced with substantially more complex code by the
6418   garbage collector runtime, as needed. The '<tt>llvm.gcwrite</tt>' intrinsic
6419   may only be used in a function which <a href="#gc">specifies a GC
6420   algorithm</a>.</p>
6421
6422</div>
6423
6424</div>
6425
6426<!-- ======================================================================= -->
6427<h3>
6428  <a name="int_codegen">Code Generator Intrinsics</a>
6429</h3>
6430
6431<div>
6432
6433<p>These intrinsics are provided by LLVM to expose special features that may
6434   only be implemented with code generator support.</p>
6435
6436<!-- _______________________________________________________________________ -->
6437<h4>
6438  <a name="int_returnaddress">'<tt>llvm.returnaddress</tt>' Intrinsic</a>
6439</h4>
6440
6441<div>
6442
6443<h5>Syntax:</h5>
6444<pre>
6445  declare i8  *@llvm.returnaddress(i32 &lt;level&gt;)
6446</pre>
6447
6448<h5>Overview:</h5>
6449<p>The '<tt>llvm.returnaddress</tt>' intrinsic attempts to compute a
6450   target-specific value indicating the return address of the current function
6451   or one of its callers.</p>
6452
6453<h5>Arguments:</h5>
6454<p>The argument to this intrinsic indicates which function to return the address
6455   for.  Zero indicates the calling function, one indicates its caller, etc.
6456   The argument is <b>required</b> to be a constant integer value.</p>
6457
6458<h5>Semantics:</h5>
6459<p>The '<tt>llvm.returnaddress</tt>' intrinsic either returns a pointer
6460   indicating the return address of the specified call frame, or zero if it
6461   cannot be identified.  The value returned by this intrinsic is likely to be
6462   incorrect or 0 for arguments other than zero, so it should only be used for
6463   debugging purposes.</p>
6464
6465<p>Note that calling this intrinsic does not prevent function inlining or other
6466   aggressive transformations, so the value returned may not be that of the
6467   obvious source-language caller.</p>
6468
6469</div>
6470
6471<!-- _______________________________________________________________________ -->
6472<h4>
6473  <a name="int_frameaddress">'<tt>llvm.frameaddress</tt>' Intrinsic</a>
6474</h4>
6475
6476<div>
6477
6478<h5>Syntax:</h5>
6479<pre>
6480  declare i8* @llvm.frameaddress(i32 &lt;level&gt;)
6481</pre>
6482
6483<h5>Overview:</h5>
6484<p>The '<tt>llvm.frameaddress</tt>' intrinsic attempts to return the
6485   target-specific frame pointer value for the specified stack frame.</p>
6486
6487<h5>Arguments:</h5>
6488<p>The argument to this intrinsic indicates which function to return the frame
6489   pointer for.  Zero indicates the calling function, one indicates its caller,
6490   etc.  The argument is <b>required</b> to be a constant integer value.</p>
6491
6492<h5>Semantics:</h5>
6493<p>The '<tt>llvm.frameaddress</tt>' intrinsic either returns a pointer
6494   indicating the frame address of the specified call frame, or zero if it
6495   cannot be identified.  The value returned by this intrinsic is likely to be
6496   incorrect or 0 for arguments other than zero, so it should only be used for
6497   debugging purposes.</p>
6498
6499<p>Note that calling this intrinsic does not prevent function inlining or other
6500   aggressive transformations, so the value returned may not be that of the
6501   obvious source-language caller.</p>
6502
6503</div>
6504
6505<!-- _______________________________________________________________________ -->
6506<h4>
6507  <a name="int_stacksave">'<tt>llvm.stacksave</tt>' Intrinsic</a>
6508</h4>
6509
6510<div>
6511
6512<h5>Syntax:</h5>
6513<pre>
6514  declare i8* @llvm.stacksave()
6515</pre>
6516
6517<h5>Overview:</h5>
6518<p>The '<tt>llvm.stacksave</tt>' intrinsic is used to remember the current state
6519   of the function stack, for use
6520   with <a href="#int_stackrestore"> <tt>llvm.stackrestore</tt></a>.  This is
6521   useful for implementing language features like scoped automatic variable
6522   sized arrays in C99.</p>
6523
6524<h5>Semantics:</h5>
6525<p>This intrinsic returns a opaque pointer value that can be passed
6526   to <a href="#int_stackrestore"><tt>llvm.stackrestore</tt></a>.  When
6527   an <tt>llvm.stackrestore</tt> intrinsic is executed with a value saved
6528   from <tt>llvm.stacksave</tt>, it effectively restores the state of the stack
6529   to the state it was in when the <tt>llvm.stacksave</tt> intrinsic executed.
6530   In practice, this pops any <a href="#i_alloca">alloca</a> blocks from the
6531   stack that were allocated after the <tt>llvm.stacksave</tt> was executed.</p>
6532
6533</div>
6534
6535<!-- _______________________________________________________________________ -->
6536<h4>
6537  <a name="int_stackrestore">'<tt>llvm.stackrestore</tt>' Intrinsic</a>
6538</h4>
6539
6540<div>
6541
6542<h5>Syntax:</h5>
6543<pre>
6544  declare void @llvm.stackrestore(i8* %ptr)
6545</pre>
6546
6547<h5>Overview:</h5>
6548<p>The '<tt>llvm.stackrestore</tt>' intrinsic is used to restore the state of
6549   the function stack to the state it was in when the
6550   corresponding <a href="#int_stacksave"><tt>llvm.stacksave</tt></a> intrinsic
6551   executed.  This is useful for implementing language features like scoped
6552   automatic variable sized arrays in C99.</p>
6553
6554<h5>Semantics:</h5>
6555<p>See the description
6556   for <a href="#int_stacksave"><tt>llvm.stacksave</tt></a>.</p>
6557
6558</div>
6559
6560<!-- _______________________________________________________________________ -->
6561<h4>
6562  <a name="int_prefetch">'<tt>llvm.prefetch</tt>' Intrinsic</a>
6563</h4>
6564
6565<div>
6566
6567<h5>Syntax:</h5>
6568<pre>
6569  declare void @llvm.prefetch(i8* &lt;address&gt;, i32 &lt;rw&gt;, i32 &lt;locality&gt;, i32 &lt;cache type&gt;)
6570</pre>
6571
6572<h5>Overview:</h5>
6573<p>The '<tt>llvm.prefetch</tt>' intrinsic is a hint to the code generator to
6574   insert a prefetch instruction if supported; otherwise, it is a noop.
6575   Prefetches have no effect on the behavior of the program but can change its
6576   performance characteristics.</p>
6577
6578<h5>Arguments:</h5>
6579<p><tt>address</tt> is the address to be prefetched, <tt>rw</tt> is the
6580   specifier determining if the fetch should be for a read (0) or write (1),
6581   and <tt>locality</tt> is a temporal locality specifier ranging from (0) - no
6582   locality, to (3) - extremely local keep in cache. The <tt>cache type</tt>
6583   specifies whether the prefetch is performed on the data (1) or instruction (0)
6584   cache. The <tt>rw</tt>, <tt>locality</tt> and <tt>cache type</tt> arguments
6585   must be constant integers.</p>
6586
6587<h5>Semantics:</h5>
6588<p>This intrinsic does not modify the behavior of the program.  In particular,
6589   prefetches cannot trap and do not produce a value.  On targets that support
6590   this intrinsic, the prefetch can provide hints to the processor cache for
6591   better performance.</p>
6592
6593</div>
6594
6595<!-- _______________________________________________________________________ -->
6596<h4>
6597  <a name="int_pcmarker">'<tt>llvm.pcmarker</tt>' Intrinsic</a>
6598</h4>
6599
6600<div>
6601
6602<h5>Syntax:</h5>
6603<pre>
6604  declare void @llvm.pcmarker(i32 &lt;id&gt;)
6605</pre>
6606
6607<h5>Overview:</h5>
6608<p>The '<tt>llvm.pcmarker</tt>' intrinsic is a method to export a Program
6609   Counter (PC) in a region of code to simulators and other tools.  The method
6610   is target specific, but it is expected that the marker will use exported
6611   symbols to transmit the PC of the marker.  The marker makes no guarantees
6612   that it will remain with any specific instruction after optimizations.  It is
6613   possible that the presence of a marker will inhibit optimizations.  The
6614   intended use is to be inserted after optimizations to allow correlations of
6615   simulation runs.</p>
6616
6617<h5>Arguments:</h5>
6618<p><tt>id</tt> is a numerical id identifying the marker.</p>
6619
6620<h5>Semantics:</h5>
6621<p>This intrinsic does not modify the behavior of the program.  Backends that do
6622   not support this intrinsic may ignore it.</p>
6623
6624</div>
6625
6626<!-- _______________________________________________________________________ -->
6627<h4>
6628  <a name="int_readcyclecounter">'<tt>llvm.readcyclecounter</tt>' Intrinsic</a>
6629</h4>
6630
6631<div>
6632
6633<h5>Syntax:</h5>
6634<pre>
6635  declare i64 @llvm.readcyclecounter()
6636</pre>
6637
6638<h5>Overview:</h5>
6639<p>The '<tt>llvm.readcyclecounter</tt>' intrinsic provides access to the cycle
6640   counter register (or similar low latency, high accuracy clocks) on those
6641   targets that support it.  On X86, it should map to RDTSC.  On Alpha, it
6642   should map to RPCC.  As the backing counters overflow quickly (on the order
6643   of 9 seconds on alpha), this should only be used for small timings.</p>
6644
6645<h5>Semantics:</h5>
6646<p>When directly supported, reading the cycle counter should not modify any
6647   memory.  Implementations are allowed to either return a application specific
6648   value or a system wide value.  On backends without support, this is lowered
6649   to a constant 0.</p>
6650
6651</div>
6652
6653</div>
6654
6655<!-- ======================================================================= -->
6656<h3>
6657  <a name="int_libc">Standard C Library Intrinsics</a>
6658</h3>
6659
6660<div>
6661
6662<p>LLVM provides intrinsics for a few important standard C library functions.
6663   These intrinsics allow source-language front-ends to pass information about
6664   the alignment of the pointer arguments to the code generator, providing
6665   opportunity for more efficient code generation.</p>
6666
6667<!-- _______________________________________________________________________ -->
6668<h4>
6669  <a name="int_memcpy">'<tt>llvm.memcpy</tt>' Intrinsic</a>
6670</h4>
6671
6672<div>
6673
6674<h5>Syntax:</h5>
6675<p>This is an overloaded intrinsic. You can use <tt>llvm.memcpy</tt> on any
6676   integer bit width and for different address spaces. Not all targets support
6677   all bit widths however.</p>
6678
6679<pre>
6680  declare void @llvm.memcpy.p0i8.p0i8.i32(i8* &lt;dest&gt;, i8* &lt;src&gt;,
6681                                          i32 &lt;len&gt;, i32 &lt;align&gt;, i1 &lt;isvolatile&gt;)
6682  declare void @llvm.memcpy.p0i8.p0i8.i64(i8* &lt;dest&gt;, i8* &lt;src&gt;,
6683                                          i64 &lt;len&gt;, i32 &lt;align&gt;, i1 &lt;isvolatile&gt;)
6684</pre>
6685
6686<h5>Overview:</h5>
6687<p>The '<tt>llvm.memcpy.*</tt>' intrinsics copy a block of memory from the
6688   source location to the destination location.</p>
6689
6690<p>Note that, unlike the standard libc function, the <tt>llvm.memcpy.*</tt>
6691   intrinsics do not return a value, takes extra alignment/isvolatile arguments
6692   and the pointers can be in specified address spaces.</p>
6693
6694<h5>Arguments:</h5>
6695
6696<p>The first argument is a pointer to the destination, the second is a pointer
6697   to the source.  The third argument is an integer argument specifying the
6698   number of bytes to copy, the fourth argument is the alignment of the
6699   source and destination locations, and the fifth is a boolean indicating a
6700   volatile access.</p>
6701
6702<p>If the call to this intrinsic has an alignment value that is not 0 or 1,
6703   then the caller guarantees that both the source and destination pointers are
6704   aligned to that boundary.</p>
6705
6706<p>If the <tt>isvolatile</tt> parameter is <tt>true</tt>, the
6707   <tt>llvm.memcpy</tt> call is a <a href="#volatile">volatile operation</a>.
6708   The detailed access behavior is not very cleanly specified and it is unwise
6709   to depend on it.</p>
6710
6711<h5>Semantics:</h5>
6712
6713<p>The '<tt>llvm.memcpy.*</tt>' intrinsics copy a block of memory from the
6714   source location to the destination location, which are not allowed to
6715   overlap.  It copies "len" bytes of memory over.  If the argument is known to
6716   be aligned to some boundary, this can be specified as the fourth argument,
6717   otherwise it should be set to 0 or 1.</p>
6718
6719</div>
6720
6721<!-- _______________________________________________________________________ -->
6722<h4>
6723  <a name="int_memmove">'<tt>llvm.memmove</tt>' Intrinsic</a>
6724</h4>
6725
6726<div>
6727
6728<h5>Syntax:</h5>
6729<p>This is an overloaded intrinsic. You can use llvm.memmove on any integer bit
6730   width and for different address space. Not all targets support all bit
6731   widths however.</p>
6732
6733<pre>
6734  declare void @llvm.memmove.p0i8.p0i8.i32(i8* &lt;dest&gt;, i8* &lt;src&gt;,
6735                                           i32 &lt;len&gt;, i32 &lt;align&gt;, i1 &lt;isvolatile&gt;)
6736  declare void @llvm.memmove.p0i8.p0i8.i64(i8* &lt;dest&gt;, i8* &lt;src&gt;,
6737                                           i64 &lt;len&gt;, i32 &lt;align&gt;, i1 &lt;isvolatile&gt;)
6738</pre>
6739
6740<h5>Overview:</h5>
6741<p>The '<tt>llvm.memmove.*</tt>' intrinsics move a block of memory from the
6742   source location to the destination location. It is similar to the
6743   '<tt>llvm.memcpy</tt>' intrinsic but allows the two memory locations to
6744   overlap.</p>
6745
6746<p>Note that, unlike the standard libc function, the <tt>llvm.memmove.*</tt>
6747   intrinsics do not return a value, takes extra alignment/isvolatile arguments
6748   and the pointers can be in specified address spaces.</p>
6749
6750<h5>Arguments:</h5>
6751
6752<p>The first argument is a pointer to the destination, the second is a pointer
6753   to the source.  The third argument is an integer argument specifying the
6754   number of bytes to copy, the fourth argument is the alignment of the
6755   source and destination locations, and the fifth is a boolean indicating a
6756   volatile access.</p>
6757
6758<p>If the call to this intrinsic has an alignment value that is not 0 or 1,
6759   then the caller guarantees that the source and destination pointers are
6760   aligned to that boundary.</p>
6761
6762<p>If the <tt>isvolatile</tt> parameter is <tt>true</tt>, the
6763   <tt>llvm.memmove</tt> call is a <a href="#volatile">volatile operation</a>.
6764   The detailed access behavior is not very cleanly specified and it is unwise
6765   to depend on it.</p>
6766
6767<h5>Semantics:</h5>
6768
6769<p>The '<tt>llvm.memmove.*</tt>' intrinsics copy a block of memory from the
6770   source location to the destination location, which may overlap.  It copies
6771   "len" bytes of memory over.  If the argument is known to be aligned to some
6772   boundary, this can be specified as the fourth argument, otherwise it should
6773   be set to 0 or 1.</p>
6774
6775</div>
6776
6777<!-- _______________________________________________________________________ -->
6778<h4>
6779  <a name="int_memset">'<tt>llvm.memset.*</tt>' Intrinsics</a>
6780</h4>
6781
6782<div>
6783
6784<h5>Syntax:</h5>
6785<p>This is an overloaded intrinsic. You can use llvm.memset on any integer bit
6786   width and for different address spaces. However, not all targets support all
6787   bit widths.</p>
6788
6789<pre>
6790  declare void @llvm.memset.p0i8.i32(i8* &lt;dest&gt;, i8 &lt;val&gt;,
6791                                     i32 &lt;len&gt;, i32 &lt;align&gt;, i1 &lt;isvolatile&gt;)
6792  declare void @llvm.memset.p0i8.i64(i8* &lt;dest&gt;, i8 &lt;val&gt;,
6793                                     i64 &lt;len&gt;, i32 &lt;align&gt;, i1 &lt;isvolatile&gt;)
6794</pre>
6795
6796<h5>Overview:</h5>
6797<p>The '<tt>llvm.memset.*</tt>' intrinsics fill a block of memory with a
6798   particular byte value.</p>
6799
6800<p>Note that, unlike the standard libc function, the <tt>llvm.memset</tt>
6801   intrinsic does not return a value and takes extra alignment/volatile
6802   arguments.  Also, the destination can be in an arbitrary address space.</p>
6803
6804<h5>Arguments:</h5>
6805<p>The first argument is a pointer to the destination to fill, the second is the
6806   byte value with which to fill it, the third argument is an integer argument
6807   specifying the number of bytes to fill, and the fourth argument is the known
6808   alignment of the destination location.</p>
6809
6810<p>If the call to this intrinsic has an alignment value that is not 0 or 1,
6811   then the caller guarantees that the destination pointer is aligned to that
6812   boundary.</p>
6813
6814<p>If the <tt>isvolatile</tt> parameter is <tt>true</tt>, the
6815   <tt>llvm.memset</tt> call is a <a href="#volatile">volatile operation</a>.
6816   The detailed access behavior is not very cleanly specified and it is unwise
6817   to depend on it.</p>
6818
6819<h5>Semantics:</h5>
6820<p>The '<tt>llvm.memset.*</tt>' intrinsics fill "len" bytes of memory starting
6821   at the destination location.  If the argument is known to be aligned to some
6822   boundary, this can be specified as the fourth argument, otherwise it should
6823   be set to 0 or 1.</p>
6824
6825</div>
6826
6827<!-- _______________________________________________________________________ -->
6828<h4>
6829  <a name="int_sqrt">'<tt>llvm.sqrt.*</tt>' Intrinsic</a>
6830</h4>
6831
6832<div>
6833
6834<h5>Syntax:</h5>
6835<p>This is an overloaded intrinsic. You can use <tt>llvm.sqrt</tt> on any
6836   floating point or vector of floating point type. Not all targets support all
6837   types however.</p>
6838
6839<pre>
6840  declare float     @llvm.sqrt.f32(float %Val)
6841  declare double    @llvm.sqrt.f64(double %Val)
6842  declare x86_fp80  @llvm.sqrt.f80(x86_fp80 %Val)
6843  declare fp128     @llvm.sqrt.f128(fp128 %Val)
6844  declare ppc_fp128 @llvm.sqrt.ppcf128(ppc_fp128 %Val)
6845</pre>
6846
6847<h5>Overview:</h5>
6848<p>The '<tt>llvm.sqrt</tt>' intrinsics return the sqrt of the specified operand,
6849   returning the same value as the libm '<tt>sqrt</tt>' functions would.
6850   Unlike <tt>sqrt</tt> in libm, however, <tt>llvm.sqrt</tt> has undefined
6851   behavior for negative numbers other than -0.0 (which allows for better
6852   optimization, because there is no need to worry about errno being
6853   set).  <tt>llvm.sqrt(-0.0)</tt> is defined to return -0.0 like IEEE sqrt.</p>
6854
6855<h5>Arguments:</h5>
6856<p>The argument and return value are floating point numbers of the same
6857   type.</p>
6858
6859<h5>Semantics:</h5>
6860<p>This function returns the sqrt of the specified operand if it is a
6861   nonnegative floating point number.</p>
6862
6863</div>
6864
6865<!-- _______________________________________________________________________ -->
6866<h4>
6867  <a name="int_powi">'<tt>llvm.powi.*</tt>' Intrinsic</a>
6868</h4>
6869
6870<div>
6871
6872<h5>Syntax:</h5>
6873<p>This is an overloaded intrinsic. You can use <tt>llvm.powi</tt> on any
6874   floating point or vector of floating point type. Not all targets support all
6875   types however.</p>
6876
6877<pre>
6878  declare float     @llvm.powi.f32(float  %Val, i32 %power)
6879  declare double    @llvm.powi.f64(double %Val, i32 %power)
6880  declare x86_fp80  @llvm.powi.f80(x86_fp80  %Val, i32 %power)
6881  declare fp128     @llvm.powi.f128(fp128 %Val, i32 %power)
6882  declare ppc_fp128 @llvm.powi.ppcf128(ppc_fp128  %Val, i32 %power)
6883</pre>
6884
6885<h5>Overview:</h5>
6886<p>The '<tt>llvm.powi.*</tt>' intrinsics return the first operand raised to the
6887   specified (positive or negative) power.  The order of evaluation of
6888   multiplications is not defined.  When a vector of floating point type is
6889   used, the second argument remains a scalar integer value.</p>
6890
6891<h5>Arguments:</h5>
6892<p>The second argument is an integer power, and the first is a value to raise to
6893   that power.</p>
6894
6895<h5>Semantics:</h5>
6896<p>This function returns the first value raised to the second power with an
6897   unspecified sequence of rounding operations.</p>
6898
6899</div>
6900
6901<!-- _______________________________________________________________________ -->
6902<h4>
6903  <a name="int_sin">'<tt>llvm.sin.*</tt>' Intrinsic</a>
6904</h4>
6905
6906<div>
6907
6908<h5>Syntax:</h5>
6909<p>This is an overloaded intrinsic. You can use <tt>llvm.sin</tt> on any
6910   floating point or vector of floating point type. Not all targets support all
6911   types however.</p>
6912
6913<pre>
6914  declare float     @llvm.sin.f32(float  %Val)
6915  declare double    @llvm.sin.f64(double %Val)
6916  declare x86_fp80  @llvm.sin.f80(x86_fp80  %Val)
6917  declare fp128     @llvm.sin.f128(fp128 %Val)
6918  declare ppc_fp128 @llvm.sin.ppcf128(ppc_fp128  %Val)
6919</pre>
6920
6921<h5>Overview:</h5>
6922<p>The '<tt>llvm.sin.*</tt>' intrinsics return the sine of the operand.</p>
6923
6924<h5>Arguments:</h5>
6925<p>The argument and return value are floating point numbers of the same
6926   type.</p>
6927
6928<h5>Semantics:</h5>
6929<p>This function returns the sine of the specified operand, returning the same
6930   values as the libm <tt>sin</tt> functions would, and handles error conditions
6931   in the same way.</p>
6932
6933</div>
6934
6935<!-- _______________________________________________________________________ -->
6936<h4>
6937  <a name="int_cos">'<tt>llvm.cos.*</tt>' Intrinsic</a>
6938</h4>
6939
6940<div>
6941
6942<h5>Syntax:</h5>
6943<p>This is an overloaded intrinsic. You can use <tt>llvm.cos</tt> on any
6944   floating point or vector of floating point type. Not all targets support all
6945   types however.</p>
6946
6947<pre>
6948  declare float     @llvm.cos.f32(float  %Val)
6949  declare double    @llvm.cos.f64(double %Val)
6950  declare x86_fp80  @llvm.cos.f80(x86_fp80  %Val)
6951  declare fp128     @llvm.cos.f128(fp128 %Val)
6952  declare ppc_fp128 @llvm.cos.ppcf128(ppc_fp128  %Val)
6953</pre>
6954
6955<h5>Overview:</h5>
6956<p>The '<tt>llvm.cos.*</tt>' intrinsics return the cosine of the operand.</p>
6957
6958<h5>Arguments:</h5>
6959<p>The argument and return value are floating point numbers of the same
6960   type.</p>
6961
6962<h5>Semantics:</h5>
6963<p>This function returns the cosine of the specified operand, returning the same
6964   values as the libm <tt>cos</tt> functions would, and handles error conditions
6965   in the same way.</p>
6966
6967</div>
6968
6969<!-- _______________________________________________________________________ -->
6970<h4>
6971  <a name="int_pow">'<tt>llvm.pow.*</tt>' Intrinsic</a>
6972</h4>
6973
6974<div>
6975
6976<h5>Syntax:</h5>
6977<p>This is an overloaded intrinsic. You can use <tt>llvm.pow</tt> on any
6978   floating point or vector of floating point type. Not all targets support all
6979   types however.</p>
6980
6981<pre>
6982  declare float     @llvm.pow.f32(float  %Val, float %Power)
6983  declare double    @llvm.pow.f64(double %Val, double %Power)
6984  declare x86_fp80  @llvm.pow.f80(x86_fp80  %Val, x86_fp80 %Power)
6985  declare fp128     @llvm.pow.f128(fp128 %Val, fp128 %Power)
6986  declare ppc_fp128 @llvm.pow.ppcf128(ppc_fp128  %Val, ppc_fp128 Power)
6987</pre>
6988
6989<h5>Overview:</h5>
6990<p>The '<tt>llvm.pow.*</tt>' intrinsics return the first operand raised to the
6991   specified (positive or negative) power.</p>
6992
6993<h5>Arguments:</h5>
6994<p>The second argument is a floating point power, and the first is a value to
6995   raise to that power.</p>
6996
6997<h5>Semantics:</h5>
6998<p>This function returns the first value raised to the second power, returning
6999   the same values as the libm <tt>pow</tt> functions would, and handles error
7000   conditions in the same way.</p>
7001
7002</div>
7003
7004</div>
7005
7006<!-- _______________________________________________________________________ -->
7007<h4>
7008  <a name="int_exp">'<tt>llvm.exp.*</tt>' Intrinsic</a>
7009</h4>
7010
7011<div>
7012
7013<h5>Syntax:</h5>
7014<p>This is an overloaded intrinsic. You can use <tt>llvm.exp</tt> on any
7015   floating point or vector of floating point type. Not all targets support all
7016   types however.</p>
7017
7018<pre>
7019  declare float     @llvm.exp.f32(float  %Val)
7020  declare double    @llvm.exp.f64(double %Val)
7021  declare x86_fp80  @llvm.exp.f80(x86_fp80  %Val)
7022  declare fp128     @llvm.exp.f128(fp128 %Val)
7023  declare ppc_fp128 @llvm.exp.ppcf128(ppc_fp128  %Val)
7024</pre>
7025
7026<h5>Overview:</h5>
7027<p>The '<tt>llvm.exp.*</tt>' intrinsics perform the exp function.</p>
7028
7029<h5>Arguments:</h5>
7030<p>The argument and return value are floating point numbers of the same
7031   type.</p>
7032
7033<h5>Semantics:</h5>
7034<p>This function returns the same values as the libm <tt>exp</tt> functions
7035   would, and handles error conditions in the same way.</p>
7036
7037</div>
7038
7039<!-- _______________________________________________________________________ -->
7040<h4>
7041  <a name="int_log">'<tt>llvm.log.*</tt>' Intrinsic</a>
7042</h4>
7043
7044<div>
7045
7046<h5>Syntax:</h5>
7047<p>This is an overloaded intrinsic. You can use <tt>llvm.log</tt> on any
7048   floating point or vector of floating point type. Not all targets support all
7049   types however.</p>
7050
7051<pre>
7052  declare float     @llvm.log.f32(float  %Val)
7053  declare double    @llvm.log.f64(double %Val)
7054  declare x86_fp80  @llvm.log.f80(x86_fp80  %Val)
7055  declare fp128     @llvm.log.f128(fp128 %Val)
7056  declare ppc_fp128 @llvm.log.ppcf128(ppc_fp128  %Val)
7057</pre>
7058
7059<h5>Overview:</h5>
7060<p>The '<tt>llvm.log.*</tt>' intrinsics perform the log function.</p>
7061
7062<h5>Arguments:</h5>
7063<p>The argument and return value are floating point numbers of the same
7064   type.</p>
7065
7066<h5>Semantics:</h5>
7067<p>This function returns the same values as the libm <tt>log</tt> functions
7068   would, and handles error conditions in the same way.</p>
7069
7070<h4>
7071  <a name="int_fma">'<tt>llvm.fma.*</tt>' Intrinsic</a>
7072</h4>
7073
7074<div>
7075
7076<h5>Syntax:</h5>
7077<p>This is an overloaded intrinsic. You can use <tt>llvm.fma</tt> on any
7078   floating point or vector of floating point type. Not all targets support all
7079   types however.</p>
7080
7081<pre>
7082  declare float     @llvm.fma.f32(float  %a, float  %b, float  %c)
7083  declare double    @llvm.fma.f64(double %a, double %b, double %c)
7084  declare x86_fp80  @llvm.fma.f80(x86_fp80 %a, x86_fp80 %b, x86_fp80 %c)
7085  declare fp128     @llvm.fma.f128(fp128 %a, fp128 %b, fp128 %c)
7086  declare ppc_fp128 @llvm.fma.ppcf128(ppc_fp128 %a, ppc_fp128 %b, ppc_fp128 %c)
7087</pre>
7088
7089<h5>Overview:</h5>
7090<p>The '<tt>llvm.fma.*</tt>' intrinsics perform the fused multiply-add
7091   operation.</p>
7092
7093<h5>Arguments:</h5>
7094<p>The argument and return value are floating point numbers of the same
7095   type.</p>
7096
7097<h5>Semantics:</h5>
7098<p>This function returns the same values as the libm <tt>fma</tt> functions
7099   would.</p>
7100
7101</div>
7102
7103<!-- ======================================================================= -->
7104<h3>
7105  <a name="int_manip">Bit Manipulation Intrinsics</a>
7106</h3>
7107
7108<div>
7109
7110<p>LLVM provides intrinsics for a few important bit manipulation operations.
7111   These allow efficient code generation for some algorithms.</p>
7112
7113<!-- _______________________________________________________________________ -->
7114<h4>
7115  <a name="int_bswap">'<tt>llvm.bswap.*</tt>' Intrinsics</a>
7116</h4>
7117
7118<div>
7119
7120<h5>Syntax:</h5>
7121<p>This is an overloaded intrinsic function. You can use bswap on any integer
7122   type that is an even number of bytes (i.e. BitWidth % 16 == 0).</p>
7123
7124<pre>
7125  declare i16 @llvm.bswap.i16(i16 &lt;id&gt;)
7126  declare i32 @llvm.bswap.i32(i32 &lt;id&gt;)
7127  declare i64 @llvm.bswap.i64(i64 &lt;id&gt;)
7128</pre>
7129
7130<h5>Overview:</h5>
7131<p>The '<tt>llvm.bswap</tt>' family of intrinsics is used to byte swap integer
7132   values with an even number of bytes (positive multiple of 16 bits).  These
7133   are useful for performing operations on data that is not in the target's
7134   native byte order.</p>
7135
7136<h5>Semantics:</h5>
7137<p>The <tt>llvm.bswap.i16</tt> intrinsic returns an i16 value that has the high
7138   and low byte of the input i16 swapped.  Similarly,
7139   the <tt>llvm.bswap.i32</tt> intrinsic returns an i32 value that has the four
7140   bytes of the input i32 swapped, so that if the input bytes are numbered 0, 1,
7141   2, 3 then the returned i32 will have its bytes in 3, 2, 1, 0 order.
7142   The <tt>llvm.bswap.i48</tt>, <tt>llvm.bswap.i64</tt> and other intrinsics
7143   extend this concept to additional even-byte lengths (6 bytes, 8 bytes and
7144   more, respectively).</p>
7145
7146</div>
7147
7148<!-- _______________________________________________________________________ -->
7149<h4>
7150  <a name="int_ctpop">'<tt>llvm.ctpop.*</tt>' Intrinsic</a>
7151</h4>
7152
7153<div>
7154
7155<h5>Syntax:</h5>
7156<p>This is an overloaded intrinsic. You can use llvm.ctpop on any integer bit
7157   width, or on any vector with integer elements. Not all targets support all
7158  bit widths or vector types, however.</p>
7159
7160<pre>
7161  declare i8 @llvm.ctpop.i8(i8  &lt;src&gt;)
7162  declare i16 @llvm.ctpop.i16(i16 &lt;src&gt;)
7163  declare i32 @llvm.ctpop.i32(i32 &lt;src&gt;)
7164  declare i64 @llvm.ctpop.i64(i64 &lt;src&gt;)
7165  declare i256 @llvm.ctpop.i256(i256 &lt;src&gt;)
7166  declare &lt;2 x i32&gt; @llvm.ctpop.v2i32(&lt;2 x i32&gt; &lt;src&gt;)
7167</pre>
7168
7169<h5>Overview:</h5>
7170<p>The '<tt>llvm.ctpop</tt>' family of intrinsics counts the number of bits set
7171   in a value.</p>
7172
7173<h5>Arguments:</h5>
7174<p>The only argument is the value to be counted.  The argument may be of any
7175   integer type, or a vector with integer elements.
7176   The return type must match the argument type.</p>
7177
7178<h5>Semantics:</h5>
7179<p>The '<tt>llvm.ctpop</tt>' intrinsic counts the 1's in a variable, or within each
7180   element of a vector.</p>
7181
7182</div>
7183
7184<!-- _______________________________________________________________________ -->
7185<h4>
7186  <a name="int_ctlz">'<tt>llvm.ctlz.*</tt>' Intrinsic</a>
7187</h4>
7188
7189<div>
7190
7191<h5>Syntax:</h5>
7192<p>This is an overloaded intrinsic. You can use <tt>llvm.ctlz</tt> on any
7193   integer bit width, or any vector whose elements are integers. Not all
7194   targets support all bit widths or vector types, however.</p>
7195
7196<pre>
7197  declare i8 @llvm.ctlz.i8 (i8  &lt;src&gt;)
7198  declare i16 @llvm.ctlz.i16(i16 &lt;src&gt;)
7199  declare i32 @llvm.ctlz.i32(i32 &lt;src&gt;)
7200  declare i64 @llvm.ctlz.i64(i64 &lt;src&gt;)
7201  declare i256 @llvm.ctlz.i256(i256 &lt;src&gt;)
7202  declare &lt;2 x i32&gt; @llvm.ctlz.v2i32(&lt;2 x i32&gt; &lt;src;gt)
7203</pre>
7204
7205<h5>Overview:</h5>
7206<p>The '<tt>llvm.ctlz</tt>' family of intrinsic functions counts the number of
7207   leading zeros in a variable.</p>
7208
7209<h5>Arguments:</h5>
7210<p>The only argument is the value to be counted.  The argument may be of any
7211   integer type, or any vector type with integer element type.
7212   The return type must match the argument type.</p>
7213
7214<h5>Semantics:</h5>
7215<p>The '<tt>llvm.ctlz</tt>' intrinsic counts the leading (most significant)
7216   zeros in a variable, or within each element of the vector if the operation
7217   is of vector type.  If the src == 0 then the result is the size in bits of
7218   the type of src. For example, <tt>llvm.ctlz(i32 2) = 30</tt>.</p>
7219
7220</div>
7221
7222<!-- _______________________________________________________________________ -->
7223<h4>
7224  <a name="int_cttz">'<tt>llvm.cttz.*</tt>' Intrinsic</a>
7225</h4>
7226
7227<div>
7228
7229<h5>Syntax:</h5>
7230<p>This is an overloaded intrinsic. You can use <tt>llvm.cttz</tt> on any
7231   integer bit width, or any vector of integer elements. Not all targets
7232   support all bit widths or vector types, however.</p>
7233
7234<pre>
7235  declare i8 @llvm.cttz.i8 (i8  &lt;src&gt;)
7236  declare i16 @llvm.cttz.i16(i16 &lt;src&gt;)
7237  declare i32 @llvm.cttz.i32(i32 &lt;src&gt;)
7238  declare i64 @llvm.cttz.i64(i64 &lt;src&gt;)
7239  declare i256 @llvm.cttz.i256(i256 &lt;src&gt;)
7240  declase &lt;2 x i32&gt; @llvm.cttz.v2i32(&lt;2 x i32&gt; &lt;src&gt;)
7241</pre>
7242
7243<h5>Overview:</h5>
7244<p>The '<tt>llvm.cttz</tt>' family of intrinsic functions counts the number of
7245   trailing zeros.</p>
7246
7247<h5>Arguments:</h5>
7248<p>The only argument is the value to be counted.  The argument may be of any
7249   integer type, or a vectory with integer element type..  The return type
7250   must match the argument type.</p>
7251
7252<h5>Semantics:</h5>
7253<p>The '<tt>llvm.cttz</tt>' intrinsic counts the trailing (least significant)
7254   zeros in a variable, or within each element of a vector.
7255   If the src == 0 then the result is the size in bits of
7256   the type of src.  For example, <tt>llvm.cttz(2) = 1</tt>.</p>
7257
7258</div>
7259
7260</div>
7261
7262<!-- ======================================================================= -->
7263<h3>
7264  <a name="int_overflow">Arithmetic with Overflow Intrinsics</a>
7265</h3>
7266
7267<div>
7268
7269<p>LLVM provides intrinsics for some arithmetic with overflow operations.</p>
7270
7271<!-- _______________________________________________________________________ -->
7272<h4>
7273  <a name="int_sadd_overflow">
7274    '<tt>llvm.sadd.with.overflow.*</tt>' Intrinsics
7275  </a>
7276</h4>
7277
7278<div>
7279
7280<h5>Syntax:</h5>
7281<p>This is an overloaded intrinsic. You can use <tt>llvm.sadd.with.overflow</tt>
7282   on any integer bit width.</p>
7283
7284<pre>
7285  declare {i16, i1} @llvm.sadd.with.overflow.i16(i16 %a, i16 %b)
7286  declare {i32, i1} @llvm.sadd.with.overflow.i32(i32 %a, i32 %b)
7287  declare {i64, i1} @llvm.sadd.with.overflow.i64(i64 %a, i64 %b)
7288</pre>
7289
7290<h5>Overview:</h5>
7291<p>The '<tt>llvm.sadd.with.overflow</tt>' family of intrinsic functions perform
7292   a signed addition of the two arguments, and indicate whether an overflow
7293   occurred during the signed summation.</p>
7294
7295<h5>Arguments:</h5>
7296<p>The arguments (%a and %b) and the first element of the result structure may
7297   be of integer types of any bit width, but they must have the same bit
7298   width. The second element of the result structure must be of
7299   type <tt>i1</tt>. <tt>%a</tt> and <tt>%b</tt> are the two values that will
7300   undergo signed addition.</p>
7301
7302<h5>Semantics:</h5>
7303<p>The '<tt>llvm.sadd.with.overflow</tt>' family of intrinsic functions perform
7304   a signed addition of the two variables. They return a structure &mdash; the
7305   first element of which is the signed summation, and the second element of
7306   which is a bit specifying if the signed summation resulted in an
7307   overflow.</p>
7308
7309<h5>Examples:</h5>
7310<pre>
7311  %res = call {i32, i1} @llvm.sadd.with.overflow.i32(i32 %a, i32 %b)
7312  %sum = extractvalue {i32, i1} %res, 0
7313  %obit = extractvalue {i32, i1} %res, 1
7314  br i1 %obit, label %overflow, label %normal
7315</pre>
7316
7317</div>
7318
7319<!-- _______________________________________________________________________ -->
7320<h4>
7321  <a name="int_uadd_overflow">
7322    '<tt>llvm.uadd.with.overflow.*</tt>' Intrinsics
7323  </a>
7324</h4>
7325
7326<div>
7327
7328<h5>Syntax:</h5>
7329<p>This is an overloaded intrinsic. You can use <tt>llvm.uadd.with.overflow</tt>
7330   on any integer bit width.</p>
7331
7332<pre>
7333  declare {i16, i1} @llvm.uadd.with.overflow.i16(i16 %a, i16 %b)
7334  declare {i32, i1} @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
7335  declare {i64, i1} @llvm.uadd.with.overflow.i64(i64 %a, i64 %b)
7336</pre>
7337
7338<h5>Overview:</h5>
7339<p>The '<tt>llvm.uadd.with.overflow</tt>' family of intrinsic functions perform
7340   an unsigned addition of the two arguments, and indicate whether a carry
7341   occurred during the unsigned summation.</p>
7342
7343<h5>Arguments:</h5>
7344<p>The arguments (%a and %b) and the first element of the result structure may
7345   be of integer types of any bit width, but they must have the same bit
7346   width. The second element of the result structure must be of
7347   type <tt>i1</tt>. <tt>%a</tt> and <tt>%b</tt> are the two values that will
7348   undergo unsigned addition.</p>
7349
7350<h5>Semantics:</h5>
7351<p>The '<tt>llvm.uadd.with.overflow</tt>' family of intrinsic functions perform
7352   an unsigned addition of the two arguments. They return a structure &mdash;
7353   the first element of which is the sum, and the second element of which is a
7354   bit specifying if the unsigned summation resulted in a carry.</p>
7355
7356<h5>Examples:</h5>
7357<pre>
7358  %res = call {i32, i1} @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
7359  %sum = extractvalue {i32, i1} %res, 0
7360  %obit = extractvalue {i32, i1} %res, 1
7361  br i1 %obit, label %carry, label %normal
7362</pre>
7363
7364</div>
7365
7366<!-- _______________________________________________________________________ -->
7367<h4>
7368  <a name="int_ssub_overflow">
7369    '<tt>llvm.ssub.with.overflow.*</tt>' Intrinsics
7370  </a>
7371</h4>
7372
7373<div>
7374
7375<h5>Syntax:</h5>
7376<p>This is an overloaded intrinsic. You can use <tt>llvm.ssub.with.overflow</tt>
7377   on any integer bit width.</p>
7378
7379<pre>
7380  declare {i16, i1} @llvm.ssub.with.overflow.i16(i16 %a, i16 %b)
7381  declare {i32, i1} @llvm.ssub.with.overflow.i32(i32 %a, i32 %b)
7382  declare {i64, i1} @llvm.ssub.with.overflow.i64(i64 %a, i64 %b)
7383</pre>
7384
7385<h5>Overview:</h5>
7386<p>The '<tt>llvm.ssub.with.overflow</tt>' family of intrinsic functions perform
7387   a signed subtraction of the two arguments, and indicate whether an overflow
7388   occurred during the signed subtraction.</p>
7389
7390<h5>Arguments:</h5>
7391<p>The arguments (%a and %b) and the first element of the result structure may
7392   be of integer types of any bit width, but they must have the same bit
7393   width. The second element of the result structure must be of
7394   type <tt>i1</tt>. <tt>%a</tt> and <tt>%b</tt> are the two values that will
7395   undergo signed subtraction.</p>
7396
7397<h5>Semantics:</h5>
7398<p>The '<tt>llvm.ssub.with.overflow</tt>' family of intrinsic functions perform
7399   a signed subtraction of the two arguments. They return a structure &mdash;
7400   the first element of which is the subtraction, and the second element of
7401   which is a bit specifying if the signed subtraction resulted in an
7402   overflow.</p>
7403
7404<h5>Examples:</h5>
7405<pre>
7406  %res = call {i32, i1} @llvm.ssub.with.overflow.i32(i32 %a, i32 %b)
7407  %sum = extractvalue {i32, i1} %res, 0
7408  %obit = extractvalue {i32, i1} %res, 1
7409  br i1 %obit, label %overflow, label %normal
7410</pre>
7411
7412</div>
7413
7414<!-- _______________________________________________________________________ -->
7415<h4>
7416  <a name="int_usub_overflow">
7417    '<tt>llvm.usub.with.overflow.*</tt>' Intrinsics
7418  </a>
7419</h4>
7420
7421<div>
7422
7423<h5>Syntax:</h5>
7424<p>This is an overloaded intrinsic. You can use <tt>llvm.usub.with.overflow</tt>
7425   on any integer bit width.</p>
7426
7427<pre>
7428  declare {i16, i1} @llvm.usub.with.overflow.i16(i16 %a, i16 %b)
7429  declare {i32, i1} @llvm.usub.with.overflow.i32(i32 %a, i32 %b)
7430  declare {i64, i1} @llvm.usub.with.overflow.i64(i64 %a, i64 %b)
7431</pre>
7432
7433<h5>Overview:</h5>
7434<p>The '<tt>llvm.usub.with.overflow</tt>' family of intrinsic functions perform
7435   an unsigned subtraction of the two arguments, and indicate whether an
7436   overflow occurred during the unsigned subtraction.</p>
7437
7438<h5>Arguments:</h5>
7439<p>The arguments (%a and %b) and the first element of the result structure may
7440   be of integer types of any bit width, but they must have the same bit
7441   width. The second element of the result structure must be of
7442   type <tt>i1</tt>. <tt>%a</tt> and <tt>%b</tt> are the two values that will
7443   undergo unsigned subtraction.</p>
7444
7445<h5>Semantics:</h5>
7446<p>The '<tt>llvm.usub.with.overflow</tt>' family of intrinsic functions perform
7447   an unsigned subtraction of the two arguments. They return a structure &mdash;
7448   the first element of which is the subtraction, and the second element of
7449   which is a bit specifying if the unsigned subtraction resulted in an
7450   overflow.</p>
7451
7452<h5>Examples:</h5>
7453<pre>
7454  %res = call {i32, i1} @llvm.usub.with.overflow.i32(i32 %a, i32 %b)
7455  %sum = extractvalue {i32, i1} %res, 0
7456  %obit = extractvalue {i32, i1} %res, 1
7457  br i1 %obit, label %overflow, label %normal
7458</pre>
7459
7460</div>
7461
7462<!-- _______________________________________________________________________ -->
7463<h4>
7464  <a name="int_smul_overflow">
7465    '<tt>llvm.smul.with.overflow.*</tt>' Intrinsics
7466  </a>
7467</h4>
7468
7469<div>
7470
7471<h5>Syntax:</h5>
7472<p>This is an overloaded intrinsic. You can use <tt>llvm.smul.with.overflow</tt>
7473   on any integer bit width.</p>
7474
7475<pre>
7476  declare {i16, i1} @llvm.smul.with.overflow.i16(i16 %a, i16 %b)
7477  declare {i32, i1} @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
7478  declare {i64, i1} @llvm.smul.with.overflow.i64(i64 %a, i64 %b)
7479</pre>
7480
7481<h5>Overview:</h5>
7482
7483<p>The '<tt>llvm.smul.with.overflow</tt>' family of intrinsic functions perform
7484   a signed multiplication of the two arguments, and indicate whether an
7485   overflow occurred during the signed multiplication.</p>
7486
7487<h5>Arguments:</h5>
7488<p>The arguments (%a and %b) and the first element of the result structure may
7489   be of integer types of any bit width, but they must have the same bit
7490   width. The second element of the result structure must be of
7491   type <tt>i1</tt>. <tt>%a</tt> and <tt>%b</tt> are the two values that will
7492   undergo signed multiplication.</p>
7493
7494<h5>Semantics:</h5>
7495<p>The '<tt>llvm.smul.with.overflow</tt>' family of intrinsic functions perform
7496   a signed multiplication of the two arguments. They return a structure &mdash;
7497   the first element of which is the multiplication, and the second element of
7498   which is a bit specifying if the signed multiplication resulted in an
7499   overflow.</p>
7500
7501<h5>Examples:</h5>
7502<pre>
7503  %res = call {i32, i1} @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
7504  %sum = extractvalue {i32, i1} %res, 0
7505  %obit = extractvalue {i32, i1} %res, 1
7506  br i1 %obit, label %overflow, label %normal
7507</pre>
7508
7509</div>
7510
7511<!-- _______________________________________________________________________ -->
7512<h4>
7513  <a name="int_umul_overflow">
7514    '<tt>llvm.umul.with.overflow.*</tt>' Intrinsics
7515  </a>
7516</h4>
7517
7518<div>
7519
7520<h5>Syntax:</h5>
7521<p>This is an overloaded intrinsic. You can use <tt>llvm.umul.with.overflow</tt>
7522   on any integer bit width.</p>
7523
7524<pre>
7525  declare {i16, i1} @llvm.umul.with.overflow.i16(i16 %a, i16 %b)
7526  declare {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
7527  declare {i64, i1} @llvm.umul.with.overflow.i64(i64 %a, i64 %b)
7528</pre>
7529
7530<h5>Overview:</h5>
7531<p>The '<tt>llvm.umul.with.overflow</tt>' family of intrinsic functions perform
7532   a unsigned multiplication of the two arguments, and indicate whether an
7533   overflow occurred during the unsigned multiplication.</p>
7534
7535<h5>Arguments:</h5>
7536<p>The arguments (%a and %b) and the first element of the result structure may
7537   be of integer types of any bit width, but they must have the same bit
7538   width. The second element of the result structure must be of
7539   type <tt>i1</tt>. <tt>%a</tt> and <tt>%b</tt> are the two values that will
7540   undergo unsigned multiplication.</p>
7541
7542<h5>Semantics:</h5>
7543<p>The '<tt>llvm.umul.with.overflow</tt>' family of intrinsic functions perform
7544   an unsigned multiplication of the two arguments. They return a structure
7545   &mdash; the first element of which is the multiplication, and the second
7546   element of which is a bit specifying if the unsigned multiplication resulted
7547   in an overflow.</p>
7548
7549<h5>Examples:</h5>
7550<pre>
7551  %res = call {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
7552  %sum = extractvalue {i32, i1} %res, 0
7553  %obit = extractvalue {i32, i1} %res, 1
7554  br i1 %obit, label %overflow, label %normal
7555</pre>
7556
7557</div>
7558
7559</div>
7560
7561<!-- ======================================================================= -->
7562<h3>
7563  <a name="int_fp16">Half Precision Floating Point Intrinsics</a>
7564</h3>
7565
7566<div>
7567
7568<p>Half precision floating point is a storage-only format. This means that it is
7569   a dense encoding (in memory) but does not support computation in the
7570   format.</p>
7571
7572<p>This means that code must first load the half-precision floating point
7573   value as an i16, then convert it to float with <a
7574   href="#int_convert_from_fp16"><tt>llvm.convert.from.fp16</tt></a>.
7575   Computation can then be performed on the float value (including extending to
7576   double etc).  To store the value back to memory, it is first converted to
7577   float if needed, then converted to i16 with
7578   <a href="#int_convert_to_fp16"><tt>llvm.convert.to.fp16</tt></a>, then
7579   storing as an i16 value.</p>
7580
7581<!-- _______________________________________________________________________ -->
7582<h4>
7583  <a name="int_convert_to_fp16">
7584    '<tt>llvm.convert.to.fp16</tt>' Intrinsic
7585  </a>
7586</h4>
7587
7588<div>
7589
7590<h5>Syntax:</h5>
7591<pre>
7592  declare i16 @llvm.convert.to.fp16(f32 %a)
7593</pre>
7594
7595<h5>Overview:</h5>
7596<p>The '<tt>llvm.convert.to.fp16</tt>' intrinsic function performs
7597   a conversion from single precision floating point format to half precision
7598   floating point format.</p>
7599
7600<h5>Arguments:</h5>
7601<p>The intrinsic function contains single argument - the value to be
7602   converted.</p>
7603
7604<h5>Semantics:</h5>
7605<p>The '<tt>llvm.convert.to.fp16</tt>' intrinsic function performs
7606   a conversion from single precision floating point format to half precision
7607   floating point format. The return value is an <tt>i16</tt> which
7608   contains the converted number.</p>
7609
7610<h5>Examples:</h5>
7611<pre>
7612  %res = call i16 @llvm.convert.to.fp16(f32 %a)
7613  store i16 %res, i16* @x, align 2
7614</pre>
7615
7616</div>
7617
7618<!-- _______________________________________________________________________ -->
7619<h4>
7620  <a name="int_convert_from_fp16">
7621    '<tt>llvm.convert.from.fp16</tt>' Intrinsic
7622  </a>
7623</h4>
7624
7625<div>
7626
7627<h5>Syntax:</h5>
7628<pre>
7629  declare f32 @llvm.convert.from.fp16(i16 %a)
7630</pre>
7631
7632<h5>Overview:</h5>
7633<p>The '<tt>llvm.convert.from.fp16</tt>' intrinsic function performs
7634   a conversion from half precision floating point format to single precision
7635   floating point format.</p>
7636
7637<h5>Arguments:</h5>
7638<p>The intrinsic function contains single argument - the value to be
7639   converted.</p>
7640
7641<h5>Semantics:</h5>
7642<p>The '<tt>llvm.convert.from.fp16</tt>' intrinsic function performs a
7643   conversion from half single precision floating point format to single
7644   precision floating point format. The input half-float value is represented by
7645   an <tt>i16</tt> value.</p>
7646
7647<h5>Examples:</h5>
7648<pre>
7649  %a = load i16* @x, align 2
7650  %res = call f32 @llvm.convert.from.fp16(i16 %a)
7651</pre>
7652
7653</div>
7654
7655</div>
7656
7657<!-- ======================================================================= -->
7658<h3>
7659  <a name="int_debugger">Debugger Intrinsics</a>
7660</h3>
7661
7662<div>
7663
7664<p>The LLVM debugger intrinsics (which all start with <tt>llvm.dbg.</tt>
7665   prefix), are described in
7666   the <a href="SourceLevelDebugging.html#format_common_intrinsics">LLVM Source
7667   Level Debugging</a> document.</p>
7668
7669</div>
7670
7671<!-- ======================================================================= -->
7672<h3>
7673  <a name="int_eh">Exception Handling Intrinsics</a>
7674</h3>
7675
7676<div>
7677
7678<p>The LLVM exception handling intrinsics (which all start with
7679   <tt>llvm.eh.</tt> prefix), are described in
7680   the <a href="ExceptionHandling.html#format_common_intrinsics">LLVM Exception
7681   Handling</a> document.</p>
7682
7683</div>
7684
7685<!-- ======================================================================= -->
7686<h3>
7687  <a name="int_trampoline">Trampoline Intrinsics</a>
7688</h3>
7689
7690<div>
7691
7692<p>These intrinsics make it possible to excise one parameter, marked with
7693   the <a href="#nest"><tt>nest</tt></a> attribute, from a function.
7694   The result is a callable
7695   function pointer lacking the nest parameter - the caller does not need to
7696   provide a value for it.  Instead, the value to use is stored in advance in a
7697   "trampoline", a block of memory usually allocated on the stack, which also
7698   contains code to splice the nest value into the argument list.  This is used
7699   to implement the GCC nested function address extension.</p>
7700
7701<p>For example, if the function is
7702   <tt>i32 f(i8* nest %c, i32 %x, i32 %y)</tt> then the resulting function
7703   pointer has signature <tt>i32 (i32, i32)*</tt>.  It can be created as
7704   follows:</p>
7705
7706<pre class="doc_code">
7707  %tramp = alloca [10 x i8], align 4 ; size and alignment only correct for X86
7708  %tramp1 = getelementptr [10 x i8]* %tramp, i32 0, i32 0
7709  call i8* @llvm.init.trampoline(i8* %tramp1, i8* bitcast (i32 (i8*, i32, i32)* @f to i8*), i8* %nval)
7710  %p = call i8* @llvm.adjust.trampoline(i8* %tramp1)
7711  %fp = bitcast i8* %p to i32 (i32, i32)*
7712</pre>
7713
7714<p>The call <tt>%val = call i32 %fp(i32 %x, i32 %y)</tt> is then equivalent
7715   to <tt>%val = call i32 %f(i8* %nval, i32 %x, i32 %y)</tt>.</p>
7716
7717<!-- _______________________________________________________________________ -->
7718<h4>
7719  <a name="int_it">
7720    '<tt>llvm.init.trampoline</tt>' Intrinsic
7721  </a>
7722</h4>
7723
7724<div>
7725
7726<h5>Syntax:</h5>
7727<pre>
7728  declare void @llvm.init.trampoline(i8* &lt;tramp&gt;, i8* &lt;func&gt;, i8* &lt;nval&gt;)
7729</pre>
7730
7731<h5>Overview:</h5>
7732<p>This fills the memory pointed to by <tt>tramp</tt> with executable code,
7733   turning it into a trampoline.</p>
7734
7735<h5>Arguments:</h5>
7736<p>The <tt>llvm.init.trampoline</tt> intrinsic takes three arguments, all
7737   pointers.  The <tt>tramp</tt> argument must point to a sufficiently large and
7738   sufficiently aligned block of memory; this memory is written to by the
7739   intrinsic.  Note that the size and the alignment are target-specific - LLVM
7740   currently provides no portable way of determining them, so a front-end that
7741   generates this intrinsic needs to have some target-specific knowledge.
7742   The <tt>func</tt> argument must hold a function bitcast to
7743   an <tt>i8*</tt>.</p>
7744
7745<h5>Semantics:</h5>
7746<p>The block of memory pointed to by <tt>tramp</tt> is filled with target
7747   dependent code, turning it into a function.  Then <tt>tramp</tt> needs to be
7748   passed to <a href="#int_at">llvm.adjust.trampoline</a> to get a pointer
7749   which can be <a href="#int_trampoline">bitcast (to a new function) and
7750   called</a>.  The new function's signature is the same as that of
7751   <tt>func</tt> with any arguments marked with the <tt>nest</tt> attribute
7752   removed.  At most one such <tt>nest</tt> argument is allowed, and it must be of
7753   pointer type.  Calling the new function is equivalent to calling <tt>func</tt>
7754   with the same argument list, but with <tt>nval</tt> used for the missing
7755   <tt>nest</tt> argument.  If, after calling <tt>llvm.init.trampoline</tt>, the
7756   memory pointed to by <tt>tramp</tt> is modified, then the effect of any later call
7757   to the returned function pointer is undefined.</p>
7758</div>
7759
7760<!-- _______________________________________________________________________ -->
7761<h4>
7762  <a name="int_at">
7763    '<tt>llvm.adjust.trampoline</tt>' Intrinsic
7764  </a>
7765</h4>
7766
7767<div>
7768
7769<h5>Syntax:</h5>
7770<pre>
7771  declare i8* @llvm.adjust.trampoline(i8* &lt;tramp&gt;)
7772</pre>
7773
7774<h5>Overview:</h5>
7775<p>This performs any required machine-specific adjustment to the address of a
7776   trampoline (passed as <tt>tramp</tt>).</p>
7777
7778<h5>Arguments:</h5>
7779<p><tt>tramp</tt> must point to a block of memory which already has trampoline code
7780   filled in by a previous call to <a href="#int_it"><tt>llvm.init.trampoline</tt>
7781   </a>.</p>
7782
7783<h5>Semantics:</h5>
7784<p>On some architectures the address of the code to be executed needs to be
7785   different to the address where the trampoline is actually stored.  This
7786   intrinsic returns the executable address corresponding to <tt>tramp</tt>
7787   after performing the required machine specific adjustments.
7788   The pointer returned can then be <a href="#int_trampoline"> bitcast and
7789   executed</a>.
7790</p>
7791
7792</div>
7793
7794</div>
7795
7796<!-- ======================================================================= -->
7797<h3>
7798  <a name="int_memorymarkers">Memory Use Markers</a>
7799</h3>
7800
7801<div>
7802
7803<p>This class of intrinsics exists to information about the lifetime of memory
7804   objects and ranges where variables are immutable.</p>
7805
7806<!-- _______________________________________________________________________ -->
7807<h4>
7808  <a name="int_lifetime_start">'<tt>llvm.lifetime.start</tt>' Intrinsic</a>
7809</h4>
7810
7811<div>
7812
7813<h5>Syntax:</h5>
7814<pre>
7815  declare void @llvm.lifetime.start(i64 &lt;size&gt;, i8* nocapture &lt;ptr&gt;)
7816</pre>
7817
7818<h5>Overview:</h5>
7819<p>The '<tt>llvm.lifetime.start</tt>' intrinsic specifies the start of a memory
7820   object's lifetime.</p>
7821
7822<h5>Arguments:</h5>
7823<p>The first argument is a constant integer representing the size of the
7824   object, or -1 if it is variable sized.  The second argument is a pointer to
7825   the object.</p>
7826
7827<h5>Semantics:</h5>
7828<p>This intrinsic indicates that before this point in the code, the value of the
7829   memory pointed to by <tt>ptr</tt> is dead.  This means that it is known to
7830   never be used and has an undefined value.  A load from the pointer that
7831   precedes this intrinsic can be replaced with
7832   <tt>'<a href="#undefvalues">undef</a>'</tt>.</p>
7833
7834</div>
7835
7836<!-- _______________________________________________________________________ -->
7837<h4>
7838  <a name="int_lifetime_end">'<tt>llvm.lifetime.end</tt>' Intrinsic</a>
7839</h4>
7840
7841<div>
7842
7843<h5>Syntax:</h5>
7844<pre>
7845  declare void @llvm.lifetime.end(i64 &lt;size&gt;, i8* nocapture &lt;ptr&gt;)
7846</pre>
7847
7848<h5>Overview:</h5>
7849<p>The '<tt>llvm.lifetime.end</tt>' intrinsic specifies the end of a memory
7850   object's lifetime.</p>
7851
7852<h5>Arguments:</h5>
7853<p>The first argument is a constant integer representing the size of the
7854   object, or -1 if it is variable sized.  The second argument is a pointer to
7855   the object.</p>
7856
7857<h5>Semantics:</h5>
7858<p>This intrinsic indicates that after this point in the code, the value of the
7859   memory pointed to by <tt>ptr</tt> is dead.  This means that it is known to
7860   never be used and has an undefined value.  Any stores into the memory object
7861   following this intrinsic may be removed as dead.
7862
7863</div>
7864
7865<!-- _______________________________________________________________________ -->
7866<h4>
7867  <a name="int_invariant_start">'<tt>llvm.invariant.start</tt>' Intrinsic</a>
7868</h4>
7869
7870<div>
7871
7872<h5>Syntax:</h5>
7873<pre>
7874  declare {}* @llvm.invariant.start(i64 &lt;size&gt;, i8* nocapture &lt;ptr&gt;)
7875</pre>
7876
7877<h5>Overview:</h5>
7878<p>The '<tt>llvm.invariant.start</tt>' intrinsic specifies that the contents of
7879   a memory object will not change.</p>
7880
7881<h5>Arguments:</h5>
7882<p>The first argument is a constant integer representing the size of the
7883   object, or -1 if it is variable sized.  The second argument is a pointer to
7884   the object.</p>
7885
7886<h5>Semantics:</h5>
7887<p>This intrinsic indicates that until an <tt>llvm.invariant.end</tt> that uses
7888   the return value, the referenced memory location is constant and
7889   unchanging.</p>
7890
7891</div>
7892
7893<!-- _______________________________________________________________________ -->
7894<h4>
7895  <a name="int_invariant_end">'<tt>llvm.invariant.end</tt>' Intrinsic</a>
7896</h4>
7897
7898<div>
7899
7900<h5>Syntax:</h5>
7901<pre>
7902  declare void @llvm.invariant.end({}* &lt;start&gt;, i64 &lt;size&gt;, i8* nocapture &lt;ptr&gt;)
7903</pre>
7904
7905<h5>Overview:</h5>
7906<p>The '<tt>llvm.invariant.end</tt>' intrinsic specifies that the contents of
7907   a memory object are mutable.</p>
7908
7909<h5>Arguments:</h5>
7910<p>The first argument is the matching <tt>llvm.invariant.start</tt> intrinsic.
7911   The second argument is a constant integer representing the size of the
7912   object, or -1 if it is variable sized and the third argument is a pointer
7913   to the object.</p>
7914
7915<h5>Semantics:</h5>
7916<p>This intrinsic indicates that the memory is mutable again.</p>
7917
7918</div>
7919
7920</div>
7921
7922<!-- ======================================================================= -->
7923<h3>
7924  <a name="int_general">General Intrinsics</a>
7925</h3>
7926
7927<div>
7928
7929<p>This class of intrinsics is designed to be generic and has no specific
7930   purpose.</p>
7931
7932<!-- _______________________________________________________________________ -->
7933<h4>
7934  <a name="int_var_annotation">'<tt>llvm.var.annotation</tt>' Intrinsic</a>
7935</h4>
7936
7937<div>
7938
7939<h5>Syntax:</h5>
7940<pre>
7941  declare void @llvm.var.annotation(i8* &lt;val&gt;, i8* &lt;str&gt;, i8* &lt;str&gt;, i32  &lt;int&gt;)
7942</pre>
7943
7944<h5>Overview:</h5>
7945<p>The '<tt>llvm.var.annotation</tt>' intrinsic.</p>
7946
7947<h5>Arguments:</h5>
7948<p>The first argument is a pointer to a value, the second is a pointer to a
7949   global string, the third is a pointer to a global string which is the source
7950   file name, and the last argument is the line number.</p>
7951
7952<h5>Semantics:</h5>
7953<p>This intrinsic allows annotation of local variables with arbitrary strings.
7954   This can be useful for special purpose optimizations that want to look for
7955   these annotations.  These have no other defined use; they are ignored by code
7956   generation and optimization.</p>
7957
7958</div>
7959
7960<!-- _______________________________________________________________________ -->
7961<h4>
7962  <a name="int_annotation">'<tt>llvm.annotation.*</tt>' Intrinsic</a>
7963</h4>
7964
7965<div>
7966
7967<h5>Syntax:</h5>
7968<p>This is an overloaded intrinsic. You can use '<tt>llvm.annotation</tt>' on
7969   any integer bit width.</p>
7970
7971<pre>
7972  declare i8 @llvm.annotation.i8(i8 &lt;val&gt;, i8* &lt;str&gt;, i8* &lt;str&gt;, i32  &lt;int&gt;)
7973  declare i16 @llvm.annotation.i16(i16 &lt;val&gt;, i8* &lt;str&gt;, i8* &lt;str&gt;, i32  &lt;int&gt;)
7974  declare i32 @llvm.annotation.i32(i32 &lt;val&gt;, i8* &lt;str&gt;, i8* &lt;str&gt;, i32  &lt;int&gt;)
7975  declare i64 @llvm.annotation.i64(i64 &lt;val&gt;, i8* &lt;str&gt;, i8* &lt;str&gt;, i32  &lt;int&gt;)
7976  declare i256 @llvm.annotation.i256(i256 &lt;val&gt;, i8* &lt;str&gt;, i8* &lt;str&gt;, i32  &lt;int&gt;)
7977</pre>
7978
7979<h5>Overview:</h5>
7980<p>The '<tt>llvm.annotation</tt>' intrinsic.</p>
7981
7982<h5>Arguments:</h5>
7983<p>The first argument is an integer value (result of some expression), the
7984   second is a pointer to a global string, the third is a pointer to a global
7985   string which is the source file name, and the last argument is the line
7986   number.  It returns the value of the first argument.</p>
7987
7988<h5>Semantics:</h5>
7989<p>This intrinsic allows annotations to be put on arbitrary expressions with
7990   arbitrary strings.  This can be useful for special purpose optimizations that
7991   want to look for these annotations.  These have no other defined use; they
7992   are ignored by code generation and optimization.</p>
7993
7994</div>
7995
7996<!-- _______________________________________________________________________ -->
7997<h4>
7998  <a name="int_trap">'<tt>llvm.trap</tt>' Intrinsic</a>
7999</h4>
8000
8001<div>
8002
8003<h5>Syntax:</h5>
8004<pre>
8005  declare void @llvm.trap()
8006</pre>
8007
8008<h5>Overview:</h5>
8009<p>The '<tt>llvm.trap</tt>' intrinsic.</p>
8010
8011<h5>Arguments:</h5>
8012<p>None.</p>
8013
8014<h5>Semantics:</h5>
8015<p>This intrinsics is lowered to the target dependent trap instruction. If the
8016   target does not have a trap instruction, this intrinsic will be lowered to
8017   the call of the <tt>abort()</tt> function.</p>
8018
8019</div>
8020
8021<!-- _______________________________________________________________________ -->
8022<h4>
8023  <a name="int_stackprotector">'<tt>llvm.stackprotector</tt>' Intrinsic</a>
8024</h4>
8025
8026<div>
8027
8028<h5>Syntax:</h5>
8029<pre>
8030  declare void @llvm.stackprotector(i8* &lt;guard&gt;, i8** &lt;slot&gt;)
8031</pre>
8032
8033<h5>Overview:</h5>
8034<p>The <tt>llvm.stackprotector</tt> intrinsic takes the <tt>guard</tt> and
8035   stores it onto the stack at <tt>slot</tt>. The stack slot is adjusted to
8036   ensure that it is placed on the stack before local variables.</p>
8037
8038<h5>Arguments:</h5>
8039<p>The <tt>llvm.stackprotector</tt> intrinsic requires two pointer
8040   arguments. The first argument is the value loaded from the stack
8041   guard <tt>@__stack_chk_guard</tt>. The second variable is an <tt>alloca</tt>
8042   that has enough space to hold the value of the guard.</p>
8043
8044<h5>Semantics:</h5>
8045<p>This intrinsic causes the prologue/epilogue inserter to force the position of
8046   the <tt>AllocaInst</tt> stack slot to be before local variables on the
8047   stack. This is to ensure that if a local variable on the stack is
8048   overwritten, it will destroy the value of the guard. When the function exits,
8049   the guard on the stack is checked against the original guard. If they are
8050   different, then the program aborts by calling the <tt>__stack_chk_fail()</tt>
8051   function.</p>
8052
8053</div>
8054
8055<!-- _______________________________________________________________________ -->
8056<h4>
8057  <a name="int_objectsize">'<tt>llvm.objectsize</tt>' Intrinsic</a>
8058</h4>
8059
8060<div>
8061
8062<h5>Syntax:</h5>
8063<pre>
8064  declare i32 @llvm.objectsize.i32(i8* &lt;object&gt;, i1 &lt;type&gt;)
8065  declare i64 @llvm.objectsize.i64(i8* &lt;object&gt;, i1 &lt;type&gt;)
8066</pre>
8067
8068<h5>Overview:</h5>
8069<p>The <tt>llvm.objectsize</tt> intrinsic is designed to provide information to
8070   the optimizers to determine at compile time whether a) an operation (like
8071   memcpy) will overflow a buffer that corresponds to an object, or b) that a
8072   runtime check for overflow isn't necessary. An object in this context means
8073   an allocation of a specific class, structure, array, or other object.</p>
8074
8075<h5>Arguments:</h5>
8076<p>The <tt>llvm.objectsize</tt> intrinsic takes two arguments. The first
8077   argument is a pointer to or into the <tt>object</tt>. The second argument
8078   is a boolean 0 or 1. This argument determines whether you want the
8079   maximum (0) or minimum (1) bytes remaining. This needs to be a literal 0 or
8080   1, variables are not allowed.</p>
8081
8082<h5>Semantics:</h5>
8083<p>The <tt>llvm.objectsize</tt> intrinsic is lowered to either a constant
8084   representing the size of the object concerned, or <tt>i32/i64 -1 or 0</tt>,
8085   depending on the <tt>type</tt> argument, if the size cannot be determined at
8086   compile time.</p>
8087
8088</div>
8089
8090</div>
8091
8092</div>
8093
8094<!-- *********************************************************************** -->
8095<hr>
8096<address>
8097  <a href="http://jigsaw.w3.org/css-validator/check/referer"><img
8098  src="http://jigsaw.w3.org/css-validator/images/vcss-blue" alt="Valid CSS"></a>
8099  <a href="http://validator.w3.org/check/referer"><img
8100  src="http://www.w3.org/Icons/valid-html401-blue" alt="Valid HTML 4.01"></a>
8101
8102  <a href="mailto:sabre@nondot.org">Chris Lattner</a><br>
8103  <a href="http://llvm.org/">The LLVM Compiler Infrastructure</a><br>
8104  Last modified: $Date: 2011-10-26 18:35:59 -0400 (Wed, 26 Oct 2011) $
8105</address>
8106
8107</body>
8108</html>
8109