-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
+ "http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<title>LLVM Assembly Language Reference Manual</title>
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
+ <meta name="author" content="Chris Lattner">
+ <meta name="description"
+ content="LLVM Assembly Language Reference Manual.">
<link rel="stylesheet" href="llvm.css" type="text/css">
</head>
+
<body>
+
<div class="doc_title"> LLVM Language Reference Manual </div>
<ol>
<li><a href="#abstract">Abstract</a></li>
<li><a href="#introduction">Introduction</a></li>
<li><a href="#identifiers">Identifiers</a></li>
+ <li><a href="#highlevel">High Level Structure</a>
+ <ol>
+ <li><a href="#modulestructure">Module Structure</a></li>
+ <li><a href="#linkage">Linkage Types</a></li>
+ <li><a href="#callingconv">Calling Conventions</a></li>
+ <li><a href="#globalvars">Global Variables</a></li>
+ <li><a href="#functionstructure">Functions</a></li>
+ <li><a href="#moduleasm">Module-Level Inline Assembly</a></li>
+ </ol>
+ </li>
<li><a href="#typesystem">Type System</a>
<ol>
- <li><a href="#t_primitive">Primitive Types</a>
+ <li><a href="#t_primitive">Primitive Types</a>
<ol>
<li><a href="#t_classifications">Type Classifications</a></li>
</ol>
<li><a href="#t_function">Function Type</a></li>
<li><a href="#t_pointer">Pointer Type</a></li>
<li><a href="#t_struct">Structure Type</a></li>
-<!-- <li><a href="#t_packed" >Packed Type</a> -->
+ <li><a href="#t_packed">Packed Type</a></li>
+ <li><a href="#t_opaque">Opaque Type</a></li>
</ol>
</li>
</ol>
</li>
- <li><a href="#highlevel">High Level Structure</a>
+ <li><a href="#constants">Constants</a>
<ol>
- <li><a href="#modulestructure">Module Structure</a></li>
- <li><a href="#globalvars">Global Variables</a></li>
- <li><a href="#functionstructure">Function Structure</a></li>
+ <li><a href="#simpleconstants">Simple Constants</a>
+ <li><a href="#aggregateconstants">Aggregate Constants</a>
+ <li><a href="#globalconstants">Global Variable and Function Addresses</a>
+ <li><a href="#undefvalues">Undefined Values</a>
+ <li><a href="#constantexprs">Constant Expressions</a>
+ </ol>
+ </li>
+ <li><a href="#othervalues">Other Values</a>
+ <ol>
+ <li><a href="#inlineasm">Inline Assembler Expressions</a>
</ol>
</li>
<li><a href="#instref">Instruction Reference</a>
<li><a href="#i_switch">'<tt>switch</tt>' Instruction</a></li>
<li><a href="#i_invoke">'<tt>invoke</tt>' Instruction</a></li>
<li><a href="#i_unwind">'<tt>unwind</tt>' Instruction</a></li>
+ <li><a href="#i_unreachable">'<tt>unreachable</tt>' Instruction</a></li>
</ol>
</li>
<li><a href="#binaryops">Binary Operations</a>
<li><a href="#i_malloc">'<tt>malloc</tt>' Instruction</a></li>
<li><a href="#i_free">'<tt>free</tt>' Instruction</a></li>
<li><a href="#i_alloca">'<tt>alloca</tt>' Instruction</a></li>
- <li><a href="#i_load">'<tt>load</tt>' Instruction</a></li>
- <li><a href="#i_store">'<tt>store</tt>' Instruction</a></li>
- <li><a href="#i_getelementptr">'<tt>getelementptr</tt>' Instruction</a></li>
+ <li><a href="#i_load">'<tt>load</tt>' Instruction</a></li>
+ <li><a href="#i_store">'<tt>store</tt>' Instruction</a></li>
+ <li><a href="#i_getelementptr">'<tt>getelementptr</tt>' Instruction</a></li>
</ol>
</li>
<li><a href="#otherops">Other Operations</a>
<ol>
<li><a href="#i_phi">'<tt>phi</tt>' Instruction</a></li>
<li><a href="#i_cast">'<tt>cast .. to</tt>' Instruction</a></li>
+ <li><a href="#i_select">'<tt>select</tt>' Instruction</a></li>
+ <li><a href="#i_vsetint">'<tt>vsetint</tt>' Instruction</a></li>
+ <li><a href="#i_vsetfp">'<tt>vsetfp</tt>' Instruction</a></li>
+ <li><a href="#i_vselect">'<tt>vselect</tt>' Instruction</a></li>
+ <li><a href="#i_extractelement">'<tt>extractelement</tt>' Instruction</a></li>
+ <li><a href="#i_insertelement">'<tt>insertelement</tt>' Instruction</a></li>
<li><a href="#i_call">'<tt>call</tt>' Instruction</a></li>
- <li><a href="#i_vanext">'<tt>vanext</tt>' Instruction</a></li>
- <li><a href="#i_vaarg">'<tt>vaarg</tt>' Instruction</a></li>
+ <li><a href="#i_va_arg">'<tt>va_arg</tt>' Instruction</a></li>
</ol>
</li>
</ol>
<li><a href="#i_va_copy">'<tt>llvm.va_copy</tt>' Intrinsic</a></li>
</ol>
</li>
+ <li><a href="#int_gc">Accurate Garbage Collection Intrinsics</a>
+ <ol>
+ <li><a href="#i_gcroot">'<tt>llvm.gcroot</tt>' Intrinsic</a></li>
+ <li><a href="#i_gcread">'<tt>llvm.gcread</tt>' Intrinsic</a></li>
+ <li><a href="#i_gcwrite">'<tt>llvm.gcwrite</tt>' Intrinsic</a></li>
+ </ol>
+ </li>
+ <li><a href="#int_codegen">Code Generator Intrinsics</a>
+ <ol>
+ <li><a href="#i_returnaddress">'<tt>llvm.returnaddress</tt>' Intrinsic</a></li>
+ <li><a href="#i_frameaddress">'<tt>llvm.frameaddress</tt>' Intrinsic</a></li>
+ <li><a href="#i_stacksave">'<tt>llvm.stacksave</tt>' Intrinsic</a></li>
+ <li><a href="#i_stackrestore">'<tt>llvm.stackrestore</tt>' Intrinsic</a></li>
+ <li><a href="#i_prefetch">'<tt>llvm.prefetch</tt>' Intrinsic</a></li>
+ <li><a href="#i_pcmarker">'<tt>llvm.pcmarker</tt>' Intrinsic</a></li>
+ <li><a href="#i_readcyclecounter"><tt>llvm.readcyclecounter</tt>' Intrinsic</a></li>
+ </ol>
+ </li>
<li><a href="#int_libc">Standard C Library Intrinsics</a>
<ol>
- <li><a href="#i_memcpy">'<tt>llvm.memcpy</tt>' Intrinsic</a></li>
- <li><a href="#i_memmove">'<tt>llvm.memmove</tt>' Intrinsic</a></li>
+ <li><a href="#i_memcpy">'<tt>llvm.memcpy.*</tt>' Intrinsic</a></li>
+ <li><a href="#i_memmove">'<tt>llvm.memmove.*</tt>' Intrinsic</a></li>
+ <li><a href="#i_memset">'<tt>llvm.memset.*</tt>' Intrinsic</a></li>
+ <li><a href="#i_isunordered">'<tt>llvm.isunordered.*</tt>' Intrinsic</a></li>
+ <li><a href="#i_sqrt">'<tt>llvm.sqrt.*</tt>' Intrinsic</a></li>
+
+ </ol>
+ </li>
+ <li><a href="#int_manip">Bit Manipulation Intrinsics</a>
+ <ol>
+ <li><a href="#i_bswap">'<tt>llvm.bswap.*</tt>' Intrinsics</a></li>
+ <li><a href="#int_ctpop">'<tt>llvm.ctpop.*</tt>' Intrinsic </a></li>
+ <li><a href="#int_ctlz">'<tt>llvm.ctlz.*</tt>' Intrinsic </a></li>
+ <li><a href="#int_cttz">'<tt>llvm.cttz.*</tt>' Intrinsic </a></li>
</ol>
</li>
- <li><a href="#int_debugger">Debugger intrinsics</a>
+ <li><a href="#int_debugger">Debugger intrinsics</a></li>
</ol>
</li>
</ol>
-<div class="doc_text">
-<p><b>Written by <a href="mailto:sabre@nondot.org">Chris Lattner</a>
-and <a href="mailto:vadve@cs.uiuc.edu">Vikram Adve</a></b></p>
-<p> </p>
+
+<div class="doc_author">
+ <p>Written by <a href="mailto:sabre@nondot.org">Chris Lattner</a>
+ and <a href="mailto:vadve@cs.uiuc.edu">Vikram Adve</a></p>
</div>
+
<!-- *********************************************************************** -->
<div class="doc_section"> <a name="abstract">Abstract </a></div>
<!-- *********************************************************************** -->
+
<div class="doc_text">
<p>This document is a reference manual for the LLVM assembly language.
LLVM is an SSA based representation that provides type safety,
representation used throughout all phases of the LLVM compilation
strategy.</p>
</div>
+
<!-- *********************************************************************** -->
<div class="doc_section"> <a name="introduction">Introduction</a> </div>
<!-- *********************************************************************** -->
+
<div class="doc_text">
+
<p>The LLVM code representation is designed to be used in three
different forms: as an in-memory compiler IR, as an on-disk bytecode
representation (suitable for fast loading by a Just-In-Time compiler),
to debug and visualize the transformations. The three different forms
of LLVM are all equivalent. This document describes the human readable
representation and notation.</p>
-<p>The LLVM representation aims to be a light-weight and low-level
+
+<p>The LLVM representation aims to be light-weight and low-level
while being expressive, typed, and extensible at the same time. It
aims to be a "universal IR" of sorts, by being at a low enough level
that high-level ideas may be cleanly mapped to it (similar to how
can be proven that a C automatic variable is never accessed outside of
the current function... allowing it to be promoted to a simple SSA
value instead of a memory location.</p>
+
</div>
+
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection"> <a name="wellformed">Well-Formedness</a> </div>
+
<div class="doc_text">
+
<p>It is important to note that this document describes 'well formed'
LLVM assembly language. There is a difference between what the parser
accepts and what is considered 'well formed'. For example, the
following instruction is syntactically okay, but not well formed:</p>
-<pre> %x = <a href="#i_add">add</a> int 1, %x<br></pre>
+
+<pre>
+ %x = <a href="#i_add">add</a> int 1, %x
+</pre>
+
<p>...because the definition of <tt>%x</tt> does not dominate all of
its uses. The LLVM infrastructure provides a verification pass that may
be used to verify that an LLVM module is well formed. This pass is
-automatically run by the parser after parsing input assembly, and by
+automatically run by the parser after parsing input assembly and by
the optimizer before it outputs bytecode. The violations pointed out
by the verifier pass indicate bugs in transformation passes or input to
the parser.</p>
+
<!-- Describe the typesetting conventions here. --> </div>
+
<!-- *********************************************************************** -->
<div class="doc_section"> <a name="identifiers">Identifiers</a> </div>
<!-- *********************************************************************** -->
+
<div class="doc_text">
+
<p>LLVM uses three different forms of identifiers, for different
purposes:</p>
+
<ol>
- <li>Numeric constants are represented as you would expect: 12, -3
-123.421, etc. Floating point constants have an optional hexidecimal
-notation.</li>
- <li>Named values are represented as a string of characters with a '%'
-prefix. For example, %foo, %DivisionByZero,
-%a.really.long.identifier. The actual regular expression used is '<tt>%[a-zA-Z$._][a-zA-Z$._0-9]*</tt>'.
-Identifiers which require other characters in their names can be
-surrounded with quotes. In this way, anything except a <tt>"</tt>
-character can be used in a name.</li>
- <li>Unnamed values are represented as an unsigned numeric value with
-a '%' prefix. For example, %12, %2, %44.</li>
+ <li>Named values are represented as a string of characters with a '%' prefix.
+ For example, %foo, %DivisionByZero, %a.really.long.identifier. The actual
+ regular expression used is '<tt>%[a-zA-Z$._][a-zA-Z$._0-9]*</tt>'.
+ Identifiers which require other characters in their names can be surrounded
+ with quotes. In this way, anything except a <tt>"</tt> character can be used
+ in a name.</li>
+
+ <li>Unnamed values are represented as an unsigned numeric value with a '%'
+ prefix. For example, %12, %2, %44.</li>
+
+ <li>Constants, which are described in a <a href="#constants">section about
+ constants</a>, below.</li>
</ol>
-<p>LLVM requires the values start with a '%' sign for two reasons:
-Compilers don't need to worry about name clashes with reserved words,
-and the set of reserved words may be expanded in the future without
-penalty. Additionally, unnamed identifiers allow a compiler to quickly
-come up with a temporary variable without having to avoid symbol table
-conflicts.</p>
+
+<p>LLVM requires that values start with a '%' sign for two reasons: Compilers
+don't need to worry about name clashes with reserved words, and the set of
+reserved words may be expanded in the future without penalty. Additionally,
+unnamed identifiers allow a compiler to quickly come up with a temporary
+variable without having to avoid symbol table conflicts.</p>
+
<p>Reserved words in LLVM are very similar to reserved words in other
languages. There are keywords for different opcodes ('<tt><a
- href="#i_add">add</a></tt>', '<tt><a href="#i_cast">cast</a></tt>', '<tt><a
- href="#i_ret">ret</a></tt>', etc...), for primitive type names ('<tt><a
- href="#t_void">void</a></tt>', '<tt><a href="#t_uint">uint</a></tt>',
-etc...), and others. These reserved words cannot conflict with
-variable names, because none of them start with a '%' character.</p>
-<p>Here is an example of LLVM code to multiply the integer variable '<tt>%X</tt>'
-by 8:</p>
+href="#i_add">add</a></tt>', '<tt><a href="#i_cast">cast</a></tt>', '<tt><a
+href="#i_ret">ret</a></tt>', etc...), for primitive type names ('<tt><a
+href="#t_void">void</a></tt>', '<tt><a href="#t_uint">uint</a></tt>', etc...),
+and others. These reserved words cannot conflict with variable names, because
+none of them start with a '%' character.</p>
+
+<p>Here is an example of LLVM code to multiply the integer variable
+'<tt>%X</tt>' by 8:</p>
+
<p>The easy way:</p>
-<pre> %result = <a href="#i_mul">mul</a> uint %X, 8<br></pre>
+
+<pre>
+ %result = <a href="#i_mul">mul</a> uint %X, 8
+</pre>
+
<p>After strength reduction:</p>
-<pre> %result = <a href="#i_shl">shl</a> uint %X, ubyte 3<br></pre>
+
+<pre>
+ %result = <a href="#i_shl">shl</a> uint %X, ubyte 3
+</pre>
+
<p>And the hard way:</p>
-<pre> <a href="#i_add">add</a> uint %X, %X <i>; yields {uint}:%0</i>
- <a
- href="#i_add">add</a> uint %0, %0 <i>; yields {uint}:%1</i>
- %result = <a
- href="#i_add">add</a> uint %1, %1<br></pre>
+
+<pre>
+ <a href="#i_add">add</a> uint %X, %X <i>; yields {uint}:%0</i>
+ <a href="#i_add">add</a> uint %0, %0 <i>; yields {uint}:%1</i>
+ %result = <a href="#i_add">add</a> uint %1, %1
+</pre>
+
<p>This last way of multiplying <tt>%X</tt> by 8 illustrates several
important lexical features of LLVM:</p>
+
<ol>
- <li>Comments are delimited with a '<tt>;</tt>' and go until the end
-of line.</li>
- <li>Unnamed temporaries are created when the result of a computation
-is not assigned to a named value.</li>
+
+ <li>Comments are delimited with a '<tt>;</tt>' and go until the end of
+ line.</li>
+
+ <li>Unnamed temporaries are created when the result of a computation is not
+ assigned to a named value.</li>
+
<li>Unnamed temporaries are numbered sequentially</li>
+
</ol>
-<p>...and it also show a convention that we follow in this document.
-When demonstrating instructions, we will follow an instruction with a
-comment that defines the type and name of value produced. Comments are
-shown in italic text.</p>
-<p>The one non-intuitive notation for constants is the optional
-hexidecimal form of floating point constants. For example, the form '<tt>double
-0x432ff973cafa8000</tt>' is equivalent to (but harder to read than) '<tt>double
-4.5e+15</tt>' which is also supported by the parser. The only time
-hexadecimal floating point constants are useful (and the only time that
-they are generated by the disassembler) is when an FP constant has to
-be emitted that is not representable as a decimal floating point number
-exactly. For example, NaN's, infinities, and other special cases are
-represented in their IEEE hexadecimal format so that assembly and
-disassembly do not cause any bits to change in the constants.</p>
+
+<p>...and it also shows a convention that we follow in this document. When
+demonstrating instructions, we will follow an instruction with a comment that
+defines the type and name of value produced. Comments are shown in italic
+text.</p>
+
+</div>
+
+<!-- *********************************************************************** -->
+<div class="doc_section"> <a name="highlevel">High Level Structure</a> </div>
+<!-- *********************************************************************** -->
+
+<!-- ======================================================================= -->
+<div class="doc_subsection"> <a name="modulestructure">Module Structure</a>
+</div>
+
+<div class="doc_text">
+
+<p>LLVM programs are composed of "Module"s, each of which is a
+translation unit of the input programs. Each module consists of
+functions, global variables, and symbol table entries. Modules may be
+combined together with the LLVM linker, which merges function (and
+global variable) definitions, resolves forward declarations, and merges
+symbol table entries. Here is an example of the "hello world" module:</p>
+
+<pre><i>; Declare the string constant as a global constant...</i>
+<a href="#identifiers">%.LC0</a> = <a href="#linkage_internal">internal</a> <a
+ href="#globalvars">constant</a> <a href="#t_array">[13 x sbyte]</a> c"hello world\0A\00" <i>; [13 x sbyte]*</i>
+
+<i>; External declaration of the puts function</i>
+<a href="#functionstructure">declare</a> int %puts(sbyte*) <i>; int(sbyte*)* </i>
+
+<i>; Definition of main function</i>
+int %main() { <i>; int()* </i>
+ <i>; Convert [13x sbyte]* to sbyte *...</i>
+ %cast210 = <a
+ href="#i_getelementptr">getelementptr</a> [13 x sbyte]* %.LC0, long 0, long 0 <i>; sbyte*</i>
+
+ <i>; Call puts function to write out the string to stdout...</i>
+ <a
+ href="#i_call">call</a> int %puts(sbyte* %cast210) <i>; int</i>
+ <a
+ href="#i_ret">ret</a> int 0<br>}<br></pre>
+
+<p>This example is made up of a <a href="#globalvars">global variable</a>
+named "<tt>.LC0</tt>", an external declaration of the "<tt>puts</tt>"
+function, and a <a href="#functionstructure">function definition</a>
+for "<tt>main</tt>".</p>
+
+<p>In general, a module is made up of a list of global values,
+where both functions and global variables are global values. Global values are
+represented by a pointer to a memory location (in this case, a pointer to an
+array of char, and a pointer to a function), and have one of the following <a
+href="#linkage">linkage types</a>.</p>
+
+</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="linkage">Linkage Types</a>
+</div>
+
+<div class="doc_text">
+
+<p>
+All Global Variables and Functions have one of the following types of linkage:
+</p>
+
+<dl>
+
+ <dt><tt><b><a name="linkage_internal">internal</a></b></tt> </dt>
+
+ <dd>Global values with internal linkage are only directly accessible by
+ objects in the current module. In particular, linking code into a module with
+ an internal global value may cause the internal to be renamed as necessary to
+ avoid collisions. Because the symbol is internal to the module, all
+ references can be updated. This corresponds to the notion of the
+ '<tt>static</tt>' keyword in C, or the idea of "anonymous namespaces" in C++.
+ </dd>
+
+ <dt><tt><b><a name="linkage_linkonce">linkonce</a></b></tt>: </dt>
+
+ <dd>"<tt>linkonce</tt>" linkage is similar to <tt>internal</tt> linkage, with
+ the twist that linking together two modules defining the same
+ <tt>linkonce</tt> globals will cause one of the globals to be discarded. This
+ is typically used to implement inline functions. Unreferenced
+ <tt>linkonce</tt> globals are allowed to be discarded.
+ </dd>
+
+ <dt><tt><b><a name="linkage_weak">weak</a></b></tt>: </dt>
+
+ <dd>"<tt>weak</tt>" linkage is exactly the same as <tt>linkonce</tt> linkage,
+ except that unreferenced <tt>weak</tt> globals may not be discarded. This is
+ used to implement constructs in C such as "<tt>int X;</tt>" at global scope.
+ </dd>
+
+ <dt><tt><b><a name="linkage_appending">appending</a></b></tt>: </dt>
+
+ <dd>"<tt>appending</tt>" linkage may only be applied to global variables of
+ pointer to array type. When two global variables with appending linkage are
+ linked together, the two global arrays are appended together. This is the
+ LLVM, typesafe, equivalent of having the system linker append together
+ "sections" with identical names when .o files are linked.
+ </dd>
+
+ <dt><tt><b><a name="linkage_external">externally visible</a></b></tt>:</dt>
+
+ <dd>If none of the above identifiers are used, the global is externally
+ visible, meaning that it participates in linkage and can be used to resolve
+ external symbol references.
+ </dd>
+</dl>
+
+<p><a name="linkage_external">For example, since the "<tt>.LC0</tt>"
+variable is defined to be internal, if another module defined a "<tt>.LC0</tt>"
+variable and was linked with this one, one of the two would be renamed,
+preventing a collision. Since "<tt>main</tt>" and "<tt>puts</tt>" are
+external (i.e., lacking any linkage declarations), they are accessible
+outside of the current module. It is illegal for a function <i>declaration</i>
+to have any linkage type other than "externally visible".</a></p>
+
+</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="callingconv">Calling Conventions</a>
+</div>
+
+<div class="doc_text">
+
+<p>LLVM <a href="#functionstructure">functions</a>, <a href="#i_call">calls</a>
+and <a href="#i_invoke">invokes</a> can all have an optional calling convention
+specified for the call. The calling convention of any pair of dynamic
+caller/callee must match, or the behavior of the program is undefined. The
+following calling conventions are supported by LLVM, and more may be added in
+the future:</p>
+
+<dl>
+ <dt><b>"<tt>ccc</tt>" - The C calling convention</b>:</dt>
+
+ <dd>This calling convention (the default if no other calling convention is
+ specified) matches the target C calling conventions. This calling convention
+ supports varargs function calls and tolerates some mismatch in the declared
+ prototype and implemented declaration of the function (as does normal C).
+ </dd>
+
+ <dt><b>"<tt>fastcc</tt>" - The fast calling convention</b>:</dt>
+
+ <dd>This calling convention attempts to make calls as fast as possible
+ (e.g. by passing things in registers). This calling convention allows the
+ target to use whatever tricks it wants to produce fast code for the target,
+ without having to conform to an externally specified ABI. Implementations of
+ this convention should allow arbitrary tail call optimization to be supported.
+ This calling convention does not support varargs and requires the prototype of
+ all callees to exactly match the prototype of the function definition.
+ </dd>
+
+ <dt><b>"<tt>coldcc</tt>" - The cold calling convention</b>:</dt>
+
+ <dd>This calling convention attempts to make code in the caller as efficient
+ as possible under the assumption that the call is not commonly executed. As
+ such, these calls often preserve all registers so that the call does not break
+ any live ranges in the caller side. This calling convention does not support
+ varargs and requires the prototype of all callees to exactly match the
+ prototype of the function definition.
+ </dd>
+
+ <dt><b>"<tt>cc <<em>n</em>></tt>" - Numbered convention</b>:</dt>
+
+ <dd>Any calling convention may be specified by number, allowing
+ target-specific calling conventions to be used. Target specific calling
+ conventions start at 64.
+ </dd>
+</dl>
+
+<p>More calling conventions can be added/defined on an as-needed basis, to
+support pascal conventions or any other well-known target-independent
+convention.</p>
+
+</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="globalvars">Global Variables</a>
+</div>
+
+<div class="doc_text">
+
+<p>Global variables define regions of memory allocated at compilation time
+instead of run-time. Global variables may optionally be initialized, may have
+an explicit section to be placed in, and may
+have an optional explicit alignment specified. A
+variable may be defined as a global "constant," which indicates that the
+contents of the variable will <b>never</b> be modified (enabling better
+optimization, allowing the global data to be placed in the read-only section of
+an executable, etc). Note that variables that need runtime initialization
+cannot be marked "constant" as there is a store to the variable.</p>
+
+<p>
+LLVM explicitly allows <em>declarations</em> of global variables to be marked
+constant, even if the final definition of the global is not. This capability
+can be used to enable slightly better optimization of the program, but requires
+the language definition to guarantee that optimizations based on the
+'constantness' are valid for the translation units that do not include the
+definition.
+</p>
+
+<p>As SSA values, global variables define pointer values that are in
+scope (i.e. they dominate) all basic blocks in the program. Global
+variables always define a pointer to their "content" type because they
+describe a region of memory, and all memory objects in LLVM are
+accessed through pointers.</p>
+
+<p>LLVM allows an explicit section to be specified for globals. If the target
+supports it, it will emit globals to the section specified.</p>
+
+<p>An explicit alignment may be specified for a global. If not present, or if
+the alignment is set to zero, the alignment of the global is set by the target
+to whatever it feels convenient. If an explicit alignment is specified, the
+global is forced to have at least that much alignment. All alignments must be
+a power of 2.</p>
+
+</div>
+
+
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="functionstructure">Functions</a>
+</div>
+
+<div class="doc_text">
+
+<p>LLVM function definitions consist of an optional <a href="#linkage">linkage
+type</a>, an optional <a href="#callingconv">calling convention</a>, a return
+type, a function name, a (possibly empty) argument list, an optional section,
+an optional alignment, an opening curly brace,
+a list of basic blocks, and a closing curly brace. LLVM function declarations
+are defined with the "<tt>declare</tt>" keyword, an optional <a
+href="#callingconv">calling convention</a>, a return type, a function name,
+a possibly empty list of arguments, and an optional alignment.</p>
+
+<p>A function definition contains a list of basic blocks, forming the CFG for
+the function. Each basic block may optionally start with a label (giving the
+basic block a symbol table entry), contains a list of instructions, and ends
+with a <a href="#terminators">terminator</a> instruction (such as a branch or
+function return).</p>
+
+<p>The first basic block in a program is special in two ways: it is immediately
+executed on entrance to the function, and it is not allowed to have predecessor
+basic blocks (i.e. there can not be any branches to the entry block of a
+function). Because the block can have no predecessors, it also cannot have any
+<a href="#i_phi">PHI nodes</a>.</p>
+
+<p>LLVM functions are identified by their name and type signature. Hence, two
+functions with the same name but different parameter lists or return values are
+considered different functions, and LLVM will resolve references to each
+appropriately.</p>
+
+<p>LLVM allows an explicit section to be specified for functions. If the target
+supports it, it will emit functions to the section specified.</p>
+
+<p>An explicit alignment may be specified for a function. If not present, or if
+the alignment is set to zero, the alignment of the function is set by the target
+to whatever it feels convenient. If an explicit alignment is specified, the
+function is forced to have at least that much alignment. All alignments must be
+a power of 2.</p>
+
+</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="moduleasm">Module-Level Inline Assembly</a></li>
+</div>
+
+<div class="doc_text">
+<p>
+Modules may contain "module-level inline asm" blocks, which corresponds to the
+GCC "file scope inline asm" blocks. These blocks are internally concatenated by
+LLVM and treated as a single unit, but may be separated in the .ll file if
+desired. The syntax is very simple:
+</p>
+
+<div class="doc_code"><pre>
+ module asm "inline asm code goes here"
+ module asm "more can go here"
+</pre></div>
+
+<p>The strings can contain any character by escaping non-printable characters.
+ The escape sequence used is simply "\xx" where "xx" is the two digit hex code
+ for the number.
+</p>
+
+<p>
+ The inline asm code is simply printed to the machine code .s file when
+ assembly code is generated.
+</p>
</div>
+
+
<!-- *********************************************************************** -->
<div class="doc_section"> <a name="typesystem">Type System</a> </div>
<!-- *********************************************************************** -->
+
<div class="doc_text">
+
<p>The LLVM type system is one of the most important features of the
intermediate representation. Being typed enables a number of
optimizations to be performed on the IR directly, without having to do
system makes it easier to read the generated code and enables novel
analyses and transformations that are not feasible to perform on normal
three address code representations.</p>
-<!-- The written form for the type system was heavily influenced by the
-syntactic problems with types in the C language<sup><a
-href="#rw_stroustrup">1</a></sup>.<p> --> </div>
+
+</div>
+
<!-- ======================================================================= -->
<div class="doc_subsection"> <a name="t_primitive">Primitive Types</a> </div>
<div class="doc_text">
-<p>The primitive types are the fundemental building blocks of the LLVM
-system. The current set of primitive types are as follows:</p>
-<p>
-<table border="0" align="center">
- <tbody>
- <tr>
- <td>
- <table border="1" cellspacing="0" cellpadding="4" align="center">
+<p>The primitive types are the fundamental building blocks of the LLVM
+system. The current set of primitive types is as follows:</p>
+
+<table class="layout">
+ <tr class="layout">
+ <td class="left">
+ <table>
<tbody>
- <tr>
- <td><tt>void</tt></td>
- <td>No value</td>
- </tr>
- <tr>
- <td><tt>ubyte</tt></td>
- <td>Unsigned 8 bit value</td>
- </tr>
- <tr>
- <td><tt>ushort</tt></td>
- <td>Unsigned 16 bit value</td>
- </tr>
- <tr>
- <td><tt>uint</tt></td>
- <td>Unsigned 32 bit value</td>
- </tr>
- <tr>
- <td><tt>ulong</tt></td>
- <td>Unsigned 64 bit value</td>
- </tr>
- <tr>
- <td><tt>float</tt></td>
- <td>32 bit floating point value</td>
- </tr>
- <tr>
- <td><tt>label</tt></td>
- <td>Branch destination</td>
- </tr>
+ <tr><th>Type</th><th>Description</th></tr>
+ <tr><td><tt>void</tt></td><td>No value</td></tr>
+ <tr><td><tt>ubyte</tt></td><td>Unsigned 8-bit value</td></tr>
+ <tr><td><tt>ushort</tt></td><td>Unsigned 16-bit value</td></tr>
+ <tr><td><tt>uint</tt></td><td>Unsigned 32-bit value</td></tr>
+ <tr><td><tt>ulong</tt></td><td>Unsigned 64-bit value</td></tr>
+ <tr><td><tt>float</tt></td><td>32-bit floating point value</td></tr>
+ <tr><td><tt>label</tt></td><td>Branch destination</td></tr>
</tbody>
</table>
- </td>
- <td valign="top">
- <table border="1" cellspacing="0" cellpadding="4" align="center"">
+ </td>
+ <td class="right">
+ <table>
<tbody>
- <tr>
- <td><tt>bool</tt></td>
- <td>True or False value</td>
- </tr>
- <tr>
- <td><tt>sbyte</tt></td>
- <td>Signed 8 bit value</td>
- </tr>
- <tr>
- <td><tt>short</tt></td>
- <td>Signed 16 bit value</td>
- </tr>
- <tr>
- <td><tt>int</tt></td>
- <td>Signed 32 bit value</td>
- </tr>
- <tr>
- <td><tt>long</tt></td>
- <td>Signed 64 bit value</td>
- </tr>
- <tr>
- <td><tt>double</tt></td>
- <td>64 bit floating point value</td>
- </tr>
+ <tr><th>Type</th><th>Description</th></tr>
+ <tr><td><tt>bool</tt></td><td>True or False value</td></tr>
+ <tr><td><tt>sbyte</tt></td><td>Signed 8-bit value</td></tr>
+ <tr><td><tt>short</tt></td><td>Signed 16-bit value</td></tr>
+ <tr><td><tt>int</tt></td><td>Signed 32-bit value</td></tr>
+ <tr><td><tt>long</tt></td><td>Signed 64-bit value</td></tr>
+ <tr><td><tt>double</tt></td><td>64-bit floating point value</td></tr>
</tbody>
</table>
- </td>
- </tr>
- </tbody>
+ </td>
+ </tr>
</table>
-</p>
</div>
+
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection"> <a name="t_classifications">Type
Classifications</a> </div>
<div class="doc_text">
<p>These different primitive types fall into a few useful
classifications:</p>
-<p>
-<table border="1" cellspacing="0" cellpadding="4" align="center">
+
+<table border="1" cellspacing="0" cellpadding="4">
<tbody>
+ <tr><th>Classification</th><th>Types</th></tr>
<tr>
<td><a name="t_signed">signed</a></td>
<td><tt>sbyte, short, int, long, float, double</tt></td>
</tr>
<tr>
<td><a name="t_integral">integral</a></td>
- <td><tt>bool, ubyte, sbyte, ushort, short, uint, int, ulong, long</tt></td>
+ <td><tt>bool, ubyte, sbyte, ushort, short, uint, int, ulong, long</tt>
+ </td>
</tr>
<tr>
<td><a name="t_floating">floating point</a></td>
</tr>
<tr>
<td><a name="t_firstclass">first class</a></td>
- <td><tt>bool, ubyte, sbyte, ushort, short,<br>
-uint, int, ulong, long, float, double, <a href="#t_pointer">pointer</a></tt></td>
+ <td><tt>bool, ubyte, sbyte, ushort, short, uint, int, ulong, long,<br>
+ float, double, <a href="#t_pointer">pointer</a>,
+ <a href="#t_packed">packed</a></tt></td>
</tr>
</tbody>
</table>
-</p>
+
<p>The <a href="#t_firstclass">first class</a> types are perhaps the
most important. Values of these types are the only ones which can be
produced by instructions, passed as arguments, or used as operands to
instructions. This means that all structures and arrays must be
manipulated either by pointer or by component.</p>
</div>
+
<!-- ======================================================================= -->
<div class="doc_subsection"> <a name="t_derived">Derived Types</a> </div>
+
<div class="doc_text">
+
<p>The real power in LLVM comes from the derived types in the system.
This is what allows a programmer to represent arrays, functions,
pointers, and other useful types. Note that these derived types may be
recursive: For example, it is possible to have a two dimensional array.</p>
+
</div>
+
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection"> <a name="t_array">Array Type</a> </div>
+
<div class="doc_text">
+
<h5>Overview:</h5>
+
<p>The array type is a very simple derived type that arranges elements
sequentially in memory. The array type requires a size (number of
elements) and an underlying data type.</p>
+
<h5>Syntax:</h5>
-<pre> [<# elements> x <elementtype>]<br></pre>
-<p>The number of elements is a constant integer value, elementtype may
+
+<pre>
+ [<# elements> x <elementtype>]
+</pre>
+
+<p>The number of elements is a constant integer value; elementtype may
be any type with a size.</p>
+
<h5>Examples:</h5>
-<p> <tt>[40 x int ]</tt>: Array of 40 integer values.<br>
-<tt>[41 x int ]</tt>: Array of 41 integer values.<br>
-<tt>[40 x uint]</tt>: Array of 40 unsigned integer values.</p>
-<p> </p>
+<table class="layout">
+ <tr class="layout">
+ <td class="left">
+ <tt>[40 x int ]</tt><br/>
+ <tt>[41 x int ]</tt><br/>
+ <tt>[40 x uint]</tt><br/>
+ </td>
+ <td class="left">
+ Array of 40 integer values.<br/>
+ Array of 41 integer values.<br/>
+ Array of 40 unsigned integer values.<br/>
+ </td>
+ </tr>
+</table>
<p>Here are some examples of multidimensional arrays:</p>
-<p>
-<table border="0" cellpadding="0" cellspacing="0">
- <tbody>
- <tr>
- <td><tt>[3 x [4 x int]]</tt></td>
- <td>: 3x4 array integer values.</td>
- </tr>
- <tr>
- <td><tt>[12 x [10 x float]]</tt></td>
- <td>: 12x10 array of single precision floating point values.</td>
- </tr>
- <tr>
- <td><tt>[2 x [3 x [4 x uint]]]</tt></td>
- <td>: 2x3x4 array of unsigned integer values.</td>
- </tr>
- </tbody>
+<table class="layout">
+ <tr class="layout">
+ <td class="left">
+ <tt>[3 x [4 x int]]</tt><br/>
+ <tt>[12 x [10 x float]]</tt><br/>
+ <tt>[2 x [3 x [4 x uint]]]</tt><br/>
+ </td>
+ <td class="left">
+ 3x4 array of integer values.<br/>
+ 12x10 array of single precision floating point values.<br/>
+ 2x3x4 array of unsigned integer values.<br/>
+ </td>
+ </tr>
</table>
-</p>
+
+<p>Note that 'variable sized arrays' can be implemented in LLVM with a zero
+length array. Normally, accesses past the end of an array are undefined in
+LLVM (e.g. it is illegal to access the 5th element of a 3 element array).
+As a special case, however, zero length arrays are recognized to be variable
+length. This allows implementation of 'pascal style arrays' with the LLVM
+type "{ int, [0 x float]}", for example.</p>
+
</div>
+
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection"> <a name="t_function">Function Type</a> </div>
<div class="doc_text">
</p>
<h5>Syntax:</h5>
<pre> <returntype> (<parameter list>)<br></pre>
-<p>Where '<tt><parameter list></tt>' is a comma-separated list of
-type specifiers. Optionally, the parameter list may include a type <tt>...</tt>,
+<p>...where '<tt><parameter list></tt>' is a comma-separated list of type
+specifiers. Optionally, the parameter list may include a type <tt>...</tt>,
which indicates that the function takes a variable number of arguments.
Variable argument functions can access their arguments with the <a
href="#int_varargs">variable argument handling intrinsic</a> functions.</p>
<h5>Examples:</h5>
-<p>
-<table border="0" cellpadding="0" cellspacing="0">
- <tbody>
- <tr>
- <td><tt>int (int)</tt></td>
- <td>: function taking an <tt>int</tt>, returning an <tt>int</tt></td>
- </tr>
- <tr>
- <td><tt>float (int, int *) *</tt></td>
- <td>: <a href="#t_pointer">Pointer</a> to a function that takes
-an <tt>int</tt> and a <a href="#t_pointer">pointer</a> to <tt>int</tt>,
-returning <tt>float</tt>.</td>
- </tr>
- <tr>
- <td><tt>int (sbyte *, ...)</tt></td>
- <td>: A vararg function that takes at least one <a
- href="#t_pointer">pointer</a> to <tt>sbyte</tt> (signed char in C),
-which returns an integer. This is the signature for <tt>printf</tt>
-in LLVM.</td>
- </tr>
- </tbody>
+<table class="layout">
+ <tr class="layout">
+ <td class="left">
+ <tt>int (int)</tt> <br/>
+ <tt>float (int, int *) *</tt><br/>
+ <tt>int (sbyte *, ...)</tt><br/>
+ </td>
+ <td class="left">
+ function taking an <tt>int</tt>, returning an <tt>int</tt><br/>
+ <a href="#t_pointer">Pointer</a> to a function that takes an
+ <tt>int</tt> and a <a href="#t_pointer">pointer</a> to <tt>int</tt>,
+ returning <tt>float</tt>.<br/>
+ A vararg function that takes at least one <a href="#t_pointer">pointer</a>
+ to <tt>sbyte</tt> (signed char in C), which returns an integer. This is
+ the signature for <tt>printf</tt> in LLVM.<br/>
+ </td>
+ </tr>
</table>
-</p>
+
</div>
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection"> <a name="t_struct">Structure Type</a> </div>
<h5>Syntax:</h5>
<pre> { <type list> }<br></pre>
<h5>Examples:</h5>
-<p>
-<table border="0" cellpadding="0" cellspacing="0">
- <tbody>
- <tr>
- <td><tt>{ int, int, int }</tt></td>
- <td>: a triple of three <tt>int</tt> values</td>
- </tr>
- <tr>
- <td><tt>{ float, int (int) * }</tt></td>
- <td>: A pair, where the first element is a <tt>float</tt> and the
-second element is a <a href="#t_pointer">pointer</a> to a <a
- href="t_function">function</a> that takes an <tt>int</tt>, returning
-an <tt>int</tt>.</td>
- </tr>
- </tbody>
+<table class="layout">
+ <tr class="layout">
+ <td class="left">
+ <tt>{ int, int, int }</tt><br/>
+ <tt>{ float, int (int) * }</tt><br/>
+ </td>
+ <td class="left">
+ a triple of three <tt>int</tt> values<br/>
+ A pair, where the first element is a <tt>float</tt> and the second element
+ is a <a href="#t_pointer">pointer</a> to a <a href="#t_function">function</a>
+ that takes an <tt>int</tt>, returning an <tt>int</tt>.<br/>
+ </td>
+ </tr>
</table>
-</p>
</div>
+
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection"> <a name="t_pointer">Pointer Type</a> </div>
<div class="doc_text">
<h5>Syntax:</h5>
<pre> <type> *<br></pre>
<h5>Examples:</h5>
-<p>
-<table border="0" cellpadding="0" cellspacing="0">
- <tbody>
- <tr>
- <td><tt>[4x int]*</tt></td>
- <td>: <a href="#t_pointer">pointer</a> to <a href="#t_array">array</a>
-of four <tt>int</tt> values</td>
- </tr>
- <tr>
- <td><tt>int (int *) *</tt></td>
- <td>: A <a href="#t_pointer">pointer</a> to a <a
- href="t_function">function</a> that takes an <tt>int</tt>, returning
-an <tt>int</tt>.</td>
- </tr>
- </tbody>
+<table class="layout">
+ <tr class="layout">
+ <td class="left">
+ <tt>[4x int]*</tt><br/>
+ <tt>int (int *) *</tt><br/>
+ </td>
+ <td class="left">
+ A <a href="#t_pointer">pointer</a> to <a href="#t_array">array</a> of
+ four <tt>int</tt> values<br/>
+ A <a href="#t_pointer">pointer</a> to a <a
+ href="#t_function">function</a> that takes an <tt>int*</tt>, returning an
+ <tt>int</tt>.<br/>
+ </td>
+ </tr>
</table>
-</p>
</div>
-<!-- _______________________________________________________________________ --><!--
-<div class="doc_subsubsection">
- <a name="t_packed">Packed Type</a>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="t_packed">Packed Type</a> </div>
+<div class="doc_text">
+
+<h5>Overview:</h5>
+
+<p>A packed type is a simple derived type that represents a vector
+of elements. Packed types are used when multiple primitive data
+are operated in parallel using a single instruction (SIMD).
+A packed type requires a size (number of
+elements) and an underlying primitive data type. Vectors must have a power
+of two length (1, 2, 4, 8, 16 ...). Packed types are
+considered <a href="#t_firstclass">first class</a>.</p>
+
+<h5>Syntax:</h5>
+
+<pre>
+ < <# elements> x <elementtype> >
+</pre>
+
+<p>The number of elements is a constant integer value; elementtype may
+be any integral or floating point type.</p>
+
+<h5>Examples:</h5>
+
+<table class="layout">
+ <tr class="layout">
+ <td class="left">
+ <tt><4 x int></tt><br/>
+ <tt><8 x float></tt><br/>
+ <tt><2 x uint></tt><br/>
+ </td>
+ <td class="left">
+ Packed vector of 4 integer values.<br/>
+ Packed vector of 8 floating-point values.<br/>
+ Packed vector of 2 unsigned integer values.<br/>
+ </td>
+ </tr>
+</table>
</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="t_opaque">Opaque Type</a> </div>
<div class="doc_text">
-Mention/decide that packed types work with saturation or not. Maybe have a packed+saturated type in addition to just a packed type.<p>
+<h5>Overview:</h5>
+
+<p>Opaque types are used to represent unknown types in the system. This
+corresponds (for example) to the C notion of a foward declared structure type.
+In LLVM, opaque types can eventually be resolved to any type (not just a
+structure type).</p>
+
+<h5>Syntax:</h5>
+
+<pre>
+ opaque
+</pre>
-Packed types should be 'nonsaturated' because standard data types are not saturated. Maybe have a saturated packed type?<p>
+<h5>Examples:</h5>
+<table class="layout">
+ <tr class="layout">
+ <td class="left">
+ <tt>opaque</tt>
+ </td>
+ <td class="left">
+ An opaque type.<br/>
+ </td>
+ </tr>
+</table>
</div>
---><!-- *********************************************************************** -->
-<div class="doc_section"> <a name="highlevel">High Level Structure</a> </div>
-<!-- *********************************************************************** --><!-- ======================================================================= -->
-<div class="doc_subsection"> <a name="modulestructure">Module Structure</a> </div>
+
+<!-- *********************************************************************** -->
+<div class="doc_section"> <a name="constants">Constants</a> </div>
+<!-- *********************************************************************** -->
+
<div class="doc_text">
-<p>LLVM programs are composed of "Module"s, each of which is a
-translation unit of the input programs. Each module consists of
-functions, global variables, and symbol table entries. Modules may be
-combined together with the LLVM linker, which merges function (and
-global variable) definitions, resolves forward declarations, and merges
-symbol table entries. Here is an example of the "hello world" module:</p>
-<pre><i>; Declare the string constant as a global constant...</i>
-<a href="#identifiers">%.LC0</a> = <a href="#linkage_internal">internal</a> <a
- href="#globalvars">constant</a> <a href="#t_array">[13 x sbyte]</a> c"hello world\0A\00" <i>; [13 x sbyte]*</i>
-<i>; External declaration of the puts function</i>
-<a href="#functionstructure">declare</a> int %puts(sbyte*) <i>; int(sbyte*)* </i>
+<p>LLVM has several different basic types of constants. This section describes
+them all and their syntax.</p>
-<i>; Definition of main function</i>
-int %main() { <i>; int()* </i>
- <i>; Convert [13x sbyte]* to sbyte *...</i>
- %cast210 = <a
- href="#i_getelementptr">getelementptr</a> [13 x sbyte]* %.LC0, long 0, long 0 <i>; sbyte*</i>
+</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection"><a name="simpleconstants">Simple Constants</a></div>
+
+<div class="doc_text">
- <i>; Call puts function to write out the string to stdout...</i>
- <a
- href="#i_call">call</a> int %puts(sbyte* %cast210) <i>; int</i>
- <a
- href="#i_ret">ret</a> int 0<br>}<br></pre>
-<p>This example is made up of a <a href="#globalvars">global variable</a>
-named "<tt>.LC0</tt>", an external declaration of the "<tt>puts</tt>"
-function, and a <a href="#functionstructure">function definition</a>
-for "<tt>main</tt>".</p>
-<a name="linkage"> In general, a module is made up of a list of global
-values, where both functions and global variables are global values.
-Global values are represented by a pointer to a memory location (in
-this case, a pointer to an array of char, and a pointer to a function),
-and have one of the following linkage types:</a>
-<p> </p>
<dl>
- <a name="linkage_internal"> <dt><tt><b>internal</b></tt> </dt>
- <dd>Global values with internal linkage are only directly accessible
-by objects in the current module. In particular, linking code into a
-module with an internal global value may cause the internal to be
-renamed as necessary to avoid collisions. Because the symbol is
-internal to the module, all references can be updated. This
-corresponds to the notion of the '<tt>static</tt>' keyword in C, or the
-idea of "anonymous namespaces" in C++.
- <p> </p>
+ <dt><b>Boolean constants</b></dt>
+
+ <dd>The two strings '<tt>true</tt>' and '<tt>false</tt>' are both valid
+ constants of the <tt><a href="#t_primitive">bool</a></tt> type.
+ </dd>
+
+ <dt><b>Integer constants</b></dt>
+
+ <dd>Standard integers (such as '4') are constants of the <a
+ href="#t_integer">integer</a> type. Negative numbers may be used with signed
+ integer types.
</dd>
- </a><a name="linkage_linkonce"> <dt><tt><b>linkonce</b></tt>: </dt>
- <dd>"<tt>linkonce</tt>" linkage is similar to <tt>internal</tt>
-linkage, with the twist that linking together two modules defining the
-same <tt>linkonce</tt> globals will cause one of the globals to be
-discarded. This is typically used to implement inline functions.
-Unreferenced <tt>linkonce</tt> globals are allowed to be discarded.
- <p> </p>
+
+ <dt><b>Floating point constants</b></dt>
+
+ <dd>Floating point constants use standard decimal notation (e.g. 123.421),
+ exponential notation (e.g. 1.23421e+2), or a more precise hexadecimal
+ notation (see below). Floating point constants must have a <a
+ href="#t_floating">floating point</a> type. </dd>
+
+ <dt><b>Null pointer constants</b></dt>
+
+ <dd>The identifier '<tt>null</tt>' is recognized as a null pointer constant
+ and must be of <a href="#t_pointer">pointer type</a>.</dd>
+
+</dl>
+
+<p>The one non-intuitive notation for constants is the optional hexadecimal form
+of floating point constants. For example, the form '<tt>double
+0x432ff973cafa8000</tt>' is equivalent to (but harder to read than) '<tt>double
+4.5e+15</tt>'. The only time hexadecimal floating point constants are required
+(and the only time that they are generated by the disassembler) is when a
+floating point constant must be emitted but it cannot be represented as a
+decimal floating point number. For example, NaN's, infinities, and other
+special values are represented in their IEEE hexadecimal format so that
+assembly and disassembly do not cause any bits to change in the constants.</p>
+
+</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection"><a name="aggregateconstants">Aggregate Constants</a>
+</div>
+
+<div class="doc_text">
+<p>Aggregate constants arise from aggregation of simple constants
+and smaller aggregate constants.</p>
+
+<dl>
+ <dt><b>Structure constants</b></dt>
+
+ <dd>Structure constants are represented with notation similar to structure
+ type definitions (a comma separated list of elements, surrounded by braces
+ (<tt>{}</tt>)). For example: "<tt>{ int 4, float 17.0, int* %G }</tt>",
+ where "<tt>%G</tt>" is declared as "<tt>%G = external global int</tt>". Structure constants
+ must have <a href="#t_struct">structure type</a>, and the number and
+ types of elements must match those specified by the type.
</dd>
- </a><a name="linkage_weak"> <dt><tt><b>weak</b></tt>: </dt>
- <dd>"<tt>weak</tt>" linkage is exactly the same as <tt>linkonce</tt>
-linkage, except that unreferenced <tt>weak</tt> globals may not be
-discarded. This is used to implement constructs in C such as "<tt>int
-X;</tt>" at global scope.
- <p> </p>
+
+ <dt><b>Array constants</b></dt>
+
+ <dd>Array constants are represented with notation similar to array type
+ definitions (a comma separated list of elements, surrounded by square brackets
+ (<tt>[]</tt>)). For example: "<tt>[ int 42, int 11, int 74 ]</tt>". Array
+ constants must have <a href="#t_array">array type</a>, and the number and
+ types of elements must match those specified by the type.
</dd>
- </a><a name="linkage_appending"> <dt><tt><b>appending</b></tt>: </dt>
- <dd>"<tt>appending</tt>" linkage may only be applied to global
-variables of pointer to array type. When two global variables with
-appending linkage are linked together, the two global arrays are
-appended together. This is the LLVM, typesafe, equivalent of having
-the system linker append together "sections" with identical names when
-.o files are linked.
- <p> </p>
+
+ <dt><b>Packed constants</b></dt>
+
+ <dd>Packed constants are represented with notation similar to packed type
+ definitions (a comma separated list of elements, surrounded by
+ less-than/greater-than's (<tt><></tt>)). For example: "<tt>< int 42,
+ int 11, int 74, int 100 ></tt>". Packed constants must have <a
+ href="#t_packed">packed type</a>, and the number and types of elements must
+ match those specified by the type.
</dd>
- </a><a name="linkage_external"> <dt><tt><b>externally visible</b></tt>:</dt>
- <dd>If none of the above identifiers are used, the global is
-externally visible, meaning that it participates in linkage and can be
-used to resolve external symbol references.
- <p> </p>
+
+ <dt><b>Zero initialization</b></dt>
+
+ <dd>The string '<tt>zeroinitializer</tt>' can be used to zero initialize a
+ value to zero of <em>any</em> type, including scalar and aggregate types.
+ This is often used to avoid having to print large zero initializers (e.g. for
+ large arrays) and is always exactly equivalent to using explicit zero
+ initializers.
</dd>
- </a>
</dl>
-<p> </p>
-<p><a name="linkage_external">For example, since the "<tt>.LC0</tt>"
-variable is defined to be internal, if another module defined a "<tt>.LC0</tt>"
-variable and was linked with this one, one of the two would be renamed,
-preventing a collision. Since "<tt>main</tt>" and "<tt>puts</tt>" are
-external (i.e., lacking any linkage declarations), they are accessible
-outside of the current module. It is illegal for a function <i>declaration</i>
-to have any linkage type other than "externally visible".</a></p>
+
</div>
+
<!-- ======================================================================= -->
-<div class="doc_subsection"> <a name="globalvars">Global Variables</a> </div>
-<div class="doc_text">
-<p>Global variables define regions of memory allocated at compilation
-time instead of run-time. Global variables may optionally be
-initialized. A variable may be defined as a global "constant", which
-indicates that the contents of the variable will never be modified
-(opening options for optimization). Constants must always have an
-initial value.</p>
-<p>As SSA values, global variables define pointer values that are in
-scope (i.e. they dominate) for all basic blocks in the program. Global
-variables always define a pointer to their "content" type because they
-describe a region of memory, and all memory objects in LLVM are
-accessed through pointers.</p>
+<div class="doc_subsection">
+ <a name="globalconstants">Global Variable and Function Addresses</a>
+</div>
+
+<div class="doc_text">
+
+<p>The addresses of <a href="#globalvars">global variables</a> and <a
+href="#functionstructure">functions</a> are always implicitly valid (link-time)
+constants. These constants are explicitly referenced when the <a
+href="#identifiers">identifier for the global</a> is used and always have <a
+href="#t_pointer">pointer</a> type. For example, the following is a legal LLVM
+file:</p>
+
+<pre>
+ %X = global int 17
+ %Y = global int 42
+ %Z = global [2 x int*] [ int* %X, int* %Y ]
+</pre>
+
+</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection"><a name="undefvalues">Undefined Values</a></div>
+<div class="doc_text">
+ <p>The string '<tt>undef</tt>' is recognized as a type-less constant that has
+ no specific value. Undefined values may be of any type and be used anywhere
+ a constant is permitted.</p>
+
+ <p>Undefined values indicate to the compiler that the program is well defined
+ no matter what value is used, giving the compiler more freedom to optimize.
+ </p>
+</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection"><a name="constantexprs">Constant Expressions</a>
+</div>
+
+<div class="doc_text">
+
+<p>Constant expressions are used to allow expressions involving other constants
+to be used as constants. Constant expressions may be of any <a
+href="#t_firstclass">first class</a> type and may involve any LLVM operation
+that does not have side effects (e.g. load and call are not supported). The
+following is the syntax for constant expressions:</p>
+
+<dl>
+ <dt><b><tt>cast ( CST to TYPE )</tt></b></dt>
+
+ <dd>Cast a constant to another type.</dd>
+
+ <dt><b><tt>getelementptr ( CSTPTR, IDX0, IDX1, ... )</tt></b></dt>
+
+ <dd>Perform the <a href="#i_getelementptr">getelementptr operation</a> on
+ constants. As with the <a href="#i_getelementptr">getelementptr</a>
+ instruction, the index list may have zero or more indexes, which are required
+ to make sense for the type of "CSTPTR".</dd>
+
+ <dt><b><tt>select ( COND, VAL1, VAL2 )</tt></b></dt>
+
+ <dd>Perform the <a href="#i_select">select operation</a> on
+ constants.
+
+ <dt><b><tt>extractelement ( VAL, IDX )</tt></b></dt>
+
+ <dd>Perform the <a href="#i_extractelement">extractelement
+ operation</a> on constants.
+
+ <dt><b><tt>insertelement ( VAL, ELT, IDX )</tt></b></dt>
+
+ <dd>Perform the <a href="#i_insertelement">insertelement
+ operation</a> on constants.
+
+ <dt><b><tt>OPCODE ( LHS, RHS )</tt></b></dt>
+
+ <dd>Perform the specified operation of the LHS and RHS constants. OPCODE may
+ be any of the <a href="#binaryops">binary</a> or <a href="#bitwiseops">bitwise
+ binary</a> operations. The constraints on operands are the same as those for
+ the corresponding instruction (e.g. no bitwise operations on floating point
+ values are allowed).</dd>
+</dl>
</div>
+
+<!-- *********************************************************************** -->
+<div class="doc_section"> <a name="othervalues">Other Values</a> </div>
+<!-- *********************************************************************** -->
+
<!-- ======================================================================= -->
-<div class="doc_subsection"> <a name="functionstructure">Functions</a> </div>
-<div class="doc_text">
-<p>LLVM function definitions are composed of a (possibly empty)
-argument list, an opening curly brace, a list of basic blocks, and a
-closing curly brace. LLVM function declarations are defined with the "<tt>declare</tt>"
-keyword, a function name, and a function signature.</p>
-<p>A function definition contains a list of basic blocks, forming the
-CFG for the function. Each basic block may optionally start with a
-label (giving the basic block a symbol table entry), contains a list of
-instructions, and ends with a <a href="#terminators">terminator</a>
-instruction (such as a branch or function return).</p>
-<p>The first basic block in program is special in two ways: it is
-immediately executed on entrance to the function, and it is not allowed
-to have predecessor basic blocks (i.e. there can not be any branches to
-the entry block of a function). Because the block can have no
-predecessors, it also cannot have any <a href="#i_phi">PHI nodes</a>.</p>
-<p>
-LLVM functions are identified by their name and type signature. Hence, two
-functions with the same name but different parameter lists or return values
-are considered different functions, and LLVM will resolves references to each
-appropriately.
+<div class="doc_subsection">
+<a name="inlineasm">Inline Assembler Expressions</a>
+</div>
+
+<div class="doc_text">
+
+<p>
+LLVM supports inline assembler expressions (as opposed to <a href="#moduleasm">
+Module-Level Inline Assembly</a>) through the use of a special value. This
+value represents the inline assembler as a string (containing the instructions
+to emit), a list of operand constraints (stored as a string), and a flag that
+indicates whether or not the inline asm expression has side effects. An example
+inline assembler expression is:
+</p>
+
+<pre>
+ int(int) asm "bswap $0", "=r,r"
+</pre>
+
+<p>
+Inline assembler expressions may <b>only</b> be used as the callee operand of
+a <a href="#i_call"><tt>call</tt> instruction</a>. Thus, typically we have:
+</p>
+
+<pre>
+ %X = call int asm "<a href="#i_bswap">bswap</a> $0", "=r,r"(int %Y)
+</pre>
+
+<p>
+Inline asms with side effects not visible in the constraint list must be marked
+as having side effects. This is done through the use of the
+'<tt>sideeffect</tt>' keyword, like so:
+</p>
+
+<pre>
+ call void asm sideeffect "eieio", ""()
+</pre>
+
+<p>TODO: The format of the asm and constraints string still need to be
+documented here. Constraints on what can be done (e.g. duplication, moving, etc
+need to be documented).
</p>
+
</div>
+
<!-- *********************************************************************** -->
<div class="doc_section"> <a name="instref">Instruction Reference</a> </div>
<!-- *********************************************************************** -->
+
<div class="doc_text">
+
<p>The LLVM instruction set consists of several different
classifications of instructions: <a href="#terminators">terminator
-instructions</a>, <a href="#binaryops">binary instructions</a>, <a
+instructions</a>, <a href="#binaryops">binary instructions</a>,
+<a href="#bitwiseops">bitwise binary instructions</a>, <a
href="#memoryops">memory instructions</a>, and <a href="#otherops">other
instructions</a>.</p>
+
</div>
+
<!-- ======================================================================= -->
<div class="doc_subsection"> <a name="terminators">Terminator
Instructions</a> </div>
+
<div class="doc_text">
+
<p>As mentioned <a href="#functionstructure">previously</a>, every
basic block in a program ends with a "Terminator" instruction, which
indicates which block should be executed after the current block is
finished. These terminator instructions typically yield a '<tt>void</tt>'
value: they produce control flow, not values (the one exception being
the '<a href="#i_invoke"><tt>invoke</tt></a>' instruction).</p>
-<p>There are five different terminator instructions: the '<a
+<p>There are six different terminator instructions: the '<a
href="#i_ret"><tt>ret</tt></a>' instruction, the '<a href="#i_br"><tt>br</tt></a>'
instruction, the '<a href="#i_switch"><tt>switch</tt></a>' instruction,
-the '<a href="#i_invoke"><tt>invoke</tt></a>' instruction, and the '<a
- href="#i_unwind"><tt>unwind</tt></a>' instruction.</p>
+the '<a href="#i_invoke"><tt>invoke</tt></a>' instruction, the '<a
+ href="#i_unwind"><tt>unwind</tt></a>' instruction, and the '<a
+ href="#i_unreachable"><tt>unreachable</tt></a>' instruction.</p>
+
</div>
+
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection"> <a name="i_ret">'<tt>ret</tt>'
Instruction</a> </div>
</pre>
<h5>Overview:</h5>
<p>The '<tt>ret</tt>' instruction is used to return control flow (and a
-value) from a function, back to the caller.</p>
-<p>There are two forms of the '<tt>ret</tt>' instructruction: one that
+value) from a function back to the caller.</p>
+<p>There are two forms of the '<tt>ret</tt>' instruction: one that
returns a value and then causes control flow, and one that just causes
control flow to occur.</p>
<h5>Arguments:</h5>
<h5>Semantics:</h5>
<p>When the '<tt>ret</tt>' instruction is executed, control flow
returns back to the calling function's context. If the caller is a "<a
- href="#i_call"><tt>call</tt></a> instruction, execution continues at
+ href="#i_call"><tt>call</tt></a>" instruction, execution continues at
the instruction after the call. If the caller was an "<a
href="#i_invoke"><tt>invoke</tt></a>" instruction, execution continues
-at the beginning "normal" of the destination block. If the instruction
+at the beginning of the "normal" destination block. If the instruction
returns a value, that value shall set the call or invoke instruction's
return value.</p>
<h5>Example:</h5>
href="#i_ret">ret</a> int 1<br>IfUnequal:<br> <a href="#i_ret">ret</a> int 0<br></pre>
</div>
<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection"> <a name="i_switch">'<tt>switch</tt>'
-Instruction</a> </div>
+<div class="doc_subsubsection">
+ <a name="i_switch">'<tt>switch</tt>' Instruction</a>
+</div>
+
<div class="doc_text">
<h5>Syntax:</h5>
-<pre> switch uint <value>, label <defaultdest> [ int <val>, label &dest>, ... ]<br></pre>
+
+<pre>
+ switch <intty> <value>, label <defaultdest> [ <intty> <val>, label <dest> ... ]
+</pre>
+
<h5>Overview:</h5>
-<p>The '<tt>switch</tt>' instruction is used to transfer control flow
-to one of several different places. It is a generalization of the '<tt>br</tt>'
+
+<p>The '<tt>switch</tt>' instruction is used to transfer control flow to one of
+several different places. It is a generalization of the '<tt>br</tt>'
instruction, allowing a branch to occur to one of many possible
destinations.</p>
+
+
<h5>Arguments:</h5>
-<p>The '<tt>switch</tt>' instruction uses three parameters: a '<tt>uint</tt>'
-comparison value '<tt>value</tt>', a default '<tt>label</tt>'
-destination, and an array of pairs of comparison value constants and '<tt>label</tt>'s.</p>
+
+<p>The '<tt>switch</tt>' instruction uses three parameters: an integer
+comparison value '<tt>value</tt>', a default '<tt>label</tt>' destination, and
+an array of pairs of comparison value constants and '<tt>label</tt>'s. The
+table is not allowed to contain duplicate constant entries.</p>
+
<h5>Semantics:</h5>
+
<p>The <tt>switch</tt> instruction specifies a table of values and
destinations. When the '<tt>switch</tt>' instruction is executed, this
-table is searched for the given value. If the value is found, the
-corresponding destination is branched to, otherwise the default value
-it transfered to.</p>
+table is searched for the given value. If the value is found, control flow is
+transfered to the corresponding destination; otherwise, control flow is
+transfered to the default destination.</p>
+
<h5>Implementation:</h5>
-<p>Depending on properties of the target machine and the particular <tt>switch</tt>
-instruction, this instruction may be code generated as a series of
-chained conditional branches, or with a lookup table.</p>
+
+<p>Depending on properties of the target machine and the particular
+<tt>switch</tt> instruction, this instruction may be code generated in different
+ways. For example, it could be generated as a series of chained conditional
+branches or with a lookup table.</p>
+
<h5>Example:</h5>
-<pre> <i>; Emulate a conditional br instruction</i>
- %Val = <a
- href="#i_cast">cast</a> bool %value to uint<br> switch uint %Val, label %truedest [int 0, label %falsedest ]<br><br> <i>; Emulate an unconditional br instruction</i>
- switch uint 0, label %dest [ ]
- <i>; Implement a jump table:</i>
- switch uint %val, label %otherwise [ int 0, label %onzero,
- int 1, label %onone,
- int 2, label %ontwo ]
+<pre>
+ <i>; Emulate a conditional br instruction</i>
+ %Val = <a href="#i_cast">cast</a> bool %value to int
+ switch int %Val, label %truedest [int 0, label %falsedest ]
+
+ <i>; Emulate an unconditional br instruction</i>
+ switch uint 0, label %dest [ ]
+
+ <i>; Implement a jump table:</i>
+ switch uint %val, label %otherwise [ uint 0, label %onzero
+ uint 1, label %onone
+ uint 2, label %ontwo ]
</pre>
</div>
+
<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection"> <a name="i_invoke">'<tt>invoke</tt>'
-Instruction</a> </div>
+<div class="doc_subsubsection">
+ <a name="i_invoke">'<tt>invoke</tt>' Instruction</a>
+</div>
+
<div class="doc_text">
+
<h5>Syntax:</h5>
-<pre> <result> = invoke <ptr to function ty> %<function ptr val>(<function args>)<br> to label <normal label> except label <exception label><br></pre>
-<h5>Overview:</h5>
-<p>The '<tt>invoke</tt>' instruction causes control to transfer to a
-specified function, with the possibility of control flow transfer to
-either the '<tt>normal</tt>' <tt>label</tt> label or the '<tt>exception</tt>'<tt>label</tt>.
-If the callee function returns with the "<tt><a href="#i_ret">ret</a></tt>"
-instruction, control flow will return to the "normal" label. If the
-callee (or any indirect callees) returns with the "<a href="#i_unwind"><tt>unwind</tt></a>"
-instruction, control is interrupted, and continued at the dynamically
-nearest "except" label.</p>
-<h5>Arguments:</h5>
-<p>This instruction requires several arguments:</p>
+
+<pre>
+ <result> = invoke [<a href="#callingconv">cconv</a>] <ptr to function ty> %<function ptr val>(<function args>)
+ to label <normal label> except label <exception label>
+</pre>
+
+<h5>Overview:</h5>
+
+<p>The '<tt>invoke</tt>' instruction causes control to transfer to a specified
+function, with the possibility of control flow transfer to either the
+'<tt>normal</tt>' label or the
+'<tt>exception</tt>' label. If the callee function returns with the
+"<tt><a href="#i_ret">ret</a></tt>" instruction, control flow will return to the
+"normal" label. If the callee (or any indirect callees) returns with the "<a
+href="#i_unwind"><tt>unwind</tt></a>" instruction, control is interrupted and
+continued at the dynamically nearest "exception" label.</p>
+
+<h5>Arguments:</h5>
+
+<p>This instruction requires several arguments:</p>
+
<ol>
- <li>'<tt>ptr to function ty</tt>': shall be the signature of the
-pointer to function value being invoked. In most cases, this is a
-direct function invocation, but indirect <tt>invoke</tt>s are just as
-possible, branching off an arbitrary pointer to function value. </li>
- <li>'<tt>function ptr val</tt>': An LLVM value containing a pointer
-to a function to be invoked. </li>
- <li>'<tt>function args</tt>': argument list whose types match the
-function signature argument types. If the function signature indicates
-the function accepts a variable number of arguments, the extra
-arguments can be specified. </li>
- <li>'<tt>normal label</tt>': the label reached when the called
-function executes a '<tt><a href="#i_ret">ret</a></tt>' instruction. </li>
- <li>'<tt>exception label</tt>': the label reached when a callee
-returns with the <a href="#i_unwind"><tt>unwind</tt></a> instruction. </li>
+ <li>
+ The optional "cconv" marker indicates which <a href="callingconv">calling
+ convention</a> the call should use. If none is specified, the call defaults
+ to using C calling conventions.
+ </li>
+ <li>'<tt>ptr to function ty</tt>': shall be the signature of the pointer to
+ function value being invoked. In most cases, this is a direct function
+ invocation, but indirect <tt>invoke</tt>s are just as possible, branching off
+ an arbitrary pointer to function value.
+ </li>
+
+ <li>'<tt>function ptr val</tt>': An LLVM value containing a pointer to a
+ function to be invoked. </li>
+
+ <li>'<tt>function args</tt>': argument list whose types match the function
+ signature argument types. If the function signature indicates the function
+ accepts a variable number of arguments, the extra arguments can be
+ specified. </li>
+
+ <li>'<tt>normal label</tt>': the label reached when the called function
+ executes a '<tt><a href="#i_ret">ret</a></tt>' instruction. </li>
+
+ <li>'<tt>exception label</tt>': the label reached when a callee returns with
+ the <a href="#i_unwind"><tt>unwind</tt></a> instruction. </li>
+
</ol>
+
<h5>Semantics:</h5>
+
<p>This instruction is designed to operate as a standard '<tt><a
- href="#i_call">call</a></tt>' instruction in most regards. The
-primary difference is that it establishes an association with a label,
-which is used by the runtime library to unwind the stack.</p>
-<p>This instruction is used in languages with destructors to ensure
-that proper cleanup is performed in the case of either a <tt>longjmp</tt>
-or a thrown exception. Additionally, this is important for
-implementation of '<tt>catch</tt>' clauses in high-level languages that
-support them.</p>
+href="#i_call">call</a></tt>' instruction in most regards. The primary
+difference is that it establishes an association with a label, which is used by
+the runtime library to unwind the stack.</p>
+
+<p>This instruction is used in languages with destructors to ensure that proper
+cleanup is performed in the case of either a <tt>longjmp</tt> or a thrown
+exception. Additionally, this is important for implementation of
+'<tt>catch</tt>' clauses in high-level languages that support them.</p>
+
<h5>Example:</h5>
-<pre> %retval = invoke int %Test(int 15)<br> to label %Continue<br> except label %TestCleanup <i>; {int}:retval set</i>
+<pre>
+ %retval = invoke int %Test(int 15) to label %Continue
+ except label %TestCleanup <i>; {int}:retval set</i>
+ %retval = invoke <a href="#callingconv">coldcc</a> int %Test(int 15) to label %Continue
+ except label %TestCleanup <i>; {int}:retval set</i>
</pre>
</div>
+
+
<!-- _______________________________________________________________________ -->
+
<div class="doc_subsubsection"> <a name="i_unwind">'<tt>unwind</tt>'
Instruction</a> </div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ unwind
+</pre>
+
+<h5>Overview:</h5>
+
+<p>The '<tt>unwind</tt>' instruction unwinds the stack, continuing control flow
+at the first callee in the dynamic call stack which used an <a
+href="#i_invoke"><tt>invoke</tt></a> instruction to perform the call. This is
+primarily used to implement exception handling.</p>
+
+<h5>Semantics:</h5>
+
+<p>The '<tt>unwind</tt>' intrinsic causes execution of the current function to
+immediately halt. The dynamic call stack is then searched for the first <a
+href="#i_invoke"><tt>invoke</tt></a> instruction on the call stack. Once found,
+execution continues at the "exceptional" destination block specified by the
+<tt>invoke</tt> instruction. If there is no <tt>invoke</tt> instruction in the
+dynamic call chain, undefined behavior results.</p>
+</div>
+
+<!-- _______________________________________________________________________ -->
+
+<div class="doc_subsubsection"> <a name="i_unreachable">'<tt>unreachable</tt>'
+Instruction</a> </div>
+
<div class="doc_text">
+
<h5>Syntax:</h5>
-<pre> unwind<br></pre>
+<pre>
+ unreachable
+</pre>
+
<h5>Overview:</h5>
-<p>The '<tt>unwind</tt>' instruction unwinds the stack, continuing
-control flow at the first callee in the dynamic call stack which used
-an <a href="#i_invoke"><tt>invoke</tt></a> instruction to perform the
-call. This is primarily used to implement exception handling.</p>
+
+<p>The '<tt>unreachable</tt>' instruction has no defined semantics. This
+instruction is used to inform the optimizer that a particular portion of the
+code is not reachable. This can be used to indicate that the code after a
+no-return function cannot be reached, and other facts.</p>
+
<h5>Semantics:</h5>
-<p>The '<tt>unwind</tt>' intrinsic causes execution of the current
-function to immediately halt. The dynamic call stack is then searched
-for the first <a href="#i_invoke"><tt>invoke</tt></a> instruction on
-the call stack. Once found, execution continues at the "exceptional"
-destination block specified by the <tt>invoke</tt> instruction. If
-there is no <tt>invoke</tt> instruction in the dynamic call chain,
-undefined behavior results.</p>
+
+<p>The '<tt>unreachable</tt>' instruction has no defined semantics.</p>
</div>
+
+
+
<!-- ======================================================================= -->
<div class="doc_subsection"> <a name="binaryops">Binary Operations</a> </div>
<div class="doc_text">
<p>Binary operators are used to do most of the computation in a
program. They require two operands, execute an operation on them, and
-produce a single value. The result value of a binary operator is not
+produce a single value. The operands might represent
+multiple data, as is the case with the <a href="#t_packed">packed</a> data type.
+The result value of a binary operator is not
necessarily the same type as its operands.</p>
<p>There are several different binary operators:</p>
</div>
<p>The '<tt>add</tt>' instruction returns the sum of its two operands.</p>
<h5>Arguments:</h5>
<p>The two arguments to the '<tt>add</tt>' instruction must be either <a
- href="#t_integer">integer</a> or <a href="#t_floating">floating point</a>
-values. Both arguments must have identical types.</p>
+ href="#t_integer">integer</a> or <a href="#t_floating">floating point</a> values.
+ This instruction can also take <a href="#t_packed">packed</a> versions of the values.
+Both arguments must have identical types.</p>
<h5>Semantics:</h5>
<p>The value produced is the integer or floating point sum of the two
operands.</p>
<h5>Arguments:</h5>
<p>The two arguments to the '<tt>sub</tt>' instruction must be either <a
href="#t_integer">integer</a> or <a href="#t_floating">floating point</a>
-values. Both arguments must have identical types.</p>
+values.
+This instruction can also take <a href="#t_packed">packed</a> versions of the values.
+Both arguments must have identical types.</p>
<h5>Semantics:</h5>
<p>The value produced is the integer or floating point difference of
the two operands.</p>
<h5>Arguments:</h5>
<p>The two arguments to the '<tt>mul</tt>' instruction must be either <a
href="#t_integer">integer</a> or <a href="#t_floating">floating point</a>
-values. Both arguments must have identical types.</p>
+values.
+This instruction can also take <a href="#t_packed">packed</a> versions of the values.
+Both arguments must have identical types.</p>
<h5>Semantics:</h5>
<p>The value produced is the integer or floating point product of the
two operands.</p>
<h5>Arguments:</h5>
<p>The two arguments to the '<tt>div</tt>' instruction must be either <a
href="#t_integer">integer</a> or <a href="#t_floating">floating point</a>
-values. Both arguments must have identical types.</p>
+values.
+This instruction can also take <a href="#t_packed">packed</a> versions of the values.
+Both arguments must have identical types.</p>
<h5>Semantics:</h5>
<p>The value produced is the integer or floating point quotient of the
two operands.</p>
<h5>Arguments:</h5>
<p>The two arguments to the '<tt>rem</tt>' instruction must be either <a
href="#t_integer">integer</a> or <a href="#t_floating">floating point</a>
-values. Both arguments must have identical types.</p>
+values.
+This instruction can also take <a href="#t_packed">packed</a> versions of the values.
+Both arguments must have identical types.</p>
<h5>Semantics:</h5>
<p>This returns the <i>remainder</i> of a division (where the result
has the same sign as the divisor), not the <i>modulus</i> (where the
result has the same sign as the dividend) of a value. For more
-information about the difference, see: <a
+information about the difference, see <a
href="http://mathforum.org/dr.math/problems/anne.4.28.99.html">The
Math Forum</a>.</p>
<h5>Example:</h5>
<pre> <result> = rem int 4, %var <i>; yields {int}:result = 4 % %var</i>
</pre>
+
</div>
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection"> <a name="i_setcc">'<tt>set<i>cc</i></tt>'
<result> = setge sbyte 4, 5 <i>; yields {bool}:result = false</i>
</pre>
</div>
+
<!-- ======================================================================= -->
<div class="doc_subsection"> <a name="bitwiseops">Bitwise Binary
Operations</a> </div>
<div class="doc_text">
<p>Bitwise binary operators are used to do various forms of
bit-twiddling in a program. They are generally very efficient
-instructions, and can commonly be strength reduced from other
+instructions and can commonly be strength reduced from other
instructions. They require two operands, execute an operation on them,
and produce a single value. The resulting value of the bitwise binary
operators is always the same type as its first operand.</p>
<h5>Semantics:</h5>
<p>The truth table used for the '<tt>and</tt>' instruction is:</p>
<p> </p>
-<center>
+<div style="align: center">
<table border="1" cellspacing="0" cellpadding="4">
<tbody>
<tr>
</tr>
</tbody>
</table>
-</center>
+</div>
<h5>Example:</h5>
<pre> <result> = and int 4, %var <i>; yields {int}:result = 4 & %var</i>
<result> = and int 15, 40 <i>; yields {int}:result = 8</i>
<h5>Semantics:</h5>
<p>The truth table used for the '<tt>or</tt>' instruction is:</p>
<p> </p>
-<center>
+<div style="align: center">
<table border="1" cellspacing="0" cellpadding="4">
<tbody>
<tr>
</tr>
</tbody>
</table>
-</center>
+</div>
<h5>Example:</h5>
<pre> <result> = or int 4, %var <i>; yields {int}:result = 4 | %var</i>
<result> = or int 15, 40 <i>; yields {int}:result = 47</i>
<h5>Semantics:</h5>
<p>The truth table used for the '<tt>xor</tt>' instruction is:</p>
<p> </p>
-<center>
+<div style="align: center">
<table border="1" cellspacing="0" cellpadding="4">
<tbody>
<tr>
</tr>
</tbody>
</table>
-</center>
+</div>
<p> </p>
<h5>Example:</h5>
<pre> <result> = xor int 4, %var <i>; yields {int}:result = 4 ^ %var</i>
<result> = shr sbyte -2, ubyte 1 <i>; yields {sbyte}:result = -1</i>
</pre>
</div>
+
<!-- ======================================================================= -->
-<div class="doc_subsection"> <a name="memoryops">Memory Access
-Operations</a></div>
+<div class="doc_subsection">
+ <a name="memoryops">Memory Access Operations</a>
+</div>
+
<div class="doc_text">
+
<p>A key design point of an SSA-based representation is how it
represents memory. In LLVM, no memory locations are in SSA form, which
makes things very simple. This section describes how to read, write,
-allocate and free memory in LLVM.</p>
+allocate, and free memory in LLVM.</p>
+
</div>
+
<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection"> <a name="i_malloc">'<tt>malloc</tt>'
-Instruction</a> </div>
+<div class="doc_subsubsection">
+ <a name="i_malloc">'<tt>malloc</tt>' Instruction</a>
+</div>
+
<div class="doc_text">
+
<h5>Syntax:</h5>
-<pre> <result> = malloc <type>, uint <NumElements> <i>; yields {type*}:result</i>
- <result> = malloc <type> <i>; yields {type*}:result</i>
+
+<pre>
+ <result> = malloc <type>[, uint <NumElements>][, align <alignment>] <i>; yields {type*}:result</i>
</pre>
+
<h5>Overview:</h5>
+
<p>The '<tt>malloc</tt>' instruction allocates memory from the system
heap and returns a pointer to it.</p>
+
<h5>Arguments:</h5>
-<p>The the '<tt>malloc</tt>' instruction allocates <tt>sizeof(<type>)*NumElements</tt>
-bytes of memory from the operating system, and returns a pointer of the
-appropriate type to the program. The second form of the instruction is
-a shorter version of the first instruction that defaults to allocating
-one element.</p>
+
+<p>The '<tt>malloc</tt>' instruction allocates
+<tt>sizeof(<type>)*NumElements</tt>
+bytes of memory from the operating system and returns a pointer of the
+appropriate type to the program. If "NumElements" is specified, it is the
+number of elements allocated. If an alignment is specified, the value result
+of the allocation is guaranteed to be aligned to at least that boundary. If
+not specified, or if zero, the target can choose to align the allocation on any
+convenient boundary.</p>
+
<p>'<tt>type</tt>' must be a sized type.</p>
+
<h5>Semantics:</h5>
+
<p>Memory is allocated using the system "<tt>malloc</tt>" function, and
a pointer is returned.</p>
+
<h5>Example:</h5>
-<pre> %array = malloc [4 x ubyte ] <i>; yields {[%4 x ubyte]*}:array</i>
- %size = <a
- href="#i_add">add</a> uint 2, 2 <i>; yields {uint}:size = uint 4</i>
+<pre>
+ %array = malloc [4 x ubyte ] <i>; yields {[%4 x ubyte]*}:array</i>
+
+ %size = <a href="#i_add">add</a> uint 2, 2 <i>; yields {uint}:size = uint 4</i>
%array1 = malloc ubyte, uint 4 <i>; yields {ubyte*}:array1</i>
%array2 = malloc [12 x ubyte], uint %size <i>; yields {[12 x ubyte]*}:array2</i>
+ %array3 = malloc int, uint 4, align 1024 <i>; yields {int*}:array3</i>
+ %array4 = malloc int, align 1024 <i>; yields {int*}:array4</i>
</pre>
</div>
+
<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection"> <a name="i_free">'<tt>free</tt>'
-Instruction</a> </div>
+<div class="doc_subsubsection">
+ <a name="i_free">'<tt>free</tt>' Instruction</a>
+</div>
+
<div class="doc_text">
+
<h5>Syntax:</h5>
-<pre> free <type> <value> <i>; yields {void}</i>
+
+<pre>
+ free <type> <value> <i>; yields {void}</i>
</pre>
+
<h5>Overview:</h5>
+
<p>The '<tt>free</tt>' instruction returns memory back to the unused
-memory heap, to be reallocated in the future.</p>
-<p> </p>
+memory heap to be reallocated in the future.</p>
+
<h5>Arguments:</h5>
+
<p>'<tt>value</tt>' shall be a pointer value that points to a value
that was allocated with the '<tt><a href="#i_malloc">malloc</a></tt>'
instruction.</p>
+
<h5>Semantics:</h5>
-<p>Access to the memory pointed to by the pointer is not longer defined
+
+<p>Access to the memory pointed to by the pointer is no longer defined
after this instruction executes.</p>
+
<h5>Example:</h5>
-<pre> %array = <a href="#i_malloc">malloc</a> [4 x ubyte] <i>; yields {[4 x ubyte]*}:array</i>
+
+<pre>
+ %array = <a href="#i_malloc">malloc</a> [4 x ubyte] <i>; yields {[4 x ubyte]*}:array</i>
free [4 x ubyte]* %array
</pre>
</div>
+
<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection"> <a name="i_alloca">'<tt>alloca</tt>'
-Instruction</a> </div>
+<div class="doc_subsubsection">
+ <a name="i_alloca">'<tt>alloca</tt>' Instruction</a>
+</div>
+
<div class="doc_text">
+
<h5>Syntax:</h5>
-<pre> <result> = alloca <type>, uint <NumElements> <i>; yields {type*}:result</i>
- <result> = alloca <type> <i>; yields {type*}:result</i>
+
+<pre>
+ <result> = alloca <type>[, uint <NumElements>][, align <alignment>] <i>; yields {type*}:result</i>
</pre>
+
<h5>Overview:</h5>
+
<p>The '<tt>alloca</tt>' instruction allocates memory on the current
stack frame of the procedure that is live until the current function
returns to its caller.</p>
+
<h5>Arguments:</h5>
-<p>The the '<tt>alloca</tt>' instruction allocates <tt>sizeof(<type>)*NumElements</tt>
+
+<p>The '<tt>alloca</tt>' instruction allocates <tt>sizeof(<type>)*NumElements</tt>
bytes of memory on the runtime stack, returning a pointer of the
-appropriate type to the program. The second form of the instruction is
-a shorter version of the first that defaults to allocating one element.</p>
+appropriate type to the program. If "NumElements" is specified, it is the
+number of elements allocated. If an alignment is specified, the value result
+of the allocation is guaranteed to be aligned to at least that boundary. If
+not specified, or if zero, the target can choose to align the allocation on any
+convenient boundary.</p>
+
<p>'<tt>type</tt>' may be any sized type.</p>
+
<h5>Semantics:</h5>
-<p>Memory is allocated, a pointer is returned. '<tt>alloca</tt>'d
+
+<p>Memory is allocated; a pointer is returned. '<tt>alloca</tt>'d
memory is automatically released when the function returns. The '<tt>alloca</tt>'
instruction is commonly used to represent automatic variables that must
have an address available. When the function returns (either with the <tt><a
- href="#i_ret">ret</a></tt> or <tt><a href="#i_invoke">invoke</a></tt>
+ href="#i_ret">ret</a></tt> or <tt><a href="#i_unwind">unwind</a></tt>
instructions), the memory is reclaimed.</p>
+
<h5>Example:</h5>
-<pre> %ptr = alloca int <i>; yields {int*}:ptr</i>
+
+<pre>
+ %ptr = alloca int <i>; yields {int*}:ptr</i>
%ptr = alloca int, uint 4 <i>; yields {int*}:ptr</i>
+ %ptr = alloca int, uint 4, align 1024 <i>; yields {int*}:ptr</i>
+ %ptr = alloca int, align 1024 <i>; yields {int*}:ptr</i>
</pre>
</div>
+
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection"> <a name="i_load">'<tt>load</tt>'
Instruction</a> </div>
<p>The '<tt>load</tt>' instruction is used to read from memory.</p>
<h5>Arguments:</h5>
<p>The argument to the '<tt>load</tt>' instruction specifies the memory
-address to load from. The pointer must point to a <a
- href="t_firstclass">first class</a> type. If the <tt>load</tt> is
-marked as <tt>volatile</tt> then the optimizer is not allowed to modify
+address from which to load. The pointer must point to a <a
+ href="#t_firstclass">first class</a> type. If the <tt>load</tt> is
+marked as <tt>volatile</tt>, then the optimizer is not allowed to modify
the number or order of execution of this <tt>load</tt> with other
volatile <tt>load</tt> and <tt><a href="#i_store">store</a></tt>
instructions. </p>
<p>The '<tt>store</tt>' instruction is used to write to memory.</p>
<h5>Arguments:</h5>
<p>There are two arguments to the '<tt>store</tt>' instruction: a value
-to store and an address to store it into. The type of the '<tt><pointer></tt>'
+to store and an address in which to store it. The type of the '<tt><pointer></tt>'
operand must be a pointer to the type of the '<tt><value></tt>'
-operand. If the <tt>store</tt> is marked as <tt>volatile</tt> then the
+operand. If the <tt>store</tt> is marked as <tt>volatile</tt>, then the
optimizer is not allowed to modify the number or order of execution of
this <tt>store</tt> with other volatile <tt>load</tt> and <tt><a
href="#i_store">store</a></tt> instructions.</p>
%val = load int* %ptr <i>; yields {int}:val = int 3</i>
</pre>
<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection"> <a name="i_getelementptr">'<tt>getelementptr</tt>'
-Instruction</a> </div>
+<div class="doc_subsubsection">
+ <a name="i_getelementptr">'<tt>getelementptr</tt>' Instruction</a>
+</div>
+
<div class="doc_text">
<h5>Syntax:</h5>
-<pre> <result> = getelementptr <ty>* <ptrval>{, long <aidx>|, ubyte <sidx>}*<br></pre>
+<pre>
+ <result> = getelementptr <ty>* <ptrval>{, <ty> <idx>}*
+</pre>
+
<h5>Overview:</h5>
-<p>The '<tt>getelementptr</tt>' instruction is used to get the address
-of a subelement of an aggregate data structure.</p>
+
+<p>
+The '<tt>getelementptr</tt>' instruction is used to get the address of a
+subelement of an aggregate data structure.</p>
+
<h5>Arguments:</h5>
-<p>This instruction takes a list of <tt>long</tt> values and <tt>ubyte</tt>
-constants that indicate what form of addressing to perform. The actual
-types of the arguments provided depend on the type of the first pointer
-argument. The '<tt>getelementptr</tt>' instruction is used to index
-down through the type levels of a structure.</p>
+
+<p>This instruction takes a list of integer constants that indicate what
+elements of the aggregate object to index to. The actual types of the arguments
+provided depend on the type of the first pointer argument. The
+'<tt>getelementptr</tt>' instruction is used to index down through the type
+levels of a structure or to a specific index in an array. When indexing into a
+structure, only <tt>uint</tt>
+integer constants are allowed. When indexing into an array or pointer,
+<tt>int</tt> and <tt>long</tt> indexes are allowed of any sign.</p>
+
<p>For example, let's consider a C code fragment and how it gets
compiled to LLVM:</p>
-<pre>struct RT {<br> char A;<br> int B[10][20];<br> char C;<br>};<br>struct ST {<br> int X;<br> double Y;<br> struct RT Z;<br>};<br><br>int *foo(struct ST *s) {<br> return &s[1].Z.B[5][13];<br>}<br></pre>
+
+<pre>
+ struct RT {
+ char A;
+ int B[10][20];
+ char C;
+ };
+ struct ST {
+ int X;
+ double Y;
+ struct RT Z;
+ };
+
+ int *foo(struct ST *s) {
+ return &s[1].Z.B[5][13];
+ }
+</pre>
+
<p>The LLVM code generated by the GCC frontend is:</p>
-<pre>%RT = type { sbyte, [10 x [20 x int]], sbyte }<br>%ST = type { int, double, %RT }<br><br>int* "foo"(%ST* %s) {<br> %reg = getelementptr %ST* %s, long 1, ubyte 2, ubyte 1, long 5, long 13<br> ret int* %reg<br>}<br></pre>
+
+<pre>
+ %RT = type { sbyte, [10 x [20 x int]], sbyte }
+ %ST = type { int, double, %RT }
+
+ implementation
+
+ int* %foo(%ST* %s) {
+ entry:
+ %reg = getelementptr %ST* %s, int 1, uint 2, uint 1, int 5, int 13
+ ret int* %reg
+ }
+</pre>
+
<h5>Semantics:</h5>
-<p>The index types specified for the '<tt>getelementptr</tt>'
-instruction depend on the pointer type that is being index into. <a
- href="t_pointer">Pointer</a> and <a href="t_array">array</a> types
-require '<tt>long</tt>' values, and <a href="t_struct">structure</a>
-types require '<tt>ubyte</tt>' <b>constants</b>.</p>
+
+<p>The index types specified for the '<tt>getelementptr</tt>' instruction depend
+on the pointer type that is being indexed into. <a href="#t_pointer">Pointer</a>
+and <a href="#t_array">array</a> types require <tt>uint</tt>, <tt>int</tt>,
+<tt>ulong</tt>, or <tt>long</tt> values, and <a href="#t_struct">structure</a>
+types require <tt>uint</tt> <b>constants</b>.</p>
+
<p>In the example above, the first index is indexing into the '<tt>%ST*</tt>'
-type, which is a pointer, yielding a '<tt>%ST</tt>' = '<tt>{ int,
-double, %RT }</tt>' type, a structure. The second index indexes into
-the third element of the structure, yielding a '<tt>%RT</tt>' = '<tt>{
-sbyte, [10 x [20 x int]], sbyte }</tt>' type, another structure. The
-third index indexes into the second element of the structure, yielding
-a '<tt>[10 x [20 x int]]</tt>' type, an array. The two dimensions of
-the array are subscripted into, yielding an '<tt>int</tt>' type. The '<tt>getelementptr</tt>'
-instruction return a pointer to this element, thus yielding a '<tt>int*</tt>'
-type.</p>
+type, which is a pointer, yielding a '<tt>%ST</tt>' = '<tt>{ int, double, %RT
+}</tt>' type, a structure. The second index indexes into the third element of
+the structure, yielding a '<tt>%RT</tt>' = '<tt>{ sbyte, [10 x [20 x int]],
+sbyte }</tt>' type, another structure. The third index indexes into the second
+element of the structure, yielding a '<tt>[10 x [20 x int]]</tt>' type, an
+array. The two dimensions of the array are subscripted into, yielding an
+'<tt>int</tt>' type. The '<tt>getelementptr</tt>' instruction returns a pointer
+to this element, thus computing a value of '<tt>int*</tt>' type.</p>
+
<p>Note that it is perfectly legal to index partially through a
structure, returning a pointer to an inner element. Because of this,
the LLVM code for the given testcase is equivalent to:</p>
-<pre>int* "foo"(%ST* %s) {<br> %t1 = getelementptr %ST* %s , long 1 <i>; yields %ST*:%t1</i>
- %t2 = getelementptr %ST* %t1, long 0, ubyte 2 <i>; yields %RT*:%t2</i>
- %t3 = getelementptr %RT* %t2, long 0, ubyte 1 <i>; yields [10 x [20 x int]]*:%t3</i>
- %t4 = getelementptr [10 x [20 x int]]* %t3, long 0, long 5 <i>; yields [20 x int]*:%t4</i>
- %t5 = getelementptr [20 x int]* %t4, long 0, long 13 <i>; yields int*:%t5</i>
- ret int* %t5
-}
+
+<pre>
+ int* %foo(%ST* %s) {
+ %t1 = getelementptr %ST* %s, int 1 <i>; yields %ST*:%t1</i>
+ %t2 = getelementptr %ST* %t1, int 0, uint 2 <i>; yields %RT*:%t2</i>
+ %t3 = getelementptr %RT* %t2, int 0, uint 1 <i>; yields [10 x [20 x int]]*:%t3</i>
+ %t4 = getelementptr [10 x [20 x int]]* %t3, int 0, int 5 <i>; yields [20 x int]*:%t4</i>
+ %t5 = getelementptr [20 x int]* %t4, int 0, int 13 <i>; yields int*:%t5</i>
+ ret int* %t5
+ }
</pre>
+
+<p>Note that it is undefined to access an array out of bounds: array and
+pointer indexes must always be within the defined bounds of the array type.
+The one exception for this rules is zero length arrays. These arrays are
+defined to be accessible as variable length arrays, which requires access
+beyond the zero'th element.</p>
+
<h5>Example:</h5>
-<pre> <i>; yields [12 x ubyte]*:aptr</i>
- %aptr = getelementptr {int, [12 x ubyte]}* %sptr, long 0, ubyte 1<br></pre>
-<h5> Note To The Novice:</h5>
-When using indexing into global arrays with the '<tt>getelementptr</tt>'
-instruction, you must remember that the </div>
+
+<pre>
+ <i>; yields [12 x ubyte]*:aptr</i>
+ %aptr = getelementptr {int, [12 x ubyte]}* %sptr, long 0, uint 1
+</pre>
+
+</div>
<!-- ======================================================================= -->
<div class="doc_subsection"> <a name="otherops">Other Operations</a> </div>
<div class="doc_text">
-<p>The instructions in this catagory are the "miscellaneous"
+<p>The instructions in this category are the "miscellaneous"
instructions, which defy better classification.</p>
</div>
<!-- _______________________________________________________________________ -->
<h5>Example:</h5>
<pre>Loop: ; Infinite loop that counts from 0 on up...<br> %indvar = phi uint [ 0, %LoopHeader ], [ %nextindvar, %Loop ]<br> %nextindvar = add uint %indvar, 1<br> br label %Loop<br></pre>
</div>
+
<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection"> <a name="i_cast">'<tt>cast .. to</tt>'
-Instruction</a> </div>
+<div class="doc_subsubsection">
+ <a name="i_cast">'<tt>cast .. to</tt>' Instruction</a>
+</div>
+
<div class="doc_text">
+
<h5>Syntax:</h5>
-<pre> <result> = cast <ty> <value> to <ty2> <i>; yields ty2</i>
+
+<pre>
+ <result> = cast <ty> <value> to <ty2> <i>; yields ty2</i>
</pre>
+
<h5>Overview:</h5>
-<p>The '<tt>cast</tt>' instruction is used as the primitive means to
-convert integers to floating point, change data type sizes, and break
-type safety (by casting pointers).</p>
+
+<p>
+The '<tt>cast</tt>' instruction is used as the primitive means to convert
+integers to floating point, change data type sizes, and break type safety (by
+casting pointers).
+</p>
+
+
<h5>Arguments:</h5>
-<p>The '<tt>cast</tt>' instruction takes a value to cast, which must be
-a first class value, and a type to cast it to, which must also be a <a
- href="#t_firstclass">first class</a> type.</p>
+
+<p>
+The '<tt>cast</tt>' instruction takes a value to cast, which must be a first
+class value, and a type to cast it to, which must also be a <a
+href="#t_firstclass">first class</a> type.
+</p>
+
<h5>Semantics:</h5>
-<p>This instruction follows the C rules for explicit casts when
-determining how the data being cast must change to fit in its new
-container.</p>
-<p>When casting to bool, any value that would be considered true in the
-context of a C '<tt>if</tt>' condition is converted to the boolean '<tt>true</tt>'
-values, all else are '<tt>false</tt>'.</p>
-<p>When extending an integral value from a type of one signness to
-another (for example '<tt>sbyte</tt>' to '<tt>ulong</tt>'), the value
-is sign-extended if the <b>source</b> value is signed, and
-zero-extended if the source value is unsigned. <tt>bool</tt> values
-are always zero extended into either zero or one.</p>
+
+<p>
+This instruction follows the C rules for explicit casts when determining how the
+data being cast must change to fit in its new container.
+</p>
+
+<p>
+When casting to bool, any value that would be considered true in the context of
+a C '<tt>if</tt>' condition is converted to the boolean '<tt>true</tt>' values,
+all else are '<tt>false</tt>'.
+</p>
+
+<p>
+When extending an integral value from a type of one signness to another (for
+example '<tt>sbyte</tt>' to '<tt>ulong</tt>'), the value is sign-extended if the
+<b>source</b> value is signed, and zero-extended if the source value is
+unsigned. <tt>bool</tt> values are always zero extended into either zero or
+one.
+</p>
+
<h5>Example:</h5>
-<pre> %X = cast int 257 to ubyte <i>; yields ubyte:1</i>
+
+<pre>
+ %X = cast int 257 to ubyte <i>; yields ubyte:1</i>
%Y = cast int 123 to bool <i>; yields bool:true</i>
</pre>
</div>
+
<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection"> <a name="i_call">'<tt>call</tt>'
-Instruction</a> </div>
+<div class="doc_subsubsection">
+ <a name="i_select">'<tt>select</tt>' Instruction</a>
+</div>
+
<div class="doc_text">
+
<h5>Syntax:</h5>
-<pre> <result> = call <ty>* <fnptrval>(<param list>)<br></pre>
+
+<pre>
+ <result> = select bool <cond>, <ty> <val1>, <ty> <val2> <i>; yields ty</i>
+</pre>
+
<h5>Overview:</h5>
-<p>The '<tt>call</tt>' instruction represents a simple function call.</p>
+
+<p>
+The '<tt>select</tt>' instruction is used to choose one value based on a
+condition, without branching.
+</p>
+
+
<h5>Arguments:</h5>
-<p>This instruction requires several arguments:</p>
-<ol>
- <li>
- <p>'<tt>ty</tt>': shall be the signature of the pointer to function
-value being invoked. The argument types must match the types implied
-by this signature.</p>
- </li>
- <li>
- <p>'<tt>fnptrval</tt>': An LLVM value containing a pointer to a
-function to be invoked. In most cases, this is a direct function
-invocation, but indirect <tt>call</tt>s are just as possible,
-calling an arbitrary pointer to function values.</p>
- </li>
- <li>
- <p>'<tt>function args</tt>': argument list whose types match the
-function signature argument types. If the function signature
-indicates the function accepts a variable number of arguments, the
-extra arguments can be specified.</p>
- </li>
-</ol>
+
+<p>
+The '<tt>select</tt>' instruction requires a boolean value indicating the condition, and two values of the same <a href="#t_firstclass">first class</a> type.
+</p>
+
<h5>Semantics:</h5>
-<p>The '<tt>call</tt>' instruction is used to cause control flow to
-transfer to a specified function, with its incoming arguments bound to
-the specified values. Upon a '<tt><a href="#i_ret">ret</a></tt>'
-instruction in the called function, control flow continues with the
-instruction after the function call, and the return value of the
-function is bound to the result argument. This is a simpler case of
-the <a href="#i_invoke">invoke</a> instruction.</p>
+
+<p>
+If the boolean condition evaluates to true, the instruction returns the first
+value argument; otherwise, it returns the second value argument.
+</p>
+
<h5>Example:</h5>
-<pre> %retval = call int %test(int %argc)<br> call int(sbyte*, ...) *%printf(sbyte* %msg, int 12, sbyte 42);<br></pre>
+
+<pre>
+ %X = select bool true, ubyte 17, ubyte 42 <i>; yields ubyte:17</i>
+</pre>
</div>
+
<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection"> <a name="i_vanext">'<tt>vanext</tt>'
+<div class="doc_subsubsection"> <a name="i_vsetint">'<tt>vsetint</tt>'
Instruction</a> </div>
<div class="doc_text">
<h5>Syntax:</h5>
-<pre> <resultarglist> = vanext <va_list> <arglist>, <argty><br></pre>
+<pre><result> = vsetint <op>, <n x <ty>> <var1>, <var2> <i>; yields <n x bool></i>
+</pre>
+
<h5>Overview:</h5>
-<p>The '<tt>vanext</tt>' instruction is used to access arguments passed
-through the "variable argument" area of a function call. It is used to
-implement the <tt>va_arg</tt> macro in C.</p>
+
+<p>The '<tt>vsetint</tt>' instruction takes two integer vectors and
+returns a vector of boolean values representing, at each position, the
+result of the comparison between the values at that position in the
+two operands.</p>
+
<h5>Arguments:</h5>
-<p>This instruction takes a <tt>valist</tt> value and the type of the
-argument. It returns another <tt>valist</tt>.</p>
+
+<p>The arguments to a '<tt>vsetint</tt>' instruction are a comparison
+operation and two value arguments. The value arguments must be of <a
+href="#t_integral">integral</a> <a href="#t_packed">packed</a> type,
+and they must have identical types. The operation argument must be
+one of <tt>eq</tt>, <tt>ne</tt>, <tt>slt</tt>, <tt>sgt</tt>,
+<tt>sle</tt>, <tt>sge</tt>, <tt>ult</tt>, <tt>ugt</tt>, <tt>ule</tt>,
+<tt>uge</tt>, <tt>true</tt>, and <tt>false</tt>. The result is a
+packed <tt>bool</tt> value with the same length as each operand.</p>
+
<h5>Semantics:</h5>
-<p>The '<tt>vanext</tt>' instruction advances the specified <tt>valist</tt>
-past an argument of the specified type. In conjunction with the <a
- href="#i_vaarg"><tt>vaarg</tt></a> instruction, it is used to implement
-the <tt>va_arg</tt> macro available in C. For more information, see
-the variable argument handling <a href="#int_varargs">Intrinsic
-Functions</a>.</p>
-<p>It is legal for this instruction to be called in a function which
-does not take a variable number of arguments, for example, the <tt>vfprintf</tt>
-function.</p>
-<p><tt>vanext</tt> is an LLVM instruction instead of an <a
- href="#intrinsics">intrinsic function</a> because it takes an type as
-an argument.</p>
+
+<p>The following table shows the semantics of '<tt>vsetint</tt>'. For
+each position of the result, the comparison is done on the
+corresponding positions of the two value arguments. Note that the
+signedness of the comparison depends on the comparison opcode and
+<i>not</i> on the signedness of the value operands. E.g., <tt>vsetint
+slt <4 x unsigned> %x, %y</tt> does an elementwise <i>signed</i>
+comparison of <tt>%x</tt> and <tt>%y</tt>.</p>
+
+<table border="1" cellspacing="0" cellpadding="4">
+ <tbody>
+ <tr><th>Operation</th><th>Result is true iff</th><th>Comparison is</th></tr>
+ <tr><td><tt>eq</tt></td><td>var1 == var2</td><td>--</td></tr>
+ <tr><td><tt>ne</tt></td><td>var1 != var2</td><td>--</td></tr>
+ <tr><td><tt>slt</tt></td><td>var1 < var2</td><td>signed</td></tr>
+ <tr><td><tt>sgt</tt></td><td>var1 > var2</td><td>signed</td></tr>
+ <tr><td><tt>sle</tt></td><td>var1 <= var2</td><td>signed</td></tr>
+ <tr><td><tt>sge</tt></td><td>var1 >= var2</td><td>signed</td></tr>
+ <tr><td><tt>ult</tt></td><td>var1 < var2</td><td>unsigned</td></tr>
+ <tr><td><tt>ugt</tt></td><td>var1 > var2</td><td>unsigned</td></tr>
+ <tr><td><tt>ule</tt></td><td>var1 <= var2</td><td>unsigned</td></tr>
+ <tr><td><tt>uge</tt></td><td>var1 >= var2</td><td>unsigned</td></tr>
+ <tr><td><tt>true</tt></td><td>always</td><td>--</td></tr>
+ <tr><td><tt>false</tt></td><td>never</td><td>--</td></tr>
+ </tbody>
+</table>
+
<h5>Example:</h5>
-<p>See the <a href="#int_varargs">variable argument processing</a>
-section.</p>
+<pre> <result> = vsetint eq <2 x int> <int 0, int 1>, <int 1, int 0> <i>; yields {<2 x bool>}:result = false, false</i>
+ <result> = vsetint ne <2 x int> <int 0, int 1>, <int 1, int 0> <i>; yields {<2 x bool>}:result = true, true</i>
+ <result> = vsetint slt <2 x int> <int 0, int 1>, <int 1, int 0> <i>; yields {<2 x bool>}:result = true, false</i>
+ <result> = vsetint sgt <2 x int> <int 0, int 1>, <int 1, int 0> <i>; yields {<2 x bool>}:result = false, true</i>
+ <result> = vsetint sle <2 x int> <int 0, int 1>, <int 1, int 0> <i>; yields {<2 x bool>}:result = true, false</i>
+ <result> = vsetint sge <2 x int> <int 0, int 1>, <int 1, int 0> <i>; yields {<2 x bool>}:result = false, true</i>
+</pre>
</div>
+
<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection"> <a name="i_vaarg">'<tt>vaarg</tt>'
+<div class="doc_subsubsection"> <a name="i_vsetfp">'<tt>vsetfp</tt>'
Instruction</a> </div>
<div class="doc_text">
<h5>Syntax:</h5>
-<pre> <resultval> = vaarg <va_list> <arglist>, <argty><br></pre>
+<pre><result> = vsetfp <op>, <n x <ty>> <var1>, <var2> <i>; yields <n x bool></i>
+</pre>
+
<h5>Overview:</h5>
-<p>The '<tt>vaarg</tt>' instruction is used to access arguments passed
-through the "variable argument" area of a function call. It is used to
-implement the <tt>va_arg</tt> macro in C.</p>
+
+<p>The '<tt>vsetfp</tt>' instruction takes two floating point vector
+arguments and returns a vector of boolean values representing, at each
+position, the result of the comparison between the values at that
+position in the two operands.</p>
+
<h5>Arguments:</h5>
-<p>This instruction takes a <tt>valist</tt> value and the type of the
-argument. It returns a value of the specified argument type.</p>
+
+<p>The arguments to a '<tt>vsetfp</tt>' instruction are a comparison
+operation and two value arguments. The value arguments must be of <a
+href="t_floating">floating point</a> <a href="#t_packed">packed</a>
+type, and they must have identical types. The operation argument must
+be one of <tt>eq</tt>, <tt>ne</tt>, <tt>lt</tt>, <tt>gt</tt>,
+<tt>le</tt>, <tt>ge</tt>, <tt>oeq</tt>, <tt>one</tt>, <tt>olt</tt>,
+<tt>ogt</tt>, <tt>ole</tt>, <tt>oge</tt>, <tt>ueq</tt>, <tt>une</tt>,
+<tt>ult</tt>, <tt>ugt</tt>, <tt>ule</tt>, <tt>uge</tt>, <tt>o</tt>,
+<tt>u</tt>, <tt>true</tt>, and <tt>false</tt>. The result is a packed
+<tt>bool</tt> value with the same length as each operand.</p>
+
<h5>Semantics:</h5>
-<p>The '<tt>vaarg</tt>' instruction loads an argument of the specified
-type from the specified <tt>va_list</tt>. In conjunction with the <a
- href="#i_vanext"><tt>vanext</tt></a> instruction, it is used to
-implement the <tt>va_arg</tt> macro available in C. For more
-information, see the variable argument handling <a href="#int_varargs">Intrinsic
+
+<p>The following table shows the semantics of '<tt>vsetfp</tt>' for
+floating point types. If either operand is a floating point Not a
+Number (NaN) value, the operation is unordered, and the value in the
+first column below is produced at that position. Otherwise, the
+operation is ordered, and the value in the second column is
+produced.</p>
+
+<table border="1" cellspacing="0" cellpadding="4">
+ <tbody>
+ <tr><th>Operation</th><th>If unordered<th>Otherwise true iff</th></tr>
+ <tr><td><tt>eq</tt></td><td>undefined</td><td>var1 == var2</td></tr>
+ <tr><td><tt>ne</tt></td><td>undefined</td><td>var1 != var2</td></tr>
+ <tr><td><tt>lt</tt></td><td>undefined</td><td>var1 < var2</td></tr>
+ <tr><td><tt>gt</tt></td><td>undefined</td><td>var1 > var2</td></tr>
+ <tr><td><tt>le</tt></td><td>undefined</td><td>var1 <= var2</td></tr>
+ <tr><td><tt>ge</tt></td><td>undefined</td><td>var1 >= var2</td></tr>
+ <tr><td><tt>oeq</tt></td><td>false</td><td>var1 == var2</td></tr>
+ <tr><td><tt>one</tt></td><td>false</td><td>var1 != var2</td></tr>
+ <tr><td><tt>olt</tt></td><td>false</td><td>var1 < var2</td></tr>
+ <tr><td><tt>ogt</tt></td><td>false</td><td>var1 > var2</td></tr>
+ <tr><td><tt>ole</tt></td><td>false</td><td>var1 <= var2</td></tr>
+ <tr><td><tt>oge</tt></td><td>false</td><td>var1 >= var2</td></tr>
+ <tr><td><tt>ueq</tt></td><td>true</td><td>var1 == var2</td></tr>
+ <tr><td><tt>une</tt></td><td>true</td><td>var1 != var2</td></tr>
+ <tr><td><tt>ult</tt></td><td>true</td><td>var1 < var2</td></tr>
+ <tr><td><tt>ugt</tt></td><td>true</td><td>var1 > var2</td></tr>
+ <tr><td><tt>ule</tt></td><td>true</td><td>var1 <= var2</td></tr>
+ <tr><td><tt>uge</tt></td><td>true</td><td>var1 >= var2</td></tr>
+ <tr><td><tt>o</tt></td><td>false</td><td>always</td></tr>
+ <tr><td><tt>u</tt></td><td>true</td><td>never</td></tr>
+ <tr><td><tt>true</tt></td><td>true</td><td>always</td></tr>
+ <tr><td><tt>false</tt></td><td>false</td><td>never</td></tr>
+ </tbody>
+</table>
+
+<h5>Example:</h5>
+<pre> <result> = vsetfp eq <2 x float> <float 0.0, float 1.0>, <float 1.0, float 0.0> <i>; yields {<2 x bool>}:result = false, false</i>
+ <result> = vsetfp ne <2 x float> <float 0.0, float 1.0>, <float 1.0, float 0.0> <i>; yields {<2 x bool>}:result = true, true</i>
+ <result> = vsetfp lt <2 x float> <float 0.0, float 1.0>, <float 1.0, float 0.0> <i>; yields {<2 x bool>}:result = true, false</i>
+ <result> = vsetfp gt <2 x float> <float 0.0, float 1.0>, <float 1.0, float 0.0> <i>; yields {<2 x bool>}:result = false, true</i>
+ <result> = vsetfp le <2 x float> <float 0.0, float 1.0>, <float 1.0, float 0.0> <i>; yields {<2 x bool>}:result = true, false</i>
+ <result> = vsetfp ge <2 x float> <float 0.0, float 1.0>, <float 1.0, float 0.0> <i>; yields {<2 x bool>}:result = false, true</i>
+</pre>
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_vselect">'<tt>vselect</tt>' Instruction</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+
+<pre>
+ <result> = vselect <n x bool> <cond>, <n x <ty>> <val1>, <n x <ty>> <val2> <i>; yields <n x <ty>></i>
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>vselect</tt>' instruction chooses one value at each position
+of a vector based on a condition.
+</p>
+
+
+<h5>Arguments:</h5>
+
+<p>
+The '<tt>vselect</tt>' instruction requires a <a
+href="#t_packed">packed</a> <tt>bool</tt> value indicating the
+condition at each vector position, and two values of the same packed
+type. All three operands must have the same length. The type of the
+result is the same as the type of the two value operands.</p>
+
+<h5>Semantics:</h5>
+
+<p>
+At each position where the <tt>bool</tt> vector is true, that position
+of the result gets its value from the first value argument; otherwise,
+it gets its value from the second value argument.
+</p>
+
+<h5>Example:</h5>
+
+<pre>
+ %X = vselect bool <2 x bool> <bool true, bool false>, <2 x ubyte> <ubyte 17, ubyte 17>,
+ <2 x ubyte> <ubyte 42, ubyte 42> <i>; yields <2 x ubyte>:17, 42</i>
+</pre>
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_extractelement">'<tt>extractelement</tt>' Instruction</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+
+<pre>
+ <result> = extractelement <n x <ty>> <val>, uint <idx> <i>; yields <ty></i>
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>extractelement</tt>' instruction extracts a single scalar
+element from a packed vector at a specified index.
+</p>
+
+
+<h5>Arguments:</h5>
+
+<p>
+The first operand of an '<tt>extractelement</tt>' instruction is a
+value of <a href="#t_packed">packed</a> type. The second operand is
+an index indicating the position from which to extract the element.
+The index may be a variable.</p>
+
+<h5>Semantics:</h5>
+
+<p>
+The result is a scalar of the same type as the element type of
+<tt>val</tt>. Its value is the value at position <tt>idx</tt> of
+<tt>val</tt>. If <tt>idx</tt> exceeds the length of <tt>val</tt>, the
+results are undefined.
+</p>
+
+<h5>Example:</h5>
+
+<pre>
+ %result = extractelement <4 x int> %vec, uint 0 <i>; yields int</i>
+</pre>
+</div>
+
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_insertelement">'<tt>insertelement</tt>' Instruction</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+
+<pre>
+ <result> = insertelement <n x <ty>> <val>, <ty> <elt>, uint <idx> <i>; yields <n x <ty>></i>
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>insertelement</tt>' instruction inserts a scalar
+element into a packed vector at a specified index.
+</p>
+
+
+<h5>Arguments:</h5>
+
+<p>
+The first operand of an '<tt>insertelement</tt>' instruction is a
+value of <a href="#t_packed">packed</a> type. The second operand is a
+scalar value whose type must equal the element type of the first
+operand. The third operand is an index indicating the position at
+which to insert the value. The index may be a variable.</p>
+
+<h5>Semantics:</h5>
+
+<p>
+The result is a packed vector of the same type as <tt>val</tt>. Its
+element values are those of <tt>val</tt> except at position
+<tt>idx</tt>, where it gets the value <tt>elt</tt>. If <tt>idx</tt>
+exceeds the length of <tt>val</tt>, the results are undefined.
+</p>
+
+<h5>Example:</h5>
+
+<pre>
+ %result = insertelement <4 x int> %vec, int 1, uint 0 <i>; yields <4 x int></i>
+</pre>
+</div>
+
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_call">'<tt>call</tt>' Instruction</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ <result> = [tail] call [<a href="#callingconv">cconv</a>] <ty>* <fnptrval>(<param list>)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>The '<tt>call</tt>' instruction represents a simple function call.</p>
+
+<h5>Arguments:</h5>
+
+<p>This instruction requires several arguments:</p>
+
+<ol>
+ <li>
+ <p>The optional "tail" marker indicates whether the callee function accesses
+ any allocas or varargs in the caller. If the "tail" marker is present, the
+ function call is eligible for tail call optimization. Note that calls may
+ be marked "tail" even if they do not occur before a <a
+ href="#i_ret"><tt>ret</tt></a> instruction.
+ </li>
+ <li>
+ <p>The optional "cconv" marker indicates which <a href="callingconv">calling
+ convention</a> the call should use. If none is specified, the call defaults
+ to using C calling conventions.
+ </li>
+ <li>
+ <p>'<tt>ty</tt>': shall be the signature of the pointer to function value
+ being invoked. The argument types must match the types implied by this
+ signature. This type can be omitted if the function is not varargs and
+ if the function type does not return a pointer to a function.</p>
+ </li>
+ <li>
+ <p>'<tt>fnptrval</tt>': An LLVM value containing a pointer to a function to
+ be invoked. In most cases, this is a direct function invocation, but
+ indirect <tt>call</tt>s are just as possible, calling an arbitrary pointer
+ to function value.</p>
+ </li>
+ <li>
+ <p>'<tt>function args</tt>': argument list whose types match the
+ function signature argument types. All arguments must be of
+ <a href="#t_firstclass">first class</a> type. If the function signature
+ indicates the function accepts a variable number of arguments, the extra
+ arguments can be specified.</p>
+ </li>
+</ol>
+
+<h5>Semantics:</h5>
+
+<p>The '<tt>call</tt>' instruction is used to cause control flow to
+transfer to a specified function, with its incoming arguments bound to
+the specified values. Upon a '<tt><a href="#i_ret">ret</a></tt>'
+instruction in the called function, control flow continues with the
+instruction after the function call, and the return value of the
+function is bound to the result argument. This is a simpler case of
+the <a href="#i_invoke">invoke</a> instruction.</p>
+
+<h5>Example:</h5>
+
+<pre>
+ %retval = call int %test(int %argc)
+ call int(sbyte*, ...) *%printf(sbyte* %msg, int 12, sbyte 42);
+ %X = tail call int %foo()
+ %Y = tail call <a href="#callingconv">fastcc</a> int %foo()
+</pre>
+
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_va_arg">'<tt>va_arg</tt>' Instruction</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+
+<pre>
+ <resultval> = va_arg <va_list*> <arglist>, <argty>
+</pre>
+
+<h5>Overview:</h5>
+
+<p>The '<tt>va_arg</tt>' instruction is used to access arguments passed through
+the "variable argument" area of a function call. It is used to implement the
+<tt>va_arg</tt> macro in C.</p>
+
+<h5>Arguments:</h5>
+
+<p>This instruction takes a <tt>va_list*</tt> value and the type of
+the argument. It returns a value of the specified argument type and
+increments the <tt>va_list</tt> to point to the next argument. Again, the
+actual type of <tt>va_list</tt> is target specific.</p>
+
+<h5>Semantics:</h5>
+
+<p>The '<tt>va_arg</tt>' instruction loads an argument of the specified
+type from the specified <tt>va_list</tt> and causes the
+<tt>va_list</tt> to point to the next argument. For more information,
+see the variable argument handling <a href="#int_varargs">Intrinsic
Functions</a>.</p>
-<p>It is legal for this instruction to be called in a function which
-does not take a variable number of arguments, for example, the <tt>vfprintf</tt>
+
+<p>It is legal for this instruction to be called in a function which does not
+take a variable number of arguments, for example, the <tt>vfprintf</tt>
function.</p>
-<p><tt>vaarg</tt> is an LLVM instruction instead of an <a
- href="#intrinsics">intrinsic function</a> because it takes an type as
-an argument.</p>
+
+<p><tt>va_arg</tt> is an LLVM instruction instead of an <a
+href="#intrinsics">intrinsic function</a> because it takes a type as an
+argument.</p>
+
<h5>Example:</h5>
-<p>See the <a href="#int_varargs">variable argument processing</a>
-section.</p>
+
+<p>See the <a href="#int_varargs">variable argument processing</a> section.</p>
+
</div>
<!-- *********************************************************************** -->
<div class="doc_text">
<p>LLVM supports the notion of an "intrinsic function". These functions have
-well known names and semantics, and are required to follow certain
+well known names and semantics and are required to follow certain
restrictions. Overall, these instructions represent an extension mechanism for
the LLVM language that does not require changing all of the transformations in
LLVM to add to the language (or the bytecode reader/writer, the parser,
etc...).</p>
-<p>Intrinsic function names must all start with an "<tt>llvm.</tt>" prefix, this
-prefix is reserved in LLVM for intrinsic names, thus functions may not be named
+<p>Intrinsic function names must all start with an "<tt>llvm.</tt>" prefix. This
+prefix is reserved in LLVM for intrinsic names; thus, functions may not be named
this. Intrinsic functions must always be external functions: you cannot define
the body of intrinsic functions. Intrinsic functions may only be used in call
or invoke instructions: it is illegal to take the address of an intrinsic
language, it is required that they all be documented here if any are added.</p>
-<p>
-Adding an intrinsic to LLVM is straight-forward if it is possible to express the
-concept in LLVM directly (ie, code generator support is not _required_). To do
-this, extend the default implementation of the IntrinsicLowering class to handle
-the intrinsic. Code generators use this class to lower intrinsics they do not
-understand to raw LLVM instructions that they do.
+<p>To learn how to add an intrinsic function, please see the <a
+href="ExtendingLLVM.html">Extending LLVM Guide</a>.
</p>
</div>
</div>
<div class="doc_text">
+
<p>Variable argument support is defined in LLVM with the <a
- href="#i_vanext"><tt>vanext</tt></a> instruction and these three
+ href="#i_va_arg"><tt>va_arg</tt></a> instruction and these three
intrinsic functions. These functions are related to the similarly
named macros defined in the <tt><stdarg.h></tt> header file.</p>
+
<p>All of these functions operate on arguments that use a
target-specific value type "<tt>va_list</tt>". The LLVM assembly
language reference manual does not define what this type is, so all
transformations should be prepared to handle intrinsics with any type
used.</p>
+
<p>This example shows how the <a href="#i_vanext"><tt>vanext</tt></a>
instruction and the variable argument handling intrinsic functions are
used.</p>
+
<pre>
int %test(int %X, ...) {
; Initialize variable argument processing
- %ap = call sbyte* %<a href="#i_va_start">llvm.va_start</a>()
+ %ap = alloca sbyte*
+ call void %<a href="#i_va_start">llvm.va_start</a>(sbyte** %ap)
; Read a single integer argument
- %tmp = vaarg sbyte* %ap, int
-
- ; Advance to the next argument
- %ap2 = vanext sbyte* %ap, int
+ %tmp = va_arg sbyte** %ap, int
; Demonstrate usage of llvm.va_copy and llvm.va_end
- %aq = call sbyte* %<a href="#i_va_copy">llvm.va_copy</a>(sbyte* %ap2)
- call void %<a href="#i_va_end">llvm.va_end</a>(sbyte* %aq)
+ %aq = alloca sbyte*
+ call void %<a href="#i_va_copy">llvm.va_copy</a>(sbyte** %aq, sbyte** %ap)
+ call void %<a href="#i_va_end">llvm.va_end</a>(sbyte** %aq)
; Stop processing of arguments.
- call void %<a href="#i_va_end">llvm.va_end</a>(sbyte* %ap2)
+ call void %<a href="#i_va_end">llvm.va_end</a>(sbyte** %ap)
ret int %tmp
}
</pre>
<div class="doc_text">
<h5>Syntax:</h5>
-<pre> call va_list ()* %llvm.va_start()<br></pre>
+<pre> declare void %llvm.va_start(<va_list>* <arglist>)<br></pre>
<h5>Overview:</h5>
-<p>The '<tt>llvm.va_start</tt>' intrinsic returns a new <tt><arglist></tt>
-for subsequent use by the variable argument intrinsics.</p>
+<P>The '<tt>llvm.va_start</tt>' intrinsic initializes
+<tt>*<arglist></tt> for subsequent use by <tt><a
+href="#i_va_arg">va_arg</a></tt>.</p>
+
+<h5>Arguments:</h5>
+
+<P>The argument is a pointer to a <tt>va_list</tt> element to initialize.</p>
+
<h5>Semantics:</h5>
-<p>The '<tt>llvm.va_start</tt>' intrinsic works just like the <tt>va_start</tt>
-macro available in C. In a target-dependent way, it initializes and
-returns a <tt>va_list</tt> element, so that the next <tt>vaarg</tt>
-will produce the first variable argument passed to the function. Unlike
-the C <tt>va_start</tt> macro, this intrinsic does not need to know the
+
+<P>The '<tt>llvm.va_start</tt>' intrinsic works just like the <tt>va_start</tt>
+macro available in C. In a target-dependent way, it initializes the
+<tt>va_list</tt> element the argument points to, so that the next call to
+<tt>va_arg</tt> will produce the first variable argument passed to the function.
+Unlike the C <tt>va_start</tt> macro, this intrinsic does not need to know the
last argument of the function, the compiler can figure that out.</p>
-<p>Note that this intrinsic function is only legal to be called from
-within the body of a variable argument function.</p>
+
</div>
<!-- _______________________________________________________________________ -->
<div class="doc_text">
<h5>Syntax:</h5>
-<pre> call void (va_list)* %llvm.va_end(va_list <arglist>)<br></pre>
+<pre> declare void %llvm.va_end(<va_list*> <arglist>)<br></pre>
<h5>Overview:</h5>
<p>The '<tt>llvm.va_end</tt>' intrinsic destroys <tt><arglist></tt>
which has been initialized previously with <tt><a href="#i_va_start">llvm.va_start</a></tt>
</div>
<div class="doc_text">
+
<h5>Syntax:</h5>
-<pre> call va_list (va_list)* %llvm.va_copy(va_list <destarglist>)<br></pre>
+
+<pre>
+ declare void %llvm.va_copy(<va_list>* <destarglist>,
+ <va_list>* <srcarglist>)
+</pre>
+
<h5>Overview:</h5>
-<p>The '<tt>llvm.va_copy</tt>' intrinsic copies the current argument
-position from the source argument list to the destination argument list.</p>
+
+<p>The '<tt>llvm.va_copy</tt>' intrinsic copies the current argument position from
+the source argument list to the destination argument list.</p>
+
<h5>Arguments:</h5>
-<p>The argument is the <tt>va_list</tt> to copy.</p>
+
+<p>The first argument is a pointer to a <tt>va_list</tt> element to initialize.
+The second argument is a pointer to a <tt>va_list</tt> element to copy from.</p>
+
+
<h5>Semantics:</h5>
-<p>The '<tt>llvm.va_copy</tt>' intrinsic works just like the <tt>va_copy</tt>
-macro available in C. In a target-dependent way, it copies the source <tt>va_list</tt>
-element into the returned list. This intrinsic is necessary because the <tt><a
- href="i_va_start">llvm.va_start</a></tt> intrinsic may be arbitrarily
-complex and require memory allocation, for example.</p>
+
+<p>The '<tt>llvm.va_copy</tt>' intrinsic works just like the <tt>va_copy</tt> macro
+available in C. In a target-dependent way, it copies the source
+<tt>va_list</tt> element into the destination list. This intrinsic is necessary
+because the <tt><a href="i_va_begin">llvm.va_begin</a></tt> intrinsic may be
+arbitrarily complex and require memory allocation, for example.</p>
+
</div>
<!-- ======================================================================= -->
<div class="doc_subsection">
- <a name="int_libc">Standard C Library Intrinsics</a>
+ <a name="int_gc">Accurate Garbage Collection Intrinsics</a>
</div>
<div class="doc_text">
-<p>
+<p>
+LLVM support for <a href="GarbageCollection.html">Accurate Garbage
+Collection</a> requires the implementation and generation of these intrinsics.
+These intrinsics allow identification of <a href="#i_gcroot">GC roots on the
+stack</a>, as well as garbage collector implementations that require <a
+href="#i_gcread">read</a> and <a href="#i_gcwrite">write</a> barriers.
+Front-ends for type-safe garbage collected languages should generate these
+intrinsics to make use of the LLVM garbage collectors. For more details, see <a
+href="GarbageCollection.html">Accurate Garbage Collection with LLVM</a>.
</p>
-
</div>
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection">
- <a name="i_memcpy">'<tt>llvm.memcpy</tt>' Intrinsic</a>
+ <a name="i_gcroot">'<tt>llvm.gcroot</tt>' Intrinsic</a>
</div>
<div class="doc_text">
<h5>Syntax:</h5>
+
<pre>
- call void (sbyte*, sbyte*, uint, uint)* %llvm.memcpy(sbyte* <dest>, sbyte* <src>,
- uint <len>, uint <align>)
+ declare void %llvm.gcroot(<ty>** %ptrloc, <ty2>* %metadata)
</pre>
<h5>Overview:</h5>
-<p>
-The '<tt>llvm.memcpy</tt>' intrinsic copies a block of memory from the source
-location to the destination location.
-</p>
-
-<p>
-Note that, unlike the standard libc function, the <tt>llvm.memcpy</tt> intrinsic
-does not return a value, and takes an extra alignment argument.
-</p>
+<p>The '<tt>llvm.gcroot</tt>' intrinsic declares the existence of a GC root to
+the code generator, and allows some metadata to be associated with it.</p>
<h5>Arguments:</h5>
-<p>
-The first argument is a pointer to the destination, the second is a pointer to
-the source. The third argument is an (arbitrarily sized) integer argument
-specifying the number of bytes to copy, and the fourth argument is the alignment
-of the source and destination locations.
-</p>
+<p>The first argument specifies the address of a stack object that contains the
+root pointer. The second pointer (which must be either a constant or a global
+value address) contains the meta-data to be associated with the root.</p>
<h5>Semantics:</h5>
-<p>
-The '<tt>llvm.memcpy</tt>' intrinsic copies a block of memory from the source
-location to the destination location, which are not allowed to overlap. It
-copies "len" bytes of memory over. If the argument is known to be aligned to
-some boundary, this can be specified as the fourth argument, otherwise it should
-be set to 0 or 1.
+<p>At runtime, a call to this intrinsics stores a null pointer into the "ptrloc"
+location. At compile-time, the code generator generates information to allow
+the runtime to find the pointer at GC safe points.
</p>
+
</div>
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection">
- <a name="i_memmove">'<tt>llvm.memmove</tt>' Intrinsic</a>
+ <a name="i_gcread">'<tt>llvm.gcread</tt>' Intrinsic</a>
</div>
<div class="doc_text">
<h5>Syntax:</h5>
+
<pre>
- call void (sbyte*, sbyte*, uint, uint)* %llvm.memmove(sbyte* <dest>, sbyte* <src>,
- uint <len>, uint <align>)
+ declare sbyte* %llvm.gcread(sbyte* %ObjPtr, sbyte** %Ptr)
</pre>
<h5>Overview:</h5>
-<p>
-The '<tt>llvm.memmove</tt>' intrinsic moves a block of memory from the source
-location to the destination location. It is similar to the '<tt>llvm.memcpy</tt>'
-intrinsic but allows the two memory locations to overlap.
-</p>
-
-<p>
-Note that, unlike the standard libc function, the <tt>llvm.memmove</tt> intrinsic
-does not return a value, and takes an extra alignment argument.
-</p>
+<p>The '<tt>llvm.gcread</tt>' intrinsic identifies reads of references from heap
+locations, allowing garbage collector implementations that require read
+barriers.</p>
<h5>Arguments:</h5>
-<p>
-The first argument is a pointer to the destination, the second is a pointer to
-the source. The third argument is an (arbitrarily sized) integer argument
-specifying the number of bytes to copy, and the fourth argument is the alignment
-of the source and destination locations.
-</p>
+<p>The second argument is the address to read from, which should be an address
+allocated from the garbage collector. The first object is a pointer to the
+start of the referenced object, if needed by the language runtime (otherwise
+null).</p>
<h5>Semantics:</h5>
-<p>
-The '<tt>llvm.memmove</tt>' intrinsic copies a block of memory from the source
-location to the destination location, which may overlap. It
-copies "len" bytes of memory over. If the argument is known to be aligned to
-some boundary, this can be specified as the fourth argument, otherwise it should
-be set to 0 or 1.
-</p>
+<p>The '<tt>llvm.gcread</tt>' intrinsic has the same semantics as a load
+instruction, but may be replaced with substantially more complex code by the
+garbage collector runtime, as needed.</p>
+
</div>
-<!-- ======================================================================= -->
-<div class="doc_subsection">
- <a name="int_debugger">Debugger Intrinsics</a>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_gcwrite">'<tt>llvm.gcwrite</tt>' Intrinsic</a>
</div>
<div class="doc_text">
-<p>
-The LLVM debugger intrinsics (which all start with <tt>llvm.dbg.</tt> prefix),
+
+<h5>Syntax:</h5>
+
+<pre>
+ declare void %llvm.gcwrite(sbyte* %P1, sbyte* %Obj, sbyte** %P2)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>The '<tt>llvm.gcwrite</tt>' intrinsic identifies writes of references to heap
+locations, allowing garbage collector implementations that require write
+barriers (such as generational or reference counting collectors).</p>
+
+<h5>Arguments:</h5>
+
+<p>The first argument is the reference to store, the second is the start of the
+object to store it to, and the third is the address of the field of Obj to
+store to. If the runtime does not require a pointer to the object, Obj may be
+null.</p>
+
+<h5>Semantics:</h5>
+
+<p>The '<tt>llvm.gcwrite</tt>' intrinsic has the same semantics as a store
+instruction, but may be replaced with substantially more complex code by the
+garbage collector runtime, as needed.</p>
+
+</div>
+
+
+
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="int_codegen">Code Generator Intrinsics</a>
+</div>
+
+<div class="doc_text">
+<p>
+These intrinsics are provided by LLVM to expose special features that may only
+be implemented with code generator support.
+</p>
+
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_returnaddress">'<tt>llvm.returnaddress</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare sbyte *%llvm.returnaddress(uint <level>)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.returnaddress</tt>' intrinsic returns a target-specific value
+indicating the return address of the current function or one of its callers.
+</p>
+
+<h5>Arguments:</h5>
+
+<p>
+The argument to this intrinsic indicates which function to return the address
+for. Zero indicates the calling function, one indicates its caller, etc. The
+argument is <b>required</b> to be a constant integer value.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+The '<tt>llvm.returnaddress</tt>' intrinsic either returns a pointer indicating
+the return address of the specified call frame, or zero if it cannot be
+identified. The value returned by this intrinsic is likely to be incorrect or 0
+for arguments other than zero, so it should only be used for debugging purposes.
+</p>
+
+<p>
+Note that calling this intrinsic does not prevent function inlining or other
+aggressive transformations, so the value returned may not be that of the obvious
+source-language caller.
+</p>
+</div>
+
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_frameaddress">'<tt>llvm.frameaddress</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare sbyte *%llvm.frameaddress(uint <level>)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.frameaddress</tt>' intrinsic returns the target-specific frame
+pointer value for the specified stack frame.
+</p>
+
+<h5>Arguments:</h5>
+
+<p>
+The argument to this intrinsic indicates which function to return the frame
+pointer for. Zero indicates the calling function, one indicates its caller,
+etc. The argument is <b>required</b> to be a constant integer value.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+The '<tt>llvm.frameaddress</tt>' intrinsic either returns a pointer indicating
+the frame address of the specified call frame, or zero if it cannot be
+identified. The value returned by this intrinsic is likely to be incorrect or 0
+for arguments other than zero, so it should only be used for debugging purposes.
+</p>
+
+<p>
+Note that calling this intrinsic does not prevent function inlining or other
+aggressive transformations, so the value returned may not be that of the obvious
+source-language caller.
+</p>
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_stacksave">'<tt>llvm.stacksave</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare sbyte *%llvm.stacksave()
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.stacksave</tt>' intrinsic is used to remember the current state of
+the function stack, for use with <a href="#i_stackrestore">
+<tt>llvm.stackrestore</tt></a>. This is useful for implementing language
+features like scoped automatic variable sized arrays in C99.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+This intrinsic returns a opaque pointer value that can be passed to <a
+href="#i_stackrestore"><tt>llvm.stackrestore</tt></a>. When an
+<tt>llvm.stackrestore</tt> intrinsic is executed with a value saved from
+<tt>llvm.stacksave</tt>, it effectively restores the state of the stack to the
+state it was in when the <tt>llvm.stacksave</tt> intrinsic executed. In
+practice, this pops any <a href="#i_alloca">alloca</a> blocks from the stack
+that were allocated after the <tt>llvm.stacksave</tt> was executed.
+</p>
+
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_stackrestore">'<tt>llvm.stackrestore</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare void %llvm.stackrestore(sbyte* %ptr)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.stackrestore</tt>' intrinsic is used to restore the state of
+the function stack to the state it was in when the corresponding <a
+href="#llvm.stacksave"><tt>llvm.stacksave</tt></a> intrinsic executed. This is
+useful for implementing language features like scoped automatic variable sized
+arrays in C99.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+See the description for <a href="#i_stacksave"><tt>llvm.stacksave</tt></a>.
+</p>
+
+</div>
+
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_prefetch">'<tt>llvm.prefetch</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare void %llvm.prefetch(sbyte * <address>,
+ uint <rw>, uint <locality>)
+</pre>
+
+<h5>Overview:</h5>
+
+
+<p>
+The '<tt>llvm.prefetch</tt>' intrinsic is a hint to the code generator to insert
+a prefetch instruction if supported; otherwise, it is a noop. Prefetches have
+no
+effect on the behavior of the program but can change its performance
+characteristics.
+</p>
+
+<h5>Arguments:</h5>
+
+<p>
+<tt>address</tt> is the address to be prefetched, <tt>rw</tt> is the specifier
+determining if the fetch should be for a read (0) or write (1), and
+<tt>locality</tt> is a temporal locality specifier ranging from (0) - no
+locality, to (3) - extremely local keep in cache. The <tt>rw</tt> and
+<tt>locality</tt> arguments must be constant integers.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+This intrinsic does not modify the behavior of the program. In particular,
+prefetches cannot trap and do not produce a value. On targets that support this
+intrinsic, the prefetch can provide hints to the processor cache for better
+performance.
+</p>
+
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_pcmarker">'<tt>llvm.pcmarker</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare void %llvm.pcmarker( uint <id> )
+</pre>
+
+<h5>Overview:</h5>
+
+
+<p>
+The '<tt>llvm.pcmarker</tt>' intrinsic is a method to export a Program Counter
+(PC) in a region of
+code to simulators and other tools. The method is target specific, but it is
+expected that the marker will use exported symbols to transmit the PC of the marker.
+The marker makes no guarantees that it will remain with any specific instruction
+after optimizations. It is possible that the presence of a marker will inhibit
+optimizations. The intended use is to be inserted after optimizations to allow
+correlations of simulation runs.
+</p>
+
+<h5>Arguments:</h5>
+
+<p>
+<tt>id</tt> is a numerical id identifying the marker.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+This intrinsic does not modify the behavior of the program. Backends that do not
+support this intrinisic may ignore it.
+</p>
+
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_readcyclecounter">'<tt>llvm.readcyclecounter</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare ulong %llvm.readcyclecounter( )
+</pre>
+
+<h5>Overview:</h5>
+
+
+<p>
+The '<tt>llvm.readcyclecounter</tt>' intrinsic provides access to the cycle
+counter register (or similar low latency, high accuracy clocks) on those targets
+that support it. On X86, it should map to RDTSC. On Alpha, it should map to RPCC.
+As the backing counters overflow quickly (on the order of 9 seconds on alpha), this
+should only be used for small timings.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+When directly supported, reading the cycle counter should not modify any memory.
+Implementations are allowed to either return a application specific value or a
+system wide value. On backends without support, this is lowered to a constant 0.
+</p>
+
+</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="int_libc">Standard C Library Intrinsics</a>
+</div>
+
+<div class="doc_text">
+<p>
+LLVM provides intrinsics for a few important standard C library functions.
+These intrinsics allow source-language front-ends to pass information about the
+alignment of the pointer arguments to the code generator, providing opportunity
+for more efficient code generation.
+</p>
+
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_memcpy">'<tt>llvm.memcpy</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare void %llvm.memcpy.i32(sbyte* <dest>, sbyte* <src>,
+ uint <len>, uint <align>)
+ declare void %llvm.memcpy.i64(sbyte* <dest>, sbyte* <src>,
+ ulong <len>, uint <align>)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.memcpy.*</tt>' intrinsics copy a block of memory from the source
+location to the destination location.
+</p>
+
+<p>
+Note that, unlike the standard libc function, the <tt>llvm.memcpy.*</tt>
+intrinsics do not return a value, and takes an extra alignment argument.
+</p>
+
+<h5>Arguments:</h5>
+
+<p>
+The first argument is a pointer to the destination, the second is a pointer to
+the source. The third argument is an integer argument
+specifying the number of bytes to copy, and the fourth argument is the alignment
+of the source and destination locations.
+</p>
+
+<p>
+If the call to this intrinisic has an alignment value that is not 0 or 1, then
+the caller guarantees that both the source and destination pointers are aligned
+to that boundary.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+The '<tt>llvm.memcpy.*</tt>' intrinsics copy a block of memory from the source
+location to the destination location, which are not allowed to overlap. It
+copies "len" bytes of memory over. If the argument is known to be aligned to
+some boundary, this can be specified as the fourth argument, otherwise it should
+be set to 0 or 1.
+</p>
+</div>
+
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_memmove">'<tt>llvm.memmove</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare void %llvm.memmove.i32(sbyte* <dest>, sbyte* <src>,
+ uint <len>, uint <align>)
+ declare void %llvm.memmove.i64(sbyte* <dest>, sbyte* <src>,
+ ulong <len>, uint <align>)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.memmove.*</tt>' intrinsics move a block of memory from the source
+location to the destination location. It is similar to the
+'<tt>llvm.memcmp</tt>' intrinsic but allows the two memory locations to overlap.
+</p>
+
+<p>
+Note that, unlike the standard libc function, the <tt>llvm.memmove.*</tt>
+intrinsics do not return a value, and takes an extra alignment argument.
+</p>
+
+<h5>Arguments:</h5>
+
+<p>
+The first argument is a pointer to the destination, the second is a pointer to
+the source. The third argument is an integer argument
+specifying the number of bytes to copy, and the fourth argument is the alignment
+of the source and destination locations.
+</p>
+
+<p>
+If the call to this intrinisic has an alignment value that is not 0 or 1, then
+the caller guarantees that the source and destination pointers are aligned to
+that boundary.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+The '<tt>llvm.memmove.*</tt>' intrinsics copy a block of memory from the source
+location to the destination location, which may overlap. It
+copies "len" bytes of memory over. If the argument is known to be aligned to
+some boundary, this can be specified as the fourth argument, otherwise it should
+be set to 0 or 1.
+</p>
+</div>
+
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_memset">'<tt>llvm.memset.*</tt>' Intrinsics</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare void %llvm.memset.i32(sbyte* <dest>, ubyte <val>,
+ uint <len>, uint <align>)
+ declare void %llvm.memset.i64(sbyte* <dest>, ubyte <val>,
+ ulong <len>, uint <align>)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.memset.*</tt>' intrinsics fill a block of memory with a particular
+byte value.
+</p>
+
+<p>
+Note that, unlike the standard libc function, the <tt>llvm.memset</tt> intrinsic
+does not return a value, and takes an extra alignment argument.
+</p>
+
+<h5>Arguments:</h5>
+
+<p>
+The first argument is a pointer to the destination to fill, the second is the
+byte value to fill it with, the third argument is an integer
+argument specifying the number of bytes to fill, and the fourth argument is the
+known alignment of destination location.
+</p>
+
+<p>
+If the call to this intrinisic has an alignment value that is not 0 or 1, then
+the caller guarantees that the destination pointer is aligned to that boundary.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+The '<tt>llvm.memset.*</tt>' intrinsics fill "len" bytes of memory starting at
+the
+destination location. If the argument is known to be aligned to some boundary,
+this can be specified as the fourth argument, otherwise it should be set to 0 or
+1.
+</p>
+</div>
+
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_isunordered">'<tt>llvm.isunordered.*</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare bool %llvm.isunordered.f32(float Val1, float Val2)
+ declare bool %llvm.isunordered.f64(double Val1, double Val2)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.isunordered</tt>' intrinsics return true if either or both of the
+specified floating point values is a NAN.
+</p>
+
+<h5>Arguments:</h5>
+
+<p>
+The arguments are floating point numbers of the same type.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+If either or both of the arguments is a SNAN or QNAN, it returns true, otherwise
+false.
+</p>
+</div>
+
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_sqrt">'<tt>llvm.sqrt.*</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare double %llvm.sqrt.f32(float Val)
+ declare double %llvm.sqrt.f64(double Val)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.sqrt</tt>' intrinsics return the sqrt of the specified operand,
+returning the same value as the libm '<tt>sqrt</tt>' function would. Unlike
+<tt>sqrt</tt> in libm, however, <tt>llvm.sqrt</tt> has undefined behavior for
+negative numbers (which allows for better optimization).
+</p>
+
+<h5>Arguments:</h5>
+
+<p>
+The argument and return value are floating point numbers of the same type.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+This function returns the sqrt of the specified operand if it is a positive
+floating point number.
+</p>
+</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="int_manip">Bit Manipulation Intrinsics</a>
+</div>
+
+<div class="doc_text">
+<p>
+LLVM provides intrinsics for a few important bit manipulation operations.
+These allow efficient code generation for some algorithms.
+</p>
+
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_bswap">'<tt>llvm.bswap.*</tt>' Intrinsics</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare ushort %llvm.bswap.i16(ushort <id>)
+ declare uint %llvm.bswap.i32(uint <id>)
+ declare ulong %llvm.bswap.i64(ulong <id>)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.bwsap</tt>' family of intrinsics is used to byteswap a 16, 32 or
+64 bit quantity. These are useful for performing operations on data that is not
+in the target's native byte order.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+The <tt>llvm.bswap.16</tt> intrinsic returns a ushort value that has the high and low
+byte of the input ushort swapped. Similarly, the <tt>llvm.bswap.i32</tt> intrinsic
+returns a uint value that has the four bytes of the input uint swapped, so that
+if the input bytes are numbered 0, 1, 2, 3 then the returned uint will have its
+bytes in 3, 2, 1, 0 order. The <tt>llvm.bswap.i64</tt> intrinsic extends this concept
+to 64 bits.
+</p>
+
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="int_ctpop">'<tt>llvm.ctpop.*</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare ubyte %llvm.ctpop.i8 (ubyte <src>)
+ declare ushort %llvm.ctpop.i16(ushort <src>)
+ declare uint %llvm.ctpop.i32(uint <src>)
+ declare ulong %llvm.ctpop.i64(ulong <src>)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.ctpop</tt>' family of intrinsics counts the number of bits set in a
+value.
+</p>
+
+<h5>Arguments:</h5>
+
+<p>
+The only argument is the value to be counted. The argument may be of any
+unsigned integer type. The return type must match the argument type.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+The '<tt>llvm.ctpop</tt>' intrinsic counts the 1's in a variable.
+</p>
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="int_ctlz">'<tt>llvm.ctlz.*</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare ubyte %llvm.ctlz.i8 (ubyte <src>)
+ declare ushort %llvm.ctlz.i16(ushort <src>)
+ declare uint %llvm.ctlz.i32(uint <src>)
+ declare ulong %llvm.ctlz.i64(ulong <src>)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.ctlz</tt>' family of intrinsic functions counts the number of
+leading zeros in a variable.
+</p>
+
+<h5>Arguments:</h5>
+
+<p>
+The only argument is the value to be counted. The argument may be of any
+unsigned integer type. The return type must match the argument type.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+The '<tt>llvm.ctlz</tt>' intrinsic counts the leading (most significant) zeros
+in a variable. If the src == 0 then the result is the size in bits of the type
+of src. For example, <tt>llvm.cttz(int 2) = 30</tt>.
+</p>
+</div>
+
+
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="int_cttz">'<tt>llvm.cttz.*</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre>
+ declare ubyte %llvm.cttz.i8 (ubyte <src>)
+ declare ushort %llvm.cttz.i16(ushort <src>)
+ declare uint %llvm.cttz.i32(uint <src>)
+ declare ulong %llvm.cttz.i64(ulong <src>)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>
+The '<tt>llvm.cttz</tt>' family of intrinsic functions counts the number of
+trailing zeros.
+</p>
+
+<h5>Arguments:</h5>
+
+<p>
+The only argument is the value to be counted. The argument may be of any
+unsigned integer type. The return type must match the argument type.
+</p>
+
+<h5>Semantics:</h5>
+
+<p>
+The '<tt>llvm.cttz</tt>' intrinsic counts the trailing (least significant) zeros
+in a variable. If the src == 0 then the result is the size in bits of the type
+of src. For example, <tt>llvm.cttz(2) = 1</tt>.
+</p>
+</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="int_debugger">Debugger Intrinsics</a>
+</div>
+
+<div class="doc_text">
+<p>
+The LLVM debugger intrinsics (which all start with <tt>llvm.dbg.</tt> prefix),
are described in the <a
href="SourceLevelDebugging.html#format_common_intrinsics">LLVM Source Level
Debugging</a> document.
<!-- *********************************************************************** -->
<hr>
-<div class="doc_footer">
-<address><a href="mailto:sabre@nondot.org">Chris Lattner</a></address>
-<a href="http://llvm.cs.uiuc.edu">The LLVM Compiler Infrastructure</a> <br>
-Last modified: $Date$ </div>
+<address>
+ <a href="http://jigsaw.w3.org/css-validator/check/referer"><img
+ src="http://jigsaw.w3.org/css-validator/images/vcss" alt="Valid CSS!"></a>
+ <a href="http://validator.w3.org/check/referer"><img
+ src="http://www.w3.org/Icons/valid-html401" alt="Valid HTML 4.01!" /></a>
+
+ <a href="mailto:sabre@nondot.org">Chris Lattner</a><br>
+ <a href="http://llvm.org">The LLVM Compiler Infrastructure</a><br>
+ Last modified: $Date$
+</address>
</body>
</html>