-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
-<html><head><title>llvm Assembly Language Reference Manual</title></head>
-<body bgcolor=white>
+<!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>
+ <link rel="stylesheet" href="llvm.css" type="text/css">
+</head>
-<table width="100%" bgcolor="#330077" border=0 cellpadding=4 cellspacing=0>
-<tr><td> <font size=+5 color="#EEEEFF" face="Georgia,Palatino,Times,Roman"><b>llvm Assembly Language Reference Manual</b></font></td>
-</tr></table>
+<body>
+<div class="doc_title"> LLVM Language Reference Manual </div>
<ol>
- <li><a href="#abstract">Abstract</a>
- <li><a href="#introduction">Introduction</a>
- <li><a href="#identifiers">Identifiers</a>
+ <li><a href="#abstract">Abstract</a></li>
+ <li><a href="#introduction">Introduction</a></li>
+ <li><a href="#identifiers">Identifiers</a></li>
<li><a href="#typesystem">Type System</a>
<ol>
- <li><a href="#t_primitive">Primitive Types</a>
- <ol>
- <li><a href="#t_classifications">Type Classifications</a>
+ <li><a href="#t_primitive">Primitive Types</a>
+ <li><a href="#t_classifications">Type Classifications</a></li>
</ol>
+ </li>
<li><a href="#t_derived">Derived Types</a>
<ol>
- <li><a href="#t_array" >Array Type</a>
- <li><a href="#t_method" >Method Type</a>
- <li><a href="#t_pointer">Pointer Type</a>
- <li><a href="#t_struct" >Structure Type</a>
- <li><a href="#t_packed" >Packed Type</a>
+ <li><a href="#t_array">Array Type</a></li>
+ <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> -->
</ol>
+ </li>
</ol>
+ </li>
<li><a href="#highlevel">High Level Structure</a>
<ol>
- <li><a href="#modulestructure">Module Structure</a>
- <li><a href="#methodstructure">Method Structure</a>
+ <li><a href="#modulestructure">Module Structure</a></li>
+ <li><a href="#globalvars">Global Variables</a></li>
+ <li><a href="#functionstructure">Function Structure</a></li>
</ol>
+ </li>
<li><a href="#instref">Instruction Reference</a>
<ol>
<li><a href="#terminators">Terminator Instructions</a>
<ol>
- <li><a href="#i_ret" >'<tt>ret</tt>' Instruction</a>
- <li><a href="#i_br" >'<tt>br</tt>' Instruction</a>
- <li><a href="#i_switch" >'<tt>switch</tt>' Instruction</a>
- <li><a href="#i_callwith">'<tt>call .. with</tt>' Instruction</a>
- </ol>
- <li><a href="#unaryops">Unary Operations</a>
- <ol>
- <li><a href="#i_not" >'<tt>not</tt>' Instruction</a>
- <li><a href="#i_cast">'<tt>cast .. to</tt>' Instruction</a>
+ <li><a href="#i_ret">'<tt>ret</tt>' Instruction</a></li>
+ <li><a href="#i_br">'<tt>br</tt>' Instruction</a></li>
+ <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>
</ol>
+ </li>
<li><a href="#binaryops">Binary Operations</a>
<ol>
- <li><a href="#i_add" >'<tt>add</tt>' Instruction</a>
- <li><a href="#i_sub" >'<tt>sub</tt>' Instruction</a>
- <li><a href="#i_mul" >'<tt>mul</tt>' Instruction</a>
- <li><a href="#i_div" >'<tt>div</tt>' Instruction</a>
- <li><a href="#i_rem" >'<tt>rem</tt>' Instruction</a>
- <li><a href="#i_setcc">'<tt>set<i>cc</i></tt>' Instructions</a>
+ <li><a href="#i_add">'<tt>add</tt>' Instruction</a></li>
+ <li><a href="#i_sub">'<tt>sub</tt>' Instruction</a></li>
+ <li><a href="#i_mul">'<tt>mul</tt>' Instruction</a></li>
+ <li><a href="#i_div">'<tt>div</tt>' Instruction</a></li>
+ <li><a href="#i_rem">'<tt>rem</tt>' Instruction</a></li>
+ <li><a href="#i_setcc">'<tt>set<i>cc</i></tt>' Instructions</a></li>
</ol>
+ </li>
<li><a href="#bitwiseops">Bitwise Binary Operations</a>
<ol>
- <li><a href="#i_and">'<tt>and</tt>' Instruction</a>
- <li><a href="#i_or" >'<tt>or</tt>' Instruction</a>
- <li><a href="#i_xor">'<tt>xor</tt>' Instruction</a>
- <li><a href="#i_shl">'<tt>shl</tt>' Instruction</a>
- <li><a href="#i_shr">'<tt>shr</tt>' Instruction</a>
+ <li><a href="#i_and">'<tt>and</tt>' Instruction</a></li>
+ <li><a href="#i_or">'<tt>or</tt>' Instruction</a></li>
+ <li><a href="#i_xor">'<tt>xor</tt>' Instruction</a></li>
+ <li><a href="#i_shl">'<tt>shl</tt>' Instruction</a></li>
+ <li><a href="#i_shr">'<tt>shr</tt>' Instruction</a></li>
</ol>
+ </li>
<li><a href="#memoryops">Memory Access Operations</a>
<ol>
- <li><a href="#i_malloc" >'<tt>malloc</tt>' Instruction</a>
- <li><a href="#i_free" >'<tt>free</tt>' Instruction</a>
- <li><a href="#i_alloca" >'<tt>alloca</tt>' Instruction</a>
- <li><a href="#i_load" >'<tt>load</tt>' Instruction</a>
- <li><a href="#i_store" >'<tt>store</tt>' Instruction</a>
- <li><a href="#i_getfieldptr">'<tt>getfieldptr</tt>' Instruction</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>
</ol>
+ </li>
<li><a href="#otherops">Other Operations</a>
<ol>
- <li><a href="#i_call" >'<tt>call</tt>' Instruction</a>
- <li><a href="#i_icall">'<tt>icall</tt>' Instruction</a>
- <li><a href="#i_phi" >'<tt>phi</tt>' Instruction</a>
+ <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_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>
</ol>
- <li><a href="#builtinfunc">Builtin Functions</a>
+ </li>
</ol>
- <li><a href="#todo">TODO List</a>
+ </li>
+ <li><a href="#intrinsics">Intrinsic Functions</a>
<ol>
- <li><a href="#exception">Exception Handling Instructions</a>
- <li><a href="#synchronization">Synchronization Instructions</a>
- </ol>
- <li><a href="#extensions">Possible Extensions</a>
- <ol>
- <li><a href="#i_tailcall">'<tt>tailcall</tt>' Instruction</a>
- <li><a href="#globalvars">Global Variables</a>
- <li><a href="#explicitparrellelism">Explicit Parrellelism</a>
+ <li><a href="#int_varargs">Variable Argument Handling Intrinsics</a>
+ <ol>
+ <li><a href="#i_va_start">'<tt>llvm.va_start</tt>' Intrinsic</a></li>
+ <li><a href="#i_va_end">'<tt>llvm.va_end</tt>' Intrinsic</a></li>
+ <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>
+ </ol>
+ </li>
+ <li><a href="#int_os">Operating System Intrinsics</a>
+ <ol>
+ <li><a href="#i_readport">'<tt>llvm.readport</tt>' Intrinsic</a></li>
+ <li><a href="#i_writeport">'<tt>llvm.writeport</tt>' Intrinsic</a></li>
+ <li><a href="#i_readio">'<tt>llvm.readio</tt>' Intrinsic</a></li>
+ <li><a href="#i_writeio">'<tt>llvm.writeio</tt>' Intrinsic</a></li>
+ </ol>
+ <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_memset">'<tt>llvm.memset</tt>' Intrinsic</a></li>
+ <li><a href="#i_isunordered">'<tt>llvm.isunordered</tt>' Intrinsic</a></li>
+ </ol>
+ </li>
+ <li><a href="#int_debugger">Debugger intrinsics</a></li>
</ol>
- <li><a href="#related">Related Work</a>
+ </li>
</ol>
+<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>
<!-- *********************************************************************** -->
-<p><table width="100%" bgcolor="#330077" border=0 cellpadding=4 cellspacing=0><tr><td align=center><font color="#EEEEFF" size=+2 face="Georgia,Palatino"><b>
-<a name="abstract">Abstract
-</b></font></td></tr></table><ul>
+<div class="doc_section"> <a name="abstract">Abstract </a></div>
<!-- *********************************************************************** -->
-<blockquote>
- This document describes the LLVM assembly language IR/VM. LLVM is an SSA
- based representation that attempts to be a useful midlevel IR by providing
- type safety, low level operations, flexibility, and the capability to
- represent 'all' high level languages cleanly.
-</blockquote>
-
-
-
+<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,
+low-level operations, flexibility, and the capability of representing
+'all' high-level languages cleanly. It is the common code
+representation used throughout all phases of the LLVM compilation
+strategy.</p>
+</div>
<!-- *********************************************************************** -->
-</ul><table width="100%" bgcolor="#330077" border=0 cellpadding=4 cellspacing=0><tr><td align=center><font color="#EEEEFF" size=+2 face="Georgia,Palatino"><b>
-<a name="introduction">Introduction
-</b></font></td></tr></table><ul>
+<div class="doc_section"> <a name="introduction">Introduction</a> </div>
<!-- *********************************************************************** -->
-The LLVM is designed to exhibit a dual nature: on one hand, it is a useful compiler IR, on the other hand, it is a bytecode representation for dynamic compilation. We contend that this is a natural and good thing, making LLVM a natural form of communication between different compiler phases, and also between a static and dynamic compiler.<p>
-
-This dual nature leads to three different representations of LLVM (the human readable assembly representation, the compact bytecode representation, and the in memory, pointer based, representation). This document describes the human readable representation and notation.<p>
-
-The LLVM representation aims to be a light weight and low level while being expressive, type safe, 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. By providing type safety, LLVM can be used as the target of optimizations: for example, through pointer analysis, it 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 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),
+and as a human readable assembly language representation. This allows
+LLVM to provide a powerful intermediate representation for efficient
+compiler transformations and analysis, while providing a natural means
+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
+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
+microprocessors are "universal IR's", allowing many source languages to
+be mapped to them). By providing type information, LLVM can be used as
+the target of optimizations: for example, through pointer analysis, it
+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>
<!-- _______________________________________________________________________ -->
-</ul><a name="wellformed"><h4><hr size=0>Well Formedness</h4><ul>
+<div class="doc_subsubsection"> <a name="wellformed">Well-Formedness</a> </div>
-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>
+<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
</pre>
-...because only a <tt><a href="#i_phi">phi</a></tt> node may refer to itself. The LLVM api provides a verification function (<tt>verify</tt>) that may be used to verify that a whole module or a single method is well formed. It is useful to validate whether an optimization pass performed a well formed transformation to the code.<p>
-
-
-Describe the typesetting conventions here.
+<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
+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>
<!-- *********************************************************************** -->
-</ul><table width="100%" bgcolor="#330077" border=0 cellpadding=4 cellspacing=0><tr><td align=center><font color="#EEEEFF" size=+2 face="Georgia,Palatino"><b>
-<a name="identifiers">Identifiers
-</b></font></td></tr></table><ul>
+<div class="doc_section"> <a name="identifiers">Identifiers</a> </div>
<!-- *********************************************************************** -->
-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.
-<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>'.
-<li>Unnamed values are represented as an unsigned numeric value with a '%' prefix. For example, %12, %2, %44.
-</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>
-
-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 may start with a '%' character.<p>
-
-Here is an example of LLVM code to multiply the integer variable '<tt>%X</tt>' by 8:<p>
-
-The easy way:
-<pre>
- %result = <a href="#i_mul">mul</a> int %X, 8
-</pre>
-
-After strength reduction:
-<pre>
- %result = <a href="#i_shl">shl</a> int %X, ubyte 3
-</pre>
-
-And the hard way:
-<pre>
- <a href="#i_add">add</a> int %X, %X <i>; yields {int}:%0</i>
- <a href="#i_add">add</a> int %0, %0 <i>; yields {int}:%1</i>
- %result = <a href="#i_add">add</a> int %1, %1
-</pre>
+<div class="doc_text">
-This last way of multiplying <tt>%X</tt> by 8 illustrates several important lexical features of LLVM:<p>
+<p>LLVM uses three different forms of identifiers, for different
+purposes:</p>
<ol>
-<li>Comments are delimited with a '<tt>;</tt>' and go until the end of line.
-<li>Unnamed temporaries are created when the result of a computation is not assigned to a named value.
-<li>Unnamed temporaries are numbered sequentially
-</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>
-
-
-
+ <li>Numeric constants are represented as you would expect: 12, -3
+123.421, etc. Floating point constants have an optional hexadecimal
+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>
+</ol>
+<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>
+<p>The easy way:</p>
+<pre> %result = <a href="#i_mul">mul</a> uint %X, 8<br></pre>
+<p>After strength reduction:</p>
+<pre> %result = <a href="#i_shl">shl</a> uint %X, ubyte 3<br></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>
+<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>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>
+</div>
<!-- *********************************************************************** -->
-</ul><table width="100%" bgcolor="#330077" border=0 cellpadding=4 cellspacing=0><tr><td align=center><font color="#EEEEFF" size=+2 face="Georgia,Palatino"><b>
-<a name="typesystem">Type System
-</b></font></td></tr></table><ul>
+<div class="doc_section"> <a name="typesystem">Type System</a> </div>
<!-- *********************************************************************** -->
-
-The LLVM type system is important to the overall usefulness of the language and VM runtime. By being strongly typed, a number of optimizations may be performed on the IR directly, without having to do extra analysis to derive types. A strong type system also makes it easier to comprehend generated code and assists with safety concerns.<p>
-
-The assembly language form for the type system was heavily influenced by the type problems in the C language<sup><a href="#rw_stroustrup">1</a></sup>.<p>
-
-
-
+<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
+extra analyses on the side before the transformation. A strong type
+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>
<!-- ======================================================================= -->
-</ul><table width="100%" bgcolor="#441188" border=0 cellpadding=4 cellspacing=0><tr><td> </td><td width="100%"> <font color="#EEEEFF" face="Georgia,Palatino"><b>
-<a name="t_primitive">Primitive Types
-</b></font></td></tr></table><ul>
-
-The primitive types are the fundemental building blocks of the LLVM system. The current set of primitive types are as follows:<p>
-
-<table border=0 align=center><tr><td>
-
-<table border=1 cellspacing=0 cellpadding=4 align=center>
-<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>
+<div class="doc_subsection"> <a name="t_primitive">Primitive Types</a> </div>
+<div class="doc_text">
+<p>The primitive types are the fundamental building blocks of the LLVM
+system. The current set of primitive types are as follows:</p>
+
+<table border="0" style="align: center">
+ <tbody>
+ <tr>
+ <td>
+ <table border="1" cellspacing="0" cellpadding="4" style="align: center">
+ <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>
+ </tbody>
+ </table>
+ </td>
+ <td valign="top">
+ <table border="1" cellspacing="0" cellpadding="4">
+ <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>
+ </tbody>
+ </table>
+ </td>
+ </tr>
+ </tbody>
</table>
-</td><td>
-
-<table border=1 cellspacing=0 cellpadding=4 align=center>
-<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><td><tt>lock</tt></td> <td>Recursive mutex value</td></tr>
-</table>
-
-</td></tr></table><p>
-
-
-
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="t_classifications"><h4><hr size=0>Type Classifications</h4><ul>
-
-These different primitive types fall into a few useful classifications:<p>
-
-<table border=1 cellspacing=0 cellpadding=4 align=center>
-<tr><td><a name="t_signed">signed</td> <td><tt>sbyte, short, int, long, float, double</tt></td></tr>
-<tr><td><a name="t_unsigned">unsigned</td><td><tt>ubyte, ushort, uint, ulong</tt></td></tr>
-<tr><td><a name="t_integral">integral</td><td><tt>ubyte, sbyte, ushort, short, uint, int, ulong, long</tt></td></tr>
-<tr><td><a name="t_floating">floating point</td><td><tt>float, double</tt></td></tr>
-<tr><td><a name="t_firstclass">first class</td><td><tt>bool, ubyte, sbyte, ushort, short, uint, int, ulong, long, float, double, lock</tt></td></tr>
-</table><p>
-
-
-
-
+<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>
+
+<table border="1" cellspacing="0" cellpadding="4">
+ <tbody>
+ <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_unsigned">unsigned</a></td>
+ <td><tt>ubyte, ushort, uint, ulong</tt></td>
+ </tr>
+ <tr>
+ <td><a name="t_integer">integer</a></td>
+ <td><tt>ubyte, sbyte, ushort, short, uint, int, ulong, long</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>
+ </tr>
+ <tr>
+ <td><a name="t_floating">floating point</a></td>
+ <td><tt>float, double</tt></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>
+ </tr>
+ </tbody>
+</table>
+<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>
<!-- ======================================================================= -->
-</ul><table width="100%" bgcolor="#441188" border=0 cellpadding=4 cellspacing=0><tr><td> </td><td width="100%"> <font color="#EEEEFF" face="Georgia,Palatino"><b>
-<a name="t_derived">Derived Types
-</b></font></td></tr></table><ul>
-
-The real power in LLVM comes from the derived types in the system. This is what allows a programmer to represent arrays, methods, 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 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>
<!-- _______________________________________________________________________ -->
-</ul><a name="t_array"><h4><hr size=0>Array Type</h4><ul>
-
+<div class="doc_subsubsection"> <a name="t_array">Array Type</a> </div>
+<div class="doc_text">
<h5>Overview:</h5>
-
-The array type is a very simple derived type. It arranges elements sequentially in memory. There are two different forms of the array type:<p>
-
-<ol>
-<a name="t_array_fixed"><b><li>Fixed size array type:</b><br>
- The simplest form of the array type, has a size hard coded in as part of the type. Thus these are three distinct type qualifiers:<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>
-
-Fixed sized arrays are very useful for compiler optimization passes and for representing analysis results. Additionally, multidimensional arrays must have fixed sizes for all dimensions except the outer-most dimension.<p>
-
-<a name="t_array_unsized"><b><li>Dynamically sized array type:</b><br>
- The dynamically sized arrays are very similar to the fixed size arrays, except that the size of the array is calculated at runtime by the virtual machine. This is useful for representing generic methods that take any size array as an argument, or when representing Java style arrays.
-</ol><p>
-
-Here are some examples of multidimensional arrays:<p>
-<ul>
-<table border=0 cellpadding=0 cellspacing=0>
-<tr><td><tt>[3 x [4 x int]]</tt></td><td>: 3x4 array integer values.</td></tr>
-<tr><td><tt>[[10 x int]]</tt></td><td>: Nx10 array of integer values.</td></tr>
-<tr><td><tt>[2 x [3 x [4 x uint]]]</tt></td><td>: 2x3x4 array of unsigned integer values.</td></tr>
+<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
+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>
+<p>Here are some examples of multidimensional arrays:</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>
-</ul>
-
-
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="t_method"><h4><hr size=0>Method Type</h4><ul>
-
+<div class="doc_subsubsection"> <a name="t_function">Function Type</a> </div>
+<div class="doc_text">
<h5>Overview:</h5>
-
-The method type can be thought of as a method signature. It consists of a return type and a list of formal parameter types. Method types are usually used when to build virtual function tables (which are structures of pointers to methods) and for indirect method calls.<p>
-
+<p>The function type can be thought of as a function signature. It
+consists of a return type and a list of formal parameter types.
+Function types are usually used to build virtual function tables
+(which are structures of pointers to functions), for indirect function
+calls, and when defining a function.</p>
+<p>
+The return type of a function type cannot be an aggregate type.
+</p>
<h5>Syntax:</h5>
-<pre>
- <returntype> (<parameter list>)
-</pre>
-
-Where '<tt><parameter list></tt>' is a comma seperated list of type specifiers.<p>
-
+<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>,
+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>
-<ul>
-<table border=0 cellpadding=0 cellspacing=0>
-<tr><td><tt>int (int)</tt></td><td>: method 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 method that takes an <tt>int</tt> and a <a href="#t_pointer">pointer</a> to <tt>int</tt>, returning <tt>float</tt>.</td></tr>
-</table>
-</ul>
-
+<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>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="t_struct"><h4><hr size=0>Structure Type</h4><ul>
-
+<div class="doc_subsubsection"> <a name="t_struct">Structure Type</a> </div>
+<div class="doc_text">
<h5>Overview:</h5>
-
-The structure type is used to represent a collection of data members together in memory. Although the runtime is allowed to lay out the data members any way that it would like, they are guaranteed to be "close" to each other.<p>
-
-Structures are accessed using '<tt><a href="#i_load">load</a></tt> and '<tt><a href="#i_store">store</a></tt>' by getting a pointer to a field with the '<tt><a href="#i_getfieldptr">getfieldptr</a></tt>' instruction.<p>
-
+<p>The structure type is used to represent a collection of data members
+together in memory. The packing of the field types is defined to match
+the ABI of the underlying processor. The elements of a structure may
+be any type that has a size.</p>
+<p>Structures are accessed using '<tt><a href="#i_load">load</a></tt>
+and '<tt><a href="#i_store">store</a></tt>' by getting a pointer to a
+field with the '<tt><a href="#i_getelementptr">getelementptr</a></tt>'
+instruction.</p>
<h5>Syntax:</h5>
-<pre>
- { <type list> }
-</pre>
-
-
+<pre> { <type list> }<br></pre>
<h5>Examples:</h5>
-<table border=0 cellpadding=0 cellspacing=0>
-<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_method">method</a> that takes an <tt>int</tt>, returning an <tt>int</tt>.</td></tr>
-</table>
+<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>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="t_pointer"><h4><hr size=0>Pointer Type</h4><ul>
+<div class="doc_subsubsection"> <a name="t_pointer">Pointer Type</a> </div>
+<div class="doc_text">
+<h5>Overview:</h5>
+<p>As in many languages, the pointer type represents a pointer or
+reference to another object, which must live in memory.</p>
+<h5>Syntax:</h5>
+<pre> <type> *<br></pre>
+<h5>Examples:</h5>
+
+<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>
+</div>
+<!-- _______________________________________________________________________ --><!--
+<div class="doc_subsubsection">
+ <a name="t_packed">Packed Type</a>
+</div>
-<!-- _______________________________________________________________________ -->
-</ul><a name="t_packed"><h4><hr size=0>Packed Type</h4><ul>
+<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>
Packed types should be 'nonsaturated' because standard data types are not saturated. Maybe have a saturated packed type?<p>
-
-<!-- *********************************************************************** -->
-</ul><table width="100%" bgcolor="#330077" border=0 cellpadding=4 cellspacing=0><tr><td align=center><font color="#EEEEFF" size=+2 face="Georgia,Palatino"><b>
-<a name="highlevel">High Level Structure
-</b></font></td></tr></table><ul>
-<!-- *********************************************************************** -->
-
+</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>
+<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>
+ <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++.
+ <p> </p>
+ </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.
+ <p> </p>
+ </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.
+ <p> </p>
+ </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.
+ <p> </p>
+ </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.
+ <p> </p>
+ </dd>
+</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>
<!-- ======================================================================= -->
-</ul><table width="100%" bgcolor="#441188" border=0 cellpadding=4 cellspacing=0><tr><td> </td><td width="100%"> <font color="#EEEEFF" face="Georgia,Palatino"><b>
-<a name="modulestructure">Module Structure
-</b></font></td></tr></table><ul>
+<div class="doc_subsection">
+ <a name="globalvars">Global Variables</a>
+</div>
+<div class="doc_text">
-talk about the elements of a module: constant pool and method list.<p>
+<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).</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>
-<!-- ======================================================================= -->
-</ul><table width="100%" bgcolor="#441188" border=0 cellpadding=4 cellspacing=0><tr><td> </td><td width="100%"> <font color="#EEEEFF" face="Georgia,Palatino"><b>
-<a name="methodstructure">Method Structure
-</b></font></td></tr></table><ul>
-
+</div>
-talk about the constant pool<p>
-talk about how basic blocks delinate labels<p>
-talk about how basic blocks end with terminators<p>
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="functionstructure">Functions</a>
+</div>
-<!-- *********************************************************************** -->
-</ul><table width="100%" bgcolor="#330077" border=0 cellpadding=4 cellspacing=0><tr><td align=center><font color="#EEEEFF" size=+2 face="Georgia,Palatino"><b>
-<a name="instref">Instruction Reference
-</b></font></td></tr></table><ul>
-<!-- *********************************************************************** -->
+<div class="doc_text">
-List all of the instructions, list valid types that they accept. Tell what they
-do and stuff also.
+<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>
-<!-- ======================================================================= -->
-</ul><table width="100%" bgcolor="#441188" border=0 cellpadding=4 cellspacing=0><tr><td> </td><td width="100%"> <font color="#EEEEFF" face="Georgia,Palatino"><b>
-<a name="terminators">Terminator Instructions
-</b></font></td></tr></table><ul>
+<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.</p>
-As was mentioned <a href="#methodstructure">previously</a>, every basic block in
-a program ends with a "Terminator" instruction. Additionally, all terminators yield a '<tt>void</tt>' value: they produce control flow, not values.<p>
-
-There are three different terminator instructions: the '<a href="#i_ret"><tt>ret</tt></a>' instruction, the '<a href="#i_br"><tt>br</tt></a>' instruction, and the '<a href="#i_switch"><tt>switch</tt></a>' instruction.<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
+ 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
+ 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>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_ret"><h4><hr size=0>'<tt>ret</tt>' Instruction</h4><ul>
-
+<div class="doc_subsubsection"> <a name="i_ret">'<tt>ret</tt>'
+Instruction</a> </div>
+<div class="doc_text">
<h5>Syntax:</h5>
-<pre>
- ret <type> <value> <i>; Return a value from a non-void method</i>
- ret void <i>; Return from void method</i>
+<pre> ret <type> <value> <i>; Return a value from a non-void function</i>
+ ret void <i>; Return from void function</i>
</pre>
-
<h5>Overview:</h5>
-The '<tt>ret</tt>' instruction is used to return control flow (and optionally a value) from a method, back to the caller.<p>
-
-There are two forms of the '<tt>ret</tt>' instructruction: one that returns a value and then causes control flow, and one that just causes control flow to occur.<p>
-
+<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>' instruction: one that
+returns a value and then causes control flow, and one that just causes
+control flow to occur.</p>
<h5>Arguments:</h5>
-The '<tt>ret</tt>' instruction may return any '<a href="#t_firstclass">first class</a>' type. Notice that a method is not <a href="#wellformed">well formed</a> if there exists a '<tt>ret</tt>' instruction inside of the method that returns a value that does not match the return type of the method.<p>
-
+<p>The '<tt>ret</tt>' instruction may return any '<a
+ href="#t_firstclass">first class</a>' type. Notice that a function is
+not <a href="#wellformed">well formed</a> if there exists a '<tt>ret</tt>'
+instruction inside of the function that returns a value that does not
+match the return type of the function.</p>
<h5>Semantics:</h5>
-When the '<tt>ret</tt>' instruction is executed, control flow returns back to the calling method's context. If the instruction returns a value, that value shall be propogated into the calling method's data space.<p>
-
+<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
+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
+returns a value, that value shall set the call or invoke instruction's
+return value.</p>
<h5>Example:</h5>
-<pre>
- ret int 5 <i>; Return an integer value of 5</i>
- ret void <i>; Return from a void method</i>
+<pre> ret int 5 <i>; Return an integer value of 5</i>
+ ret void <i>; Return from a void function</i>
</pre>
-
-
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_br"><h4><hr size=0>'<tt>br</tt>' Instruction</h4><ul>
-
+<div class="doc_subsubsection"> <a name="i_br">'<tt>br</tt>' Instruction</a> </div>
+<div class="doc_text">
<h5>Syntax:</h5>
-<pre>
- br bool <cond>, label <iftrue>, label <iffalse>
- br label <dest> <i>; Unconditional branch</i>
+<pre> br bool <cond>, label <iftrue>, label <iffalse><br> br label <dest> <i>; Unconditional branch</i>
</pre>
-
<h5>Overview:</h5>
-The '<tt>br</tt>' instruction is used to cause control flow to transfer to a different basic block in the current method. There are two forms of this instruction, corresponding to a conditional branch and an unconditional branch. The '<tt>br</tt>' instruction is a (useful) special case '<tt><a href="#i_switch">switch</a></tt>' instruction.<p>
-
+<p>The '<tt>br</tt>' instruction is used to cause control flow to
+transfer to a different basic block in the current function. There are
+two forms of this instruction, corresponding to a conditional branch
+and an unconditional branch.</p>
<h5>Arguments:</h5>
-
-The conditional branch form of the '<tt>br</tt>' instruction shall take a single '<tt>bool</tt>' value and two '<tt>label</tt>' values. The unconditional form of the '<tt>br</tt>' instruction takes a single '<tt>label</tt>' value as a target.<p>
-
+<p>The conditional branch form of the '<tt>br</tt>' instruction takes a
+single '<tt>bool</tt>' value and two '<tt>label</tt>' values. The
+unconditional form of the '<tt>br</tt>' instruction takes a single '<tt>label</tt>'
+value as a target.</p>
<h5>Semantics:</h5>
-
-Upon execution of a conditional '<tt>br</tt>' instruction, the '<tt>bool</tt>' argument is evaluated. If the value is <tt>true</tt>, control flows to the '<tt>iftrue</tt>' '<tt>label</tt>' argument. If "cond" is <tt>false</tt>, control flows to the '<tt>iffalse</tt>' '<tt>label</tt>' argument.<p>
-
+<p>Upon execution of a conditional '<tt>br</tt>' instruction, the '<tt>bool</tt>'
+argument is evaluated. If the value is <tt>true</tt>, control flows
+to the '<tt>iftrue</tt>' <tt>label</tt> argument. If "cond" is <tt>false</tt>,
+control flows to the '<tt>iffalse</tt>' <tt>label</tt> argument.</p>
<h5>Example:</h5>
-<pre>
-Test:
- %cond = <a href="#i_setcc">seteq</a> int %a, %b
- br bool %cond, label %IfEqual, label %IfUnequal
-IfEqual:
- <a href="#i_ret">ret</a> bool true
-IfUnequal:
- <a href="#i_ret">ret</a> bool false
-</pre>
-
-
+<pre>Test:<br> %cond = <a href="#i_setcc">seteq</a> int %a, %b<br> br bool %cond, label %IfEqual, label %IfUnequal<br>IfEqual:<br> <a
+ href="#i_ret">ret</a> int 1<br>IfUnequal:<br> <a href="#i_ret">ret</a> int 0<br></pre>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_switch"><h4><hr size=0>'<tt>switch</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_switch">'<tt>switch</tt>' Instruction</a>
+</div>
+<div class="doc_text">
<h5>Syntax:</h5>
-<pre>
- <i>; Definitions for lookup indirect branch</i>
- %switchtype = type [<anysize> x { uint, label }]
- <i>; Lookup indirect branch</i>
- switch uint <value>, label <defaultdest>, %switchtype <switchtable>
-
- <i>; Indexed indirect branch</i>
- switch uint <idxvalue>, label <defaultdest>, [<anysize> x label] <desttable>
+<pre>
+ switch <intty> <value>, label <defaultdest> [ <intty> <val>, label <dest> ... ]
</pre>
<h5>Overview:</h5>
-The '<tt>switch</tt>' instruction is used to transfer control flow to one of several different places. It is a simple generalization of the '<tt>br</tt>' instruction, and supports a strict superset of its functionality.<p>
-The '<tt>switch</tt>' statement supports two different styles of indirect branching: lookup branching and indexed branching. Lookup branching is generally useful if the values to switch on are spread far appart, where index branching is useful if the values to switch on are generally dense.<p>
+<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>
-The two different forms of the '<tt>switch</tt>' statement are simple hints to the underlying virtual machine implementation. For example, a virtual machine may choose to implement a small indirect branch table as a series of predicated comparisons: if it is faster for the target architecture.<p>
<h5>Arguments:</h5>
-The lookup form of the '<tt>switch</tt>' instruction uses three parameters: a '<tt>uint</tt>' comparison value '<tt>value</tt>', a default '<tt>label</tt>' destination, and a sized array of pairs of comparison value constants and '<tt>label</tt>'s. The sized array must be a constant value.<p>
-The indexed form of the '<tt>switch</tt>' instruction uses three parameters: an '<tt>uint</tt>' index value, a default '<tt>label</tt>' and a sized array of '<tt>label</tt>'s. The '<tt>dests</tt>' array must be a constant array.
+<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>
-The lookup style switch statement 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. <p>
-The index branch form simply looks up a label element directly in a table and branches to it.<p>
+<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>
+
+<h5>Implementation:</h5>
-In either case, the compiler knows the static size of the array, because it is provided as part of the constant values type.<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 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
- switch uint %Val, label %truedest, [1 x label] [label %falsedest ]
-
- <i>; Emulate an unconditional br instruction</i>
- switch uint 0, label %dest, [ 0 x label] [ ]
-
- <i>; Implement a jump table using the constant pool:</i>
- void "testmeth"(int %arg0)
- %switchdests = [3 x label] [ label %onzero, label %onone, label %ontwo ]
- {
- ...
- switch uint %val, label %otherwise, [3 x label] %switchdests...
- ...
- }
+ <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>; Implement the equivilent jump table directly:</i>
- switch uint %val, label %otherwise, [3 x label] [ label %onzero,
- label %onone,
- label %ontwo ]
+ <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>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_callwith"><h4><hr size=0>'<tt>call .. with</tt>' Instruction</h4><ul>
-
+<div class="doc_subsubsection"> <a name="i_invoke">'<tt>invoke</tt>'
+Instruction</a> </div>
+<div class="doc_text">
<h5>Syntax:</h5>
-<pre>
- <result> = call <method ty> %<method name>(<method args>) with label <break label>
-</pre>
-
+<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>
-The '<tt>call .. with</tt>' instruction is used to cause control flow to transfer to a specified method, with the possibility of control flow transfer to the '<tt>break label</tt>' label, in addition to the possibility of fallthrough to the next basic block. The '<tt><a href="#i_call">call</a></tt>' instruction is closely related, but does guarantees that control flow either never returns from the invoked method, or that it returns to the instruction succeeding the '<tt><a href="#i_call">call</a></tt>' instruction.<p>
-
-TODO: icall .. with needs to be defined as well for an indirect call.<p>
-
+<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>
-
-This instruction requires several arguments:<p>
+<p>This instruction requires several arguments:</p>
<ol>
-<li>'<tt>method ty</tt>': shall be the signature of the named method being invoked. This must be a <a href="#t_method">method type</a>.
-<li>'<tt>method name</tt>': method name to be invoked.
-<li>'<tt>method args</tt>': argument list whose types match the method signature argument types.
-<li>'<tt>break label</tt>': a label that specifies the break label associated with this call.
+ <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>
-
-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 assiciates a label with the method invocation that may be accessed via the runtime library provided by the execution environment. 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>
-
-For a more comprehensive explanation of this instruction look in the llvm/docs/2001-05-18-ExceptionHandling.txt document.
-
+<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>
<h5>Example:</h5>
-<pre>
- %retval = call int (int) %Test(int 15) with label %TestCleanup <i>; {int}:retval set</i>
+<pre> %retval = invoke int %Test(int 15)<br> to label %Continue<br> 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<br></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>
<!-- ======================================================================= -->
-</ul><table width="100%" bgcolor="#441188" border=0 cellpadding=4 cellspacing=0><tr><td> </td><td width="100%"> <font color="#EEEEFF" face="Georgia,Palatino"><b>
-<a name="unaryops">Unary Operations
-</b></font></td></tr></table><ul>
-
-Unary operators are used to do a simple operation to a single value.<p>
-
-There are two different unary operators: the '<a href="#i_not"><tt>not</tt></a>' instruction and the '<a href="#i_cast"><tt>cast</tt></a>' instruction.<p>
-
-
+<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
+necessarily the same type as its operands.</p>
+<p>There are several different binary operators:</p>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_not"><h4><hr size=0>'<tt>not</tt>' Instruction</h4><ul>
-
+<div class="doc_subsubsection"> <a name="i_add">'<tt>add</tt>'
+Instruction</a> </div>
+<div class="doc_text">
<h5>Syntax:</h5>
-<pre>
- <result> = not <ty> <var> <i>; yields {ty}:result</i>
+<pre> <result> = add <ty> <var1>, <var2> <i>; yields {ty}:result</i>
</pre>
-
<h5>Overview:</h5>
-The '<tt>not</tt>' instruction returns the <a href="#logical_integrals">logical</a> inverse of its operand.<p>
-
+<p>The '<tt>add</tt>' instruction returns the sum of its two operands.</p>
<h5>Arguments:</h5>
-The single argument to '<tt>not</tt>' must be of of <a href="#t_integral">integral</a> type.<p>
-
-
+<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>
<h5>Semantics:</h5>
-The '<tt>not</tt>' instruction returns the <a href="#logical_integrals">logical</a> inverse of an <a href="#t_integral">integral</a> type.<p>
-
-Note that the '<tt>not</tt>' instruction is is not defined over to '<tt>bool</tt>' type. To invert a boolean value, the recommended method is to use:<p>
-
-<pre>
- <result> = xor bool true, <var> <i>; yields {bool}:result</i>
+<p>The value produced is the integer or floating point sum of the two
+operands.</p>
+<h5>Example:</h5>
+<pre> <result> = add int 4, %var <i>; yields {int}:result = 4 + %var</i>
</pre>
-
+</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="i_sub">'<tt>sub</tt>'
+Instruction</a> </div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> <result> = sub <ty> <var1>, <var2> <i>; yields {ty}:result</i>
+</pre>
+<h5>Overview:</h5>
+<p>The '<tt>sub</tt>' instruction returns the difference of its two
+operands.</p>
+<p>Note that the '<tt>sub</tt>' instruction is used to represent the '<tt>neg</tt>'
+instruction present in most other intermediate representations.</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>
+<h5>Semantics:</h5>
+<p>The value produced is the integer or floating point difference of
+the two operands.</p>
<h5>Example:</h5>
-<pre>
- %x = not int 1 <i>; {int}:x is now equal to 0</i>
- %x = not bool true <i>; {bool}:x is now equal to false</i>
+<pre> <result> = sub int 4, %var <i>; yields {int}:result = 4 - %var</i>
+ <result> = sub int 0, %val <i>; yields {int}:result = -%var</i>
</pre>
-
-
-
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_cast"><h4><hr size=0>'<tt>cast .. to</tt>' Instruction</h4><ul>
-
-<h1>TODO</h1>
-
-<a name="logical_integrals">
- Talk about what is considered true or false for integrals.
-
-
-
+<div class="doc_subsubsection"> <a name="i_mul">'<tt>mul</tt>'
+Instruction</a> </div>
+<div class="doc_text">
<h5>Syntax:</h5>
-<pre>
+<pre> <result> = mul <ty> <var1>, <var2> <i>; yields {ty}:result</i>
</pre>
-
<h5>Overview:</h5>
-
-
+<p>The '<tt>mul</tt>' instruction returns the product of its 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>
<h5>Semantics:</h5>
+<p>The value produced is the integer or floating point product of the
+two operands.</p>
+<p>There is no signed vs unsigned multiplication. The appropriate
+action is taken based on the type of the operand.</p>
+<h5>Example:</h5>
+<pre> <result> = mul int 4, %var <i>; yields {int}:result = 4 * %var</i>
+</pre>
+</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="i_div">'<tt>div</tt>'
+Instruction</a> </div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> <result> = div <ty> <var1>, <var2> <i>; yields {ty}:result</i>
+</pre>
+<h5>Overview:</h5>
+<p>The '<tt>div</tt>' instruction returns the quotient of its 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>
+<h5>Semantics:</h5>
+<p>The value produced is the integer or floating point quotient of the
+two operands.</p>
+<h5>Example:</h5>
+<pre> <result> = div int 4, %var <i>; yields {int}:result = 4 / %var</i>
+</pre>
+</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="i_rem">'<tt>rem</tt>'
+Instruction</a> </div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> <result> = rem <ty> <var1>, <var2> <i>; yields {ty}:result</i>
+</pre>
+<h5>Overview:</h5>
+<p>The '<tt>rem</tt>' instruction returns the remainder from the
+division of its 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>
+<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
+ 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>'
+Instructions</a> </div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> <result> = seteq <ty> <var1>, <var2> <i>; yields {bool}:result</i>
+ <result> = setne <ty> <var1>, <var2> <i>; yields {bool}:result</i>
+ <result> = setlt <ty> <var1>, <var2> <i>; yields {bool}:result</i>
+ <result> = setgt <ty> <var1>, <var2> <i>; yields {bool}:result</i>
+ <result> = setle <ty> <var1>, <var2> <i>; yields {bool}:result</i>
+ <result> = setge <ty> <var1>, <var2> <i>; yields {bool}:result</i>
+</pre>
+<h5>Overview:</h5>
+<p>The '<tt>set<i>cc</i></tt>' family of instructions returns a boolean
+value based on a comparison of their two operands.</p>
+<h5>Arguments:</h5>
+<p>The two arguments to the '<tt>set<i>cc</i></tt>' instructions must
+be of <a href="#t_firstclass">first class</a> type (it is not possible
+to compare '<tt>label</tt>'s, '<tt>array</tt>'s, '<tt>structure</tt>'
+or '<tt>void</tt>' values, etc...). Both arguments must have identical
+types.</p>
+<h5>Semantics:</h5>
+<p>The '<tt>seteq</tt>' instruction yields a <tt>true</tt> '<tt>bool</tt>'
+value if both operands are equal.<br>
+The '<tt>setne</tt>' instruction yields a <tt>true</tt> '<tt>bool</tt>'
+value if both operands are unequal.<br>
+The '<tt>setlt</tt>' instruction yields a <tt>true</tt> '<tt>bool</tt>'
+value if the first operand is less than the second operand.<br>
+The '<tt>setgt</tt>' instruction yields a <tt>true</tt> '<tt>bool</tt>'
+value if the first operand is greater than the second operand.<br>
+The '<tt>setle</tt>' instruction yields a <tt>true</tt> '<tt>bool</tt>'
+value if the first operand is less than or equal to the second operand.<br>
+The '<tt>setge</tt>' instruction yields a <tt>true</tt> '<tt>bool</tt>'
+value if the first operand is greater than or equal to the second
+operand.</p>
+<h5>Example:</h5>
+<pre> <result> = seteq int 4, 5 <i>; yields {bool}:result = false</i>
+ <result> = setne float 4, 5 <i>; yields {bool}:result = true</i>
+ <result> = setlt uint 4, 5 <i>; yields {bool}:result = true</i>
+ <result> = setgt sbyte 4, 5 <i>; yields {bool}:result = false</i>
+ <result> = setle sbyte 4, 5 <i>; yields {bool}:result = true</i>
+ <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. 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>
+</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="i_and">'<tt>and</tt>'
+Instruction</a> </div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> <result> = and <ty> <var1>, <var2> <i>; yields {ty}:result</i>
+</pre>
+<h5>Overview:</h5>
+<p>The '<tt>and</tt>' instruction returns the bitwise logical and of
+its two operands.</p>
+<h5>Arguments:</h5>
+<p>The two arguments to the '<tt>and</tt>' instruction must be <a
+ href="#t_integral">integral</a> values. Both arguments must have
+identical types.</p>
+<h5>Semantics:</h5>
+<p>The truth table used for the '<tt>and</tt>' instruction is:</p>
+<p> </p>
+<div style="align: center">
+<table border="1" cellspacing="0" cellpadding="4">
+ <tbody>
+ <tr>
+ <td>In0</td>
+ <td>In1</td>
+ <td>Out</td>
+ </tr>
+ <tr>
+ <td>0</td>
+ <td>0</td>
+ <td>0</td>
+ </tr>
+ <tr>
+ <td>0</td>
+ <td>1</td>
+ <td>0</td>
+ </tr>
+ <tr>
+ <td>1</td>
+ <td>0</td>
+ <td>0</td>
+ </tr>
+ <tr>
+ <td>1</td>
+ <td>1</td>
+ <td>1</td>
+ </tr>
+ </tbody>
+</table>
+</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>
+ <result> = and int 4, 8 <i>; yields {int}:result = 0</i>
+</pre>
+</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="i_or">'<tt>or</tt>' Instruction</a> </div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> <result> = or <ty> <var1>, <var2> <i>; yields {ty}:result</i>
+</pre>
+<h5>Overview:</h5>
+<p>The '<tt>or</tt>' instruction returns the bitwise logical inclusive
+or of its two operands.</p>
+<h5>Arguments:</h5>
+<p>The two arguments to the '<tt>or</tt>' instruction must be <a
+ href="#t_integral">integral</a> values. Both arguments must have
+identical types.</p>
+<h5>Semantics:</h5>
+<p>The truth table used for the '<tt>or</tt>' instruction is:</p>
+<p> </p>
+<div style="align: center">
+<table border="1" cellspacing="0" cellpadding="4">
+ <tbody>
+ <tr>
+ <td>In0</td>
+ <td>In1</td>
+ <td>Out</td>
+ </tr>
+ <tr>
+ <td>0</td>
+ <td>0</td>
+ <td>0</td>
+ </tr>
+ <tr>
+ <td>0</td>
+ <td>1</td>
+ <td>1</td>
+ </tr>
+ <tr>
+ <td>1</td>
+ <td>0</td>
+ <td>1</td>
+ </tr>
+ <tr>
+ <td>1</td>
+ <td>1</td>
+ <td>1</td>
+ </tr>
+ </tbody>
+</table>
+</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>
+ <result> = or int 4, 8 <i>; yields {int}:result = 12</i>
+</pre>
+</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="i_xor">'<tt>xor</tt>'
+Instruction</a> </div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> <result> = xor <ty> <var1>, <var2> <i>; yields {ty}:result</i>
+</pre>
+<h5>Overview:</h5>
+<p>The '<tt>xor</tt>' instruction returns the bitwise logical exclusive
+or of its two operands. The <tt>xor</tt> is used to implement the
+"one's complement" operation, which is the "~" operator in C.</p>
+<h5>Arguments:</h5>
+<p>The two arguments to the '<tt>xor</tt>' instruction must be <a
+ href="#t_integral">integral</a> values. Both arguments must have
+identical types.</p>
+<h5>Semantics:</h5>
+<p>The truth table used for the '<tt>xor</tt>' instruction is:</p>
+<p> </p>
+<div style="align: center">
+<table border="1" cellspacing="0" cellpadding="4">
+ <tbody>
+ <tr>
+ <td>In0</td>
+ <td>In1</td>
+ <td>Out</td>
+ </tr>
+ <tr>
+ <td>0</td>
+ <td>0</td>
+ <td>0</td>
+ </tr>
+ <tr>
+ <td>0</td>
+ <td>1</td>
+ <td>1</td>
+ </tr>
+ <tr>
+ <td>1</td>
+ <td>0</td>
+ <td>1</td>
+ </tr>
+ <tr>
+ <td>1</td>
+ <td>1</td>
+ <td>0</td>
+ </tr>
+ </tbody>
+</table>
+</div>
+<p> </p>
+<h5>Example:</h5>
+<pre> <result> = xor int 4, %var <i>; yields {int}:result = 4 ^ %var</i>
+ <result> = xor int 15, 40 <i>; yields {int}:result = 39</i>
+ <result> = xor int 4, 8 <i>; yields {int}:result = 12</i>
+ <result> = xor int %V, -1 <i>; yields {int}:result = ~%V</i>
+</pre>
+</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="i_shl">'<tt>shl</tt>'
+Instruction</a> </div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> <result> = shl <ty> <var1>, ubyte <var2> <i>; yields {ty}:result</i>
+</pre>
+<h5>Overview:</h5>
+<p>The '<tt>shl</tt>' instruction returns the first operand shifted to
+the left a specified number of bits.</p>
+<h5>Arguments:</h5>
+<p>The first argument to the '<tt>shl</tt>' instruction must be an <a
+ href="#t_integer">integer</a> type. The second argument must be an '<tt>ubyte</tt>'
+type.</p>
+<h5>Semantics:</h5>
+<p>The value produced is <tt>var1</tt> * 2<sup><tt>var2</tt></sup>.</p>
+<h5>Example:</h5>
+<pre> <result> = shl int 4, ubyte %var <i>; yields {int}:result = 4 << %var</i>
+ <result> = shl int 4, ubyte 2 <i>; yields {int}:result = 16</i>
+ <result> = shl int 1, ubyte 10 <i>; yields {int}:result = 1024</i>
+</pre>
+</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="i_shr">'<tt>shr</tt>'
+Instruction</a> </div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> <result> = shr <ty> <var1>, ubyte <var2> <i>; yields {ty}:result</i>
+</pre>
+<h5>Overview:</h5>
+<p>The '<tt>shr</tt>' instruction returns the first operand shifted to
+the right a specified number of bits.</p>
+<h5>Arguments:</h5>
+<p>The first argument to the '<tt>shr</tt>' instruction must be an <a
+ href="#t_integer">integer</a> type. The second argument must be an '<tt>ubyte</tt>'
+type.</p>
+<h5>Semantics:</h5>
+<p>If the first argument is a <a href="#t_signed">signed</a> type, the
+most significant bit is duplicated in the newly free'd bit positions.
+If the first argument is unsigned, zero bits shall fill the empty
+positions.</p>
+<h5>Example:</h5>
+<pre> <result> = shr int 4, ubyte %var <i>; yields {int}:result = 4 >> %var</i>
+ <result> = shr uint 4, ubyte 1 <i>; yields {uint}:result = 2</i>
+ <result> = shr int 4, ubyte 2 <i>; yields {int}:result = 1</i>
+ <result> = shr sbyte 4, ubyte 3 <i>; yields {sbyte}:result = 0</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_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>
+</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>
+<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 '<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>'<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>
+ %array1 = malloc ubyte, uint 4 <i>; yields {ubyte*}:array1</i>
+ %array2 = malloc [12 x ubyte], uint %size <i>; yields {[12 x ubyte]*}:array2</i>
+</pre>
+</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>
+<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>
+<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
+after this instruction executes.</p>
<h5>Example:</h5>
-<pre>
+<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_text">
+<h5>Syntax:</h5>
+<pre> <result> = alloca <type>, uint <NumElements> <i>; yields {type*}:result</i>
+ <result> = alloca <type> <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>
+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>
+<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
+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>
+instructions), the memory is reclaimed.</p>
+<h5>Example:</h5>
+<pre> %ptr = alloca int <i>; yields {int*}:ptr</i>
+ %ptr = alloca int, uint 4 <i>; yields {int*}:ptr</i>
+</pre>
+</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="i_load">'<tt>load</tt>'
+Instruction</a> </div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> <result> = load <ty>* <pointer><br> <result> = volatile load <ty>* <pointer><br></pre>
+<h5>Overview:</h5>
+<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
+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>
+<h5>Semantics:</h5>
+<p>The location of memory pointed to is loaded.</p>
+<h5>Examples:</h5>
+<pre> %ptr = <a href="#i_alloca">alloca</a> int <i>; yields {int*}:ptr</i>
+ <a
+ href="#i_store">store</a> int 3, int* %ptr <i>; yields {void}</i>
+ %val = load int* %ptr <i>; yields {int}:val = int 3</i>
</pre>
+</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="i_store">'<tt>store</tt>'
+Instruction</a> </div>
+<h5>Syntax:</h5>
+<pre> store <ty> <value>, <ty>* <pointer> <i>; yields {void}</i>
+ volatile store <ty> <value>, <ty>* <pointer> <i>; yields {void}</i>
+</pre>
+<h5>Overview:</h5>
+<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>'
+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
+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>
+<h5>Semantics:</h5>
+<p>The contents of memory are updated to contain '<tt><value></tt>'
+at the location specified by the '<tt><pointer></tt>' operand.</p>
+<h5>Example:</h5>
+<pre> %ptr = <a href="#i_alloca">alloca</a> int <i>; yields {int*}:ptr</i>
+ <a
+ href="#i_store">store</a> int 3, int* %ptr <i>; yields {void}</i>
+ %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_text">
+<h5>Syntax:</h5>
+<pre>
+ <result> = getelementptr <ty>* <ptrval>{, <ty> <idx>}*
+</pre>
-<!-- ======================================================================= -->
-</ul><table width="100%" bgcolor="#441188" border=0 cellpadding=4 cellspacing=0><tr><td> </td><td width="100%"> <font color="#EEEEFF" face="Georgia,Palatino"><b>
-<a name="binaryops">Binary Operations
-</b></font></td></tr></table><ul>
+<h5>Overview:</h5>
-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 neccesarily the same type as its operands.<p>
+<p>
+The '<tt>getelementptr</tt>' instruction is used to get the address of a
+subelement of an aggregate data structure.</p>
-There are several different binary operators:<p>
+<h5>Arguments:</h5>
+<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. 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>
-<!-- _______________________________________________________________________ -->
-</ul><a name="i_add"><h4><hr size=0>'<tt>add</tt>' Instruction</h4><ul>
+<p>For example, let's consider a C code fragment and how it gets
+compiled to LLVM:</p>
-<h5>Syntax:</h5>
<pre>
- <result> = add <ty> <var1>, <var2> <i>; yields {ty}:result</i>
+ 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>
-<h5>Overview:</h5>
-The '<tt>add</tt>' instruction returns the sum of its two operands.<p>
+<p>The LLVM code generated by the GCC frontend is:</p>
+
+<pre>
+ %RT = type { sbyte, [10 x [20 x int]], sbyte }
+ %ST = type { int, double, %RT }
-<h5>Arguments:</h5>
-The two arguments to the '<tt>add</tt>' instruction must be either <a href="#t_integral">integral</a> or <a href="#t_floating">floating point</a> values. Both arguments must have identical types.<p>
+ int* "foo"(%ST* %s) {
+ %reg = getelementptr %ST* %s, int 1, uint 2, uint 1, int 5, int 13<br>
+ ret int* %reg
+ }
+</pre>
<h5>Semantics:</h5>
-...<p>
+<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>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 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) {
+ %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>
<h5>Example:</h5>
<pre>
- <result> = add int 4, %var <i>; yields {int}:result = 4 + %var</i>
+ <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 category are the "miscellaneous"
+instructions, which defy better classification.</p>
+</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="i_phi">'<tt>phi</tt>'
+Instruction</a> </div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> <result> = phi <ty> [ <val0>, <label0>], ...<br></pre>
+<h5>Overview:</h5>
+<p>The '<tt>phi</tt>' instruction is used to implement the φ node in
+the SSA graph representing the function.</p>
+<h5>Arguments:</h5>
+<p>The type of the incoming values are specified with the first type
+field. After this, the '<tt>phi</tt>' instruction takes a list of pairs
+as arguments, with one pair for each predecessor basic block of the
+current block. Only values of <a href="#t_firstclass">first class</a>
+type may be used as the value arguments to the PHI node. Only labels
+may be used as the label arguments.</p>
+<p>There must be no non-phi instructions between the start of a basic
+block and the PHI instructions: i.e. PHI instructions must be first in
+a basic block.</p>
+<h5>Semantics:</h5>
+<p>At runtime, the '<tt>phi</tt>' instruction logically takes on the
+value specified by the parameter, depending on which basic block we
+came from in the last <a href="#terminators">terminator</a> instruction.</p>
+<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>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_sub"><h4><hr size=0>'<tt>sub</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_cast">'<tt>cast .. to</tt>' Instruction</a>
+</div>
+
+<div class="doc_text">
<h5>Syntax:</h5>
+
<pre>
- <result> = sub <ty> <var1>, <var2> <i>; yields {ty}:result</i>
+ <result> = cast <ty> <value> to <ty2> <i>; yields ty2</i>
</pre>
<h5>Overview:</h5>
-The '<tt>sub</tt>' instruction returns the difference of its two operands.<p>
-Note that the '<tt>sub</tt>' instruction is the cannonical way the '<tt>neg</tt>' instruction is represented as well.<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>
-The two arguments to the '<tt>sub</tt>' instruction must be either <a href="#t_integral">integral</a> or <a href="#t_floating">floating point</a> values. Both arguments must have identical types.<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>
+
+<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>
- <result> = sub int 4, %var <i>; yields {int}:result = 4 - %var</i>
- <result> = sub int 0, %val <i>; yields {int}:result = -%var</i>
+ %X = cast int 257 to ubyte <i>; yields ubyte:1</i>
+ %Y = cast int 123 to bool <i>; yields bool:true</i>
</pre>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_mul"><h4><hr size=0>'<tt>mul</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_select">'<tt>select</tt>' Instruction</a>
+</div>
+
+<div class="doc_text">
<h5>Syntax:</h5>
+
<pre>
- <result> = mul <ty> <var1>, <var2> <i>; yields {ty}:result</i>
+ <result> = select bool <cond>, <ty> <val1>, <ty> <val2> <i>; yields ty</i>
</pre>
<h5>Overview:</h5>
-The '<tt>mul</tt>' instruction returns the product of its two operands.<p>
+
+<p>
+The '<tt>select</tt>' instruction is used to choose one value based on a
+condition, without branching.
+</p>
+
<h5>Arguments:</h5>
-The two arguments to the '<tt>mul</tt>' instruction must be either <a href="#t_integral">integral</a> or <a href="#t_floating">floating point</a> values. Both arguments must have identical types.<p>
+
+<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>
-There is no signed vs unsigned multiplication. The appropriate action is taken based on the type of the operand. <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>
- <result> = mul int 4, %var <i>; yields {int}:result = 4 * %var</i>
+ %X = select bool true, ubyte 17, ubyte 42 <i>; yields ubyte:17</i>
</pre>
+</div>
-<!-- _______________________________________________________________________ -->
-</ul><a name="i_div"><h4><hr size=0>'<tt>div</tt>' Instruction</h4><ul>
-<h5>Syntax:</h5>
-<pre>
- <result> = div <ty> <var1>, <var2> <i>; yields {ty}:result</i>
-</pre>
-<h5>Overview:</h5>
-The '<tt>div</tt>' instruction returns the quotient of its two operands.<p>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="i_call">'<tt>call</tt>'
+Instruction</a> </div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> <result> = call <ty>* <fnptrval>(<param list>)<br></pre>
+<h5>Overview:</h5>
+<p>The '<tt>call</tt>' instruction represents a simple function call.</p>
<h5>Arguments:</h5>
-The two arguments to the '<tt>div</tt>' instruction must be either <a href="#t_integral">integral</a> or <a href="#t_floating">floating point</a> values. Both arguments must have identical types.<p>
-
+<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>
<h5>Semantics:</h5>
-...<p>
-
+<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>
- <result> = div int 4, %var <i>; yields {int}:result = 4 / %var</i>
-</pre>
-
-
+<pre> %retval = call int %test(int %argc)<br> call int(sbyte*, ...) *%printf(sbyte* %msg, int 12, sbyte 42);<br></pre>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_rem"><h4><hr size=0>'<tt>rem</tt>' Instruction</h4><ul>
-
+<div class="doc_subsubsection"> <a name="i_vanext">'<tt>vanext</tt>'
+Instruction</a> </div>
+<div class="doc_text">
<h5>Syntax:</h5>
-<pre>
- <result> = rem <ty> <var1>, <var2> <i>; yields {ty}:result</i>
-</pre>
-
+<pre> <resultarglist> = vanext <va_list> <arglist>, <argty><br></pre>
<h5>Overview:</h5>
-The '<tt>rem</tt>' instruction returns the remainder from the division of its two operands.<p>
-
+<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>
<h5>Arguments:</h5>
-The two arguments to the '<tt>rem</tt>' instruction must be either <a href="#t_integral">integral</a> or <a href="#t_floating">floating point</a> values. Both arguments must have identical types.<p>
-
+<p>This instruction takes a <tt>valist</tt> value and the type of the
+argument. It returns another <tt>valist</tt>.</p>
<h5>Semantics:</h5>
-TODO: remainder or modulus?<p>
-...<p>
-
+<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>
<h5>Example:</h5>
-<pre>
- <result> = rem int 4, %var <i>; yields {int}:result = 4 % %var</i>
-</pre>
-
-
+<p>See the <a href="#int_varargs">variable argument processing</a>
+section.</p>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_setcc"><h4><hr size=0>'<tt>set<i>cc</i></tt>' Instructions</h4><ul>
-
+<div class="doc_subsubsection"> <a name="i_vaarg">'<tt>vaarg</tt>'
+Instruction</a> </div>
+<div class="doc_text">
<h5>Syntax:</h5>
-<pre>
- <result> = seteq <ty> <var1>, <var2> <i>; yields {bool}:result</i>
- <result> = setne <ty> <var1>, <var2> <i>; yields {bool}:result</i>
- <result> = setlt <ty> <var1>, <var2> <i>; yields {bool}:result</i>
- <result> = setgt <ty> <var1>, <var2> <i>; yields {bool}:result</i>
- <result> = setle <ty> <var1>, <var2> <i>; yields {bool}:result</i>
- <result> = setge <ty> <var1>, <var2> <i>; yields {bool}:result</i>
-</pre>
-
+<pre> <resultval> = vaarg <va_list> <arglist>, <argty><br></pre>
<h5>Overview:</h5>
-The '<tt>set<i>cc</i></tt>' family of instructions returns a boolean value based on a comparison of their two operands.<p>
-
+<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>
<h5>Arguments:</h5>
-The two arguments to the '<tt>set<i>cc</i></tt>' instructions must be of <a href="#t_firstclass">first class</a> or <a href="#t_derived">derived</a> type (it is not possible to compare '<tt>label</tt>'s or '<tt>void</tt>' values). Both arguments must have identical types.<p>
+<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>
+<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
+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>vaarg</tt> is an LLVM instruction instead of an <a
+ href="#intrinsics">intrinsic function</a> because it takes an type as
+an argument.</p>
+<h5>Example:</h5>
+<p>See the <a href="#int_varargs">variable argument processing</a>
+section.</p>
+</div>
-The '<tt>setlt</tt>', '<tt>setgt</tt>', '<tt>setle</tt>', and '<tt>setge</tt>' instructions do not operate on '<tt>bool</tt>' typed arguments.<p>
+<!-- *********************************************************************** -->
+<div class="doc_section"> <a name="intrinsics">Intrinsic Functions</a> </div>
+<!-- *********************************************************************** -->
-<h5>Semantics:</h5>
-The '<tt>seteq</tt>' instruction yields a <tt>true</tt> '<tt>bool</tt>' value if both operands are equal.<br>
-The '<tt>setne</tt>' instruction yields a <tt>true</tt> '<tt>bool</tt>' value if both operands are unequal.<br>
-The '<tt>setlt</tt>' instruction yields a <tt>true</tt> '<tt>bool</tt>' value if the first operand is less than the second operand.<br>
-The '<tt>setgt</tt>' instruction yields a <tt>true</tt> '<tt>bool</tt>' value if the first operand is greater than the second operand.<br>
-The '<tt>setle</tt>' instruction yields a <tt>true</tt> '<tt>bool</tt>' value if the first operand is less than or equal to the second operand.<br>
-The '<tt>setge</tt>' instruction yields a <tt>true</tt> '<tt>bool</tt>' value if the first operand is greater than or equal to the second operand.<p>
+<div class="doc_text">
-<h5>Example:</h5>
-<pre>
- <result> = seteq int 4, 5 <i>; yields {bool}:result = false</i>
- <result> = setne float 4, 5 <i>; yields {bool}:result = true</i>
- <result> = setlt uint 4, 5 <i>; yields {bool}:result = true</i>
- <result> = setgt sbyte 4, 5 <i>; yields {bool}:result = false</i>
- <result> = setle sbyte 4, 5 <i>; yields {bool}:result = true</i>
- <result> = setge sbyte 4, 5 <i>; yields {bool}:result = false</i>
-</pre>
+<p>LLVM supports the notion of an "intrinsic function". These functions have
+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
+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
+function. Additionally, because intrinsic functions are part of the LLVM
+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>
+
+</div>
<!-- ======================================================================= -->
-</ul><table width="100%" bgcolor="#441188" border=0 cellpadding=4 cellspacing=0><tr><td> </td><td width="100%"> <font color="#EEEEFF" face="Georgia,Palatino"><b>
-<a name="bitwiseops">Bitwise Binary Operations
-</b></font></td></tr></table><ul>
+<div class="doc_subsection">
+ <a name="int_varargs">Variable Argument Handling Intrinsics</a>
+</div>
-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. 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>
+<div class="doc_text">
-<!-- _______________________________________________________________________ -->
-</ul><a name="i_and"><h4><hr size=0>'<tt>and</tt>' Instruction</h4><ul>
+<p>Variable argument support is defined in LLVM with the <a
+ href="#i_vanext"><tt>vanext</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>
-<h5>Syntax:</h5>
-<pre>
- <result> = and <ty> <var1>, <var2> <i>; yields {ty}:result</i>
-</pre>
+<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>
-<h5>Overview:</h5>
-The '<tt>and</tt>' instruction returns the bitwise logical and of its two operands.<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>
-<h5>Arguments:</h5>
-The two arguments to the '<tt>and</tt>' instruction must be either <a href="#t_integral">integral</a> or <a href="#t_bool"><tt>bool</tt></a> values. Both arguments must have identical types.<p>
+<pre>
+int %test(int %X, ...) {
+ ; Initialize variable argument processing
+ %ap = call sbyte* %<a href="#i_va_start">llvm.va_start</a>()
+ ; Read a single integer argument
+ %tmp = vaarg sbyte* %ap, int
-<h5>Semantics:</h5>
-...<p>
+ ; Advance to the next argument
+ %ap2 = vanext 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)
-<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>
- <result> = and int 4, 8 <i>; yields {int}:result = 0</i>
+ ; Stop processing of arguments.
+ call void %<a href="#i_va_end">llvm.va_end</a>(sbyte* %ap2)
+ ret int %tmp
+}
</pre>
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_va_start">'<tt>llvm.va_start</tt>' Intrinsic</a>
+</div>
+
+
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> call va_list ()* %llvm.va_start()<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>
+<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
+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_subsubsection">
+ <a name="i_va_end">'<tt>llvm.va_end</tt>' Intrinsic</a>
+</div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre> call void (va_list)* %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>
+or <tt><a href="#i_va_copy">llvm.va_copy</a></tt>.</p>
+<h5>Arguments:</h5>
+<p>The argument is a <tt>va_list</tt> to destroy.</p>
+<h5>Semantics:</h5>
+<p>The '<tt>llvm.va_end</tt>' intrinsic works just like the <tt>va_end</tt>
+macro available in C. In a target-dependent way, it destroys the <tt>va_list</tt>.
+Calls to <a href="#i_va_start"><tt>llvm.va_start</tt></a> and <a
+ href="#i_va_copy"><tt>llvm.va_copy</tt></a> must be matched exactly
+with calls to <tt>llvm.va_end</tt>.</p>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_or"><h4><hr size=0>'<tt>or</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_va_copy">'<tt>llvm.va_copy</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
<h5>Syntax:</h5>
+
<pre>
- <result> = or <ty> <var1>, <var2> <i>; yields {ty}:result</i>
+ call va_list (va_list)* %llvm.va_copy(va_list <destarglist>)
</pre>
<h5>Overview:</h5>
-The '<tt>or</tt>' instruction returns the bitwise logical inclusive or of its two operands.<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>
-The two arguments to the '<tt>or</tt>' instruction must be either <a href="#t_integral">integral</a> or <a href="#t_bool"><tt>bool</tt></a> values. Both arguments must have identical types.<p>
+<p>The argument is the <tt>va_list</tt> to copy.</p>
<h5>Semantics:</h5>
-...<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 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>
-<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>
- <result> = or int 4, 8 <i>; yields {int}:result = 12</i>
-</pre>
+</div>
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="int_gc">Accurate Garbage Collection Intrinsics</a>
+</div>
+
+<div class="doc_text">
+
+<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>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_xor"><h4><hr size=0>'<tt>xor</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_gcroot">'<tt>llvm.gcroot</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
<h5>Syntax:</h5>
+
<pre>
- <result> = xor <ty> <var1>, <var2> <i>; yields {ty}:result</i>
+ call void (<ty>**, <ty2>*)* %llvm.gcroot(<ty>** %ptrloc, <ty2>* %metadata)
</pre>
<h5>Overview:</h5>
-The '<tt>xor</tt>' instruction returns the bitwise logical exclusive or of its two operands.<p>
+
+<p>The '<tt>llvm.gcroot</tt>' intrinsic declares the existance of a GC root to
+the code generator, and allows some metadata to be associated with it.</p>
<h5>Arguments:</h5>
-The two arguments to the '<tt>xor</tt>' instruction must be either <a href="#t_integral">integral</a> or <a href="#t_bool"><tt>bool</tt></a> values. Both arguments must have identical types.<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>
+<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>
-<h5>Example:</h5>
-<pre>
- <result> = xor int 4, %var <i>; yields {int}:result = 4 ^ %var</i>
- <result> = xor int 15, 40 <i>; yields {int}:result = 39</i>
- <result> = xor int 4, 8 <i>; yields {int}:result = 12</i>
-</pre>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_shl"><h4><hr size=0>'<tt>shl</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_gcread">'<tt>llvm.gcread</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
<h5>Syntax:</h5>
+
<pre>
- <result> = shl <ty> <var1>, ubyte <var2> <i>; yields {ty}:result</i>
+ call sbyte* (sbyte**)* %llvm.gcread(sbyte** %Ptr)
</pre>
<h5>Overview:</h5>
-The '<tt>shl</tt>' instruction returns the first operand shifted to the left a specified number of bits.
+
+<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>
-The first argument to the '<tt>shl</tt>' instruction must be an <a href="#t_integral">integral</a> type. The second argument must be an '<tt>ubyte</tt>' type.<p>
+
+<p>The argument is the address to read from, which should be an address
+allocated from the garbage collector.</p>
<h5>Semantics:</h5>
-... 0 bits are shifted into the emptied bit positions...<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>
-<h5>Example:</h5>
-<pre>
- <result> = shl int 4, ubyte %var <i>; yields {int}:result = 4 << %var</i>
- <result> = shl int 4, ubyte 2 <i>; yields {int}:result = 16</i>
- <result> = shl int 1, ubyte 10 <i>; yields {int}:result = 1024</i>
-</pre>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_shr"><h4><hr size=0>'<tt>shr</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_gcwrite">'<tt>llvm.gcwrite</tt>' Intrinsic</a>
+</div>
+<div class="doc_text">
<h5>Syntax:</h5>
+
<pre>
- <result> = shr <ty> <var1>, ubyte <var2> <i>; yields {ty}:result</i>
+ call void (sbyte*, sbyte**)* %llvm.gcwrite(sbyte* %P1, sbyte** %P2)
</pre>
<h5>Overview:</h5>
-The '<tt>shr</tt>' instruction returns the first operand shifted to the right a specified number of bits.
+
+<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>
-The first argument to the '<tt>shr</tt>' instruction must be an <a href="#t_integral">integral</a> type. The second argument must be an '<tt>ubyte</tt>' type.<p>
-<h5>Semantics:</h5>
-... if the first argument is a <a href="#t_signed">signed</a> type, the most significant bit is duplicated in the newly free'd bit positions. If the first argument is unsigned, zeros shall fill the empty positions...<p>
+<p>The first argument is the reference to store, and the second is the heap
+location to store to.</p>
-<h5>Example:</h5>
-<pre>
- <result> = shr int 4, ubyte %var <i>; yields {int}:result = 4 >> %var</i>
- <result> = shr int 4, ubyte 1 <i>; yields {int}:result = 2</i>
- <result> = shr int 4, ubyte 2 <i>; yields {int}:result = 1</i>
- <result> = shr int 4, ubyte 3 <i>; yields {int}:result = 0</i>
-</pre>
+<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>
<!-- ======================================================================= -->
-</ul><table width="100%" bgcolor="#441188" border=0 cellpadding=4 cellspacing=0><tr><td> </td><td width="100%"> <font color="#EEEEFF" face="Georgia,Palatino"><b>
-<a name="memoryops">Memory Access Operations
-</b></font></td></tr></table><ul>
+<div class="doc_subsection">
+ <a name="int_codegen">Code Generator Intrinsics</a>
+</div>
-Accessing memory in SSA form is, well, sticky at best. This section describes how to read and write memory in LLVM.<p>
+<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>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_malloc"><h4><hr size=0>'<tt>malloc</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_returnaddress">'<tt>llvm.returnaddress</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
<h5>Syntax:</h5>
<pre>
- <result> = malloc <type> <i>; yields { type *}:result</i>
- <result> = malloc [<type>], uint <NumElements> <i>; yields {[type] *}:result</i>
+ call void* ()* %llvm.returnaddress(uint <level>)
</pre>
<h5>Overview:</h5>
-The '<tt>malloc</tt>' instruction allocates memory from the system heap and returns a pointer to it.<p>
-<h5>Arguments:</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>
-There are two forms of the '<tt>malloc</tt>' instruction, one for allocating a variable of a fixed type, and one for allocating an array. The array form is used to allocate an array, where the upper bound is not known until run time. If the upper bound is known at compile time, it is recommended that the first form be used with a <a href="#t_array_fixed">sized array type</a>.<p>
+<h5>Arguments:</h5>
-'<tt>type</tt>' may be any type except for a <a href="#t_array_unsized">unsized array type</a>.<p>
+<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>
-Memory is allocated, a pointer is returned.<p>
-<h5>Example:</h5>
-<pre>
- %array = malloc [4 x ubyte ] <i>; yields {[%4 x ubyte]*}:array</i>
+<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>
- %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 [ubyte], uint %size <i>; yields {[ubyte]*}:array2</i>
-</pre>
+<p>
+Note that calling this intrinsic does not prevent function inlining or other
+aggressive transformations, so the value returned may not that of the obvious
+source-language caller.
+</p>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_free"><h4><hr size=0>'<tt>free</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_frameaddress">'<tt>llvm.frameaddress</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
<h5>Syntax:</h5>
<pre>
- free <type> <value> <i>; yields {void}</i>
+ call void* ()* %llvm.frameaddress(uint <level>)
</pre>
-
<h5>Overview:</h5>
-The '<tt>free</tt>' instruction returns memory back to the unused memory heap, to be reallocated in the future.<p>
+<p>
+The '<tt>llvm.frameaddress</tt>' intrinsic returns the target-specific frame
+pointer value for the specified stack frame.
+</p>
<h5>Arguments:</h5>
-'<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>
-
+<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>
-Memory is available for use after this point. The contents of the '<tt>value</tt>' pointer are undefined after this instruction.<p>
+<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>
-<h5>Example:</h5>
-<pre>
- %array = <a href="#i_malloc">malloc</a> [4 x ubyte] <i>; yields {[4 x ubyte]*}:array</i>
- free [4 x ubyte]* %array
-</pre>
+<p>
+Note that calling this intrinsic does not prevent function inlining or other
+aggressive transformations, so the value returned may not that of the obvious
+source-language caller.
+</p>
+</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="int_os">Operating System Intrinsics</a>
+</div>
+<div class="doc_text">
+<p>
+These intrinsics are provided by LLVM to support the implementation of
+operating system level code.
+</p>
+
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_alloca"><h4><hr size=0>'<tt>alloca</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_readport">'<tt>llvm.readport</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
<h5>Syntax:</h5>
<pre>
- <result> = alloca <type> <i>; yields {type*}:result</i>
- <result> = alloca [<type>], uint <NumElements> <i>; yields {[type] *}:result</i>
+ call <integer type> (<integer type>)* %llvm.readport (<integer type> <address>)
</pre>
<h5>Overview:</h5>
-The '<tt>alloca</tt>' instruction allocates memory on the current stack frame of the procedure that is live as long as the method does not return.<p>
+<p>
+The '<tt>llvm.readport</tt>' intrinsic reads data from the specified hardware
+I/O port.
+</p>
<h5>Arguments:</h5>
-There are two forms of the '<tt>alloca</tt>' instruction, one for allocating a variable of a fixed type, and one for allocating an array. The array form is used to allocate an array, where the upper bound is not known until run time. If the upper bound is known at compile time, it is recommended that the first form be used with a <a href="#t_array_fixed">sized array type</a>.<p>
-
-'<tt>type</tt>' may be any type except for a <a href="#t_array_unsized">unsized array type</a>.<p>
-
-Note that a virtual machine may generate more efficient native code for a method if all of the fixed size '<tt>alloca</tt>' instructions live in the first basic block of that method.
+<p>
+The argument to this intrinsic indicates the hardware I/O address from which
+to read the data. The address is in the hardware I/O address namespace (as
+opposed to being a memory location for memory mapped I/O).
+</p>
<h5>Semantics:</h5>
-Memory is allocated, a pointer is returned. '<tt>alloca</tt>'d memory is automatically released when the method returns. The '<tt>alloca</tt>' utility is how variable spills shall be implemented.<p>
-<h5>Example:</h5>
-<pre>
- %ptr = alloca int <i>; yields {int*}:ptr</i>
- %ptr = alloca [int], uint 4 <i>; yields {[int]*}:ptr</i>
-</pre>
+<p>
+The '<tt>llvm.readport</tt>' intrinsic reads data from the hardware I/O port
+specified by <i>address</i> and returns the value. The address and return
+value must be integers, but the size is dependent upon the platform upon which
+the program is code generated. For example, on x86, the address must be an
+unsigned 16 bit value, and the return value must be 8, 16, or 32 bits.
+</p>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_load"><h4><hr size=0>'<tt>load</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_writeport">'<tt>llvm.writeport</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
<h5>Syntax:</h5>
<pre>
- <result> = load <ty>* <pointer> <i>; yields {ty}:result</i>
- <result> = load <ty>* <arrayptr>, uint <idx> <i>; yields {ty}:result</i>
- <result> = load <ty>* <structptr>{, <idx>}* <i>; yields field type</i>
+ call void (<integer type>, <integer type>)* %llvm.writeport (<integer type> <value>, <integer type> <address>)
</pre>
<h5>Overview:</h5>
-The '<tt>load</tt>' instruction is used to read from memory.<p>
-<h5>Arguments:</h5>
+<p>
+The '<tt>llvm.writeport</tt>' intrinsic writes data to the specified hardware
+I/O port.
+</p>
-There are three forms of the '<tt>load</tt>' instruction: one for reading from a general pointer, one for reading from a pointer to an array, and one for reading from a pointer to a structure.<p>
+<h5>Arguments:</h5>
-In the first form, '<tt><ty></tt>' may be any pointer type. If it is a pointer to an array, the first (zeroth) element is read from). In the second form, '<tt><ty></tt>' must be a pointer to an array. No bounds checking is performed on array reads. In the third form, the pointer must point to a (possibly nested) structure. There shall be one ubyte argument for each level of dereferencing involved.<p>
+<p>
+The first argument is the value to write to the I/O port.
+</p>
+<p>
+The second argument indicates the hardware I/O address to which data should be
+written. The address is in the hardware I/O address namespace (as opposed to
+being a memory location for memory mapped I/O).
+</p>
<h5>Semantics:</h5>
-...
-
-<h5>Examples:</h5>
-<pre>
- %ptr = <a href="#i_alloca">alloca</a> int <i>; yields {int*}:ptr</i>
- <a href="#i_store">store</a> int* %ptr, int 3 <i>; yields {void}</i>
- %val = load int* %ptr <i>; yields {int}:val = int 3</i>
-
- %array = <a href="#i_malloc">malloc</a> [4 x ubyte] <i>; yields {[4 x ubyte]*}:array</i>
- <a href="#i_store">store</a> [4 x ubyte]* %array,
- uint 4, ubyte 124
- %val = load [4 x ubyte]* %array, uint 4 <i>; yields {ubyte}:val = ubyte 124</i>
- %val = load {{int, float}}* %stptr, 0, 1 <i>; yields {float}:val</i>
-</pre>
-
+<p>
+The '<tt>llvm.writeport</tt>' intrinsic writes <i>value</i> to the I/O port
+specified by <i>address</i>. The address and value must be integers, but the
+size is dependent upon the platform upon which the program is code generated.
+For example, on x86, the address must be an unsigned 16 bit value, and the
+value written must be 8, 16, or 32 bits in length.
+</p>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_store"><h4><hr size=0>'<tt>store</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_readio">'<tt>llvm.readio</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
<h5>Syntax:</h5>
<pre>
- store <ty>* <pointer>, <ty> <value> <i>; yields {void}</i>
- store <ty>* <arrayptr>, uint <idx>, <ty> <value> <i>; yields {void}</i>
+ call <result> (<ty>*)* %llvm.readio (<ty> * <pointer>)
</pre>
<h5>Overview:</h5>
-The '<tt>store</tt>' instruction is used to write to memory.<p>
+<p>
+The '<tt>llvm.readio</tt>' intrinsic reads data from a memory mapped I/O
+address.
+</p>
<h5>Arguments:</h5>
-There are two forms of the '<tt>store</tt>' instruction: one for writing through a general pointer, and one for writing through a pointer to an array.<p>
-
-In the first form, '<tt><ty></tt>' may be any pointer type. If it is a pointer to an array, the first (zeroth) element is writen to). In the second form, '<tt><ty></tt>' must be a pointer to an array. No bounds checking is performed on array writes.<p>
+<p>
+The argument to this intrinsic is a pointer indicating the memory address from
+which to read the data. The data must be a
+<a href="#t_firstclass">first class</a> type.
+</p>
<h5>Semantics:</h5>
-...
-
-<h5>Example:</h5>
-<pre>
- %ptr = <a href="#i_alloca">alloca</a> int <i>; yields {int*}:ptr</i>
- store int* %ptr, int 3 <i>; yields {void}</i>
- %val = <a href="#i_load">load</a> int* %ptr <i>; yields {int}:val = int 3</i>
-
- %array = <a href="#i_malloc">malloc</a> [4 x ubyte] <i>; yields {[4 x ubyte]*}:array</i>
- store [4 x ubyte]* %array,
- uint 4, ubyte 124
- %val = <a href="#i_load">load</a> [4 x ubyte]* %array, uint 4 <i>; yields {ubyte}:val = ubyte 124</i>
-</pre>
-
-
+<p>
+The '<tt>llvm.readio</tt>' intrinsic reads data from a memory mapped I/O
+location specified by <i>pointer</i> and returns the value. The argument must
+be a pointer, and the return value must be a
+<a href="#t_firstclass">first class</a> type. However, certain architectures
+may not support I/O on all first class types. For example, 32 bit processors
+may only support I/O on data types that are 32 bits or less.
+</p>
+
+<p>
+This intrinsic enforces an in-order memory model for llvm.readio and
+llvm.writeio calls on machines that use dynamic scheduling. Dynamically
+scheduled processors may execute loads and stores out of order, re-ordering at
+run time accesses to memory mapped I/O registers. Using these intrinsics
+ensures that accesses to memory mapped I/O registers occur in program order.
+</p>
+
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_getfieldptr"><h4><hr size=0>'<tt>getfieldptr</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_writeio">'<tt>llvm.writeio</tt>' Intrinsic</a>
+</div>
+
+<div class="doc_text">
<h5>Syntax:</h5>
<pre>
-
+ call void (<ty1>, <ty2>*)* %llvm.writeio (<ty1> <value>, <ty2> * <pointer>)
</pre>
<h5>Overview:</h5>
-getfield takes a structure pointer, and an unsigned byte. It returns a pointer to the specified element, of the correct type. At the implementation level, this would be compiled down to an addition of a constant int.
+<p>
+The '<tt>llvm.writeio</tt>' intrinsic writes data to the specified memory
+mapped I/O address.
+</p>
<h5>Arguments:</h5>
+<p>
+The first argument is the value to write to the memory mapped I/O location.
+The second argument is a pointer indicating the memory address to which the
+data should be written.
+</p>
<h5>Semantics:</h5>
+<p>
+The '<tt>llvm.writeio</tt>' intrinsic writes <i>value</i> to the memory mapped
+I/O address specified by <i>pointer</i>. The value must be a
+<a href="#t_firstclass">first class</a> type. However, certain architectures
+may not support I/O on all first class types. For example, 32 bit processors
+may only support I/O on data types that are 32 bits or less.
+</p>
-<h5>Example:</h5>
-<pre>
-
-</pre>
+<p>
+This intrinsic enforces an in-order memory model for llvm.readio and
+llvm.writeio calls on machines that use dynamic scheduling. Dynamically
+scheduled processors may execute loads and stores out of order, re-ordering at
+run time accesses to memory mapped I/O registers. Using these intrinsics
+ensures that accesses to memory mapped I/O registers occur in program order.
+</p>
+</div>
<!-- ======================================================================= -->
-</ul><table width="100%" bgcolor="#441188" border=0 cellpadding=4 cellspacing=0><tr><td> </td><td width="100%"> <font color="#EEEEFF" face="Georgia,Palatino"><b>
-<a name="otherops">Other Operations
-</b></font></td></tr></table><ul>
+<div class="doc_subsection">
+ <a name="int_libc">Standard C Library Intrinsics</a>
+</div>
-The instructions in this catagory are the "miscellaneous" functions, that defy better classification.<p>
+<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>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_call"><h4><hr size=0>'<tt>call</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_memcpy">'<tt>llvm.memcpy</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>)
</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>
-<h5>Arguments:</h5>
-
-
-<h5>Semantics:</h5>
-
-
-<h5>Example:</h5>
-<pre>
- %retval = call int %test(int %argc)
-</pre>
-
+<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>
-<!-- _______________________________________________________________________ --></ul><a name="i_icall"><h3><hr size=0>'<tt>icall</tt>' Instruction</h3><ul>
+<h5>Arguments:</h5>
-Indirect calls are desperately needed to implement virtual function tables (C++, java) and function pointers (C, C++, ...).<p>
+<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>
-A new instruction <tt>icall</tt> or similar should be introduced to represent an indirect call.<p>
+<p>
+If the call to this intrinisic has an alignment value that is not 0 or 1, then
+the caller guarantees that the size of the copy is a multiple of the alignment
+and that both the source and destination pointers are aligned to that boundary.
+</p>
-Example:
-<pre>
- %retval = icall int %funcptr(int %arg1) <i>; yields {int}:%retval</i>
-</pre>
+<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>
+</div>
<!-- _______________________________________________________________________ -->
-</ul><a name="i_phi"><h4><hr size=0>'<tt>phi</tt>' Instruction</h4><ul>
+<div class="doc_subsubsection">
+ <a name="i_memmove">'<tt>llvm.memmove</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>)
</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>
-<h5>Arguments:</h5>
-
-
-<h5>Semantics:</h5>
-
-
-<h5>Example:</h5>
-<pre>
-</pre>
-
+<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>
-<!-- ======================================================================= -->
-</ul><table width="100%" bgcolor="#441188" border=0 cellpadding=4 cellspacing=0><tr><td> </td><td width="100%"> <font color="#EEEEFF" face="Georgia,Palatino"><b>
-<a name="builtinfunc">Builtin Functions
-</b></font></td></tr></table><ul>
+<h5>Arguments:</h5>
-<b>Notice:</b> Preliminary idea!<p>
+<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>
-Builtin functions are very similar to normal functions, except they are defined by the implementation. Invocations of these functions are very similar to method invocations, except that the syntax is a little less verbose.<p>
+<p>
+If the call to this intrinisic has an alignment value that is not 0 or 1, then
+the caller guarantees that the size of the copy is a multiple of the alignment
+and that both the source and destination pointers are aligned to that boundary.
+</p>
-Builtin functions are useful to implement semi-high level ideas like a '<tt>min</tt>' or '<tt>max</tt>' operation that can have important properties when doing program analysis. For example:
+<h5>Semantics:</h5>
-<ul>
-<li>Some optimizations can make use of identities defined over the functions,
- for example a parrallelizing compiler could make use of '<tt>min</tt>'
- identities to parrellelize a loop.
-<li>Builtin functions would have polymorphic types, where normal method calls
- may only have a single type.
-<li>Builtin functions would be known to not have side effects, simplifying
- analysis over straight method calls.
-<li>The syntax of the builtin are cleaner than the syntax of the
- '<a href="#i_call"><tt>call</tt></a>' instruction (very minor point).
-</ul>
+<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>
+</div>
-Because these invocations are explicit in the representation, the runtime can choose to implement these builtin functions any way that they want, including:
-<ul>
-<li>Inlining the code directly into the invocation
-<li>Implementing the functions in some sort of Runtime class, convert invocation
- to a standard method call.
-<li>Implementing the functions in some sort of Runtime class, and perform
- standard inlining optimizations on it.
-</ul>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_memset">'<tt>llvm.memset</tt>' Intrinsic</a>
+</div>
-Note that these builtins do not use quoted identifiers: the name of the builtin effectively becomes an identifier in the language.<p>
+<div class="doc_text">
-Example:
+<h5>Syntax:</h5>
<pre>
- ; Example of a normal method call
- %maximum = call int %maximum(int %arg1, int %arg2) <i>; yields {int}:%maximum</i>
-
- ; Examples of potential builtin functions
- %max = max(int %arg1, int %arg2) <i>; yields {int}:%max</i>
- %min = min(int %arg1, int %arg2) <i>; yields {int}:%min</i>
- %sin = sin(double %arg) <i>; yields {double}:%sin</i>
- %cos = cos(double %arg) <i>; yields {double}:%cos</i>
-
- ; Show that builtin's are polymorphic, like instructions
- %max = max(float %arg1, float %arg2) <i>; yields {float}:%max</i>
- %cos = cos(float %arg) <i>; yields {float}:%cos</i>
+ call void (sbyte*, ubyte, uint, uint)* %llvm.memset(sbyte* <dest>, ubyte <val>,
+ uint <len>, uint <align>)
</pre>
-The '<tt>maximum</tt>' vs '<tt>max</tt>' example illustrates the difference in calling semantics between a '<a href="#i_call"><tt>call</tt></a>' instruction and a builtin function invocation. Notice that the '<tt>maximum</tt>' example assumes that the method is defined local to the caller.<p>
-
-
-
-
-<!-- *********************************************************************** -->
-</ul><table width="100%" bgcolor="#330077" border=0 cellpadding=4 cellspacing=0><tr><td align=center><font color="#EEEEFF" size=+2 face="Georgia,Palatino"><b>
-<a name="todo">TODO List
-</b></font></td></tr></table><ul>
-<!-- *********************************************************************** -->
-
-This list of random topics includes things that will <b>need</b> to be addressed before the llvm may be used to implement a java like langauge. Right now, it is pretty much useless for any language, given to unavailable of structure types<p>
-
-<!-- _______________________________________________________________________ -->
-</ul><a name="synchronization"><h3><hr size=0>Synchronization Instructions</h3><ul>
-
-We will need some type of synchronization instructions to be able to implement stuff in Java well. The way I currently envision doing this is to introduce a '<tt>lock</tt>' type, and then add two (builtin or instructions) operations to lock and unlock the lock.<p>
-
+<h5>Overview:</h5>
-<!-- *********************************************************************** -->
-</ul><table width="100%" bgcolor="#330077" border=0 cellpadding=4 cellspacing=0><tr><td align=center><font color="#EEEEFF" size=+2 face="Georgia,Palatino"><b>
-<a name="extensions">Possible Extensions
-</b></font></td></tr></table><ul>
-<!-- *********************************************************************** -->
+<p>
+The '<tt>llvm.memset</tt>' intrinsic fills a block of memory with a particular
+byte value.
+</p>
-These extensions are distinct from the TODO list, as they are mostly "interesting" ideas that could be implemented in the future by someone so motivated. They are not directly required to get <a href="#rw_java">Java</a> like languages working.<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>
-<!-- _______________________________________________________________________ -->
-</ul><a name="i_tailcall"><h3><hr size=0>'<tt>tailcall</tt>' Instruction</h3><ul>
+<h5>Arguments:</h5>
-This could be useful. Who knows. '.net' does it, but is the optimization really worth the extra hassle? Using strong typing would make this trivial to implement and a runtime could always callback to using downconverting this to a normal '<a href="#i_call"><tt>call</tt></a>' instruction.<p>
+<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 (arbitrarily sized) 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 size of the copy is a multiple of the alignment
+and that the destination pointer is aligned to that boundary.
+</p>
-<!-- _______________________________________________________________________ -->
-</ul><a name="globalvars"><h3><hr size=0>Global Variables</h3><ul>
+<h5>Semantics:</h5>
-In order to represent programs written in languages like C, we need to be able to support variables at the module (global) scope. Perhaps they should be written outside of the module definition even. Maybe global functions should be handled like this as well.<p>
+<p>
+The '<tt>llvm.memset</tt>' intrinsic fills "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>
<!-- _______________________________________________________________________ -->
-</ul><a name="explicitparrellelism"><h3><hr size=0>Explicit Parrellelism</h3><ul>
-
-With the rise of massively parrellel architectures (like <a href="#rw_ia64">the IA64 architecture</a>, multithreaded CPU cores, and SIMD data sets) it is becoming increasingly more important to extract all of the ILP from a code stream possible. It would be interesting to research encoding methods that can explicitly represent this. One straightforward way to do this would be to introduce a "stop" instruction that is equilivent to the IA64 stop bit.<p>
-
-
-
-<!-- *********************************************************************** -->
-</ul><table width="100%" bgcolor="#330077" border=0 cellpadding=4 cellspacing=0><tr><td align=center><font color="#EEEEFF" size=+2 face="Georgia,Palatino"><b>
-<a name="related">Related Work
-</b></font></td></tr></table><ul>
-<!-- *********************************************************************** -->
-
+<div class="doc_subsubsection">
+ <a name="i_isunordered">'<tt>llvm.isunordered</tt>' Intrinsic</a>
+</div>
-Codesigned virtual machines.<p>
+<div class="doc_text">
-<dl>
-<a name="rw_safetsa">
-<dt>SafeTSA
-<DD>Description here<p>
-
-<a name="rw_java">
-<dt><a href="http://www.javasoft.com">Java</a>
-<DD>Desciption here<p>
+<h5>Syntax:</h5>
+<pre>
+ call bool (<float or double>, <float or double>)* %llvm.isunordered(<float or double> Val1,
+ <float or double> Val2)
+</pre>
-<a name="rw_net">
-<dt><a href="http://www.microsoft.com/net">Microsoft .net</a>
-<DD>Desciption here<p>
+<h5>Overview:</h5>
-<a name="rw_gccrtl">
-<dt><a href="http://www.math.umn.edu/systems_guide/gcc-2.95.1/gcc_15.html">GNU RTL Intermediate Representation</a>
-<DD>Desciption here<p>
+<p>
+The '<tt>llvm.isunordered</tt>' intrinsic returns true if either or both of the
+specified floating point values is a NAN.
+</p>
-<a name="rw_ia64">
-<dt><a href="http://developer.intel.com/design/ia-64/index.htm">IA64 Architecture & Instruction Set</a>
-<DD>Desciption here<p>
+<h5>Arguments:</h5>
-<a name="rw_mmix">
-<dt><a href="http://www-cs-faculty.stanford.edu/~knuth/mmix-news.html">MMIX Instruction Set</a>
-<DD>Desciption here<p>
+<p>
+The arguments are floating point numbers of the same type.
+</p>
-<a name="rw_stroustrup">
-<dt><a href="http://www.research.att.com/~bs/devXinterview.html">"Interview With Bjarne Stroustrup"</a>
-<DD>This interview influenced the design and thought process behind LLVM in several ways, most notably the way that derived types are written in text format. See the question that starts with "you defined the C declarator syntax as an experiment that failed".<p>
-</dl>
+<h5>Semantics:</h5>
-<!-- _______________________________________________________________________ -->
-</ul><a name="rw_vectorization"><h3><hr size=0>Vectorized Architectures</h3><ul>
+<p>
+If either or both of the arguments is a SNAN or QNAN, it returns true, otherwise
+false.
+</p>
+</div>
-<dl>
-<a name="rw_intel_simd">
-<dt>Intel MMX, MMX2, SSE, SSE2
-<DD>Description here<p>
-<a name="rw_amd_simd">
-<dt><a href="http://www.nondot.org/~sabre/os/H1ChipFeatures/3DNow!TechnologyManual.pdf">AMD 3Dnow!, 3Dnow! 2</a>
-<DD>Desciption here<p>
-<a name="rw_sun_simd">
-<dt><a href="http://www.nondot.org/~sabre/os/H1ChipFeatures/VISInstructionSetUsersManual.pdf">Sun VIS ISA</a>
-<DD>Desciption here<p>
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="int_debugger">Debugger Intrinsics</a>
+</div>
-</dl>
+<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.
+</p>
+</div>
-more...
<!-- *********************************************************************** -->
-</ul>
-<!-- *********************************************************************** -->
-
-
<hr>
-<font size=-1>
-<address><a href="mailto:sabre@nondot.org">Chris Lattner</a></address>
-<!-- Created: Tue Jan 23 15:19:28 CST 2001 -->
-<!-- hhmts start -->
-Last modified: Mon Jun 11 09:30:45 CDT 2001
-<!-- hhmts end -->
-</font>
-</body></html>
+<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.cs.uiuc.edu">The LLVM Compiler Infrastructure</a><br>
+ Last modified: $Date$
+</address>
+</body>
+</html>
projects / oota-llvm.git / blobdiff