forked from OSchip/llvm-project
3963 lines
143 KiB
HTML
3963 lines
143 KiB
HTML
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
|
|
"http://www.w3.org/TR/html4/strict.dtd">
|
|
<html>
|
|
<head>
|
|
<title>LLVM Assembly Language Reference Manual</title>
|
|
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
|
|
<meta name="author" content="Chris Lattner">
|
|
<meta name="description"
|
|
content="LLVM Assembly Language Reference Manual.">
|
|
<link rel="stylesheet" href="llvm.css" type="text/css">
|
|
</head>
|
|
|
|
<body>
|
|
|
|
<div class="doc_title"> LLVM Language Reference Manual </div>
|
|
<ol>
|
|
<li><a href="#abstract">Abstract</a></li>
|
|
<li><a href="#introduction">Introduction</a></li>
|
|
<li><a href="#identifiers">Identifiers</a></li>
|
|
<li><a href="#highlevel">High Level Structure</a>
|
|
<ol>
|
|
<li><a href="#modulestructure">Module Structure</a></li>
|
|
<li><a href="#linkage">Linkage Types</a></li>
|
|
<li><a href="#callingconv">Calling Conventions</a></li>
|
|
<li><a href="#globalvars">Global Variables</a></li>
|
|
<li><a href="#functionstructure">Functions</a></li>
|
|
<li><a href="#moduleasm">Module-Level Inline Assembly</a></li>
|
|
</ol>
|
|
</li>
|
|
<li><a href="#typesystem">Type System</a>
|
|
<ol>
|
|
<li><a href="#t_primitive">Primitive Types</a>
|
|
<ol>
|
|
<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>
|
|
<li><a href="#t_function">Function Type</a></li>
|
|
<li><a href="#t_pointer">Pointer Type</a></li>
|
|
<li><a href="#t_struct">Structure Type</a></li>
|
|
<li><a href="#t_packed">Packed Type</a></li>
|
|
<li><a href="#t_opaque">Opaque Type</a></li>
|
|
</ol>
|
|
</li>
|
|
</ol>
|
|
</li>
|
|
<li><a href="#constants">Constants</a>
|
|
<ol>
|
|
<li><a href="#simpleconstants">Simple Constants</a>
|
|
<li><a href="#aggregateconstants">Aggregate Constants</a>
|
|
<li><a href="#globalconstants">Global Variable and Function Addresses</a>
|
|
<li><a href="#undefvalues">Undefined Values</a>
|
|
<li><a href="#constantexprs">Constant Expressions</a>
|
|
</ol>
|
|
</li>
|
|
<li><a href="#othervalues">Other Values</a>
|
|
<ol>
|
|
<li><a href="#inlineasm">Inline Assembler Expressions</a>
|
|
</ol>
|
|
</li>
|
|
<li><a href="#instref">Instruction Reference</a>
|
|
<ol>
|
|
<li><a href="#terminators">Terminator Instructions</a>
|
|
<ol>
|
|
<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>
|
|
<li><a href="#i_unreachable">'<tt>unreachable</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>
|
|
<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_udiv">'<tt>udiv</tt>' Instruction</a></li>
|
|
<li><a href="#i_sdiv">'<tt>sdiv</tt>' Instruction</a></li>
|
|
<li><a href="#i_fdiv">'<tt>fdiv</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>
|
|
<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="#vectorops">Vector Operations</a>
|
|
<ol>
|
|
<li><a href="#i_extractelement">'<tt>extractelement</tt>' Instruction</a></li>
|
|
<li><a href="#i_insertelement">'<tt>insertelement</tt>' Instruction</a></li>
|
|
<li><a href="#i_shufflevector">'<tt>shufflevector</tt>' Instruction</a></li>
|
|
<li><a href="#i_vsetint">'<tt>vsetint</tt>' Instruction</a></li>
|
|
<li><a href="#i_vsetfp">'<tt>vsetfp</tt>' Instruction</a></li>
|
|
<li><a href="#i_vselect">'<tt>vselect</tt>' Instruction</a></li>
|
|
</ol>
|
|
</li>
|
|
<li><a href="#memoryops">Memory Access and Addressing Operations</a>
|
|
<ol>
|
|
<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_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_va_arg">'<tt>va_arg</tt>' Instruction</a></li>
|
|
</ol>
|
|
</li>
|
|
</ol>
|
|
</li>
|
|
<li><a href="#intrinsics">Intrinsic Functions</a>
|
|
<ol>
|
|
<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>
|
|
<li><a href="#i_stacksave">'<tt>llvm.stacksave</tt>' Intrinsic</a></li>
|
|
<li><a href="#i_stackrestore">'<tt>llvm.stackrestore</tt>' Intrinsic</a></li>
|
|
<li><a href="#i_prefetch">'<tt>llvm.prefetch</tt>' Intrinsic</a></li>
|
|
<li><a href="#i_pcmarker">'<tt>llvm.pcmarker</tt>' Intrinsic</a></li>
|
|
<li><a href="#i_readcyclecounter"><tt>llvm.readcyclecounter</tt>' Intrinsic</a></li>
|
|
</ol>
|
|
</li>
|
|
<li><a href="#int_libc">Standard C Library Intrinsics</a>
|
|
<ol>
|
|
<li><a href="#i_memcpy">'<tt>llvm.memcpy.*</tt>' Intrinsic</a></li>
|
|
<li><a href="#i_memmove">'<tt>llvm.memmove.*</tt>' Intrinsic</a></li>
|
|
<li><a href="#i_memset">'<tt>llvm.memset.*</tt>' Intrinsic</a></li>
|
|
<li><a href="#i_isunordered">'<tt>llvm.isunordered.*</tt>' Intrinsic</a></li>
|
|
<li><a href="#i_sqrt">'<tt>llvm.sqrt.*</tt>' Intrinsic</a></li>
|
|
<li><a href="#i_powi">'<tt>llvm.powi.*</tt>' Intrinsic</a></li>
|
|
</ol>
|
|
</li>
|
|
<li><a href="#int_manip">Bit Manipulation Intrinsics</a>
|
|
<ol>
|
|
<li><a href="#i_bswap">'<tt>llvm.bswap.*</tt>' Intrinsics</a></li>
|
|
<li><a href="#int_ctpop">'<tt>llvm.ctpop.*</tt>' Intrinsic </a></li>
|
|
<li><a href="#int_ctlz">'<tt>llvm.ctlz.*</tt>' Intrinsic </a></li>
|
|
<li><a href="#int_cttz">'<tt>llvm.cttz.*</tt>' Intrinsic </a></li>
|
|
</ol>
|
|
</li>
|
|
<li><a href="#int_debugger">Debugger intrinsics</a></li>
|
|
</ol>
|
|
</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>
|
|
|
|
<!-- *********************************************************************** -->
|
|
<div class="doc_section"> <a name="abstract">Abstract </a></div>
|
|
<!-- *********************************************************************** -->
|
|
|
|
<div class="doc_text">
|
|
<p>This document is a reference manual for the LLVM assembly language.
|
|
LLVM is an SSA based representation that provides type safety,
|
|
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>
|
|
|
|
<!-- *********************************************************************** -->
|
|
<div class="doc_section"> <a name="introduction">Introduction</a> </div>
|
|
<!-- *********************************************************************** -->
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>The LLVM code representation is designed to be used in three
|
|
different forms: as an in-memory compiler IR, as an on-disk bytecode
|
|
representation (suitable for fast loading by a Just-In-Time compiler),
|
|
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 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>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="wellformed">Well-Formedness</a> </div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>It is important to note that this document describes 'well formed'
|
|
LLVM assembly language. There is a difference between what the parser
|
|
accepts and what is considered 'well formed'. For example, the
|
|
following instruction is syntactically okay, but not well formed:</p>
|
|
|
|
<pre>
|
|
%x = <a href="#i_add">add</a> int 1, %x
|
|
</pre>
|
|
|
|
<p>...because the definition of <tt>%x</tt> does not dominate all of
|
|
its uses. The LLVM infrastructure provides a verification pass that may
|
|
be used to verify that an LLVM module is well formed. This pass is
|
|
automatically run by the parser after parsing input assembly and by
|
|
the optimizer before it outputs bytecode. The violations pointed out
|
|
by the verifier pass indicate bugs in transformation passes or input to
|
|
the parser.</p>
|
|
|
|
<!-- Describe the typesetting conventions here. --> </div>
|
|
|
|
<!-- *********************************************************************** -->
|
|
<div class="doc_section"> <a name="identifiers">Identifiers</a> </div>
|
|
<!-- *********************************************************************** -->
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>LLVM uses three different forms of identifiers, for different
|
|
purposes:</p>
|
|
|
|
<ol>
|
|
<li>Named values are represented as a string of characters with a '%' prefix.
|
|
For example, %foo, %DivisionByZero, %a.really.long.identifier. The actual
|
|
regular expression used is '<tt>%[a-zA-Z$._][a-zA-Z$._0-9]*</tt>'.
|
|
Identifiers which require other characters in their names can be surrounded
|
|
with quotes. In this way, anything except a <tt>"</tt> character can be used
|
|
in a name.</li>
|
|
|
|
<li>Unnamed values are represented as an unsigned numeric value with a '%'
|
|
prefix. For example, %12, %2, %44.</li>
|
|
|
|
<li>Constants, which are described in a <a href="#constants">section about
|
|
constants</a>, below.</li>
|
|
</ol>
|
|
|
|
<p>LLVM requires 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
|
|
</pre>
|
|
|
|
<p>After strength reduction:</p>
|
|
|
|
<pre>
|
|
%result = <a href="#i_shl">shl</a> uint %X, ubyte 3
|
|
</pre>
|
|
|
|
<p>And the hard way:</p>
|
|
|
|
<pre>
|
|
<a href="#i_add">add</a> uint %X, %X <i>; yields {uint}:%0</i>
|
|
<a href="#i_add">add</a> uint %0, %0 <i>; yields {uint}:%1</i>
|
|
%result = <a href="#i_add">add</a> uint %1, %1
|
|
</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 shows a convention that we follow in this document. When
|
|
demonstrating instructions, we will follow an instruction with a comment that
|
|
defines the type and name of value produced. Comments are shown in italic
|
|
text.</p>
|
|
|
|
</div>
|
|
|
|
<!-- *********************************************************************** -->
|
|
<div class="doc_section"> <a name="highlevel">High Level Structure</a> </div>
|
|
<!-- *********************************************************************** -->
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection"> <a name="modulestructure">Module Structure</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>LLVM programs are composed of "Module"s, each of which is a
|
|
translation unit of the input programs. Each module consists of
|
|
functions, global variables, and symbol table entries. Modules may be
|
|
combined together with the LLVM linker, which merges function (and
|
|
global variable) definitions, resolves forward declarations, and merges
|
|
symbol table entries. Here is an example of the "hello world" module:</p>
|
|
|
|
<pre><i>; Declare the string constant as a global constant...</i>
|
|
<a href="#identifiers">%.LC0</a> = <a href="#linkage_internal">internal</a> <a
|
|
href="#globalvars">constant</a> <a href="#t_array">[13 x sbyte]</a> c"hello world\0A\00" <i>; [13 x sbyte]*</i>
|
|
|
|
<i>; External declaration of the puts function</i>
|
|
<a href="#functionstructure">declare</a> int %puts(sbyte*) <i>; int(sbyte*)* </i>
|
|
|
|
<i>; Global variable / Function body section separator</i>
|
|
implementation
|
|
|
|
<i>; Definition of main function</i>
|
|
int %main() { <i>; int()* </i>
|
|
<i>; Convert [13x sbyte]* to sbyte *...</i>
|
|
%cast210 = <a
|
|
href="#i_getelementptr">getelementptr</a> [13 x sbyte]* %.LC0, long 0, long 0 <i>; sbyte*</i>
|
|
|
|
<i>; Call puts function to write out the string to stdout...</i>
|
|
<a
|
|
href="#i_call">call</a> int %puts(sbyte* %cast210) <i>; int</i>
|
|
<a
|
|
href="#i_ret">ret</a> int 0<br>}<br></pre>
|
|
|
|
<p>This example is made up of a <a href="#globalvars">global variable</a>
|
|
named "<tt>.LC0</tt>", an external declaration of the "<tt>puts</tt>"
|
|
function, and a <a href="#functionstructure">function definition</a>
|
|
for "<tt>main</tt>".</p>
|
|
|
|
<p>In general, a module is made up of a list of global values,
|
|
where both functions and global variables are global values. Global values are
|
|
represented by a pointer to a memory location (in this case, a pointer to an
|
|
array of char, and a pointer to a function), and have one of the following <a
|
|
href="#linkage">linkage types</a>.</p>
|
|
|
|
<p>Due to a limitation in the current LLVM assembly parser (it is limited by
|
|
one-token lookahead), modules are split into two pieces by the "implementation"
|
|
keyword. Global variable prototypes and definitions must occur before the
|
|
keyword, and function definitions must occur after it. Function prototypes may
|
|
occur either before or after it. In the future, the implementation keyword may
|
|
become a noop, if the parser gets smarter.</p>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="linkage">Linkage Types</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>
|
|
All Global Variables and Functions have one of the following types of linkage:
|
|
</p>
|
|
|
|
<dl>
|
|
|
|
<dt><tt><b><a name="linkage_internal">internal</a></b></tt> </dt>
|
|
|
|
<dd>Global values with internal linkage are only directly accessible by
|
|
objects in the current module. In particular, linking code into a module with
|
|
an internal global value may cause the internal to be renamed as necessary to
|
|
avoid collisions. Because the symbol is internal to the module, all
|
|
references can be updated. This corresponds to the notion of the
|
|
'<tt>static</tt>' keyword in C, or the idea of "anonymous namespaces" in C++.
|
|
</dd>
|
|
|
|
<dt><tt><b><a name="linkage_linkonce">linkonce</a></b></tt>: </dt>
|
|
|
|
<dd>"<tt>linkonce</tt>" linkage is similar to <tt>internal</tt> linkage, with
|
|
the twist that linking together two modules defining the same
|
|
<tt>linkonce</tt> globals will cause one of the globals to be discarded. This
|
|
is typically used to implement inline functions. Unreferenced
|
|
<tt>linkonce</tt> globals are allowed to be discarded.
|
|
</dd>
|
|
|
|
<dt><tt><b><a name="linkage_weak">weak</a></b></tt>: </dt>
|
|
|
|
<dd>"<tt>weak</tt>" linkage is exactly the same as <tt>linkonce</tt> linkage,
|
|
except that unreferenced <tt>weak</tt> globals may not be discarded. This is
|
|
used to implement constructs in C such as "<tt>int X;</tt>" at global scope.
|
|
</dd>
|
|
|
|
<dt><tt><b><a name="linkage_appending">appending</a></b></tt>: </dt>
|
|
|
|
<dd>"<tt>appending</tt>" linkage may only be applied to global variables of
|
|
pointer to array type. When two global variables with appending linkage are
|
|
linked together, the two global arrays are appended together. This is the
|
|
LLVM, typesafe, equivalent of having the system linker append together
|
|
"sections" with identical names when .o files are linked.
|
|
</dd>
|
|
|
|
<dt><tt><b><a name="linkage_external">externally visible</a></b></tt>:</dt>
|
|
|
|
<dd>If none of the above identifiers are used, the global is externally
|
|
visible, meaning that it participates in linkage and can be used to resolve
|
|
external symbol references.
|
|
</dd>
|
|
|
|
<dt><tt><b><a name="linkage_externweak">extern_weak</a></b></tt>: </dt>
|
|
|
|
<dd>"<tt>extern_weak</tt>" TBD
|
|
</dd>
|
|
|
|
<p>
|
|
The next two types of linkage are targeted for Microsoft Windows platform
|
|
only. They are designed to support importing (exporting) symbols from (to)
|
|
DLLs.
|
|
</p>
|
|
|
|
<dt><tt><b><a name="linkage_dllimport">dllimport</a></b></tt>: </dt>
|
|
|
|
<dd>"<tt>dllimport</tt>" linkage causes the compiler to reference a function
|
|
or variable via a global pointer to a pointer that is set up by the DLL
|
|
exporting the symbol. On Microsoft Windows targets, the pointer name is
|
|
formed by combining <code>_imp__</code> and the function or variable name.
|
|
</dd>
|
|
|
|
<dt><tt><b><a name="linkage_dllexport">dllexport</a></b></tt>: </dt>
|
|
|
|
<dd>"<tt>dllexport</tt>" linkage causes the compiler to provide a global
|
|
pointer to a pointer in a DLL, so that it can be referenced with the
|
|
<tt>dllimport</tt> attribute. On Microsoft Windows targets, the pointer
|
|
name is formed by combining <code>_imp__</code> and the function or variable
|
|
name.
|
|
</dd>
|
|
|
|
</dl>
|
|
|
|
<p><a name="linkage_external">For example, since the "<tt>.LC0</tt>"
|
|
variable is defined to be internal, if another module defined a "<tt>.LC0</tt>"
|
|
variable and was linked with this one, one of the two would be renamed,
|
|
preventing a collision. Since "<tt>main</tt>" and "<tt>puts</tt>" are
|
|
external (i.e., lacking any linkage declarations), they are accessible
|
|
outside of the current module. It is illegal for a function <i>declaration</i>
|
|
to have any linkage type other than "externally visible".</a></p>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="callingconv">Calling Conventions</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>LLVM <a href="#functionstructure">functions</a>, <a href="#i_call">calls</a>
|
|
and <a href="#i_invoke">invokes</a> can all have an optional calling convention
|
|
specified for the call. The calling convention of any pair of dynamic
|
|
caller/callee must match, or the behavior of the program is undefined. The
|
|
following calling conventions are supported by LLVM, and more may be added in
|
|
the future:</p>
|
|
|
|
<dl>
|
|
<dt><b>"<tt>ccc</tt>" - The C calling convention</b>:</dt>
|
|
|
|
<dd>This calling convention (the default if no other calling convention is
|
|
specified) matches the target C calling conventions. This calling convention
|
|
supports varargs function calls and tolerates some mismatch in the declared
|
|
prototype and implemented declaration of the function (as does normal C).
|
|
</dd>
|
|
|
|
<dt><b>"<tt>csretcc</tt>" - The C struct return calling convention</b>:</dt>
|
|
|
|
<dd>This calling convention matches the target C calling conventions, except
|
|
that functions with this convention are required to take a pointer as their
|
|
first argument, and the return type of the function must be void. This is
|
|
used for C functions that return aggregates by-value. In this case, the
|
|
function has been transformed to take a pointer to the struct as the first
|
|
argument to the function. For targets where the ABI specifies specific
|
|
behavior for structure-return calls, the calling convention can be used to
|
|
distinguish between struct return functions and other functions that take a
|
|
pointer to a struct as the first argument.
|
|
</dd>
|
|
|
|
<dt><b>"<tt>fastcc</tt>" - The fast calling convention</b>:</dt>
|
|
|
|
<dd>This calling convention attempts to make calls as fast as possible
|
|
(e.g. by passing things in registers). This calling convention allows the
|
|
target to use whatever tricks it wants to produce fast code for the target,
|
|
without having to conform to an externally specified ABI. Implementations of
|
|
this convention should allow arbitrary tail call optimization to be supported.
|
|
This calling convention does not support varargs and requires the prototype of
|
|
all callees to exactly match the prototype of the function definition.
|
|
</dd>
|
|
|
|
<dt><b>"<tt>coldcc</tt>" - The cold calling convention</b>:</dt>
|
|
|
|
<dd>This calling convention attempts to make code in the caller as efficient
|
|
as possible under the assumption that the call is not commonly executed. As
|
|
such, these calls often preserve all registers so that the call does not break
|
|
any live ranges in the caller side. This calling convention does not support
|
|
varargs and requires the prototype of all callees to exactly match the
|
|
prototype of the function definition.
|
|
</dd>
|
|
|
|
<dt><b>"<tt>cc <<em>n</em>></tt>" - Numbered convention</b>:</dt>
|
|
|
|
<dd>Any calling convention may be specified by number, allowing
|
|
target-specific calling conventions to be used. Target specific calling
|
|
conventions start at 64.
|
|
</dd>
|
|
</dl>
|
|
|
|
<p>More calling conventions can be added/defined on an as-needed basis, to
|
|
support pascal conventions or any other well-known target-independent
|
|
convention.</p>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="globalvars">Global Variables</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>Global variables define regions of memory allocated at compilation time
|
|
instead of run-time. Global variables may optionally be initialized, may have
|
|
an explicit section to be placed in, and may
|
|
have an optional explicit alignment specified. A
|
|
variable may be defined as a global "constant," which indicates that the
|
|
contents of the variable will <b>never</b> be modified (enabling better
|
|
optimization, allowing the global data to be placed in the read-only section of
|
|
an executable, etc). Note that variables that need runtime initialization
|
|
cannot be marked "constant" as there is a store to the variable.</p>
|
|
|
|
<p>
|
|
LLVM explicitly allows <em>declarations</em> of global variables to be marked
|
|
constant, even if the final definition of the global is not. This capability
|
|
can be used to enable slightly better optimization of the program, but requires
|
|
the language definition to guarantee that optimizations based on the
|
|
'constantness' are valid for the translation units that do not include the
|
|
definition.
|
|
</p>
|
|
|
|
<p>As SSA values, global variables define pointer values that are in
|
|
scope (i.e. they dominate) all basic blocks in the program. Global
|
|
variables always define a pointer to their "content" type because they
|
|
describe a region of memory, and all memory objects in LLVM are
|
|
accessed through pointers.</p>
|
|
|
|
<p>LLVM allows an explicit section to be specified for globals. If the target
|
|
supports it, it will emit globals to the section specified.</p>
|
|
|
|
<p>An explicit alignment may be specified for a global. If not present, or if
|
|
the alignment is set to zero, the alignment of the global is set by the target
|
|
to whatever it feels convenient. If an explicit alignment is specified, the
|
|
global is forced to have at least that much alignment. All alignments must be
|
|
a power of 2.</p>
|
|
|
|
</div>
|
|
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="functionstructure">Functions</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>LLVM function definitions consist of an optional <a href="#linkage">linkage
|
|
type</a>, an optional <a href="#callingconv">calling convention</a>, a return
|
|
type, a function name, a (possibly empty) argument list, an optional section,
|
|
an optional alignment, an opening curly brace,
|
|
a list of basic blocks, and a closing curly brace. LLVM function declarations
|
|
are defined with the "<tt>declare</tt>" keyword, an optional <a
|
|
href="#callingconv">calling convention</a>, a return type, a function name,
|
|
a possibly empty list of arguments, and an optional alignment.</p>
|
|
|
|
<p>A function definition contains a list of basic blocks, forming the CFG for
|
|
the function. Each basic block may optionally start with a label (giving the
|
|
basic block a symbol table entry), contains a list of instructions, and ends
|
|
with a <a href="#terminators">terminator</a> instruction (such as a branch or
|
|
function return).</p>
|
|
|
|
<p>The first basic block in a program is special in two ways: it is immediately
|
|
executed on entrance to the function, and it is not allowed to have predecessor
|
|
basic blocks (i.e. there can not be any branches to the entry block of a
|
|
function). Because the block can have no predecessors, it also cannot have any
|
|
<a href="#i_phi">PHI nodes</a>.</p>
|
|
|
|
<p>LLVM functions are identified by their name and type signature. Hence, two
|
|
functions with the same name but different parameter lists or return values are
|
|
considered different functions, and LLVM will resolve references to each
|
|
appropriately.</p>
|
|
|
|
<p>LLVM allows an explicit section to be specified for functions. If the target
|
|
supports it, it will emit functions to the section specified.</p>
|
|
|
|
<p>An explicit alignment may be specified for a function. If not present, or if
|
|
the alignment is set to zero, the alignment of the function is set by the target
|
|
to whatever it feels convenient. If an explicit alignment is specified, the
|
|
function is forced to have at least that much alignment. All alignments must be
|
|
a power of 2.</p>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="moduleasm">Module-Level Inline Assembly</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
<p>
|
|
Modules may contain "module-level inline asm" blocks, which corresponds to the
|
|
GCC "file scope inline asm" blocks. These blocks are internally concatenated by
|
|
LLVM and treated as a single unit, but may be separated in the .ll file if
|
|
desired. The syntax is very simple:
|
|
</p>
|
|
|
|
<div class="doc_code"><pre>
|
|
module asm "inline asm code goes here"
|
|
module asm "more can go here"
|
|
</pre></div>
|
|
|
|
<p>The strings can contain any character by escaping non-printable characters.
|
|
The escape sequence used is simply "\xx" where "xx" is the two digit hex code
|
|
for the number.
|
|
</p>
|
|
|
|
<p>
|
|
The inline asm code is simply printed to the machine code .s file when
|
|
assembly code is generated.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<!-- *********************************************************************** -->
|
|
<div class="doc_section"> <a name="typesystem">Type System</a> </div>
|
|
<!-- *********************************************************************** -->
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>The LLVM type system is one of the most important features of the
|
|
intermediate representation. Being typed enables a number of
|
|
optimizations to be performed on the IR directly, without having to do
|
|
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>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<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 is as follows:</p>
|
|
|
|
<table class="layout">
|
|
<tr class="layout">
|
|
<td class="left">
|
|
<table>
|
|
<tbody>
|
|
<tr><th>Type</th><th>Description</th></tr>
|
|
<tr><td><tt>void</tt></td><td>No value</td></tr>
|
|
<tr><td><tt>ubyte</tt></td><td>Unsigned 8-bit value</td></tr>
|
|
<tr><td><tt>ushort</tt></td><td>Unsigned 16-bit value</td></tr>
|
|
<tr><td><tt>uint</tt></td><td>Unsigned 32-bit value</td></tr>
|
|
<tr><td><tt>ulong</tt></td><td>Unsigned 64-bit value</td></tr>
|
|
<tr><td><tt>float</tt></td><td>32-bit floating point value</td></tr>
|
|
<tr><td><tt>label</tt></td><td>Branch destination</td></tr>
|
|
</tbody>
|
|
</table>
|
|
</td>
|
|
<td class="right">
|
|
<table>
|
|
<tbody>
|
|
<tr><th>Type</th><th>Description</th></tr>
|
|
<tr><td><tt>bool</tt></td><td>True or False value</td></tr>
|
|
<tr><td><tt>sbyte</tt></td><td>Signed 8-bit value</td></tr>
|
|
<tr><td><tt>short</tt></td><td>Signed 16-bit value</td></tr>
|
|
<tr><td><tt>int</tt></td><td>Signed 32-bit value</td></tr>
|
|
<tr><td><tt>long</tt></td><td>Signed 64-bit value</td></tr>
|
|
<tr><td><tt>double</tt></td><td>64-bit floating point value</td></tr>
|
|
</tbody>
|
|
</table>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="t_classifications">Type
|
|
Classifications</a> </div>
|
|
<div class="doc_text">
|
|
<p>These different primitive types fall into a few useful
|
|
classifications:</p>
|
|
|
|
<table border="1" cellspacing="0" cellpadding="4">
|
|
<tbody>
|
|
<tr><th>Classification</th><th>Types</th></tr>
|
|
<tr>
|
|
<td><a name="t_signed">signed</a></td>
|
|
<td><tt>sbyte, short, int, long, float, double</tt></td>
|
|
</tr>
|
|
<tr>
|
|
<td><a name="t_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, uint, int, ulong, long,<br>
|
|
float, double, <a href="#t_pointer">pointer</a>,
|
|
<a href="#t_packed">packed</a></tt></td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
<p>The <a href="#t_firstclass">first class</a> types are perhaps the
|
|
most important. Values of these types are the only ones which can be
|
|
produced by instructions, passed as arguments, or used as operands to
|
|
instructions. This means that all structures and arrays must be
|
|
manipulated either by pointer or by component.</p>
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection"> <a name="t_derived">Derived Types</a> </div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>The real power in LLVM comes from the derived types in the system.
|
|
This is what allows a programmer to represent arrays, functions,
|
|
pointers, and other useful types. Note that these derived types may be
|
|
recursive: For example, it is possible to have a two dimensional array.</p>
|
|
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="t_array">Array Type</a> </div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The array type is a very simple derived type that arranges elements
|
|
sequentially in memory. The array type requires a size (number of
|
|
elements) and an underlying data type.</p>
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
[<# elements> x <elementtype>]
|
|
</pre>
|
|
|
|
<p>The number of elements is a constant integer value; elementtype may
|
|
be any type with a size.</p>
|
|
|
|
<h5>Examples:</h5>
|
|
<table class="layout">
|
|
<tr class="layout">
|
|
<td class="left">
|
|
<tt>[40 x int ]</tt><br/>
|
|
<tt>[41 x int ]</tt><br/>
|
|
<tt>[40 x uint]</tt><br/>
|
|
</td>
|
|
<td class="left">
|
|
Array of 40 integer values.<br/>
|
|
Array of 41 integer values.<br/>
|
|
Array of 40 unsigned integer values.<br/>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
<p>Here are some examples of multidimensional arrays:</p>
|
|
<table class="layout">
|
|
<tr class="layout">
|
|
<td class="left">
|
|
<tt>[3 x [4 x int]]</tt><br/>
|
|
<tt>[12 x [10 x float]]</tt><br/>
|
|
<tt>[2 x [3 x [4 x uint]]]</tt><br/>
|
|
</td>
|
|
<td class="left">
|
|
3x4 array of integer values.<br/>
|
|
12x10 array of single precision floating point values.<br/>
|
|
2x3x4 array of unsigned integer values.<br/>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
|
|
<p>Note that 'variable sized arrays' can be implemented in LLVM with a zero
|
|
length array. Normally, accesses past the end of an array are undefined in
|
|
LLVM (e.g. it is illegal to access the 5th element of a 3 element array).
|
|
As a special case, however, zero length arrays are recognized to be variable
|
|
length. This allows implementation of 'pascal style arrays' with the LLVM
|
|
type "{ int, [0 x float]}", for example.</p>
|
|
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="t_function">Function Type</a> </div>
|
|
<div class="doc_text">
|
|
<h5>Overview:</h5>
|
|
<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>)<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>
|
|
<table class="layout">
|
|
<tr class="layout">
|
|
<td class="left">
|
|
<tt>int (int)</tt> <br/>
|
|
<tt>float (int, int *) *</tt><br/>
|
|
<tt>int (sbyte *, ...)</tt><br/>
|
|
</td>
|
|
<td class="left">
|
|
function taking an <tt>int</tt>, returning an <tt>int</tt><br/>
|
|
<a href="#t_pointer">Pointer</a> to a function that takes an
|
|
<tt>int</tt> and a <a href="#t_pointer">pointer</a> to <tt>int</tt>,
|
|
returning <tt>float</tt>.<br/>
|
|
A vararg function that takes at least one <a href="#t_pointer">pointer</a>
|
|
to <tt>sbyte</tt> (signed char in C), which returns an integer. This is
|
|
the signature for <tt>printf</tt> in LLVM.<br/>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
|
|
</div>
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="t_struct">Structure Type</a> </div>
|
|
<div class="doc_text">
|
|
<h5>Overview:</h5>
|
|
<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> }<br></pre>
|
|
<h5>Examples:</h5>
|
|
<table class="layout">
|
|
<tr class="layout">
|
|
<td class="left">
|
|
<tt>{ int, int, int }</tt><br/>
|
|
<tt>{ float, int (int) * }</tt><br/>
|
|
</td>
|
|
<td class="left">
|
|
a triple of three <tt>int</tt> values<br/>
|
|
A pair, where the first element is a <tt>float</tt> and the second element
|
|
is a <a href="#t_pointer">pointer</a> to a <a href="#t_function">function</a>
|
|
that takes an <tt>int</tt>, returning an <tt>int</tt>.<br/>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<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 class="layout">
|
|
<tr class="layout">
|
|
<td class="left">
|
|
<tt>[4x int]*</tt><br/>
|
|
<tt>int (int *) *</tt><br/>
|
|
</td>
|
|
<td class="left">
|
|
A <a href="#t_pointer">pointer</a> to <a href="#t_array">array</a> of
|
|
four <tt>int</tt> values<br/>
|
|
A <a href="#t_pointer">pointer</a> to a <a
|
|
href="#t_function">function</a> that takes an <tt>int*</tt>, returning an
|
|
<tt>int</tt>.<br/>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="t_packed">Packed Type</a> </div>
|
|
<div class="doc_text">
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>A packed type is a simple derived type that represents a vector
|
|
of elements. Packed types are used when multiple primitive data
|
|
are operated in parallel using a single instruction (SIMD).
|
|
A packed type requires a size (number of
|
|
elements) and an underlying primitive data type. Vectors must have a power
|
|
of two length (1, 2, 4, 8, 16 ...). Packed types are
|
|
considered <a href="#t_firstclass">first class</a>.</p>
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
< <# elements> x <elementtype> >
|
|
</pre>
|
|
|
|
<p>The number of elements is a constant integer value; elementtype may
|
|
be any integral or floating point type.</p>
|
|
|
|
<h5>Examples:</h5>
|
|
|
|
<table class="layout">
|
|
<tr class="layout">
|
|
<td class="left">
|
|
<tt><4 x int></tt><br/>
|
|
<tt><8 x float></tt><br/>
|
|
<tt><2 x uint></tt><br/>
|
|
</td>
|
|
<td class="left">
|
|
Packed vector of 4 integer values.<br/>
|
|
Packed vector of 8 floating-point values.<br/>
|
|
Packed vector of 2 unsigned integer values.<br/>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="t_opaque">Opaque Type</a> </div>
|
|
<div class="doc_text">
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>Opaque types are used to represent unknown types in the system. This
|
|
corresponds (for example) to the C notion of a foward declared structure type.
|
|
In LLVM, opaque types can eventually be resolved to any type (not just a
|
|
structure type).</p>
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
opaque
|
|
</pre>
|
|
|
|
<h5>Examples:</h5>
|
|
|
|
<table class="layout">
|
|
<tr class="layout">
|
|
<td class="left">
|
|
<tt>opaque</tt>
|
|
</td>
|
|
<td class="left">
|
|
An opaque type.<br/>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</div>
|
|
|
|
|
|
<!-- *********************************************************************** -->
|
|
<div class="doc_section"> <a name="constants">Constants</a> </div>
|
|
<!-- *********************************************************************** -->
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>LLVM has several different basic types of constants. This section describes
|
|
them all and their syntax.</p>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection"><a name="simpleconstants">Simple Constants</a></div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<dl>
|
|
<dt><b>Boolean constants</b></dt>
|
|
|
|
<dd>The two strings '<tt>true</tt>' and '<tt>false</tt>' are both valid
|
|
constants of the <tt><a href="#t_primitive">bool</a></tt> type.
|
|
</dd>
|
|
|
|
<dt><b>Integer constants</b></dt>
|
|
|
|
<dd>Standard integers (such as '4') are constants of the <a
|
|
href="#t_integer">integer</a> type. Negative numbers may be used with signed
|
|
integer types.
|
|
</dd>
|
|
|
|
<dt><b>Floating point constants</b></dt>
|
|
|
|
<dd>Floating point constants use standard decimal notation (e.g. 123.421),
|
|
exponential notation (e.g. 1.23421e+2), or a more precise hexadecimal
|
|
notation (see below). Floating point constants must have a <a
|
|
href="#t_floating">floating point</a> type. </dd>
|
|
|
|
<dt><b>Null pointer constants</b></dt>
|
|
|
|
<dd>The identifier '<tt>null</tt>' is recognized as a null pointer constant
|
|
and must be of <a href="#t_pointer">pointer type</a>.</dd>
|
|
|
|
</dl>
|
|
|
|
<p>The one non-intuitive notation for constants is the optional hexadecimal form
|
|
of floating point constants. For example, the form '<tt>double
|
|
0x432ff973cafa8000</tt>' is equivalent to (but harder to read than) '<tt>double
|
|
4.5e+15</tt>'. The only time hexadecimal floating point constants are required
|
|
(and the only time that they are generated by the disassembler) is when a
|
|
floating point constant must be emitted but it cannot be represented as a
|
|
decimal floating point number. For example, NaN's, infinities, and other
|
|
special values are represented in their IEEE hexadecimal format so that
|
|
assembly and disassembly do not cause any bits to change in the constants.</p>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection"><a name="aggregateconstants">Aggregate Constants</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
<p>Aggregate constants arise from aggregation of simple constants
|
|
and smaller aggregate constants.</p>
|
|
|
|
<dl>
|
|
<dt><b>Structure constants</b></dt>
|
|
|
|
<dd>Structure constants are represented with notation similar to structure
|
|
type definitions (a comma separated list of elements, surrounded by braces
|
|
(<tt>{}</tt>)). For example: "<tt>{ int 4, float 17.0, int* %G }</tt>",
|
|
where "<tt>%G</tt>" is declared as "<tt>%G = external global int</tt>". Structure constants
|
|
must have <a href="#t_struct">structure type</a>, and the number and
|
|
types of elements must match those specified by the type.
|
|
</dd>
|
|
|
|
<dt><b>Array constants</b></dt>
|
|
|
|
<dd>Array constants are represented with notation similar to array type
|
|
definitions (a comma separated list of elements, surrounded by square brackets
|
|
(<tt>[]</tt>)). For example: "<tt>[ int 42, int 11, int 74 ]</tt>". Array
|
|
constants must have <a href="#t_array">array type</a>, and the number and
|
|
types of elements must match those specified by the type.
|
|
</dd>
|
|
|
|
<dt><b>Packed constants</b></dt>
|
|
|
|
<dd>Packed constants are represented with notation similar to packed type
|
|
definitions (a comma separated list of elements, surrounded by
|
|
less-than/greater-than's (<tt><></tt>)). For example: "<tt>< int 42,
|
|
int 11, int 74, int 100 ></tt>". Packed constants must have <a
|
|
href="#t_packed">packed type</a>, and the number and types of elements must
|
|
match those specified by the type.
|
|
</dd>
|
|
|
|
<dt><b>Zero initialization</b></dt>
|
|
|
|
<dd>The string '<tt>zeroinitializer</tt>' can be used to zero initialize a
|
|
value to zero of <em>any</em> type, including scalar and aggregate types.
|
|
This is often used to avoid having to print large zero initializers (e.g. for
|
|
large arrays) and is always exactly equivalent to using explicit zero
|
|
initializers.
|
|
</dd>
|
|
</dl>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="globalconstants">Global Variable and Function Addresses</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>The addresses of <a href="#globalvars">global variables</a> and <a
|
|
href="#functionstructure">functions</a> are always implicitly valid (link-time)
|
|
constants. These constants are explicitly referenced when the <a
|
|
href="#identifiers">identifier for the global</a> is used and always have <a
|
|
href="#t_pointer">pointer</a> type. For example, the following is a legal LLVM
|
|
file:</p>
|
|
|
|
<pre>
|
|
%X = global int 17
|
|
%Y = global int 42
|
|
%Z = global [2 x int*] [ int* %X, int* %Y ]
|
|
</pre>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection"><a name="undefvalues">Undefined Values</a></div>
|
|
<div class="doc_text">
|
|
<p>The string '<tt>undef</tt>' is recognized as a type-less constant that has
|
|
no specific value. Undefined values may be of any type and be used anywhere
|
|
a constant is permitted.</p>
|
|
|
|
<p>Undefined values indicate to the compiler that the program is well defined
|
|
no matter what value is used, giving the compiler more freedom to optimize.
|
|
</p>
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection"><a name="constantexprs">Constant Expressions</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>Constant expressions are used to allow expressions involving other constants
|
|
to be used as constants. Constant expressions may be of any <a
|
|
href="#t_firstclass">first class</a> type and may involve any LLVM operation
|
|
that does not have side effects (e.g. load and call are not supported). The
|
|
following is the syntax for constant expressions:</p>
|
|
|
|
<dl>
|
|
<dt><b><tt>cast ( CST to TYPE )</tt></b></dt>
|
|
|
|
<dd>Cast a constant to another type.</dd>
|
|
|
|
<dt><b><tt>getelementptr ( CSTPTR, IDX0, IDX1, ... )</tt></b></dt>
|
|
|
|
<dd>Perform the <a href="#i_getelementptr">getelementptr operation</a> on
|
|
constants. As with the <a href="#i_getelementptr">getelementptr</a>
|
|
instruction, the index list may have zero or more indexes, which are required
|
|
to make sense for the type of "CSTPTR".</dd>
|
|
|
|
<dt><b><tt>select ( COND, VAL1, VAL2 )</tt></b></dt>
|
|
|
|
<dd>Perform the <a href="#i_select">select operation</a> on
|
|
constants.
|
|
|
|
<dt><b><tt>extractelement ( VAL, IDX )</tt></b></dt>
|
|
|
|
<dd>Perform the <a href="#i_extractelement">extractelement
|
|
operation</a> on constants.
|
|
|
|
<dt><b><tt>insertelement ( VAL, ELT, IDX )</tt></b></dt>
|
|
|
|
<dd>Perform the <a href="#i_insertelement">insertelement
|
|
operation</a> on constants.
|
|
|
|
|
|
<dt><b><tt>shufflevector ( VEC1, VEC2, IDXMASK )</tt></b></dt>
|
|
|
|
<dd>Perform the <a href="#i_shufflevector">shufflevector
|
|
operation</a> on constants.
|
|
|
|
<dt><b><tt>OPCODE ( LHS, RHS )</tt></b></dt>
|
|
|
|
<dd>Perform the specified operation of the LHS and RHS constants. OPCODE may
|
|
be any of the <a href="#binaryops">binary</a> or <a href="#bitwiseops">bitwise
|
|
binary</a> operations. The constraints on operands are the same as those for
|
|
the corresponding instruction (e.g. no bitwise operations on floating point
|
|
values are allowed).</dd>
|
|
</dl>
|
|
</div>
|
|
|
|
<!-- *********************************************************************** -->
|
|
<div class="doc_section"> <a name="othervalues">Other Values</a> </div>
|
|
<!-- *********************************************************************** -->
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="inlineasm">Inline Assembler Expressions</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>
|
|
LLVM supports inline assembler expressions (as opposed to <a href="#moduleasm">
|
|
Module-Level Inline Assembly</a>) through the use of a special value. This
|
|
value represents the inline assembler as a string (containing the instructions
|
|
to emit), a list of operand constraints (stored as a string), and a flag that
|
|
indicates whether or not the inline asm expression has side effects. An example
|
|
inline assembler expression is:
|
|
</p>
|
|
|
|
<pre>
|
|
int(int) asm "bswap $0", "=r,r"
|
|
</pre>
|
|
|
|
<p>
|
|
Inline assembler expressions may <b>only</b> be used as the callee operand of
|
|
a <a href="#i_call"><tt>call</tt> instruction</a>. Thus, typically we have:
|
|
</p>
|
|
|
|
<pre>
|
|
%X = call int asm "<a href="#i_bswap">bswap</a> $0", "=r,r"(int %Y)
|
|
</pre>
|
|
|
|
<p>
|
|
Inline asms with side effects not visible in the constraint list must be marked
|
|
as having side effects. This is done through the use of the
|
|
'<tt>sideeffect</tt>' keyword, like so:
|
|
</p>
|
|
|
|
<pre>
|
|
call void asm sideeffect "eieio", ""()
|
|
</pre>
|
|
|
|
<p>TODO: The format of the asm and constraints string still need to be
|
|
documented here. Constraints on what can be done (e.g. duplication, moving, etc
|
|
need to be documented).
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<!-- *********************************************************************** -->
|
|
<div class="doc_section"> <a name="instref">Instruction Reference</a> </div>
|
|
<!-- *********************************************************************** -->
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>The LLVM instruction set consists of several different
|
|
classifications of instructions: <a href="#terminators">terminator
|
|
instructions</a>, <a href="#binaryops">binary instructions</a>,
|
|
<a href="#bitwiseops">bitwise binary instructions</a>, <a
|
|
href="#memoryops">memory instructions</a>, and <a href="#otherops">other
|
|
instructions</a>.</p>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection"> <a name="terminators">Terminator
|
|
Instructions</a> </div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>As mentioned <a href="#functionstructure">previously</a>, every
|
|
basic block in a program ends with a "Terminator" instruction, which
|
|
indicates which block should be executed after the current block is
|
|
finished. These terminator instructions typically yield a '<tt>void</tt>'
|
|
value: they produce control flow, not values (the one exception being
|
|
the '<a href="#i_invoke"><tt>invoke</tt></a>' instruction).</p>
|
|
<p>There are six different terminator instructions: the '<a
|
|
href="#i_ret"><tt>ret</tt></a>' instruction, the '<a href="#i_br"><tt>br</tt></a>'
|
|
instruction, the '<a href="#i_switch"><tt>switch</tt></a>' instruction,
|
|
the '<a href="#i_invoke"><tt>invoke</tt></a>' instruction, the '<a
|
|
href="#i_unwind"><tt>unwind</tt></a>' instruction, and the '<a
|
|
href="#i_unreachable"><tt>unreachable</tt></a>' instruction.</p>
|
|
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="i_ret">'<tt>ret</tt>'
|
|
Instruction</a> </div>
|
|
<div class="doc_text">
|
|
<h5>Syntax:</h5>
|
|
<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>
|
|
<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>
|
|
<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>
|
|
<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 of the "normal" destination block. If the instruction
|
|
returns a value, that value shall set the call or invoke instruction's
|
|
return value.</p>
|
|
<h5>Example:</h5>
|
|
<pre> ret int 5 <i>; Return an integer value of 5</i>
|
|
ret void <i>; Return from a void function</i>
|
|
</pre>
|
|
</div>
|
|
<!-- _______________________________________________________________________ -->
|
|
<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> br label <dest> <i>; Unconditional branch</i>
|
|
</pre>
|
|
<h5>Overview:</h5>
|
|
<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>
|
|
<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>
|
|
<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:<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>
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_switch">'<tt>switch</tt>' Instruction</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
switch <intty> <value>, label <defaultdest> [ <intty> <val>, label <dest> ... ]
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>switch</tt>' instruction is used to transfer control flow to one of
|
|
several different places. It is a generalization of the '<tt>br</tt>'
|
|
instruction, allowing a branch to occur to one of many possible
|
|
destinations.</p>
|
|
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>The '<tt>switch</tt>' instruction uses three parameters: an integer
|
|
comparison value '<tt>value</tt>', a default '<tt>label</tt>' destination, and
|
|
an array of pairs of comparison value constants and '<tt>label</tt>'s. The
|
|
table is not allowed to contain duplicate constant entries.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>The <tt>switch</tt> instruction specifies a table of values and
|
|
destinations. When the '<tt>switch</tt>' instruction is executed, this
|
|
table is searched for the given value. If the value is found, control flow is
|
|
transfered to the corresponding destination; otherwise, control flow is
|
|
transfered to the default destination.</p>
|
|
|
|
<h5>Implementation:</h5>
|
|
|
|
<p>Depending on properties of the target machine and the particular
|
|
<tt>switch</tt> instruction, this instruction may be code generated in different
|
|
ways. For example, it could be generated as a series of chained conditional
|
|
branches or with a lookup table.</p>
|
|
|
|
<h5>Example:</h5>
|
|
|
|
<pre>
|
|
<i>; Emulate a conditional br instruction</i>
|
|
%Val = <a href="#i_cast">cast</a> bool %value to int
|
|
switch int %Val, label %truedest [int 0, label %falsedest ]
|
|
|
|
<i>; Emulate an unconditional br instruction</i>
|
|
switch uint 0, label %dest [ ]
|
|
|
|
<i>; Implement a jump table:</i>
|
|
switch uint %val, label %otherwise [ uint 0, label %onzero
|
|
uint 1, label %onone
|
|
uint 2, label %ontwo ]
|
|
</pre>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_invoke">'<tt>invoke</tt>' Instruction</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
<result> = invoke [<a href="#callingconv">cconv</a>] <ptr to function ty> %<function ptr val>(<function args>)
|
|
to label <normal label> unwind label <exception label>
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>invoke</tt>' instruction causes control to transfer to a specified
|
|
function, with the possibility of control flow transfer to either the
|
|
'<tt>normal</tt>' label or the
|
|
'<tt>exception</tt>' label. If the callee function returns with the
|
|
"<tt><a href="#i_ret">ret</a></tt>" instruction, control flow will return to the
|
|
"normal" label. If the callee (or any indirect callees) returns with the "<a
|
|
href="#i_unwind"><tt>unwind</tt></a>" instruction, control is interrupted and
|
|
continued at the dynamically nearest "exception" label.</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>This instruction requires several arguments:</p>
|
|
|
|
<ol>
|
|
<li>
|
|
The optional "cconv" marker indicates which <a href="callingconv">calling
|
|
convention</a> the call should use. If none is specified, the call defaults
|
|
to using C calling conventions.
|
|
</li>
|
|
<li>'<tt>ptr to function ty</tt>': shall be the signature of the pointer to
|
|
function value being invoked. In most cases, this is a direct function
|
|
invocation, but indirect <tt>invoke</tt>s are just as possible, branching off
|
|
an arbitrary pointer to function value.
|
|
</li>
|
|
|
|
<li>'<tt>function ptr val</tt>': An LLVM value containing a pointer to a
|
|
function to be invoked. </li>
|
|
|
|
<li>'<tt>function args</tt>': argument list whose types match the function
|
|
signature argument types. If the function signature indicates the function
|
|
accepts a variable number of arguments, the extra arguments can be
|
|
specified. </li>
|
|
|
|
<li>'<tt>normal label</tt>': the label reached when the called function
|
|
executes a '<tt><a href="#i_ret">ret</a></tt>' instruction. </li>
|
|
|
|
<li>'<tt>exception label</tt>': the label reached when a callee returns with
|
|
the <a href="#i_unwind"><tt>unwind</tt></a> instruction. </li>
|
|
|
|
</ol>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>This instruction is designed to operate as a standard '<tt><a
|
|
href="#i_call">call</a></tt>' instruction in most regards. The primary
|
|
difference is that it establishes an association with a label, which is used by
|
|
the runtime library to unwind the stack.</p>
|
|
|
|
<p>This instruction is used in languages with destructors to ensure that proper
|
|
cleanup is performed in the case of either a <tt>longjmp</tt> or a thrown
|
|
exception. Additionally, this is important for implementation of
|
|
'<tt>catch</tt>' clauses in high-level languages that support them.</p>
|
|
|
|
<h5>Example:</h5>
|
|
<pre>
|
|
%retval = invoke int %Test(int 15) to label %Continue
|
|
unwind label %TestCleanup <i>; {int}:retval set</i>
|
|
%retval = invoke <a href="#callingconv">coldcc</a> int %Test(int 15) to label %Continue
|
|
unwind label %TestCleanup <i>; {int}:retval set</i>
|
|
</pre>
|
|
</div>
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
|
|
<div class="doc_subsubsection"> <a name="i_unwind">'<tt>unwind</tt>'
|
|
Instruction</a> </div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
unwind
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>unwind</tt>' instruction unwinds the stack, continuing control flow
|
|
at the first callee in the dynamic call stack which used an <a
|
|
href="#i_invoke"><tt>invoke</tt></a> instruction to perform the call. This is
|
|
primarily used to implement exception handling.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>The '<tt>unwind</tt>' intrinsic causes execution of the current function to
|
|
immediately halt. The dynamic call stack is then searched for the first <a
|
|
href="#i_invoke"><tt>invoke</tt></a> instruction on the call stack. Once found,
|
|
execution continues at the "exceptional" destination block specified by the
|
|
<tt>invoke</tt> instruction. If there is no <tt>invoke</tt> instruction in the
|
|
dynamic call chain, undefined behavior results.</p>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
|
|
<div class="doc_subsubsection"> <a name="i_unreachable">'<tt>unreachable</tt>'
|
|
Instruction</a> </div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
unreachable
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>unreachable</tt>' instruction has no defined semantics. This
|
|
instruction is used to inform the optimizer that a particular portion of the
|
|
code is not reachable. This can be used to indicate that the code after a
|
|
no-return function cannot be reached, and other facts.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>The '<tt>unreachable</tt>' instruction has no defined semantics.</p>
|
|
</div>
|
|
|
|
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection"> <a name="binaryops">Binary Operations</a> </div>
|
|
<div class="doc_text">
|
|
<p>Binary operators are used to do most of the computation in a
|
|
program. They require two operands, execute an operation on them, and
|
|
produce a single value. The operands might represent
|
|
multiple data, as is the case with the <a href="#t_packed">packed</a> data type.
|
|
The result value of a binary operator is not
|
|
necessarily the same type as its operands.</p>
|
|
<p>There are several different binary operators:</p>
|
|
</div>
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="i_add">'<tt>add</tt>'
|
|
Instruction</a> </div>
|
|
<div class="doc_text">
|
|
<h5>Syntax:</h5>
|
|
<pre> <result> = add <ty> <var1>, <var2> <i>; yields {ty}:result</i>
|
|
</pre>
|
|
<h5>Overview:</h5>
|
|
<p>The '<tt>add</tt>' instruction returns the sum of its two operands.</p>
|
|
<h5>Arguments:</h5>
|
|
<p>The two arguments to the '<tt>add</tt>' instruction must be either <a
|
|
href="#t_integer">integer</a> or <a href="#t_floating">floating point</a> values.
|
|
This instruction can also take <a href="#t_packed">packed</a> versions of the values.
|
|
Both arguments must have identical types.</p>
|
|
<h5>Semantics:</h5>
|
|
<p>The value produced is the integer or floating point sum of the two
|
|
operands.</p>
|
|
<h5>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.
|
|
This instruction can also take <a href="#t_packed">packed</a> versions of the values.
|
|
Both arguments must have identical types.</p>
|
|
<h5>Semantics:</h5>
|
|
<p>The value produced is the integer or floating point difference of
|
|
the two operands.</p>
|
|
<h5>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>
|
|
</pre>
|
|
</div>
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="i_mul">'<tt>mul</tt>'
|
|
Instruction</a> </div>
|
|
<div class="doc_text">
|
|
<h5>Syntax:</h5>
|
|
<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.
|
|
This instruction can also take <a href="#t_packed">packed</a> versions of the values.
|
|
Both arguments must have identical types.</p>
|
|
<h5>Semantics:</h5>
|
|
<p>The value produced is the integer or floating point product of the
|
|
two operands.</p>
|
|
<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_udiv">'<tt>udiv</tt>' Instruction
|
|
</a></div>
|
|
<div class="doc_text">
|
|
<h5>Syntax:</h5>
|
|
<pre> <result> = udiv <ty> <var1>, <var2> <i>; yields {ty}:result</i>
|
|
</pre>
|
|
<h5>Overview:</h5>
|
|
<p>The '<tt>udiv</tt>' instruction returns the quotient of its two
|
|
operands.</p>
|
|
<h5>Arguments:</h5>
|
|
<p>The two arguments to the '<tt>udiv</tt>' instruction must be
|
|
<a href="#t_integer">integer</a> values. Both arguments must have identical
|
|
types. This instruction can also take <a href="#t_packed">packed</a> versions
|
|
of the values in which case the elements must be integers.</p>
|
|
<h5>Semantics:</h5>
|
|
<p>The value produced is the unsigned integer quotient of the two operands. This
|
|
instruction always performs an unsigned division operation, regardless of
|
|
whether the arguments are unsigned or not.</p>
|
|
<h5>Example:</h5>
|
|
<pre> <result> = udiv uint 4, %var <i>; yields {uint}:result = 4 / %var</i>
|
|
</pre>
|
|
</div>
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="i_sdiv">'<tt>sdiv</tt>' Instruction
|
|
</a> </div>
|
|
<div class="doc_text">
|
|
<h5>Syntax:</h5>
|
|
<pre> <result> = sdiv <ty> <var1>, <var2> <i>; yields {ty}:result</i>
|
|
</pre>
|
|
<h5>Overview:</h5>
|
|
<p>The '<tt>sdiv</tt>' instruction returns the quotient of its two
|
|
operands.</p>
|
|
<h5>Arguments:</h5>
|
|
<p>The two arguments to the '<tt>sdiv</tt>' instruction must be
|
|
<a href="#t_integer">integer</a> values. Both arguments must have identical
|
|
types. This instruction can also take <a href="#t_packed">packed</a> versions
|
|
of the values in which case the elements must be integers.</p>
|
|
<h5>Semantics:</h5>
|
|
<p>The value produced is the signed integer quotient of the two operands. This
|
|
instruction always performs a signed division operation, regardless of whether
|
|
the arguments are signed or not.</p>
|
|
<h5>Example:</h5>
|
|
<pre> <result> = sdiv int 4, %var <i>; yields {int}:result = 4 / %var</i>
|
|
</pre>
|
|
</div>
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="i_fdiv">'<tt>fdiv</tt>'
|
|
Instruction</a> </div>
|
|
<div class="doc_text">
|
|
<h5>Syntax:</h5>
|
|
<pre> <result> = fdiv <ty> <var1>, <var2> <i>; yields {ty}:result</i>
|
|
</pre>
|
|
<h5>Overview:</h5>
|
|
<p>The '<tt>fdiv</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
|
|
<a href="#t_floating">floating point</a> values. Both arguments must have
|
|
identical types. This instruction can also take <a href="#t_packed">packed</a>
|
|
versions of the values in which case the elements must be floating point.</p>
|
|
<h5>Semantics:</h5>
|
|
<p>The value produced is the floating point quotient of the two operands.</p>
|
|
<h5>Example:</h5>
|
|
<pre> <result> = fdiv float 4.0, %var <i>; yields {float}:result = 4.0 / %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.
|
|
This instruction can also take <a href="#t_packed">packed</a> versions of the values.
|
|
Both arguments must have identical types.</p>
|
|
<h5>Semantics:</h5>
|
|
<p>This returns the <i>remainder</i> of a division (where the result
|
|
has the same sign as the divisor), not the <i>modulus</i> (where the
|
|
result has the same sign as the dividend) of a value. For more
|
|
information about the difference, see <a
|
|
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="vectorops">Vector Operations</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>LLVM supports several instructions to represent vector operations in a
|
|
target-independent manner. This instructions cover the element-access and
|
|
vector-specific operations needed to process vectors effectively. While LLVM
|
|
does directly support these vector operations, many sophisticated algorithms
|
|
will want to use target-specific intrinsics to take full advantage of a specific
|
|
target.</p>
|
|
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_extractelement">'<tt>extractelement</tt>' Instruction</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
<result> = extractelement <n x <ty>> <val>, uint <idx> <i>; yields <ty></i>
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>extractelement</tt>' instruction extracts a single scalar
|
|
element from a packed vector at a specified index.
|
|
</p>
|
|
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The first operand of an '<tt>extractelement</tt>' instruction is a
|
|
value of <a href="#t_packed">packed</a> type. The second operand is
|
|
an index indicating the position from which to extract the element.
|
|
The index may be a variable.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
The result is a scalar of the same type as the element type of
|
|
<tt>val</tt>. Its value is the value at position <tt>idx</tt> of
|
|
<tt>val</tt>. If <tt>idx</tt> exceeds the length of <tt>val</tt>, the
|
|
results are undefined.
|
|
</p>
|
|
|
|
<h5>Example:</h5>
|
|
|
|
<pre>
|
|
%result = extractelement <4 x int> %vec, uint 0 <i>; yields int</i>
|
|
</pre>
|
|
</div>
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_insertelement">'<tt>insertelement</tt>' Instruction</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
<result> = insertelement <n x <ty>> <val>, <ty> <elt>, uint <idx> <i>; yields <n x <ty>></i>
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>insertelement</tt>' instruction inserts a scalar
|
|
element into a packed vector at a specified index.
|
|
</p>
|
|
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The first operand of an '<tt>insertelement</tt>' instruction is a
|
|
value of <a href="#t_packed">packed</a> type. The second operand is a
|
|
scalar value whose type must equal the element type of the first
|
|
operand. The third operand is an index indicating the position at
|
|
which to insert the value. The index may be a variable.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
The result is a packed vector of the same type as <tt>val</tt>. Its
|
|
element values are those of <tt>val</tt> except at position
|
|
<tt>idx</tt>, where it gets the value <tt>elt</tt>. If <tt>idx</tt>
|
|
exceeds the length of <tt>val</tt>, the results are undefined.
|
|
</p>
|
|
|
|
<h5>Example:</h5>
|
|
|
|
<pre>
|
|
%result = insertelement <4 x int> %vec, int 1, uint 0 <i>; yields <4 x int></i>
|
|
</pre>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_shufflevector">'<tt>shufflevector</tt>' Instruction</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
<result> = shufflevector <n x <ty>> <v1>, <n x <ty>> <v2>, <n x uint> <mask> <i>; yields <n x <ty>></i>
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>shufflevector</tt>' instruction constructs a permutation of elements
|
|
from two input vectors, returning a vector of the same type.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The first two operands of a '<tt>shufflevector</tt>' instruction are vectors
|
|
with types that match each other and types that match the result of the
|
|
instruction. The third argument is a shuffle mask, which has the same number
|
|
of elements as the other vector type, but whose element type is always 'uint'.
|
|
</p>
|
|
|
|
<p>
|
|
The shuffle mask operand is required to be a constant vector with either
|
|
constant integer or undef values.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
The elements of the two input vectors are numbered from left to right across
|
|
both of the vectors. The shuffle mask operand specifies, for each element of
|
|
the result vector, which element of the two input registers the result element
|
|
gets. The element selector may be undef (meaning "don't care") and the second
|
|
operand may be undef if performing a shuffle from only one vector.
|
|
</p>
|
|
|
|
<h5>Example:</h5>
|
|
|
|
<pre>
|
|
%result = shufflevector <4 x int> %v1, <4 x int> %v2,
|
|
<4 x uint> <uint 0, uint 4, uint 1, uint 5> <i>; yields <4 x int></i>
|
|
%result = shufflevector <4 x int> %v1, <4 x int> undef,
|
|
<4 x uint> <uint 0, uint 1, uint 2, uint 3> <i>; yields <4 x int></i> - Identity shuffle.
|
|
</pre>
|
|
</div>
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="i_vsetint">'<tt>vsetint</tt>'
|
|
Instruction</a> </div>
|
|
<div class="doc_text">
|
|
<h5>Syntax:</h5>
|
|
<pre><result> = vsetint <op>, <n x <ty>> <var1>, <var2> <i>; yields <n x bool></i>
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>vsetint</tt>' instruction takes two integer vectors and
|
|
returns a vector of boolean values representing, at each position, the
|
|
result of the comparison between the values at that position in the
|
|
two operands.</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>The arguments to a '<tt>vsetint</tt>' instruction are a comparison
|
|
operation and two value arguments. The value arguments must be of <a
|
|
href="#t_integral">integral</a> <a href="#t_packed">packed</a> type,
|
|
and they must have identical types. The operation argument must be
|
|
one of <tt>eq</tt>, <tt>ne</tt>, <tt>slt</tt>, <tt>sgt</tt>,
|
|
<tt>sle</tt>, <tt>sge</tt>, <tt>ult</tt>, <tt>ugt</tt>, <tt>ule</tt>,
|
|
<tt>uge</tt>, <tt>true</tt>, and <tt>false</tt>. The result is a
|
|
packed <tt>bool</tt> value with the same length as each operand.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>The following table shows the semantics of '<tt>vsetint</tt>'. For
|
|
each position of the result, the comparison is done on the
|
|
corresponding positions of the two value arguments. Note that the
|
|
signedness of the comparison depends on the comparison opcode and
|
|
<i>not</i> on the signedness of the value operands. E.g., <tt>vsetint
|
|
slt <4 x unsigned> %x, %y</tt> does an elementwise <i>signed</i>
|
|
comparison of <tt>%x</tt> and <tt>%y</tt>.</p>
|
|
|
|
<table border="1" cellspacing="0" cellpadding="4">
|
|
<tbody>
|
|
<tr><th>Operation</th><th>Result is true iff</th><th>Comparison is</th></tr>
|
|
<tr><td><tt>eq</tt></td><td>var1 == var2</td><td>--</td></tr>
|
|
<tr><td><tt>ne</tt></td><td>var1 != var2</td><td>--</td></tr>
|
|
<tr><td><tt>slt</tt></td><td>var1 < var2</td><td>signed</td></tr>
|
|
<tr><td><tt>sgt</tt></td><td>var1 > var2</td><td>signed</td></tr>
|
|
<tr><td><tt>sle</tt></td><td>var1 <= var2</td><td>signed</td></tr>
|
|
<tr><td><tt>sge</tt></td><td>var1 >= var2</td><td>signed</td></tr>
|
|
<tr><td><tt>ult</tt></td><td>var1 < var2</td><td>unsigned</td></tr>
|
|
<tr><td><tt>ugt</tt></td><td>var1 > var2</td><td>unsigned</td></tr>
|
|
<tr><td><tt>ule</tt></td><td>var1 <= var2</td><td>unsigned</td></tr>
|
|
<tr><td><tt>uge</tt></td><td>var1 >= var2</td><td>unsigned</td></tr>
|
|
<tr><td><tt>true</tt></td><td>always</td><td>--</td></tr>
|
|
<tr><td><tt>false</tt></td><td>never</td><td>--</td></tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
<h5>Example:</h5>
|
|
<pre> <result> = vsetint eq <2 x int> <int 0, int 1>, <int 1, int 0> <i>; yields {<2 x bool>}:result = false, false</i>
|
|
<result> = vsetint ne <2 x int> <int 0, int 1>, <int 1, int 0> <i>; yields {<2 x bool>}:result = true, true</i>
|
|
<result> = vsetint slt <2 x int> <int 0, int 1>, <int 1, int 0> <i>; yields {<2 x bool>}:result = true, false</i>
|
|
<result> = vsetint sgt <2 x int> <int 0, int 1>, <int 1, int 0> <i>; yields {<2 x bool>}:result = false, true</i>
|
|
<result> = vsetint sle <2 x int> <int 0, int 1>, <int 1, int 0> <i>; yields {<2 x bool>}:result = true, false</i>
|
|
<result> = vsetint sge <2 x int> <int 0, int 1>, <int 1, int 0> <i>; yields {<2 x bool>}:result = false, true</i>
|
|
</pre>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="i_vsetfp">'<tt>vsetfp</tt>'
|
|
Instruction</a> </div>
|
|
<div class="doc_text">
|
|
<h5>Syntax:</h5>
|
|
<pre><result> = vsetfp <op>, <n x <ty>> <var1>, <var2> <i>; yields <n x bool></i>
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>vsetfp</tt>' instruction takes two floating point vector
|
|
arguments and returns a vector of boolean values representing, at each
|
|
position, the result of the comparison between the values at that
|
|
position in the two operands.</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>The arguments to a '<tt>vsetfp</tt>' instruction are a comparison
|
|
operation and two value arguments. The value arguments must be of <a
|
|
href="t_floating">floating point</a> <a href="#t_packed">packed</a>
|
|
type, and they must have identical types. The operation argument must
|
|
be one of <tt>eq</tt>, <tt>ne</tt>, <tt>lt</tt>, <tt>gt</tt>,
|
|
<tt>le</tt>, <tt>ge</tt>, <tt>oeq</tt>, <tt>one</tt>, <tt>olt</tt>,
|
|
<tt>ogt</tt>, <tt>ole</tt>, <tt>oge</tt>, <tt>ueq</tt>, <tt>une</tt>,
|
|
<tt>ult</tt>, <tt>ugt</tt>, <tt>ule</tt>, <tt>uge</tt>, <tt>o</tt>,
|
|
<tt>u</tt>, <tt>true</tt>, and <tt>false</tt>. The result is a packed
|
|
<tt>bool</tt> value with the same length as each operand.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>The following table shows the semantics of '<tt>vsetfp</tt>' for
|
|
floating point types. If either operand is a floating point Not a
|
|
Number (NaN) value, the operation is unordered, and the value in the
|
|
first column below is produced at that position. Otherwise, the
|
|
operation is ordered, and the value in the second column is
|
|
produced.</p>
|
|
|
|
<table border="1" cellspacing="0" cellpadding="4">
|
|
<tbody>
|
|
<tr><th>Operation</th><th>If unordered<th>Otherwise true iff</th></tr>
|
|
<tr><td><tt>eq</tt></td><td>undefined</td><td>var1 == var2</td></tr>
|
|
<tr><td><tt>ne</tt></td><td>undefined</td><td>var1 != var2</td></tr>
|
|
<tr><td><tt>lt</tt></td><td>undefined</td><td>var1 < var2</td></tr>
|
|
<tr><td><tt>gt</tt></td><td>undefined</td><td>var1 > var2</td></tr>
|
|
<tr><td><tt>le</tt></td><td>undefined</td><td>var1 <= var2</td></tr>
|
|
<tr><td><tt>ge</tt></td><td>undefined</td><td>var1 >= var2</td></tr>
|
|
<tr><td><tt>oeq</tt></td><td>false</td><td>var1 == var2</td></tr>
|
|
<tr><td><tt>one</tt></td><td>false</td><td>var1 != var2</td></tr>
|
|
<tr><td><tt>olt</tt></td><td>false</td><td>var1 < var2</td></tr>
|
|
<tr><td><tt>ogt</tt></td><td>false</td><td>var1 > var2</td></tr>
|
|
<tr><td><tt>ole</tt></td><td>false</td><td>var1 <= var2</td></tr>
|
|
<tr><td><tt>oge</tt></td><td>false</td><td>var1 >= var2</td></tr>
|
|
<tr><td><tt>ueq</tt></td><td>true</td><td>var1 == var2</td></tr>
|
|
<tr><td><tt>une</tt></td><td>true</td><td>var1 != var2</td></tr>
|
|
<tr><td><tt>ult</tt></td><td>true</td><td>var1 < var2</td></tr>
|
|
<tr><td><tt>ugt</tt></td><td>true</td><td>var1 > var2</td></tr>
|
|
<tr><td><tt>ule</tt></td><td>true</td><td>var1 <= var2</td></tr>
|
|
<tr><td><tt>uge</tt></td><td>true</td><td>var1 >= var2</td></tr>
|
|
<tr><td><tt>o</tt></td><td>false</td><td>always</td></tr>
|
|
<tr><td><tt>u</tt></td><td>true</td><td>never</td></tr>
|
|
<tr><td><tt>true</tt></td><td>true</td><td>always</td></tr>
|
|
<tr><td><tt>false</tt></td><td>false</td><td>never</td></tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
<h5>Example:</h5>
|
|
<pre> <result> = vsetfp eq <2 x float> <float 0.0, float 1.0>, <float 1.0, float 0.0> <i>; yields {<2 x bool>}:result = false, false</i>
|
|
<result> = vsetfp ne <2 x float> <float 0.0, float 1.0>, <float 1.0, float 0.0> <i>; yields {<2 x bool>}:result = true, true</i>
|
|
<result> = vsetfp lt <2 x float> <float 0.0, float 1.0>, <float 1.0, float 0.0> <i>; yields {<2 x bool>}:result = true, false</i>
|
|
<result> = vsetfp gt <2 x float> <float 0.0, float 1.0>, <float 1.0, float 0.0> <i>; yields {<2 x bool>}:result = false, true</i>
|
|
<result> = vsetfp le <2 x float> <float 0.0, float 1.0>, <float 1.0, float 0.0> <i>; yields {<2 x bool>}:result = true, false</i>
|
|
<result> = vsetfp ge <2 x float> <float 0.0, float 1.0>, <float 1.0, float 0.0> <i>; yields {<2 x bool>}:result = false, true</i>
|
|
</pre>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_vselect">'<tt>vselect</tt>' Instruction</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
<result> = vselect <n x bool> <cond>, <n x <ty>> <val1>, <n x <ty>> <val2> <i>; yields <n x <ty>></i>
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>vselect</tt>' instruction chooses one value at each position
|
|
of a vector based on a condition.
|
|
</p>
|
|
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The '<tt>vselect</tt>' instruction requires a <a
|
|
href="#t_packed">packed</a> <tt>bool</tt> value indicating the
|
|
condition at each vector position, and two values of the same packed
|
|
type. All three operands must have the same length. The type of the
|
|
result is the same as the type of the two value operands.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
At each position where the <tt>bool</tt> vector is true, that position
|
|
of the result gets its value from the first value argument; otherwise,
|
|
it gets its value from the second value argument.
|
|
</p>
|
|
|
|
<h5>Example:</h5>
|
|
|
|
<pre>
|
|
%X = vselect bool <2 x bool> <bool true, bool false>, <2 x ubyte> <ubyte 17, ubyte 17>,
|
|
<2 x ubyte> <ubyte 42, ubyte 42> <i>; yields <2 x ubyte>:17, 42</i>
|
|
</pre>
|
|
</div>
|
|
|
|
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="memoryops">Memory Access and Addressing 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>][, align <alignment>] <i>; yields {type*}:result</i>
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>malloc</tt>' instruction allocates memory from the system
|
|
heap and returns a pointer to it.</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>The '<tt>malloc</tt>' instruction allocates
|
|
<tt>sizeof(<type>)*NumElements</tt>
|
|
bytes of memory from the operating system and returns a pointer of the
|
|
appropriate type to the program. If "NumElements" is specified, it is the
|
|
number of elements allocated. If an alignment is specified, the value result
|
|
of the allocation is guaranteed to be aligned to at least that boundary. If
|
|
not specified, or if zero, the target can choose to align the allocation on any
|
|
convenient boundary.</p>
|
|
|
|
<p>'<tt>type</tt>' must be a sized type.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>Memory is allocated using the system "<tt>malloc</tt>" function, and
|
|
a pointer is returned.</p>
|
|
|
|
<h5>Example:</h5>
|
|
|
|
<pre>
|
|
%array = malloc [4 x ubyte ] <i>; yields {[%4 x ubyte]*}:array</i>
|
|
|
|
%size = <a href="#i_add">add</a> uint 2, 2 <i>; yields {uint}:size = uint 4</i>
|
|
%array1 = malloc ubyte, uint 4 <i>; yields {ubyte*}:array1</i>
|
|
%array2 = malloc [12 x ubyte], uint %size <i>; yields {[12 x ubyte]*}:array2</i>
|
|
%array3 = malloc int, uint 4, align 1024 <i>; yields {int*}:array3</i>
|
|
%array4 = malloc int, align 1024 <i>; yields {int*}:array4</i>
|
|
</pre>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_free">'<tt>free</tt>' Instruction</a>
|
|
</div>
|
|
|
|
<div class="doc_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>
|
|
|
|
<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 no longer defined
|
|
after this instruction executes.</p>
|
|
|
|
<h5>Example:</h5>
|
|
|
|
<pre>
|
|
%array = <a href="#i_malloc">malloc</a> [4 x ubyte] <i>; yields {[4 x ubyte]*}:array</i>
|
|
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>][, align <alignment>] <i>; yields {type*}:result</i>
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>alloca</tt>' instruction allocates memory on the current
|
|
stack frame of the procedure that is live until the current function
|
|
returns to its caller.</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>The '<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. If "NumElements" is specified, it is the
|
|
number of elements allocated. If an alignment is specified, the value result
|
|
of the allocation is guaranteed to be aligned to at least that boundary. If
|
|
not specified, or if zero, the target can choose to align the allocation on any
|
|
convenient boundary.</p>
|
|
|
|
<p>'<tt>type</tt>' may be any sized type.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>Memory is allocated; a pointer is returned. '<tt>alloca</tt>'d
|
|
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_unwind">unwind</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>
|
|
%ptr = alloca int, uint 4, align 1024 <i>; yields {int*}:ptr</i>
|
|
%ptr = alloca int, align 1024 <i>; yields {int*}:ptr</i>
|
|
</pre>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection"> <a name="i_load">'<tt>load</tt>'
|
|
Instruction</a> </div>
|
|
<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 from which to load. The pointer must point to a <a
|
|
href="#t_firstclass">first class</a> type. If the <tt>load</tt> is
|
|
marked as <tt>volatile</tt>, then the optimizer is not allowed to modify
|
|
the number or order of execution of this <tt>load</tt> with other
|
|
volatile <tt>load</tt> and <tt><a href="#i_store">store</a></tt>
|
|
instructions. </p>
|
|
<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 in which to store it. The type of the '<tt><pointer></tt>'
|
|
operand must be a pointer to the type of the '<tt><value></tt>'
|
|
operand. If the <tt>store</tt> is marked as <tt>volatile</tt>, then the
|
|
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>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>getelementptr</tt>' instruction is used to get the address of a
|
|
subelement of an aggregate data structure.</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>This instruction takes a list of integer constants that indicate what
|
|
elements of the aggregate object to index to. The actual types of the arguments
|
|
provided depend on the type of the first pointer argument. The
|
|
'<tt>getelementptr</tt>' instruction is used to index down through the type
|
|
levels of a structure or to a specific index in an array. When indexing into a
|
|
structure, only <tt>uint</tt>
|
|
integer constants are allowed. When indexing into an array or pointer,
|
|
<tt>int</tt> and <tt>long</tt> indexes are allowed of any sign.</p>
|
|
|
|
<p>For example, let's consider a C code fragment and how it gets
|
|
compiled to LLVM:</p>
|
|
|
|
<pre>
|
|
struct RT {
|
|
char A;
|
|
int B[10][20];
|
|
char C;
|
|
};
|
|
struct ST {
|
|
int X;
|
|
double Y;
|
|
struct RT Z;
|
|
};
|
|
|
|
int *foo(struct ST *s) {
|
|
return &s[1].Z.B[5][13];
|
|
}
|
|
</pre>
|
|
|
|
<p>The LLVM code generated by the GCC frontend is:</p>
|
|
|
|
<pre>
|
|
%RT = type { sbyte, [10 x [20 x int]], sbyte }
|
|
%ST = type { int, double, %RT }
|
|
|
|
implementation
|
|
|
|
int* %foo(%ST* %s) {
|
|
entry:
|
|
%reg = getelementptr %ST* %s, int 1, uint 2, uint 1, int 5, int 13
|
|
ret int* %reg
|
|
}
|
|
</pre>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>The index types specified for the '<tt>getelementptr</tt>' instruction depend
|
|
on the pointer type that is being indexed into. <a href="#t_pointer">Pointer</a>
|
|
and <a href="#t_array">array</a> types require <tt>uint</tt>, <tt>int</tt>,
|
|
<tt>ulong</tt>, or <tt>long</tt> values, and <a href="#t_struct">structure</a>
|
|
types require <tt>uint</tt> <b>constants</b>.</p>
|
|
|
|
<p>In the example above, the first index is indexing into the '<tt>%ST*</tt>'
|
|
type, which is a pointer, yielding a '<tt>%ST</tt>' = '<tt>{ int, double, %RT
|
|
}</tt>' type, a structure. The second index indexes into the third element of
|
|
the structure, yielding a '<tt>%RT</tt>' = '<tt>{ sbyte, [10 x [20 x int]],
|
|
sbyte }</tt>' type, another structure. The third index indexes into the second
|
|
element of the structure, yielding a '<tt>[10 x [20 x int]]</tt>' type, an
|
|
array. The two dimensions of the array are subscripted into, yielding an
|
|
'<tt>int</tt>' type. The '<tt>getelementptr</tt>' instruction returns a pointer
|
|
to this element, thus computing a value of '<tt>int*</tt>' type.</p>
|
|
|
|
<p>Note that it is perfectly legal to index partially through a
|
|
structure, returning a pointer to an inner element. Because of this,
|
|
the LLVM code for the given testcase is equivalent to:</p>
|
|
|
|
<pre>
|
|
int* %foo(%ST* %s) {
|
|
%t1 = getelementptr %ST* %s, int 1 <i>; yields %ST*:%t1</i>
|
|
%t2 = getelementptr %ST* %t1, int 0, uint 2 <i>; yields %RT*:%t2</i>
|
|
%t3 = getelementptr %RT* %t2, int 0, uint 1 <i>; yields [10 x [20 x int]]*:%t3</i>
|
|
%t4 = getelementptr [10 x [20 x int]]* %t3, int 0, int 5 <i>; yields [20 x int]*:%t4</i>
|
|
%t5 = getelementptr [20 x int]* %t4, int 0, int 13 <i>; yields int*:%t5</i>
|
|
ret int* %t5
|
|
}
|
|
</pre>
|
|
|
|
<p>Note that it is undefined to access an array out of bounds: array and
|
|
pointer indexes must always be within the defined bounds of the array type.
|
|
The one exception for this rules is zero length arrays. These arrays are
|
|
defined to be accessible as variable length arrays, which requires access
|
|
beyond the zero'th element.</p>
|
|
|
|
<p>The getelementptr instruction is often confusing. For some more insight
|
|
into how it works, see <a href="GetElementPtr.html">the getelementptr
|
|
FAQ</a>.</p>
|
|
|
|
<h5>Example:</h5>
|
|
|
|
<pre>
|
|
<i>; yields [12 x ubyte]*:aptr</i>
|
|
%aptr = getelementptr {int, [12 x ubyte]}* %sptr, long 0, uint 1
|
|
</pre>
|
|
|
|
</div>
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection"> <a name="otherops">Other Operations</a> </div>
|
|
<div class="doc_text">
|
|
<p>The instructions in this 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>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_cast">'<tt>cast .. to</tt>' Instruction</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
<result> = cast <ty> <value> to <ty2> <i>; yields ty2</i>
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>cast</tt>' instruction is used as the primitive means to convert
|
|
integers to floating point, change data type sizes, and break type safety (by
|
|
casting pointers).
|
|
</p>
|
|
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The '<tt>cast</tt>' instruction takes a value to cast, which must be a first
|
|
class value, and a type to cast it to, which must also be a <a
|
|
href="#t_firstclass">first class</a> type.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
This instruction follows the C rules for explicit casts when determining how the
|
|
data being cast must change to fit in its new container.
|
|
</p>
|
|
|
|
<p>
|
|
When casting to bool, any value that would be considered true in the context of
|
|
a C '<tt>if</tt>' condition is converted to the boolean '<tt>true</tt>' values,
|
|
all else are '<tt>false</tt>'.
|
|
</p>
|
|
|
|
<p>
|
|
When extending an integral value from a type of one signness to another (for
|
|
example '<tt>sbyte</tt>' to '<tt>ulong</tt>'), the value is sign-extended if the
|
|
<b>source</b> value is signed, and zero-extended if the source value is
|
|
unsigned. <tt>bool</tt> values are always zero extended into either zero or
|
|
one.
|
|
</p>
|
|
|
|
<h5>Example:</h5>
|
|
|
|
<pre>
|
|
%X = cast int 257 to ubyte <i>; yields ubyte:1</i>
|
|
%Y = cast int 123 to bool <i>; yields bool:true</i>
|
|
</pre>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_select">'<tt>select</tt>' Instruction</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
<result> = select bool <cond>, <ty> <val1>, <ty> <val2> <i>; yields ty</i>
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>select</tt>' instruction is used to choose one value based on a
|
|
condition, without branching.
|
|
</p>
|
|
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<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>
|
|
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>
|
|
%X = select bool true, ubyte 17, ubyte 42 <i>; yields ubyte:17</i>
|
|
</pre>
|
|
</div>
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_call">'<tt>call</tt>' Instruction</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
<result> = [tail] call [<a href="#callingconv">cconv</a>] <ty>* <fnptrval>(<param list>)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>call</tt>' instruction represents a simple function call.</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>This instruction requires several arguments:</p>
|
|
|
|
<ol>
|
|
<li>
|
|
<p>The optional "tail" marker indicates whether the callee function accesses
|
|
any allocas or varargs in the caller. If the "tail" marker is present, the
|
|
function call is eligible for tail call optimization. Note that calls may
|
|
be marked "tail" even if they do not occur before a <a
|
|
href="#i_ret"><tt>ret</tt></a> instruction.
|
|
</li>
|
|
<li>
|
|
<p>The optional "cconv" marker indicates which <a href="callingconv">calling
|
|
convention</a> the call should use. If none is specified, the call defaults
|
|
to using C calling conventions.
|
|
</li>
|
|
<li>
|
|
<p>'<tt>ty</tt>': shall be the signature of the pointer to function value
|
|
being invoked. The argument types must match the types implied by this
|
|
signature. This type can be omitted if the function is not varargs and
|
|
if the function type does not return a pointer to a function.</p>
|
|
</li>
|
|
<li>
|
|
<p>'<tt>fnptrval</tt>': An LLVM value containing a pointer to a function to
|
|
be invoked. In most cases, this is a direct function invocation, but
|
|
indirect <tt>call</tt>s are just as possible, calling an arbitrary pointer
|
|
to function value.</p>
|
|
</li>
|
|
<li>
|
|
<p>'<tt>function args</tt>': argument list whose types match the
|
|
function signature argument types. All arguments must be of
|
|
<a href="#t_firstclass">first class</a> type. If the function signature
|
|
indicates the function accepts a variable number of arguments, the extra
|
|
arguments can be specified.</p>
|
|
</li>
|
|
</ol>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>The '<tt>call</tt>' instruction is used to cause control flow to
|
|
transfer to a specified function, with its incoming arguments bound to
|
|
the specified values. Upon a '<tt><a href="#i_ret">ret</a></tt>'
|
|
instruction in the called function, control flow continues with the
|
|
instruction after the function call, and the return value of the
|
|
function is bound to the result argument. This is a simpler case of
|
|
the <a href="#i_invoke">invoke</a> instruction.</p>
|
|
|
|
<h5>Example:</h5>
|
|
|
|
<pre>
|
|
%retval = call int %test(int %argc)
|
|
call int(sbyte*, ...) *%printf(sbyte* %msg, int 12, sbyte 42);
|
|
%X = tail call int %foo()
|
|
%Y = tail call <a href="#callingconv">fastcc</a> int %foo()
|
|
</pre>
|
|
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_va_arg">'<tt>va_arg</tt>' Instruction</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
<resultval> = va_arg <va_list*> <arglist>, <argty>
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>va_arg</tt>' instruction is used to access arguments passed through
|
|
the "variable argument" area of a function call. It is used to implement the
|
|
<tt>va_arg</tt> macro in C.</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>This instruction takes a <tt>va_list*</tt> value and the type of
|
|
the argument. It returns a value of the specified argument type and
|
|
increments the <tt>va_list</tt> to point to the next argument. Again, the
|
|
actual type of <tt>va_list</tt> is target specific.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>The '<tt>va_arg</tt>' instruction loads an argument of the specified
|
|
type from the specified <tt>va_list</tt> and causes the
|
|
<tt>va_list</tt> to point to the next argument. For more information,
|
|
see the variable argument handling <a href="#int_varargs">Intrinsic
|
|
Functions</a>.</p>
|
|
|
|
<p>It is legal for this instruction to be called in a function which does not
|
|
take a variable number of arguments, for example, the <tt>vfprintf</tt>
|
|
function.</p>
|
|
|
|
<p><tt>va_arg</tt> is an LLVM instruction instead of an <a
|
|
href="#intrinsics">intrinsic function</a> because it takes a type as an
|
|
argument.</p>
|
|
|
|
<h5>Example:</h5>
|
|
|
|
<p>See the <a href="#int_varargs">variable argument processing</a> section.</p>
|
|
|
|
</div>
|
|
|
|
<!-- *********************************************************************** -->
|
|
<div class="doc_section"> <a name="intrinsics">Intrinsic Functions</a> </div>
|
|
<!-- *********************************************************************** -->
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>LLVM supports the notion of an "intrinsic function". These functions have
|
|
well known names and semantics and are required to follow certain
|
|
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>To learn how to add an intrinsic function, please see the <a
|
|
href="ExtendingLLVM.html">Extending LLVM Guide</a>.
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="int_varargs">Variable Argument Handling Intrinsics</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<p>Variable argument support is defined in LLVM with the <a
|
|
href="#i_va_arg"><tt>va_arg</tt></a> instruction and these three
|
|
intrinsic functions. These functions are related to the similarly
|
|
named macros defined in the <tt><stdarg.h></tt> header file.</p>
|
|
|
|
<p>All of these functions operate on arguments that use a
|
|
target-specific value type "<tt>va_list</tt>". The LLVM assembly
|
|
language reference manual does not define what this type is, so all
|
|
transformations should be prepared to handle intrinsics with any type
|
|
used.</p>
|
|
|
|
<p>This example shows how the <a href="#i_va_arg"><tt>va_arg</tt></a>
|
|
instruction and the variable argument handling intrinsic functions are
|
|
used.</p>
|
|
|
|
<pre>
|
|
int %test(int %X, ...) {
|
|
; Initialize variable argument processing
|
|
%ap = alloca sbyte*
|
|
call void %<a href="#i_va_start">llvm.va_start</a>(sbyte** %ap)
|
|
|
|
; Read a single integer argument
|
|
%tmp = va_arg sbyte** %ap, int
|
|
|
|
; Demonstrate usage of llvm.va_copy and llvm.va_end
|
|
%aq = alloca sbyte*
|
|
call void %<a href="#i_va_copy">llvm.va_copy</a>(sbyte** %aq, sbyte** %ap)
|
|
call void %<a href="#i_va_end">llvm.va_end</a>(sbyte** %aq)
|
|
|
|
; Stop processing of arguments.
|
|
call void %<a href="#i_va_end">llvm.va_end</a>(sbyte** %ap)
|
|
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> declare void %llvm.va_start(<va_list>* <arglist>)<br></pre>
|
|
<h5>Overview:</h5>
|
|
<P>The '<tt>llvm.va_start</tt>' intrinsic initializes
|
|
<tt>*<arglist></tt> for subsequent use by <tt><a
|
|
href="#i_va_arg">va_arg</a></tt>.</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<P>The argument is a pointer to a <tt>va_list</tt> element to initialize.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<P>The '<tt>llvm.va_start</tt>' intrinsic works just like the <tt>va_start</tt>
|
|
macro available in C. In a target-dependent way, it initializes the
|
|
<tt>va_list</tt> element the argument points to, so that the next call to
|
|
<tt>va_arg</tt> will produce the first variable argument passed to the function.
|
|
Unlike the C <tt>va_start</tt> macro, this intrinsic does not need to know the
|
|
last argument of the function, the compiler can figure that out.</p>
|
|
|
|
</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> declare void %llvm.va_end(<va_list*> <arglist>)<br></pre>
|
|
<h5>Overview:</h5>
|
|
<p>The '<tt>llvm.va_end</tt>' intrinsic destroys <tt><arglist></tt>
|
|
which has been initialized previously with <tt><a href="#i_va_start">llvm.va_start</a></tt>
|
|
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>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<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>
|
|
declare void %llvm.va_copy(<va_list>* <destarglist>,
|
|
<va_list>* <srcarglist>)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>llvm.va_copy</tt>' intrinsic copies the current argument position from
|
|
the source argument list to the destination argument list.</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>The first argument is a pointer to a <tt>va_list</tt> element to initialize.
|
|
The second argument is a pointer to a <tt>va_list</tt> element to copy from.</p>
|
|
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>The '<tt>llvm.va_copy</tt>' intrinsic works just like the <tt>va_copy</tt> macro
|
|
available in C. In a target-dependent way, it copies the source
|
|
<tt>va_list</tt> element into the destination list. This intrinsic is necessary
|
|
because the <tt><a href="i_va_begin">llvm.va_begin</a></tt> intrinsic may be
|
|
arbitrarily complex and require memory allocation, for example.</p>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="int_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>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_gcroot">'<tt>llvm.gcroot</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
declare void %llvm.gcroot(<ty>** %ptrloc, <ty2>* %metadata)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>llvm.gcroot</tt>' intrinsic declares the existence of a GC root to
|
|
the code generator, and allows some metadata to be associated with it.</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>The first argument 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>At runtime, a call to this intrinsics stores a null pointer into the "ptrloc"
|
|
location. At compile-time, the code generator generates information to allow
|
|
the runtime to find the pointer at GC safe points.
|
|
</p>
|
|
|
|
</div>
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_gcread">'<tt>llvm.gcread</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
declare sbyte* %llvm.gcread(sbyte* %ObjPtr, sbyte** %Ptr)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>llvm.gcread</tt>' intrinsic identifies reads of references from heap
|
|
locations, allowing garbage collector implementations that require read
|
|
barriers.</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>The second argument is the address to read from, which should be an address
|
|
allocated from the garbage collector. The first object is a pointer to the
|
|
start of the referenced object, if needed by the language runtime (otherwise
|
|
null).</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>The '<tt>llvm.gcread</tt>' intrinsic has the same semantics as a load
|
|
instruction, but may be replaced with substantially more complex code by the
|
|
garbage collector runtime, as needed.</p>
|
|
|
|
</div>
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_gcwrite">'<tt>llvm.gcwrite</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
|
|
<pre>
|
|
declare void %llvm.gcwrite(sbyte* %P1, sbyte* %Obj, sbyte** %P2)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>The '<tt>llvm.gcwrite</tt>' intrinsic identifies writes of references to heap
|
|
locations, allowing garbage collector implementations that require write
|
|
barriers (such as generational or reference counting collectors).</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>The first argument is the reference to store, the second is the start of the
|
|
object to store it to, and the third is the address of the field of Obj to
|
|
store to. If the runtime does not require a pointer to the object, Obj may be
|
|
null.</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>The '<tt>llvm.gcwrite</tt>' intrinsic has the same semantics as a store
|
|
instruction, but may be replaced with substantially more complex code by the
|
|
garbage collector runtime, as needed.</p>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="int_codegen">Code Generator Intrinsics</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
<p>
|
|
These intrinsics are provided by LLVM to expose special features that may only
|
|
be implemented with code generator support.
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_returnaddress">'<tt>llvm.returnaddress</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare sbyte *%llvm.returnaddress(uint <level>)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.returnaddress</tt>' intrinsic attempts to compute a
|
|
target-specific value indicating the return address of the current function
|
|
or one of its callers.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The argument to this intrinsic indicates which function to return the address
|
|
for. Zero indicates the calling function, one indicates its caller, etc. The
|
|
argument is <b>required</b> to be a constant integer value.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.returnaddress</tt>' intrinsic either returns a pointer indicating
|
|
the return address of the specified call frame, or zero if it cannot be
|
|
identified. The value returned by this intrinsic is likely to be incorrect or 0
|
|
for arguments other than zero, so it should only be used for debugging purposes.
|
|
</p>
|
|
|
|
<p>
|
|
Note that calling this intrinsic does not prevent function inlining or other
|
|
aggressive transformations, so the value returned may not be that of the obvious
|
|
source-language caller.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_frameaddress">'<tt>llvm.frameaddress</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare sbyte *%llvm.frameaddress(uint <level>)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.frameaddress</tt>' intrinsic attempts to return the
|
|
target-specific frame pointer value for the specified stack frame.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The argument to this intrinsic indicates which function to return the frame
|
|
pointer for. Zero indicates the calling function, one indicates its caller,
|
|
etc. The argument is <b>required</b> to be a constant integer value.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.frameaddress</tt>' intrinsic either returns a pointer indicating
|
|
the frame address of the specified call frame, or zero if it cannot be
|
|
identified. The value returned by this intrinsic is likely to be incorrect or 0
|
|
for arguments other than zero, so it should only be used for debugging purposes.
|
|
</p>
|
|
|
|
<p>
|
|
Note that calling this intrinsic does not prevent function inlining or other
|
|
aggressive transformations, so the value returned may not be that of the obvious
|
|
source-language caller.
|
|
</p>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_stacksave">'<tt>llvm.stacksave</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare sbyte *%llvm.stacksave()
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.stacksave</tt>' intrinsic is used to remember the current state of
|
|
the function stack, for use with <a href="#i_stackrestore">
|
|
<tt>llvm.stackrestore</tt></a>. This is useful for implementing language
|
|
features like scoped automatic variable sized arrays in C99.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
This intrinsic returns a opaque pointer value that can be passed to <a
|
|
href="#i_stackrestore"><tt>llvm.stackrestore</tt></a>. When an
|
|
<tt>llvm.stackrestore</tt> intrinsic is executed with a value saved from
|
|
<tt>llvm.stacksave</tt>, it effectively restores the state of the stack to the
|
|
state it was in when the <tt>llvm.stacksave</tt> intrinsic executed. In
|
|
practice, this pops any <a href="#i_alloca">alloca</a> blocks from the stack
|
|
that were allocated after the <tt>llvm.stacksave</tt> was executed.
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_stackrestore">'<tt>llvm.stackrestore</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare void %llvm.stackrestore(sbyte* %ptr)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.stackrestore</tt>' intrinsic is used to restore the state of
|
|
the function stack to the state it was in when the corresponding <a
|
|
href="#llvm.stacksave"><tt>llvm.stacksave</tt></a> intrinsic executed. This is
|
|
useful for implementing language features like scoped automatic variable sized
|
|
arrays in C99.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
See the description for <a href="#i_stacksave"><tt>llvm.stacksave</tt></a>.
|
|
</p>
|
|
|
|
</div>
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_prefetch">'<tt>llvm.prefetch</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare void %llvm.prefetch(sbyte * <address>,
|
|
uint <rw>, uint <locality>)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
|
|
<p>
|
|
The '<tt>llvm.prefetch</tt>' intrinsic is a hint to the code generator to insert
|
|
a prefetch instruction if supported; otherwise, it is a noop. Prefetches have
|
|
no
|
|
effect on the behavior of the program but can change its performance
|
|
characteristics.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
<tt>address</tt> is the address to be prefetched, <tt>rw</tt> is the specifier
|
|
determining if the fetch should be for a read (0) or write (1), and
|
|
<tt>locality</tt> is a temporal locality specifier ranging from (0) - no
|
|
locality, to (3) - extremely local keep in cache. The <tt>rw</tt> and
|
|
<tt>locality</tt> arguments must be constant integers.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
This intrinsic does not modify the behavior of the program. In particular,
|
|
prefetches cannot trap and do not produce a value. On targets that support this
|
|
intrinsic, the prefetch can provide hints to the processor cache for better
|
|
performance.
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_pcmarker">'<tt>llvm.pcmarker</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare void %llvm.pcmarker( uint <id> )
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
|
|
<p>
|
|
The '<tt>llvm.pcmarker</tt>' intrinsic is a method to export a Program Counter
|
|
(PC) in a region of
|
|
code to simulators and other tools. The method is target specific, but it is
|
|
expected that the marker will use exported symbols to transmit the PC of the marker.
|
|
The marker makes no guarantees that it will remain with any specific instruction
|
|
after optimizations. It is possible that the presence of a marker will inhibit
|
|
optimizations. The intended use is to be inserted after optimizations to allow
|
|
correlations of simulation runs.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
<tt>id</tt> is a numerical id identifying the marker.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
This intrinsic does not modify the behavior of the program. Backends that do not
|
|
support this intrinisic may ignore it.
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_readcyclecounter">'<tt>llvm.readcyclecounter</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare ulong %llvm.readcyclecounter( )
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
|
|
<p>
|
|
The '<tt>llvm.readcyclecounter</tt>' intrinsic provides access to the cycle
|
|
counter register (or similar low latency, high accuracy clocks) on those targets
|
|
that support it. On X86, it should map to RDTSC. On Alpha, it should map to RPCC.
|
|
As the backing counters overflow quickly (on the order of 9 seconds on alpha), this
|
|
should only be used for small timings.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
When directly supported, reading the cycle counter should not modify any memory.
|
|
Implementations are allowed to either return a application specific value or a
|
|
system wide value. On backends without support, this is lowered to a constant 0.
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="int_libc">Standard C Library Intrinsics</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
<p>
|
|
LLVM provides intrinsics for a few important standard C library functions.
|
|
These intrinsics allow source-language front-ends to pass information about the
|
|
alignment of the pointer arguments to the code generator, providing opportunity
|
|
for more efficient code generation.
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_memcpy">'<tt>llvm.memcpy</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare void %llvm.memcpy.i32(sbyte* <dest>, sbyte* <src>,
|
|
uint <len>, uint <align>)
|
|
declare void %llvm.memcpy.i64(sbyte* <dest>, sbyte* <src>,
|
|
ulong <len>, uint <align>)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.memcpy.*</tt>' intrinsics copy a block of memory from the source
|
|
location to the destination location.
|
|
</p>
|
|
|
|
<p>
|
|
Note that, unlike the standard libc function, the <tt>llvm.memcpy.*</tt>
|
|
intrinsics do not return a value, and takes an extra alignment argument.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The first argument is a pointer to the destination, the second is a pointer to
|
|
the source. The third argument is an integer argument
|
|
specifying the number of bytes to copy, and the fourth argument is the alignment
|
|
of the source and destination locations.
|
|
</p>
|
|
|
|
<p>
|
|
If the call to this intrinisic has an alignment value that is not 0 or 1, then
|
|
the caller guarantees that both the source and destination pointers are aligned
|
|
to that boundary.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.memcpy.*</tt>' intrinsics copy a block of memory from the source
|
|
location to the destination location, which are not allowed to overlap. It
|
|
copies "len" bytes of memory over. If the argument is known to be aligned to
|
|
some boundary, this can be specified as the fourth argument, otherwise it should
|
|
be set to 0 or 1.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_memmove">'<tt>llvm.memmove</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare void %llvm.memmove.i32(sbyte* <dest>, sbyte* <src>,
|
|
uint <len>, uint <align>)
|
|
declare void %llvm.memmove.i64(sbyte* <dest>, sbyte* <src>,
|
|
ulong <len>, uint <align>)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.memmove.*</tt>' intrinsics move a block of memory from the source
|
|
location to the destination location. It is similar to the
|
|
'<tt>llvm.memcmp</tt>' intrinsic but allows the two memory locations to overlap.
|
|
</p>
|
|
|
|
<p>
|
|
Note that, unlike the standard libc function, the <tt>llvm.memmove.*</tt>
|
|
intrinsics do not return a value, and takes an extra alignment argument.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The first argument is a pointer to the destination, the second is a pointer to
|
|
the source. The third argument is an integer argument
|
|
specifying the number of bytes to copy, and the fourth argument is the alignment
|
|
of the source and destination locations.
|
|
</p>
|
|
|
|
<p>
|
|
If the call to this intrinisic has an alignment value that is not 0 or 1, then
|
|
the caller guarantees that the source and destination pointers are aligned to
|
|
that boundary.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.memmove.*</tt>' intrinsics copy a block of memory from the source
|
|
location to the destination location, which may overlap. It
|
|
copies "len" bytes of memory over. If the argument is known to be aligned to
|
|
some boundary, this can be specified as the fourth argument, otherwise it should
|
|
be set to 0 or 1.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_memset">'<tt>llvm.memset.*</tt>' Intrinsics</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare void %llvm.memset.i32(sbyte* <dest>, ubyte <val>,
|
|
uint <len>, uint <align>)
|
|
declare void %llvm.memset.i64(sbyte* <dest>, ubyte <val>,
|
|
ulong <len>, uint <align>)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.memset.*</tt>' intrinsics fill a block of memory with a particular
|
|
byte value.
|
|
</p>
|
|
|
|
<p>
|
|
Note that, unlike the standard libc function, the <tt>llvm.memset</tt> intrinsic
|
|
does not return a value, and takes an extra alignment argument.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The first argument is a pointer to the destination to fill, the second is the
|
|
byte value to fill it with, the third argument is an integer
|
|
argument specifying the number of bytes to fill, and the fourth argument is the
|
|
known alignment of destination location.
|
|
</p>
|
|
|
|
<p>
|
|
If the call to this intrinisic has an alignment value that is not 0 or 1, then
|
|
the caller guarantees that the destination pointer is aligned to that boundary.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.memset.*</tt>' intrinsics fill "len" bytes of memory starting at
|
|
the
|
|
destination location. If the argument is known to be aligned to some boundary,
|
|
this can be specified as the fourth argument, otherwise it should be set to 0 or
|
|
1.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_isunordered">'<tt>llvm.isunordered.*</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare bool %llvm.isunordered.f32(float Val1, float Val2)
|
|
declare bool %llvm.isunordered.f64(double Val1, double Val2)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.isunordered</tt>' intrinsics return true if either or both of the
|
|
specified floating point values is a NAN.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The arguments are floating point numbers of the same type.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
If either or both of the arguments is a SNAN or QNAN, it returns true, otherwise
|
|
false.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_sqrt">'<tt>llvm.sqrt.*</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare float %llvm.sqrt.f32(float %Val)
|
|
declare double %llvm.sqrt.f64(double %Val)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.sqrt</tt>' intrinsics return the sqrt of the specified operand,
|
|
returning the same value as the libm '<tt>sqrt</tt>' function would. Unlike
|
|
<tt>sqrt</tt> in libm, however, <tt>llvm.sqrt</tt> has undefined behavior for
|
|
negative numbers (which allows for better optimization).
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The argument and return value are floating point numbers of the same type.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
This function returns the sqrt of the specified operand if it is a positive
|
|
floating point number.
|
|
</p>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_powi">'<tt>llvm.powi.*</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare float %llvm.powi.f32(float %Val, int %power)
|
|
declare double %llvm.powi.f64(double %Val, int %power)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.powi.*</tt>' intrinsics return the first operand raised to the
|
|
specified (positive or negative) power. The order of evaluation of
|
|
multiplications is not defined.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The second argument is an integer power, and the first is a value to raise to
|
|
that power.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
This function returns the first value raised to the second power with an
|
|
unspecified sequence of rounding operations.</p>
|
|
</div>
|
|
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="int_manip">Bit Manipulation Intrinsics</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
<p>
|
|
LLVM provides intrinsics for a few important bit manipulation operations.
|
|
These allow efficient code generation for some algorithms.
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="i_bswap">'<tt>llvm.bswap.*</tt>' Intrinsics</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare ushort %llvm.bswap.i16(ushort <id>)
|
|
declare uint %llvm.bswap.i32(uint <id>)
|
|
declare ulong %llvm.bswap.i64(ulong <id>)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.bwsap</tt>' family of intrinsics is used to byteswap a 16, 32 or
|
|
64 bit quantity. These are useful for performing operations on data that is not
|
|
in the target's native byte order.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
The <tt>llvm.bswap.16</tt> intrinsic returns a ushort value that has the high and low
|
|
byte of the input ushort swapped. Similarly, the <tt>llvm.bswap.i32</tt> intrinsic
|
|
returns a uint value that has the four bytes of the input uint swapped, so that
|
|
if the input bytes are numbered 0, 1, 2, 3 then the returned uint will have its
|
|
bytes in 3, 2, 1, 0 order. The <tt>llvm.bswap.i64</tt> intrinsic extends this concept
|
|
to 64 bits.
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="int_ctpop">'<tt>llvm.ctpop.*</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare ubyte %llvm.ctpop.i8 (ubyte <src>)
|
|
declare ushort %llvm.ctpop.i16(ushort <src>)
|
|
declare uint %llvm.ctpop.i32(uint <src>)
|
|
declare ulong %llvm.ctpop.i64(ulong <src>)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.ctpop</tt>' family of intrinsics counts the number of bits set in a
|
|
value.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The only argument is the value to be counted. The argument may be of any
|
|
unsigned integer type. The return type must match the argument type.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.ctpop</tt>' intrinsic counts the 1's in a variable.
|
|
</p>
|
|
</div>
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="int_ctlz">'<tt>llvm.ctlz.*</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare ubyte %llvm.ctlz.i8 (ubyte <src>)
|
|
declare ushort %llvm.ctlz.i16(ushort <src>)
|
|
declare uint %llvm.ctlz.i32(uint <src>)
|
|
declare ulong %llvm.ctlz.i64(ulong <src>)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.ctlz</tt>' family of intrinsic functions counts the number of
|
|
leading zeros in a variable.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The only argument is the value to be counted. The argument may be of any
|
|
unsigned integer type. The return type must match the argument type.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.ctlz</tt>' intrinsic counts the leading (most significant) zeros
|
|
in a variable. If the src == 0 then the result is the size in bits of the type
|
|
of src. For example, <tt>llvm.ctlz(int 2) = 30</tt>.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
|
|
<!-- _______________________________________________________________________ -->
|
|
<div class="doc_subsubsection">
|
|
<a name="int_cttz">'<tt>llvm.cttz.*</tt>' Intrinsic</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
|
|
<h5>Syntax:</h5>
|
|
<pre>
|
|
declare ubyte %llvm.cttz.i8 (ubyte <src>)
|
|
declare ushort %llvm.cttz.i16(ushort <src>)
|
|
declare uint %llvm.cttz.i32(uint <src>)
|
|
declare ulong %llvm.cttz.i64(ulong <src>)
|
|
</pre>
|
|
|
|
<h5>Overview:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.cttz</tt>' family of intrinsic functions counts the number of
|
|
trailing zeros.
|
|
</p>
|
|
|
|
<h5>Arguments:</h5>
|
|
|
|
<p>
|
|
The only argument is the value to be counted. The argument may be of any
|
|
unsigned integer type. The return type must match the argument type.
|
|
</p>
|
|
|
|
<h5>Semantics:</h5>
|
|
|
|
<p>
|
|
The '<tt>llvm.cttz</tt>' intrinsic counts the trailing (least significant) zeros
|
|
in a variable. If the src == 0 then the result is the size in bits of the type
|
|
of src. For example, <tt>llvm.cttz(2) = 1</tt>.
|
|
</p>
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<div class="doc_subsection">
|
|
<a name="int_debugger">Debugger Intrinsics</a>
|
|
</div>
|
|
|
|
<div class="doc_text">
|
|
<p>
|
|
The LLVM debugger intrinsics (which all start with <tt>llvm.dbg.</tt> prefix),
|
|
are described in the <a
|
|
href="SourceLevelDebugging.html#format_common_intrinsics">LLVM Source Level
|
|
Debugging</a> document.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<!-- *********************************************************************** -->
|
|
<hr>
|
|
<address>
|
|
<a href="http://jigsaw.w3.org/css-validator/check/referer"><img
|
|
src="http://jigsaw.w3.org/css-validator/images/vcss" alt="Valid CSS!"></a>
|
|
<a href="http://validator.w3.org/check/referer"><img
|
|
src="http://www.w3.org/Icons/valid-html401" alt="Valid HTML 4.01!" /></a>
|
|
|
|
<a href="mailto:sabre@nondot.org">Chris Lattner</a><br>
|
|
<a href="http://llvm.org">The LLVM Compiler Infrastructure</a><br>
|
|
Last modified: $Date$
|
|
</address>
|
|
</body>
|
|
</html>
|