<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="#namedtypes">Named Types</a></li>
<li><a href="#globalvars">Global Variables</a></li>
<li><a href="#functionstructure">Functions</a></li>
- <li><a href="#aliasstructure">Aliases</a>
+ <li><a href="#aliasstructure">Aliases</a></li>
<li><a href="#paramattrs">Parameter Attributes</a></li>
<li><a href="#fnattrs">Function Attributes</a></li>
<li><a href="#gc">Garbage Collector Names</a></li>
<li><a href="#t_floating">Floating Point Types</a></li>
<li><a href="#t_void">Void Type</a></li>
<li><a href="#t_label">Label Type</a></li>
+ <li><a href="#t_metadata">Metadata Type</a></li>
</ol>
</li>
<li><a href="#t_derived">Derived Types</a>
<li><a href="#t_opaque">Opaque Type</a></li>
</ol>
</li>
+ <li><a href="#t_uprefs">Type Up-references</a></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>
+ <li><a href="#simpleconstants">Simple Constants</a></li>
+ <li><a href="#complexconstants">Complex Constants</a></li>
+ <li><a href="#globalconstants">Global Variable and Function Addresses</a></li>
+ <li><a href="#undefvalues">Undefined Values</a></li>
+ <li><a href="#constantexprs">Constant Expressions</a></li>
+ <li><a href="#metadata">Embedded Metadata</a></li>
</ol>
</li>
<li><a href="#othervalues">Other Values</a>
<ol>
- <li><a href="#inlineasm">Inline Assembler Expressions</a>
+ <li><a href="#inlineasm">Inline Assembler Expressions</a></li>
</ol>
</li>
<li><a href="#instref">Instruction Reference</a>
<li><a href="#binaryops">Binary Operations</a>
<ol>
<li><a href="#i_add">'<tt>add</tt>' Instruction</a></li>
+ <li><a href="#i_fadd">'<tt>fadd</tt>' Instruction</a></li>
<li><a href="#i_sub">'<tt>sub</tt>' Instruction</a></li>
+ <li><a href="#i_fsub">'<tt>fsub</tt>' Instruction</a></li>
<li><a href="#i_mul">'<tt>mul</tt>' Instruction</a></li>
+ <li><a href="#i_fmul">'<tt>fmul</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_inttoptr">'<tt>inttoptr .. to</tt>' Instruction</a></li>
<li><a href="#i_bitcast">'<tt>bitcast .. to</tt>' Instruction</a></li>
</ol>
+ </li>
<li><a href="#otherops">Other Operations</a>
<ol>
<li><a href="#i_icmp">'<tt>icmp</tt>' Instruction</a></li>
<li><a href="#i_fcmp">'<tt>fcmp</tt>' Instruction</a></li>
- <li><a href="#i_vicmp">'<tt>vicmp</tt>' Instruction</a></li>
- <li><a href="#i_vfcmp">'<tt>vfcmp</tt>' Instruction</a></li>
<li><a href="#i_phi">'<tt>phi</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>
- <li><a href="#i_getresult">'<tt>getresult</tt>' Instruction</a></li>
</ol>
</li>
</ol>
<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>
- <li><a href="#int_part_select">'<tt>llvm.part.select.*</tt>' Intrinsic </a></li>
- <li><a href="#int_part_set">'<tt>llvm.part.set.*</tt>' Intrinsic </a></li>
+ </ol>
+ </li>
+ <li><a href="#int_overflow">Arithmetic with Overflow Intrinsics</a>
+ <ol>
+ <li><a href="#int_sadd_overflow">'<tt>llvm.sadd.with.overflow.*</tt> Intrinsics</a></li>
+ <li><a href="#int_uadd_overflow">'<tt>llvm.uadd.with.overflow.*</tt> Intrinsics</a></li>
+ <li><a href="#int_ssub_overflow">'<tt>llvm.ssub.with.overflow.*</tt> Intrinsics</a></li>
+ <li><a href="#int_usub_overflow">'<tt>llvm.usub.with.overflow.*</tt> Intrinsics</a></li>
+ <li><a href="#int_smul_overflow">'<tt>llvm.smul.with.overflow.*</tt> Intrinsics</a></li>
+ <li><a href="#int_umul_overflow">'<tt>llvm.umul.with.overflow.*</tt> Intrinsics</a></li>
</ol>
</li>
<li><a href="#int_debugger">Debugger intrinsics</a></li>
<li><a href="#int_it">'<tt>llvm.init.trampoline</tt>' Intrinsic</a></li>
</ol>
</li>
- <li><a href="#int_atomics">Atomic intrinsics</a>
- <ol>
- <li><a href="#int_memory_barrier"><tt>llvm.memory_barrier</tt></a></li>
- <li><a href="#int_atomic_cmp_swap"><tt>llvm.atomic.cmp.swap</tt></a></li>
- <li><a href="#int_atomic_swap"><tt>llvm.atomic.swap</tt></a></li>
- <li><a href="#int_atomic_load_add"><tt>llvm.atomic.load.add</tt></a></li>
- <li><a href="#int_atomic_load_sub"><tt>llvm.atomic.load.sub</tt></a></li>
- <li><a href="#int_atomic_load_and"><tt>llvm.atomic.load.and</tt></a></li>
- <li><a href="#int_atomic_load_nand"><tt>llvm.atomic.load.nand</tt></a></li>
- <li><a href="#int_atomic_load_or"><tt>llvm.atomic.load.or</tt></a></li>
- <li><a href="#int_atomic_load_xor"><tt>llvm.atomic.load.xor</tt></a></li>
- <li><a href="#int_atomic_load_max"><tt>llvm.atomic.load.max</tt></a></li>
- <li><a href="#int_atomic_load_min"><tt>llvm.atomic.load.min</tt></a></li>
- <li><a href="#int_atomic_load_umax"><tt>llvm.atomic.load.umax</tt></a></li>
- <li><a href="#int_atomic_load_umin"><tt>llvm.atomic.load.umin</tt></a></li>
- </ol>
- </li>
+ <li><a href="#int_atomics">Atomic intrinsics</a>
+ <ol>
+ <li><a href="#int_memory_barrier"><tt>llvm.memory_barrier</tt></a></li>
+ <li><a href="#int_atomic_cmp_swap"><tt>llvm.atomic.cmp.swap</tt></a></li>
+ <li><a href="#int_atomic_swap"><tt>llvm.atomic.swap</tt></a></li>
+ <li><a href="#int_atomic_load_add"><tt>llvm.atomic.load.add</tt></a></li>
+ <li><a href="#int_atomic_load_sub"><tt>llvm.atomic.load.sub</tt></a></li>
+ <li><a href="#int_atomic_load_and"><tt>llvm.atomic.load.and</tt></a></li>
+ <li><a href="#int_atomic_load_nand"><tt>llvm.atomic.load.nand</tt></a></li>
+ <li><a href="#int_atomic_load_or"><tt>llvm.atomic.load.or</tt></a></li>
+ <li><a href="#int_atomic_load_xor"><tt>llvm.atomic.load.xor</tt></a></li>
+ <li><a href="#int_atomic_load_max"><tt>llvm.atomic.load.max</tt></a></li>
+ <li><a href="#int_atomic_load_min"><tt>llvm.atomic.load.min</tt></a></li>
+ <li><a href="#int_atomic_load_umax"><tt>llvm.atomic.load.umax</tt></a></li>
+ <li><a href="#int_atomic_load_umin"><tt>llvm.atomic.load.umin</tt></a></li>
+ </ol>
+ </li>
<li><a href="#int_general">General intrinsics</a>
<ol>
<li><a href="#int_var_annotation">
- <tt>llvm.var.annotation</tt>' Intrinsic</a></li>
+ '<tt>llvm.var.annotation</tt>' Intrinsic</a></li>
<li><a href="#int_annotation">
- <tt>llvm.annotation.*</tt>' Intrinsic</a></li>
+ '<tt>llvm.annotation.*</tt>' Intrinsic</a></li>
<li><a href="#int_trap">
- <tt>llvm.trap</tt>' Intrinsic</a></li>
+ '<tt>llvm.trap</tt>' Intrinsic</a></li>
+ <li><a href="#int_stackprotector">
+ '<tt>llvm.stackprotector</tt>' Intrinsic</a></li>
</ol>
</li>
</ol>
<p>LLVM identifiers come in two basic types: global and local. Global
identifiers (functions, global variables) begin with the @ character. Local
identifiers (register names, types) begin with the % character. Additionally,
- there are three different formats for identifiers, for different purposes:
+ there are three different formats for identifiers, for different purposes:</p>
<ol>
<li>Named values are represented as a string of characters with their 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 named value.</li>
+ with quotes. Special characters may be escaped using "\xx" where xx is the
+ ASCII code for the character in hexadecimal. In this way, any character can
+ be used in a name value, even quotes themselves.
<li>Unnamed values are represented as an unsigned numeric value with their
prefix. For example, %12, @2, %44.</li>
<i>; Definition of main function</i>
define i32 @main() { <i>; i32()* </i>
- <i>; Convert [13x i8 ]* to i8 *...</i>
+ <i>; Convert [13 x i8]* to i8 *...</i>
%cast210 = <a
- href="#i_getelementptr">getelementptr</a> [13 x i8 ]* @.LC0, i64 0, i64 0 <i>; i8 *</i>
+ href="#i_getelementptr">getelementptr</a> [13 x i8]* @.LC0, i64 0, i64 0 <i>; i8 *</i>
<i>; Call puts function to write out the string to stdout...</i>
<a
<dl>
- <dt><tt><b><a name="linkage_internal">internal</a></b></tt>: </dt>
+ <dt><tt><b><a name="linkage_private">private</a></b></tt>: </dt>
- <dd>Global values with internal linkage are only directly accessible by
+ <dd>Global values with private 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
+ an private global value may cause the private to be renamed as necessary to
+ avoid collisions. Because the symbol is private to the module, all
+ references can be updated. This doesn't show up in any symbol table in the
+ object file.
+ </dd>
+
+ <dt><tt><b><a name="linkage_internal">internal</a></b></tt>: </dt>
+
+ <dd> Similar to private, but the value shows as a local symbol (STB_LOCAL in
+ the case of ELF) in the object file. This corresponds to the notion of the
'<tt>static</tt>' keyword in C.
</dd>
+ <dt><tt><b><a name="available_externally">available_externally</a></b></tt>:
+ </dt>
+
+ <dd>Globals with "<tt>available_externally</tt>" linkage are never emitted
+ into the object file corresponding to the LLVM module. They exist to
+ allow inlining and other optimizations to take place given knowledge of the
+ definition of the global, which is known to be somewhere outside the module.
+ Globals with <tt>available_externally</tt> linkage are allowed to be discarded
+ at will, and are otherwise the same as <tt>linkonce_odr</tt>. This linkage
+ type is only allowed on definitions, not declarations.</dd>
+
<dt><tt><b><a name="linkage_linkonce">linkonce</a></b></tt>: </dt>
<dd>Globals with "<tt>linkonce</tt>" linkage are merged with other globals of
</dd>
<dt><tt><b><a name="linkage_externweak">extern_weak</a></b></tt>: </dt>
+
<dd>The semantics of this linkage follow the ELF object file model: the
symbol is weak until linked, if not linked, the symbol becomes null instead
of being an undefined reference.
</dd>
+ <dt><tt><b><a name="linkage_linkonce">linkonce_odr</a></b></tt>: </dt>
+ <dt><tt><b><a name="linkage_weak">weak_odr</a></b></tt>: </dt>
+ <dd>Some languages allow differing globals to be merged, such as two
+ functions with different semantics. Other languages, such as <tt>C++</tt>,
+ ensure that only equivalent globals are ever merged (the "one definition
+ rule" - "ODR"). Such languages can use the <tt>linkonce_odr</tt>
+ and <tt>weak_odr</tt> linkage types to indicate that the global will only
+ be merged with equivalent globals. These linkage types are otherwise the
+ same as their non-<tt>odr</tt> versions.
+ </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
<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.
+ 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 is formed by combining <code>__imp_</code> and the function or variable
name.
</dd>
</dl>
-<p><a name="linkage_external"></a>For example, since the "<tt>.LC0</tt>"
+<p>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.</p>
<p>It is illegal for a function <i>declaration</i>
-to have any linkage type other than "externally visible", <tt>dllimport</tt>,
+to have any linkage type other than "externally visible", <tt>dllimport</tt>
or <tt>extern_weak</tt>.</p>
-<p>Aliases can have only <tt>external</tt>, <tt>internal</tt> and <tt>weak</tt>
-linkages.
+<p>Aliases can have only <tt>external</tt>, <tt>internal</tt>, <tt>weak</tt>
+or <tt>weak_odr</tt> linkages.</p>
</div>
<!-- ======================================================================= -->
</div>
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="namedtypes">Named Types</a>
+</div>
+
+<div class="doc_text">
+
+<p>LLVM IR allows you to specify name aliases for certain types. This can make
+it easier to read the IR and make the IR more condensed (particularly when
+recursive types are involved). An example of a name specification is:
+</p>
+
+<div class="doc_code">
+<pre>
+%mytype = type { %mytype*, i32 }
+</pre>
+</div>
+
+<p>You may give a name to any <a href="#typesystem">type</a> except "<a
+href="t_void">void</a>". Type name aliases may be used anywhere a type is
+expected with the syntax "%mytype".</p>
+
+<p>Note that type names are aliases for the structural type that they indicate,
+and that you can therefore specify multiple names for the same type. This often
+leads to confusing behavior when dumping out a .ll file. Since LLVM IR uses
+structural typing, the name is not part of the type. When printing out LLVM IR,
+the printer will pick <em>one name</em> to render all types of a particular
+shape. This means that if you have code where two different source types end up
+having the same LLVM type, that the dumper will sometimes print the "wrong" or
+unexpected type. This is an important design point and isn't going to
+change.</p>
+
+</div>
+
<!-- ======================================================================= -->
<div class="doc_subsection">
<a name="globalvars">Global Variables</a>
describe a region of memory, and all memory objects in LLVM are
accessed through pointers.</p>
-<p>A global variable may be declared to reside in a target-specifc numbered
+<p>A global variable may be declared to reside in a target-specific numbered
address space. For targets that support them, address spaces may affect how
optimizations are performed and/or what target instructions are used to access
the variable. The default address space is zero. The address space qualifier
<div class="doc_code">
<pre>
-@G = constant float 1.0 addrspace(5), section "foo", align 4
+@G = addrspace(5) constant float 1.0, section "foo", align 4
</pre>
</div>
<a href="#callingconv">calling convention</a>, a return type, an optional
<a href="#paramattrs">parameter attribute</a> for the return type, a function
name, a (possibly empty) argument list (each with optional
-<a href="#paramattrs">parameter attributes</a>), an optional section, an
-optional alignment, an optional <a href="#gc">garbage collector name</a>,
+<a href="#paramattrs">parameter attributes</a>), optional
+<a href="#fnattrs">function attributes</a>, an optional section,
+an optional alignment, an optional <a href="#gc">garbage collector name</a>,
an opening curly brace, a list of basic blocks, and a closing curly brace.
LLVM function declarations consist of the "<tt>declare</tt>" keyword, an
function is forced to have at least that much alignment. All alignments must be
a power of 2.</p>
+ <h5>Syntax:</h5>
+
+<div class="doc_code">
+<tt>
+define [<a href="#linkage">linkage</a>] [<a href="#visibility">visibility</a>]
+ [<a href="#callingconv">cconv</a>] [<a href="#paramattrs">ret attrs</a>]
+ <ResultType> @<FunctionName> ([argument list])
+ [<a href="#fnattrs">fn Attrs</a>] [section "name"] [align N]
+ [<a href="#gc">gc</a>] { ... }
+</tt>
+</div>
+
</div>
<div class="doc_code">
<pre>
-declare i32 @printf(i8* noalias , ...)
+declare i32 @printf(i8* noalias nocapture, ...)
declare i32 @atoi(i8 zeroext)
declare signext i8 @returns_signed_char()
</pre>
to memory, though some targets use it to distinguish between two different
kinds of registers). Use of this attribute is target-specific.</dd>
- <dt><tt>byval</tt></dt>
+ <dt><tt><a name="byval">byval</a></tt></dt>
<dd>This indicates that the pointer parameter should really be passed by
value to the function. The attribute implies that a hidden copy of the
pointee is made between the caller and the callee, so the callee is unable
to modify the value in the callee. This attribute is only valid on LLVM
pointer arguments. It is generally used to pass structs and arrays by
- value, but is also valid on pointers to scalars.</dd>
+ value, but is also valid on pointers to scalars. The copy is considered to
+ belong to the caller not the callee (for example,
+ <tt><a href="#readonly">readonly</a></tt> functions should not write to
+ <tt>byval</tt> parameters). This is not a valid attribute for return
+ values. The byval attribute also supports specifying an alignment with the
+ align attribute. This has a target-specific effect on the code generator
+ that usually indicates a desired alignment for the synthesized stack
+ slot.</dd>
<dt><tt>sret</tt></dt>
<dd>This indicates that the pointer parameter specifies the address of a
structure that is the return value of the function in the source program.
This pointer must be guaranteed by the caller to be valid: loads and stores
to the structure may be assumed by the callee to not to trap. This may only
- be applied to the first parameter.</dd>
+ be applied to the first parameter. This is not a valid attribute for
+ return values. </dd>
<dt><tt>noalias</tt></dt>
- <dd>This indicates that the parameter does not alias any global or any other
- parameter. The caller is responsible for ensuring that this is the case,
- usually by placing the value in a stack allocation.</dd>
+ <dd>This indicates that the pointer does not alias any global or any other
+ parameter. The caller is responsible for ensuring that this is the
+ case. On a function return value, <tt>noalias</tt> additionally indicates
+ that the pointer does not alias any other pointers visible to the
+ caller. For further details, please see the discussion of the NoAlias
+ response in
+ <a href="http://llvm.org/docs/AliasAnalysis.html#MustMayNo">alias
+ analysis</a>.</dd>
+
+ <dt><tt>nocapture</tt></dt>
+ <dd>This indicates that the callee does not make any copies of the pointer
+ that outlive the callee itself. This is not a valid attribute for return
+ values.</dd>
<dt><tt>nest</tt></dt>
<dd>This indicates that the pointer parameter can be excised using the
- <a href="#int_trampoline">trampoline intrinsics</a>.</dd>
+ <a href="#int_trampoline">trampoline intrinsics</a>. This is not a valid
+ attribute for return values.</dd>
</dl>
</div>
<dt><tt>noinline</tt></dt>
<dd>This attribute indicates that the inliner should never inline this function
-in any situation. This attribute may not be used together with
+in any situation. This attribute may not be used together with the
<tt>alwaysinline</tt> attribute.</dd>
<dt><tt>optsize</tt></dt>
behavior is undefined.</dd>
<dt><tt>readnone</tt></dt>
-<dd>This attribute indicates that the function computes its result (or its
-thrown exception) based strictly on its arguments. It does not read any global
-mutable state (e.g. memory, control registers, etc) visible to caller functions.
-Furthermore, <tt>readnone</tt> functions never change any state visible to their
-caller.
-
-<dt><tt>readonly</tt></dt>
-<dd>This function attribute indicates that the function has no side-effects on
-the calling function, but that it depends on state (memory state, control
-register state, etc) that may be set in the caller. A readonly function always
-returns the same value (or throws the same exception) whenever it is called with
-a particular set of arguments and global state.</dd>
+<dd>This attribute indicates that the function computes its result (or decides to
+unwind an exception) based strictly on its arguments, without dereferencing any
+pointer arguments or otherwise accessing any mutable state (e.g. memory, control
+registers, etc) visible to caller functions. It does not write through any
+pointer arguments (including <tt><a href="#byval">byval</a></tt> arguments) and
+never changes any state visible to callers. This means that it cannot unwind
+exceptions by calling the <tt>C++</tt> exception throwing methods, but could
+use the <tt>unwind</tt> instruction.</dd>
+
+<dt><tt><a name="readonly">readonly</a></tt></dt>
+<dd>This attribute indicates that the function does not write through any
+pointer arguments (including <tt><a href="#byval">byval</a></tt> arguments)
+or otherwise modify any state (e.g. memory, control registers, etc) visible to
+caller functions. It may dereference pointer arguments and read state that may
+be set in the caller. A readonly function always returns the same value (or
+unwinds an exception identically) when called with the same set of arguments
+and global state. It cannot unwind an exception by calling the <tt>C++</tt>
+exception throwing methods, but may use the <tt>unwind</tt> instruction.</dd>
+
+<dt><tt><a name="ssp">ssp</a></tt></dt>
+<dd>This attribute indicates that the function should emit a stack smashing
+protector. It is in the form of a "canary"—a random value placed on the
+stack before the local variables that's checked upon return from the function to
+see if it has been overwritten. A heuristic is used to determine if a function
+needs stack protectors or not.
+
+<br><br>If a function that has an <tt>ssp</tt> attribute is inlined into a function
+that doesn't have an <tt>ssp</tt> attribute, then the resulting function will
+have an <tt>ssp</tt> attribute.</dd>
+
+<dt><tt>sspreq</tt></dt>
+<dd>This attribute indicates that the function should <em>always</em> emit a
+stack smashing protector. This overrides the <tt><a href="#ssp">ssp</a></tt>
+function attribute.
+
+If a function that has an <tt>sspreq</tt> attribute is inlined into a
+function that doesn't have an <tt>sspreq</tt> attribute or which has
+an <tt>ssp</tt> attribute, then the resulting function will have
+an <tt>sspreq</tt> attribute.</dd>
+
+<dt><tt>noredzone</tt></dt>
+<dd>This attribute indicates that the code generator should not use a
+red zone, even if the target-specific ABI normally permits it.
+</dd>
+
+<dt><tt>noimplicitfloat</tt></dt>
+<dd>This attributes disables implicit floating point instructions.</dd>
+
+<dt><tt>naked</tt></dt>
+<dd>This attribute disables prologue / epilogue emission for the function.
+This can have very system-specific consequences.</dd>
</dl>
<dt><tt>a<i>size</i>:<i>abi</i>:<i>pref</i></tt></dt>
<dd>This specifies the alignment for an aggregate type of a given bit
<i>size</i>.</dd>
+ <dt><tt>s<i>size</i>:<i>abi</i>:<i>pref</i></tt></dt>
+ <dd>This specifies the alignment for a stack object of a given bit
+ <i>size</i>.</dd>
</dl>
<p>When constructing the data layout for a given target, LLVM starts with a
default set of specifications which are then (possibly) overriden by the
<li><tt>v64:64:64</tt> - 64-bit vector is 64-bit aligned</li>
<li><tt>v128:128:128</tt> - 128-bit vector is 128-bit aligned</li>
<li><tt>a0:0:1</tt> - aggregates are 8-bit aligned</li>
+ <li><tt>s0:64:64</tt> - stack objects are 64-bit aligned</li>
</ul>
<p>When LLVM is determining the alignment for a given type, it uses the
-following rules:
+following rules:</p>
<ol>
<li>If the type sought is an exact match for one of the specifications, that
specification is used.</li>
i65 and i256 will use the alignment of i64 (largest specified).</li>
<li>If no match is found, and the type sought is a vector type, then the
largest vector type that is smaller than the sought vector type will be used
- as a fall back. This happens because <128 x double> can be implemented in
- terms of 64 <2 x double>, for example.</li>
+ as a fall back. This happens because <128 x double> can be implemented
+ in terms of 64 <2 x double>, for example.</li>
</ol>
</div>
<a href="#t_vector">vector</a>,
<a href="#t_struct">structure</a>,
<a href="#t_array">array</a>,
- <a href="#t_label">label</a>.
+ <a href="#t_label">label</a>,
+ <a href="#t_metadata">metadata</a>.
</td>
</tr>
<tr>
<td><a href="#t_primitive">primitive</a></td>
<td><a href="#t_label">label</a>,
<a href="#t_void">void</a>,
- <a href="#t_floating">floating point</a>.</td>
+ <a href="#t_floating">floating point</a>,
+ <a href="#t_metadata">metadata</a>.</td>
</tr>
<tr>
<td><a href="#t_derived">derived</a></td>
<a href="#t_pstruct">packed structure</a>,
<a href="#t_vector">vector</a>,
<a href="#t_opaque">opaque</a>.
+ </td>
</tr>
</tbody>
</table>
</pre>
</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection"> <a name="t_metadata">Metadata Type</a> </div>
+
+<div class="doc_text">
+<h5>Overview:</h5>
+<p>The metadata type represents embedded metadata. The only derived type that
+may contain metadata is <tt>metadata*</tt> or a function type that returns or
+takes metadata typed parameters, but not pointer to metadata types.</p>
+
+<h5>Syntax:</h5>
+
+<pre>
+ metadata
+</pre>
+</div>
+
<!-- ======================================================================= -->
<div class="doc_subsection"> <a name="t_derived">Derived Types</a> </div>
<h5>Examples:</h5>
<table class="layout">
- <tbody>
- <tr>
- <td><tt>i1</tt></td>
- <td>a single-bit integer.</td>
- </tr><tr>
- <td><tt>i32</tt></td>
- <td>a 32-bit integer.</td>
- </tr><tr>
- <td><tt>i1942652</tt></td>
- <td>a really big integer of over 1 million bits.</td>
+ <tr class="layout">
+ <td class="left"><tt>i1</tt></td>
+ <td class="left">a single-bit integer.</td>
+ </tr>
+ <tr class="layout">
+ <td class="left"><tt>i32</tt></td>
+ <td class="left">a 32-bit integer.</td>
+ </tr>
+ <tr class="layout">
+ <td class="left"><tt>i1942652</tt></td>
+ <td class="left">a really big integer of over 1 million bits.</td>
</tr>
- </tbody>
</table>
+
+<p>Note that the code generator does not yet support large integer types
+to be used as function return types. The specific limit on how large a
+return type the code generator can currently handle is target-dependent;
+currently it's often 64 bits for 32-bit targets and 128 bits for 64-bit
+targets.</p>
+
</div>
<!-- _______________________________________________________________________ -->
length. This allows implementation of 'pascal style arrays' with the LLVM
type "{ i32, [0 x float]}", for example.</p>
+<p>Note that the code generator does not yet support large aggregate types
+to be used as function return types. The specific limit on how large an
+aggregate return type the code generator can currently handle is
+target-dependent, and also dependent on the aggregate element types.</p>
+
</div>
<!-- _______________________________________________________________________ -->
</td>
</tr><tr class="layout">
<td class="left"><tt>{i32, i32} (i32)</tt></td>
- <td class="left">A function taking an <tt>i32></tt>, returning two
- <tt> i32 </tt> values as an aggregate of type <tt>{ i32, i32 }</tt>
+ <td class="left">A function taking an <tt>i32</tt>, returning two
+ <tt>i32</tt> values as an aggregate of type <tt>{ i32, i32 }</tt>
</td>
</tr>
</table>
an <tt>i32</tt>.</td>
</tr>
</table>
+
+<p>Note that the code generator does not yet support large aggregate types
+to be used as function return types. The specific limit on how large an
+aggregate return type the code generator can currently handle is
+target-dependent, and also dependent on the aggregate element types.</p>
+
</div>
<!-- _______________________________________________________________________ -->
an optional address space attribute defining the target-specific numbered
address space where the pointed-to object resides. The default address space is
zero.</p>
+
+<p>Note that LLVM does not permit pointers to void (<tt>void*</tt>) nor does
+it permit pointers to labels (<tt>label*</tt>). Use <tt>i8*</tt> instead.</p>
+
<h5>Syntax:</h5>
<pre> <type> *<br></pre>
<h5>Examples:</h5>
<table class="layout">
<tr class="layout">
- <td class="left"><tt>[4x i32]*</tt></td>
+ <td class="left"><tt>[4 x i32]*</tt></td>
<td class="left">A <a href="#t_pointer">pointer</a> to <a
href="#t_array">array</a> of four <tt>i32</tt> values.</td>
</tr>
<td class="left">Vector of 2 64-bit integer values.</td>
</tr>
</table>
+
+<p>Note that the code generator does not yet support large vector types
+to be used as function return types. The specific limit on how large a
+vector return type codegen can currently handle is target-dependent;
+currently it's often a few times longer than a hardware vector register.</p>
+
</div>
<!-- _______________________________________________________________________ -->
</table>
</div>
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="t_uprefs">Type Up-references</a>
+</div>
+
+<div class="doc_text">
+<h5>Overview:</h5>
+<p>
+An "up reference" allows you to refer to a lexically enclosing type without
+requiring it to have a name. For instance, a structure declaration may contain a
+pointer to any of the types it is lexically a member of. Example of up
+references (with their equivalent as named type declarations) include:</p>
+
+<pre>
+ { \2 * } %x = type { %x* }
+ { \2 }* %y = type { %y }*
+ \1* %z = type %z*
+</pre>
+
+<p>
+An up reference is needed by the asmprinter for printing out cyclic types when
+there is no declared name for a type in the cycle. Because the asmprinter does
+not want to print out an infinite type string, it needs a syntax to handle
+recursive types that have no names (all names are optional in llvm IR).
+</p>
+
+<h5>Syntax:</h5>
+<pre>
+ \<level>
+</pre>
+
+<p>
+The level is the count of the lexical type that is being referred to.
+</p>
+
+<h5>Examples:</h5>
+
+<table class="layout">
+ <tr class="layout">
+ <td class="left"><tt>\1*</tt></td>
+ <td class="left">Self-referential pointer.</td>
+ </tr>
+ <tr class="layout">
+ <td class="left"><tt>{ { \3*, i8 }, i32 }</tt></td>
+ <td class="left">Recursive structure where the upref refers to the out-most
+ structure.</td>
+ </tr>
+</table>
+</div>
+
<!-- *********************************************************************** -->
<div class="doc_section"> <a name="constants">Constants</a> </div>
</dl>
-<p>The one non-intuitive notation for constants is the optional hexadecimal form
+<p>The one non-intuitive notation for constants is the 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
+decimal floating point number in a reasonable number of digits. 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>
-
+<p>When using the hexadecimal form, constants of types float and double are
+represented using the 16-digit form shown above (which matches the IEEE754
+representation for double); float values must, however, be exactly representable
+as IEE754 single precision.
+Hexadecimal format is always used for long
+double, and there are three forms of long double. The 80-bit
+format used by x86 is represented as <tt>0xK</tt>
+followed by 20 hexadecimal digits.
+The 128-bit format used by PowerPC (two adjacent doubles) is represented
+by <tt>0xM</tt> followed by 32 hexadecimal digits. The IEEE 128-bit
+format is represented
+by <tt>0xL</tt> followed by 32 hexadecimal digits; no currently supported
+target uses this format. Long doubles will only work if they match
+the long double format on your target. All hexadecimal formats are big-endian
+(sign bit at the left).</p>
</div>
<!-- ======================================================================= -->
-<div class="doc_subsection"><a name="aggregateconstants">Aggregate Constants</a>
+<div class="doc_subsection">
+<a name="aggregateconstants"> <!-- old anchor -->
+<a name="complexconstants">Complex Constants</a></a>
</div>
<div class="doc_text">
-<p>Aggregate constants arise from aggregation of simple constants
-and smaller aggregate constants.</p>
+<p>Complex constants are a (potentially recursive) combination of simple
+constants and smaller complex constants.</p>
<dl>
<dt><b>Structure constants</b></dt>
large arrays) and is always exactly equivalent to using explicit zero
initializers.
</dd>
+
+ <dt><b>Metadata node</b></dt>
+
+ <dd>A metadata node is a structure-like constant with
+ <a href="#t_metadata">metadata type</a>. For example:
+ "<tt>metadata !{ i32 0, metadata !"test" }</tt>". Unlike other constants
+ that are meant to be interpreted as part of the instruction stream, metadata
+ is a place to attach additional information such as debug info.
+ </dd>
</dl>
</div>
<i>really</i> dangerous!</dd>
<dt><b><tt>bitcast ( CST to TYPE )</tt></b></dt>
- <dd>Convert a constant, CST, to another TYPE. The size of CST and TYPE must be
- identical (same number of bits). The conversion is done as if the CST value
- was stored to memory and read back as TYPE. In other words, no bits change
- with this operator, just the type. This can be used for conversion of
- vector types to any other type, as long as they have the same bit width. For
- pointers it is only valid to cast to another pointer type. It is not valid
- to bitcast to or from an aggregate type.
- </dd>
+ <dd>Convert a constant, CST, to another TYPE. The constraints of the operands
+ are the same as those for the <a href="#i_bitcast">bitcast
+ instruction</a>.</dd>
<dt><b><tt>getelementptr ( CSTPTR, IDX0, IDX1, ... )</tt></b></dt>
<dt><b><tt>fcmp COND ( VAL1, VAL2 )</tt></b></dt>
<dd>Performs the <a href="#i_fcmp">fcmp operation</a> on constants.</dd>
- <dt><b><tt>vicmp COND ( VAL1, VAL2 )</tt></b></dt>
- <dd>Performs the <a href="#i_vicmp">vicmp operation</a> on constants.</dd>
-
- <dt><b><tt>vfcmp COND ( VAL1, VAL2 )</tt></b></dt>
- <dd>Performs the <a href="#i_vfcmp">vfcmp operation</a> on constants.</dd>
-
<dt><b><tt>extractelement ( VAL, IDX )</tt></b></dt>
<dd>Perform the <a href="#i_extractelement">extractelement
- operation</a> on constants.
+ operation</a> on constants.</dd>
<dt><b><tt>insertelement ( VAL, ELT, IDX )</tt></b></dt>
</dl>
</div>
+<!-- ======================================================================= -->
+<div class="doc_subsection"><a name="metadata">Embedded Metadata</a>
+</div>
+
+<div class="doc_text">
+
+<p>Embedded metadata provides a way to attach arbitrary data to the
+instruction stream without affecting the behaviour of the program. There are
+two metadata primitives, strings and nodes. All metadata has the
+<tt>metadata</tt> type and is identified in syntax by a preceding exclamation
+point ('<tt>!</tt>').
+</p>
+
+<p>A metadata string is a string surrounded by double quotes. It can contain
+any character by escaping non-printable characters with "\xx" where "xx" is
+the two digit hex code. For example: "<tt>!"test\00"</tt>".
+</p>
+
+<p>Metadata nodes are represented with notation similar to structure constants
+(a comma separated list of elements, surrounded by braces and preceeded by an
+exclamation point). For example: "<tt>!{ metadata !"test\00", i32 10}</tt>".
+</p>
+
+<p>A metadata node will attempt to track changes to the values it holds. In
+the event that a value is deleted, it will be replaced with a typeless
+"<tt>null</tt>", such as "<tt>metadata !{null, i32 10}</tt>".</p>
+
+<p>Optimizations may rely on metadata to provide additional information about
+the program that isn't available in the instructions, or that isn't easily
+computable. Similarly, the code generator may expect a certain metadata format
+to be used to express debugging information.</p>
+</div>
+
<!-- *********************************************************************** -->
<div class="doc_section"> <a name="othervalues">Other Values</a> </div>
<!-- *********************************************************************** -->
<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).
+need to be documented). This is probably best done by reference to another
+document that covers inline asm from a holistic perspective.
</p>
</div>
Instruction</a> </div>
<div class="doc_text">
<h5>Syntax:</h5>
-<pre> ret <type> <value> <i>; Return a value from a non-void function</i>
+<pre>
+ ret <type> <value> <i>; Return a value from a non-void function</i>
ret void <i>; Return from void function</i>
- ret <type> <value>, <type> <value> <i>; Return two values from a non-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>The '<tt>ret</tt>' instruction is used to return control flow (and
+optionally a value) from a function back to the caller.</p>
<p>There are two forms of the '<tt>ret</tt>' instruction: one that
-returns value(s) and then causes control flow, and one that just causes
+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 zero, one or multiple values.
-The type of each return value must be a '<a href="#t_firstclass">first
-class</a>' type. Note 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 values that do not match the return type of the
-function.</p>
+<p>The '<tt>ret</tt>' instruction optionally accepts a single argument,
+the return value. The type of the return value must be a
+'<a href="#t_firstclass">first class</a>' type.</p>
+
+<p>A function is not <a href="#wellformed">well formed</a> if
+it it has a non-void return type and contains a '<tt>ret</tt>'
+instruction with no return value or a return value with a type that
+does not match its type, or if it has a void return type and contains
+a '<tt>ret</tt>' instruction with a return value.</p>
<h5>Semantics:</h5>
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. If the instruction returns multiple values then these
-values can only be accessed through a '<a href="#i_getresult"><tt>getresult</tt>
-</a>' instruction.</p>
+return value.</p>
<h5>Example:</h5>
<pre>
ret i32 5 <i>; Return an integer value of 5</i>
ret void <i>; Return from a void function</i>
- ret i32 4, i8 2 <i>; Return two values 4 and 2 </i>
+ ret { i32, i8 } { i32 4, i8 2 } <i>; Return a struct of values 4 and 2</i>
</pre>
+
+<p>Note that the code generator does not yet fully support large
+ return values. The specific sizes that are currently supported are
+ dependent on the target. For integers, on 32-bit targets the limit
+ is often 64 bits, and on 64-bit targets the limit is often 128 bits.
+ For aggregate types, the current limits are dependent on the element
+ types; for example targets are often limited to 2 total integer
+ elements and 2 total floating-point elements.</p>
+
</div>
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection"> <a name="i_br">'<tt>br</tt>' Instruction</a> </div>
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_icmp">icmp</a> eq, i32 %a, %b<br> br i1 %cond, label %IfEqual, label %IfUnequal<br>IfEqual:<br> <a
+<pre>Test:<br> %cond = <a href="#i_icmp">icmp</a> eq i32 %a, %b<br> br i1 %cond, label %IfEqual, label %IfUnequal<br>IfEqual:<br> <a
href="#i_ret">ret</a> i32 1<br>IfUnequal:<br> <a href="#i_ret">ret</a> i32 0<br></pre>
</div>
<!-- _______________________________________________________________________ -->
<pre>
<i>; Emulate a conditional br instruction</i>
%Val = <a href="#i_zext">zext</a> i1 %value to i32
- switch i32 %Val, label %truedest [i32 0, label %falsedest ]
+ switch i32 %Val, label %truedest [ i32 0, label %falsedest ]
<i>; Emulate an unconditional br instruction</i>
switch i32 0, label %dest [ ]
<i>; Implement a jump table:</i>
- switch i32 %val, label %otherwise [ i32 0, label %onzero
- i32 1, label %onone
- i32 2, label %ontwo ]
+ switch i32 %val, label %otherwise [ i32 0, label %onzero
+ i32 1, label %onone
+ i32 2, label %ontwo ]
</pre>
</div>
<h5>Syntax:</h5>
<pre>
- <result> = invoke [<a href="#callingconv">cconv</a>] <ptr to function ty> <function ptr val>(<function args>)
+ <result> = invoke [<a href="#callingconv">cconv</a>] [<a href="#paramattrs">ret attrs</a>] <ptr to function ty> <function ptr val>(<function args>) [<a href="#fnattrs">fn attrs</a>]
to label <normal label> unwind label <exception label>
</pre>
"<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. If the callee function
-returns multiple values then individual return values are only accessible through
-a '<tt><a href="#i_getresult">getresult</a></tt>' instruction.</p>
+continued at the dynamically nearest "exception" label.</p>
<h5>Arguments:</h5>
convention</a> the call should use. If none is specified, the call defaults
to using C calling conventions.
</li>
+
+ <li>The optional <a href="#paramattrs">Parameter Attributes</a> list for
+ return values. Only '<tt>zeroext</tt>', '<tt>signext</tt>',
+ and '<tt>inreg</tt>' attributes are valid here.</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
<li>'<tt>exception label</tt>': the label reached when a callee returns with
the <a href="#i_unwind"><tt>unwind</tt></a> instruction. </li>
+ <li>The optional <a href="#fnattrs">function attributes</a> list. Only
+ '<tt>noreturn</tt>', '<tt>nounwind</tt>', '<tt>readonly</tt>' and
+ '<tt>readnone</tt>' attributes are valid here.</li>
</ol>
<h5>Semantics:</h5>
exception. Additionally, this is important for implementation of
'<tt>catch</tt>' clauses in high-level languages that support them.</p>
+<p>For the purposes of the SSA form, the definition of the value
+returned by the '<tt>invoke</tt>' instruction is deemed to occur on
+the edge from the current block to the "normal" label. If the callee
+unwinds then no return value is available.</p>
+
<h5>Example:</h5>
<pre>
%retval = invoke i32 @Test(i32 15) to label %Continue
<h5>Arguments:</h5>
<p>The two arguments to the '<tt>add</tt>' instruction must be <a
- href="#t_integer">integer</a>, <a href="#t_floating">floating point</a>, or
- <a href="#t_vector">vector</a> values. Both arguments must have identical
- types.</p>
+ href="#t_integer">integer</a> or
+ <a href="#t_vector">vector</a> of integer 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>
+<p>The value produced is the integer sum of the two operands.</p>
-<p>If an integer sum has unsigned overflow, the result returned is the
+<p>If the sum has unsigned overflow, the result returned is the
mathematical result modulo 2<sup>n</sup>, where n is the bit width of
the result.</p>
</pre>
</div>
<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_fadd">'<tt>fadd</tt>' Instruction</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+
+<pre>
+ <result> = fadd <ty> <op1>, <op2> <i>; yields {ty}:result</i>
+</pre>
+
+<h5>Overview:</h5>
+
+<p>The '<tt>fadd</tt>' instruction returns the sum of its two operands.</p>
+
+<h5>Arguments:</h5>
+
+<p>The two arguments to the '<tt>fadd</tt>' instruction must be
+<a href="#t_floating">floating point</a> or <a href="#t_vector">vector</a> of
+floating point values. Both arguments must have identical types.</p>
+
+<h5>Semantics:</h5>
+
+<p>The value produced is the floating point sum of the two operands.</p>
+
+<h5>Example:</h5>
+
+<pre>
+ <result> = fadd float 4.0, %var <i>; yields {float}:result = 4.0 + %var</i>
+</pre>
+</div>
+<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection">
<a name="i_sub">'<tt>sub</tt>' Instruction</a>
</div>
<h5>Arguments:</h5>
<p>The two arguments to the '<tt>sub</tt>' instruction must be <a
- href="#t_integer">integer</a>, <a href="#t_floating">floating point</a>,
- or <a href="#t_vector">vector</a> values. Both arguments must have identical
- types.</p>
+ href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of
+ integer 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>
+<p>The value produced is the integer difference of the two operands.</p>
-<p>If an integer difference has unsigned overflow, the result returned is the
+<p>If the difference has unsigned overflow, the result returned is the
mathematical result modulo 2<sup>n</sup>, where n is the bit width of
the result.</p>
</pre>
</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_fsub">'<tt>fsub</tt>' Instruction</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+
+<pre>
+ <result> = fsub <ty> <op1>, <op2> <i>; yields {ty}:result</i>
+</pre>
+
+<h5>Overview:</h5>
+
+<p>The '<tt>fsub</tt>' instruction returns the difference of its two
+operands.</p>
+
+<p>Note that the '<tt>fsub</tt>' instruction is used to represent the
+'<tt>fneg</tt>' instruction present in most other intermediate
+representations.</p>
+
+<h5>Arguments:</h5>
+
+<p>The two arguments to the '<tt>fsub</tt>' instruction must be <a
+ <a href="#t_floating">floating point</a> or <a href="#t_vector">vector</a>
+ of floating point values. Both arguments must have identical types.</p>
+
+<h5>Semantics:</h5>
+
+<p>The value produced is the floating point difference of the two operands.</p>
+
+<h5>Example:</h5>
+<pre>
+ <result> = fsub float 4.0, %var <i>; yields {float}:result = 4.0 - %var</i>
+ <result> = fsub float -0.0, %val <i>; yields {float}:result = -%var</i>
+</pre>
+</div>
+
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection">
<a name="i_mul">'<tt>mul</tt>' Instruction</a>
<h5>Arguments:</h5>
<p>The two arguments to the '<tt>mul</tt>' instruction must be <a
-href="#t_integer">integer</a>, <a href="#t_floating">floating point</a>,
-or <a href="#t_vector">vector</a> values. Both arguments must have identical
-types.</p>
+href="#t_integer">integer</a> or <a href="#t_vector">vector</a> of integer
+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>The value produced is the integer product of the two operands.</p>
-<p>If the result of an integer multiplication has unsigned overflow,
+<p>If the result of the multiplication has unsigned overflow,
the result returned is the mathematical result modulo
2<sup>n</sup>, where n is the bit width of the result.</p>
<p>Because LLVM integers use a two's complement representation, and the
</pre>
</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="i_fmul">'<tt>fmul</tt>' Instruction</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+<pre> <result> = fmul <ty> <op1>, <op2> <i>; yields {ty}:result</i>
+</pre>
+<h5>Overview:</h5>
+<p>The '<tt>fmul</tt>' instruction returns the product of its two
+operands.</p>
+
+<h5>Arguments:</h5>
+
+<p>The two arguments to the '<tt>fmul</tt>' instruction must be
+<a href="#t_floating">floating point</a> or <a href="#t_vector">vector</a>
+of floating point values. Both arguments must have identical types.</p>
+
+<h5>Semantics:</h5>
+
+<p>The value produced is the floating point product of the two operands.</p>
+
+<h5>Example:</h5>
+<pre> <result> = fmul float 4.0, %var <i>; yields {float}:result = 4.0 * %var</i>
+</pre>
+</div>
+
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection"> <a name="i_udiv">'<tt>udiv</tt>' Instruction
</a></div>
<p>The value produced is <tt>op1</tt> * 2<sup><tt>op2</tt></sup> mod 2<sup>n</sup>,
where n is the width of the result. If <tt>op2</tt> is (statically or dynamically) negative or
-equal to or larger than the number of bits in <tt>op1</tt>, the result is undefined.</p>
+equal to or larger than the number of bits in <tt>op1</tt>, the result is undefined.
+If the arguments are vectors, each vector element of <tt>op1</tt> is shifted by the
+corresponding shift amount in <tt>op2</tt>.</p>
<h5>Example:</h5><pre>
<result> = shl i32 4, %var <i>; yields {i32}: 4 << %var</i>
<result> = shl i32 4, 2 <i>; yields {i32}: 16</i>
<result> = shl i32 1, 10 <i>; yields {i32}: 1024</i>
<result> = shl i32 1, 32 <i>; undefined</i>
+ <result> = shl <2 x i32> < i32 1, i32 1>, < i32 1, i32 2> <i>; yields: result=<2 x i32> < i32 2, i32 4></i>
</pre>
</div>
<!-- _______________________________________________________________________ -->
<p>This instruction always performs a logical shift right operation. The most
significant bits of the result will be filled with zero bits after the
shift. If <tt>op2</tt> is (statically or dynamically) equal to or larger than
-the number of bits in <tt>op1</tt>, the result is undefined.</p>
+the number of bits in <tt>op1</tt>, the result is undefined. If the arguments are
+vectors, each vector element of <tt>op1</tt> is shifted by the corresponding shift
+amount in <tt>op2</tt>.</p>
<h5>Example:</h5>
<pre>
<result> = lshr i8 4, 3 <i>; yields {i8}:result = 0</i>
<result> = lshr i8 -2, 1 <i>; yields {i8}:result = 0x7FFFFFFF </i>
<result> = lshr i32 1, 32 <i>; undefined</i>
+ <result> = lshr <2 x i32> < i32 -2, i32 4>, < i32 1, i32 2> <i>; yields: result=<2 x i32> < i32 0x7FFFFFFF, i32 1></i>
</pre>
</div>
<p>This instruction always performs an arithmetic shift right operation,
The most significant bits of the result will be filled with the sign bit
of <tt>op1</tt>. If <tt>op2</tt> is (statically or dynamically) equal to or
-larger than the number of bits in <tt>op1</tt>, the result is undefined.
-</p>
+larger than the number of bits in <tt>op1</tt>, the result is undefined. If the
+arguments are vectors, each vector element of <tt>op1</tt> is shifted by the
+corresponding shift amount in <tt>op2</tt>.</p>
<h5>Example:</h5>
<pre>
<result> = ashr i8 4, 3 <i>; yields {i8}:result = 0</i>
<result> = ashr i8 -2, 1 <i>; yields {i8}:result = -1</i>
<result> = ashr i32 1, 32 <i>; undefined</i>
+ <result> = ashr <2 x i32> < i32 -2, i32 4>, < i32 1, i32 3> <i>; yields: result=<2 x i32> < i32 -1, i32 0></i>
</pre>
</div>
<h5>Syntax:</h5>
<pre>
- <result> = shufflevector <n x <ty>> <v1>, <n x <ty>> <v2>, <n x i32> <mask> <i>; yields <n x <ty>></i>
+ <result> = shufflevector <n x <ty>> <v1>, <n x <ty>> <v2>, <m x i32> <mask> <i>; yields <m 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.
+from two input vectors, returning a vector with the same element type as
+the input and length that is the same as the shuffle mask.
</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 'i32'.
+The first two operands of a '<tt>shufflevector</tt>' instruction are vectors
+with types that match each other. The third argument is a shuffle mask whose
+element type is always 'i32'. The result of the instruction is a vector whose
+length is the same as the shuffle mask and whose element type is the same as
+the element type of the first two operands.
</p>
<p>
<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
+the result vector, which element of the two input vectors 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>
<4 x i32> <i32 0, i32 4, i32 1, i32 5> <i>; yields <4 x i32></i>
%result = shufflevector <4 x i32> %v1, <4 x i32> undef,
<4 x i32> <i32 0, i32 1, i32 2, i32 3> <i>; yields <4 x i32></i> - Identity shuffle.
+ %result = shufflevector <8 x i32> %v1, <8 x i32> undef,
+ <4 x i32> <i32 0, i32 1, i32 2, i32 3> <i>; yields <4 x i32></i>
+ %result = shufflevector <4 x i32> %v1, <4 x i32> %v2,
+ <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7 > <i>; yields <8 x i32></i>
</pre>
</div>
'<tt><a href="#i_getelementptr">getelementptr</a></tt>' instruction.
The value to insert must have the same type as the value identified
by the indices.
+</p>
<h5>Semantics:</h5>
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, otherwise "NumElements" is defaulted to be one.
-If a constant 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>
+If a constant 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
+compatible with the type.</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. The result of a zero byte allocattion is undefined. The
+a pointer is returned. The result of a zero byte allocation is undefined. The
result is null if there is insufficient memory available.</p>
<h5>Example:</h5>
<pre>
- %array = malloc [4 x i8 ] <i>; yields {[%4 x i8]*}:array</i>
+ %array = malloc [4 x i8] <i>; yields {[%4 x i8]*}:array</i>
%size = <a href="#i_add">add</a> i32 2, 2 <i>; yields {i32}:size = i32 4</i>
%array1 = malloc i8, i32 4 <i>; yields {i8*}:array1</i>
%array3 = malloc i32, i32 4, align 1024 <i>; yields {i32*}:array3</i>
%array4 = malloc i32, align 1024 <i>; yields {i32*}:array4</i>
</pre>
+
+<p>Note that the code generator does not yet respect the
+ alignment value.</p>
+
</div>
<!-- _______________________________________________________________________ -->
<h5>Syntax:</h5>
<pre>
- free <type> <value> <i>; yields {void}</i>
+ free <type> <value> <i>; yields {void}</i>
</pre>
<h5>Overview:</h5>
<h5>Example:</h5>
<pre>
- %array = <a href="#i_malloc">malloc</a> [4 x i8] <i>; yields {[4 x i8]*}:array</i>
+ %array = <a href="#i_malloc">malloc</a> [4 x i8] <i>; yields {[4 x i8]*}:array</i>
free [4 x i8]* %array
</pre>
</div>
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, otherwise "NumElements" is defaulted to be one.
-If a constant 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>
+If a constant 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
+compatible with the type.</p>
<p>'<tt>type</tt>' may be any sized type.</p>
<h5>Semantics:</h5>
-<p>Memory is allocated; a pointer is returned. The operation is undefiend if
+<p>Memory is allocated; a pointer is returned. The operation is undefined if
there is insufficient stack space for the allocation. '<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
<h5>Example:</h5>
<pre>
- %ptr = alloca i32 <i>; yields {i32*}:ptr</i>
- %ptr = alloca i32, i32 4 <i>; yields {i32*}:ptr</i>
- %ptr = alloca i32, i32 4, align 1024 <i>; yields {i32*}:ptr</i>
- %ptr = alloca i32, align 1024 <i>; yields {i32*}:ptr</i>
+ %ptr = alloca i32 <i>; yields {i32*}:ptr</i>
+ %ptr = alloca i32, i32 4 <i>; yields {i32*}:ptr</i>
+ %ptr = alloca i32, i32 4, align 1024 <i>; yields {i32*}:ptr</i>
+ %ptr = alloca i32, align 1024 <i>; yields {i32*}:ptr</i>
</pre>
</div>
safe.
</p>
<h5>Semantics:</h5>
-<p>The location of memory pointed to is loaded.</p>
+<p>The location of memory pointed to is loaded. If the value being loaded
+is of scalar type then the number of bytes read does not exceed the minimum
+number of bytes needed to hold all bits of the type. For example, loading an
+<tt>i24</tt> reads at most three bytes. When loading a value of a type like
+<tt>i20</tt> with a size that is not an integral number of bytes, the result
+is undefined if the value was not originally written using a store of the
+same type.</p>
<h5>Examples:</h5>
<pre> %ptr = <a href="#i_alloca">alloca</a> i32 <i>; yields {i32*}:ptr</i>
<a
</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>
+at the location specified by the '<tt><pointer></tt>' operand.
+If '<tt><value></tt>' is of scalar type then the number of bytes
+written does not exceed the minimum number of bytes needed to hold all
+bits of the type. For example, storing an <tt>i24</tt> writes at most
+three bytes. When writing a value of a type like <tt>i20</tt> with a
+size that is not an integral number of bytes, it is unspecified what
+happens to the extra bits that do not belong to the type, but they will
+typically be overwritten.</p>
<h5>Example:</h5>
<pre> %ptr = <a href="#i_alloca">alloca</a> i32 <i>; yields {i32*}:ptr</i>
store i32 3, i32* %ptr <i>; yields {void}</i>
<div class="doc_text">
<h5>Syntax:</h5>
<pre>
- <result> = getelementptr <ty>* <ptrval>{, <ty> <idx>}*
+ <result> = getelementptr <pty>* <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>
+subelement of an aggregate data structure. It performs address calculation only
+and does not access memory.</p>
<h5>Arguments:</h5>
-<p>This instruction takes a list of integer operands 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>i32</tt> integer constants are allowed. When indexing
-into an array or pointer, only integers of 32 or 64 bits are allowed; 32-bit
-values will be sign extended to 64-bits if required.</p>
+<p>The first argument is always a pointer, and forms the basis of the
+calculation. The remaining arguments are indices, that indicate which of the
+elements of the aggregate object are indexed. The interpretation of each index
+is dependent on the type being indexed into. The first index always indexes the
+pointer value given as the first argument, the second index indexes a value of
+the type pointed to (not necessarily the value directly pointed to, since the
+first index can be non-zero), etc. The first type indexed into must be a pointer
+value, subsequent types can be arrays, vectors and structs. Note that subsequent
+types being indexed into can never be pointers, since that would require loading
+the pointer before continuing calculation.</p>
+
+<p>The type of each index argument depends on the type it is indexing into.
+When indexing into a (packed) structure, only <tt>i32</tt> integer
+<b>constants</b> are allowed. When indexing into an array, pointer or vector,
+integers of any width are allowed (also non-constants).</p>
<p>For example, let's consider a C code fragment and how it gets
compiled to LLVM:</p>
<div class="doc_code">
<pre>
-%RT = type { i8 , [10 x [20 x i32]], i8 }
-%ST = type { i32, double, %RT }
+%RT = <a href="#namedtypes">type</a> { i8 , [10 x [20 x i32]], i8 }
+%ST = <a href="#namedtypes">type</a> { i32, double, %RT }
define i32* %foo(%ST* %s) {
entry:
<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 can use a 32-bit or 64-bit
-<a href="#t_integer">integer</a> type but the value will always be sign extended
-to 64-bits. <a href="#t_struct">Structure</a> and <a href="#t_pstruct">packed
-structure</a> types require <tt>i32</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>{ i32, double, %RT
}</tt>' type, a structure. The second index indexes into the third element of
}
</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 rule 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>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 when accessed with an instruction that dereferences the
+pointer (e.g. a load or store instruction). The one exception for
+this rule 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
<pre>
<i>; yields [12 x i8]*:aptr</i>
- %aptr = getelementptr {i32, [12 x i8]}* %sptr, i64 0, i32 1
+ %aptr = getelementptr {i32, [12 x i8]}* %saptr, i64 0, i32 1
+ <i>; yields i8*:vptr</i>
+ %vptr = getelementptr {i32, <2 x i8>}* %svptr, i64 0, i32 1, i32 1
+ <i>; yields i8*:eptr</i>
+ %eptr = getelementptr [12 x i8]* %aptr, i64 0, i32 1
+ <i>; yields i32*:iptr</i>
+ %iptr = getelementptr [10 x i32]* @arr, i16 0, i16 0
</pre>
</div>
<h5>Example:</h5>
<pre>
%X = uitofp i32 257 to float <i>; yields float:257.0</i>
- %Y = uitofp i8 -1 to double <i>; yields double:255.0</i>
+ %Y = uitofp i8 -1 to double <i>; yields double:255.0</i>
</pre>
</div>
<h5>Example:</h5>
<pre>
%X = sitofp i32 257 to float <i>; yields float:257.0</i>
- %Y = sitofp i8 -1 to double <i>; yields double:-1.0</i>
+ %Y = sitofp i8 -1 to double <i>; yields double:-1.0</i>
</pre>
</div>
<h5>Arguments:</h5>
<p>The '<tt>ptrtoint</tt>' instruction takes a <tt>value</tt> to cast, which
must be a <a href="#t_pointer">pointer</a> value, and a type to cast it to
-<tt>ty2</tt>, which must be an <a href="#t_integer">integer</a> type.
+<tt>ty2</tt>, which must be an <a href="#t_integer">integer</a> type.</p>
<h5>Semantics:</h5>
<p>The '<tt>ptrtoint</tt>' instruction converts <tt>value</tt> to integer type
<h5>Arguments:</h5>
<p>The '<tt>inttoptr</tt>' instruction takes an <a href="#t_integer">integer</a>
value to cast, and a type to cast it to, which must be a
-<a href="#t_pointer">pointer</a> type.
+<a href="#t_pointer">pointer</a> type.</p>
<h5>Semantics:</h5>
<p>The '<tt>inttoptr</tt>' instruction converts <tt>value</tt> to type
<pre>
%X = bitcast i8 255 to i8 <i>; yields i8 :-1</i>
%Y = bitcast i32* %x to sint* <i>; yields sint*:%x</i>
- %Z = bitcast <2xint> %V to i64; <i>; yields i64: %V</i>
+ %Z = bitcast <2 x int> %V to i64; <i>; yields i64: %V</i>
</pre>
</div>
</div>
<div class="doc_text">
<h5>Syntax:</h5>
-<pre> <result> = icmp <cond> <ty> <op1>, <op2> <i>; yields {i1} or {<N x i1>}:result</i>
+<pre> <result> = icmp <cond> <ty> <op1>, <op2> <i>; yields {i1} or {<N x i1>}:result</i>
</pre>
<h5>Overview:</h5>
<p>The '<tt>icmp</tt>' instruction returns a boolean value or
<p>The '<tt>icmp</tt>' instruction takes three operands. The first operand is
the condition code indicating the kind of comparison to perform. It is not
a value, just a keyword. The possible condition code are:
+</p>
<ol>
<li><tt>eq</tt>: equal</li>
<li><tt>ne</tt>: not equal </li>
<p>The '<tt>icmp</tt>' compares <tt>op1</tt> and <tt>op2</tt> according to
the condition code given as <tt>cond</tt>. The comparison performed always
yields either an <a href="#t_primitive"><tt>i1</tt></a> or vector of <tt>i1</tt> result, as follows:
+</p>
<ol>
<li><tt>eq</tt>: yields <tt>true</tt> if the operands are equal,
<tt>false</tt> otherwise. No sign interpretation is necessary or performed.
</li>
<li><tt>ne</tt>: yields <tt>true</tt> if the operands are unequal,
- <tt>false</tt> otherwise. No sign interpretation is necessary or performed.
+ <tt>false</tt> otherwise. No sign interpretation is necessary or performed.</li>
<li><tt>ugt</tt>: interprets the operands as unsigned values and yields
<tt>true</tt> if <tt>op1</tt> is greater than <tt>op2</tt>.</li>
<li><tt>uge</tt>: interprets the operands as unsigned values and yields
<result> = icmp ule i16 -4, 5 <i>; yields: result=false</i>
<result> = icmp sge i16 4, 5 <i>; yields: result=false</i>
</pre>
+
+<p>Note that the code generator does not yet support vector types with
+ the <tt>icmp</tt> instruction.</p>
+
</div>
<!-- _______________________________________________________________________ -->
</div>
<div class="doc_text">
<h5>Syntax:</h5>
-<pre> <result> = fcmp <cond> <ty> <op1>, <op2> <i>; yields {i1} or {<N x i1>}:result</i>
+<pre> <result> = fcmp <cond> <ty> <op1>, <op2> <i>; yields {i1} or {<N x i1>}:result</i>
</pre>
<h5>Overview:</h5>
<p>The '<tt>fcmp</tt>' instruction returns a boolean value
or vector of boolean values based on comparison
-of its operands.
+of its operands.</p>
<p>
If the operands are floating point scalars, then the result
type is a boolean (<a href="#t_primitive"><tt>i1</tt></a>).
<h5>Arguments:</h5>
<p>The '<tt>fcmp</tt>' instruction takes three operands. The first operand is
the condition code indicating the kind of comparison to perform. It is not
-a value, just a keyword. The possible condition code are:
+a value, just a keyword. The possible condition code are:</p>
<ol>
<li><tt>false</tt>: no comparison, always returns false</li>
<li><tt>oeq</tt>: ordered and equal</li>
If the operands are vectors, then the vectors are compared
element by element.
Each comparison performed
-always yields an <a href="#t_primitive">i1</a> result, as follows:
+always yields an <a href="#t_primitive">i1</a> result, as follows:</p>
<ol>
<li><tt>false</tt>: always yields <tt>false</tt>, regardless of operands.</li>
<li><tt>oeq</tt>: yields <tt>true</tt> if both operands are not a QNAN and
<result> = fcmp olt float 4.0, 5.0 <i>; yields: result=true</i>
<result> = fcmp ueq double 1.0, 2.0 <i>; yields: result=false</i>
</pre>
-</div>
-<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection">
- <a name="i_vicmp">'<tt>vicmp</tt>' Instruction</a>
-</div>
-<div class="doc_text">
-<h5>Syntax:</h5>
-<pre> <result> = vicmp <cond> <ty> <op1>, <op2> <i>; yields {ty}:result</i>
-</pre>
-<h5>Overview:</h5>
-<p>The '<tt>vicmp</tt>' instruction returns an integer vector value based on
-element-wise comparison of its two integer vector operands.</p>
-<h5>Arguments:</h5>
-<p>The '<tt>vicmp</tt>' instruction takes three operands. The first operand is
-the condition code indicating the kind of comparison to perform. It is not
-a value, just a keyword. The possible condition code are:
-<ol>
- <li><tt>eq</tt>: equal</li>
- <li><tt>ne</tt>: not equal </li>
- <li><tt>ugt</tt>: unsigned greater than</li>
- <li><tt>uge</tt>: unsigned greater or equal</li>
- <li><tt>ult</tt>: unsigned less than</li>
- <li><tt>ule</tt>: unsigned less or equal</li>
- <li><tt>sgt</tt>: signed greater than</li>
- <li><tt>sge</tt>: signed greater or equal</li>
- <li><tt>slt</tt>: signed less than</li>
- <li><tt>sle</tt>: signed less or equal</li>
-</ol>
-<p>The remaining two arguments must be <a href="#t_vector">vector</a> or
-<a href="#t_integer">integer</a> typed. They must also be identical types.</p>
-<h5>Semantics:</h5>
-<p>The '<tt>vicmp</tt>' instruction compares <tt>op1</tt> and <tt>op2</tt>
-according to the condition code given as <tt>cond</tt>. The comparison yields a
-<a href="#t_vector">vector</a> of <a href="#t_integer">integer</a> result, of
-identical type as the values being compared. The most significant bit in each
-element is 1 if the element-wise comparison evaluates to true, and is 0
-otherwise. All other bits of the result are undefined. The condition codes
-are evaluated identically to the <a href="#i_icmp">'<tt>icmp</tt>'
-instruction</a>.
-
-<h5>Example:</h5>
-<pre>
- <result> = vicmp eq <2 x i32> < i32 4, i32 0>, < i32 5, i32 0> <i>; yields: result=<2 x i32> < i32 0, i32 -1 ></i>
- <result> = vicmp ult <2 x i8 > < i8 1, i8 2>, < i8 2, i8 2 > <i>; yields: result=<2 x i8> < i8 -1, i8 0 ></i>
-</pre>
-</div>
-
-<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection">
- <a name="i_vfcmp">'<tt>vfcmp</tt>' Instruction</a>
-</div>
-<div class="doc_text">
-<h5>Syntax:</h5>
-<pre> <result> = vfcmp <cond> <ty> <op1>, <op2></pre>
-<h5>Overview:</h5>
-<p>The '<tt>vfcmp</tt>' instruction returns an integer vector value based on
-element-wise comparison of its two floating point vector operands. The output
-elements have the same width as the input elements.</p>
-<h5>Arguments:</h5>
-<p>The '<tt>vfcmp</tt>' instruction takes three operands. The first operand is
-the condition code indicating the kind of comparison to perform. It is not
-a value, just a keyword. The possible condition code are:
-<ol>
- <li><tt>false</tt>: no comparison, always returns false</li>
- <li><tt>oeq</tt>: ordered and equal</li>
- <li><tt>ogt</tt>: ordered and greater than </li>
- <li><tt>oge</tt>: ordered and greater than or equal</li>
- <li><tt>olt</tt>: ordered and less than </li>
- <li><tt>ole</tt>: ordered and less than or equal</li>
- <li><tt>one</tt>: ordered and not equal</li>
- <li><tt>ord</tt>: ordered (no nans)</li>
- <li><tt>ueq</tt>: unordered or equal</li>
- <li><tt>ugt</tt>: unordered or greater than </li>
- <li><tt>uge</tt>: unordered or greater than or equal</li>
- <li><tt>ult</tt>: unordered or less than </li>
- <li><tt>ule</tt>: unordered or less than or equal</li>
- <li><tt>une</tt>: unordered or not equal</li>
- <li><tt>uno</tt>: unordered (either nans)</li>
- <li><tt>true</tt>: no comparison, always returns true</li>
-</ol>
-<p>The remaining two arguments must be <a href="#t_vector">vector</a> of
-<a href="#t_floating">floating point</a> typed. They must also be identical
-types.</p>
-<h5>Semantics:</h5>
-<p>The '<tt>vfcmp</tt>' instruction compares <tt>op1</tt> and <tt>op2</tt>
-according to the condition code given as <tt>cond</tt>. The comparison yields a
-<a href="#t_vector">vector</a> of <a href="#t_integer">integer</a> result, with
-an identical number of elements as the values being compared, and each element
-having identical with to the width of the floating point elements. The most
-significant bit in each element is 1 if the element-wise comparison evaluates to
-true, and is 0 otherwise. All other bits of the result are undefined. The
-condition codes are evaluated identically to the
-<a href="#i_fcmp">'<tt>fcmp</tt>' instruction</a>.
+<p>Note that the code generator does not yet support vector types with
+ the <tt>fcmp</tt> instruction.</p>
-<h5>Example:</h5>
-<pre>
- <result> = vfcmp oeq <2 x float> < float 4, float 0 >, < float 5, float 0 > <i>; yields: result=<2 x i32> < i32 0, i32 -1 ></i>
- <result> = vfcmp ult <2 x double> < double 1, double 2 >, < double 2, double 2> <i>; yields: result=<2 x i64> < i64 -1, i64 0 ></i>
-</pre>
</div>
<!-- _______________________________________________________________________ -->
block and the PHI instructions: i.e. PHI instructions must be first in
a basic block.</p>
+<p>For the purposes of the SSA form, the use of each incoming value is
+deemed to occur on the edge from the corresponding predecessor block
+to the current block (but after any definition of an '<tt>invoke</tt>'
+instruction's return value on the same edge).</p>
+
<h5>Semantics:</h5>
<p>At runtime, the '<tt>phi</tt>' instruction logically takes on the value
<pre>
<result> = select <i>selty</i> <cond>, <ty> <val1>, <ty> <val2> <i>; yields ty</i>
- <i>selty</i> is either i1 or {<N x i1>}
+ <i>selty</i> is either i1 or {<N x i1>}
</pre>
<h5>Overview:</h5>
<pre>
%X = select i1 true, i8 17, i8 42 <i>; yields i8:17</i>
</pre>
+
+<p>Note that the code generator does not yet support conditions
+ with vector type.</p>
+
</div>
<h5>Syntax:</h5>
<pre>
- <result> = [tail] call [<a href="#callingconv">cconv</a>] <ty> [<fnty>*] <fnptrval>(<param list>)
+ <result> = [tail] call [<a href="#callingconv">cconv</a>] [<a href="#paramattrs">ret attrs</a>] <ty> [<fnty>*] <fnptrval>(<function args>) [<a href="#fnattrs">fn attrs</a>]
</pre>
<h5>Overview:</h5>
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.
+ href="#i_ret"><tt>ret</tt></a> instruction.</p>
</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.
+ to using C calling conventions.</p>
+ </li>
+
+ <li>
+ <p>The optional <a href="#paramattrs">Parameter Attributes</a> list for
+ return values. Only '<tt>zeroext</tt>', '<tt>signext</tt>',
+ and '<tt>inreg</tt>' attributes are valid here.</p>
</li>
+
<li>
<p>'<tt>ty</tt>': the type of the call instruction itself which is also
the type of the return value. Functions that return no value are marked
indicates the function accepts a variable number of arguments, the extra
arguments can be specified.</p>
</li>
+ <li>
+ <p>The optional <a href="#fnattrs">function attributes</a> list. Only
+ '<tt>noreturn</tt>', '<tt>nounwind</tt>', '<tt>readonly</tt>' and
+ '<tt>readnone</tt>' attributes are valid here.</p>
+ </li>
</ol>
<h5>Semantics:</h5>
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. If the callee returns multiple
-values then the return values of the function are only accessible through
-the '<tt><a href="#i_getresult">getresult</a></tt>' instruction.</p>
+function is bound to the result argument.</p>
<h5>Example:</h5>
call void %foo(i8 97 signext)
%struct.A = type { i32, i8 }
- %r = call %struct.A @foo() <i>; yields { 32, i8 }</i>
- %gr = getresult %struct.A %r, 0 <i>; yields i32</i>
- %gr1 = getresult %struct.A %r, 1 <i>; yields i8</i>
+ %r = call %struct.A @foo() <i>; yields { 32, i8 }</i>
+ %gr = extractvalue %struct.A %r, 0 <i>; yields i32</i>
+ %gr1 = extractvalue %struct.A %r, 1 <i>; yields i8</i>
+ %Z = call void @foo() noreturn <i>; indicates that %foo never returns normally</i>
+ %ZZ = call zeroext i32 @bar() <i>; Return value is %zero extended</i>
</pre>
</div>
<p>See the <a href="#int_varargs">variable argument processing</a> section.</p>
-</div>
-
-<!-- _______________________________________________________________________ -->
-<div class="doc_subsubsection">
- <a name="i_getresult">'<tt>getresult</tt>' Instruction</a>
-</div>
-
-<div class="doc_text">
-
-<h5>Syntax:</h5>
-<pre>
- <resultval> = getresult <type> <retval>, <index>
-</pre>
-
-<h5>Overview:</h5>
-
-<p> The '<tt>getresult</tt>' instruction is used to extract individual values
-from a '<tt><a href="#i_call">call</a></tt>'
-or '<tt><a href="#i_invoke">invoke</a></tt>' instruction that returns multiple
-results.</p>
-
-<h5>Arguments:</h5>
-
-<p>The '<tt>getresult</tt>' instruction takes a call or invoke value as its
-first argument, or an undef value. The value must have <a
-href="#t_struct">structure type</a>. The second argument is a constant
-unsigned index value which must be in range for the number of values returned
-by the call.</p>
-
-<h5>Semantics:</h5>
-
-<p>The '<tt>getresult</tt>' instruction extracts the element identified by
-'<tt>index</tt>' from the aggregate value.</p>
-
-<h5>Example:</h5>
-
-<pre>
- %struct.A = type { i32, i8 }
-
- %r = call %struct.A @foo()
- %gr = getresult %struct.A %r, 0 <i>; yields i32:%gr</i>
- %gr1 = getresult %struct.A %r, 1 <i>; yields i8:%gr1</i>
- add i32 %gr, 42
- add i8 %gr1, 41
-</pre>
+<p>Note that the code generator does not yet fully support va_arg
+ on many targets. Also, it does not currently support va_arg with
+ aggregate types on any target.</p>
</div>
<h5>Syntax:</h5>
<pre> declare void %llvm.va_start(i8* <arglist>)<br></pre>
<h5>Overview:</h5>
-<P>The '<tt>llvm.va_start</tt>' intrinsic initializes
+<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>
+<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>
+<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 to which the argument points, so that the next call to
<tt>va_arg</tt> will produce the first variable argument passed to the function.
<div class="doc_text">
<h5>Syntax:</h5>
+<p>This is an overloaded intrinsic. You can use llvm.memcpy on any integer bit
+width. Not all targets support all bit widths however.</p>
<pre>
+ declare void @llvm.memcpy.i8(i8 * <dest>, i8 * <src>,
+ i8 <len>, i32 <align>)
+ declare void @llvm.memcpy.i16(i8 * <dest>, i8 * <src>,
+ i16 <len>, i32 <align>)
declare void @llvm.memcpy.i32(i8 * <dest>, i8 * <src>,
i32 <len>, i32 <align>)
declare void @llvm.memcpy.i64(i8 * <dest>, i8 * <src>,
<div class="doc_text">
<h5>Syntax:</h5>
+<p>This is an overloaded intrinsic. You can use llvm.memmove on any integer bit
+width. Not all targets support all bit widths however.</p>
<pre>
+ declare void @llvm.memmove.i8(i8 * <dest>, i8 * <src>,
+ i8 <len>, i32 <align>)
+ declare void @llvm.memmove.i16(i8 * <dest>, i8 * <src>,
+ i16 <len>, i32 <align>)
declare void @llvm.memmove.i32(i8 * <dest>, i8 * <src>,
i32 <len>, i32 <align>)
declare void @llvm.memmove.i64(i8 * <dest>, i8 * <src>,
<div class="doc_text">
<h5>Syntax:</h5>
+<p>This is an overloaded intrinsic. You can use llvm.memset on any integer bit
+width. Not all targets support all bit widths however.</p>
<pre>
+ declare void @llvm.memset.i8(i8 * <dest>, i8 <val>,
+ i8 <len>, i32 <align>)
+ declare void @llvm.memset.i16(i8 * <dest>, i8 <val>,
+ i16 <len>, i32 <align>)
declare void @llvm.memset.i32(i8 * <dest>, i8 <val>,
i32 <len>, i32 <align>)
declare void @llvm.memset.i64(i8 * <dest>, i8 <val>,
<h5>Syntax:</h5>
<p>This is an overloaded intrinsic. You can use <tt>llvm.sqrt</tt> on any
floating point or vector of floating point type. Not all targets support all
-types however.
+types however.</p>
<pre>
declare float @llvm.sqrt.f32(float %Val)
declare double @llvm.sqrt.f64(double %Val)
<h5>Syntax:</h5>
<p>This is an overloaded intrinsic. You can use <tt>llvm.powi</tt> on any
floating point or vector of floating point type. Not all targets support all
-types however.
+types however.</p>
<pre>
declare float @llvm.powi.f32(float %Val, i32 %power)
declare double @llvm.powi.f64(double %Val, i32 %power)
<h5>Syntax:</h5>
<p>This is an overloaded intrinsic. You can use <tt>llvm.sin</tt> on any
floating point or vector of floating point type. Not all targets support all
-types however.
+types however.</p>
<pre>
declare float @llvm.sin.f32(float %Val)
declare double @llvm.sin.f64(double %Val)
<h5>Syntax:</h5>
<p>This is an overloaded intrinsic. You can use <tt>llvm.cos</tt> on any
floating point or vector of floating point type. Not all targets support all
-types however.
+types however.</p>
<pre>
declare float @llvm.cos.f32(float %Val)
declare double @llvm.cos.f64(double %Val)
<h5>Syntax:</h5>
<p>This is an overloaded intrinsic. You can use <tt>llvm.pow</tt> on any
floating point or vector of floating point type. Not all targets support all
-types however.
+types however.</p>
<pre>
declare float @llvm.pow.f32(float %Val, float %Power)
declare double @llvm.pow.f64(double %Val, double %Power)
<h5>Syntax:</h5>
<p>This is an overloaded intrinsic function. You can use bswap on any integer
-type that is an even number of bytes (i.e. BitWidth % 16 == 0).
+type that is an even number of bytes (i.e. BitWidth % 16 == 0).</p>
<pre>
declare i16 @llvm.bswap.i16(i16 <id>)
declare i32 @llvm.bswap.i32(i32 <id>)
<h5>Syntax:</h5>
<p>This is an overloaded intrinsic. You can use llvm.ctpop on any integer bit
-width. Not all targets support all bit widths however.
+width. Not all targets support all bit widths however.</p>
<pre>
- declare i8 @llvm.ctpop.i8 (i8 <src>)
+ declare i8 @llvm.ctpop.i8(i8 <src>)
declare i16 @llvm.ctpop.i16(i16 <src>)
declare i32 @llvm.ctpop.i32(i32 <src>)
declare i64 @llvm.ctpop.i64(i64 <src>)
<h5>Syntax:</h5>
<p>This is an overloaded intrinsic. You can use <tt>llvm.ctlz</tt> on any
-integer bit width. Not all targets support all bit widths however.
+integer bit width. Not all targets support all bit widths however.</p>
<pre>
declare i8 @llvm.ctlz.i8 (i8 <src>)
declare i16 @llvm.ctlz.i16(i16 <src>)
<h5>Syntax:</h5>
<p>This is an overloaded intrinsic. You can use <tt>llvm.cttz</tt> on any
-integer bit width. Not all targets support all bit widths however.
+integer bit width. Not all targets support all bit widths however.</p>
<pre>
declare i8 @llvm.cttz.i8 (i8 <src>)
declare i16 @llvm.cttz.i16(i16 <src>)
</p>
</div>
+
+<!-- ======================================================================= -->
+<div class="doc_subsection">
+ <a name="int_overflow">Arithmetic with Overflow Intrinsics</a>
+</div>
+
+<div class="doc_text">
+<p>
+LLVM provides intrinsics for some arithmetic with overflow operations.
+</p>
+
+</div>
+
<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection">
- <a name="int_part_select">'<tt>llvm.part.select.*</tt>' Intrinsic</a>
+ <a name="int_sadd_overflow">'<tt>llvm.sadd.with.overflow.*</tt>' Intrinsics</a>
</div>
<div class="doc_text">
<h5>Syntax:</h5>
-<p>This is an overloaded intrinsic. You can use <tt>llvm.part.select</tt>
-on any integer bit width.
+
+<p>This is an overloaded intrinsic. You can use <tt>llvm.sadd.with.overflow</tt>
+on any integer bit width.</p>
+
<pre>
- declare i17 @llvm.part.select.i17 (i17 %val, i32 %loBit, i32 %hiBit)
- declare i29 @llvm.part.select.i29 (i29 %val, i32 %loBit, i32 %hiBit)
+ declare {i16, i1} @llvm.sadd.with.overflow.i16(i16 %a, i16 %b)
+ declare {i32, i1} @llvm.sadd.with.overflow.i32(i32 %a, i32 %b)
+ declare {i64, i1} @llvm.sadd.with.overflow.i64(i64 %a, i64 %b)
</pre>
<h5>Overview:</h5>
-<p>The '<tt>llvm.part.select</tt>' family of intrinsic functions selects a
-range of bits from an integer value and returns them in the same bit width as
-the original value.</p>
+
+<p>The '<tt>llvm.sadd.with.overflow</tt>' family of intrinsic functions perform
+a signed addition of the two arguments, and indicate whether an overflow
+occurred during the signed summation.</p>
<h5>Arguments:</h5>
-<p>The first argument, <tt>%val</tt> and the result may be integer types of
-any bit width but they must have the same bit width. The second and third
-arguments must be <tt>i32</tt> type since they specify only a bit index.</p>
+
+<p>The arguments (%a and %b) and the first element of the result structure may
+be of integer types of any bit width, but they must have the same bit width. The
+second element of the result structure must be of type <tt>i1</tt>. <tt>%a</tt>
+and <tt>%b</tt> are the two values that will undergo signed addition.</p>
<h5>Semantics:</h5>
-<p>The operation of the '<tt>llvm.part.select</tt>' intrinsic has two modes
-of operation: forwards and reverse. If <tt>%loBit</tt> is greater than
-<tt>%hiBits</tt> then the intrinsic operates in reverse mode. Otherwise it
-operates in forward mode.</p>
-<p>In forward mode, this intrinsic is the equivalent of shifting <tt>%val</tt>
-right by <tt>%loBit</tt> bits and then ANDing it with a mask with
-only the <tt>%hiBit - %loBit</tt> bits set, as follows:</p>
-<ol>
- <li>The <tt>%val</tt> is shifted right (LSHR) by the number of bits specified
- by <tt>%loBits</tt>. This normalizes the value to the low order bits.</li>
- <li>The <tt>%loBits</tt> value is subtracted from the <tt>%hiBits</tt> value
- to determine the number of bits to retain.</li>
- <li>A mask of the retained bits is created by shifting a -1 value.</li>
- <li>The mask is ANDed with <tt>%val</tt> to produce the result.
-</ol>
-<p>In reverse mode, a similar computation is made except that the bits are
-returned in the reverse order. So, for example, if <tt>X</tt> has the value
-<tt>i16 0x0ACF (101011001111)</tt> and we apply
-<tt>part.select(i16 X, 8, 3)</tt> to it, we get back the value
-<tt>i16 0x0026 (000000100110)</tt>.</p>
+
+<p>The '<tt>llvm.sadd.with.overflow</tt>' family of intrinsic functions perform
+a signed addition of the two variables. They return a structure — the
+first element of which is the signed summation, and the second element of which
+is a bit specifying if the signed summation resulted in an overflow.</p>
+
+<h5>Examples:</h5>
+<pre>
+ %res = call {i32, i1} @llvm.sadd.with.overflow.i32(i32 %a, i32 %b)
+ %sum = extractvalue {i32, i1} %res, 0
+ %obit = extractvalue {i32, i1} %res, 1
+ br i1 %obit, label %overflow, label %normal
+</pre>
+
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="int_uadd_overflow">'<tt>llvm.uadd.with.overflow.*</tt>' Intrinsics</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+
+<p>This is an overloaded intrinsic. You can use <tt>llvm.uadd.with.overflow</tt>
+on any integer bit width.</p>
+
+<pre>
+ declare {i16, i1} @llvm.uadd.with.overflow.i16(i16 %a, i16 %b)
+ declare {i32, i1} @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
+ declare {i64, i1} @llvm.uadd.with.overflow.i64(i64 %a, i64 %b)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>The '<tt>llvm.uadd.with.overflow</tt>' family of intrinsic functions perform
+an unsigned addition of the two arguments, and indicate whether a carry occurred
+during the unsigned summation.</p>
+
+<h5>Arguments:</h5>
+
+<p>The arguments (%a and %b) and the first element of the result structure may
+be of integer types of any bit width, but they must have the same bit width. The
+second element of the result structure must be of type <tt>i1</tt>. <tt>%a</tt>
+and <tt>%b</tt> are the two values that will undergo unsigned addition.</p>
+
+<h5>Semantics:</h5>
+
+<p>The '<tt>llvm.uadd.with.overflow</tt>' family of intrinsic functions perform
+an unsigned addition of the two arguments. They return a structure — the
+first element of which is the sum, and the second element of which is a bit
+specifying if the unsigned summation resulted in a carry.</p>
+
+<h5>Examples:</h5>
+<pre>
+ %res = call {i32, i1} @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
+ %sum = extractvalue {i32, i1} %res, 0
+ %obit = extractvalue {i32, i1} %res, 1
+ br i1 %obit, label %carry, label %normal
+</pre>
+
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="int_ssub_overflow">'<tt>llvm.ssub.with.overflow.*</tt>' Intrinsics</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+
+<p>This is an overloaded intrinsic. You can use <tt>llvm.ssub.with.overflow</tt>
+on any integer bit width.</p>
+
+<pre>
+ declare {i16, i1} @llvm.ssub.with.overflow.i16(i16 %a, i16 %b)
+ declare {i32, i1} @llvm.ssub.with.overflow.i32(i32 %a, i32 %b)
+ declare {i64, i1} @llvm.ssub.with.overflow.i64(i64 %a, i64 %b)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>The '<tt>llvm.ssub.with.overflow</tt>' family of intrinsic functions perform
+a signed subtraction of the two arguments, and indicate whether an overflow
+occurred during the signed subtraction.</p>
+
+<h5>Arguments:</h5>
+
+<p>The arguments (%a and %b) and the first element of the result structure may
+be of integer types of any bit width, but they must have the same bit width. The
+second element of the result structure must be of type <tt>i1</tt>. <tt>%a</tt>
+and <tt>%b</tt> are the two values that will undergo signed subtraction.</p>
+
+<h5>Semantics:</h5>
+
+<p>The '<tt>llvm.ssub.with.overflow</tt>' family of intrinsic functions perform
+a signed subtraction of the two arguments. They return a structure — the
+first element of which is the subtraction, and the second element of which is a bit
+specifying if the signed subtraction resulted in an overflow.</p>
+
+<h5>Examples:</h5>
+<pre>
+ %res = call {i32, i1} @llvm.ssub.with.overflow.i32(i32 %a, i32 %b)
+ %sum = extractvalue {i32, i1} %res, 0
+ %obit = extractvalue {i32, i1} %res, 1
+ br i1 %obit, label %overflow, label %normal
+</pre>
+
</div>
+<!-- _______________________________________________________________________ -->
<div class="doc_subsubsection">
- <a name="int_part_set">'<tt>llvm.part.set.*</tt>' Intrinsic</a>
+ <a name="int_usub_overflow">'<tt>llvm.usub.with.overflow.*</tt>' Intrinsics</a>
</div>
<div class="doc_text">
<h5>Syntax:</h5>
-<p>This is an overloaded intrinsic. You can use <tt>llvm.part.set</tt>
-on any integer bit width.
+
+<p>This is an overloaded intrinsic. You can use <tt>llvm.usub.with.overflow</tt>
+on any integer bit width.</p>
+
<pre>
- declare i17 @llvm.part.set.i17.i9 (i17 %val, i9 %repl, i32 %lo, i32 %hi)
- declare i29 @llvm.part.set.i29.i9 (i29 %val, i9 %repl, i32 %lo, i32 %hi)
+ declare {i16, i1} @llvm.usub.with.overflow.i16(i16 %a, i16 %b)
+ declare {i32, i1} @llvm.usub.with.overflow.i32(i32 %a, i32 %b)
+ declare {i64, i1} @llvm.usub.with.overflow.i64(i64 %a, i64 %b)
</pre>
<h5>Overview:</h5>
-<p>The '<tt>llvm.part.set</tt>' family of intrinsic functions replaces a range
-of bits in an integer value with another integer value. It returns the integer
-with the replaced bits.</p>
+
+<p>The '<tt>llvm.usub.with.overflow</tt>' family of intrinsic functions perform
+an unsigned subtraction of the two arguments, and indicate whether an overflow
+occurred during the unsigned subtraction.</p>
<h5>Arguments:</h5>
-<p>The first argument, <tt>%val</tt> and the result may be integer types of
-any bit width but they must have the same bit width. <tt>%val</tt> is the value
-whose bits will be replaced. The second argument, <tt>%repl</tt> may be an
-integer of any bit width. The third and fourth arguments must be <tt>i32</tt>
-type since they specify only a bit index.</p>
+
+<p>The arguments (%a and %b) and the first element of the result structure may
+be of integer types of any bit width, but they must have the same bit width. The
+second element of the result structure must be of type <tt>i1</tt>. <tt>%a</tt>
+and <tt>%b</tt> are the two values that will undergo unsigned subtraction.</p>
<h5>Semantics:</h5>
-<p>The operation of the '<tt>llvm.part.set</tt>' intrinsic has two modes
-of operation: forwards and reverse. If <tt>%lo</tt> is greater than
-<tt>%hi</tt> then the intrinsic operates in reverse mode. Otherwise it
-operates in forward mode.</p>
-<p>For both modes, the <tt>%repl</tt> value is prepared for use by either
-truncating it down to the size of the replacement area or zero extending it
-up to that size.</p>
-<p>In forward mode, the bits between <tt>%lo</tt> and <tt>%hi</tt> (inclusive)
-are replaced with corresponding bits from <tt>%repl</tt>. That is the 0th bit
-in <tt>%repl</tt> replaces the <tt>%lo</tt>th bit in <tt>%val</tt> and etc. up
-to the <tt>%hi</tt>th bit.
-<p>In reverse mode, a similar computation is made except that the bits are
-reversed. That is, the <tt>0</tt>th bit in <tt>%repl</tt> replaces the
-<tt>%hi</tt> bit in <tt>%val</tt> and etc. down to the <tt>%lo</tt>th bit.
+
+<p>The '<tt>llvm.usub.with.overflow</tt>' family of intrinsic functions perform
+an unsigned subtraction of the two arguments. They return a structure — the
+first element of which is the subtraction, and the second element of which is a bit
+specifying if the unsigned subtraction resulted in an overflow.</p>
+
<h5>Examples:</h5>
<pre>
- llvm.part.set(0xFFFF, 0, 4, 7) -> 0xFF0F
- llvm.part.set(0xFFFF, 0, 7, 4) -> 0xFF0F
- llvm.part.set(0xFFFF, 1, 7, 4) -> 0xFF8F
- llvm.part.set(0xFFFF, F, 8, 3) -> 0xFFE7
- llvm.part.set(0xFFFF, 0, 3, 8) -> 0xFE07
+ %res = call {i32, i1} @llvm.usub.with.overflow.i32(i32 %a, i32 %b)
+ %sum = extractvalue {i32, i1} %res, 0
+ %obit = extractvalue {i32, i1} %res, 1
+ br i1 %obit, label %overflow, label %normal
</pre>
+
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="int_smul_overflow">'<tt>llvm.smul.with.overflow.*</tt>' Intrinsics</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+
+<p>This is an overloaded intrinsic. You can use <tt>llvm.smul.with.overflow</tt>
+on any integer bit width.</p>
+
+<pre>
+ declare {i16, i1} @llvm.smul.with.overflow.i16(i16 %a, i16 %b)
+ declare {i32, i1} @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
+ declare {i64, i1} @llvm.smul.with.overflow.i64(i64 %a, i64 %b)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>The '<tt>llvm.smul.with.overflow</tt>' family of intrinsic functions perform
+a signed multiplication of the two arguments, and indicate whether an overflow
+occurred during the signed multiplication.</p>
+
+<h5>Arguments:</h5>
+
+<p>The arguments (%a and %b) and the first element of the result structure may
+be of integer types of any bit width, but they must have the same bit width. The
+second element of the result structure must be of type <tt>i1</tt>. <tt>%a</tt>
+and <tt>%b</tt> are the two values that will undergo signed multiplication.</p>
+
+<h5>Semantics:</h5>
+
+<p>The '<tt>llvm.smul.with.overflow</tt>' family of intrinsic functions perform
+a signed multiplication of the two arguments. They return a structure —
+the first element of which is the multiplication, and the second element of
+which is a bit specifying if the signed multiplication resulted in an
+overflow.</p>
+
+<h5>Examples:</h5>
+<pre>
+ %res = call {i32, i1} @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
+ %sum = extractvalue {i32, i1} %res, 0
+ %obit = extractvalue {i32, i1} %res, 1
+ br i1 %obit, label %overflow, label %normal
+</pre>
+
+</div>
+
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="int_umul_overflow">'<tt>llvm.umul.with.overflow.*</tt>' Intrinsics</a>
+</div>
+
+<div class="doc_text">
+
+<h5>Syntax:</h5>
+
+<p>This is an overloaded intrinsic. You can use <tt>llvm.umul.with.overflow</tt>
+on any integer bit width.</p>
+
+<pre>
+ declare {i16, i1} @llvm.umul.with.overflow.i16(i16 %a, i16 %b)
+ declare {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
+ declare {i64, i1} @llvm.umul.with.overflow.i64(i64 %a, i64 %b)
+</pre>
+
+<h5>Overview:</h5>
+
+<p>The '<tt>llvm.umul.with.overflow</tt>' family of intrinsic functions perform
+a unsigned multiplication of the two arguments, and indicate whether an overflow
+occurred during the unsigned multiplication.</p>
+
+<h5>Arguments:</h5>
+
+<p>The arguments (%a and %b) and the first element of the result structure may
+be of integer types of any bit width, but they must have the same bit width. The
+second element of the result structure must be of type <tt>i1</tt>. <tt>%a</tt>
+and <tt>%b</tt> are the two values that will undergo unsigned
+multiplication.</p>
+
+<h5>Semantics:</h5>
+
+<p>The '<tt>llvm.umul.with.overflow</tt>' family of intrinsic functions perform
+an unsigned multiplication of the two arguments. They return a structure —
+the first element of which is the multiplication, and the second element of
+which is a bit specifying if the unsigned multiplication resulted in an
+overflow.</p>
+
+<h5>Examples:</h5>
+<pre>
+ %res = call {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
+ %sum = extractvalue {i32, i1} %res, 0
+ %obit = extractvalue {i32, i1} %res, 1
+ br i1 %obit, label %overflow, label %normal
+</pre>
+
</div>
<!-- ======================================================================= -->
<li><tt>ls</tt>: load-store barrier</li>
<li><tt>sl</tt>: store-load barrier</li>
<li><tt>ss</tt>: store-store barrier</li>
- <li><tt>device</tt>: barrier applies to device and uncached memory also.
+ <li><tt>device</tt>: barrier applies to device and uncached memory also.</li>
</ul>
<h5>Semantics:</h5>
<p>
with arbitrary strings. This can be useful for special purpose optimizations
that want to look for these annotations. These have no other defined use, they
are ignored by code generation and optimization.
+</p>
</div>
<!-- _______________________________________________________________________ -->
</p>
</div>
+<!-- _______________________________________________________________________ -->
+<div class="doc_subsubsection">
+ <a name="int_stackprotector">'<tt>llvm.stackprotector</tt>' Intrinsic</a>
+</div>
+<div class="doc_text">
+<h5>Syntax:</h5>
+<pre>
+declare void @llvm.stackprotector( i8* <guard>, i8** <slot> )
+
+</pre>
+<h5>Overview:</h5>
+<p>
+ The <tt>llvm.stackprotector</tt> intrinsic takes the <tt>guard</tt> and stores
+ it onto the stack at <tt>slot</tt>. The stack slot is adjusted to ensure that
+ it is placed on the stack before local variables.
+</p>
+<h5>Arguments:</h5>
+<p>
+ The <tt>llvm.stackprotector</tt> intrinsic requires two pointer arguments. The
+ first argument is the value loaded from the stack guard
+ <tt>@__stack_chk_guard</tt>. The second variable is an <tt>alloca</tt> that
+ has enough space to hold the value of the guard.
+</p>
+<h5>Semantics:</h5>
+<p>
+ This intrinsic causes the prologue/epilogue inserter to force the position of
+ the <tt>AllocaInst</tt> stack slot to be before local variables on the
+ stack. This is to ensure that if a local variable on the stack is overwritten,
+ it will destroy the value of the guard. When the function exits, the guard on
+ the stack is checked against the original guard. If they're different, then
+ the program aborts by calling the <tt>__stack_chk_fail()</tt> function.
+</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>
+ src="http://jigsaw.w3.org/css-validator/images/vcss-blue" 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>
+ src="http://www.w3.org/Icons/valid-html401-blue" 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>