X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=docs%2FLangRef.html;h=01b971bf2f0a9402a06394a4ec68ffff9503b983;hb=a6fb5b54f3a35fdefbb03b9c7be4c6d6d53cdd35;hp=16a23f5809ad67836edf29ae8659c22ef0d7e784;hpb=4580e529f9f7038f91735b20bbbca384902574b9;p=oota-llvm.git diff --git a/docs/LangRef.html b/docs/LangRef.html index 16a23f5809a..01b971bf2f0 100644 --- a/docs/LangRef.html +++ b/docs/LangRef.html @@ -24,25 +24,32 @@
  • Calling Conventions
  • Global Variables
  • Functions
    • +
  • Aliases
  • Parameter Attributes
    • +
  • Garbage Collector Names
  • Module-Level Inline Assembly
    • +
  • Data Layout
  • Type System
      +
    1. Type Classifications
    2. Primitive Types
        -
      1. Type Classifications
        2. +
      2. Floating Point Types
        3. +
      3. Void Type
        4. +
      4. Label Type
    3. Derived Types
        +
      1. Integer Type
      2. Array Type
      3. Function Type
      4. Pointer Type
      5. Structure Type
      6. Packed Structure Type
        7. -
      7. Packed Type
        8. +
      8. Vector Type
      9. Opaque Type
      4. @@ -89,12 +96,12 @@
    4. Bitwise Binary Operations
        -
      1. 'and' Instruction
        2. -
      2. 'or' Instruction
        3. -
      3. 'xor' Instruction
      4. 'shl' Instruction
      5. 'lshr' Instruction
      6. 'ashr' Instruction
        7. +
      7. 'and' Instruction
        8. +
      8. 'or' Instruction
        9. +
      9. 'xor' Instruction
    5. Vector Operations @@ -104,6 +111,12 @@
    6. 'shufflevector' Instruction
    • +
  • Aggregate Operations +
      +
    1. 'extractvalue' Instruction
      2. +
    2. 'insertvalue' Instruction
      3. +
    +
  • Memory Access and Addressing Operations
    1. 'malloc' Instruction
      2. @@ -133,10 +146,13 @@
      1. 'icmp' Instruction
      2. 'fcmp' Instruction
        3. +
      3. 'vicmp' Instruction
        4. +
      4. 'vfcmp' Instruction
      5. 'phi' Instruction
      6. 'select' Instruction
      7. 'call' Instruction
      8. 'va_arg' Instruction
        9. +
      9. 'getresult' Instruction
    @@ -145,47 +161,76 @@
    1. Variable Argument Handling Intrinsics
        -
      1. 'llvm.va_start' Intrinsic
        2. -
      2. 'llvm.va_end' Intrinsic
        3. -
      3. 'llvm.va_copy' Intrinsic
        4. +
      4. 'llvm.va_start' Intrinsic
        5. +
      5. 'llvm.va_end' Intrinsic
        6. +
      6. 'llvm.va_copy' Intrinsic
    2. Accurate Garbage Collection Intrinsics
        -
      1. 'llvm.gcroot' Intrinsic
        2. -
      2. 'llvm.gcread' Intrinsic
        3. -
      3. 'llvm.gcwrite' Intrinsic
        4. +
      4. 'llvm.gcroot' Intrinsic
        5. +
      5. 'llvm.gcread' Intrinsic
        6. +
      6. 'llvm.gcwrite' Intrinsic
    3. Code Generator Intrinsics
        -
      1. 'llvm.returnaddress' Intrinsic
        2. -
      2. 'llvm.frameaddress' Intrinsic
        3. -
      3. 'llvm.stacksave' Intrinsic
        4. -
      4. 'llvm.stackrestore' Intrinsic
        5. -
      5. 'llvm.prefetch' Intrinsic
        6. -
      6. 'llvm.pcmarker' Intrinsic
        7. -
      7. llvm.readcyclecounter' Intrinsic
        8. +
      8. 'llvm.returnaddress' Intrinsic
        9. +
      9. 'llvm.frameaddress' Intrinsic
        10. +
      10. 'llvm.stacksave' Intrinsic
        11. +
      11. 'llvm.stackrestore' Intrinsic
        12. +
      12. 'llvm.prefetch' Intrinsic
        13. +
      13. 'llvm.pcmarker' Intrinsic
        14. +
      14. llvm.readcyclecounter' Intrinsic
    4. Standard C Library Intrinsics
        -
      1. 'llvm.memcpy.*' Intrinsic
        2. -
      2. 'llvm.memmove.*' Intrinsic
        3. -
      3. 'llvm.memset.*' Intrinsic
        4. -
      4. 'llvm.sqrt.*' Intrinsic
        5. -
      5. 'llvm.powi.*' Intrinsic
        6. +
      6. 'llvm.memcpy.*' Intrinsic
        7. +
      7. 'llvm.memmove.*' Intrinsic
        8. +
      8. 'llvm.memset.*' Intrinsic
        9. +
      9. 'llvm.sqrt.*' Intrinsic
        10. +
      10. 'llvm.powi.*' Intrinsic
        11. +
      11. 'llvm.sin.*' Intrinsic
        12. +
      12. 'llvm.cos.*' Intrinsic
        13. +
      13. 'llvm.pow.*' Intrinsic
    5. Bit Manipulation Intrinsics
        -
      1. 'llvm.bswap.*' Intrinsics
        2. +
      2. 'llvm.bswap.*' Intrinsics
      3. 'llvm.ctpop.*' Intrinsic
      4. 'llvm.ctlz.*' Intrinsic
      5. 'llvm.cttz.*' Intrinsic
        6. +
      6. 'llvm.part.select.*' Intrinsic
        7. +
      7. 'llvm.part.set.*' Intrinsic
    6. Debugger intrinsics
      7. +
    7. Exception Handling intrinsics
      8. +
    8. Trampoline Intrinsic +
        +
      1. 'llvm.init.trampoline' Intrinsic
        2. +
      +
      9. +
    9. Atomic intrinsics +
        +
      1. llvm.memory_barrier
        2. +
      2. llvm.atomic.lcs
        3. +
      3. llvm.atomic.las
        4. +
      4. llvm.atomic.swap
        5. +
      +
      10. +
    10. General intrinsics +
        +
      1. + llvm.var.annotation' Intrinsic
        2. +
      2. + llvm.annotation.*' Intrinsic
        3. +
      3. + llvm.trap' Intrinsic
        4. +
      +
    • @@ -215,7 +260,7 @@ strategy.

    The LLVM code representation is designed to be used in three -different forms: as an in-memory compiler IR, as an on-disk bytecode +different forms: as an in-memory compiler IR, as an on-disk bitcode representation (suitable for fast loading by a Just-In-Time compiler), and as a human readable assembly language representation. This allows LLVM to provide a powerful intermediate representation for efficient @@ -247,19 +292,22 @@ LLVM assembly language. There is a difference between what the parser accepts and what is considered 'well formed'. For example, the following instruction is syntactically okay, but not well formed:

    +
    -  %x = add i32 1, %x
+%x = add i32 1, %x
    +

    ...because the definition of %x does not dominate all of its uses. The LLVM infrastructure provides a verification pass that may be used to verify that an LLVM module is well formed. This pass is automatically run by the parser after parsing input assembly and by -the optimizer before it outputs bytecode. The violations pointed out +the optimizer before it outputs bitcode. The violations pointed out by the verifier pass indicate bugs in transformation passes or input to the parser.

    +
    - +
    Identifiers
    @@ -267,25 +315,27 @@ the parser.

    -

    LLVM uses three different forms of identifiers, for different -purposes:

    +

    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:

      -
    1. Named values are represented as a string of characters with a '%' prefix. - For example, %foo, %DivisionByZero, %a.really.long.identifier. The actual - regular expression used is '%[a-zA-Z$._][a-zA-Z$._0-9]*'. +
    2. 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 '[%@][a-zA-Z$._][a-zA-Z$._0-9]*'. Identifiers which require other characters in their names can be surrounded - with quotes. In this way, anything except a " character can be used - in a name.
      3. + with quotes. In this way, anything except a " character can + be used in a named value. -
    3. Unnamed values are represented as an unsigned numeric value with a '%' - prefix. For example, %12, %2, %44.
      4. +
    4. Unnamed values are represented as an unsigned numeric value with their + prefix. For example, %12, @2, %44.
    5. Constants, which are described in a section about constants, below.
    -

    LLVM requires that values start with a '%' sign for two reasons: Compilers +

    LLVM requires that values start with a prefix for two reasons: Compilers don't need to worry about name clashes with reserved words, and the set of reserved words may be expanded in the future without penalty. Additionally, unnamed identifiers allow a compiler to quickly come up with a temporary @@ -298,30 +348,36 @@ languages. There are keywords for different opcodes 'ret', etc...), for primitive type names ('void', 'i32', etc...), and others. These reserved words cannot conflict with variable names, because -none of them start with a '%' character.

    +none of them start with a prefix character ('%' or '@').

    Here is an example of LLVM code to multiply the integer variable '%X' by 8:

    The easy way:

    +
    -  %result = mul i32 %X, 8
+%result = mul i32 %X, 8
    +

    After strength reduction:

    +
    -  %result = shl i32 %X, i8 3
+%result = shl i32 %X, i8 3
    +

    And the hard way:

    +
    -  add i32 %X, %X           ; yields {i32}:%0
-  add i32 %0, %0           ; yields {i32}:%1
-  %result = add i32 %1, %1
+add i32 %X, %X           ; yields {i32}:%0
+add i32 %0, %0           ; yields {i32}:%1
+%result = add i32 %1, %1
    +

    This last way of multiplying %X by 8 illustrates several important lexical features of LLVM:

    @@ -362,27 +418,27 @@ combined together with the LLVM linker, which merges function (and global variable) definitions, resolves forward declarations, and merges symbol table entries. Here is an example of the "hello world" module:

    +
    ; Declare the string constant as a global constant...
-%.LC0 = internal constant [13 x i8 ] c"hello world\0A\00"          ; [13 x i8 ]*
+@.LC0 = internal constant [13 x i8] c"hello world\0A\00"          ; [13 x i8]*
 
 ; External declaration of the puts function
-declare i32 %puts(i8 *)                                            ; i32(i8 *)* 
-
-; Global variable / Function body section separator
-implementation
+declare i32 @puts(i8 *)                                            ; i32(i8 *)* 
 
 ; Definition of main function
-define i32 %main() {                                                 ; i32()* 
+define i32 @main() {                                                 ; i32()* 
         ; Convert [13x i8 ]* to i8  *...
         %cast210 = getelementptr [13 x i8 ]* %.LC0, i64 0, i64 0 ; i8 *
+ href="#i_getelementptr">getelementptr [13 x i8 ]* @.LC0, i64 0, i64 0 ; i8 *
 
         ; Call puts function to write out the string to stdout...
         call i32 %puts(i8 * %cast210)                              ; i32
+ href="#i_call">call i32 @puts(i8 * %cast210)                              ; i32
         ret i32 0
    }
    + href="#i_ret">ret i32 0
    }
    + +

    This example is made up of a global variable named ".LC0", an external declaration of the "puts" @@ -395,13 +451,6 @@ represented by a pointer to a memory location (in this case, a pointer to an array of char, and a pointer to a function), and have one of the following linkage types.

    -

    Due to a limitation in the current LLVM assembly parser (it is limited by -one-token lookahead), modules are split into two pieces by the "implementation" -keyword. Global variable prototypes and definitions must occur before the -keyword, and function definitions must occur after it. Function prototypes may -occur either before or after it. In the future, the implementation keyword may -become a noop, if the parser gets smarter.

    -
    @@ -417,30 +466,41 @@ All Global Variables and Functions have one of the following types of linkage:
    -
    internal
    +
    internal:
    Global values with internal linkage are only directly accessible by objects in the current module. In particular, linking code into a module with an internal global value may cause the internal to be renamed as necessary to avoid collisions. Because the symbol is internal to the module, all references can be updated. This corresponds to the notion of the - 'static' keyword in C, or the idea of "anonymous namespaces" in C++. + 'static' keyword in C.
    linkonce:
    -
    "linkonce" linkage is similar to internal linkage, with - the twist that linking together two modules defining the same - linkonce globals will cause one of the globals to be discarded. This - is typically used to implement inline functions. Unreferenced - linkonce globals are allowed to be discarded. +
    Globals with "linkonce" linkage are merged with other globals of + the same name when linkage occurs. This is typically used to implement + inline functions, templates, or other code which must be generated in each + translation unit that uses it. Unreferenced linkonce globals are + allowed to be discarded. +
    + +
    common:
    + +
    "common" linkage is exactly the same as linkonce + linkage, except that unreferenced common globals may not be + discarded. This is used for globals that may be emitted in multiple + translation units, but that are not guaranteed to be emitted into every + translation unit that uses them. One example of this is tentative + definitions in C, such as "int X;" at global scope.
    weak:
    -
    "weak" linkage is exactly the same as linkonce linkage, - except that unreferenced weak globals may not be discarded. This is - used to implement constructs in C such as "int X;" at global scope. +
    "weak" linkage is the same as common linkage, except + that some targets may choose to emit different assembly sequences for them + for target-dependent reasons. This is used for globals that are declared + "weak" in C source code.
    appending:
    @@ -457,7 +517,6 @@ All Global Variables and Functions have one of the following types of linkage: until linked, if not linked, the symbol becomes null instead of being an undefined reference. -
    externally visible:
    @@ -465,6 +524,7 @@ All Global Variables and Functions have one of the following types of linkage: visible, meaning that it participates in linkage and can be used to resolve external symbol references. +

    The next two types of linkage are targeted for Microsoft Windows platform @@ -501,7 +561,8 @@ outside of the current module.

    It is illegal for a function declaration to have any linkage type other than "externally visible", dllimport, or extern_weak.

    - +

    Aliases can have only external, internal and weak +linkages. @@ -527,28 +588,17 @@ the future:

    prototype and implemented declaration of the function (as does normal C). -
    "csretcc" - The C struct return calling convention:
    - -
    This calling convention matches the target C calling conventions, except - that functions with this convention are required to take a pointer as their - first argument, and the return type of the function must be void. This is - used for C functions that return aggregates by-value. In this case, the - function has been transformed to take a pointer to the struct as the first - argument to the function. For targets where the ABI specifies specific - behavior for structure-return calls, the calling convention can be used to - distinguish between struct return functions and other functions that take a - pointer to a struct as the first argument. -
    -
    "fastcc" - The fast calling convention:
    This calling convention attempts to make calls as fast as possible (e.g. by passing things in registers). This calling convention allows the target to use whatever tricks it wants to produce fast code for the target, without having to conform to an externally specified ABI. Implementations of - this convention should allow arbitrary tail call optimization to be supported. - This calling convention does not support varargs and requires the prototype of - all callees to exactly match the prototype of the function definition. + this convention should allow arbitrary + tail call optimization to be + supported. This calling convention does not support varargs and requires the + prototype of all callees to exactly match the prototype of the function + definition.
    "coldcc" - The cold calling convention:
    @@ -575,6 +625,47 @@ convention.

    + +
    + Visibility Styles +
    + +
    + +

    +All Global Variables and Functions have one of the following visibility styles: +

    + +
    +
    "default" - Default style:
    + +
    On ELF, default visibility means that the declaration is visible to other + modules and, in shared libraries, means that the declared entity may be + overridden. On Darwin, default visibility means that the declaration is + visible to other modules. Default visibility corresponds to "external + linkage" in the language. +
    + +
    "hidden" - Hidden style:
    + +
    Two declarations of an object with hidden visibility refer to the same + object if they are in the same shared object. Usually, hidden visibility + indicates that the symbol will not be placed into the dynamic symbol table, + so no other module (executable or shared library) can reference it + directly. +
    + +
    "protected" - Protected style:
    + +
    On ELF, protected visibility indicates that the symbol will be placed in + the dynamic symbol table, but that references within the defining module will + bind to the local symbol. That is, the symbol cannot be overridden by another + module. +
    +
    + +
    +
    Global Variables @@ -584,10 +675,11 @@ convention.

    Global variables define regions of memory allocated at compilation time instead of run-time. Global variables may optionally be initialized, may have -an explicit section to be placed in, and may -have an optional explicit alignment specified. A -variable may be defined as a global "constant," which indicates that the -contents of the variable will never be modified (enabling better +an explicit section to be placed in, and may have an optional explicit alignment +specified. A variable may be defined as "thread_local", which means that it +will not be shared by threads (each thread will have a separated copy of the +variable). A variable may be defined as a global "constant," which indicates +that the contents of the variable will never be modified (enabling better optimization, allowing the global data to be placed in the read-only section of an executable, etc). Note that variables that need runtime initialization cannot be marked "constant" as there is a store to the variable.

    @@ -607,6 +699,12 @@ variables always define a pointer to their "content" type because they describe a region of memory, and all memory objects in LLVM are accessed through pointers.

    +

    A global variable may be declared to reside in a target-specifc 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 +must precede any other attributes.

    +

    LLVM allows an explicit section to be specified for globals. If the target supports it, it will emit globals to the section specified.

    @@ -616,12 +714,14 @@ to whatever it feels convenient. If an explicit alignment is specified, the global is forced to have at least that much alignment. All alignments must be a power of 2.

    -

    For example, the following defines a global with an initializer, section, - and alignment:

    +

    For example, the following defines a global in a numbered address space with +an initializer, section, and alignment:

    +
    -  %G = constant float 1.0, section "foo", align 4
+@G = constant float 1.0 addrspace(5), section "foo", align 4
    +
    @@ -635,16 +735,21 @@ a power of 2.

    LLVM function definitions consist of the "define" keyord, an optional linkage type, an optional +visibility style, an optional calling convention, a return type, an optional parameter attribute for the return type, a function name, a (possibly empty) argument list (each with optional -parameter attributes), an optional section, an -optional alignment, an opening curly brace, a list of basic blocks, and a -closing curly brace. LLVM function declarations -consist of the "declare" keyword, an optional calling convention, a return type, an optional +parameter attributes), an optional section, an +optional alignment, an optional garbage collector name, an +opening curly brace, a list of basic blocks, and a closing curly brace. + +LLVM function declarations consist of the "declare" keyword, an +optional linkage type, an optional +visibility style, an optional +calling convention, a return type, an optional parameter attribute for the return type, a function -name, a possibly empty list of arguments, and an optional alignment.

    +name, a possibly empty list of arguments, an optional alignment, and an optional +garbage collector name.

    A function definition contains a list of basic blocks, forming the CFG for the function. Each basic block may optionally start with a label (giving the @@ -652,17 +757,12 @@ basic block a symbol table entry), contains a list of instructions, and ends with a terminator instruction (such as a branch or function return).

    -

    The first basic block in a program is special in two ways: it is immediately +

    The first basic block in a function is special in two ways: it is immediately executed on entrance to the function, and it is not allowed to have predecessor basic blocks (i.e. there can not be any branches to the entry block of a function). Because the block can have no predecessors, it also cannot have any PHI nodes.

    -

    LLVM functions are identified by their name and type signature. Hence, two -functions with the same name but different parameter lists or return values are -considered different functions, and LLVM will resolve references to each -appropriately.

    -

    LLVM allows an explicit section to be specified for functions. If the target supports it, it will emit functions to the section specified.

    @@ -674,40 +774,129 @@ a power of 2.

    + + +
    + Aliases +
    +
    +

    Aliases act as "second name" for the aliasee value (which can be either + function, global variable, another alias or bitcast of global value). Aliases + may have an optional linkage type, and an + optional visibility style.

    + +
    Syntax:
    + +
    +
    +@<Name> = [Linkage] [Visibility] alias <AliaseeTy> @<Aliasee>
+
    +
    + +
    + + +
    Parameter Attributes

    The return type and each parameter of a function type may have a set of parameter attributes associated with them. Parameter attributes are used to communicate additional information about the result or parameters of - a function. Parameter attributes are considered to be part of the function - type so two functions types that differ only by the parameter attributes - are different function types.

    - -

    Parameter attributes consist of an at sign (@) followed by either a single - keyword or a comma separate list of keywords enclosed in parentheses. For - example:

    -    %someFunc = i16 @zext (i8 @(sext) %someParam)
-    %someFunc = i16 @zext (i8 @zext %someParam)
    -

    Note that the two function types above are unique because the parameter has - a different attribute (@sext in the first one, @zext in the second).

    + a function. Parameter attributes are considered to be part of the function, + not of the function type, so functions with different parameter attributes + can have the same function type.

    + +

    Parameter attributes are simple keywords that follow the type specified. If + multiple parameter attributes are needed, they are space separated. For + example:

    + +
    +
    +declare i32 @printf(i8* noalias , ...) nounwind
+declare i32 @atoi(i8*) nounwind readonly
+
    +
    + +

    Note that any attributes for the function result (nounwind, + readonly) come immediately after the argument list.

    Currently, only the following parameter attributes are defined:

    -
    @zext
    +
    zeroext
    This indicates that the parameter should be zero extended just before a call to this function.
    -
    @sext
    + +
    signext
    This indicates that the parameter should be sign extended just before a call to this function.
    + +
    inreg
    +
    This indicates that the parameter should be placed in register (if + possible) during assembling function call. Support for this attribute is + target-specific
    + +
    byval
    +
    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 scalars (even though this is silly).
    + +
    sret
    +
    This indicates that the pointer parameter specifies the address of a + structure that is the return value of the function in the source program. + Loads and stores to the structure are assumed not to trap. + May only be applied to the first parameter.
    + +
    noalias
    +
    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.
    + +
    noreturn
    +
    This function attribute indicates that the function never returns. This + indicates to LLVM that every call to this function should be treated as if + an unreachable instruction immediately followed the call.
    + +
    nounwind
    +
    This function attribute indicates that no exceptions unwind out of the + function. Usually this is because the function makes no use of exceptions, + but it may also be that the function catches any exceptions thrown when + executing it.
    + +
    nest
    +
    This indicates that the parameter can be excised using the + trampoline intrinsics.
    +
    readonly
    +
    This function attribute indicates that the function has no side-effects + except for producing a return value or throwing an exception. The value + returned must only depend on the function arguments and/or global variables. + It may use values obtained by dereferencing pointers.
    +
    readnone
    +
    A readnone function has the same restrictions as a readonly + function, but in addition it is not allowed to dereference any pointer arguments + or global variables.
    -

    The current motivation for parameter attributes is to enable the sign and - zero extend information necessary for the C calling convention to be passed - from the front end to LLVM. The @zext and @sext attributes - are used by the code generator to perform the required extension. However, - parameter attributes are an orthogonal feature to calling conventions and - may be used for other purposes in the future.

    +
    + + +
    + Garbage Collector Names +
    + +
    +

    Each function may specify a garbage collector name, which is simply a +string.

    + +
    define void @f() gc "name" { ...
    + +

    The compiler declares the supported values of name. Specifying a +collector which will cause the compiler to alter its output in order to support +the named garbage collection algorithm.

    @@ -723,10 +912,12 @@ LLVM and treated as a single unit, but may be separated in the .ll file if desired. The syntax is very simple:

    -
    -  module asm "inline asm code goes here"
-  module asm "more can go here"
-
    +
    +
    +module asm "inline asm code goes here"
+module asm "more can go here"
+
    +

    The strings can contain any character by escaping non-printable characters. The escape sequence used is simply "\xx" where "xx" is the two digit hex code @@ -739,6 +930,81 @@ desired. The syntax is very simple:

    + +
    + Data Layout +
    + +
    +

    A module may specify a target specific data layout string that specifies how +data is to be laid out in memory. The syntax for the data layout is simply:

    +
        target datalayout = "layout specification"
    +

    The layout specification consists of a list of specifications +separated by the minus sign character ('-'). Each specification starts with a +letter and may include other information after the letter to define some +aspect of the data layout. The specifications accepted are as follows:

    +
    +
    E
    +
    Specifies that the target lays out data in big-endian form. That is, the + bits with the most significance have the lowest address location.
    +
    e
    +
    Specifies that hte target lays out data in little-endian form. That is, + the bits with the least significance have the lowest address location.
    +
    p:size:abi:pref
    +
    This specifies the size of a pointer and its abi and + preferred alignments. All sizes are in bits. Specifying the pref + alignment is optional. If omitted, the preceding : should be omitted + too.
    +
    isize:abi:pref
    +
    This specifies the alignment for an integer type of a given bit + size. The value of size must be in the range [1,2^23).
    +
    vsize:abi:pref
    +
    This specifies the alignment for a vector type of a given bit + size.
    +
    fsize:abi:pref
    +
    This specifies the alignment for a floating point type of a given bit + size. The value of size must be either 32 (float) or 64 + (double).
    +
    asize:abi:pref
    +
    This specifies the alignment for an aggregate type of a given bit + size.
    +
    +

    When constructing the data layout for a given target, LLVM starts with a +default set of specifications which are then (possibly) overriden by the +specifications in the datalayout keyword. The default specifications +are given in this list:

    + +

    When llvm is determining the alignment for a given type, it uses the +following rules: +

      +
    1. If the type sought is an exact match for one of the specifications, that + specification is used.
      2. +
    2. If no match is found, and the type sought is an integer type, then the + smallest integer type that is larger than the bitwidth of the sought type is + used. If none of the specifications are larger than the bitwidth then the the + largest integer type is used. For example, given the default specifications + above, the i7 type will use the alignment of i8 (next largest) while both + i65 and i256 will use the alignment of i64 (largest specified).
      3. +
    3. 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.
      4. +
    +
    Type System
    @@ -757,68 +1023,50 @@ three address code representations.

    -
    Primitive Types
    -
    -

    The primitive types are the fundamental building blocks of the LLVM -system. The current set of primitive types is as follows:

    - - - - - - -
    - - - - - - - - - -
    TypeDescription
    voidNo value
    i8Signless 8-bit value
    i32Signless 32-bit value
    float32-bit floating point value
    labelBranch destination
    -     		- - - - - - - - -
    TypeDescription
    i1True or False value
    i16Signless 16-bit value
    i64Signless 64-bit value
    double64-bit floating point value
    -
    -
    - - -
    Type +
    Type Classifications
    -

    These different primitive types fall into a few useful +

    The types fall into a few useful classifications:

    - - + + + + + + - - + - - + + - - + +
    ClassificationTypes
    integeri8, i16, i32, i64integeri1, i2, i3, ... i8, ... i16, ... i32, ... i64, ...
    floating pointfloat, double, x86_fp80, fp128, ppc_fp128
    integrali1, i8, i16, i32, i64 + first classinteger, + floating point, + pointer, + vector, + structure, + array, + label.
    floating pointfloat, doubleprimitivelabel, + void, + floating point.
    first classi1, i8, i16, i32, i64, float, double,
    - pointer,packed     -     		derivedinteger, + array, + function, + pointer, + structure, + packed structure, + vector, + opaque.
    @@ -826,10 +1074,63 @@ classifications:

    The first class types are perhaps the most important. Values of these types are the only ones which can be produced by instructions, passed as arguments, or used as operands to -instructions. This means that all structures and arrays must be -manipulated either by pointer or by component.

    +instructions.

    +
    + + +
    Primitive Types
    + +
    +

    The primitive types are the fundamental building blocks of the LLVM +system.

    + +
    + + +
    Floating Point Types
    + +
    + + + + + + + + + +
    TypeDescription
    float32-bit floating point value
    double64-bit floating point value
    fp128128-bit floating point value (112-bit mantissa)
    x86_fp8080-bit floating point value (X87)
    ppc_fp128128-bit floating point value (two 64-bits)
    +
    + + +
    Void Type
    + +
    +
    Overview:
    +

    The void type does not represent any value and has no size.

    + +
    Syntax:
    + +
    +  void
+
    + +
    Label Type
    + +
    +
    Overview:
    +

    The label type represents code labels.

    + +
    Syntax:
    + +
    +  label
+
    +
    + +
    Derived Types
    @@ -842,6 +1143,42 @@ recursive: For example, it is possible to have a two dimensional array.

    + +
    Integer Type
    + +
    + +
    Overview:
    +

    The integer type is a very simple derived type that simply specifies an +arbitrary bit width for the integer type desired. Any bit width from 1 bit to +2^23-1 (about 8 million) can be specified.

    + +
    Syntax:
    + +
    +  iN
+
    + +

    The number of bits the integer will occupy is specified by the N +value.

    + +
    Examples:
    + + + + + + + + + + + + + +
    i1a single-bit integer.
    i32a 32-bit integer.
    i1942652a really big integer of over 1 million bits.
    +
    +
    Array Type
    @@ -865,31 +1202,31 @@ be any type with a size.

    Examples:
    - - + + + + + + + + + +
    - [40 x i32 ]
    - [41 x i32 ]
    - [40 x i8]
    -     		- Array of 40 32-bit integer values.
    - Array of 41 32-bit integer values.
    - Array of 40 8-bit integer values.
    -     		[40 x i32]Array of 40 32-bit integer values.
    [41 x i32]Array of 41 32-bit integer values.
    [4 x i8]Array of 4 8-bit integer values.

    Here are some examples of multidimensional arrays:

    - - + + + + + + + + + +
    - [3 x [4 x i32]]
    - [12 x [10 x float]]
    - [2 x [3 x [4 x i16]]]
    -     		- 3x4 array of 32-bit integer values.
    - 12x10 array of single precision floating point values.
    - 2x3x4 array of 16-bit integer values.
    -     		[3 x [4 x i32]]3x4 array of 32-bit integer values.
    [12 x [10 x float]]12x10 array of single precision floating point values.
    [2 x [3 x [4 x i16]]]2x3x4 array of 16-bit integer values.
    @@ -905,22 +1242,29 @@ type "{ i32, [0 x float]}", for example.

    Function Type
    +
    Overview:
    +

    The function type can be thought of as a function signature. It -consists of a return type and a list of formal parameter types. -Function types are usually used to build virtual function tables -(which are structures of pointers to functions), for indirect function -calls, and when defining a function.

    -

    -The return type of a function type cannot be an aggregate type. -

    +consists of a return type and a list of formal parameter types. The +return type of a function type is a scalar type, a void type, or a struct type. +If the return type is a struct type then all struct elements must be of first +class types, and the struct must have at least one element.

    +
    Syntax:
    -
      <returntype> (<parameter list>)
    + +
    +  <returntype list> (<parameter list>)
+
    +

    ...where '<parameter list>' is a comma-separated list of type specifiers. Optionally, the parameter list may include a type ..., which indicates that the function takes a variable number of arguments. Variable argument functions can access their arguments with the variable argument handling intrinsic functions.

    + href="#int_varargs">variable argument handling intrinsic functions. +'<returntype list>' is a comma-separated list of +first class type specifiers.

    +
    Examples:
    @@ -928,7 +1272,7 @@ Variable argument functions can access their arguments with the function taking an i32, returning an i32 - + + +
    float (i16 @sext, i32 *) * + float (i16 signext, i32 *) * Pointer to a function that takes an i16 that should be sign extended and a @@ -942,6 +1286,11 @@ Variable argument functions can access their arguments with the printf in LLVM.
    {i32, i32} (i32)A function taking an i32>, returning two + i32 values as an aggregate of type { i32, i32 } +
    @@ -963,16 +1312,14 @@ instruction.

    Examples:
    - - + + + + +
    - { i32, i32, i32 }
    - { float, i32 (i32) * }
    -     		- a triple of three i32 values
    - A pair, where the first element is a float and the second element - is a pointer to a function - that takes an i32, returning an i32.
    -     		{ i32, i32, i32 }A triple of three i32 values
    { float, i32 (i32) * }A pair, where the first element is a float and the + second element is a pointer to a + function that takes an i32, returning + an i32.
    @@ -995,16 +1342,14 @@ instruction.

    Examples:
    - - + + + + +
    - < { i32, i32, i32 } >
    - < { float, i32 (i32) * } >
    -     		- a triple of three i32 values
    - A pair, where the first element is a float and the second element - is a pointer to a function - that takes an i32, returning an i32.
    -     		< { i32, i32, i32 } >A triple of three i32 values
    < { float, i32 (i32)* } >A pair, where the first element is a float and the + second element is a pointer to a + function that takes an i32, returning + an i32.
    @@ -1014,39 +1359,45 @@ instruction.

    Overview:

    As in many languages, the pointer type represents a pointer or -reference to another object, which must live in memory.

    +reference to another object, which must live in memory. Pointer types may have +an optional address space attribute defining the target-specific numbered +address space where the pointed-to object resides. The default address space is +zero.

    Syntax:
      <type> *
    Examples:
    - - + + + + + + i32. + + + +
    - [4x i32]*
    - i32 (i32 *) *
    -     		- A pointer to array of - four i32 values
    - A pointer to a [4x i32]*    		A pointer to array of four i32 values.
    i32 (i32 *) * A pointer to a function that takes an i32*, returning an - i32.
    -
    i32 addrspace(5)*A pointer to an i32 value + that resides in address space #5.
    -
    Packed Type
    +
    Vector Type
    Overview:
    -

    A packed type is a simple derived type that represents a vector -of elements. Packed types are used when multiple primitive data +

    A vector type is a simple derived type that represents a vector +of elements. Vector types are used when multiple primitive data are operated in parallel using a single instruction (SIMD). -A packed type requires a size (number of +A vector type requires a size (number of elements) and an underlying primitive data type. Vectors must have a power -of two length (1, 2, 4, 8, 16 ...). Packed types are +of two length (1, 2, 4, 8, 16 ...). Vector types are considered first class.

    Syntax:
    @@ -1056,22 +1407,22 @@ considered first class.

    The number of elements is a constant integer value; elementtype may -be any integral or floating point type.

    +be any integer or floating point type.

    Examples:
    - - + + + + + + + + + +
    - <4 x i32>
    - <8 x float>
    - <2 x i64>
    -     		- Packed vector of 4 32-bit integer values.
    - Packed vector of 8 floating-point values.
    - Packed vector of 2 64-bit integer values.
    -     		<4 x i32>Vector of 4 32-bit integer values.
    <8 x float>Vector of 8 32-bit floating-point values.
    <2 x i64>Vector of 2 64-bit integer values.
    @@ -1083,7 +1434,7 @@ be any integral or floating point type.

    Overview:

    Opaque types are used to represent unknown types in the system. This -corresponds (for example) to the C notion of a foward declared structure type. +corresponds (for example) to the C notion of a forward declared structure type. In LLVM, opaque types can eventually be resolved to any type (not just a structure type).

    @@ -1097,12 +1448,8 @@ structure type).

    - - + +
    - opaque - - An opaque type.
    -     		opaqueAn opaque type.
    @@ -1142,8 +1489,10 @@ them all and their syntax.

    Floating point constants use standard decimal notation (e.g. 123.421), exponential notation (e.g. 1.23421e+2), or a more precise hexadecimal - notation (see below). Floating point constants must have a floating point type.
    + notation (see below). The assembler requires the exact decimal value of + a floating-point constant. For example, the assembler accepts 1.25 but + rejects 1.3 because 1.3 is a repeating decimal in binary. Floating point + constants must have a floating point type.
    Null pointer constants
    @@ -1177,8 +1526,8 @@ and smaller aggregate constants.

    Structure constants are represented with notation similar to structure type definitions (a comma separated list of elements, surrounded by braces - ({})). For example: "{ i32 4, float 17.0, i32* %G }", - where "%G" is declared as "%G = external global i32". Structure constants + ({})). For example: "{ i32 4, float 17.0, i32* @G }", + where "@G" is declared as "@G = external global i32". Structure constants must have structure type, and the number and types of elements must match those specified by the type.
    @@ -1192,13 +1541,13 @@ and smaller aggregate constants.

    types of elements must match those specified by the type. -
    Packed constants
    +
    Vector constants
    -
    Packed constants are represented with notation similar to packed type +
    Vector constants are represented with notation similar to vector type definitions (a comma separated list of elements, surrounded by less-than/greater-than's (<>)). For example: "< i32 42, - i32 11, i32 74, i32 100 >". Packed constants must have packed type, and the number and types of elements must + i32 11, i32 74, i32 100 >". Vector constants must have vector type, and the number and types of elements must match those specified by the type.
    @@ -1228,11 +1577,13 @@ href="#identifiers">identifier for the global is used and always have pointer type. For example, the following is a legal LLVM file:

    +
    -  %X = global i32 17
-  %Y = global i32 42
-  %Z = global [2 x i32*] [ i32* %X, i32* %Y ]
+@X = global i32 17
+@Y = global i32 42
+@Z = global [2 x i32*] [ i32* @X, i32* @Y ]
    +
    @@ -1263,15 +1614,15 @@ following is the syntax for constant expressions:

    trunc ( CST to TYPE )
    Truncate a constant to another type. The bit size of CST must be larger - than the bit size of TYPE. Both types must be integral.
    + than the bit size of TYPE. Both types must be integers.
    zext ( CST to TYPE )
    Zero extend a constant to another type. The bit size of CST must be - smaller or equal to the bit size of TYPE. Both types must be integral.
    + smaller or equal to the bit size of TYPE. Both types must be integers.
    sext ( CST to TYPE )
    Sign extend a constant to another type. The bit size of CST must be - smaller or equal to the bit size of TYPE. Both types must be integral.
    + smaller or equal to the bit size of TYPE. Both types must be integers.
    fptrunc ( CST to TYPE )
    Truncate a floating point constant to another floating point type. The @@ -1282,25 +1633,33 @@ following is the syntax for constant expressions:

    Floating point extend a constant to another type. The size of CST must be smaller or equal to the size of TYPE. Both types must be floating point.
    -
    fp2uint ( CST to TYPE )
    +
    fptoui ( CST to TYPE )
    Convert a floating point constant to the corresponding unsigned integer - constant. TYPE must be an integer type. CST must be floating point. If the - value won't fit in the integer type, the results are undefined.
    + constant. TYPE must be a scalar or vector integer type. CST must be of scalar + or vector floating point type. Both CST and TYPE must be scalars, or vectors + of the same number of elements. If the value won't fit in the integer type, + the results are undefined.
    fptosi ( CST to TYPE )
    Convert a floating point constant to the corresponding signed integer - constant. TYPE must be an integer type. CST must be floating point. If the - value won't fit in the integer type, the results are undefined.
    + constant. TYPE must be a scalar or vector integer type. CST must be of scalar + or vector floating point type. Both CST and TYPE must be scalars, or vectors + of the same number of elements. If the value won't fit in the integer type, + the results are undefined.
    uitofp ( CST to TYPE )
    Convert an unsigned integer constant to the corresponding floating point - constant. TYPE must be floating point. CST must be of integer type. If the - value won't fit in the floating point type, the results are undefined.
    + constant. TYPE must be a scalar or vector floating point type. CST must be of + scalar or vector integer type. Both CST and TYPE must be scalars, or vectors + of the same number of elements. If the value won't fit in the floating point + type, the results are undefined.
    sitofp ( CST to TYPE )
    Convert a signed integer constant to the corresponding floating point - constant. TYPE must be floating point. CST must be of integer type. If the - value won't fit in the floating point type, the results are undefined.
    + constant. TYPE must be a scalar or vector floating point type. CST must be of + scalar or vector integer type. Both CST and TYPE must be scalars, or vectors + of the same number of elements. If the value won't fit in the floating point + type, the results are undefined.
    ptrtoint ( CST to TYPE )
    Convert a pointer typed constant to the corresponding integer constant @@ -1318,7 +1677,7 @@ following is the syntax for constant expressions:

    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 - packed types to any other type, as long as they have the same bit width. For + 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.
    @@ -1340,6 +1699,12 @@ following is the syntax for constant expressions:

    fcmp COND ( VAL1, VAL2 )
    Performs the fcmp operation on constants.
    +
    vicmp COND ( VAL1, VAL2 )
    +
    Performs the vicmp operation on constants.
    + +
    vfcmp COND ( VAL1, VAL2 )
    +
    Performs the vfcmp operation on constants.
    +
    extractelement ( VAL, IDX )
    Perform the extractelement @@ -1386,18 +1751,22 @@ indicates whether or not the inline asm expression has side effects. An example inline assembler expression is:

    +
    -  i32 (i32) asm "bswap $0", "=r,r"
+i32 (i32) asm "bswap $0", "=r,r"
    +

    Inline assembler expressions may only be used as the callee operand of a call instruction. Thus, typically we have:

    +
    -  %X = call i32 asm "bswap $0", "=r,r"(i32 %Y)
+%X = call i32 asm "bswap $0", "=r,r"(i32 %Y)
    +

    Inline asms with side effects not visible in the constraint list must be marked @@ -1405,9 +1774,11 @@ as having side effects. This is done through the use of the 'sideeffect' keyword, like so:

    +
    -  call void asm sideeffect "eieio", ""()
+call void asm sideeffect "eieio", ""()
    +

    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 @@ -1459,20 +1830,28 @@ Instruction

    Syntax:
      ret <type> <value>       ; Return a value from a non-void function
   ret void                 ; Return from void function
+  ret <type> <value>, <type> <value>  ; Return two values from a non-void function
    +
    Overview:
    +

    The 'ret' instruction is used to return control flow (and a value) from a function back to the caller.

    There are two forms of the 'ret' instruction: one that -returns a value and then causes control flow, and one that just causes +returns value(s) and then causes control flow, and one that just causes control flow to occur.

    +
    Arguments:
    -

    The 'ret' instruction may return any 'first class' type. Notice that a function is -not well formed if there exists a 'ret' -instruction inside of the function that returns a value that does not -match the return type of the function.

    + +

    The 'ret' instruction may return zero, one or multiple values. +The type of each return value must be a 'first +class' type. Note that a function is not well +formed if there exists a 'ret' instruction inside of the +function that returns values that do not match the return type of the +function.

    +
    Semantics:
    +

    When the 'ret' instruction is executed, control flow returns back to the calling function's context. If the caller is a "call" instruction, execution continues at @@ -1480,10 +1859,16 @@ the instruction after the call. If the caller was an "invoke" 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.

    +return value. If the instruction returns multiple values then these +values can only be accessed through a 'getresult +' instruction.

    +
    Example:
    -
      ret i32 5                       ; Return an integer value of 5
+
+
    +  ret i32 5                       ; Return an integer value of 5
   ret void                        ; Return from a void function
+  ret i32 4, i8 2                 ; Return two values 4 and 2  
 
    
 
 
@@ -1500,8 +1885,8 @@ and an unconditional branch.
    
 
    Arguments:
    
 
    The conditional branch form of the 'br' instruction takes a
 single 'i1' value and two 'label' values.  The
-unconditional form of the 'br' instruction takes a single 'label'
-value as a target.
    
+unconditional form of the 'br' instruction takes a single 
+'label' value as a target.
    
 
    Semantics:
    
 
    Upon execution of a conditional 'br' instruction, the 'i1'
 argument is evaluated.  If the value is true, control flows
@@ -1580,7 +1965,7 @@ branches or with a lookup table.
    
 
    Syntax:
    
 
 
    -  <result> = invoke [cconv] <ptr to function ty> %<function ptr val>(<function args>) 
+  <result> = invoke [cconv] <ptr to function ty> <function ptr val>(<function args>) 
                 to label <normal label> unwind label <exception label>
 
    
 
@@ -1593,7 +1978,9 @@ function, with the possibility of control flow transfer to either the
 "ret" instruction, control flow will return to the
 "normal" label.  If the callee (or any indirect callees) returns with the "unwind" instruction, control is interrupted and
-continued at the dynamically nearest "exception" label.
    
+continued at the dynamically nearest "exception" label. If the callee function 
+returns multiple values then individual return values are only accessible through 
+a 'getresult' instruction.
    
 
 
    Arguments:
    
 
@@ -1601,7 +1988,7 @@ continued at the dynamically nearest "exception" label.
    
 
 
      
   
    1. 
-    The optional "cconv" marker indicates which calling
+    The optional "cconv" marker indicates which calling
     convention the call should use.  If none is specified, the call defaults
     to using C calling conventions.
   
      2. 
@@ -1641,10 +2028,10 @@ exception.  Additionally, this is important for implementation of
 
 
      Example:
      
 
      -  %retval = invoke i32 %Test(i32 15)             to label %Continue
-              unwind label %TestCleanup     ; {i32}:retval set
-  %retval = invoke coldcc i32 %Test(i32 15)             to label %Continue
-              unwind label %TestCleanup     ; {i32}:retval set
+  %retval = invoke i32 @Test(i32 15) to label %Continue
+              unwind label %TestCleanup              ; {i32}:retval set
+  %retval = invoke coldcc i32 %Testfnptr(i32 15) to label %Continue
+              unwind label %TestCleanup              ; {i32}:retval set
 
      
 
 
@@ -1670,7 +2057,7 @@ primarily used to implement exception handling.
      
 
 
      Semantics:
      
 
-
      The 'unwind' intrinsic causes execution of the current function to
+
      The 'unwind' instruction causes execution of the current function to
 immediately halt.  The dynamic call stack is then searched for the first invoke instruction on the call stack.  Once found,
 execution continues at the "exceptional" destination block specified by the
@@ -1708,86 +2095,142 @@ no-return function cannot be reached, and other facts.
      
 
       Binary Operations 
      
 
      
 
      Binary operators are used to do most of the computation in a
-program.  They require two operands, execute an operation on them, and
+program.  They require two operands of the same type, execute an operation on them, and
 produce a single value.  The operands might represent 
-multiple data, as is the case with the packed data type. 
-The result value of a binary operator is not
-necessarily the same type as its operands.
      
+multiple data, as is the case with the vector data type. 
+The result value has the same type as its operands.
      
 
      There are several different binary operators:
      
 
      
 
-
       'add'
-Instruction 
      
+
      
+  'add' Instruction
+
      
+
 
      
+
 
      Syntax:
      
-
        <result> = add <ty> <var1>, <var2>   ; yields {ty}:result
+
+
      +  <result> = add <ty> <var1>, <var2>   ; yields {ty}:result
 
      
+
 
      Overview:
      
+
 
      The 'add' instruction returns the sum of its two operands.
      
+
 
      Arguments:
      
-
      The two arguments to the 'add' instruction must be either integer or floating point values.
- This instruction can also take packed versions of the values.
-Both arguments must have identical types.
      
+
+
      The two arguments to the 'add' instruction must be integer, floating point, or
+ vector values. Both arguments must have identical
+ types.
      
+
 
      Semantics:
      
+
 
      The value produced is the integer or floating point sum of the two
 operands.
      
+
+
      If an integer sum has unsigned overflow, the result returned is the
+mathematical result modulo 2n, where n is the bit width of
+the result.
      
+
+
      Because LLVM integers use a two's complement representation, this
+instruction is appropriate for both signed and unsigned integers.
      
+
 
      Example:
      
-
        <result> = add i32 4, %var          ; yields {i32}:result = 4 + %var
+
+
      +  <result> = add i32 4, %var          ; yields {i32}:result = 4 + %var
 
      
 
      
 
-
       'sub'
-Instruction 
      
+
      
+   'sub' Instruction
+
      
+
 
      
+
 
      Syntax:
      
-
        <result> = sub <ty> <var1>, <var2>   ; yields {ty}:result
+
+
      +  <result> = sub <ty> <var1>, <var2>   ; yields {ty}:result
 
      
+
 
      Overview:
      
+
 
      The 'sub' instruction returns the difference of its two
 operands.
      
-
      Note that the 'sub' instruction is used to represent the 'neg'
-instruction present in most other intermediate representations.
      
+
+
      Note that the 'sub' instruction is used to represent the
+'neg' instruction present in most other intermediate 
+representations.
      
+
 
      Arguments:
      
-
      The two arguments to the 'sub' instruction must be either integer or floating point
-values. 
-This instruction can also take packed versions of the values.
-Both arguments must have identical types.
      
+
+
      The two arguments to the 'sub' instruction must be integer, floating point,
+ or vector values.  Both arguments must have identical
+ types.
      
+
 
      Semantics:
      
+
 
      The value produced is the integer or floating point difference of
 the two operands.
      
+
+
      If an integer difference has unsigned overflow, the result returned is the
+mathematical result modulo 2n, where n is the bit width of
+the result.
      
+
+
      Because LLVM integers use a two's complement representation, this
+instruction is appropriate for both signed and unsigned integers.
      
+
 
      Example:
      
-
        <result> = sub i32 4, %var          ; yields {i32}:result = 4 - %var
+
      +  <result> = sub i32 4, %var          ; yields {i32}:result = 4 - %var
   <result> = sub i32 0, %val          ; yields {i32}:result = -%var
 
      
 
      
+
 
-
       'mul'
-Instruction 
      
+
      
+  'mul' Instruction
+
      
+
 
      
+
 
      Syntax:
      
 
        <result> = mul <ty> <var1>, <var2>   ; yields {ty}:result
 
      
 
      Overview:
      
 
      The  'mul' instruction returns the product of its two
 operands.
      
+
 
      Arguments:
      
-
      The two arguments to the 'mul' instruction must be either integer or floating point
-values. 
-This instruction can also take packed versions of the values.
-Both arguments must have identical types.
      
+
+
      The two arguments to the 'mul' instruction must be integer, floating point,
+or vector values.  Both arguments must have identical
+types.
      
+ 
 
      Semantics:
      
+
 
      The value produced is the integer or floating point product of the
 two operands.
      
-
      Because the operands are the same width, the result of an integer
-multiplication is the same whether the operands should be deemed unsigned or
-signed.
      
+
+
      If the result of an integer multiplication has unsigned overflow,
+the result returned is the mathematical result modulo 
+2n, where n is the bit width of the result.
      
+
      Because LLVM integers use a two's complement representation, and the
+result is the same width as the operands, this instruction returns the
+correct result for both signed and unsigned integers.  If a full product
+(e.g. i32xi32->i64) is needed, the operands
+should be sign-extended or zero-extended as appropriate to the
+width of the full product.
      
 
      Example:
      
 
        <result> = mul i32 4, %var          ; yields {i32}:result = 4 * %var
 
      
 
      
+
 
 
       'udiv' Instruction
 
      
@@ -1798,15 +2241,19 @@ signed.
      
 
      Overview:
      
 
      The 'udiv' instruction returns the quotient of its two
 operands.
      
+
 
      Arguments:
      
+
 
      The two arguments to the 'udiv' instruction must be 
-integer values. Both arguments must have identical 
-types. This instruction can also take packed versions 
-of the values in which case the elements must be integers.
      
+integer or vector of integer
+values.  Both arguments must have identical types.
      
+
 
      Semantics:
      
-
      The value produced is the unsigned integer quotient of the two operands. This
-instruction always performs an unsigned division operation, regardless of 
-whether the arguments are unsigned or not.
      
+
+
      The value produced is the unsigned integer quotient of the two operands.
      
+
      Note that unsigned integer division and signed integer division are distinct
+operations; for signed integer division, use 'sdiv'.
      
+
      Division by zero leads to undefined behavior.
      
 
      Example:
      
 
        <result> = udiv i32 4, %var          ; yields {i32}:result = 4 / %var
 
      
@@ -1816,20 +2263,28 @@ whether the arguments are unsigned or not.
      
  
 
      
 
      Syntax:
      
-
        <result> = sdiv <ty> <var1>, <var2>   ; yields {ty}:result
+
      +  <result> = sdiv <ty> <var1>, <var2>   ; yields {ty}:result
 
      
+
 
      Overview:
      
+
 
      The 'sdiv' instruction returns the quotient of its two
 operands.
      
+
 
      Arguments:
      
-
      The two arguments to the 'sdiv' instruction must be
-integer values.  Both arguments must have identical 
-types. This instruction can also take packed versions 
-of the values in which case the elements must be integers.
      
+
+
      The two arguments to the 'sdiv' instruction must be 
+integer or vector of integer
+values.  Both arguments must have identical types.
      
+
 
      Semantics:
      
-
      The value produced is the signed integer quotient of the two operands. This
-instruction always performs a signed division operation, regardless of whether
-the arguments are signed or not.
      
+
      The value produced is the signed integer quotient of the two operands rounded towards zero.
      
+
      Note that signed integer division and unsigned integer division are distinct
+operations; for unsigned integer division, use 'udiv'.
      
+
      Division by zero leads to undefined behavior. Overflow also leads to
+undefined behavior; this is a rare case, but can occur, for example,
+by doing a 32-bit division of -2147483648 by -1.
      
 
      Example:
      
 
        <result> = sdiv i32 4, %var          ; yields {i32}:result = 4 / %var
 
      
@@ -1839,22 +2294,31 @@ the arguments are signed or not.
      
 Instruction 
      
 
      
 
      Syntax:
      
-
        <result> = fdiv <ty> <var1>, <var2>   ; yields {ty}:result
+
      +  <result> = fdiv <ty> <var1>, <var2>   ; yields {ty}:result
 
      
 
      Overview:
      
+
 
      The 'fdiv' instruction returns the quotient of its two
 operands.
      
+
 
      Arguments:
      
-
      The two arguments to the 'div' instruction must be
-floating point values.  Both arguments must have
-identical types.  This instruction can also take packed
-versions of the values in which case the elements must be floating point.
      
+
+
      The two arguments to the 'fdiv' instruction must be
+floating point or vector
+of floating point values.  Both arguments must have identical types.
      
+
 
      Semantics:
      
+
 
      The value produced is the floating point quotient of the two operands.
      
+
 
      Example:
      
-
        <result> = fdiv float 4.0, %var          ; yields {float}:result = 4.0 / %var
+
+
      +  <result> = fdiv float 4.0, %var          ; yields {float}:result = 4.0 / %var
 
      
 
      
+
 
 
       'urem' Instruction
 
      
@@ -1866,48 +2330,75 @@ versions of the values in which case the elements must be floating point.
      
 
      The 'urem' instruction returns the remainder from the
 unsigned division of its two arguments.
      
 
      Arguments:
      
-
      The two arguments to the 'urem' instruction must be
-integer values. Both arguments must have identical
-types.
      
+
      The two arguments to the 'urem' instruction must be 
+integer or vector of integer
+values.  Both arguments must have identical types.
      
 
      Semantics:
      
 
      This instruction returns the unsigned integer remainder of a division.
-This instruction always performs an unsigned division to get the remainder,
-regardless of whether the arguments are unsigned or not.
      
+This instruction always performs an unsigned division to get the remainder.
      
+
      Note that unsigned integer remainder and signed integer remainder are
+distinct operations; for signed integer remainder, use 'srem'.
      
+
      Taking the remainder of a division by zero leads to undefined behavior.
      
 
      Example:
      
 
        <result> = urem i32 4, %var          ; yields {i32}:result = 4 % %var
 
      
 
 
 
-
       'srem'
-Instruction 
      
+
      
+  'srem' Instruction
+
      
+
 
      
+
 
      Syntax:
      
-
        <result> = srem <ty> <var1>, <var2>   ; yields {ty}:result
+
+
      +  <result> = srem <ty> <var1>, <var2>   ; yields {ty}:result
 
      
+
 
      Overview:
      
+
 
      The 'srem' instruction returns the remainder from the
-signed division of its two operands.
      
+signed division of its two operands. This instruction can also take
+vector versions of the values in which case
+the elements must be integers.
      
+
 
      Arguments:
      
+
 
      The two arguments to the 'srem' instruction must be 
-integer values.  Both arguments must have identical 
-types.
      
+integer or vector of integer
+values.  Both arguments must have identical types.
      
+
 
      Semantics:
      
+
 
      This instruction returns the remainder of a division (where the result
-has the same sign as the divisor), not the modulus (where the
-result has the same sign as the dividend) of a value.  For more
-information about the difference, see var1), not the modulo 
+operator (where the result has the same sign as the divisor, var2) of 
+a value.  For more information about the difference, see The
-Math Forum.
      
+Math Forum. For a table of how this is implemented in various languages,
+please see 
+Wikipedia: modulo operation.
      
+
      Note that signed integer remainder and unsigned integer remainder are
+distinct operations; for unsigned integer remainder, use 'urem'.
      
+
      Taking the remainder of a division by zero leads to undefined behavior.
+Overflow also leads to undefined behavior; this is a rare case, but can occur,
+for example, by taking the remainder of a 32-bit division of -2147483648 by -1.
+(The remainder doesn't actually overflow, but this rule lets srem be 
+implemented using instructions that return both the result of the division
+and the remainder.)
      
 
      Example:
      
 
        <result> = srem i32 4, %var          ; yields {i32}:result = 4 % %var
 
      
 
 
      
 
-
       'frem'
-Instruction 
      
+
      
+  'frem' Instruction 
      
+
 
      
+
 
      Syntax:
      
 
        <result> = frem <ty> <var1>, <var2>   ; yields {ty}:result
 
      
@@ -1916,12 +2407,18 @@ Instruction 
      
 division of its two operands.
      
 
      Arguments:
      
 
      The two arguments to the 'frem' instruction must be
-floating point values.  Both arguments must have 
-identical types.
      
+floating point or vector
+of floating point values.  Both arguments must have identical types.
      
+
 
      Semantics:
      
-
      This instruction returns the remainder of a division.
      
+
+
      This instruction returns the remainder of a division.
+The remainder has the same sign as the dividend.
      
+
 
      Example:
      
-
        <result> = frem float 4.0, %var          ; yields {float}:result = 4.0 % %var
+
+
      +  <result> = frem float 4.0, %var          ; yields {float}:result = 4.0 % %var
 
      
 
 
@@ -1932,24 +2429,137 @@ Operations 
 
      Bitwise binary operators are used to do various forms of
 bit-twiddling in a program.  They are generally very efficient
 instructions and can commonly be strength reduced from other
-instructions.  They require two operands, execute an operation on them,
-and produce a single value.  The resulting value of the bitwise binary
-operators is always the same type as its first operand.
      
+instructions.  They require two operands of the same type, execute an operation on them,
+and produce a single value.  The resulting value is the same type as its operands.
      
+
+
+
+
       'shl'
+Instruction 
      
+
      
+
      Syntax:
      
+
        <result> = shl <ty> <var1>, <var2>   ; yields {ty}:result
+
      
+
+
      Overview:
      
+
+
      The 'shl' instruction returns the first operand shifted to
+the left a specified number of bits.
      
+
+
      Arguments:
      
+
+
      Both arguments to the 'shl' instruction must be the same integer type.  'var2' is treated as an
+unsigned value.  This instruction does not support
+vector operands.
      
+ 
+
      Semantics:
      
+
+
      The value produced is var1 * 2var2 mod 2n,
+where n is the width of the result.  If var2 is (statically or dynamically) negative or
+equal to or larger than the number of bits in var1, the result is undefined.
      
+
+
      Example:
      +  <result> = shl i32 4, %var   ; yields {i32}: 4 << %var
+  <result> = shl i32 4, 2      ; yields {i32}: 16
+  <result> = shl i32 1, 10     ; yields {i32}: 1024
+  <result> = shl i32 1, 32     ; undefined
+
      
+
      
+
+
       'lshr'
+Instruction 
      
+
      
+
      Syntax:
      
+
        <result> = lshr <ty> <var1>, <var2>   ; yields {ty}:result
+
      
+
+
      Overview:
      
+
      The 'lshr' instruction (logical shift right) returns the first 
+operand shifted to the right a specified number of bits with zero fill.
      
+
+
      Arguments:
      
+
      Both arguments to the 'lshr' instruction must be the same 
+integer type.  'var2' is treated as an
+unsigned value.  This instruction does not support
+vector operands.
      
+
+
      Semantics:
      
+
+
      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 var2 is (statically or dynamically) equal to or larger than
+the number of bits in var1, the result is undefined.
      
+
+
      Example:
      
+
      +  <result> = lshr i32 4, 1   ; yields {i32}:result = 2
+  <result> = lshr i32 4, 2   ; yields {i32}:result = 1
+  <result> = lshr i8  4, 3   ; yields {i8}:result = 0
+  <result> = lshr i8 -2, 1   ; yields {i8}:result = 0x7FFFFFFF 
+  <result> = lshr i32 1, 32  ; undefined
+
      
+
      
+
+
+
       'ashr'
+Instruction 
      
+
      
+
+
      Syntax:
      
+
        <result> = ashr <ty> <var1>, <var2>   ; yields {ty}:result
+
      
+
+
      Overview:
      
+
      The 'ashr' instruction (arithmetic shift right) returns the first 
+operand shifted to the right a specified number of bits with sign extension.
      
+
+
      Arguments:
      
+
      Both arguments to the 'ashr' instruction must be the same 
+integer type.  'var2' is treated as an
+unsigned value.  This instruction does not support
+vector operands.
      
+
+
      Semantics:
      
+
      This instruction always performs an arithmetic shift right operation, 
+The most significant bits of the result will be filled with the sign bit 
+of var1.  If var2 is (statically or dynamically) equal to or
+larger than the number of bits in var1, the result is undefined.
+
      
+
+
      Example:
      
+
      +  <result> = ashr i32 4, 1   ; yields {i32}:result = 2
+  <result> = ashr i32 4, 2   ; yields {i32}:result = 1
+  <result> = ashr i8  4, 3   ; yields {i8}:result = 0
+  <result> = ashr i8 -2, 1   ; yields {i8}:result = -1
+  <result> = ashr i32 1, 32  ; undefined
+
      
 
      
+
 
 
       'and'
 Instruction 
      
+
 
      
+
 
      Syntax:
      
-
        <result> = and <ty> <var1>, <var2>   ; yields {ty}:result
+
+
      +  <result> = and <ty> <var1>, <var2>   ; yields {ty}:result
 
      
+
 
      Overview:
      
+
 
      The 'and' instruction returns the bitwise logical and of
 its two operands.
      
+
 
      Arguments:
      
-
      The two arguments to the 'and' instruction must be integral values.  Both arguments must have
-identical types.
      
+
+
      The two arguments to the 'and' instruction must be 
+integer or vector of integer
+values.  Both arguments must have identical types.
      
+
 
      Semantics:
      
 
      The truth table used for the 'and' instruction is:
      
 
       
      
@@ -1985,7 +2595,8 @@ identical types.
      
 
 
      
 
      Example:
      
-
        <result> = and i32 4, %var         ; yields {i32}:result = 4 & %var
+
      +  <result> = and i32 4, %var         ; yields {i32}:result = 4 & %var
   <result> = and i32 15, 40          ; yields {i32}:result = 8
   <result> = and i32 4, 8            ; yields {i32}:result = 0
 
      
@@ -2000,9 +2611,10 @@ identical types.
      
 
      The 'or' instruction returns the bitwise logical inclusive
 or of its two operands.
      
 
      Arguments:
      
-
      The two arguments to the 'or' instruction must be integral values.  Both arguments must have
-identical types.
      
+
+
      The two arguments to the 'or' instruction must be 
+integer or vector of integer
+values.  Both arguments must have identical types.
      
 
      Semantics:
      
 
      The truth table used for the 'or' instruction is:
      
 
       
      
@@ -2055,10 +2667,12 @@ Instruction 
 or of its two operands.  The xor is used to implement the
 "one's complement" operation, which is the "~" operator in C.
      
 
      Arguments:
      
-
      The two arguments to the 'xor' instruction must be integral values.  Both arguments must have
-identical types.
      
+
      The two arguments to the 'xor' instruction must be 
+integer or vector of integer
+values.  Both arguments must have identical types.
      
+
 
      Semantics:
      
+
 
      The truth table used for the 'xor' instruction is:
      
 
       
      
 
      
@@ -2100,89 +2714,6 @@ identical types.
      
   <result> = xor i32 %V, -1          ; yields {i32}:result = ~%V
 
      
 
-
-
       'shl'
-Instruction 
      
-
      
-
      Syntax:
      
-
        <result> = shl <ty> <var1>, i8 <var2>   ; yields {ty}:result
-
      
-
      Overview:
      
-
      The 'shl' instruction returns the first operand shifted to
-the left a specified number of bits.
      
-
      Arguments:
      
-
      The first argument to the 'shl' instruction must be an integer type.  The second argument must be an 'i8'
-type.
      
-
      Semantics:
      
-
      The value produced is var1 * 2var2.
      
-
      Example:
      
-
        <result> = shl i32 4, i8 %var   ; yields {i32}:result = 4 << %var
-  <result> = shl i32 4, i8 2      ; yields {i32}:result = 16
-  <result> = shl i32 1, i8 10     ; yields {i32}:result = 1024
-
      
-
      
-
-
       'lshr'
-Instruction 
      
-
      
-
      Syntax:
      
-
        <result> = lshr <ty> <var1>, i8 <var2>   ; yields {ty}:result
-
      
-
-
      Overview:
      
-
      The 'lshr' instruction (logical shift right) returns the first 
-operand shifted to the right a specified number of bits.
      
-
-
      Arguments:
      
-
      The first argument to the 'lshr' instruction must be an integer type.  The second argument must be an 'i8' type.
      
-
-
      Semantics:
      
-
      This instruction always performs a logical shift right operation. The 
-var2 most significant bits will be filled with zero bits after the 
-shift.
      
-
-
      Example:
      
-
      -  <result> = lshr i32 4, i8 1   ; yields {i32}:result = 2
-  <result> = lshr i32 4, i8 2    ; yields {i32}:result = 1
-  <result> = lshr i8  4, i8 3  ; yields {i8 }:result = 0
-  <result> = lshr i8  -2, i8 1 ; yields {i8 }:result = 0x7FFFFFFF 
-
      
-
      
-
-
-
       'ashr'
-Instruction 
      
-
      
-
-
      Syntax:
      
-
        <result> = ashr <ty> <var1>, i8 <var2>   ; yields {ty}:result
-
      
-
-
      Overview:
      
-
      The 'ashr' instruction (arithmetic shift right) returns the first 
-operand shifted to the right a specified number of bits.
      
-
-
      Arguments:
      
-
      The first argument to the 'ashr' instruction must be an 
-integer type.  The second argument must be an
-'i8' type.
      
-
-
      Semantics:
      
-
      This instruction always performs an arithmetic shift right operation, 
-regardless of whether the arguments are signed or not. The var2 most
-significant bits will be filled with the sign bit of var1.
      
-
-
      Example:
      
-
      -  <result> = ashr i32 4, i8 1    ; yields {i32}:result = 2
-  <result> = ashr i32 4, i8 2      ; yields {i32}:result = 1
-  <result> = ashr i8 4, i8 3    ; yields {i8}:result = 0
-  <result> = ashr i8  -2, i8 1   ; yields {i8 }:result = -1
-
      
-
      
 
 
 
       
@@ -2192,7 +2723,7 @@ significant bits will be filled with the sign bit of var1.
      
 
      
 
 
      LLVM supports several instructions to represent vector operations in a
-target-independent manner.  This instructions cover the element-access and
+target-independent manner.  These instructions cover the element-access and
 vector-specific operations needed to process vectors effectively.  While LLVM
 does directly support these vector operations, many sophisticated algorithms
 will want to use target-specific intrinsics to take full advantage of a specific
@@ -2217,7 +2748,7 @@ target.
      
 
 
      
 The 'extractelement' instruction extracts a single scalar
-element from a packed vector at a specified index.
+element from a vector at a specified index.
 
      
 
 
@@ -2225,7 +2756,7 @@ element from a packed vector at a specified index.
 
 
      
 The first operand of an 'extractelement' instruction is a
-value of packed type.  The second operand is
+value of vector type.  The second operand is
 an index indicating the position from which to extract the element.
 The index may be a variable.
      
 
@@ -2256,14 +2787,14 @@ results are undefined.
 
      Syntax:
      
 
 
      -  <result> = insertelement <n x <ty>> <val>, <ty> <elt>, i32 <idx>    ; yields <n x <ty>>
+  <result> = insertelement <n x <ty>> <val>, <ty> <elt>, i32 <idx>    ; yields <n x <ty>>
 
      
 
 
      Overview:
      
 
 
      
 The 'insertelement' instruction inserts a scalar
-element into a packed vector at a specified index.
+element into a vector at a specified index.
 
      
 
 
@@ -2271,7 +2802,7 @@ element into a packed vector at a specified index.
 
 
      
 The first operand of an 'insertelement' instruction is a
-value of packed type.  The second operand is a
+value of vector type.  The second operand is a
 scalar value whose type must equal the element type of the first
 operand.  The third operand is an index indicating the position at
 which to insert the value.  The index may be a variable.
      
@@ -2279,7 +2810,7 @@ which to insert the value.  The index may be a variable.
      
 
      Semantics:
      
 
 
      
-The result is a packed vector of the same type as val.  Its
+The result is a vector of the same type as val.  Its
 element values are those of val except at position
 idx, where it gets the value elt.  If idx
 exceeds the length of val, the results are undefined.
@@ -2340,7 +2871,7 @@ operand may be undef if performing a shuffle from only one vector.
 
 
         %result = shufflevector <4 x i32> %v1, <4 x i32> %v2, 
-                          <4 x i32> <i32 0, i32 4, i32 1, i32 5>    ; yields <4 x i32>
+                          <4 x i32> <i32 0, i32 4, i32 1, i32 5>  ; yields <4 x i32>
   %result = shufflevector <4 x i32> %v1, <4 x i32> undef, 
                           <4 x i32> <i32 0, i32 1, i32 2, i32 3>  ; yields <4 x i32> - Identity shuffle.
 
      
@@ -2349,21 +2880,19 @@ operand may be undef if performing a shuffle from only one vector.
 
 
 
       
-  Memory Access and Addressing Operations
+  Aggregate Operations
 
      
 
 
      
 
-
      A key design point of an SSA-based representation is how it
-represents memory.  In LLVM, no memory locations are in SSA form, which
-makes things very simple.  This section describes how to read, write,
-allocate, and free memory in LLVM.
      
+
      LLVM supports several instructions for working with aggregate values.
+
      
 
 
      
 
 
 
      
-  'malloc' Instruction
+   'extractvalue' Instruction
 
      
 
 
      
@@ -2371,48 +2900,45 @@ allocate, and free memory in LLVM.
      
 
      Syntax:
      
 
 
      -  <result> = malloc <type>[, i32 <NumElements>][, align <alignment>]     ; yields {type*}:result
+  <result> = extractvalue <aggregate type> <val>, <idx>{, <idx>}*
 
      
 
 
      Overview:
      
 
-
      The 'malloc' instruction allocates memory from the system
-heap and returns a pointer to it.
      
+
      
+The 'extractvalue' instruction extracts the value of a struct field
+or array element from an aggregate value.
+
      
 
-
      Arguments:
      
 
-
      The 'malloc' instruction allocates
-sizeof(<type>)*NumElements
-bytes of memory from the operating system and returns a pointer of the
-appropriate type to the program.  If "NumElements" is specified, it is the
-number of elements allocated.  If an alignment is specified, the value result
-of the allocation is guaranteed to be aligned to at least that boundary.  If
-not specified, or if zero, the target can choose to align the allocation on any
-convenient boundary.
      
+
      Arguments:
      
 
-
      'type' must be a sized type.
      
+
      
+The first operand of an 'extractvalue' instruction is a
+value of struct or array
+type.  The operands are constant indices to specify which value to extract
+in a similar manner as indices in a
+'getelementptr' instruction.
+
      
 
 
      Semantics:
      
 
-
      Memory is allocated using the system "malloc" function, and
-a pointer is returned.
      
+
      
+The result is the value at the position in the aggregate specified by
+the index operands.
+
      
 
 
      Example:
      
 
 
      -  %array  = malloc [4 x i8 ]                    ; yields {[%4 x i8]*}:array
-
-  %size   = add i32 2, 2                          ; yields {i32}:size = i32 4
-  %array1 = malloc i8, i32 4                   ; yields {i8*}:array1
-  %array2 = malloc [12 x i8], i32 %size        ; yields {[12 x i8]*}:array2
-  %array3 = malloc i32, i32 4, align 1024         ; yields {i32*}:array3
-  %array4 = malloc i32, align 1024                 ; yields {i32*}:array4
+  %result = extractvalue {i32, float} %agg, 0    ; yields i32
 
      
 
      
 
+
 
 
      
-  'free' Instruction
+   'insertvalue' Instruction
 
      
 
 
      
@@ -2420,24 +2946,140 @@ a pointer is returned.
      
 
      Syntax:
      
 
 
      -  free <type> <value>                              ; yields {void}
+  <result> = insertvalue <aggregate type> <val>, <ty> <val>, <idx>    ; yields <n x <ty>>
 
      
 
 
      Overview:
      
 
-
      The 'free' instruction returns memory back to the unused
-memory heap to be reallocated in the future.
      
+
      
+The 'insertvalue' instruction inserts a value
+into a struct field or array element in an aggregate.
+
      
+
 
 
      Arguments:
      
 
-
      'value' shall be a pointer value that points to a value
-that was allocated with the 'malloc'
-instruction.
      
+
      
+The first operand of an 'insertvalue' instruction is a
+value of struct or array type.
+The second operand is a first-class value to insert.
+The following operands are constant indices
+indicating the position at which to insert the value in a similar manner as
+indices in a
+'getelementptr' instruction.
+The value to insert must have the same type as the value identified
+by the indices.
 
 
      Semantics:
      
 
-
      Access to the memory pointed to by the pointer is no longer defined
-after this instruction executes.
      
+
      
+The result is an aggregate of the same type as val.  Its
+value is that of val except that the value at the position
+specified by the indices is that of elt.
+
      
+
+
      Example:
      
+
+
      +  %result = insertvalue {i32, float} %agg, i32 1, 0    ; yields {i32, float}
+
      
+
      
+
+
+
+
       
+  Memory Access and Addressing Operations
+
      
+
+
      
+
+
      A key design point of an SSA-based representation is how it
+represents memory.  In LLVM, no memory locations are in SSA form, which
+makes things very simple.  This section describes how to read, write,
+allocate, and free memory in LLVM.
      
+
+
      
+
+
+
      
+  'malloc' Instruction
+
      
+
+
      
+
+
      Syntax:
      
+
+
      +  <result> = malloc <type>[, i32 <NumElements>][, align <alignment>]     ; yields {type*}:result
+
      
+
+
      Overview:
      
+
+
      The 'malloc' instruction allocates memory from the system
+heap and returns a pointer to it. The object is always allocated in the generic 
+address space (address space zero).
      
+
+
      Arguments:
      
+
+
      The 'malloc' instruction allocates
+sizeof(<type>)*NumElements
+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.
      
+
+
      'type' must be a sized type.
      
+
+
      Semantics:
      
+
+
      Memory is allocated using the system "malloc" function, and
+a pointer is returned.  The result of a zero byte allocattion is undefined.  The
+result is null if there is insufficient memory available.
      
+
+
      Example:
      
+
+
      +  %array  = malloc [4 x i8 ]                    ; yields {[%4 x i8]*}:array
+
+  %size   = add i32 2, 2                        ; yields {i32}:size = i32 4
+  %array1 = malloc i8, i32 4                    ; yields {i8*}:array1
+  %array2 = malloc [12 x i8], i32 %size         ; yields {[12 x i8]*}:array2
+  %array3 = malloc i32, i32 4, align 1024       ; yields {i32*}:array3
+  %array4 = malloc i32, align 1024              ; yields {i32*}:array4
+
      
+
      
+
+
+
      
+  'free' Instruction
+
      
+
+
      
+
+
      Syntax:
      
+
+
      +  free <type> <value>                              ; yields {void}
+
      
+
+
      Overview:
      
+
+
      The 'free' instruction returns memory back to the unused
+memory heap to be reallocated in the future.
      
+
+
      Arguments:
      
+
+
      'value' shall be a pointer value that points to a value
+that was allocated with the 'malloc'
+instruction.
      
+
+
      Semantics:
      
+
+
      Access to the memory pointed to by the pointer is no longer defined
+after this instruction executes.  If the pointer is null, the operation
+is a noop.
      
 
 
      Example:
      
 
@@ -2462,37 +3104,40 @@ after this instruction executes.
      
 
 
      Overview:
      
 
-
      The 'alloca' instruction allocates memory on the current
-stack frame of the procedure that is live until the current function
-returns to its caller.
      
+
      The 'alloca' instruction allocates memory on the stack frame of the
+currently executing function, to be automatically released when this function
+returns to its caller. The object is always allocated in the generic address 
+space (address space zero).
      
 
 
      Arguments:
      
 
 
      The 'alloca' instruction allocates sizeof(<type>)*NumElements
 bytes of memory on the runtime stack, returning a pointer of the
-appropriate type to the program.    If "NumElements" is specified, it is the
-number of elements allocated.  If an alignment is specified, the value result
-of the allocation is guaranteed to be aligned to at least that boundary.  If
-not specified, or if zero, the target can choose to align the allocation on any
-convenient boundary.
      
+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.
      
 
 
      'type' may be any sized type.
      
 
 
      Semantics:
      
 
-
      Memory is allocated; a pointer is returned.  'alloca'd
+
      Memory is allocated; a pointer is returned.  The operation is undefiend if
+there is insufficient stack space for the allocation.  'alloca'd
 memory is automatically released when the function returns.  The 'alloca'
 instruction is commonly used to represent automatic variables that must
 have an address available.  When the function returns (either with the ret or unwind
-instructions), the memory is reclaimed.
      
+instructions), the memory is reclaimed.  Allocating zero bytes
+is legal, but the result is undefined.
      
 
 
      Example:
      
 
 
         %ptr = alloca i32                              ; yields {i32*}:ptr
-  %ptr = alloca i32, i32 4                      ; yields {i32*}:ptr
-  %ptr = alloca i32, i32 4, align 1024          ; yields {i32*}:ptr
+  %ptr = alloca i32, i32 4                       ; yields {i32*}:ptr
+  %ptr = alloca i32, i32 4, align 1024           ; yields {i32*}:ptr
   %ptr = alloca i32, align 1024                  ; yields {i32*}:ptr
 
      
 
      
@@ -2502,7 +3147,7 @@ instructions), the memory is reclaimed.
      
 Instruction 
      
 
      
 
      Syntax:
      
-
        <result> = load <ty>* <pointer>
        <result> = volatile load <ty>* <pointer>
      
+
        <result> = load <ty>* <pointer>[, align <alignment>]
        <result> = volatile load <ty>* <pointer>[, align <alignment>]
      
 
      Overview:
      
 
      The 'load' instruction is used to read from memory.
      
 
      Arguments:
      
@@ -2513,6 +3158,16 @@ marked as volatile, then the optimizer is not allowed to modify
 the number or order of execution of this load with other
 volatile load and store
 instructions. 
      
+
      
+The optional constant "align" argument specifies the alignment of the operation
+(that is, the alignment of the memory address). A value of 0 or an
+omitted "align" argument means that the operation has the preferential
+alignment for the target. It is the responsibility of the code emitter
+to ensure that the alignment information is correct. Overestimating
+the alignment results in an undefined behavior. Underestimating the
+alignment may produce less efficient code. An alignment of 1 is always
+safe.
+
      
 
      Semantics:
      
 
      The location of memory pointed to is loaded.
      
 
      Examples:
      
@@ -2527,27 +3182,37 @@ instructions. 
      
 Instruction 
      
 
      
 
      Syntax:
      
-
        store <ty> <value>, <ty>* <pointer>                   ; yields {void}
-  volatile store <ty> <value>, <ty>* <pointer>                   ; yields {void}
+
        store <ty> <value>, <ty>* <pointer>[, align <alignment>]                   ; yields {void}
+  volatile store <ty> <value>, <ty>* <pointer>[, align <alignment>]          ; yields {void}
 
      
 
      Overview:
      
 
      The 'store' instruction is used to write to memory.
      
 
      Arguments:
      
 
      There are two arguments to the 'store' instruction: a value
-to store and an address in which to store it.  The type of the '<pointer>'
-operand must be a pointer to the type of the '<value>'
+to store and an address at which to store it.  The type of the '<pointer>'
+operand must be a pointer to the first class type
+of the '<value>'
 operand. If the store is marked as volatile, then the
 optimizer is not allowed to modify the number or order of execution of
 this store with other volatile load and store instructions.
      
+
      
+The optional constant "align" argument specifies the alignment of the operation
+(that is, the alignment of the memory address). A value of 0 or an
+omitted "align" argument means that the operation has the preferential
+alignment for the target. It is the responsibility of the code emitter
+to ensure that the alignment information is correct. Overestimating
+the alignment results in an undefined behavior. Underestimating the
+alignment may produce less efficient code. An alignment of 1 is always
+safe.
+
      
 
      Semantics:
      
 
      The contents of memory are updated to contain '<value>'
 at the location specified by the '<pointer>' operand.
      
 
      Example:
      
 
        %ptr = alloca i32                               ; yields {i32*}:ptr
-  store i32 3, i32* %ptr                          ; yields {void}
-  %val = load i32* %ptr                           ; yields {i32}:val = i32 3
+  store i32 3, i32* %ptr                          ; yields {void}
+  %val = load i32* %ptr                           ; yields {i32}:val = i32 3
 
      
 
      
 
@@ -2576,43 +3241,45 @@ provided depend on the type of the first pointer argument.  The
 'getelementptr' 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 i32 integer constants are allowed.  When indexing 
-into an array or pointer, only integers of 32 or 64 bits are allowed, and will 
-be sign extended to 64-bit values.
      
+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.
      
 
 
      For example, let's consider a C code fragment and how it gets
 compiled to LLVM:
      
 
+
      
 
      -  struct RT {
-    char A;
-    i32 B[10][20];
-    char C;
-  };
-  struct ST {
-    i32 X;
-    double Y;
-    struct RT Z;
-  };
-
-  define i32 *foo(struct ST *s) {
-    return &s[1].Z.B[5][13];
-  }
+struct RT {
+  char A;
+  int B[10][20];
+  char C;
+};
+struct ST {
+  int X;
+  double Y;
+  struct RT Z;
+};
+
+int *foo(struct ST *s) {
+  return &s[1].Z.B[5][13];
+}
 
      
+
      
 
 
      The LLVM code generated by the GCC frontend is:
      
 
+
      
 
      -  %RT = type { i8 , [10 x [20 x i32]], i8  }
-  %ST = type { i32, double, %RT }
-
-  implementation
+%RT = type { i8 , [10 x [20 x i32]], i8  }
+%ST = type { i32, double, %RT }
 
-  define i32* %foo(%ST* %s) {
-  entry:
-    %reg = getelementptr %ST* %s, i32 1, i32 2, i32 1, i32 5, i32 13
-    ret i32* %reg
-  }
+define i32* %foo(%ST* %s) {
+entry:
+  %reg = getelementptr %ST* %s, i32 1, i32 2, i32 1, i32 5, i32 13
+  ret i32* %reg
+}
 
      
+
      
 
 
      Semantics:
      
 
@@ -2620,8 +3287,8 @@ compiled to LLVM:
      
 on the pointer type that is being indexed into. Pointer
 and array types can use a 32-bit or 64-bit
 integer type but the value will always be sign extended
-to 64-bits.  Structure types, require i32
-constants.
      
+to 64-bits.  Structure and packed
+structure types require i32 constants.
      
 
 
      In the example above, the first index is indexing into the '%ST*'
 type, which is a pointer, yielding a '%ST' = '{ i32, double, %RT
@@ -2640,8 +3307,8 @@ the LLVM code for the given testcase is equivalent to:
      
 
         define i32* %foo(%ST* %s) {
     %t1 = getelementptr %ST* %s, i32 1                        ; yields %ST*:%t1
-    %t2 = getelementptr %ST* %t1, i32 0, i32 2               ; yields %RT*:%t2
-    %t3 = getelementptr %RT* %t2, i32 0, i32 1               ; yields [10 x [20 x i32]]*:%t3
+    %t2 = getelementptr %ST* %t1, i32 0, i32 2                ; yields %RT*:%t2
+    %t3 = getelementptr %RT* %t2, i32 0, i32 1                ; yields [10 x [20 x i32]]*:%t3
     %t4 = getelementptr [10 x [20 x i32]]* %t3, i32 0, i32 5  ; yields [20 x i32]*:%t4
     %t5 = getelementptr [20 x i32]* %t4, i32 0, i32 13        ; yields i32*:%t5
     ret i32* %t5
@@ -2650,7 +3317,7 @@ the LLVM code for the given testcase is equivalent to:
      
 
 
      Note that it is undefined to access an array out of bounds: array and 
 pointer indexes must always be within the defined bounds of the array type.
-The one exception for this rules is zero length arrays.  These arrays are
+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.
      
 
@@ -2695,7 +3362,7 @@ The 'trunc' instruction truncates its operand to the type ty2.
 
      
 The 'trunc' instruction takes a value to trunc, which must 
 be an integer type, and a type that specifies the size 
-and type of the result, which must be an integral 
+and type of the result, which must be an integer 
 type. The bit size of value must be larger than the bit size of 
 ty2. Equal sized types are not allowed.
      
 
@@ -2732,17 +3399,14 @@ It will always truncate bits.
      
 
 
      Arguments:
      
 
      The 'zext' instruction takes a value to cast, which must be of 
-integral type, and a type to cast it to, which must
-also be of integral type. The bit size of the
+integer type, and a type to cast it to, which must
+also be of integer type. The bit size of the
 value must be smaller than the bit size of the destination type, 
 ty2.
      
 
 
      Semantics:
      
 
      The zext fills the high order bits of the value with zero
-bits until it reaches the size of the destination type, ty2. When the
-the operand and the type are the same size, no bit filling is done and the 
-cast is considered a no-op cast because no bits change (only the type 
-changes).
      
+bits until it reaches the size of the destination type, ty2.
      
 
 
      When zero extending from i1, the result will always be either 0 or 1.
      
 
@@ -2770,8 +3434,8 @@ changes).
      
 
      Arguments:
      
 
      
 The 'sext' instruction takes a value to cast, which must be of 
-integral type, and a type to cast it to, which must
-also be of integral type.  The bit size of the
+integer type, and a type to cast it to, which must
+also be of integer type.  The bit size of the
 value must be smaller than the bit size of the destination type, 
 ty2.
      
 
@@ -2779,9 +3443,7 @@ also be of integral type.  The bit size of the
 
      
 The 'sext' instruction performs a sign extension by copying the sign
 bit (highest order bit) of the value until it reaches the bit size of
-the type ty2.  When the the operand and the type are the same size, 
-no bit filling is done and the cast is considered a no-op cast because 
-no bits change (only the type changes).
      
+the type ty2.
      
 
 
      When sign extending from i1, the extension always results in -1 or 0.
      
 
@@ -2853,8 +3515,8 @@ type must be smaller than the destination type.
      
 
 
      Semantics:
      
 
      The 'fpext' instruction extends the value from a smaller
-floating point type to a larger 
-floating point type. The fpext cannot be 
+floating point type to a larger 
+floating point type. The fpext cannot be 
 used to make a no-op cast because it always changes bits. Use 
 bitcast to make a no-op cast for a floating point cast.
      
 
@@ -2867,40 +3529,38 @@ used to make a no-op cast because it always changes bits. Use
 
 
 
      
-   'fptoui .. to' Instruction
+   'fptoui .. to' Instruction
 
      
 
      
 
 
      Syntax:
      
 
      -  <result> = fp2uint <ty> <value> to <ty2>             ; yields ty2
+  <result> = fptoui <ty> <value> to <ty2>             ; yields ty2
 
      
 
 
      Overview:
      
-
      The 'fp2uint' converts a floating point value to its
+
      The 'fptoui' converts a floating point value to its
 unsigned integer equivalent of type ty2.
 
      
 
 
      Arguments:
      
-
      The 'fp2uint' instruction takes a value to cast, which must be a 
-floating point value, and a type to cast it to, which
-must be an integral type.
      
+
      The 'fptoui' instruction takes a value to cast, which must be a 
+scalar or vector floating point value, and a type 
+to cast it to ty2, which must be an integer 
+type. If ty is a vector floating point type, ty2 must be a
+vector integer type with the same number of elements as ty
      
 
 
      Semantics:
      
-
       The 'fp2uint' instruction converts its 
+
       The 'fptoui' instruction converts its 
 floating point operand into the nearest (rounding
 towards zero) unsigned integer value. If the value cannot fit in ty2,
 the results are undefined.
      
 
-
      When converting to i1, the conversion is done as a comparison against 
-zero. If the value was zero, the i1 result will be false. 
-If the value was non-zero, the i1 result will be true.
      
-
 
      Example:
      
 
      -  %X = fp2uint double 123.0 to i32      ; yields i32:123
-  %Y = fp2uint float 1.0E+300 to i1     ; yields i1:true
-  %X = fp2uint float 1.04E+17 to i8     ; yields undefined:1
+  %X = fptoui double 123.0 to i32      ; yields i32:123
+  %Y = fptoui float 1.0E+300 to i1     ; yields undefined:1
+  %X = fptoui float 1.04E+17 to i8     ; yields undefined:1
 
      
 
      
 
@@ -2920,11 +3580,12 @@ If the value was non-zero, the i1 result will be true.
      
 floating point value to type ty2.
 
      
 
-
 
      Arguments:
      
 
       The 'fptosi' instruction takes a value to cast, which must be a 
-floating point value, and a type to cast it to, which 
-must also be an integral type.
      
+scalar or vector floating point value, and a type 
+to cast it to ty2, which must be an integer 
+type. If ty is a vector floating point type, ty2 must be a
+vector integer type with the same number of elements as ty
      
 
 
      Semantics:
      
 
      The 'fptosi' instruction converts its 
@@ -2932,14 +3593,10 @@ must also be an integral type.
      
 towards zero) signed integer value. If the value cannot fit in ty2,
 the results are undefined.
      
 
-
      When converting to i1, the conversion is done as a comparison against 
-zero. If the value was zero, the i1 result will be false. 
-If the value was non-zero, the i1 result will be true.
      
-
 
      Example:
      
 
         %X = fptosi double -123.0 to i32      ; yields i32:-123
-  %Y = fptosi float 1.0E-247 to i1      ; yields i1:true
+  %Y = fptosi float 1.0E-247 to i1      ; yields undefined:1
   %X = fptosi float 1.04E+17 to i8      ; yields undefined:1
 
      
 
      
@@ -2959,22 +3616,22 @@ If the value was non-zero, the i1 result will be true.
      
 
      The 'uitofp' instruction regards value as an unsigned
 integer and converts that value to the ty2 type.
      
 
-
 
      Arguments:
      
-
      The 'uitofp' instruction takes a value to cast, which must be an
-integral value, and a type to cast it to, which must 
-be a floating point type.
      
+
      The 'uitofp' instruction takes a value to cast, which must be a
+scalar or vector integer value, and a type to cast it
+to ty2, which must be an floating point 
+type. If ty is a vector integer type, ty2 must be a vector
+floating point type with the same number of elements as ty
      
 
 
      Semantics:
      
 
      The 'uitofp' instruction interprets its operand as an unsigned
 integer quantity and converts it to the corresponding floating point value. If
 the value cannot fit in the floating point value, the results are undefined.
      
 
-
 
      Example:
      
 
         %X = uitofp i32 257 to float         ; yields float:257.0
-  %Y = uitofp i8  -1 to double       ; yields double:255.0
+  %Y = uitofp i8  -1 to double         ; yields double:255.0
 
      
 
 
@@ -2994,9 +3651,11 @@ the value cannot fit in the floating point value, the results are undefined.
      
 integer and converts that value to the ty2 type.
      
 
 
      Arguments:
      
-
      The 'sitofp' instruction takes a value to cast, which must be an
-integral value, and a type to cast it to, which must be
-a floating point type.
      
+
      The 'sitofp' instruction takes a value to cast, which must be a
+scalar or vector integer value, and a type to cast it
+to ty2, which must be an floating point 
+type. If ty is a vector integer type, ty2 must be a vector
+floating point type with the same number of elements as ty
      
 
 
      Semantics:
      
 
      The 'sitofp' instruction interprets its operand as a signed
@@ -3006,7 +3665,7 @@ the value cannot fit in the floating point value, the results are undefined.
      
 
      Example:
      
 
         %X = sitofp i32 257 to float         ; yields float:257.0
-  %Y = sitofp i8  -1 to double       ; yields double:-1.0
+  %Y = sitofp i8  -1 to double         ; yields double:-1.0
 
      
 
 
@@ -3027,7 +3686,7 @@ the integer type ty2.
      
 
 
      Arguments:
      
 
      The 'ptrtoint' instruction takes a value to cast, which 
-must be a pointer value, and a type to cast it to
+must be a pointer value, and a type to cast it to
 ty2, which must be an integer type. 
 
 
      Semantics:
      
@@ -3036,12 +3695,13 @@ must be a pointer value, and a type to cast it to
 truncating or zero extending that value to the size of the integer type. If
 value is smaller than ty2 then a zero extension is done. If
 value is larger than ty2 then a truncation is done. If they
-are the same size, then nothing is done (no-op cast).
      
+are the same size, then nothing is done (no-op cast) other than a type
+change.
      
 
 
      Example:
      
 
      -  %X = ptrtoint i32* %X to i8           ; yields truncation on 32-bit
-  %Y = ptrtoint i32* %x to i64          ; yields zero extend on 32-bit
+  %X = ptrtoint i32* %X to i8           ; yields truncation on 32-bit architecture
+  %Y = ptrtoint i32* %x to i64          ; yields zero extension on 32-bit architecture
 
      
 
 
@@ -3061,7 +3721,7 @@ are the same size, then nothing is done (no-op cast).
      
 a pointer type, ty2.
      
 
 
      Arguments:
      
-
      The 'inttoptr' instruction takes an integer
+
      The 'inttoptr' instruction takes an integer
 value to cast, and a type to cast it to, which must be a 
 pointer type.
 
@@ -3075,9 +3735,9 @@ nothing is done (no-op cast).
      
 
 
      Example:
      
 
      -  %X = inttoptr i32 255 to i32*            ; yields zero extend on 64-bit
-  %X = inttoptr i32 255 to i32*            ; yields no-op on 32-bit 
-  %Y = inttoptr i16 0 to i32*            ; yields zero extend on 32-bit
+  %X = inttoptr i32 255 to i32*          ; yields zero extension on 64-bit architecture
+  %X = inttoptr i32 255 to i32*          ; yields no-op on 32-bit architecture
+  %Y = inttoptr i64 0 to i32*            ; yields truncation on 32-bit architecture
 
      
 
 
@@ -3093,15 +3753,19 @@ nothing is done (no-op cast).
      
 
      
 
 
      Overview:
      
+
 
      The 'bitcast' instruction converts value to type
 ty2 without changing any bits.
      
 
 
      Arguments:
      
+
 
      The 'bitcast' instruction takes a value to cast, which must be 
 a first class value, and a type to cast it to, which must also be a first class type. The bit sizes of value
 and the destination type, ty2, must be identical. If the source
-type is a pointer, the destination type must also be a pointer.
      
+type is a pointer, the destination type must also be a pointer.  This
+instruction supports bitwise conversion of vectors to integers and to vectors
+of other types (as long as they have the same size).
      
 
 
      Semantics:
      
 
      The 'bitcast' instruction converts value to type
@@ -3114,7 +3778,7 @@ other types, use the inttoptr or
 
 
      Example:
      
 
      -  %X = bitcast i8 255 to i8          ; yields i8 :-1
+  %X = bitcast i8 255 to i8              ; yields i8 :-1
   %Y = bitcast i32* %x to sint*          ; yields sint*:%x
   %Z = bitcast <2xint> %V to i64;        ; yields i64: %V   
 
      
@@ -3132,16 +3796,15 @@ instructions, which defy better classification.
      
 
 
      
 
      Syntax:
      
-
        <result> = icmp <cond> <ty> <var1>, <var2>
-; yields {i1}:result
+
        <result> = icmp <cond> <ty> <var1>, <var2>   ; yields {i1}:result
 
      
 
      Overview:
      
 
      The 'icmp' instruction returns a boolean value based on comparison
-of its two integer operands.
      
+of its two integer or pointer operands.
      
 
      Arguments:
      
 
      The 'icmp' instruction takes three operands. The first operand is
-the condition code which indicates the kind of comparison to perform. It is not
-a value, just a keyword. The possibilities for the condition code are:
+the condition code indicating the kind of comparison to perform. It is not
+a value, just a keyword. The possible condition code are:
 
        
   
      1. eq: equal
        2. 
   
      2. ne: not equal 
        3. 
@@ -3154,7 +3817,7 @@ a value, just a keyword. The possibilities for the condition code are:
   
      3. slt: signed less than
        4. 
   
      4. sle: signed less or equal
        5. 
 
      
-
      The remaining two arguments must be integral or
+
      The remaining two arguments must be integer or
 pointer typed. They must also be identical types.
      
 
      Semantics:
      
 
      The 'icmp' compares var1 and var2 according to 
@@ -3184,10 +3847,7 @@ yields a i1 result, as follows:
   true if var1 is less than or equal to var2.
 
    
 
    If the operands are pointer typed, the pointer
-values are treated as integers and then compared.
    
-
    If the operands are packed typed, the elements of 
-the vector are compared in turn and the predicate must hold for all
-elements.
    
+values are compared as if they were integers.
    
 
 
    Example:
    
 
      <result> = icmp eq i32 4, 5          ; yields: result=false
@@ -3204,16 +3864,15 @@ elements.
    
 
 
    
 
    Syntax:
    
-
      <result> = fcmp <cond> <ty> <var1>, <var2>
-; yields {i1}:result
+
      <result> = fcmp <cond> <ty> <var1>, <var2>     ; yields {i1}:result
 
    
 
    Overview:
    
 
    The 'fcmp' instruction returns a boolean value based on comparison
 of its floating point operands.
    
 
    Arguments:
    
 
    The 'fcmp' instruction takes three operands. The first operand is
-the condition code which indicates the kind of comparison to perform. It is not
-a value, just a keyword. The possibilities for the condition code are:
+the condition code indicating the kind of comparison to perform. It is not
+a value, just a keyword. The possible condition code are:
 
      
   
    1. false: no comparison, always returns false
      2. 
   
    2. oeq: ordered and equal
      3. 
@@ -3232,17 +3891,15 @@ a value, just a keyword. The possibilities for the condition code are:
   
    3. uno: unordered (either nans)
      4. 
   
    4. true: no comparison, always returns true
      5. 
 
    
-
    In the preceding, ordered means that neither operand is a QNAN while
+
    Ordered means that neither operand is a QNAN while
 unordered means that either operand may be a QNAN.
    
 
    The val1 and val2 arguments must be
 floating point typed.  They must have identical 
 types.
    
-
    In the foregoing, ordered means that neither operand is a QNAN and 
-unordered means that either operand is a QNAN.
    
 
    Semantics:
    
-
    The 'fcmp' compares var1 and var2 according to 
-the condition code given as cond. The comparison performed always
-yields a i1 result, as follows: 
+
    The 'fcmp' instruction compares var1 and var2
+according to the condition code given as cond. The comparison performed 
+always yields a i1 result, as follows: 
 
      
   
    1. false: always yields false, regardless of operands.
      2. 
   
    2. oeq: yields true if both operands are not a QNAN and 
@@ -3273,9 +3930,6 @@ yields a i1 result, as follows:
   
    3. uno: yields true if either operand is a QNAN.
      4. 
   
    4. true: always yields true, regardless of operands.
      5. 
 
    
-
    If the operands are packed typed, the elements of 
-the vector are compared in turn and the predicate must hold for all elements.
-
    
 
 
    Example:
    
 
      <result> = fcmp oeq float 4.0, 5.0    ; yields: result=false
@@ -3286,30 +3940,144 @@ the vector are compared in turn and the predicate must hold for all elements.
 
    
 
 
-
     'phi'
-Instruction 
    
+
    
+  'vicmp' Instruction
+
    
+
    
+
    Syntax:
    
+
      <result> = vicmp <cond> <ty> <var1>, <var2>   ; yields {ty}:result
+
    
+
    Overview:
    
+
    The 'vicmp' instruction returns an integer vector value based on
+element-wise comparison of its two integer vector operands.
    
+
    Arguments:
    
+
    The 'vicmp' 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:
+
      
+  
    1. eq: equal
      2. 
+  
    2. ne: not equal 
      3. 
+  
    3. ugt: unsigned greater than
      4. 
+  
    4. uge: unsigned greater or equal
      5. 
+  
    5. ult: unsigned less than
      6. 
+  
    6. ule: unsigned less or equal
      7. 
+  
    7. sgt: signed greater than
      8. 
+  
    8. sge: signed greater or equal
      9. 
+  
    9. slt: signed less than
      10. 
+  
    10. sle: signed less or equal
      11. 
+
    
+
    The remaining two arguments must be vector of 
+integer typed. They must also be identical types.
    
+
    Semantics:
    
+
    The 'vicmp' instruction compares var1 and var2
+according to the condition code given as cond. The comparison yields a 
+vector of integer 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 'icmp'
+instruction.
+
+
    Example:
    
+
    +  <result> = vicmp eq <2 x i32> < i32 4, i32 0>, < i32 5, i32 0>   ; yields: result=<2 x i32> < i32 0, i32 -1 >
+  <result> = vicmp ult <2 x i8 > < i8 1, i8 2>, < i8 2, i8 2 >        ; yields: result=<2 x i8> < i8 -1, i8 0 >
+
    
+
    
+
+
+
    
+  'vfcmp' Instruction
+
    
+
    
+
    Syntax:
    
+
      <result> = vfcmp <cond> <ty> <var1>, <var2>
    
+
    Overview:
    
+
    The 'vfcmp' 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.
    
+
    Arguments:
    
+
    The 'vfcmp' 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:
+
      
+  
    1. false: no comparison, always returns false
      2. 
+  
    2. oeq: ordered and equal
      3. 
+  
    3. ogt: ordered and greater than 
      4. 
+  
    4. oge: ordered and greater than or equal
      5. 
+  
    5. olt: ordered and less than 
      6. 
+  
    6. ole: ordered and less than or equal
      7. 
+  
    7. one: ordered and not equal
      8. 
+  
    8. ord: ordered (no nans)
      9. 
+  
    9. ueq: unordered or equal
      10. 
+  
    10. ugt: unordered or greater than 
      11. 
+  
    11. uge: unordered or greater than or equal
      12. 
+  
    12. ult: unordered or less than 
      13. 
+  
    13. ule: unordered or less than or equal
      14. 
+  
    14. une: unordered or not equal
      15. 
+  
    15. uno: unordered (either nans)
      16. 
+  
    16. true: no comparison, always returns true
      17. 
+
    
+
    The remaining two arguments must be vector of 
+floating point typed. They must also be identical
+types.
    
+
    Semantics:
    
+
    The 'vfcmp' instruction compares var1 and var2
+according to  the condition code given as cond. The comparison yields a 
+vector of integer 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 
+'fcmp' instruction.
+
+
    Example:
    
+
    +  <result> = vfcmp oeq <2 x float> < float 4, float 0 >, < float 5, float 0 >       ; yields: result=<2 x i32> < i32 0, i32 -1 >
+  <result> = vfcmp ult <2 x double> < double 1, double 2 >, < double 2, double 2>   ; yields: result=<2 x i64> < i64 -1, i64 0 >
+
    
+
    
+
+
+
    
+  'phi' Instruction
+
    
+
 
    
+
 
    Syntax:
    
+
 
      <result> = phi <ty> [ <val0>, <label0>], ...
    
 
    Overview:
    
 
    The 'phi' instruction is used to implement the φ node in
 the SSA graph representing the function.
    
 
    Arguments:
    
-
    The type of the incoming values are specified with the first type
+
+
    The type of the incoming values is specified with the first type
 field. After this, the 'phi' instruction takes a list of pairs
 as arguments, with one pair for each predecessor basic block of the
 current block.  Only values of first class
 type may be used as the value arguments to the PHI node.  Only labels
 may be used as the label arguments.
    
+
 
    There must be no non-phi instructions between the start of a basic
 block and the PHI instructions: i.e. PHI instructions must be first in
 a basic block.
    
+
 
    Semantics:
    
-
    At runtime, the 'phi' instruction logically takes on the
-value specified by the parameter, depending on which basic block we
-came from in the last terminator instruction.
    
+
+
    At runtime, the 'phi' instruction logically takes on the value
+specified by the pair corresponding to the predecessor basic block that executed
+just prior to the current block.
    
+
 
    Example:
    
-
    Loop:       ; Infinite loop that counts from 0 on up...
      %indvar = phi i32 [ 0, %LoopHeader ], [ %nextindvar, %Loop ]
      %nextindvar = add i32 %indvar, 1
      br label %Loop
    
+
    +Loop:       ; Infinite loop that counts from 0 on up...
+  %indvar = phi i32 [ 0, %LoopHeader ], [ %nextindvar, %Loop ]
+  %nextindvar = add i32 %indvar, 1
+  br label %Loop
+
    
 
    
 
 
@@ -3336,13 +4104,16 @@ condition, without branching.
 
    Arguments:
    
 
 
    
-The 'select' instruction requires a boolean value indicating the condition, and two values of the same first class type.
+The 'select' instruction requires an 'i1' value indicating the
+condition, and two values of the same first class
+type.  If the val1/val2 are vectors, the entire vectors are selected, not
+individual elements.
 
    
 
 
    Semantics:
    
 
 
    
-If the boolean condition evaluates to true, the instruction returns the first
+If the i1 condition evaluates is 1, the instruction returns the first
 value argument; otherwise, it returns the second value argument.
 
    
 
@@ -3363,7 +4134,7 @@ value argument; otherwise, it returns the second value argument.
 
 
    Syntax:
    
 
    -  <result> = [tail] call [cconv] <ty>* <fnptrval>(<param list>)
+  <result> = [tail] call [cconv] <ty> [<fnty>*] <fnptrval>(<param list>)
 
    
 
 
    Overview:
    
@@ -3383,15 +4154,20 @@ value argument; otherwise, it returns the second value argument.
     href="#i_ret">ret instruction.
   
   
  • 
-    
    The optional "cconv" marker indicates which calling
+    
    The optional "cconv" marker indicates which calling
     convention the call should use.  If none is specified, the call defaults
     to using C calling conventions.
   
    • 
   
  • 
-    
    'ty': shall be the signature of the pointer to function value
-    being invoked.  The argument types must match the types implied by this
-    signature.  This type can be omitted if the function is not varargs and
-    if the function type does not return a pointer to a function.
    
+    
    'ty': the type of the call instruction itself which is also
+    the type of the return value.  Functions that return no value are marked
+    void.
    
+  
    • 
+  
  • 
+    
    'fnty': shall be the signature of the pointer to function
+    value being invoked.  The argument types must match the types implied by
+    this signature.  This type can be omitted if the function is not varargs
+    and if the function type does not return a pointer to a function.
    
   
    • 
   
  • 
     
    'fnptrval': An LLVM value containing a pointer to a function to
@@ -3415,16 +4191,23 @@ transfer to a specified function, with its incoming arguments bound to
 the specified values. Upon a 'ret'
 instruction in the called function, control flow continues with the
 instruction after the function call, and the return value of the
-function is bound to the result argument.  This is a simpler case of
-the invoke instruction.
    
+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 'getresult' instruction.
    
 
 
    Example:
    
 
 
    -  %retval = call i32 %test(i32 %argc)
-  call i32(i8 *, ...) *%printf(i8 * %msg, i32 12, i8  42);
-  %X = tail call i32 %foo()
-  %Y = tail call fastcc i32 %foo()
+  %retval = call i32 @test(i32 %argc)
+  call i32 (i8 *, ...)* @printf(i8 * %msg, i32 12, i8 42)      ; yields i32
+  %X = tail call i32 @foo()                                    ; yields i32
+  %Y = tail call fastcc i32 @foo()  ; yields i32
+  call void %foo(i8 97 signext)
+
+  %struct.A = type { i32, i8 }
+  %r = call %struct.A @foo()                     ; yields { 32, i8 }
+  %gr = getresult %struct.A %r, 0                ; yields i32
+  %gr1 = getresult %struct.A %r, 1               ; yields i8
 
    
 
 
@@ -3452,7 +4235,7 @@ the "variable argument" area of a function call.  It is used to implement the
 
 
    This instruction takes a va_list* value and the type of
 the argument. It returns a value of the specified argument type and
-increments the va_list to point to the next argument.  Again, the
+increments the va_list to point to the next argument.  The
 actual type of va_list is target specific.
    
 
 
    Semantics:
    
@@ -3477,6 +4260,52 @@ argument.
    
 
 
 
+
+
    
+  'getresult' Instruction
+
    
+
+
    
+
+
    Syntax:
    
+
    +  <resultval> = getresult <type> <retval>, <index>
+
    
+
+
    Overview:
    
+
+
     The 'getresult' instruction is used to extract individual values
+from a 'call' 
+or 'invoke' instruction that returns multiple
+results.
    
+
+
    Arguments:
    
+
+
    The 'getresult' instruction takes a call or invoke value as its 
+first argument, or an undef value.  The value must have structure type.  The second argument is a constant 
+unsigned index value which must be in range for the number of values returned 
+by the call.
    
+
+
    Semantics:
    
+
+
    The 'getresult' instruction extracts the element identified by
+'index' from the aggregate value.
    
+
+
    Example:
    
+
+
    +  %struct.A = type { i32, i8 }
+
+  %r = call %struct.A @foo()
+  %gr = getresult %struct.A %r, 0    ; yields i32:%gr
+  %gr1 = getresult %struct.A %r, 1   ; yields i8:%gr1
+  add i32 %gr, 42
+  add i8 %gr1, 41
+
    
+
+
    
+
 
 
     Intrinsic Functions 
    
 
@@ -3484,23 +4313,44 @@ argument.
    
 
    
 
 
    LLVM supports the notion of an "intrinsic function".  These functions have
-well known names and semantics and are required to follow certain
-restrictions. Overall, these instructions represent an extension mechanism for
-the LLVM language that does not require changing all of the transformations in
-LLVM to add to the language (or the bytecode reader/writer, the parser,
-etc...).
    
+well known names and semantics and are required to follow certain restrictions.
+Overall, these intrinsics represent an extension mechanism for the LLVM 
+language that does not require changing all of the transformations in LLVM when 
+adding to the language (or the bitcode reader/writer, the parser, etc...).
    
 
 
    Intrinsic function names must all start with an "llvm." prefix. This
-prefix is reserved in LLVM for intrinsic names; thus, functions may not be named
-this.  Intrinsic functions must always be external functions: you cannot define
-the body of intrinsic functions.  Intrinsic functions may only be used in call
-or invoke instructions: it is illegal to take the address of an intrinsic
-function.  Additionally, because intrinsic functions are part of the LLVM
-language, it is required that they all be documented here if any are added.
    
-
-
-
    To learn how to add an intrinsic function, please see the Extending LLVM Guide.
+prefix is reserved in LLVM for intrinsic names; thus, function names may not
+begin with this prefix.  Intrinsic functions must always be external functions:
+you cannot define the body of intrinsic functions.  Intrinsic functions may
+only be used in call or invoke instructions: it is illegal to take the address
+of an intrinsic function.  Additionally, because intrinsic functions are part
+of the LLVM language, it is required if any are added that they be documented
+here.
    
+
+
    Some intrinsic functions can be overloaded, i.e., the intrinsic represents 
+a family of functions that perform the same operation but on different data 
+types. Because LLVM can represent over 8 million different integer types, 
+overloading is used commonly to allow an intrinsic function to operate on any 
+integer type. One or more of the argument types or the result type can be 
+overloaded to accept any integer type. Argument types may also be defined as 
+exactly matching a previous argument's type or the result type. This allows an 
+intrinsic function which accepts multiple arguments, but needs all of them to 
+be of the same type, to only be overloaded with respect to a single argument or 
+the result.
    
+
+
    Overloaded intrinsics will have the names of its overloaded argument types 
+encoded into its function name, each preceded by a period. Only those types 
+which are overloaded result in a name suffix. Arguments whose type is matched 
+against another type do not. For example, the llvm.ctpop function can 
+take an integer of any width and returns an integer of exactly the same integer 
+width. This leads to a family of functions such as
+i8 @llvm.ctpop.i8(i8 %val) and i29 @llvm.ctpop.i29(i29 %val).
+Only one type, the return type, is overloaded, and only one type suffix is 
+required. Because the argument's type is matched against the return type, it 
+does not require its own name suffix.
    
+
+
    To learn how to add an intrinsic function, please see the 
+Extending LLVM Guide.
 
    
 
 
    
@@ -3520,39 +4370,46 @@ named macros defined in the <stdarg.h> header file.
    
 
    All of these functions operate on arguments that use a
 target-specific value type "va_list".  The LLVM assembly
 language reference manual does not define what this type is, so all
-transformations should be prepared to handle intrinsics with any type
-used.
    
+transformations should be prepared to handle these functions regardless of
+the type used.
    
 
 
    This example shows how the va_arg
 instruction and the variable argument handling intrinsic functions are
 used.
    
 
+
    
 
    -define i32 %test(i32 %X, ...) {
+define i32 @test(i32 %X, ...) {
   ; Initialize variable argument processing
-  %ap = alloca i8 *
+  %ap = alloca i8*
   %ap2 = bitcast i8** %ap to i8*
-  call void %llvm.va_start(i8* %ap2)
+  call void @llvm.va_start(i8* %ap2)
 
   ; Read a single integer argument
-  %tmp = va_arg i8 ** %ap, i32
+  %tmp = va_arg i8** %ap, i32
 
   ; Demonstrate usage of llvm.va_copy and llvm.va_end
-  %aq = alloca i8 *
+  %aq = alloca i8*
   %aq2 = bitcast i8** %aq to i8*
-  call void %llvm.va_copy(i8 *%aq2, i8* %ap2)
-  call void %llvm.va_end(i8* %aq2)
+  call void @llvm.va_copy(i8* %aq2, i8* %ap2)
+  call void @llvm.va_end(i8* %aq2)
 
   ; Stop processing of arguments.
-  call void %llvm.va_end(i8* %ap2)
+  call void @llvm.va_end(i8* %ap2)
   ret i32 %tmp
 }
+
+declare void @llvm.va_start(i8*)
+declare void @llvm.va_copy(i8*, i8*)
+declare void @llvm.va_end(i8*)
 
    
 
    
 
+
+
 
 
    
-  'llvm.va_start' Intrinsic
+  'llvm.va_start' Intrinsic
 
    
 
 
@@ -3572,44 +4429,45 @@ href="#i_va_arg">va_arg    .
    
 
 
    The 'llvm.va_start' intrinsic works just like the va_start
 macro available in C.  In a target-dependent way, it initializes the
-va_list element the argument points to, so that the next call to
+va_list element to which the argument points, so that the next call to
 va_arg will produce the first variable argument passed to the function.
 Unlike the C va_start macro, this intrinsic does not need to know the
-last argument of the function, the compiler can figure that out.
    
+last argument of the function as the compiler can figure that out.
    
 
 
 
 
 
    
- 'llvm.va_end' Intrinsic
+ 'llvm.va_end' Intrinsic
 
    
 
 
    
 
    Syntax:
    
-
      declare void %llvm.va_end(i8* <arglist>)
    
+
      declare void @llvm.va_end(i8* <arglist>)
    
 
    Overview:
    
 
-
    The 'llvm.va_end' intrinsic destroys <arglist>
-which has been initialized previously with llvm.va_start
+
    The 'llvm.va_end' intrinsic destroys *<arglist>,
+which has been initialized previously with llvm.va_start
 or llvm.va_copy.
    
 
 
    Arguments:
    
 
-
    The argument is a va_list to destroy.
    
+
    The argument is a pointer to a va_list to destroy.
    
 
 
    Semantics:
    
 
 
    The 'llvm.va_end' intrinsic works just like the va_end
-macro available in C.  In a target-dependent way, it destroys the va_list.
-Calls to llvm.va_start and llvm.va_copy must be matched exactly
-with calls to llvm.va_end.
    
+macro available in C.  In a target-dependent way, it destroys the
+va_list element to which the argument points.  Calls to llvm.va_start and 
+llvm.va_copy must be matched exactly with calls to
+llvm.va_end.
    
 
 
    
 
 
 
    
-  'llvm.va_copy' Intrinsic
+  'llvm.va_copy' Intrinsic
 
    
 
 
    
@@ -3617,13 +4475,13 @@ with calls to llvm.va_end.
    
 
    Syntax:
    
 
 
    -  declare void %llvm.va_copy(i8* <destarglist>, i8* <srcarglist>)
+  declare void @llvm.va_copy(i8* <destarglist>, i8* <srcarglist>)
 
    
 
 
    Overview:
    
 
-
    The 'llvm.va_copy' intrinsic copies the current argument position from
-the source argument list to the destination argument list.
    
+
    The 'llvm.va_copy' intrinsic copies the current argument position
+from the source argument list to the destination argument list.
    
 
 
    Arguments:
    
 
@@ -3633,11 +4491,12 @@ The second argument is a pointer to a va_list element to copy from.
    
 
 
    Semantics:
    
 
-
    The 'llvm.va_copy' intrinsic works just like the va_copy macro
-available in C.  In a target-dependent way, it copies the source
-va_list element into the destination list.  This intrinsic is necessary
-because the llvm.va_begin intrinsic may be
-arbitrarily complex and require memory allocation, for example.
    
+
    The 'llvm.va_copy' intrinsic works just like the va_copy
+macro available in C.  In a target-dependent way, it copies the source
+va_list element into the destination va_list element.  This
+intrinsic is necessary because the 
+llvm.va_start intrinsic may be arbitrarily complex and require, for
+example, memory allocation.
    
 
 
    
 
@@ -3651,18 +4510,22 @@ arbitrarily complex and require memory allocation, for example.
    
 
    
 LLVM support for Accurate Garbage
 Collection requires the implementation and generation of these intrinsics.
-These intrinsics allow identification of GC roots on the
+These intrinsics allow identification of GC roots on the
 stack, as well as garbage collector implementations that require read and write barriers.
+href="#int_gcread">read and write barriers.
 Front-ends for type-safe garbage collected languages should generate these
 intrinsics to make use of the LLVM garbage collectors.  For more details, see Accurate Garbage Collection with LLVM.
 
    
+
+
    The garbage collection intrinsics only operate on objects in the generic 
+	address space (address space zero).
    
+
 
 
 
 
    
-  'llvm.gcroot' Intrinsic
+  'llvm.gcroot' Intrinsic
 
    
 
 
    
@@ -3670,7 +4533,7 @@ href="GarbageCollection.html">Accurate Garbage Collection with LLVM.
 
    Syntax:
    
 
 
    -  declare void %llvm.gcroot(<ty>** %ptrloc, <ty2>* %metadata)
+  declare void @llvm.gcroot(i8** %ptrloc, i8* %metadata)
 
    
 
 
    Overview:
    
@@ -3686,17 +4549,18 @@ value address) contains the meta-data to be associated with the root.
    
 
 
    Semantics:
    
 
-
    At runtime, a call to this intrinsics stores a null pointer into the "ptrloc"
+
    At runtime, a call to this intrinsic stores a null pointer into the "ptrloc"
 location.  At compile-time, the code generator generates information to allow
-the runtime to find the pointer at GC safe points.
-
    
+the runtime to find the pointer at GC safe points. The 'llvm.gcroot'
+intrinsic may only be used in a function which specifies a GC
+algorithm.
    
 
 
    
 
 
 
 
    
-  'llvm.gcread' Intrinsic
+  'llvm.gcread' Intrinsic
 
    
 
 
    
@@ -3704,7 +4568,7 @@ the runtime to find the pointer at GC safe points.
 
    Syntax:
    
 
 
    -  declare i8 * %llvm.gcread(i8 * %ObjPtr, i8 ** %Ptr)
+  declare i8* @llvm.gcread(i8* %ObjPtr, i8** %Ptr)
 
    
 
 
    Overview:
    
@@ -3724,14 +4588,16 @@ null).
    
 
 
    The 'llvm.gcread' intrinsic has the same semantics as a load
 instruction, but may be replaced with substantially more complex code by the
-garbage collector runtime, as needed.
    
+garbage collector runtime, as needed. The 'llvm.gcread' intrinsic
+may only be used in a function which specifies a GC
+algorithm.
    
 
 
    
 
 
 
 
    
-  'llvm.gcwrite' Intrinsic
+  'llvm.gcwrite' Intrinsic
 
    
 
 
    
@@ -3739,7 +4605,7 @@ garbage collector runtime, as needed.
    
 
    Syntax:
    
 
 
    -  declare void %llvm.gcwrite(i8 * %P1, i8 * %Obj, i8 ** %P2)
+  declare void @llvm.gcwrite(i8* %P1, i8* %Obj, i8** %P2)
 
    
 
 
    Overview:
    
@@ -3759,7 +4625,9 @@ null.
    
 
 
    The 'llvm.gcwrite' intrinsic has the same semantics as a store
 instruction, but may be replaced with substantially more complex code by the
-garbage collector runtime, as needed.
    
+garbage collector runtime, as needed. The 'llvm.gcwrite' intrinsic
+may only be used in a function which specifies a GC
+algorithm.
    
 
 
    
 
@@ -3780,14 +4648,14 @@ be implemented with code generator support.
 
 
 
    
-  'llvm.returnaddress' Intrinsic
+  'llvm.returnaddress' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
 
    -  declare i8  *%llvm.returnaddress(i32 <level>)
+  declare i8  *@llvm.returnaddress(i32 <level>)
 
    
 
 
    Overview:
    
@@ -3825,14 +4693,14 @@ source-language caller.
 
 
 
    
-  'llvm.frameaddress' Intrinsic
+  'llvm.frameaddress' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
 
    -  declare i8  *%llvm.frameaddress(i32 <level>)
+  declare i8 *@llvm.frameaddress(i32 <level>)
 
    
 
 
    Overview:
    
@@ -3868,21 +4736,21 @@ source-language caller.
 
 
 
    
-  'llvm.stacksave' Intrinsic
+  'llvm.stacksave' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
 
    -  declare i8  *%llvm.stacksave()
+  declare i8 *@llvm.stacksave()
 
    
 
 
    Overview:
    
 
 
    
 The 'llvm.stacksave' intrinsic is used to remember the current state of
-the function stack, for use with 
+the function stack, for use with 
 llvm.stackrestore.  This is useful for implementing language
 features like scoped automatic variable sized arrays in C99.
 
    
@@ -3891,7 +4759,7 @@ features like scoped automatic variable sized arrays in C99.
 
 
    
 This intrinsic returns a opaque pointer value that can be passed to llvm.stackrestore.  When an
+href="#int_stackrestore">llvm.stackrestore.  When an
 llvm.stackrestore intrinsic is executed with a value saved from 
 llvm.stacksave, it effectively restores the state of the stack to the
 state it was in when the llvm.stacksave intrinsic executed.  In
@@ -3903,14 +4771,14 @@ that were allocated after the llvm.stacksave was executed.
 
 
 
    
-  'llvm.stackrestore' Intrinsic
+  'llvm.stackrestore' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
 
    -  declare void %llvm.stackrestore(i8 * %ptr)
+  declare void @llvm.stackrestore(i8 * %ptr)
 
    
 
 
    Overview:
    
@@ -3918,7 +4786,7 @@ that were allocated after the llvm.stacksave was executed.
 
    
 The 'llvm.stackrestore' intrinsic is used to restore the state of
 the function stack to the state it was in when the corresponding llvm.stacksave intrinsic executed.  This is
+href="#int_stacksave">llvm.stacksave intrinsic executed.  This is
 useful for implementing language features like scoped automatic variable sized
 arrays in C99.
 
    
@@ -3926,7 +4794,7 @@ arrays in C99.
 
    Semantics:
    
 
 
    
-See the description for llvm.stacksave.
+See the description for llvm.stacksave.
 
    
 
 
    
@@ -3934,15 +4802,14 @@ See the description for llvm.stacksave.
 
 
 
    
-  'llvm.prefetch' Intrinsic
+  'llvm.prefetch' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
 
    -  declare void %llvm.prefetch(i8  * <address>,
-                                i32 <rw>, i32 <locality>)
+  declare void @llvm.prefetch(i8* <address>, i32 <rw>, i32 <locality>)
 
    
 
 
    Overview:
    
@@ -3979,14 +4846,14 @@ performance.
 
 
 
    
-  'llvm.pcmarker' Intrinsic
+  'llvm.pcmarker' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
 
    -  declare void %llvm.pcmarker( i32 <id> )
+  declare void @llvm.pcmarker(i32 <id>)
 
    
 
 
    Overview:
    
@@ -4020,14 +4887,14 @@ support this intrinisic may ignore it.
 
 
 
    
-  'llvm.readcyclecounter' Intrinsic
+  'llvm.readcyclecounter' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
 
    -  declare i64 %llvm.readcyclecounter( )
+  declare i64 @llvm.readcyclecounter( )
 
    
 
 
    Overview:
    
@@ -4068,16 +4935,16 @@ for more efficient code generation.
 
 
 
    
-  'llvm.memcpy' Intrinsic
+  'llvm.memcpy' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
 
    -  declare void %llvm.memcpy.i32(i8 * <dest>, i8 * <src>,
+  declare void @llvm.memcpy.i32(i8 * <dest>, i8 * <src>,
                                 i32 <len>, i32 <align>)
-  declare void %llvm.memcpy.i64(i8 * <dest>, i8 * <src>,
+  declare void @llvm.memcpy.i64(i8 * <dest>, i8 * <src>,
                                 i64 <len>, i32 <align>)
 
    
 
@@ -4122,16 +4989,16 @@ be set to 0 or 1.
 
 
 
    
-  'llvm.memmove' Intrinsic
+  'llvm.memmove' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
 
    -  declare void %llvm.memmove.i32(i8 * <dest>, i8 * <src>,
+  declare void @llvm.memmove.i32(i8 * <dest>, i8 * <src>,
                                  i32 <len>, i32 <align>)
-  declare void %llvm.memmove.i64(i8 * <dest>, i8 * <src>,
+  declare void @llvm.memmove.i64(i8 * <dest>, i8 * <src>,
                                  i64 <len>, i32 <align>)
 
    
 
@@ -4140,7 +5007,7 @@ be set to 0 or 1.
 
    
 The 'llvm.memmove.*' intrinsics move a block of memory from the source
 location to the destination location. It is similar to the
-'llvm.memcmp' intrinsic but allows the two memory locations to overlap.
+'llvm.memcpy' intrinsic but allows the two memory locations to overlap.
 
    
 
 
    
@@ -4177,16 +5044,16 @@ be set to 0 or 1.
 
 
 
    
-  'llvm.memset.*' Intrinsics
+  'llvm.memset.*' Intrinsics
 
    
 
 
    
 
 
    Syntax:
    
 
    -  declare void %llvm.memset.i32(i8 * <dest>, i8 <val>,
+  declare void @llvm.memset.i32(i8 * <dest>, i8 <val>,
                                 i32 <len>, i32 <align>)
-  declare void %llvm.memset.i64(i8 * <dest>, i8 <val>,
+  declare void @llvm.memset.i64(i8 * <dest>, i8 <val>,
                                 i64 <len>, i32 <align>)
 
    
 
@@ -4230,24 +5097,32 @@ this can be specified as the fourth argument, otherwise it should be set to 0 or
 
 
 
    
-  'llvm.sqrt.*' Intrinsic
+  'llvm.sqrt.*' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
+
    This is an overloaded intrinsic. You can use llvm.sqrt on any 
+floating point or vector of floating point type. Not all targets support all
+types however.
 
    -  declare float %llvm.sqrt.f32(float %Val)
-  declare double %llvm.sqrt.f64(double %Val)
+  declare float     @llvm.sqrt.f32(float %Val)
+  declare double    @llvm.sqrt.f64(double %Val)
+  declare x86_fp80  @llvm.sqrt.f80(x86_fp80 %Val)
+  declare fp128     @llvm.sqrt.f128(fp128 %Val)
+  declare ppc_fp128 @llvm.sqrt.ppcf128(ppc_fp128 %Val)
 
    
 
 
    Overview:
    
 
 
    
 The 'llvm.sqrt' intrinsics return the sqrt of the specified operand,
-returning the same value as the libm 'sqrt' function would.  Unlike
+returning the same value as the libm 'sqrt' functions would.  Unlike
 sqrt in libm, however, llvm.sqrt has undefined behavior for
-negative numbers (which allows for better optimization).
+negative numbers other than -0.0 (which allows for better optimization, because
+there is no need to worry about errno being set).  llvm.sqrt(-0.0) is
+defined to return -0.0 like IEEE sqrt.
 
    
 
 
    Arguments:
    
@@ -4259,22 +5134,28 @@ The argument and return value are floating point numbers of the same type.
 
    Semantics:
    
 
 
    
-This function returns the sqrt of the specified operand if it is a positive
+This function returns the sqrt of the specified operand if it is a nonnegative
 floating point number.
 
    
 
    
 
 
 
    
-  'llvm.powi.*' Intrinsic
+  'llvm.powi.*' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
+
    This is an overloaded intrinsic. You can use llvm.powi on any 
+floating point or vector of floating point type. Not all targets support all
+types however.
 
    -  declare float  %llvm.powi.f32(float  %Val, i32 %power)
-  declare double %llvm.powi.f64(double %Val, i32 %power)
+  declare float     @llvm.powi.f32(float  %Val, i32 %power)
+  declare double    @llvm.powi.f64(double %Val, i32 %power)
+  declare x86_fp80  @llvm.powi.f80(x86_fp80  %Val, i32 %power)
+  declare fp128     @llvm.powi.f128(fp128 %Val, i32 %power)
+  declare ppc_fp128 @llvm.powi.ppcf128(ppc_fp128  %Val, i32 %power)
 
    
 
 
    Overview:
    
@@ -4282,7 +5163,8 @@ floating point number.
 
    
 The 'llvm.powi.*' intrinsics return the first operand raised to the
 specified (positive or negative) power.  The order of evaluation of
-multiplications is not defined.
+multiplications is not defined.  When a vector of floating point type is
+used, the second argument remains a scalar integer value.
 
    
 
 
    Arguments:
    
@@ -4299,89 +5181,216 @@ This function returns the first value raised to the second power with an
 unspecified sequence of rounding operations.
    
 
    
 
-
-
-
    
-  Bit Manipulation Intrinsics
-
    
-
-
    
-
    
-LLVM provides intrinsics for a few important bit manipulation operations.
-These allow efficient code generation for some algorithms.
-
    
-
-
    
-
 
 
    
-  'llvm.bswap.*' Intrinsics
+  'llvm.sin.*' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
+
    This is an overloaded intrinsic. You can use llvm.sin on any 
+floating point or vector of floating point type. Not all targets support all
+types however.
 
    -  declare i16 %llvm.bswap.i16(i16 <id>)
-  declare i32 %llvm.bswap.i32(i32 <id>)
-  declare i64 %llvm.bswap.i64(i64 <id>)
+  declare float     @llvm.sin.f32(float  %Val)
+  declare double    @llvm.sin.f64(double %Val)
+  declare x86_fp80  @llvm.sin.f80(x86_fp80  %Val)
+  declare fp128     @llvm.sin.f128(fp128 %Val)
+  declare ppc_fp128 @llvm.sin.ppcf128(ppc_fp128  %Val)
 
    
 
 
    Overview:
    
 
 
    
-The 'llvm.bwsap' family of intrinsics is used to byteswap a 16, 32 or
-64 bit quantity.  These are useful for performing operations on data that is not
-in the target's  native byte order.
+The 'llvm.sin.*' intrinsics return the sine of the operand.
 
    
 
-
    Semantics:
    
+
    Arguments:
    
 
 
    
-The llvm.bswap.16 intrinsic returns an i16 value that has the high 
-and low byte of the input i16 swapped.  Similarly, the llvm.bswap.i32 
-intrinsic returns an i32 value that has the four bytes of the input i32 
-swapped, so that if the input bytes are numbered 0, 1, 2, 3 then the returned 
-i32 will have its bytes in 3, 2, 1, 0 order.  The llvm.bswap.i64 
-intrinsic extends this concept to 64 bits.
+The argument and return value are floating point numbers of the same type.
 
    
 
+
    Semantics:
    
+
+
    
+This function returns the sine of the specified operand, returning the
+same values as the libm sin functions would, and handles error
+conditions in the same way.
    
 
    
 
 
 
    
-  'llvm.ctpop.*' Intrinsic
+  'llvm.cos.*' Intrinsic
 
    
 
 
    
 
 
    Syntax:
    
+
    This is an overloaded intrinsic. You can use llvm.cos on any 
+floating point or vector of floating point type. Not all targets support all
+types however.
 
    -  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>)
+  declare float     @llvm.cos.f32(float  %Val)
+  declare double    @llvm.cos.f64(double %Val)
+  declare x86_fp80  @llvm.cos.f80(x86_fp80  %Val)
+  declare fp128     @llvm.cos.f128(fp128 %Val)
+  declare ppc_fp128 @llvm.cos.ppcf128(ppc_fp128  %Val)
 
    
 
 
    Overview:
    
 
 
    
-The 'llvm.ctpop' family of intrinsics counts the number of bits set in a 
-value.
+The 'llvm.cos.*' intrinsics return the cosine of the operand.
 
    
 
 
    Arguments:
    
 
 
    
-The only argument is the value to be counted.  The argument may be of any
-integer type.  The return type must match the argument type.
+The argument and return value are floating point numbers of the same type.
 
    
 
 
    Semantics:
    
 
 
    
-The 'llvm.ctpop' intrinsic counts the 1's in a variable.
-
    
+This function returns the cosine of the specified operand, returning the
+same values as the libm cos functions would, and handles error
+conditions in the same way.
    
+
    
+
+
+
    
+  'llvm.pow.*' Intrinsic
+
    
+
+
    
+
+
    Syntax:
    
+
    This is an overloaded intrinsic. You can use llvm.pow on any 
+floating point or vector of floating point type. Not all targets support all
+types however.
+
    +  declare float     @llvm.pow.f32(float  %Val, float %Power)
+  declare double    @llvm.pow.f64(double %Val, double %Power)
+  declare x86_fp80  @llvm.pow.f80(x86_fp80  %Val, x86_fp80 %Power)
+  declare fp128     @llvm.pow.f128(fp128 %Val, fp128 %Power)
+  declare ppc_fp128 @llvm.pow.ppcf128(ppc_fp128  %Val, ppc_fp128 Power)
+
    
+
+
    Overview:
    
+
+
    
+The 'llvm.pow.*' intrinsics return the first operand raised to the
+specified (positive or negative) power.
+
    
+
+
    Arguments:
    
+
+
    
+The second argument is a floating point power, and the first is a value to
+raise to that power.
+
    
+
+
    Semantics:
    
+
+
    
+This function returns the first value raised to the second power,
+returning the
+same values as the libm pow functions would, and handles error
+conditions in the same way.
    
+
    
+
+
+
+
    
+  Bit Manipulation Intrinsics
+
    
+
+
    
+
    
+LLVM provides intrinsics for a few important bit manipulation operations.
+These allow efficient code generation for some algorithms.
+
    
+
+
    
+
+
+
    
+  'llvm.bswap.*' Intrinsics
+
    
+
+
    
+
+
    Syntax:
    
+
    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).
+
    +  declare i16 @llvm.bswap.i16(i16 <id>)
+  declare i32 @llvm.bswap.i32(i32 <id>)
+  declare i64 @llvm.bswap.i64(i64 <id>)
+
    
+
+
    Overview:
    
+
+
    
+The 'llvm.bswap' family of intrinsics is used to byte swap integer 
+values with an even number of bytes (positive multiple of 16 bits).  These are 
+useful for performing operations on data that is not in the target's native 
+byte order.
+
    
+
+
    Semantics:
    
+
+
    
+The llvm.bswap.i16 intrinsic returns an i16 value that has the high 
+and low byte of the input i16 swapped.  Similarly, the llvm.bswap.i32 
+intrinsic returns an i32 value that has the four bytes of the input i32 
+swapped, so that if the input bytes are numbered 0, 1, 2, 3 then the returned 
+i32 will have its bytes in 3, 2, 1, 0 order.  The llvm.bswap.i48, 
+llvm.bswap.i64 and other intrinsics extend this concept to
+additional even-byte lengths (6 bytes, 8 bytes and more, respectively).
+
    
+
+
    
+
+
+
    
+  'llvm.ctpop.*' Intrinsic
+
    
+
+
    
+
+
    Syntax:
    
+
    This is an overloaded intrinsic. You can use llvm.ctpop on any integer bit
+width. Not all targets support all bit widths however.
+
    +  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>)
+  declare i256 @llvm.ctpop.i256(i256 <src>)
+
    
+
+
    Overview:
    
+
+
    
+The 'llvm.ctpop' family of intrinsics counts the number of bits set in a 
+value.
+
    
+
+
    Arguments:
    
+
+
    
+The only argument is the value to be counted.  The argument may be of any
+integer type.  The return type must match the argument type.
+
    
+
+
    Semantics:
    
+
+
    
+The 'llvm.ctpop' intrinsic counts the 1's in a variable.
+
    
 
    
 
 
@@ -4392,11 +5401,14 @@ The 'llvm.ctpop' intrinsic counts the 1's in a variable.
 
    
 
 
    Syntax:
    
+
    This is an overloaded intrinsic. You can use llvm.ctlz on any 
+integer bit width. Not all targets support all bit widths however.
 
    -  declare i8  %llvm.ctlz.i8 (i8  <src>)
-  declare i16 %llvm.ctlz.i16(i16 <src>)
-  declare i32 %llvm.ctlz.i32(i32 <src>)
-  declare i64 %llvm.ctlz.i64(i64 <src>)
+  declare i8 @llvm.ctlz.i8 (i8  <src>)
+  declare i16 @llvm.ctlz.i16(i16 <src>)
+  declare i32 @llvm.ctlz.i32(i32 <src>)
+  declare i64 @llvm.ctlz.i64(i64 <src>)
+  declare i256 @llvm.ctlz.i256(i256 <src>)
 
    
 
 
    Overview:
    
@@ -4432,11 +5444,14 @@ of src. For example, llvm.ctlz(i32 2) = 30.
 
    
 
 
    Syntax:
    
+
    This is an overloaded intrinsic. You can use llvm.cttz on any 
+integer bit width. Not all targets support all bit widths however.
 
    -  declare i8  %llvm.cttz.i8 (i8  <src>)
-  declare i16 %llvm.cttz.i16(i16 <src>)
-  declare i32 %llvm.cttz.i32(i32 <src>)
-  declare i64 %llvm.cttz.i64(i64 <src>)
+  declare i8 @llvm.cttz.i8 (i8  <src>)
+  declare i16 @llvm.cttz.i16(i16 <src>)
+  declare i32 @llvm.cttz.i32(i32 <src>)
+  declare i64 @llvm.cttz.i64(i64 <src>)
+  declare i256 @llvm.cttz.i256(i256 <src>)
 
    
 
 
    Overview:
    
@@ -4462,6 +5477,105 @@ of src.  For example, llvm.cttz(2) = 1.
 
    
 
    
 
+
+
    
+  'llvm.part.select.*' Intrinsic
+
    
+
+
    
+
+
    Syntax:
    
+
    This is an overloaded intrinsic. You can use llvm.part.select 
+on any integer bit width.
+
    +  declare i17 @llvm.part.select.i17 (i17 %val, i32 %loBit, i32 %hiBit)
+  declare i29 @llvm.part.select.i29 (i29 %val, i32 %loBit, i32 %hiBit)
+
    
+
+
    Overview:
    
+
    The 'llvm.part.select' 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.
    
+
+
    Arguments:
    
+
    The first argument, %val 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 i32 type since they specify only a bit index.
    
+
+
    Semantics:
    
+
    The operation of the 'llvm.part.select' intrinsic has two modes
+of operation: forwards and reverse. If %loBit is greater than
+%hiBits then the intrinsic operates in reverse mode. Otherwise it
+operates in forward mode.
    
+
    In forward mode, this intrinsic is the equivalent of shifting %val
+right by %loBit bits and then ANDing it with a mask with
+only the %hiBit - %loBit bits set, as follows:
    
+
      
+  
    1. The %val is shifted right (LSHR) by the number of bits specified
+  by %loBits. This normalizes the value to the low order bits.
      2. 
+  
    2. The %loBits value is subtracted from the %hiBits value
+  to determine the number of bits to retain.
      3. 
+  
    3. A mask of the retained bits is created by shifting a -1 value.
      4. 
+  
    4. The mask is ANDed with %val to produce the result.
+
    
+
    In reverse mode, a similar computation is made except that the bits are
+returned in the reverse order. So, for example, if X has the value
+i16 0x0ACF (101011001111) and we apply 
+part.select(i16 X, 8, 3) to it, we get back the value 
+i16 0x0026 (000000100110).
    
+
    
+
+
    
+  'llvm.part.set.*' Intrinsic
+
    
+
+
    
+
+
    Syntax:
    
+
    This is an overloaded intrinsic. You can use llvm.part.set 
+on any integer bit width.
+
    +  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)
+
    
+
+
    Overview:
    
+
    The 'llvm.part.set' 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.
    
+
+
    Arguments:
    
+
    The first argument, %val and the result may be integer types of 
+any bit width but they must have the same bit width. %val is the value
+whose bits will be replaced.  The second argument, %repl may be an
+integer of any bit width. The third and fourth arguments must be i32 
+type since they specify only a bit index.
    
+
+
    Semantics:
    
+
    The operation of the 'llvm.part.set' intrinsic has two modes
+of operation: forwards and reverse. If %lo is greater than
+%hi then the intrinsic operates in reverse mode. Otherwise it
+operates in forward mode.
    
+
    For both modes, the %repl 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.
    
+
    In forward mode, the bits between %lo and %hi (inclusive)
+are replaced with corresponding bits from %repl. That is the 0th bit
+in %repl replaces the %loth bit in %val and etc. up
+to the %hith bit. 
+
    In reverse mode, a similar computation is made except that the bits are
+reversed.  That is, the 0th bit in %repl replaces the 
+%hi bit in %val and etc. down to the %loth bit.
+
    Examples:
    
+
    +  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
+
    
+
    
+
 
 
    
   Debugger Intrinsics
@@ -4477,17 +5591,495 @@ Debugging document.
 
    
 
 
+
+
    
+  Exception Handling Intrinsics
+
    
+
+
    
+
     The LLVM exception handling intrinsics (which all start with
+llvm.eh. prefix), are described in the LLVM Exception
+Handling document. 
    
+
    
+
+
+
    
+  Trampoline Intrinsic
+
    
+
+
    
+
    
+  This intrinsic makes it possible to excise one parameter, marked with
+  the nest attribute, from a function.  The result is a callable
+  function pointer lacking the nest parameter - the caller does not need
+  to provide a value for it.  Instead, the value to use is stored in
+  advance in a "trampoline", a block of memory usually allocated
+  on the stack, which also contains code to splice the nest value into the
+  argument list.  This is used to implement the GCC nested function address
+  extension.
+
    
+
    
+  For example, if the function is
+  i32 f(i8* nest  %c, i32 %x, i32 %y) then the resulting function
+  pointer has signature i32 (i32, i32)*.  It can be created as follows:
    
+
    +  %tramp = alloca [10 x i8], align 4 ; size and alignment only correct for X86
+  %tramp1 = getelementptr [10 x i8]* %tramp, i32 0, i32 0
+  %p = call i8* @llvm.init.trampoline( i8* %tramp1, i8* bitcast (i32 (i8* nest , i32, i32)* @f to i8*), i8* %nval )
+  %fp = bitcast i8* %p to i32 (i32, i32)*
+
    
+  
    The call %val = call i32 %fp( i32 %x, i32 %y ) is then equivalent
+  to %val = call i32 %f( i8* %nval, i32 %x, i32 %y ).
    
+
    
+
+
+
    
+  'llvm.init.trampoline' Intrinsic
+
    
+
    
+
    Syntax:
    
+
    +declare i8* @llvm.init.trampoline(i8* <tramp>, i8* <func>, i8* <nval>)
+
    
+
    Overview:
    
+
    
+  This fills the memory pointed to by tramp with code
+  and returns a function pointer suitable for executing it.
+
    
+
    Arguments:
    
+
    
+  The llvm.init.trampoline intrinsic takes three arguments, all
+  pointers.  The tramp argument must point to a sufficiently large
+  and sufficiently aligned block of memory; this memory is written to by the
+  intrinsic.  Note that the size and the alignment are target-specific - LLVM
+  currently provides no portable way of determining them, so a front-end that
+  generates this intrinsic needs to have some target-specific knowledge.
+  The func argument must hold a function bitcast to an i8*.
+
    
+
    Semantics:
    
+
    
+  The block of memory pointed to by tramp is filled with target
+  dependent code, turning it into a function.  A pointer to this function is
+  returned, but needs to be bitcast to an
+  appropriate function pointer type
+  before being called.  The new function's signature is the same as that of
+  func with any arguments marked with the nest attribute
+  removed.  At most one such nest argument is allowed, and it must be
+  of pointer type.  Calling the new function is equivalent to calling
+  func with the same argument list, but with nval used for the
+  missing nest argument.  If, after calling
+  llvm.init.trampoline, the memory pointed to by tramp is
+  modified, then the effect of any later call to the returned function pointer is
+  undefined.
+
    
+
    
+
+
+
    
+  Atomic Operations and Synchronization Intrinsics
+
    
+
+
    
+
    
+  These intrinsic functions expand the "universal IR" of LLVM to represent 
+  hardware constructs for atomic operations and memory synchronization.  This 
+  provides an interface to the hardware, not an interface to the programmer. It 
+  is aimed at a low enough level to allow any programming models or APIs which 
+  need atomic behaviors to map cleanly onto it. It is also modeled primarily on 
+  hardware behavior. Just as hardware provides a "universal IR" for source 
+  languages, it also provides a starting point for developing a "universal" 
+  atomic operation and synchronization IR.
+
    
+
    
+  These do not form an API such as high-level threading libraries, 
+  software transaction memory systems, atomic primitives, and intrinsic 
+  functions as found in BSD, GNU libc, atomic_ops, APR, and other system and 
+  application libraries.  The hardware interface provided by LLVM should allow 
+  a clean implementation of all of these APIs and parallel programming models. 
+  No one model or paradigm should be selected above others unless the hardware 
+  itself ubiquitously does so.
+
+
    
+
    
+
+
+
    
+  'llvm.memory.barrier' Intrinsic
+
    
+
    
+
    Syntax:
    
+
    +declare void @llvm.memory.barrier( i1 <ll>, i1 <ls>, i1 <sl>, i1 <ss>, 
+i1 <device> )
+
+
    
+
    Overview:
    
+
    
+  The llvm.memory.barrier intrinsic guarantees ordering between 
+  specific pairs of memory access types.
+
    
+
    Arguments:
    
+
    
+  The llvm.memory.barrier intrinsic requires five boolean arguments. 
+  The first four arguments enables a specific barrier as listed below.  The fith
+  argument specifies that the barrier applies to io or device or uncached memory.
+
+
    
+  
      
+    
    • ll: load-load barrier
      • 
+    
    • ls: load-store barrier
      • 
+    
    • sl: store-load barrier
      • 
+    
    • ss: store-store barrier
      • 
+    
    • device: barrier applies to device and uncached memory also.
+  
    
+
    Semantics:
    
+
    
+  This intrinsic causes the system to enforce some ordering constraints upon 
+  the loads and stores of the program. This barrier does not indicate 
+  when any events will occur, it only enforces an order in 
+  which they occur. For any of the specified pairs of load and store operations 
+  (f.ex.  load-load, or store-load), all of the first operations preceding the 
+  barrier will complete before any of the second operations succeeding the 
+  barrier begin. Specifically the semantics for each pairing is as follows:
+
    
+  
      
+    
    • ll: All loads before the barrier must complete before any load 
+    after the barrier begins.
      • 
+
+    
    • ls: All loads before the barrier must complete before any 
+    store after the barrier begins.
      • 
+    
    • ss: All stores before the barrier must complete before any 
+    store after the barrier begins.
      • 
+    
    • sl: All stores before the barrier must complete before any 
+    load after the barrier begins.
      • 
+  
    
+
    
+  These semantics are applied with a logical "and" behavior when more than  one 
+  is enabled in a single memory barrier intrinsic.  
+
    
+
    
+  Backends may implement stronger barriers than those requested when they do not
+  support as fine grained a barrier as requested.  Some architectures do not
+  need all types of barriers and on such architectures, these become noops.
+
    
+
    Example:
    
+
    +%ptr      = malloc i32
+            store i32 4, %ptr
+
+%result1  = load i32* %ptr      ; yields {i32}:result1 = 4
+            call void @llvm.memory.barrier( i1 false, i1 true, i1 false, i1 false )
+                                ; guarantee the above finishes
+            store i32 8, %ptr   ; before this begins
+
    
+
    
+
+
+
    
+  'llvm.atomic.lcs.*' Intrinsic
+
    
+
    
+
    Syntax:
    
+
    
+  This is an overloaded intrinsic. You can use llvm.atomic.lcs on any 
+  integer bit width. Not all targets support all bit widths however.
    
+
+
    +declare i8 @llvm.atomic.lcs.i8( i8* <ptr>, i8 <cmp>, i8 <val> )
+declare i16 @llvm.atomic.lcs.i16( i16* <ptr>, i16 <cmp>, i16 <val> )
+declare i32 @llvm.atomic.lcs.i32( i32* <ptr>, i32 <cmp>, i32 <val> )
+declare i64 @llvm.atomic.lcs.i64( i64* <ptr>, i64 <cmp>, i64 <val> )
+
+
    
+
    Overview:
    
+
    
+  This loads a value in memory and compares it to a given value. If they are 
+  equal, it stores a new value into the memory.
+
    
+
    Arguments:
    
+
    
+  The llvm.atomic.lcs intrinsic takes three arguments. The result as 
+  well as both cmp and val must be integer values with the 
+  same bit width. The ptr argument must be a pointer to a value of 
+  this integer type. While any bit width integer may be used, targets may only 
+  lower representations they support in hardware.
+
+
    
+
    Semantics:
    
+
    
+  This entire intrinsic must be executed atomically. It first loads the value 
+  in memory pointed to by ptr and compares it with the value 
+  cmp. If they are equal, val is stored into the memory. The 
+  loaded value is yielded in all cases. This provides the equivalent of an 
+  atomic compare-and-swap operation within the SSA framework.
+
    
+
    Examples:
    
+
+
    +%ptr      = malloc i32
+            store i32 4, %ptr
+
+%val1     = add i32 4, 4
+%result1  = call i32 @llvm.atomic.lcs.i32( i32* %ptr, i32 4, %val1 )
+                                          ; yields {i32}:result1 = 4
+%stored1  = icmp eq i32 %result1, 4       ; yields {i1}:stored1 = true
+%memval1  = load i32* %ptr                ; yields {i32}:memval1 = 8
+
+%val2     = add i32 1, 1
+%result2  = call i32 @llvm.atomic.lcs.i32( i32* %ptr, i32 5, %val2 )
+                                          ; yields {i32}:result2 = 8
+%stored2  = icmp eq i32 %result2, 5       ; yields {i1}:stored2 = false
+
+%memval2  = load i32* %ptr                ; yields {i32}:memval2 = 8
+
    
+
    
+
+
+
    
+  'llvm.atomic.swap.*' Intrinsic
+
    
+
    
+
    Syntax:
    
+
+
    
+  This is an overloaded intrinsic. You can use llvm.atomic.swap on any 
+  integer bit width. Not all targets support all bit widths however.
    
+
    +declare i8 @llvm.atomic.swap.i8( i8* <ptr>, i8 <val> )
+declare i16 @llvm.atomic.swap.i16( i16* <ptr>, i16 <val> )
+declare i32 @llvm.atomic.swap.i32( i32* <ptr>, i32 <val> )
+declare i64 @llvm.atomic.swap.i64( i64* <ptr>, i64 <val> )
+
+
    
+
    Overview:
    
+
    
+  This intrinsic loads the value stored in memory at ptr and yields 
+  the value from memory. It then stores the value in val in the memory 
+  at ptr.
+
    
+
    Arguments:
    
+
+
    
+  The llvm.atomic.ls intrinsic takes two arguments. Both the 
+  val argument and the result must be integers of the same bit width. 
+  The first argument, ptr, must be a pointer to a value of this 
+  integer type. The targets may only lower integer representations they 
+  support.
+
    
+
    Semantics:
    
+
    
+  This intrinsic loads the value pointed to by ptr, yields it, and 
+  stores val back into ptr atomically. This provides the 
+  equivalent of an atomic swap operation within the SSA framework.
+
+
    
+
    Examples:
    
+
    +%ptr      = malloc i32
+            store i32 4, %ptr
+
+%val1     = add i32 4, 4
+%result1  = call i32 @llvm.atomic.swap.i32( i32* %ptr, i32 %val1 )
+                                        ; yields {i32}:result1 = 4
+%stored1  = icmp eq i32 %result1, 4     ; yields {i1}:stored1 = true
+%memval1  = load i32* %ptr              ; yields {i32}:memval1 = 8
+
+%val2     = add i32 1, 1
+%result2  = call i32 @llvm.atomic.swap.i32( i32* %ptr, i32 %val2 )
+                                        ; yields {i32}:result2 = 8
+
+%stored2  = icmp eq i32 %result2, 8     ; yields {i1}:stored2 = true
+%memval2  = load i32* %ptr              ; yields {i32}:memval2 = 2
+
    
+
    
+
+
+
    
+  'llvm.atomic.las.*' Intrinsic
+
+
    
+
    
+
    Syntax:
    
+
    
+  This is an overloaded intrinsic. You can use llvm.atomic.las on any 
+  integer bit width. Not all targets support all bit widths however.
    
+
    +declare i8 @llvm.atomic.las.i8.( i8* <ptr>, i8 <delta> )
+declare i16 @llvm.atomic.las.i16.( i16* <ptr>, i16 <delta> )
+declare i32 @llvm.atomic.las.i32.( i32* <ptr>, i32 <delta> )
+declare i64 @llvm.atomic.las.i64.( i64* <ptr>, i64 <delta> )
+
+
    
+
    Overview:
    
+
    
+  This intrinsic adds delta to the value stored in memory at 
+  ptr. It yields the original value at ptr.
+
    
+
    Arguments:
    
+
    
+
+  The intrinsic takes two arguments, the first a pointer to an integer value 
+  and the second an integer value. The result is also an integer value. These 
+  integer types can have any bit width, but they must all have the same bit 
+  width. The targets may only lower integer representations they support.
+
    
+
    Semantics:
    
+
    
+  This intrinsic does a series of operations atomically. It first loads the 
+  value stored at ptr. It then adds delta, stores the result 
+  to ptr. It yields the original value stored at ptr.
+
    
+
+
    Examples:
    
+
    +%ptr      = malloc i32
+        store i32 4, %ptr
+%result1  = call i32 @llvm.atomic.las.i32( i32* %ptr, i32 4 )
+                                ; yields {i32}:result1 = 4
+%result2  = call i32 @llvm.atomic.las.i32( i32* %ptr, i32 2 )
+                                ; yields {i32}:result2 = 8
+%result3  = call i32 @llvm.atomic.las.i32( i32* %ptr, i32 5 )
+                                ; yields {i32}:result3 = 10
+%memval   = load i32* %ptr      ; yields {i32}:memval1 = 15
+
    
+
    
+
+
+
+
    
+  General Intrinsics
+
    
+
+
    
+
     This class of intrinsics is designed to be generic and has
+no specific purpose. 
    
+
    
+
+
+
    
+  'llvm.var.annotation' Intrinsic
+
    
+
+
    
+
+
    Syntax:
    
+
    +  declare void @llvm.var.annotation(i8* <val>, i8* <str>, i8* <str>, i32  <int> )
+
    
+
+
    Overview:
    
+
+
    
+The 'llvm.var.annotation' intrinsic
+
    
+
+
    Arguments:
    
+
+
    
+The first argument is a pointer to a value, the second is a pointer to a 
+global string, the third is a pointer to a global string which is the source 
+file name, and the last argument is the line number.
+
    
+
+
    Semantics:
    
+
+
    
+This intrinsic allows annotation of local variables 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.
+
    
+
    
+
+
+
    
+  'llvm.annotation.*' Intrinsic
+
    
+
+
    
+
+
    Syntax:
    
+
    This is an overloaded intrinsic. You can use 'llvm.annotation' on 
+any integer bit width. 
+
    
+
    +  declare i8 @llvm.annotation.i8(i8 <val>, i8* <str>, i8* <str>, i32  <int> )
+  declare i16 @llvm.annotation.i16(i16 <val>, i8* <str>, i8* <str>, i32  <int> )
+  declare i32 @llvm.annotation.i32(i32 <val>, i8* <str>, i8* <str>, i32  <int> )
+  declare i64 @llvm.annotation.i64(i64 <val>, i8* <str>, i8* <str>, i32  <int> )
+  declare i256 @llvm.annotation.i256(i256 <val>, i8* <str>, i8* <str>, i32  <int> )
+
    
+
+
    Overview:
    
+
+
    
+The 'llvm.annotation' intrinsic.
+
    
+
+
    Arguments:
    
+
+
    
+The first argument is an integer value (result of some expression), 
+the second is a pointer to a global string, the third is a pointer to a global 
+string which is the source file name, and the last argument is the line number.
+It returns the value of the first argument.
+
    
+
+
    Semantics:
    
+
+
    
+This intrinsic allows annotations to be put on arbitrary expressions
+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.
+
    
+
+
+
    
+  'llvm.trap' Intrinsic
+
    
+
+
    
+
+
    Syntax:
    
+
    +  declare void @llvm.trap()
+
    
+
+
    Overview:
    
+
+
    
+The 'llvm.trap' intrinsic
+
    
+
+
    Arguments:
    
+
+
    
+None
+
    
+
+
    Semantics:
    
+
+
    
+This intrinsics is lowered to the target dependent trap instruction. If the
+target does not have a trap instruction, this intrinsic will be lowered to the
+call of the abort() function.
+
    
+
    
+
 
 
    
 
    
   Valid CSS!
   Valid HTML 4.01!
+  src="http://www.w3.org/Icons/valid-html401" alt="Valid HTML 4.01!">
 
   Chris Lattner
    
   The LLVM Compiler Infrastructure
    
   Last modified: $Date$
 
    
+