<<

ABI
ABS
absence
    loop-carried memory dependency
accessing
    16-bit
accuracy
    controlling
add
   Improving/Restricting FP Arithmetic Precision
   Introduction to Volume II
   Test Prioritization Tool
    test2
add/subtract
   Default Compiler Optimizations
   Floating-point Arithmetic Precision for Itanium®-based Systems
   Improving/Restricting FP Arithmetic Precision
    operations
added performance
adheres
    ANSI
advanced PGO options
affected aspect of the program
affects
   Floating-point Arithmetic Precision Overview
   Using -ip with -Qoption Specifiers
    inlining
    SSE
after
    FORTRAN 77
    vectorization
       Strip-mining and Cleanup
       Vectorization Examples
ALIAS
aliased
ALIGNED
aligning
    data
alignment
    options
    strategy
all
    input/output
    optimizers
alloca
ALLOCATABLE
allowing
    optimizer
alternate
ALWAYS vector
analyzer
analyzing
   Analyzing the Effects of Multifile IPO, -ipo_c, -ipo_S
   Programming for High Performance: Overview
    code for OpenMP*
    data dependence
    data flow
    effects of multiple IPO
    performance
AND
   REDUCTION Clause
   Synchronization Constructs
another possible environment variable setting
ANSI
   Default Compiler Optimizations
   Improving/Restricting FP Arithmetic Precision
   Restricting Optimizations
   Stacks: Automatic Allocation and Checking
    adheres
    conforms
ANSI Fortran
    R818
ansi_alias
   Default Compiler Optimizations
   Stacks: Automatic Allocation and Checking
ANTI
anti-dependencies
API
   Parallelism: an Overview
   Parallelization with OpenMP* Overview
application's
   Code-coverage Tool
   Programming with OpenMP
   Test Prioritization Tool
    code coverage
    tests
    visual presentation
applications
    features contributes
applies
    ATOMIC
ar library manager
argument
   Using Arrays Efficiently
   Vectorization Examples
    aliasing
    using efficiently
arranging
    data items
array
   Alignment Options
   Coding Guidelines for Intel Architectures
   Data Dependence
   Default Compiler Optimizations
   Efficient Compilation
   Examples of OpenMP Usage
   Improving I/O Performance
   Intel Extension Routines
   Scalar Replacement (IA-32 Only)
   Setting Data Type and Alignment
   Stacks: Automatic Allocation and Checking
   Statements in the Loop Body
   Strip-mining and Cleanup
   Using Arrays Efficiently
   Vectorization Examples
   Vectorization Key Programming Guidelines
   Vectorization Support
    accessing
    assumed-shape
    compiler creates
    derived-part
    loop blocking
    natural storage order
    operations
    output argument array types
    requirements
    using efficiently
assembling
assembly files
   Analyzing the Effects of Multifile IPO
   Compilation with Real Object Files
   Creating a Multifile IPO Executable with Command Line
   Optimizations and Debugging
   Using Intel Performance Analysis Tools
   Vectorization Support
    specifying
assumed-shape arrays
ATOMIC directive
   Programming with OpenMP
   Synchronization Constructs
ATTRIBUTES C
auto-parallelization
   Auto-parallelization Overview
   Auto-parallelization Threshold Control and Diagnostics
   Parallelism: an Overview
   Programming with Auto-parallelization
   Threshold for Auto-parallelization
    data flow
    diagnostic
    enabling
    environment variables
    guidelines
    overview
    processing
    programming with
    threshold control
    threshold needed
auto-parallelized
   Auto-parallelization Threshold Control and Diagnostics
   Default Compiler Optimizations
    loops
auto-parallelizer's
   Auto-parallelization Overview
   Auto-parallelization Threshold Control and Diagnostics
   Auto-parallelization: Enabling, Options, Directives, and Environment Variables
   Parallelism: an Overview
   Programming with Auto-parallelization
    control
    enabling
       Auto-parallelization: Enabling, Options, Directives, and Environment Variables
       Parallelism: an Overview
    threshold
auto-vectorization
   Coding Guidelines for Intel Architectures
   Parallelism: an Overview
   What's New in This Release
auto-vectorizer
automatic allocation
    variables
automatic processor-specific optimization
AUTOMATIC statement
availability
    report generation
avoid
   Setting Data Type and Alignment
   Vectorization Support
    EQUIVALENCE
    mixed data type arithmetic expressions
    small integer items
    small logical items
    unaligned data
    vectorization

BACK option of IVDEP
BACKSPACE
BARRIER directive
   OpenMP Directives and Clauses Summary
   Programming with OpenMP
   Synchronization Constructs
    executes
    use
basic PGO options
    profile-guided optimization
bcolor option of code-coverage tool
before
   Programming with OpenMP
   Strip-mining and Cleanup
    inserting
    vectorization
begin
    parallel construct
    serial execution
    worksharing construct
best performance
    function
big-endian
   Little-endian-to-Big-endian Conversion
   Optimizing Compilation Process Overview
    little-endian
binding
bitwise AND
block size
blocking
    loop
BLOCKSIZE
    increasing
    omitting
    values
bound
    denormalized single-precision
Bourne shell
browsing
    frames
BUFFERCOUNT
    buffered_io option
    default
    increase
buffers
    UBC
byterecl keyword

c$omp
   Compiling with OpenMP, Directive Format, and Diagnostics
   Examples of OpenMP Usage
c$OMP BARRIER
c$OMP DO PRIVATE
c$OMP END PARALLEL
c$OMP PARALLEL
cache size intrinsic
cachesize
call stack dumps
    master thread
    worker thread
call WORK
   Parallel Region Directives
   REDUCTION Clause
   Synchronization Constructs
   Worksharing Construct Directives
callee
calls
   Improving I/O Performance
   Parallel Region Directives
   Processor-specific Runtime Checks, IA-32 Systems
   Software Convention Model Options
    malloc
    OMP_SET_NUM_THREADS
callstack
causing
    unaligned data
cc_omp keyword
ccolor option of code coverage tool
CDEC$ prefix of directives
   Auto-parallelization: Enabling, Options, Directives, and Environment Variables
   Loop Count and Loop Distribution
   Loop Unrolling Support
   Pipelining for Itanium -based Applications
   Prefetching Support
   Vectorization Support
CEIL rounding mode
changing
    number
character data
   Alignment Options
   Setting Data Type and Alignment
characteristics
   IPO Overview
   Programming with OpenMP
   Setting Optimizations with -On Options
checking
   Setting Data Type and Alignment
   Stacks: Automatic Allocation and Checking
    floating-point stack state
    inefficient unaligned data
choosing
    inline
chunk size
clause containing reduction
clauses
   Combined Parallel/Worksharing Constructs
   Compiling with OpenMP, Directive Format, and Diagnostics
   COPYIN Clause
   Data Scope Attribute Clauses Overview
   Debugging Shared Variables
   DEFAULT Clause
   OpenMP* Directives and Clauses
   Parallel Processing Thread Model
   Parallel Region Directives
   PRIVATE, FIRSTPRIVATE, and LASTPRIVATE Clauses
   Programming with OpenMP
   REDUCTION Clause
   SHARED Clause
   Specifying Schedule Type and Chunk Size
   Synchronization Constructs
   THREADPRIVATE Directive
   Worksharing Construct Directives
    comma-separated list
       Parallel Region Directives
       Worksharing Construct Directives
    cross-reference
    list
    summary
cleanup
code
    assembly
       Using Intel Performance Analysis Tools
       Vectorization Support
    preparing
code-coverage tool
Code DO
codecov
codecov_option
coding
   Coding Guidelines for Intel Architectures
   Improving Runtime Efficiency
   Introduction to Volume II
    Intel® architectures
coloring scheme
    setting
combined parallel/worksharing constructs
   Combined Parallel/Worksharing Constructs
   Programming with OpenMP
comma-separated
comma-separated list
   Data Scope Attribute Clauses Overview
   OpenMP Directives and Clauses Summary
   Parallel Region Directives
   Synchronization Constructs
   Worksharing Construct Directives
    clauses
       Parallel Region Directives
       Worksharing Construct Directives
    variables
command line
   Code-coverage Tool
   Creating a Multifile IPO Executable Using xild
   Creating a Multifile IPO Executable with Command Line
   Default Compiler Optimizations
   Optimizations and Debugging
   Restricting Optimizations
   Test Prioritization Tool
   Vectorizer Options
    options
    syntax
       Code-coverage Tool
       Compiling with OpenMP, Directive Format, and Diagnostics
       Optimization Support Features Overview
       Test Prioritization Tool
COMMON
   Coding Guidelines for Intel Architectures
   COPYIN Clause
   Stacks: Automatic Allocation and Checking
   THREADPRIVATE Directive
    block
       Alignment Options
       Coding Guidelines for Intel Architectures
       COPYIN Clause
       DEFAULT Clause
       Efficient Compilation
       Parallel Region Directives
       Programming with OpenMP
       Setting Data Type and Alignment
       Software Convention Model Options
       THREADPRIVATE Directive
        FIELDS
    statement
       Alignment Options
       Coding Guidelines for Intel Architectures
       Setting Data Type and Alignment
Compaq* Visual Fortran
compilation
   Compilation with Real Object Files, -ipo_obj
   Compiler Optimizations Overview
   Creating a Multifile IPO Executable Using xild
   Creating a Multifile IPO Executable with Command Line
   Efficient Compilation
   HLO Overview
   Multifile IPO Overview
   Optimizing Compilation Process Overview
   Parallelism: an Overview
    "mock" object files
    controlling
    customizing process of
    efficient
    optimizing
    options
       Alignment Options
       Default Compiler Optimizations
       Stacks: Automatic Allocation and Checking
       Symbol Visibility Attributes Options
    phase
    techniques
compiler
   Coding Guidelines for Intel Architectures
   Compiler Optimizations Overview
   Compiling with OpenMP, Directive Format, and Diagnostics
   Default Behavior of the Compiler Options
   Efficient Compilation
   Improving I/O Performance
   Improving Run-time Efficiency
   Optimization Support Features Overview
   Optimizing Compilation Process Overview
   Parallelism: an Overview
   Processor-specific Run-time Checks, IA-32 Systems
   Programming for High Performance: Overview
   Test Prioritization Tool
   What's New in This Release
    applying heuristic
    auto-parallelization processing
    code analysis
    commands
    compiler-created
    compiler-generated
       Coding Guidelines for Intel Architectures
       Debugging Parallel Regions
    compiler-supplied library
    compiler’s IL
    compiling with OpenMP*
    creating array descriptor
    creating temporary array
    default optimizations
    defining the size of the array elements
    directives
    efficient compilation
    implementing .il files
    Intel(R) extension routines
       Debugging Parallel Regions
       Intel Extension Routines
    IPO benefits
    issuing warnings
       Advanced PGO Options
       Basic PGO Options
       Compilation with Real Object Files
       OpenMP Directives and Clauses Summary
       PGO Environment Variables
       Vectorizer Options
    merging the data from all .dyn files
    optimization levels
    producing
       Compilation with Real Object Files
       Example of Profile-Guided Optimization
        pgopti.dpi file
    programming with OpenMP*
    relocating the source files
    report generation
    selecting routines for inlining
    treating assumed dependence
    vectorization
        support
compiling source lines
COMPLEX
   Default Compiler Optimizations
   Improving Runtime Efficiency
   Setting Data Type and Alignment
   Stacks: Automatic Allocation and Checking
conditional parallel region execution
    setting
conforming
   Improving/Restricting FP Arithmetic Precision
   Restricting Optimizations
    ANSI
    IEEE 754
constructing
    entry-point name
containing
   Creating a Library from IPO Objects
   Creating a Multifile IPO Executable Using xild
   Creating a Multifile IPO Executable with Command Line
   Optimizer Report Generation
   Setting Data Type and Alignment
    8-byte
    IR
       Creating a Multifile IPO Executable Using xild
       Creating a Multifile IPO Executable with Command Line
    substring
CONTINUE
controlling
   Controlling Inline Expansion of User Functions
   Floating-point Arithmetic Precision for IA-32 Systems
   Floating-point Arithmetic Precision for Itanium®-based Systems
   Parallelism: an Overview
    accuracy
    advanced PGO optimizations
    alignment with options
       Alignment Options
       Efficient Compilation#improve
    auto-parallelizer's diagnostic levels
       Auto-parallelization Threshold Control and Diagnostics
       Parallelism: an Overview
    compilation process
    complex flow
    computation of stacks and variables
    data scope attributes
    floating-point accuracy
    floating-point computations
    floating-point exceptions
    generation of profile information
    inline expansion
    loop vectorization
    number of threads
    OpenMP* diagnostics
    rounding
    speculation
    your program with OpenMP*
conventions
converting
    little-endian
COPYIN clause
   COPYIN Clause
   Data Scope Attribute Clauses Overview
   OpenMP Directives and Clauses Summary
   Parallel Processing Thread Model
   Parallel Region Directives
copyprivate
correct usage
   Loop Constructs
   Loop Exit Conditions
    countable
COS
   Statements in the Loop Body
   Types of Loop Vectorized
COUNT
countable
    correct usage
coverage analysis
    modules subset
CPU
   Improving I/O Performance
   Timing Your Application
   Using Arrays Efficiently
    CPU-intensive
       Improving I/O Performance
       Timing Your Application
    CPU_TIME
    use
CRAY pointer
    preventing aliasing
creating
   Coding Guidelines for Intel Architectures
   Creating a Multifile IPO Executable
   Creating a Multifile IPO Executable Using a Project Makefile
   Test Prioritization Tool
    DPI list
    multifile IPO executable using xild
    multifile IPO executable with commend line
    multithreaded applications
criteria
    inline function expansion
criteria for inline function expansion
CRITICAL directive
   OpenMP Directives and Clauses Summary
   Programming with OpenMP
   Synchronization Constructs
    use
critical/ordered
cross-iteration
cross-platform, -ansi_alias
Csh
customizing
    compilation process
CVF options

>>