<<

efficient
   Improving Run-time Efficiency
   Improving I/O Performance
    auto-parallelizer
    compilation
       Efficient Compilation
       Optimizing Compilation Process Overview
    implied-DO loop collapsing
    inlining
    parallelizer
    PGO options
    use of arrays
    use of record buffers
END PARALLEL DO
    using
endian data
    and OpenMP* extension routines
    auto-parallelization
    denormal
    dumping profile information
    for auto-parallelization
    for little endian conversion
    for profile-guided optimization
    FORT_BUFFERED
    loop constructs
    OMP_NUM_THREADS
    OMP_SCHEDULE
    OpenMP*
    parallel program development
    PROF_DIR
    PROF_DUMP_INTERVAL
    routines overriding
    using OpenMP*
    using profile-guided optimization
    vectorization
enhancing optimization
enhancing performance
EQUIVALENCE
    effect on run-time efficiency
exclude code
    code coverage tool
execution environment routines
execution flow
execution mode
explicit-shape arrays
    .dpi
       Basic PGO Options
       Profmerge and Proforder Utilities
       Code-coverage Tool
       Test-prioritization Tool
    .dyn
       Basic PGO Options
       Dumping and Resetting Profile Information
       Dumping Profile Information
       PGO Environment Variables
       Profmerge and Proforder Utilities
       Code-coverage Tool
       Test-prioritization Tool
       Profile an Application
    .spi
       Code-coverage Tool
       Test-prioritization Tool
    formatted
    OpenMP* header
    optimizing
    pgopti.dpi
    pgopti.spi
    source
       Efficient Compilation
       Example of Profile-Guided Optimization
    unformatted



FIRSTPRIVATE
    in worksharing constructs
    summary of data scope attribute clauses
    using
flow dependency in loops
flush-to-zero mode
formatted files
FORT_BUFFERED environment variable
FTZ mode
function expansion
function grouping optimization
function order list
    enabling or disabling
function order lists
function ordering optimization
function preemption



general compiler directives
   Prefetching Support
   Loop Unrolling Support
    affecting data prefetches
       Loop Count and Loop Distribution
       Prefetching Support
    affecting software pipelining
       Loop Count and Loop Distribution
       Pipelining for IA-64 Architecture
    for auto-parallelization
    for IA-32 architecture
    for improving run-time efficiency
    for inlining functions
    for profile-guided optimization
    for vectorization
       Vectorization Overview
       Key Programming Guidelines for Vectorization
    instrumented code
    processor-specific code
    profile-optimized executable
    profiling information
    reports



high performance
high performance programming
    applications for
    dispatch options for
    guidelines for
    improving performance
    list
    options for
    parsing
    performance
    processors for
       Parallelism Overview
       Automatic Processor-specific Optimization (IA-32 Architecture)
    report generation
high-level optimization
high-level optimizer
   HLO Overview
   Optimizer Report Generation
HLO
   HLO Overview
   High-Level Optimization (HLO) Report
    reports
hotspots
Hyper-Threading Technology
    parallel loops
    thread pools



IA-32 architecture based applications
    HLO
    methods of parallelization
    options
       Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
       Targeting Multiple IA-32 and Intel 64 Architecture Processors for Run-time Performance
    targeting
       Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
       Targeting Multiple IA-32 and Intel 64 Architecture Processors for Run-time Performance
    using intrinsics in
IA-64 architecture based applications
    auto-vectorization in
    HLO
    methods of parallelization
    options
    pipelining for
    report generation
    targeting
    using intrinsics in
ILO
implied-DO loop
improving
    code
    I/O performance
    run-time performance
initialization values for reduction variables
inlining
   Efficient Compilation
   Controlling Inline Expansion of User Functions
   Improving Run-time Efficiency
   Profile-guided Optimizations Overview
   User Directed Inline Expansion of User Functions
   Inline Function Expansion
    compiler directed
    developer directed
    preemption
instruction-level parallelism
instrumentation
    compilation
    execution
    feedback compilation
    generating
    preventing aliasing
    program
Intel(R) 64 architecture based applications
    HLO
    methods of parallelization
    options
       Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
       Targeting Multiple IA-32 and Intel 64 Architecture Processors for Run-time Performance
    targeting
       Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
       Targeting Multiple IA-32 and Intel 64 Architecture Processors for Run-time Performance
    using intrinsics in
Intel(R) architectures
Intel(R) compatibility libraries for OpenMP*
Intel(R) compiler-generated code
Intel(R) extension environment variables
Intel(R) extension routines
Intel(R) linking tools
Intel(R)-extended intrinsics
INTEL_PROF_DUMP_CUMULATIVE environment variable
INTEL_PROF_DUMP_INTERVAL environment variable
intermediate language scalar optimizer
intermediate representation (IR)
   Using IPO
   Interprocedural Optimization (IPO) Overview
intermediate results
    using memory for
internal subprograms
interprocedural optimizations
   Efficient Compilation
   Controlling Inline Expansion of User Functions
   Profile-guided Optimizations Overview
   Optimizer Report Generation
    capturing intermediate output
    code layout
    compilation
    compiling
    considerations
    creating libraries
    initiating
    issues
    large programs
    linking
       Interprocedural Optimization (IPO) Overview
       Using IPO
    options
    overview
    performance
    reports
    using
    whole program analysis
    xiar
    xild
    xilibtool
intrinsics
introduction to Optimizing Applications
IR
   Using IPO
   Interprocedural Optimization (IPO) Overview
IVDEP
    effect of compiler option on
    effect when tuning applications
IVDEP directive


>>