/Ap64 compiler option
/arch compiler option
/As compiler option
/bigobj compiler option
/c compiler option
/C compiler option
/D compiler option
/debug compiler option
/E compiler option
/EHa compiler option
/EHc compiler option
/EHs compiler option
/EP compiler option
/Fa compiler option
/FA compiler option
/fast compiler option
/FC compiler option
/F compiler option
/FD compiler option
/Fe compiler option
/FI compiler option
/fixed compiler option
/Fm compiler option
/Fo compiler option
/fp compiler option
fp-model, fp
Using the -fp-model (/fp) Option
Floating-point Options Quick Reference
how to use
/Fp compiler option
/Fr compiler option
/FR compiler option
/G2 compiler option
/G5 compiler option
/G6 compiler option
/G7 compiler option
/GA compiler option
/Gd compiler option
/Ge compiler option
/Gf compiler option
/GF compiler option
/Gh compiler option
/GH compiler option
/Gm compiler option
/Gr compiler option
/GR compiler option
/Gs compiler option
/GS compiler option
/GT compiler option
/GX compiler option
/Gy compileroption
/Gz compiler option
/GZ compiler option
/H compiler option
/help compiler option
/homeparams compiler option
/hotpatch compiler option
/I compiler option
/J compiler option
/LD compiler option
/link compiler option
/MD compiler option
/ML compiler option
/MP compiler option
/MT compiler option
/noBool compiler option
/nologo compiler option
/Oa compiler option
Oa
falias
/Ob compiler option
/O compiler option
/Od compiler option
/Og compiler option
/Oi compiler option
/Op compiler option
/Os compiler option
/Ot compiler option
/Ow compiler option
ffnalias
Ow
/Ox compiler option
/Oy compiler option
/P compiler option
/QA compiler option
/QA- compiler option
/Qalias-args compiler option
/Qalias-const compiler option
/Qansi-alias compiler option
/Qauto-ilp32 compiler option
/Qax compiler option
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
ax, Qax
/Qc99 compiler option
/Qchkstk compiler option
/Qcomplex-limited-range compiler option
/Qcontext-limit compiler option
/Qcov-dir compiler option
/Qcov-file compiler option
/Qcov-gen compiler option
/Qcxx-features compiler option
/QdD compiler option
/Qdiag compiler option
/Qdiag-disable compiler option
/Qdiag-dump compiler option
/Qdiag-enable:sc compiler option
/Qdiag-enable:sc-include compiler option
/Qdiag-enable:sc-parallel compiler option
/Qdiag-enable:sv-include compiler option
/Qdiag-enable compiler option
/Qdiag-error compiler option
/Qdiag-error-limit compiler option
/Qdiag-file-append compiler option
/Qdiag-file compiler option
/Qdiag-id-numbers compiler option
/Qdiag-once compiler option
/Qdiag-remark compiler option
/Qdiag-warning compiler option
/QdM compiler option
/QdN compiler option
/Qeffc++ compiler option
/Qfast-transcendentals compiler option
/Qfma compiler option
/Qfnalign compiler option
/Qfnsplit compiler option
/Qfp-port compiler option
/Qfp-relaxed compiler option
/Qfp-speculation compiler option
/Qfp-stack-check compiler option
/Qfreestanding compiler option
/Qftz compiler option
Setting the FTZ and DAZ Flags
ftz, Qftz
/Qglobal-hoist compiler option
/QH compiler option
/QIA64-fr32 compiler option
/Qinline-calloc compiler option
/Qinline-debug-info compiler option
/Qinline-dllimport compiler option
/Qinline-factor compiler option
/Qinline-forceinline compiler option
/Qinline-max-per-compile compiler option
/Qinline-max-per-routine compiler option
/Qinline-max-size compiler option
/Qinline-max-total-size compiler option
/Qinline-min-size compiler option
/Qinstruction compiler option
/Qinstrument-functions compiler option
/Qip compiler option
/QIPF-fltacc compiler option
/QIPF-flt-eval-method0 compiler option
/QIPF-fma compiler option
/QIPF-fp-relaxed compiler option
/Qip-no-inlining compiler option
/Qip-no-pinlining compiler option
/Qipo-c compiler option
/Qipo compiler option
ipo, Qipo
Using IPO
/Qipo-jobs compiler option
/Qipo-S compiler option
/Qipo-separate compiler option
/Qipp compiler option
/Qivdep-parallel compiler option
/Qkeep-static-consts compiler option
/Qlocation compiler option
/Qlong-double compiler option
/Qmap-opts compiler option
/Qmcmodel compiler option
/QM compiler option
/QMD compiler option
/QMF compiler option
/QMG compiler option
/Qmkl compiler option
/QMM compiler option
/QMMD compiler option
/Qms compiler option
/Qmspp compiler option
/QMT compiler option
/Qmultibyte-chars compiler option
/Qnobss-init compiler option
/Qnopic compiler option
/Qopenmp compiler option
/Qopenmp-lib compiler option
openmp-lib, Qopenmp-lib
OpenMP* Source Compatibility and Interoperability with Other Compilers
/Qopenmp-link compiler option
/Qopenmp-profile compiler option
/Qopenmp-report compiler option
/Qopenmp-stubs compiler option
/Qopenmp-task compiler option
/Qopenmp-threadprivate compiler option
/Qopt-block-factor compiler option
/Qopt-class-analysis compiler option
/Qoption compiler option
/Qopt-jump-tables compiler option
/Qopt-loadpair compiler option
/Qopt-mem-bandwidth compiler option
/Qopt-mod-versioning compiler option
/Qopt-multi-version-aggressive compiler option
/Qopt-prefetch compiler option
/Qopt-prefetch-initial-values compiler option
/Qopt-prefetch-issue-excl-hint compiler option
/Qopt-prefetch-next-iteration compiler option
/Qopt-ra-region-strategy compiler option
About Register Allocation
opt-ra-region-strategy, Qopt-ra-region-strategy
example
/Qopt-report compiler option
opt-report, Qopt-report
Generating Reports
/Qopt-report-file compiler option
/Qopt-report-help compiler option
/Qopt-report-phase compiler option
/Qopt-report-routine compiler option
/Qopt-streaming-stores compiler option
/Qopt-subscript-in-range compiler option
/Qpar-adjust-stack compiler option
/Qpar-affinity compiler option
/Qparallel compiler option
/Qpar-num-threads compiler option
/Qpar-report compiler option
/Qpar-runtime-control compiler option
/Qpar-schedule compiler option
/Qpar-threshold compiler option
/Qpc compiler option
/Qpchi compiler option
/Qprec_div compiler option
/Qprec compiler option
/Qprec-sqrt compiler option
/Qprof-data-order compiler option
/Qprof-dir compiler option
/Qprof-file compiler option
/Qprof-func-order compiler option
/Qprof-gen:srcpos compiler option
test prioritization Tool
code coverage Tool
Profile an Application
code coverage tool
test priorization tool
/Qprof-gen compiler option
Profile an Application
prof-gen, Qprof-gen
/Qprof-hotness-threshold compiler option
/Qprof-src-dir compiler option
/Qprof-src-root compiler option
/Qprof-src-root-cwd compiler option
/Qprof-use compiler option
profmerge and proforder Tools
code coverage Tool
prof-use, Qprof-use
code coverage tool
profmerge utility
/Qrcd compiler option
/Qrct compiler option
/Qrestrict compiler option
/Qsafeseh compiler option
/Qsave-temps compiler option
/Qscalar-rep compiler option
/Qserialize-volatile compiler option
/Qsfalign compiler option
/Qsox compiler option
/Qstd compiler option
/Qtbb compiler option
/Qtcheck compiler option
/Qtcollect compiler option
/Qtcollect-filter compiler option
/Qtemplate-depth compiler option
/Qtprofile compiler option
/Qtrapuv compiler option
/Qunroll-aggressive compiler option
/Qunroll compiler option
/Quse-asm compiler option
/Quse-intel-optimized-headers compiler option
/Quse-msasm-symbols compiler option
/Qvc compiler option
/QV compiler option
/Qvec compiler option
/Qvec-guard-write compiler option
/Qvec-report compiler option
/Qvec-threshold compiler option
/Qwd compiler option
/Qwe compiler option
/Qwn compiler option
/Qwo compiler option
/Qwr compiler option
/Qww compiler option
/Qx compiler option
Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
x, Qx
/RTC compiler option
/S compiler option
/showIncludes compiler option
/Tc compiler option
/TC compiler option
/Tp compiler option
/TP compiler option
/traceback compiler option
/u (W*) compiler option
/U compiler option
/V (W*) compiler option
/vd compiler option
/vmb compiler option
/vmg compiler option
/vmm compiler option
/vms compiler option
/vmv compiler option
/Wall compiler option
/Wcheck compiler option
/w compiler option
/W compiler option
/Werror-all compiler option
/WL compiler option
/Wp64 compiler option
/Wport compiler option
/WX compiler option
/X compiler option
/Yc compiler option
/Y- compiler option
/Yd compiler option
/Yu compiler option
/YX compiler option
/Z7 compiler option
/Za compiler option
/Zc compiler option
/Zd compiler option
/Ze compiler option
/Zg compiler option
/Zi compiler option
/ZI compiler option
/Zl compiler option
/Zp compiler option
/Zs compiler option
/Zx compiler option
.dpi file
profmerge and proforder Tools
test prioritization Tool
code coverage Tool
.dyn file
profmerge and proforder Tools
test prioritization Tool
code coverage Tool
.dyn files
Profile-Guided Optimization (PGO) Quick Reference
Profile an Application
.spi file
test prioritization Tool
code coverage Tool
-A compiler option
-A- compiler option
Advanced Encryption Standard (AES) Intrinsics
advanced PGO options
Advanced Vector Extensions (AVX) Intrinsics
Details of Intel® Advanced Vector Extensions Intrinsics
Overview: Intrinsics for Intel® Advanced Vector Extensions Instructions
Data types
Registers
AES intrinsics
Intrinsics for Carry-less Multiplication Instruction and Advanced Encryption Standard Instructions
_mm_aesdec_si128
_mm_aesdeclast_si128
_mm_aesenc_si128
_mm_aesenclast_si128
_mm_aesimc_si128
_mm_aeskeygenassist_si128
-alias-args compiler option
-alias-const compiler option
aliasing
ffnalias
falias
option specifying assumption in functions
option specifying assumption in programs
-align compiler option
aligning data
alignment
ALLOCATABLE
Overview of Parallelism Method
Programming with Auto-parallelization
code coverage Tool
basic block
code coverage
data flow
OpenMP*
visual presentation
allocating registers
alternate tools and locations
analyzing applications
Using a Performance Enhancement Methodology
Performance Enhancement Strategies
Intel® Performance Analysis Tools and Libraries
Intel(R) Debugger
Intel(R) Threading Tools
ANSI/ISO standard
Conformance to the C++ Standard
Conformance to the C Standard
-ansi-alias compiler option
-ansi compiler option
application characteristics
application performance
applications
O
option specifying code optimization for
application tests
architectures
arch
Overview: Tuning Performance
coding guidelines for
option generating instructions for
array
array operation
ar tool
assembler
Wa
use-asm, Quse-asm
option passing options to
option producing objects through
assembly files
Specifying Assembly Files
naming
-auto-ilp32 compiler option
automatic optimizations
Enabling Automatic Optimizations
Automatic Optimizations Overview
auto-parallelization
Overview of Parallelism Method
Auto-parallelization Overview
Parallelism Report
Programming with Auto-parallelization
Auto-parallelization: Enabling, Options, Directives, and Environment Variables
diagnostic
enabling
environment variables
guidelines
overview
programming with
threshold
auto-parallelized loops
auto-parallelizer
Overview of Parallelism Method
Auto-parallelization Overview
par-report, Qpar-report
Parallelism Report
par-threshold, Qpar-threshold
parallel, Qparallel
controls
Overview of Parallelism Method
Parallelism Report
enabling
option controlling level of diagnostics for
option enabling generation of multithreaded code
option setting threshold for loops
autovectorization
auto-vectorization
autovectorization of innermost loops
auto-vectorizer
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Automatic Vectorization Overview
optimization for systems based on IA-32 architecture
avoid
Avoiding Mixed Data Type Arithmetic Expressions
inefficient data types
mixed arithmetic expressions
-ax compiler option
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
ax, Qax
-B compiler option
-Bdynamic compiler option
-Bstatic compiler option
-c99 compiler option
capturing IPO output
Carry-less intrinsic
Intrinsics for Carry-less Multiplication Instruction and Advanced Encryption Standard Instructions
_mm_clmulepi64_si128
Carry-less Multiplication Instruction (PCLMULQDQ) Intrinsic
-c compiler option
c
Creating Libraries
-C compiler option
changing number of threads
OpenMP* Directives and Clauses Summary
summary table of
checking
Checking the Floating-point Stack State
floating-point stacks
stacks
Checking the Floating-point Stack State
-check-uninit compiler option
Classes
Programming Example
programming example
Class Libraries
Assignment Operator
Details About the Libraries
Integer Functions for Streaming SIMD Extensions
Shift Operators
Minimum and Maximum Operators
Logical Operators
Addition and Subtraction Operators
Clear MMX™ State Operator
Load and Store Operators
Logical Operators
Overview: Intel C++ Class Libraries
Overview: Floating-point Vector Classes
Conditional Select Operators for Fvec Classes
Rules for Operators
Unpack Operators
Pack Operators
Debug Operations
Multiplication Operators
Capabilities of C++ SIMD Classes
Data Alignment
Compare Operators
Debug Operations
Constructors and Initialization
Unpack Operators
Move Mask Operators
Overview: Integer Vector Classes
Cacheability Support Operators
Conversions
Conversions between Fvec and Ivec
Arithmetic Operators
Classes Quick Reference
C++ Classes and SIMD Operations
Comparison Operators
Conditional Select Operators
Hardware and Software Requirements
About the Classes
About the Classes
C++ classes and SIMD operations
capabilities of C++ SIMD classes
details
floating-point vector classes
Minimum and Maximum Operators
Logical Operators
Load and Store Operators
Overview: Floating-point Vector Classes
Conditional Select Operators for Fvec Classes
Unpack Operators
Data Alignment
Compare Operators
Debug Operations
Constructors and Initialization
Move Mask Operators
Cacheability Support Operators
Conversions
Arithmetic Operators
arithmetic operators
cacheability support operators
compare operators
conditional select operators
constructors and initialization
conversions
data alignment
debug operations
load and store operators
logical operators
minimum and maximum operators
move mask operators
overview
unpack operators
Hardware and Software Requirements
integer vector classes
Assignment Operator
Integer Functions for Streaming SIMD Extensions
Shift Operators
Addition and Subtraction Operators
Clear MMX™ State Operator
Rules for Operators
Pack Operators
Debug Operations
Multiplication Operators
Unpack Operators
Overview: Integer Vector Classes
Conversions between Fvec and Ivec
Comparison Operators
Conditional Select Operators
addition, subtraction operation
assignment operator
clear MMX(TM) state operators
comparison operators
conditional select operators
conversions between fvec and ivec
debug operations
element access operator
element assignment operators
functions for SSE
ivec classes
multiplication operators
pack operators
rules for operators
shift operators
unpack operators
integer vector classes
Logical Operators
logical operators
overview
Quick reference
code coverage tool
color scheme
dynamic counters in
exporting data
syntax of
codecov tool
Qcov-gen
Qcov-file
Qcov-dir
option producing an instrumented file for
option specifying a directory for profiling output for
option specifying a file name for summary files for
code layout
compilation units
Developer Directed Inline Expansion of User Functions
fminshared
option to prevent linking as shareable object
compiler
Related Information
Introducing the Intel® C++ Compiler
overview
Related Information
Introducing the Intel® C++ Compiler
compiler information
Saving Compiler Information in Your Executable
saving in your executable
compiler installation
Qinstall
option specifying root directory for
compiler operation
Compilation Phases
Compiler Input Files
Output Files
Default Behavior of the Compiler
Invoking the Compiler from the Command Line
Default Output Files
compilation phases
default behavior
input files
invoking from the command line
output files
Output Files
Default Output Files
compiler optimization
compiler optimizations
compiler option mapping tool
compiler options
Using Compiler Options
Unsupported Microsoft Visual Studio* Compiler Options
Other Considerations
About Preprocessor Options
Using Options to Define Macros
Portability Options
Specifying Symbol Visibility Explicitly
Template Instantiation
New Options
Deprecated and Removed Compiler Options
Quick Reference Guide and Cross Reference
Other Visibility-related Command-line Options
Compiler Options for Interoperability
Passing Options to the Linker
Compiler Option Descriptions and General Rules
Using Options for Preprocessing
command-line syntax
cross reference
deprecated and removed
for interoperability
for optimization
for portability
for templates
for visibility
Specifying Symbol Visibility Explicitly
Other Visibility-related Command-line Options
general rules for
linker-related
new
option categories
overview of descriptions of
preprocessor options
About Preprocessor Options
Using Options to Define Macros
Using Options for Preprocessing
quick reference guide
unsupported Microsoft Visual Studio
using
compiler reports
Requesting Compiler Reports with the xi* Tools
Compiler Reports Overview
High-level Optimization (HLO) Report
Software Pipelining (SWP) Report (Linux* and Windows*)
Interprocedural Optimizations (IPO) Report
Generating Reports
Vectorization Report
High-Level Optimization (HLO)
Interprocedural Optimizations (IPO)
report generation
requesting with xi* tools
software pipelining
vectorization
compiler reports quick reference
compilers
Multi-version Compiler Support
using multiple versions
compiling
Other Considerations
gcc* code with Intel(R) C++
compiling large programs
compiling with IPO
-complex-limited-range compiler option
complex operations
complex-limited-range, Qcomplex-limited-range
option enabling algebraic expansion of
conditional check
vec-guard-write, Qvec-guard-write
option performing in a vectorized loop
conditional parallel region execution
Compiler Directed Inline Expansion of User Functions
Overview of Parallelism Method
Parallelism Report
auto-parallelizer diagnostics
Overview of Parallelism Method
Parallelism Report
inline expansion
configuration files
conventions
Notational Conventions
in the documentation
correct usage of countable loop
COS
Loop Constructs
correct usage of
counters for dynamic profile
CPU
mtune
march
option generating code for specified
option performing optimizations for specified
CPU dispatch
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Targeting IA-32 and Intel 64 Architecture Processors Manually
automatic
CPU time
Timing Your Application
test prioritization Tool
Inline Function Expansion
DPI lists
for inline function expansion
create libraries using IPO
-cxxlib compiler option
data alignment
dataflow analysis
Overview of Parallelism Method
Auto-parallelization Overview
data format
Overview of Parallelism Method
Parallelism Report
Programming with Auto-parallelization
High-Level Optimizations (HLO) Overview
Automatic Vectorization Overview
dependence
partitioning
prefetching
sharing
type
Overview of Parallelism Method
Automatic Vectorization Overview
data ordering optimization
data prefetches
data types
Using Efficient Data Types
efficiency
DAZ flag
-D compiler option
-dD compiler option
-debug compiler option
debug (Linux* OS and Mac OS* X)
Using Options for Debug Information
debugging
debug (Linux* OS and Mac OS* X)
Using Options for Debug Information
Using the Debugger
Symbolic Debugging and Optimizations
Preparing for Debugging
compiler options for
Using Options for Debug Information
Symbolic Debugging and Optimizations
Preparing for Debugging
option affecting information generated
option specifying settings to enhance
symbolic
denormal exceptions
denormalized numbers (IEEE*)
Special Values
NaN values
denormal numbers
denormals
deprecated compiler options
determining parallelization
-diag compiler option
-diag-disable compiler option
-diag-dump compiler option
-diag-enable compiler option
-diag-enable port-win compiler option
-diag-enable sc compiler option
-diag-enable sc-include compiler option
-diag-enable sc-parallel compiler option
-diag-enable sv-include compiler option
-diag-error compiler option
-diag-error-limit compiler option
-diag-file-append compiler option
-diag-file compiler option
-diag-id-numbers compiler option
diagnostic messages
diag, Qdiag
diag-enable sc-parallel, Qdiag-enable:sc-parallel
diag-enable sc-include, Qdiag-enable:sc-include
diag-once, Qdiag-once
option affecting which are issued
option controlling auto-parallelizer
option controlling display of
option controlling OpenMP
option controlling source control
option controlling vectorizer
option enabling or disabling
option enabling parallel lint
option issuing only once
option processing include files and source files for
diagnostic reports
diagnostics
Overview of Parallelism Method
Local Program Analysis
Parallelism Report
Interprocedural Analysis
Programming Guidelines for Vectorization
Source Checker Overview
Remarks, Warnings, and Errors
OpenMP* Analysis
Fortran-Specific Analysis
C/C++ Specific Analysis
auto-parallelizer
Overview of Parallelism Method
Parallelism Report
-diag-once compiler option
-diag-remark compiler option
-diag-warning compiler option
difference operators
differential coverage
directory
isystem
B
option adding to start of include path
option specifying for executables
option specifying for includes and libraries
disabling
Compiler Directed Inline Expansion of User Functions
Profile-Guided Optimization (PGO) Quick Reference
function splitting
inlining
disabling optimization
dllimport functions
Qinline-dllimport
option controlling inlining of
-dM compiler option
-dN compiler option
DO constructs
Loop Constructs
OpenMP* Run-time Library Routines
numbers
Documentation
Notational Conventions
conventions for
driver tool commands
v
dryrun
option specifying to show and execute
option specifying to show but not execute
-dryrun compiler option
dual-core
dual core thread affinity
dumping profile information
Dumping Profile Information
Interval Profile Dumping
-dumpmachine compiler option
-dumpversion compiler option
dynamic information
Dumping Profile Information
Resetting the Dynamic Profile Counters
Profile an Application
PGO Environment Variables
OpenMP* Run-time Library Routines
Profile-Guided Optimizations Overview
dumping profile information
files
resetting profile counters
threads
dynamic-information files
-dynamiclib compiler option
Using Intel Shared Libraries
dynamiclib
Creating Libraries
dynamic libraries
dynamiclib
option invoking tool to generate
dynamic linker
dynamic-linker
option specifying analternate
-dynamic-linker compiler option
dynamic-linking of libraries
Bdynamic
option enabling
dynamic-link libraries (DLLs)
MD
option searching for unresolved references in
dynamic shared object
shared
option producing a
dyn files
Dumping and Resetting Profile Information
Dumping Profile Information
Profile-Guided Optimization (PGO) Quick Reference
Profile an Application
PGO Environment Variables
-early-template-check compiler option
ebp register
fomit-frame-pointer, Oy
option determining use in optimizations
Eclipse* integration
Project Types and Makefiles
Overview: Eclipse Integration
Exporting Makefiles
Setting Properties
Building a Project
Running a Project
Creating a New Project
Adding a C Source File
Starting Eclipse
adding a source file
building a project
creating a new project
exporting makefiles
makefiles
overview
running a project
setting properties
starting
Eclipse* projects
-E compiler option
efficiency
efficient
Compiler Directed Inline Expansion of User Functions
Overview of Parallelism Method
Profile-Guided Optimization (PGO) Quick Reference
auto-parallelizer
inlining
parallelizer
PGO options
efficient data types
EMMS Instruction
EMMS Usage Guidelines
The EMMS Instruction: Why You Need It
about
using
endian data
Overview of Parallelism Method
Loop Constructs
Dumping Profile Information
Intel Extension Routines to OpenMP*
Auto-parallelization: Enabling, Options, Directives, and Environment Variables
OpenMP* Environment Variables
Profile an Application
OpenMP* Examples
Interval Profile Dumping
PGO Environment Variables
OpenMP* Run-time Library Routines
and OpenMP* extension routines
auto-parallelization
dumping profile information
for auto-parallelization
for profile-guided optimization
loop constructs
OpenMP*
parallel program development
PROF_DIR
PROF_DUMP_INTERVAL
routines overriding
using OpenMP*
using profile-guided optimization
enhancing optimization
enhancing performance
environment variables
About Modifying the Compilation Environment
Managing Libraries
Setting Environment Variables
C_INCLUDE_PATH
CPATH
CPLUS_INCLUDE_PATH
for Linux*
IA32ROOT
IA64ROOT
ICCCFG
ICPCCFG
LD_LIBRARY_PATH
LIBRARY_PATH
modifying
PATH
PROF_DIR
PROF_DPI
SUNPRO_DEPENDENCIES
TEMP
TMP
TMPDIR
-EP compiler option
error parser
exception handling
fexceptions
option generating table of
exceptions
fnon-call-exceptions
option allowing trapping instructions to throw
exclude code
code coverage Tool
code coverage tool
exclusive hint
opt-prefetch-issue-excl-hint, Qopt-prefetch-issue-excl-hint
option causing prefetches for stores with
executable files
execution environment routines
execution flow
execution mode
explicit-shape arrays
profmerge and proforder Tools
Dumping and Resetting Profile Information
Dumping Profile Information
test prioritization Tool
Profile-Guided Optimization (PGO) Quick Reference
code coverage Tool
Profile an Application
PGO Environment Variables
OpenMP* Run-time Library Routines
.dpi
profmerge and proforder Tools
test prioritization Tool
Profile-Guided Optimization (PGO) Quick Reference
code coverage Tool
.dyn
profmerge and proforder Tools
Dumping and Resetting Profile Information
Dumping Profile Information
test prioritization Tool
Profile-Guided Optimization (PGO) Quick Reference
code coverage Tool
Profile an Application
PGO Environment Variables
.spi
test prioritization Tool
code coverage Tool
OpenMP* header
pgopti.dpi
pgopti.spi
source
-export compiler option
-export-dir compiler option
exported templates
export keyword
expressions
IPF-flt-eval-method0, QIPF-flt-eval-method0
option evaluating floating-point
-fabi-version compiler option
-falias compiler option
-falign-functions compiler option
-falign-stack compiler option
-fargument-alias compiler option
-fargument-noalias-global compiler option
-fasm-blocks compiler option
-fast compiler option
-fast-transcendentals compiler option
-fbuiltin compiler option
-fcode-asm compiler option
-fcommon compiler option
-F compiler option
-fdata-sections compiler option
-fexceptions compiler option
-ffnalias compiler option
-ffreestanding compiler option
-ffunction-sections compiler option
-finline compiler option
-finline-functions compiler option
-finline-limit compiler option
-finstrument-functions compiler option
-fjump-tables compiler option
-fkeep-static-consts compiler option
floating-point accuracy
IPF-fltacc, QIPF-fltacc
option disabling optimizations affecting
floating-point array operation
floating-point calculations
fp-model, fp
option controlling semantics of
Floating-point Compiler Options
floating-point exceptions
Reducing the Impact of Denormal Exceptions
denormal exceptions
floating-point numbers
Floating-point Formats
Overview: Floating-point Operations
Overview: Understanding IEEE Floating-point Standard
Special Values
formats for
overview
overview of
special values
floating-point operations
fp-port, Qfp-port
fp-model, fp
fma, Qfma
option controlling semantics of
option enabling combining of
option rounding results of
Floating-point Operations
Programming Tradeoffs in Floating-point Applications
programming tradeoffs
floating-point precision
pc, Qpc
prec-div, Qprec-div
mp1, Qprec
prec-sqrt, Qprec-sqrt
option controlling for significand
option improving for divides
option improving for square root
option improving general
floating-point stack
Floating-point Formats
fp-stack-check, Qfp-stack-check
option checking
float-to-integer conversion
rcd, Qrcd
option enabling fast
flow dependency in loops
-fma compiler option (Linux* only)
-fmath-errno compiler option
-fminshared compiler option
-fmudflap compiler option
-fno-gnu-keywords compiler option
-fno-implicit-inline-templates compiler option
-fno-implicit-templates compiler option
-fnon-call-exceptions compiler option
-fnon-lvalue-assign compiler option
-fno-operator-names compiler option
-fno-rtti compiler option
-fnsplit compiler option
format function security problems
Wformat-security
option issuing warning for
-fpack-struct compiler option
-fpascal-strings compiler option
-fp compiler option
-fpermissive compiler option
-fpic compiler option
Using Intel Shared Libraries
fpic
Creating Libraries
-fpie compiler option
-fp-model compiler option
fp-model, fp
Using the -fp-model (/fp) Option
Floating-point Options Quick Reference
how to use
-fp-port compiler option
-fp-relaxed compiler option
-fp-speculation compiler option
-fp-stack-check compiler option
FPU rounding control
rct, Qrct
option setting to truncate
-fr32 compiler option
-freg-struct-return compileroption
-fshort-enums compiler option
-fsource-asm compiler option
-fstack-protector compiler option
-fstack-security-check compiler option
-fsyntax-only compiler option
-ftemplate-depth compiler option
-ftls-model compiler option
-ftrapuv compiler option
-ftz compiler option
Setting the FTZ and DAZ Flags
ftz, Qftz
FTZ flag
-func-groups compiler option
function entry and exit points
finstrument-functions, Qinstrument-functions
option determining instrumentation of
function expansion
function grouping
prof-func-groups
option enabling or disabling
function grouping optimization
function ordering optimization
function order list
Profile-Guided Optimization (PGO) Quick Reference
Comparison of Function Order Lists and IPO Code Layout
enabling or disabling
function order lists
function preemption
function profiling
p
option compiling and linking for
functions
falign-functions, Qfnalign
option aligning on byte boundary
function splitting
fnsplit, Qfnsplit
option enabling or disabling
-funroll-all-loops compiler option
-funsigned-bitfields compiler option
-funsigned-char compiler option
-fverbose-asm compiler option
-fvisibility compiler option
-fvisibility-inlines-hidden compiler option
g++* language extensions
-g0 compiler option
gcc*
Porting from GNU gcc* to Microsoft Visual C++*
porting from
gcc* built-in functions
gcc* compatibility
gcc* considerations
gcc* interoperability
gcc* language extensions
GCC* project
Updating a GCC* Project to Use the Intel® C++ Compiler
updating to use the Intel(R) C++ compiler
gcc C++ run-time libraries
X
idirafter
cxxlib
include file path
option adding a directory to second
option removing standard directories from
option specifying to link to
-gcc compiler option
-gcc-name compiler option
-gcc-sys compiler option
-gcc-version compiler option
-g compiler option
-gdwarf-2 compiler option
general compiler directives
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Prefetching Support
Programming with Auto-parallelization
Programming Guidelines for Vectorization
Inline Function Expansion
Profile-Guided Optimization (PGO) Quick Reference
API Support Overview
Profile-Guided Optimizations Overview
Generating Reports
Automatic Vectorization Overview
affecting data prefetches
for auto-parallelization
for inlining functions
for profile-guided optimization
for vectorization
Programming Guidelines for Vectorization
Automatic Vectorization Overview
instrumented code
processor-specific code
profile-optimized executable
profiling information
reports
-global-hoist compiler option
global symbols
GNU C++ compatibility
-gxx-name compiler option
Half-float intrinsics
Intrinsics for Converting Half Floats
_cvtsh_ss
_cvtss_sh
_mm_cvtph_ps
_mm_cvtps_ph
Half-float Intrinsics: overview
-H compiler option
help
Getting Help and Support
using in Microsoft Visual Studio*
-help compiler option
-help-pragma compiler option
high-level optimization
high-level optimizer
High-Level Optimizations (HLO) Overview
Generating Reports
high performance
high performance programming
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Overview of Parallelism Method
High-Level Optimizations (HLO) Overview
Profile-Guided Optimizations Overview
Generating Reports
applications for
dispatch options for
options for
processors for
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Overview of Parallelism Method
report generation
HLO
High-Level Optimizations (HLO) Overview
High-level Optimization (HLO) Report
reports
hotness threshold
prof-hotness-threshold, Qprof-hotness-threshold
option setting
hot patching
hotpatch
option preparing a routine for
hotspots
Hyper-Threading Technology
Programming for Multithread Platform Consistency
parallel loops
thread pools
IA-32 architecture based applications
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Overview of Parallelism Method
High-Level Optimizations (HLO) Overview
Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
HLO
methods of parallelization
options
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
targeting
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
IA-64 architecture based applications
Overview of Parallelism Method
Targeting IA-64 Architecture Processors Automatically
High-Level Optimizations (HLO) Overview
Generating Reports
auto-vectorization in
HLO
methods of parallelization
options
report generation
targeting
IA-64 intrinsics
Lock and Atomic Operation Related Intrinsics
Miscellaneous Intrinsics
Native Intrinsics
Intrinsics for Dual-Core Intel® Itanium® 2 Processor 9000 Sequence
Load and Store Intrinsics
Synchronization Primitives
Operating System Related Intrinsics
Multimedia Addition Intrinsics
Conversion Intrinsics
Microsoft*-Compatible Intrinsics for Dual-Core Intel® Itanium® Processor 9000 Sequence
Register Names for getReg() and setReg()
conversion intrinsics
Dual-Core Itanium® processor 9000 sequence
InterlockedCompare64Exchange128
InterlockedCompare64Exchange128_acq
InterlockedCompare64Exchange128_rel
load128
load128_acq
load and store intrinsics
lock and atomic intrinsics
miscellaneous intrinsics
MS compatible intrinsics
multimedia addition intrinsics
native intrinsics
OS-related intrinsics
register names
store128
store128_rel
synchronization primitives
-icc compiler option
iccvars.sh environment script
-I compiler option
-idirafter compiler option
IEEE*
Special Values
floating-point values
ILO
-imacros compiler option
include files
-inline-calloc compiler option
inlined code
inline-debug-info, Qinline-debug-info
option producing source position information for
-inline-debug-info compiler option
-inline-factor compiler option
-inline-forceinline compiler option
inline function expansion
inline-level, Ob
option specifying level of
-inline-level compiler option
-inline-max-per-compile compiler option
-inline-max-per-routine compiler option
-inline-max-size compiler option
-inline-max-total-size compiler option
-inline-min-size compiler option
inlining
Compiler Directed Inline Expansion of User Functions
inline-min-size, Qinline-min-size
ip-no-inlining, Qip-no-inlining
inline-max-per-compile, Qinline-max-per-compile
finline-limit
ip-no-pinlining, Qip-no-pinlining
inline-max-per-routine, Qinline-max-per-routine
Developer Directed Inline Expansion of User Functions
inline-forceinline, Qinline-forceinline
inline-max-total-size, Qinline-max-total-size
Inline Function Expansion
inline-max-size, Qinline-max-size
Profile-Guided Optimizations Overview
compiler directed
developer directed
option disabling full and partial
option disabling partial
option forcing
option specifying lower limit for large routines
option specifyingmaximum size of function for
option specifying maximum times for a routine
option specifying maximum times for compilation unit
option specifying total size routine can grow
option specifying upper limit for small routine
preemption
inlining options
inline-factor, Qinline-factor
option specifying percentage multiplier for
input files
instruction-level parallelism
instrumentation
Dumping Profile Information
Profile-Guided Optimization (PGO) Quick Reference
Profile an Application
tcollect-filter, Qtcollect-filter
Profile-Guided Optimizations Overview
compilation
execution
feedback compilation
generating
option enabling or disabling for specified functions
program
INTEL_PROF_DUMP_CUMULATIVE environment variable
INTEL_PROF_DUMP_INTERVAL environment variable
Intel(R) 64 architecture based applications
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Overview of Parallelism Method
High-Level Optimizations (HLO) Overview
Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
HLO
methods of parallelization
options
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
targeting
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
Intel(R) C/C++ Error Parser
Intel(R) C++ project
Updating an Existing Intel® C++ Compiler Project
updating to use current compiler version
Intel(R) compatibility libraries for OpenMP*
Intel(R) extension environment variables
Intel(R) extension routines
Intel(R) IPP libraries
ipp, Qipp
option letting you link to
Intel(R) linking tools
Intel(R) MKL
mkl, Qmkl
option letting you link to
Intel(R) TBB libraries
tbb, Qtbb
option letting you link to
Intel(R) Trace Collector API
tcollect, Qtcollect
option inserting probes to call
Intel® AVX Intrinsic
_mm256_setzero_si256
_mm256_cvtepi32_ps
_mm256_unpacklo_ps
_mm256_andnot_ps
_mm256_movemask_pd
_mm256_insertf128_ps
_mm256_rcp_pd
_mm256_permutevar_pd, _mm_permutevar_pd
_mm256_div_ps
_mm256_extractf128_ps
_mm_cmp_ss
_mm256_setzero_pd
_mm256_and_ps
_mm256_testz_si256
_mm256_cvtepi32_pd
_mm256_set1_epi32
_mm256_set_ps
_mm256_permute2f128 _si256
_mm256_blend_ps
_mm256_addsub_pd
_mm256_sqrt_pd
_mm256_testnzc_si256
_mm256_unpackhi_pd
_mm256_testz_ps, _mm_testz_ps
_mm256_min_pd
_mm256_extractf128_si256
_mm256_maskstore_ps, _mm_maskstore_ps
_mm256_cvtpd_epi32
_mm256_or_ps
_mm256_testnzc_ps, _mm_testnzc_ps
_mm256_max_ps
_mm_cmp_ps, _m256_cmp_ps
_mm256_loadu_pd
_mm256_permute2f128 _ps
_mm256_castsi128_si256
_mm256_permute2_ps, _mm_permute2_ps
_mm256_load_ps
_mm256_castps256_ps128
_mm256_mul_pd
_mm256_broadcast_pd
_mm256_store_si256
_mm256_insertf128_si256
_mm256_load_pd
_mm256_loadu_ps
_mm256_permute_ps
_mm256_insertf128_pd
_mm256_set_epi32
_mm256_set_pd
_mm256_sub_pd
_mm256_maskstore_pd, _mm_maskstore_pd
_mm256_testc_si256
_mm256_cvttp_epi32
_mm256_storeu_ps
_mm256_hsub_pd
_mm256_load_si256
_mm256_max_pd
_mm256_zeroupper
_mm256_storeu_si256
_mm256_set1_ps
_mm256_loadu_si256
_mm256_div_pd
_mm256_or_pd
_mm256_broadcast_sd
_mm256_hadd_ps
_mm256_hadd_pd
_mm256_castsi256_pd
_mm256_maskload_ps, _mm_maskload_ps
_mm256_extractf128_pd
_mm256_dp_ps
_mm256_testc_ps, _mm_testc_ps
_mm256_shuffle_pd
_mm256_round_pd
_mm256_unpacklo_pd
_mm256_hsub_ps
_mm256_rsqrt_ps
_mm256_testc_pd, _mm_testc_pd
_mm256_permutevar_ps
_mm256_castpd128_pd256
_mm256_round_ps
_mm256_castps_pd
_mm256_cvttps_epi32
_m256_cvtps_epi32
_mm256_castpd_ps
_mm256_min_ps
_mm256_sqrt_ps
_mm_cmp_pd, _m256_cpm_pd
_mm256_sub_ps
_mm256_castps_si256
_mm256_cvtpd_ps
_mm256_add_ps
_mm256_permute_pd, _mm_permute_pd
_mm256_moveldup_ps
_mm256_storeu_pd
_mm256_blendv_ps
_mm256_add_pd
_mm256_castpd256_pd128
_mm256_setzero_ps
_mm256_lddqu_si256
_mm256_unpackhi_ps
_mm256_broadcast_ps
_m256_cvtps_pd
_mm256_castsi256_si128
_mm256_blendv_pd
_mm256_andnot_pd
_mm256_castpd_si256
_mm256_xor_pd
_mm256_mul_ps
_mm256_castsi256_ps
_mm256_movehdup_ps
_mm256_xor_ps
_mm256_testz_pd, _mm_testz_pd
_mm256_and_pd
_mm256_permute2f128_pd
_mm256_store_ps
_mm256_permute2_pd, _mm_permute2_pd
_mm256_testnzc_pd, _mm_testnzc_pd
_mm256_movemask_ps
_mm256_shuffle_ps
_mm_cmp_sd
_mm256_zeroall
_mm256_addsub_ps
_mm256_maskload_pd, _mm_maskload_pd
_mm256_movedup_pd
_mm256_set1_pd
_mm256_broadcast_ss, _mm_broadcast_ss
_mm256_castps128_ps256
_mm256_store_pd
_mm256_blend_pd
_m256_cmp_pd
_m256_cmp_ps
_m256_cvtps_epi32
_m256_cvtps_pd
_mm_broadcast_ss
_mm_cmp_pd
_mm_cmp_ps
_mm_cmp_ss
_mm_maskload_pd
_mm_maskload_ps
_mm_maskstore_pd
_mm_maskstore_ps
_mm_permute_pd
_mm_permute_ps
_mm_permute2_pd
_mm_permute2_ps
_mm_permutevar_pd
_mm_permutevar_ps
_mm_testc_pd
_mm_testc_ps
_mm_testnzc_pd
_mm_testnzc_ps
_mm_testz_pd
_mm_testz_ps
_mm256_add_pd
_mm256_extractf128_ps
_mm256_add_pd
_mm256_add_ps
_mm256_maskload_ps, _mm_maskload_ps
_mm256_add_ps
_mm_cmp_sd
_mm256_addsub_pd
_mm256_addsub_ps
_mm256_and_pd
_mm256_and_ps
_mm256_andnot_pd
_mm256_andnot_ps
_mm256_blend_pd
_mm256_blend_ps
_mm256_blendv_pd
_mm256_blendv_ps
_mm256_broadcast_pd
_mm256_broadcast_ps
_mm256_broadcast_sd
_mm256_broadcast_ss
_mm256_castpd_ps
_mm256_castpd_si256
_mm256_castpd128_pd256
_mm256_castpd256_pd128
_mm256_castps_pd
_mm256_castps_si256
_mm256_castps128_ps256
_mm256_castps256_ps128
_mm256_castsi128_si256
_mm256_castsi256_pd
_mm256_castsi256_ps
_mm256_castsi256_si128
_mm256_cvtepi32_pd
_mm256_cvtepi32_ps
_mm256_cvtpd_epi32
_mm256_cvtpd_ps
_mm256_cvttpd_epi32
_mm256_cvttps_epi32
_mm256_div_pd
_mm256_div_ps
_mm256_dp_ps
_mm256_extractf128_pd
_mm256_extractf128_si256
_mm256_hadd_pd
_mm256_hadd_ps
_mm256_hsub_pd
_mm256_hsub_ps
_mm256_insertf128_pd
_mm256_insertf128_ps
_mm256_insertf128_si256
_mm256_lddqu_si256
_mm256_load_pd
_mm256_load_ps
_mm256_load_si256
_mm256_loadu_pd
_mm256_loadu_ps
_mm256_loadu_si256
_mm256_maskload_pd
_mm256_maskstore_pd
_mm256_maskstore_ps
_mm256_max_pd
_mm256_max_ps
_mm256_min_pd
_mm256_min_ps
_mm256_movedup_pd
_mm256_movehdup_ps
_mm256_moveldup_ps
_mm256_movemask_pd
_mm256_movemask_ps
_mm256_mul_pd
_mm256_mul_ps
_mm256_or_pd
_mm256_or_ps
_mm256_permute_pd
_mm256_permute_ps
_mm256_permute2_pd
_mm256_permute2_ps
_mm256_permute2f128_pd
_mm256_permute2f128 _ps
_mm256_permute2f128 _si256
_mm256_permutevar_pd
_mm256_permutevar_ps
_mm256_rcp_pd
_mm256_round_pd
_mm256_round_ps
_mm256_rsqrt_ps
_mm256_set_epi32
_mm256_set_pd
_mm256_set_ps
_mm256_set1_epi32
_mm256_set1_pd
_mm256_set1_ps
_mm256_setzero_pd
_mm256_setzero_ps
_mm256_setzero_si256
_mm256_shuffle_pd
_mm256_shuffle_ps
_mm256_sqrt_pd
_mm256_sqrt_ps
_mm256_store_pd
_mm256_store_ps
_mm256_store_si256
_mm256_storeu_pd
_mm256_storeu_ps
_mm256_storeu_si256
_mm256_sub_pd
_mm256_sub_ps
_mm256_testc_pd
_mm256_testc_ps
_mm256_testc_si256
_mm256_testnzc_pd
_mm256_testnzc_ps, _mm_testnzc_ps
_mm256_testnzc_pd, _mm_testnzc_pd
_mm256_testnzc_si256
_mm256_testz_pd
_mm256_testz_ps
_mm256_testz_si256
_mm256_unpackhi_pd
_mm256_unpackhi_ps
_mm256_unpacklo_pd
_mm256_unpacklo_ps
_mm256_xor_pd
_mm256_xor_ps
_mm256_zeroall
_mm256_zeroupper
Intel® SVML Intrinsic
_mm_asinh_pd
_mm_asinh_ps
_mm_cos_pd
_mm_asinh_pd
_mm_asinh_ps
_mm_cos_pd
Intel-provided libraries
shared-intel
static-intel
option linking dynamically
option linking statically
intermediate files
save-temps, Qsave-temps
option saving during compilation
intermediate language scalar optimizer
intermediate representation (IR)
Interprocedural Optimization (IPO) Overview
Using IPO
interoperability
gcc Interoperability
with g++*
with gcc*
interoperability options
interprocedural optimizations
Compiler Directed Inline Expansion of User Functions
Interprocedural Optimization (IPO) Quick Reference
Creating a Library from IPO Objects
Interprocedural Optimization (IPO) Overview
Understanding Code Layout and Multi-Object IPO
ipo, Qipo
finline-functions
Using IPO
ip, Qip
Interval Profile Dumping
IPO for Large Programs
IPO-Related Performance Issues
Profile-Guided Optimizations Overview
Interprocedural Optimizations (IPO) Report
Generating Reports
capturing intermediate output
code layout
compilation
compiling
considerations
creating libraries
initiating
issues
large programs
linking
Interprocedural Optimization (IPO) Overview
Using IPO
option enabling additional
option enabling between files
option enabling for single file compilation
options
overview
performance
reports
using
whole program analysis
xiar
xild
xilibtool
intrinsics
Intrinsics that Increase Performance Across All IA
Overview: Intrinsics Reference
Prefetching Support
Naming and Usage Syntax
References
Inline Assembly
Details about Intrinsics
Alignment Support
Overview: Data Alignment, Memory Allocation Intrinsics, and Inline Assembly
Allocating and Freeing Aligned Memory Blocks
about
data alignment
Alignment Support
Overview: Data Alignment, Memory Allocation Intrinsics, and Inline Assembly
data types
Increased Performance across IA
inline assembly
Inline Assembly
Overview: Data Alignment, Memory Allocation Intrinsics, and Inline Assembly
memory allocation
Overview: Data Alignment, Memory Allocation Intrinsics, and Inline Assembly
Allocating and Freeing Aligned Memory Blocks
naming and syntax
references
registers
Intrinsics for all IA
Miscellaneous Intrinsics
Overview: Intrinsic Performance across Intel Architectures
String and Block Copy Intrinsics
Integer Arithmetic Intrinsics
Floating-point Intrinsics
arithmetic intrinsics
floating point intrinsics
miscellaneous intrinsics
string and block copy intrinsics
introduction to Optimizing Applications
introduction to the compiler
-ip compiler option
-IPF-fltacc compiler option
-IPF-flt-eval-method0 compiler option
-IPF-fma compiler option
-IPF-fp-relaxed compiler option
-ip-no-inlining compiler option
-ip-no-pinlining compiler option
IPO
ipo-jobs, Qipo-jobs
Linking Tools and Options
options
option specifying jobs during the link phase of
-ipo-c compiler option
-ipo compiler option
ipo, Qipo
Using IPO
-ipo-jobs compiler option
-ipo-S compiler option
-ipo-separate compiler option
-ipp compiler option
-iprefix compiler option
-iquote compiler option
IR
Interprocedural Optimization (IPO) Overview
Using IPO
-isystem compiler option
IVDEP
High-Level Optimizations (HLO) Overview
effect when tuning applications
-ivdep-parallel compiler option
-iwithprefixbefore compiler option
-iwithprefix compiler option
jump tables
opt-jump-tables, Qopt-jump-tables
option enabling generation of
-Kc++ compiler option
-kernel compiler option
KMP_AFFINITY
Thread Affinity Interface (Linux* and Windows*)
OpenMP* Environment Variables
modifier
offset
permute
type
KMP_ALL_THREADS
KMP_BLOCKTIME
KMP_LIBRARY
OpenMP* Environment Variables
OpenMP* Support Libraries
KMP_MONITOR_STACKSIZE
KMP_STACKSIZE
KMP_VERSION
Lambda expressions
Lambda Expressions
Understanding Lambda-Capture
Lambda Function Object
Details on Using Lambda Expressions in C++
details on using in C++
function object
lambda-capture
language extensions
gcc Compatibility
g++*
gcc*
-l compiler option
-L compiler option
LD_LIBRARY_PATH
libgcc library
shared-libgcc
static-libgcc
option linking dynamically
option linking statically
libraries
print-multi-lib
Bstatic
Using Intel Shared Libraries
Default Libraries
Managing Libraries
Timing Your Application
Bdynamic
Intel Extension Routines to OpenMP*
OpenMP* Run-time Library Routines
nodefaultlibs
static
Creating Libraries
-c compiler option
creating your own
default
-fPIC compiler option
Intel(R) Math Library
LD_LIBRARY_PATH
managing
OpenMP* run-time routines
Intel Extension Routines to OpenMP*
OpenMP* Run-time Library Routines
option enabling dynamic linking of
option enabling static linking of
option preventing linking with shared
option preventing use of standard
option printing location of system
shared
Using Intel Shared Libraries
Creating Libraries
-shared compiler option
static
library
L
l
option searching in specified directory for
option to search for
Library extensions
Introduction
Introduction to Intel's valarray Implementation
valarray implementation
library functions
Intel Extension Routines to OpenMP*
Inline Function Expansion
OpenMP* Run-time Library Routines
Intel extension
OpenMP* run-time routines
library math functions
fmath-errno
option testing errno after calls to
linker
Xlinker
mrelax
option passing linker option relax to
option passing linker option to
linking
c
nostartfiles
nostdlib
option preventing use of startup files andlibraries when
option preventing use of startup files when
option suppressing
linking options
linking tools
Creating a Library from IPO Objects
Interprocedural Optimization (IPO) Overview
IPO-Related Performance Issues
Linking Tools and Options
xild
Creating a Library from IPO Objects
Interprocedural Optimization (IPO) Overview
IPO-Related Performance Issues
xilibtool
xilink
Interprocedural Optimization (IPO) Overview
IPO-Related Performance Issues
linking with IPO
Linux* compileroptions
Wmissing-declarations
-Wmissing-declarations
Linux* compiler options
check-uninit
strict-ansi
ftemplate-depth, Qtemplate-depth
mtune
opt-report-help, Qopt-report-help
w
wn, Qwn
inline-level, Ob
Wa
traceback
tcollect, Qtcollect
use-intel-optimized-headers, Quse-intel-optimized-headers
dumpversion
ftrapuv, Qtrapuv
Wcomment
iwithprefix
par-runtime-control, Qpar-runtime-control
opt-prefetch, Qopt-prefetch
fvisibility
mserialize-volatile, Qserialize-volatile
prof-data-order, Qprof-data-order
fjump-tables
openmp-link, Qopenmp-link
openmp-stubs, Qopenmp-stubs
iquote
MF, QMF
Wabi
Wunused-function
print-multi-lib
debug (Linux* OS and Mac OS* X)
Specifying Executable Files
Wpragma-once
ftls-model
About Preprocessor Options
pie
opt-report, Qopt-report
S
ax, Qax
Using Options to Define Macros
openmp-profile, Qopenmp-profile
IPF-flt-eval-method0, QIPF-flt-eval-method0
fp-port, Qfp-port
imacros
opt-report-file, Qopt-report-file
malign-double
fmudflap
fno-implicit-templates
v
tbb, Qtbb
tcheck, Qtcheck
P
unroll, Qunroll
Winline
openmp-threadprivate, Qopenmp-threadprivate
fkeep-static-consts, Qkeep-static-consts
fp-relaxed, Qfp-relaxed
fno-implicit-inline-templates
openmp-lib, Qopenmp-lib
export-dir
Wreturn-type
mfixed-range
par-num-threads, Qpar-num-threads
inline-min-size, Qinline-min-size
Wbrief
export
C
L
pch-use
shared-libgcc
Specifying Alternate Tools and Paths
o
opt-report-phase, Qopt-report-phase
inline-factor, Qinline-factor
Specifying Include Files
rcd, Qrcd
Bstatic
shared-intel
multibyte-chars, Qmultibyte-chars
Os
prof-src-root, Qprof-src-root
Werror, WX
ip-no-inlining, Qip-no-inlining
ipo-S, Qipo-S
fast-transcendentals, Qfast-transcendentals
fnon-call-exceptions
prof-file, Qprof-file
inline-max-per-compile, Qinline-max-per-compile
Wextra-tokens
A-, QA-
global-hoist, Qglobal-hoist
par-report, Qpar-report
mp
diag, Qdiag
pthread
par-affinity, Qpar-affinity
x (type option)
use-asm, Quse-asm
finline-limit
MP
MD, QMD
vec-guard-write, Qvec-guard-write
shared
fmath-errno
Weffc++, Qeffc++
fast
T
diag-id-numbers, Qdiag-id-numbers
M, QM
Qinstall
MG, QMG
ffnalias
opt-streaming-stores, Qopt-streaming-stores
static-intel
fsource-asm
help-pragma, Qhelp-pragma
vec-threshold, Qvec-threshold
funsigned-bitfields
fexceptions
opt-loadpair, Qopt-loadpair
prof-func-order, Qprof-func-order
X
E
opt-prefetch-next-iteration, Qopt-prefetch-next-iteration
Wformat-security
par-threshold, Qpar-threshold
restrict, Qrestrict
Qoption
gxx-name
ip-no-pinlining, Qip-no-pinlining
Wl
save-temps, Qsave-temps
prof-func-groups
diag-error-limit, Qdiag-error-limit
static-libgcc
ipp, Qipp
Wreorder
version
fno-gnu-keywords
Bdynamic
diag-file-append, Qdiag-file-append
ipo, Qipo
complex-limited-range, Qcomplex-limited-range
ansi
alias-const, Qalias-const
Wp64
fpic
Wshadow
help
pragma-optimization-level
inline-max-per-routine, Qinline-max-per-routine
IPF-fltacc, QIPF-fltacc
we, Qwe
prof-src-dir, Qprof-src-dir
fstack-security-check, GS
early-template-check
finline-functions
m32, m64
fbuiltin, Oi
fomit-frame-pointer, Oy
falign-stack
inline-forceinline, Qinline-forceinline
Specifying Object Files
tprofile, Qtprofile
Wp
mcmodel
falias
inline-debug-info, Qinline-debug-info
prof-hotness-threshold, Qprof-hotness-threshold
inline-max-total-size, Qinline-max-total-size
EP
ww, Qww
c99, Qc99
ftz, Qftz
parallel, Qparallel
ivdep-parallel, Qivdep-parallel
fsyntax-only
pch-create, Yc
fp-model, fp
Wtrigraphs
use-msasm
Wuninitialized
idirafter
isystem
MM, QMM
align
openmp-report, Qopenmp-report
pc, Qpc
Qlocation
fp-speculation, Qfp-speculation
fabi-version
fma, Qfma
fverbose-asm
funroll-all-loops
prec-div, Qprec-div
vec-report, Qvec-report
MMD, QMMD
mregparm
opt-calloc
w, W
icc
g, Zi, Z7
iwithprefixbefore
dD, QdD
fminshared
rct, Qrct
no-bss-init, Qnobss-init
prof-dir, Qprof-dir
unroll-aggressive, Qunroll-aggressive
fshort-enums
sox, Qsox
std, Qstd
fargument-noalias-global
map-opts, Qmap-opts
Wunused-variable
Wformat
prof-gen, Qprof-gen
ip, Qip
c
V (Linux* and Mac OS* X)
opt-jump-tables, Qopt-jump-tables
diag-enable sc-parallel, Qdiag-enable:sc-parallel
mkl, Qmkl
fnsplit, Qfnsplit
A, QA
tcollect-filter, Qtcollect-filter
minstruction, Qinstruction
u (Linux*)
Xlinker
fno-operator-names
pch-dir
fno-rtti
m
nostartfiles
MT, QMT
finline
opt-mod-versioning, Qopt-mod-versioning
fargument-alias, Qalias-args
U
prof-use, Qprof-use
funsigned-char
fr32
ffreestanding, Qfreestanding
inline-calloc, Qinline-calloc
gcc
kernel
reserve-kernel-regs
par-schedule, Qpar-schedule
ansi-alias, Qansi-alias
fvisibility-inlines-hidden
vec, Qvec
opt-block-factor, Qopt-block-factor
Wmissing-prototypes
falign-functions, Qfnalign
prof-src-root-cwd, Qprof-src-root-cwd
Werror-all
x, Qx
fpie
Wnon-virtual-dtor
opt-ra-region-strategy, Qopt-ra-region-strategy
I
opt-class-analysis, Qopt-class-analysis
diag-enable sc-include, Qdiag-enable:sc-include
opt-subscript-in-range, Qopt-subscript-in-range
gcc-version
inline-max-size, Qinline-max-size
ipo-jobs, Qipo-jobs
p
Wmain
l
gcc-name
dryrun
march
opt-prefetch-issue-excl-hint, Qopt-prefetch-issue-excl-hint
fnon-lvalue-assign
dM, QdM
wd, Qwd
Wcontext-limit, Qcontext-limit
diag-dump, Qdiag-dump
dumpmachine
ipo-separate, Qipo-separate
g0
B
Specifying Assembly Files
Wdeprecated
dN, QdN
gdwarf-2
nodefaultlibs
scalar-rep, Qscalar-rep
Symbolic Debugging and Optimizations
Kc++, TP
pch
Wunknown-pragmas
wo, Qwo
Preparing for Debugging
H, QH
Using Options for Preprocessing
openmp-task, Qopenmp-task
wr, Qwr
ffunction-sections
fcommon
Wall
fpermissive
opt-malloc-options
opt-report-routine, Qopt-report-routine
static
finstrument-functions, Qinstrument-functions
cxxlib
fpack-struct
mp1, Qprec
prec-sqrt, Qprec-sqrt
opt-multi-version-aggressive, Qopt-multi-version-aggressive
openmp, Qopenmp
MQ
opt-prefetch-initial-values, Qopt-prefetch-initial-values
multiple-processes, MP
Wcheck
Wstrict-prototypes
O
ipo-c, Qipo-c
nostdlib
diag-file, Qdiag-file
Wpointer-arith
freg-struct-return
dynamic-linker
auto-ilp32, Qauto-ilp32
diag-once, Qdiag-once
fp-stack-check, Qfp-stack-check
nostdinc++
opt-mem-bandwidth, Qopt-mem-bandwidth
Zp
fcode-asm
D
nolib-inline
iprefix
mrelax
-A
-A-
-alias-args
-alias-const
-align
-ansi
-ansi-alias
-auto-ilp32
-ax
-B
-Bdynamic
-Bstatic
-c
Specifying Object Files
c
-C
About Preprocessor Options
C
Using Options for Preprocessing
-c99
-check-uninit
-complex-limited-range
-cxxlib
-D
About Preprocessor Options
Using Options to Define Macros
D
-dD
-debug
-diag
-diag-dump
-diag-enable sc-include
-diag-enable sc-parallel
-diag-error-limit
-diag-file
-diag-file-append
-diag-id-numbers
-diag-once
-dM
-dN
-dryrun
-dumpmachine
-dumpversion
-dynamic-linker
-E
About Preprocessor Options
E
Using Options for Preprocessing
-early-template-check
-EP
About Preprocessor Options
EP
Using Options for Preprocessing
-export
-export-dir
-fabi-version
-falias
-falign-functions
-falign-stack
-fargument-alias
-fargument-noalias-global
-fast
-fast-transcendentals
-fbuiltin
-fcode-asm
-fcommon
-fdata-sections
-fexceptions
-ffnalias
-ffreestanding
-ffunction-sections
-finline
-finline-functions
-finline-limit
-finstrument-functions
-fjump-tables
-fkeep-static-consts
-fma
-fmath-errno
-fminshared
-fmudflap
-fno-gnu-keywords
-fno-implicit-inline-templates
-fno-implicit-templates
-fnon-call-exceptions
-fnon-lvalue-assign
-fno-operator-names
-fno-rtti
-fnsplit
-fp
-fpack-struct
-fpermissive
-fpic
-fpie
-fp-model
-fp-port
-fp-relaxed
-fp-speculation
-fp-stack-check
-fr32
-freg-struct-return
-fshort-enums
-fsource-asm
-fstack-protector
-fstack-security-check
-fsyntax-only
-ftemplate-depth
-ftls-model
-ftrapuv
-ftz
-funroll-all-loops
-funsigned-bitfields
-funsigned-char
-fverbose-asm
-fvisibility
-fvisibility-inlines-hidden
-g
g, Zi, Z7
Symbolic Debugging and Optimizations
Preparing for Debugging
-g0
-gcc
-gcc-name
-gcc-sys
-gcc-version
-gdwarf-2
-global-hoist
-gxx-name
-H
-help
-help-pragma
-I
Specifying Include Files
I
-icc
-idirafter
-imacros
-inline-calloc
-inline-debug-info
-inline-factor
-inline-forceinline
-inline-level
-inline-max-per-compile
-inline-max-per-routine
-inline-max-size
-inline-max-total-size
-inline-min-size
-ip
-IPF-fltacc
-IPF-flt-eval-method0
-IPF-fma
-IPF-fp-relaxed
-ip-no-inlining
-ip-no-pinlining
-ipo
-ipo-c
-ipo-jobs
-ipo-S
-ipo-separate
-ipp
-iprefix
-iquote
-isystem
-ivdep-parallel
-iwithprefix
-iwithprefixbefore
-Kc++
-kernel
-l
-L
-m
-M
-m32
-m64
-malign-double
-map-opts
-march
-mcmodel
-mcpu
-MD
-MF
-mfixed-range
-MG
-mieee-fp
-minstruction
-mkl
-MM
-MMD
-mp
-MP
-mp1
-MQ
-mregparm
-mrelax
-mserialize-volatile
-MT
-mtune
-multibyte-chars
-multiple-processes
-nobss-init
-nodefaultlibs
-nolib-inline
-nostartfiles
-nostdinc++
-nostdlib
-o
Specifying Executable Files
o
Specifying Object Files
-O
-Ob
-openmp
-openmp-lib
-openmp-link
-openmp-profile
-openmp-report
-openmp-stubs
-openmp-task
-openmp-threadprivate
-opt-block-factor
-opt-calloc
-opt-class-analysis
-opt-jump-tables
-opt-loadpair
-opt-malloc-options
-opt-mem-bandwidth
-opt-mod-versioning
-opt-multi-version-aggressive
-opt-prefetch
-opt-prefetch-initial-values
-opt-prefetch-issue-excl-hint
-opt-prefetch-next-iteration
-opt-ra-region-strategy
-opt-report
-opt-report-file
-opt-report-help
-opt-report-phase
-opt-report-routine
-opt-streaming-stores
-opt-subscript-in-range
-Os
-p
-P
About Preprocessor Options
P
Using Options for Preprocessing
-par-affinity
-parallel
-par-num-threads
-par-report
-par-runtime-control
-par-schedule
-par-threshold
-pc
-pch
-pch-create
-pch-dir
-pch-use
-pg
-pie
-pragma-optimization-level
-prec-div
-prec-sqrt
-print-multi-lib
-prof-data-order
-prof-dir
-prof-file
-prof-func-groups
-prof-func-order
-prof-gen
-prof-hotness-threshold
-prof-src-dir
-prof-src-root
-prof-src-root-cwd
-prof-use
-pthread
-Qinstall
-Qlocation
Specifying Alternate Tools and Paths
Qlocation
-Qoption
Specifying Alternate Tools and Paths
Qoption
-qp
-rcd
-rct
-reserve-kernel-regs
-restrict
-S
S
Specifying Assembly Files
-save-temps
-scalar-rep
-shared
-shared-intel
-shared-libgcc
-sox
-static
-static-intel
-static-libgcc
-std
-strict-ansi
-T
-tbb
-tcheck
-tcollect
-tcollect-filter
-tprofile
-traceback
-U
About Preprocessor Options
Using Options to Define Macros
U
-u (L*)
-unroll
-unroll-aggressive
-use-asm
-use-intel-optimized-headers
-use-msasm
-v
-V (L*)
-vec
-vec-guard-write
-vec-report
-vec-threshold
--version
-w
w
w, W
-Wa
-Wabi
-Wall
-Wbrief
-Wcheck
-Wcomment
-Wcontext-limit
-wd
-Wdeprecated
-we
-Weffc++
-Werror
-Werror-all
-Wextra-tokens
-Wformat
-Wformat-security
-Winline
-Wl
-Wmain
-Wmissing-prototypes
-wn
-Wnon-virtual-dtor
-wo
-Wp
-Wp64
-Wpointer-arith
-Wpragma-once
-wr
-Wreorder
-Wreturn-type
-Wshadow
-Wstrict-prototypes
-Wtrigraphs
-Wuninitialized
-Wunknown-pragmas
-Wunused-function
-Wunused-variable
-ww
-x
-X
Specifying Include Files
X
-x (type)
-Xlinker
-Zp
loadpair optimization
opt-loadpair, Qopt-loadpair
option enabling
lock routines
loop blocking factor
opt-block-factor, Qopt-block-factor
option specifying
loop interchange
loops
par-runtime-control, Qpar-runtime-control
Overview of Parallelism Method
Loop Constructs
Loop Unrolling
unroll, Qunroll
Loop Independence
Programming with Auto-parallelization
Applying Optimization Strategies
High-Level Optimizations (HLO) Overview
unroll-aggressive, Qunroll-aggressive
opt-block-factor, Qopt-block-factor
Vectorization and Loops
Understanding Run-time Performance
anti dependency
constructs
dependencies
distribution
flow dependency
independence
interchange
Applying Optimization Strategies
High-Level Optimizations (HLO) Overview
Understanding Run-time Performance
manual transformation
option performing run-time checks for
option specifying blocking factor for
option specifying maximum times to unroll
option using aggressive unrolling for
output dependency
parallelization
Overview of Parallelism Method
Programming with Auto-parallelization
Vectorization and Loops
reductions
transformations
High-Level Optimizations (HLO) Overview
Understanding Run-time Performance
unrolling
vectorization
loop unrolling
Loop Unrolling
Programming Guidelines for Vectorization
High-Level Optimizations (HLO) Overview
Generating Reports
limitations of
using the HLO optimizer
High-Level Optimizations (HLO) Overview
Generating Reports
-m32 compiler option
-m64 compiler option
Mac OS* X compiler options
check-uninit
strict-ansi
ftemplate-depth, Qtemplate-depth
mtune
opt-report-help, Qopt-report-help
wn, Qwn
inline-level, Ob
Wa
traceback
use-intel-optimized-headers, Quse-intel-optimized-headers
ftrapuv, Qtrapuv
iwithprefix
par-runtime-control, Qpar-runtime-control
opt-prefetch, Qopt-prefetch
fvisibility
mserialize-volatile, Qserialize-volatile
prof-data-order, Qprof-data-order
fjump-tables
openmp-link, Qopenmp-link
openmp-stubs, Qopenmp-stubs
iquote
MF, QMF
Wabi
Wunused-function
print-multi-lib
debug (Linux* OS and Mac OS* X)
Wpragma-once
ftls-model
opt-report, Qopt-report
S
ax, Qax
fp-port, Qfp-port
imacros
opt-report-file, Qopt-report-file
malign-double
F (Mac OS* X)
fno-implicit-templates
v
unroll, Qunroll
Winline
fkeep-static-consts, Qkeep-static-consts
fno-implicit-inline-templates
export-dir
Wreturn-type
mfixed-range
par-num-threads, Qpar-num-threads
inline-min-size, Qinline-min-size
Wbrief
export
C
L
pch-use
o
opt-report-phase, Qopt-report-phase
inline-factor, Qinline-factor
rcd, Qrcd
shared-intel
multibyte-chars, Qmultibyte-chars
prof-src-root, Qprof-src-root
Werror, WX
ip-no-inlining, Qip-no-inlining
ipo-S, Qipo-S
fast-transcendentals, Qfast-transcendentals
fnon-call-exceptions
prof-file, Qprof-file
inline-max-per-compile, Qinline-max-per-compile
Wextra-tokens
A-, QA-
global-hoist, Qglobal-hoist
par-report, Qpar-report
diag, Qdiag
pthread
x (type option)
use-asm, Quse-asm
finline-limit
MP
MD, QMD
vec-guard-write, Qvec-guard-write
fmath-errno
Weffc++, Qeffc++
fast
diag-id-numbers, Qdiag-id-numbers
M, QM
Qinstall
MG, QMG
ffnalias
opt-streaming-stores, Qopt-streaming-stores
static-intel
fsource-asm
help-pragma, Qhelp-pragma
vec-threshold, Qvec-threshold
funsigned-bitfields
fexceptions
prof-func-order, Qprof-func-order
X
E
Wformat-security
par-threshold, Qpar-threshold
restrict, Qrestrict
Qoption
gxx-name
ip-no-pinlining, Qip-no-pinlining
Wl
save-temps, Qsave-temps
prof-func-groups
diag-error-limit, Qdiag-error-limit
ipp, Qipp
Wreorder
version
fno-gnu-keywords
diag-file-append, Qdiag-file-append
ipo, Qipo
complex-limited-range, Qcomplex-limited-range
ansi
malign-power
alias-const, Qalias-const
Wp64
fpic
Wshadow
help
pragma-optimization-level
inline-max-per-routine, Qinline-max-per-routine
we, Qwe
prof-src-dir, Qprof-src-dir
fstack-security-check, GS
early-template-check
finline-functions
m32, m64
fbuiltin, Oi
fomit-frame-pointer, Oy
falign-stack
inline-forceinline, Qinline-forceinline
Wp
mdynamic-no-pic
mcmodel
falias
inline-max-total-size, Qinline-max-total-size
EP
ww, Qww
c99, Qc99
ftz, Qftz
parallel, Qparallel
fsyntax-only
malign-mac68k
pch-create, Yc
fp-model, fp
Wtrigraphs
malign-natural
use-msasm
Wuninitialized
idirafter
isystem
MM, QMM
align
openmp-report, Qopenmp-report
pc, Qpc
Qlocation
fp-speculation, Qfp-speculation
fabi-version
fverbose-asm
funroll-all-loops
prec-div, Qprec-div
vec-report, Qvec-report
MMD, QMMD
mregparm
w, W
icc
g, Zi, Z7
iwithprefixbefore
dD, QdD
fminshared
dynamiclib
rct, Qrct
no-bss-init, Qnobss-init
prof-dir, Qprof-dir
unroll-aggressive, Qunroll-aggressive
fshort-enums
std, Qstd
fargument-noalias-global
Wunused-variable
Wformat
prof-gen, Qprof-gen
c
V (Linux* and Mac OS* X)
opt-jump-tables, Qopt-jump-tables
diag-enable sc-parallel, Qdiag-enable:sc-parallel
mkl, Qmkl
A, QA
minstruction, Qinstruction
u (Linux*)
Xlinker
fno-operator-names
pch-dir
fno-rtti
m
nostartfiles
MT, QMT
finline
fargument-alias, Qalias-args
prof-use, Qprof-use
funsigned-char
ffreestanding, Qfreestanding
inline-calloc, Qinline-calloc
gcc
kernel
reserve-kernel-regs
par-schedule, Qpar-schedule
ansi-alias, Qansi-alias
fpascal-strings
fvisibility-inlines-hidden
fasm-blocks
vec, Qvec
opt-block-factor, Qopt-block-factor
Wmissing-prototypes
falign-functions, Qfnalign
prof-src-root-cwd, Qprof-src-root-cwd
Werror-all
Wnon-virtual-dtor
opt-ra-region-strategy, Qopt-ra-region-strategy
I
opt-class-analysis, Qopt-class-analysis
diag-enable sc-include, Qdiag-enable:sc-include
opt-subscript-in-range, Qopt-subscript-in-range
gcc-version
inline-max-size, Qinline-max-size
ipo-jobs, Qipo-jobs
p
Wmain
gcc-name
dryrun
march
fnon-lvalue-assign
dM, QdM
wd, Qwd
Wcontext-limit, Qcontext-limit
diag-dump, Qdiag-dump
dumpmachine
ipo-separate, Qipo-separate
g0
B
Wdeprecated
dN, QdN
Wmissing-declarations
gdwarf-2
nodefaultlibs
scalar-rep, Qscalar-rep
Kc++, TP
pch
Wunknown-pragmas
wo, Qwo
H, QH
openmp-task, Qopenmp-task
wr, Qwr
ffunction-sections
fcommon
Wall
fpermissive
opt-malloc-options
opt-report-routine, Qopt-report-routine
finstrument-functions, Qinstrument-functions
cxxlib
fpack-struct
mp1, Qprec
prec-sqrt, Qprec-sqrt
opt-multi-version-aggressive, Qopt-multi-version-aggressive
openmp, Qopenmp
MQ
multiple-processes, MP
Wcheck
Wstrict-prototypes
O
ipo-c, Qipo-c
nostdlib
diag-file, Qdiag-file
Wpointer-arith
freg-struct-return
diag-once, Qdiag-once
fp-stack-check, Qfp-stack-check
nostdinc++
fcode-asm
D
staticlib
nolib-inline
iprefix
-A
-A-
-alias-args
-alias-const
-align
-ansi
-ansi-alias
-ax
-B
-c
-C
-c99
-check-uninit
-complex-limited-range
-cxxlib
-D
-dD
-debug
-diag
-diag-dump
-diag-enable sc-include
-diag-enable sc-parallel
diag-error-limit
-diag-file
-diag-file-append
-diag-id-numbers
-diag-once
-dM
-dN
-dryrun
-dumpmachine
-dynamiclib
-E
-early-template-check
-EP
-export
-export-dir
-F
-fabi-version
-falias
-falign-functions
-falign-stack
-fargument-noalias-global
-fasm-blocks
-fast
-fast-transcendentals
-fbuiltin
-fcode-asm
-fcommon
-fexceptions
-ffnalias
-ffreestanding
-ffunction-sections
-finline
-finline-functions
-finline-limit
-finstrument-functions
-fjump-tables
-fkeep-static-consts
-fmath-errno
-fminshared
-fno-gnu-keywords
-fno-implicit-inline-templates
-fno-implicit-templates
-fnon-call-exceptions
-fnon-lvalue-assign
-fno-omit-frame-pointer
-fno-operator-names
-fno-rtti
-fp
-fpack-struct
-fpascal-strings
-fpermissive
-fpic
-fp-model
-fp-port
-fp-speculation
-fp-stack-check
-freg-struct-return
-fshort-enums
-fsource-asm
-fstack-protector
-fstack-security-check
-fsyntax-only
-ftemplate-depth
-ftls-model
-ftrapuv
-ftz
-funroll-all-loops
-funroll-loops
-funsigned-bitfields
-funsigned-char
-fverbose-asm
-fvisibility
-fvisibility-inlines-hidden
-g
-g0
-gcc
-gcc-name
-gcc-sys
-gcc-version
-gdwarf-2
-global-hoist
-gxx-name
-H
-help
-help-pragma
-I
-icc
-idirafter
-imacros
-inline-calloc
-inline-factor
-inline-forceinline
-inline-level
-inline-max-per-compile
-inline-max-per-routine
-inline-max-size
-inline-max-total-size
-inline-min-size
-ip
-ip-no-inlining
-ip-no-pinlining
-ipo
-ipo-c
-ipo-jobs
-ipo-S
-ipo-separate
-ipp
-iprefix
-iquote
-isystem
-iwithprefix
-iwithprefixbefore
-Kc++
-kernel
-L
-m
-M
-m32
-m64
-malign-double
-malign-mac68k
-malign-natural
-malign-power
-march
-mcmodel
-mcpu
-MD
-mdynamic-no-pic
-MF
-mfixed-range
-MG
-minstruction
-mkl
-MM
-MMD
-MP
-mp1
-MQ
-mregparm
-mserialize-volatile
-MT
-mtune
-multibyte-chars
-multiple-processes
-nobss-init
-nodefaultlibs
-nolib-inline
-nostartfiles
-nostdinc
-nostdinc++
-nostdlib
-o
-O
-O0
-O1
-O2
-O3
-Ob
-openmp
-openmp-link
-openmp-report
-openmp-stubs
-openmp-task
-opt-block-factor
-opt-class-analysis
-opt-jump-tables
-opt-malloc-options
-opt-multi-version-aggressive
-opt-prefetch
-opt-ra-region-strategy
-opt-report
-opt-report-file
-opt-report-help
-opt-report-phase
-opt-report-routine
-opt-streaming-stores
-opt-subscript-in-range
-p
-parallel
-par-num-threads
-par-report
-par-runtime-control
-par-schedule
-par-threshold
-pc
-pch
-pch-create
-pch-dir
-pch-use
-pg
-pragma-optimization-level
-prec-div
-prec-sqrt
-print-multi-lib
-prof-data-order
-prof-dir
-prof-file
-prof-func-groups
-prof-func-order
-prof-gen
-prof-src-dir
-prof-src-root
-prof-src-root-cwd
-prof-use
-pthread
-Qinstall
-Qlocation
-Qoption
-qp
-rcd
-rct
-reserve-kernel-regs
-restrict
-S
-save-temps
-scalar-rep
-shared-intel
-static-intel
-staticlib
-std
-strict-ansi
-traceback
-u (L*)
-unroll
-unroll-aggressive
-use-asm
-use-intel-optimized-headers
-use-msasm
-v
-V
-vec
-vec-guard-write
-vec-report
-vec-threshold
--version
-w
-Wa
-Wabi
-Wall
-Wbrief
-Wcheck
-Wcontext-limit
-wd
-Wdeprecated
-we
-Weffc++
-Werror
-Werror-all
-Wextra-tokens
-Wformat
-Wformat-security
-Winline
-Wl
-Wmain
-Wmissing-declarations
-Wmissing-prototypes
-wn
-Wnon-virtual-dtor
-wo
-Wp
-Wp64
-Wpointer-arith
-Wpragma-once
-wr
-Wreorder
-Wreturn-type
-Wshadow
-Wstrict-prototypes
-Wtrigraphs
-Wuninitialized
-Wunknown-pragmas
-Wunused-function
-Wunused-variable
-ww
-x (type)
-Xlinker
macro names
D
option associating with an optional value
macros
Predefined Macros for Interoperability
Equivalent Macros
ANSI Standard Predefined Macros
Additional Predefined Macros
maintainability
Intel Extension Routines to OpenMP*
Avoiding Mixed Data Type Arithmetic Expressions
allocation
main thread
Qpar-adjust-stack
option adjusting the stack size for
make, using
makefiles
Modifying Your makefile
modifying
-malign-double compiler option
-malign-mac68k compiler option
-malign-natural compiler option
-malign-power compiler option
manual transformations
-map-opts compiler option
-march compiler option
math functions
fp-relaxed, Qfp-relaxed
option enabling faster code sequences for
Math library
Trigonometric Functions
Miscellaneous Functions
Remainder Functions
Nearest Integer Functions
Hyperbolic Functions
Complex Functions
Special Functions
Exponential Functions
Complex Functions
cabs library function
cacosh library function
cacos library function
carg library function
casinh library function
casin library function
catanh library function
catan library function
ccosh library function
ccos library function
cexp10 library function
cexp library function
cimag library function
cis library function
clog2 library function
clog library function
conj library function
cpow library function
cproj library function
creal library function
csinh library function
csin library function
csqrt library function
ctanh library function
ctan library function
Exponential Functions
cbrt library function
exp10 library function
exp2 library function
exp library function
expm1 library function
frexp library function
hypot library function
ilogb library function
ldexp library function
log10 library function
log1p library function
log2 library function
logb library function
log library function
pow library function
scalb library function
scalbn library function
sqrt library function
Hyperbolic Functions
acosh library function
asinh library function
atanh library function
cosh library function
sinhcosh library function
sinh library function
tanh library function
Miscellaneous Functions
copysign library function
fabs library function
fdim library function
finite library function
fma library function
fmax library function
fmin library function
Miscellaneous Functions
nextafter library function
Nearest Integer Functions
ceil library function
floor library function
llrint library function
llround library function
lrint library function
lround library function
modf library function
nearbyint library function
rint library function
round library function
trunc library function
Remainder Functions
fmod library function
remainder library function
remquo library function
Special Functions
annuity library function
compound library function
erfc library function
erf library function
gamma_r library function
gamma library function
j0 library function
j1 library function
jn library function
lgamma_r library function
lgamma library function
tgamma library function
y0 library function
y1 library function
yn library function
Trigonometric Functions
acosd library function
acos library function
asind library function
asin library function
atan2 library function
atand2 library function
atand library function
atan library function
cosd library function
cos library function
cotd library function
cot library function
sincosd library function
sincos library function
sind library function
sin library function
tand library function
tan library function
Math Library
Using the Intel Math Library
Function List
C99 Macros
Overview: Intel® Math Library
C99 macros
for Linux* OS
function list
using on Linux* OS
-m compiler option
-M compiler option
-mcpu compiler option
-MD compiler option
-mdynamic-no-pic compiler option
memory aliasing
memory bandwidth
opt-mem-bandwidth, Qopt-mem-bandwidth
option enabling tuning and heuristics for
memory dependency
ivdep-parallel, Qivdep-parallel
option specifying no loop-carried following IVDEP
memory loads
global-hoist, Qglobal-hoist
option enabling optimizations to move
memory model
mcmodel
option specifying large
option specifying small or medium
option to use specific
-MF compiler option
-mfixed-range compiler option
-MG compiler option
Microsoft* Visual C++
Qvc
option specifying compatibility with
Microsoft* Visual Studio
Qvc
option specifying compatibility with
-mieee-fp compiler option
-minstruction compiler option
mixing vectorizable types in a loop
-mkl compiler option
-MM compiler option
-MMD compiler option
MMX(TM)
MMX intrinsics
MMX™ Technology Shift Intrinsics
MMX™ Technology General Support Intrinsics
MMX™ Technology Compare Intrinsics
MMX™ Technology Logical Intrinsics
MMX™ Technology Packed Arithmetic Intrinsics
MMX™ Technology Set Intrinsics
add_pi16
add_pi32
add_pi8
adds_pi16
adds_pi8
adds_pu16
adds_pu8
and_si64
andnot_si64
arithmetic intrinsics
cmpeq_pi16
cmpeq_pi32
cmpeq_pi8
cmpgt_pi16
cmpgt_pi32
cmpgt_pi8
compare intrinsics
cvtm64_si64
cvtsi32_si64
cvtsi64_m64
cvtsi64_si32
empty
general support intrinsics
logical intrinsics
madd_pi16
mulhi_pi16
mullo_pi16
or_si64
packs_pi16
packs_pi32
packs_pu16
set_pi16
set_pi32
set_pi8
set1_pi16
set1_pi32
set1_pi8
set intrinsics
setr_pi16
setr_pi32
setr_pi8
setzero_si64
shift intrinsics
sll_pi16
sll_pi32
sll_pi64
slli_pi16
slli_pi32
slli_pi64
sra_pi16
sra_pi32
srai_pi16
srai_pi32
srl_pi16
srl_pi32
srl_pi64
srli_pi16
srli_pi32
srli_pi64
sub_pi16
sub_pi32
sub_pi8
subs_pi16
subs_pi8
subs_pu16
subs_pu8
unpackhi_pi16
unpackhi_pi32
unpackhi_pi8
unpacklo_pi16
unpacklo_pi32
unpacklo_pi8
xor_si64
MMX intrinsics for IA-64 architecture
MMX technology intrinsics
Details about MMX(TM) Technology Intrinsics
data types
registers
mock object files
modifying the compilation environment
modulo operations
opt-mod-versioning, Qopt-mod-versioning
option enabling versioning of
MOVBE instructions
minstruction, Qinstruction
option generating
-mp1 compiler option
-mp compiler option
-MP compiler option
-MQ compiler option
-mregparm compiler option
-mrelax compiler option
-mserialize-volatile compiler option
-MT compiler option
-mtune compiler option
-multibyte-chars compiler option
multiple processes
multiple-processes, MP
option creating
-multiple-processes compiler option
multithreaded programs
Overview of Parallelism Method
Auto-parallelization Overview
multithreading
Programming with Auto-parallelization
OpenMP* Support Libraries
multi-threading performance
tprofile, Qtprofile
option aiding analysis of
multi-version compiler supprt
MXCSR register
-nobss-init compiler option
-nodefaultlibs compiler option
-nolib-inline compiler option
non-unit memory access
NOPREFETCH
Prefetching Support
using
normalized floating-point number
-nostartfiles compiler option
-nostdinc++ compiler option
-nostdlib compiler option
Not-a-Number (NaN)
-Ob compiler option
object file
bigobj
option increasing number of sections in
object files
Specifying Object Files
specifying
-o compiler option
-O compiler option
OMP_DYNAMIC
OMP_NESTED
OMP_NUM_THREADS
OMP_SCHEDULE
OMP directives
Overview of Parallelism Method
OpenMP* Source Compatibility and Interoperability with Other Compilers
Workqueuing Constructs
Thread Affinity Interface (Linux* and Windows*)
OpenMP* Environment Variables
OpenMP* Examples
OpenMP* Support Libraries
Worksharing Using OpenMP*
OpenMP* Run-time Library Routines
Parallel Processing Model
THREADPRIVATEthreadprivate Directive
OpenMP* Advanced Issues
OpenMP* Report
advanced issues
compatibility libraries
OpenMP* Source Compatibility and Interoperability with Other Compilers
OpenMP* Support Libraries
compatibility with other compilers
debugging
directives
environment variables
Thread Affinity Interface (Linux* and Windows*)
OpenMP* Environment Variables
guidelines for using libraries
KMP_AFFINITY
Thread Affinity Interface (Linux* and Windows*)
OpenMP* Environment Variables
KMP_ALL_THREADS
KMP_BLOCKTIME
KMP_LIBRARY
KMP_MONITOR_STACKSIZE
KMP_STACKSIZE
KMP_VERSION
legacy libraries
OpenMP* Source Compatibility and Interoperability with Other Compilers
OpenMP* Support Libraries
library file names
load balancing
object-level interoperability
OMP_DYNAMIC
OMP_NESTED
OMP_NUM_THREADS
OMP_SCHEDULE
omp.h
parallel processing thread model
performance
reports
run-time library routines
source compatibility
support libraries
task
OpenMP*
openmp-stubs, Qopenmp-stubs
openmp-profile, Qopenmp-profile
openmp-threadprivate, Qopenmp-threadprivate
openmp-report, Qopenmp-report
openmp, Qopenmp
option controlling diagnostics
option enabling
option enabling analysis of applications
option enabling programs in sequential mode
option specifying threadprivate
OpenMP* analysis
OpenMP* Fortran directives
OpenMP* Directives and Clauses Summary
Intel Extension Routines to OpenMP*
OpenMP* Examples
clauses for
examples of
Intel extensions for
OpenMP* run-time library
openmp-link, Qopenmp-link
openmp-lib, Qopenmp-lib
option controlling which is linked to
option specifying
-openmp compiler option
-openmp-lib compiler option
openmp-lib, Qopenmp-lib
OpenMP* Source Compatibility and Interoperability with Other Compilers
-openmp-link compiler option
-openmp-profile compiler option (Linux* only)
-openmp-report compiler option
-openmp-stubs compiler option
-openmp-task compiler option
-openmp-threadprivate compiler option
Open Source tools
-opt-block-factor compiler option
-opt-calloc compiler option (Linux only)
-opt-class-analysis compiler option
optimal records to improve performance
Enabling Automatic Optimizations
Using a Performance Enhancement Methodology
Other Resources
Restricting Optimizations
Performance Enhancement Strategies
Generating Reports
analyzing applications
application-specific
hardware-related
library-related
methodology
options
Enabling Automatic Optimizations
Restricting Optimizations
restricting
setting
OS-related
reports
resources
restricting
setting
strategies
system-related
optimization
opt-prefetch, Qopt-prefetch
Other Considerations
ipo-S, Qipo-S
Og
O
ipo-c, Qipo-c
option enabling global
option enabling prefetch insertion
option generating single assembly file from multiple files
option generating single object file from multiple files
option specifying code
optimization report
opt-report-help, Qopt-report-help
opt-report, Qopt-report
opt-report-file, Qopt-report-file
opt-report-phase, Qopt-report-phase
opt-report-routine, Qopt-report-routine
option displaying phases for
option generating for routines with specified text
option generating to stderr
option specifying name for
option specifying phase to use for
optimizations
Overview of Parallelism Method
Ot
Targeting IA-64 Architecture Processors Automatically
Od
Os
Enabling Automatic Optimizations
Overview: Optimizing Applications
Restricting Optimizations
Profile-Guided Optimization (PGO) Quick Reference
High-Level Optimizations (HLO) Overview
Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
Profile-Guided Optimizations Overview
Automatic Optimizations Overview
compilation process
for specific processors
high-level language
option disabling all
option enabling all speed
optionenabling many speed
options for IA-32 architecture
options for IA-64 architecture
options for Intel(R) 64 architecture
overview of
Profile-Guided Optimizations Overview
Automatic Optimizations Overview
parallelization
PGO methodology
profile-guided
profile-guided optimization
optimization support
optimizer report generation
optimizing
Overview: Optimizing Applications
Performance Enhancement Strategies
Understanding Run-time Performance
applications
helping the compiler
overview
technical applications
optimizing performance
option mapping tool
options for IA-32 architectures
options used for IPO
Interprocedural Optimization (IPO) Quick Reference
Linking Tools and Options
-opt-jump-tables compiler option
-opt-loadpair compiler option
-opt-malloc-options compiler option
-opt-mem-bandwidth compiler option
-opt-mod-versioning compiler option
-opt-multi-version-aggressive compiler option
-opt-prefetch compiler option
-opt-prefetch-initial-values compiler option
-opt-prefetch-issue-excl-hint compiler option
-opt-prefetch-next-iteration compiler option
-opt-ra-region-strategy compiler option
About Register Allocation
opt-ra-region-strategy, Qopt-ra-region-strategy
example
-opt-report compiler option
opt-report, Qopt-report
Generating Reports
-opt-report-file compiler option
-opt-report-help compiler option
-opt-report-phase compiler option
-opt-report-routine compiler option
OptReport support
-opt-streaming-stores compiler option
-opt-subscript-in-range compiler option
ORDERED
OpenMP* Directives and Clauses Summary
overview of OpenMP* directives and clauses
-Os compiler option
output files
o
Output Files
option specifying name for
overflow
OpenMP* Run-time Library Routines
call to a runtime library routine
overview
Overview of Parallelism Method
Enabling Automatic Optimizations
Overview: Optimizing Applications
of optimizing for specific processors
of parallelism
packed structures
-par-affinity compiler option (Linux* only)
-parallel compiler option
PARALLEL DO
OpenMP* Directives and Clauses Summary
summary of OpenMP* directives and clauses
parallel invocations with makefile
parallelism
Overview of Parallelism Method
Auto-parallelization Overview
OpenMP* Run-time Library Routines
parallelization
Overview of Parallelism Method
Auto-parallelization Overview
Parallelism Report
Programming with Auto-parallelization
diag-enable sc-parallel, Qdiag-enable:sc-parallel
Vectorization and Loops
diagnostic
option enabling analysis in source code
parallel lint
PARALLEL OpenMP* directive
parallel processing
Parallel Processing Model
thread model
parallel programming
Overview of Parallelism Method
Overview: Optimizing Applications
parallel region
par-num-threads, Qpar-num-threads
option specifying number of threads to use in
parallel regions
PARALLEL SECTIONS
OpenMP* Directives and Clauses Summary
summary of OpenMP* directives
-par-num-threads compiler option
-par-report compiler option
-par-runtime-control compiler option
-par-schedule compiler option
-par-threshold compiler option
-pc compiler option
-pch compiler option
Using Precompiled Header Files
pch
-pch-create compiler option
Using Precompiled Header Files
pch-create, Yc
-pch-dir compiler option
Using Precompiled Header Files
pch-dir
-pch-use compiler option
pch-use
Using Precompiled Header Files
-p compiler option
-P compiler option
performance
Performance
Performance of Intel(R) Streaming SIMD Extensions Intrinsics
Performance of MMX(TM) Technology Intrinsics
MMX Intrinsics
SSE intrinsics
performance analyzer
performance issues with IPO
-pg compiler option
PGO
PGO API
Dumping and Resetting Profile Information
Resetting the Dynamic Profile Counters
API Support Overview
Interval Profile Dumping
_PGOPTI_Prof_Dump_And_Reset
_PGOPTI_Prof_Reset
_PGOPTI_Set_Interval_Prof_Dump
enable
pgopti.dpi file
Profile-Guided Optimization (PGO) Quick Reference
PGO Environment Variables
pgopti.spi file
PGO tools
profmerge and proforder Tools
PGO Tools Overview
test prioritization Tool
code coverage Tool
code coverage tool
profmerge
proforder
test prioritization tool
pgouser.h header file
-pie compiler option
pipelining
pointer aliasing
opt-multi-version-aggressive, Qopt-multi-version-aggressive
option using aggressive multi-versioning check for
porting
Porting from GNU gcc* to Microsoft Visual C++*
from GNU gcc* to Microsoft Visual C++*
porting applications
Porting from GNU gcc* to Microsoft Visual C++*
Overview: Porting Applications
position-independent code
fpic
fpie
option generating
fpic
fpie
position-independent executable
pie
option producing
position-independent external references
mdynamic-no-pic
option generating code with
pragma alloc_section
pragma distribute_point
pragma intel_omp_task
pragma intel_omp_taskq
pragma ivdep
pragma loop_count
pragma memref_control
pragma noparallel
pragma noprefetch
pragma noswp
pragma nounroll
pragma nounroll_and_jam
pragma novector
pragma optimization_level
-pragma-optimization-level compiler option
pragma optimize
pragma parallel
pragma prefetch
pragmas
help-pragma, Qhelp-pragma
option displaying
Pragmas
Intel Supported Pragmas
Overview: Intel® C++ Compiler Pragmas
Intel-supported
overview
Pragmas: Intel-specific
pragma swp
pragma unroll
pragma unroll_and_jam
pragma unused
pragma vector
vector {always|aligned|unaligned|nontemporal|temporal}
aligned
always
nontemporal
temporal
unaligned
-prec-div compiler option
precompiled header files
-prec-sqrt compiler option
predefined macros
Predefined Macros for Interoperability
ANSI Standard Predefined Macros
Additional Predefined Macros
preempting functions
PREFETCH
Prefetching Support
Prefetching with Options
options used for
using
prefetches before a loop
opt-prefetch-initial-values, Qopt-prefetch-initial-values
option enabling
prefetches for memory access in next iteration
opt-prefetch-next-iteration, Qopt-prefetch-next-iteration
option enabling
prefetches of data
Prefetching Support
Prefetching with Options
optimizations for
prefetch insertion
opt-prefetch, Qopt-prefetch
option enabling
preprocessor compiler options
-print-multi-lib compiler option
prioritizing application tests
PRIVATE
OpenMP* Directives and Clauses Summary
summary of data scope attribute clauses
processor
mtune
option optimizing for specific
processors
Targeting IA-64 Architecture Processors Automatically
Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
targeting IA-32 architecture processors using options
targeting IA-64 architecture processors using options
targeting Intel(R) 64 architecture processors using options
processor-specific code
ax, Qax
x, Qx
option generating
option generating and optimizing
PROF_DIR environment variable
PROF_DUMP_INTERVAL environment variable (deprecated)
PROF_NO_CLOBBER environment variable
-prof-data-order compiler options
-prof-dir compiler option
-prof-file compiler option
-prof-func-groups compiler option
-prof-func-order compiler options
-prof-gen:srcpos compiler option
test prioritization Tool
code coverage Tool
Profile an Application
code coverage tool
test priorization tool
-prof-gen compiler option
Profile-Guided Optimization (PGO) Quick Reference
Profile an Application
prof-gen, Qprof-gen
related options
-prof-hotness-threshold compiler option
profile data records
prof-src-root, Qprof-src-root
prof-src-dir, Qprof-src-dir
prof-src-root-cwd, Qprof-src-root-cwd
option affecting search for
option letting you use relative paths when searching for
prof-src-root, Qprof-src-root
prof-src-root-cwd, Qprof-src-root-cwd
profile-guided optimization
Dumping and Resetting Profile Information
Resetting the Dynamic Profile Counters
Profile-Guided Optimization (PGO) Quick Reference
Profile an Application
API Support Overview
Interval Profile Dumping
PGO Environment Variables
Profile-Guided Optimizations Overview
Using Function Order Lists, Function Grouping, Function Ordering, and Data Ordering Optimizations
API support
data ordering optimization
dumping profile information
environment variables
example of
function grouping optimization
function ordering optimization
function order lists optimization
interval profile dumping
options
overview
phases
resetting dynamic profile counters
resetting profile information
support
usage model
profile-optimized code
Dumping Profile Information
Resetting the Dynamic Profile Counters
Profile-Guided Optimization (PGO) Quick Reference
API Support Overview
Interval Profile Dumping
dumping
Dumping Profile Information
Interval Profile Dumping
generating information
resetting dynamic counters for
profiling
prof-file, Qprof-file
prof-dir, Qprof-dir
prof-gen, Qprof-gen
prof-use, Qprof-use
option enabling use of information from
option instrumenting a program for
option specifying directory for output files
option specifying name for summary
profiling information
prof-data-order, Qprof-data-order
prof-func-order, Qprof-func-order
option enabling function ordering
option using to order static data items
profmerge
-prof-src-dir compiler option
-prof-src-root compiler option
-prof-src-root-cwd compiler option
-prof-use compiler option
profmerge and proforder Tools
Profile-Guided Optimization (PGO) Quick Reference
code coverage Tool
prof-use, Qprof-use
code coverage tool
profmerge utility
related options
program loops
Auto-parallelization Overview
Parallel Processing Model
parallel processing model
programs
fast
falias
option maximizing speed in
option specifying aliasing should be assumed in
-pthread compiler option
-Qinstall compiler option
-Qlocation compiler option
-Qoption compiler option
-qp compiler option
quick reference
Interprocedural Optimization (IPO) Quick Reference
Enabling Automatic Optimizations
Compiler Reports Quick Reference
Profile-Guided Optimization (PGO) Quick Reference
automatic optimizations
compiler reports
IPO options
PGO options
-rcd compiler option
-rct compiler option
REDUCTION
OpenMP* Directives and Clauses Summary
summary of data scope attribute clauses
reductions in loops
register allocation
register allocator
opt-ra-region-strategy, Qopt-ra-region-strategy
option selecting method for partitioning
remarks
Werror-all
option changing to errors
removed compiler options
report generation
Requesting Compiler Reports with the xi* Tools
Dumping and Resetting Profile Information
Resetting the Dynamic Profile Counters
Intel Extension Routines to OpenMP*
OpenMP* Run-time Library Routines
Generating Reports
dynamic profile counters
Intel extension
OpenMP* run-time
profile information
timing
using compiler commands
using xi* tools
report software pipelining (SWP)
-reserve-kernel-regs compiler option
response files
-restrict compiler option
restricting optimization
routine entry
falign-stack
option specifying the stack alignment to use on
run-time checking
run-time performance
Overview: Tuning Performance
improving
sample of timing
-save-temps compiler option
-scalar-rep compiler option
scalar replacement
scalar-rep, Qscalar-rep
opt-multi-version-aggressive, Qopt-multi-version-aggressive
option enabling during loop transformation
option using aggressive multi-versioning check for
-S compiler option
shareable objects
-shared compiler option
Using Intel Shared Libraries
shared
Creating Libraries
-shared-intel compiler option
shared-intel
Using Intel Shared Libraries
-shared-libgcc compiler option
shared libraries
shared object
shared
option producing a dynamic
shared scalars
Short Vector Math Library (SVML) Intrinsics
signed infinity
signed zero
SMP systems
software pipelining
Overview of Parallelism Method
Software Pipelining (SWP) Report (Linux* and Windows*)
reports
source code analysis
Local Program Analysis
Interprocedural Analysis
Source Checker Overview
OpenMP* Analysis
Fortran-Specific Analysis
C/C++ Specific Analysis
-sox compiler option
specialized code
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Overview of Parallelism Method
specifying file names
Specifying Executable Files
Specifying Object Files
Specifying Assembly Files
for assembly files
for executable files
for object files
specifying symbol visibility
SSE
SSE2
SSE2 intrinsics
Store Intrinsics
Conversion Intrinsics
Move Intrinsics
Pause Intrinsic
Miscellaneous Intrinsics
Set Intrinsics
Load Intrinsics
Logical Intrinsics
Load Intrinsics
Shift Intrinsics
Store Intrinsics
Macro Function for Shuffle
Compare Intrinsics
Set Intrinsics
Conversion Intrinsics
Compare Intrinsics
Cacheability Support Intrinsics
Arithmetic Intrinsics
Logical Intrinsics
Arithmetic Intrinsics
Casting Support Intrinsics
add_epi16
add_epi32
add_epi64
add_epi8
add_pd
add_sd
add_si64
adds_epi16
adds_epi8
adds_epu16
adds_epu8
and_pd
and_si128
andnot_pd
andnot_si128
arithmetic operations intrinsics
avg_epu16
avg_epu8
cacheability support intrinsics
casting support intrinsics
clflush
cmpeq_epi16
cmpeq_epi32
cmpeq_epi8
cmpeq_pd
cmpeq_sd
cmpge_pd
cmpge_sd
cmpgt_epi16
cmpgt_epi32
cmpgt_epi8
cmpgt_pd
cmpgt_sd
cmple_pd
cmple_sd
cmplt_epi16
cmplt_epi32
cmplt_epi8
cmplt_pd
cmplt_sd
cmpneq_pd
cmpneq_sd
cmpnge_pd
cmpnge_sd
cmpngt_pd
cmpngt_sd
cmpnle_pd
cmpnle_sd
cmpnlt_pd
cmpnlt_sd
cmpord_pd
cmpord_sd
cmpunord_pd
cmpunord_sd
comieq_sd
comige_sd
comigt_sd
comile_sd
comilt_sd
comineq_sd
compare operation intrinsics
conversion operation intrinsics
cvtepi32_pd
cvtepi32_ps
cvtpd_epi32
cvtpd_pi32
cvtpd_ps
cvtpi32_pd
cvtps_epi32
cvtps_pd
cvtsd_f64
cvtsd_si32
cvtsd_si64
cvtsd_ss
cvtsi128_si32
cvtsi128_si64
cvtsi32_sd
cvtsi32_si128
cvtsi64_sd
cvtsi64_si128
cvtss_sd
cvttpd_epi32
cvttpd_pi32
cvttps_epi32
cvttsd_si32
cvttsd_si64
div_pd
div_sd
extract_epi16
FP arithmetic intrinsics
FP compare intrinsics
FP conversion intrinsics
FP load intrinsics
FP logical operations intrinsics
FP set intrinsics
FP store intrinsics
insert_epi16
lfence
load_pd
load_sd
load_si128
load1_pd
loadh_pd
loadl_epi64
loadl_pd
load operation intrinsics
loadr_pd
loadu_pd
loadu_si128
logical operations intrinsics
madd_epi16
maskmoveu_si128
max_epi16
max_epu8
max_pd
max_sd
mfence
min_epi16
min_epu8
min_pd
min_sd
miscellaneous intrinsics
move_epi64
move_sd
movemask_epi8
movemask_pd
move operation intrinsics
movepi64_pi64
movpi64_pi64
mul_epu32
mul_pd
mul_sd
mul_su32
mulhi_epi16
mulhi_epu16
mullo_epi16
or_pd
or_si128
packs_epi16
packs_epi32
packus_epi16
pause intrinsic
sad_epu8
set_epi16
set_epi32
set_epi64
set_epi8
set_pd
set_sd
set1_epi16
set1_epi32
set1_epi64
set1_epi8
set1_pd
set operation intrinsic
setr_epi16
setr_epi32
setr_epi64
setr_epi8
setr_pd
setzero_pd
setzero_si128
shift operation intrinsics
shuffle_epi32
shuffle_pd
shufflehi_epi16
shufflelo_epi16
shuffle macro
sll_epi16
sll_epi32
sll_epi64
slli_epi16
slli_epi32
slli_epi64
slli_si128
sqrt_pd
sqrt_sd
sra_epi16
sra_epi32
srai_epi16
srai_epi32
srl_epi16
srl_epi32
srl_epi64
srli_epi16
srli_epi32
srli_epi64
srli_si128
store_pd
store_sd
store_si128
store1_pd
storeh_pd
storel_epi64
storel_pd
store operation intrinsics
storer_pd
storeu_pd
storeu_si128
stream_pd
stream_si128
stream_si32
sub_epi16
sub_epi32
sub_epi64
sub_epi8
sub_pd
sub_sd
sub_si64
subs_epi16
subs_epi8
subs_epu16
subs_epu8
ucomieq_sd
ucomige_sd
ucomigt_sd
ucomile_sd
ucomilt_sd
ucomineq_sd
unpackhi_epi16
unpackhi_epi32
unpackhi_epi64
unpackhi_epi8
unpackhi_pd
unpacklo_epi16
unpacklo_epi32
unpacklo_epi64
unpacklo_epi8
unpacklo_pd
xor_pd
xor_si128
SSE3 intrinsics
Single-precision Floating-point Vector Intrinsics
Integer Vector Intrinsics
Miscellaneous Intrinsics
Double-precision Floating-point Vector Intrinsics
Macro Functions
addsub_pd
addsub_ps
float32 vector intrinsics
float64 vector intrinsics
hadd_pd
hadd_ps
hsub_pd
hsub_ps
integer vector intrinsic
loaddup_pd
macro functions
miscellaneous intrinsics
movedup_pd
movehdup_ps
moveldup_ps
SSE4 intrinsic
DWORD Multiply Intrinsics
Packed DWORD to Unsigned WORD Intrinsic
Packed Compare for Equal Intrinsic
Cacheability Support Intrinsic
cacheability support intrinsic
DWORD multiply intrinsics
packed compare for equal intrinsic
packed DWORD to unsigned WORD intrinsic
SSE4 intrinsics
Floating Point Rounding Intrinsics
Application Targeted Accelerators Intrinsics
Packed Blending Intrinsincs
Test Intrinsics
Register Insertion/Extraction Intrinsics
Floating Point Dot Product Intrinsincs
Packed Format Conversion Intrinsics
Packed Integer Min/Max Intrinsics
Packed Compare Intrinsics
application targeted accelerator intrinsics
floating-point rounding intrinsics
FP dot product intrinsics
packed blending intrinsics
packed compare intrinsics
packed format conversion intrinsics
packed integer min/max intrinsics
register insertion/extraction intrinsics
test intrinsics
SSE intrinsics
Miscellaneous Intrinsics
Details about Intel(R) Streaming SIMD Extension Intrinsics
Macro Function for Shuffle Operations
Intrinsics to Read and Write Registers
Compare Intrinsics
Macro Function for Matrix Transposition
Integer Intrinsics
Logical Intrinsics
Load Intrinsics
Cacheability Support Intrinsics
Using Intel(R) Streaming SIMD Extensions on IA-64 Architecture
Store Intrinsics
Set Intrinsics
Macro Functions to Read and Write Control Registers
Conversion Intrinsics
Writing Programs with Intel(R) Streaming SIMD Extensions Intrinsics
Arithmetic Intrinsics
add_ps
add_ss
and_ps
andnot_ps
arithmetic operations
avg_pu16
avg_pu8
cacheability support operations
cmpeq_ps
cmpeq_ss
cmpge_ps
cmpge_ss
cmpgt_ps
cmpgt_ss
cmple_ps
cmple_ss
cmplt_ps
cmplt_ss
cmpneq_ps
cmpneq_ss
cmpnge_ps
cmpnge_ss
cmpngt_ps
cmpngt_ss
cmpnle_ps
cmpnle_ss
cmpnlt_ps
cmpnlt_ss
cmpord_ps
cmpord_ss
cmpunord_ps
cmpunord_ss
comieq_ss
comige_ss
comigt_ss
comile_ss
comilt_ss
comineq_ss
compare operations
conversion operations
cvtpi16_ps
cvtpi32_ps
cvtpi32x2_ps
cvtpi8_ps
cvtps_pi16
cvtps_pi32
cvtps_pi8
cvtpu16_ps
cvtpu8_ps
cvtsi32_ss
cvtsi64_ss
cvtss_f32
cvtss_si32
cvtss_si64
cvttps_pi32
cvttss_si32
cvttss_si64
data types
div_ps
div_ss
extract_pi16
getcsr
insert_pi16
integer operations
load_ps
load_ps1
load_ss
loadh_pi
loadl_pi
load operations
loadr_ps(
loadu_ps
logical operations
maskmove_si641
matrix transposition macro
max_pi16
max_ps
max_pu8
max_ss
min_pi16
min_ps
min_pu8
min_ss
miscellaneous operations
move_ss
movehl_ps
movelh_ps
movemask_pi8
movemask_ps
mul_ps
mul_ss
mulhi_pu16
or_ps
prefetch
programming with SSE intrinsics
rcp_ps
rcp_ss
read/write control register macros
read/write register intrinsics
registers
rsqrt_ps
rsqrt_ss
sad_pu8
set_ps
set_ps1
set_ss
setcsr
set operations
setr_ps
setzero_ps
sfence
shuffle_pi16
shuffle_ps
shuffle function macro
sqrt_ps
sqrt_ss
store_ps
store_ps1
store_ss
storeh_pi
storel_pi
store operations
storer_ps
storeu_ps
stream_pi
stream_ps
sub_ps
sub_ss
ucomieq_ss
ucomige_ss
ucomigt_ss
ucomile_ss
ucomilt_ss
ucomineq_ss
unpackhi_ps
unpacklo_ps
using SSE intrinsics on IA-64 architecture
xor_ps
SSSE3 intrinsics
Concatenate Intrinsics
Multiplication Intrinsics
Shuffle Intrinsics
Absolute Value Intrinsics
Negation Intrinsics
Subtraction Intrinsics
Addition Intrinsics
absolute value intrinsics
addition intrinsics
concatenate intrinsics
multiplication intrinsics
negation intrinsics
shuffle intrinsics
subtraction intrinsics
stack
F (Windows*)
Qchkstk
Gs
option disabling checking for routines in
option enabling probing
option specifying reserve amount
stack alignment
Qsfalign
option specifying for functions
stack probing
Qchkstk
option enabling
stack variables
ftrapuv, Qtrapuv
option initializing to NaN
standard directories
X
option removing from include search path
standards conformance
Conformance to the C++ Standard
Conformance to the C Standard
-static compiler option
-static-intel compiler option
-staticlib compiler option
-static-libgcc compiler option
static libraries
Creating Libraries
staticlib
option invoking tool to generate
-std compiler option
strategies for optimization
Streaming SIMD Extensions
Programming Guidelines for Vectorization
Overview: Intel(R) Streaming SIMD Extensions
Streaming SIMD Extensions 2
Streaming SIMD Extensions 3
Streaming SIMD Extensions 4
streaming stores
opt-streaming-stores, Qopt-streaming-stores
option generating for optimization
-strict-ansi compiler option
subnormal numbers
subroutines in the OpenMP* run-time library
Auto-parallelization Overview
Prefetching Support
OpenMP* Support Libraries
OpenMP* Run-time Library Routines
for OpenMP*
for prefetching
parallel run-time
Supplemental Streaming SIMD Extensions 3
supported tools
SVML Intrinsic
_mm_atan2_ps
_mm_atan_pd
_mm_ccos_ps
_mm_tanh_pd
_mm_sinh_ps
_mm_log_pd
_mm_log_ps
_mm_csqrt_ps
_mm_sqrt_pd
_mm_acosh_ps
_mm_cos_ps
_mm_ctanh_ps
_mm_exp2_pd
_mm_cbrt_pd
_mm_cbrt_ps
_mm_sinh_pd
_mm_tan_ps
_mm_log2_ps
_mm_cosh_ps
_mm_clog_ps
_mm_erfc_pd
_mm_sincos_ps
_mm_asin_ps
_mm_cpow_ps
_mm_atan_ps
_mm_clog2_ps
_mm_erfc_ps
_mm_erf_ps
_mm_casin_ps
_mm_cosh_pd
_mm_acos_ps
_mm_pow_ps
_mm_cacosh_ps
_mm_sin_pd
_mm_atanh_pd
_mm_catan_ps
_mm_cexp_ps
_mm_asin_pd
_mm_log10_ps
_mm_log2_pd
_mm_ccosh_ps
_mm_ctan_ps
_mm_invcbrt_pd
_mm_exp2_ps
_mm_atan2_pd
_mm_invsqrt_pd
_mm_csinh_ps
_mm_exp_pd
_mm_pow_pd
_mm_clog10_ps
_mm_sqrt_ps
_mm_sin_ps
_mm_tanh_ps
_mm_casinh_ps
_mm_cacos_ps
_mm_csin_ps
_mm_erf_pd
_mm_acosh_pd
_mm_catanh_ps
_mm_sincos_pd
_mm_atanh_ps
_mm_exp_ps
_mm_invsqrt_ps
_mm_tan_pd
_mm_log10_pd
_mm_invcbrt_ps
_mm_acos_pd
_mm_acos_pd
_mm_acos_ps
_mm_acosh_pd
_mm_acosh_ps
_mm_asin_pd
_mm_asin_ps
_mm_atan_pd
_mm_atan_ps
_mm_atan2_pd
_mm_atan2_ps
_mm_atanh_pd
_mm_atanh_ps
_mm_cacos_ps
_mm_cacosh_ps
_mm_casin_ps
_mm_casinh_ps
_mm_catan_ps
_mm_catanh_ps
_mm_cbrt_pd
_mm_cbrt_ps
_mm_ccos_ps
_mm_ccosh_ps
_mm_cexp_ps
_mm_clog_ps
_mm_clog10_ps
_mm_clog2_ps
_mm_cos_ps
_mm_cosh_pd
_mm_cosh_ps
_mm_cpow_ps
_mm_csin_ps
_mm_csinh_ps
_mm_csqrt_ps
_mm_ctan_ps
_mm_ctanh_ps
_mm_erf_pd
_mm_erf_ps
_mm_erfc_pd
_mm_erfc_ps
_mm_exp_pd
_mm_exp_ps
_mm_exp2_pd
_mm_exp2_ps
_mm_invcbrt_pd
_mm_invcbrt_ps
_mm_invsqrt_pd
_mm_invsqrt_ps
_mm_log_pd
_mm_log_ps
_mm_log10_pd
_mm_log10_ps
_mm_log2_pd
_mm_log2_ps
_mm_pow_pd
_mm_pow_ps
_mm_sin_pd
_mm_sin_ps
_mm_sincos_pd
_mm_sincos_ps
_mm_sinh_pd
_mm_sinh_ps
_mm_sqrt_pd
_mm_sqrt_ps
_mm_tan_pd
_mm_tan_ps
_mm_tanh_pd
_mm_tanh_ps
SWP
Software Pipelining (SWP) Report (Linux* and Windows*)
SWP reports
symbol names
Quse-msasm-symbols
option using dollar sign when producing
symbol preemption
symbol visibility
fvisibility
Symbol Visibility Attribute Options (Linux* and Mac OS* X)
option specifying
specifying
symbol visibility on Linux*
symbol visibility on Mac OS* X
synchronization
Overview of Parallelism Method
Auto-parallelization Overview
Intel Extension Routines to OpenMP*
Parallel Processing Model
parallel processing model for
thread-level parallelism
thread sleep time
targeting
Targeting Multiple IA-32 and Intel(R) 64 Architecture Processors for Run-time Performance
Targeting IA-64 Architecture Processors Automatically
Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
IA-32 architecture processors
Intel(R) 64 architecture processors
Itanium(R) 2 processors
run-time checking
-tbb compiler option
-tcheck compiler option (Linux* only)
-tcollect compiler option
-tcollect-filter compiler option
-T compiler option
technical applications
template instantiation
templates
Exported Templates
exported
test prioritization tool
examples
options
requirements
thread affinity
par-affinity, Qpar-affinity
Thread Affinity Interface (Linux* and Windows*)
option specifying
threaded applications
tcheck, Qtcheck
option enabling analysis of
thread-local storage
thread pooling
threshold control for auto-parallelization
Parallelism Report
Programming Guidelines for Vectorization
OpenMP* Run-time Library Routines
OpenMP* routines for
reordering
tool options
profmerge and proforder Tools
PGO Tools Overview
test prioritization Tool
code coverage Tool
code coverage tool
profmerge
proforder
test prioritization
tools
Qoption
PGO Tools Overview
Qlocation
option passing options to
option specifying directory for supporting
topology maps
-tprofile compiler option (Linux* only)
-traceback compiler option
traceback information
traceback
option providing
transcendental functions
fast-transcendentals, Qfast-transcendentals
option replacing calls to
tselect tool
Qcov-gen
Qcov-file
Qcov-dir
option producing an instrumented file for
option specifying a directory for profiling output for
option specifying a file name for summary files for
-u (L*) compiler option
-U compiler option
Unicode*
-unroll-aggressive compiler option
-unroll compiler option
unvectorizable copy
-use-asm compiler option
-use-intel-optimized-headers compiler option
-use-msasm compiler option
user functions
Compiler Directed Inline Expansion of User Functions
Overview of Parallelism Method
Auto-parallelization Overview
Timing Your Application
Developer Directed Inline Expansion of User Functions
Profile an Application
OpenMP* Examples
PGO Environment Variables
OpenMP* Run-time Library Routines
auto-parallelization
Overview of Parallelism Method
Auto-parallelization Overview
dynamic libraries
OpenMP*
PGO environment
profile-guided optimization
timing for an application
using Intel(R) Performance Libraries
utilities
profmerge and proforder Tools
PGO Tools Overview
profmerge
proforder
-V (L*) compiler option
valarray implementation
Using Intel's valarray Implementation
compiling code
using in code
variables
fkeep-static-consts, Qkeep-static-consts
no-bss-init, Qnobss-init
option placing in DATA section
option saving always
-v compiler option
-vec compiler option
-vec-guard-write compiler option
-vec-report compiler option
-vec-threshold compiler option
vector copy
Overview of Parallelism Method
Programming Guidelines for Vectorization
Automatic Vectorization Options Quick Reference
Vectorization Report
Automatic Vectorization Overview
options
options for
overview
programming guidelines
Programming Guidelines for Vectorization
Automatic Vectorization Overview
reports
vectorization
vec-threshold, Qvec-threshold
vec, Qvec
option disabling
option setting threshold for loops
vectorizer
vec-report, Qvec-report
option controlling diagnostics reported by
vectorizing
Loop Constructs
Programming Guidelines for Vectorization
Profile-Guided Optimizations Overview
loops
Loop Constructs
Profile-Guided Optimizations Overview
version
sox, Qsox
option saving in executable or object file
--version compiler option
visibility declaration attribute
-Wabi compiler option
-Wa compiler option
-Wall compiler option
warnings
Werror, WX
Werror-all
option changing to errors
Werror, WX
Werror-all
warnings and errors
-Wbrief compiler option
-Wcheck compiler option
-Wcomment compiler option
-w compiler option
w
w, W
-Wcontext-limit compiler option
-wd compiler option
-Wdeprecated compiler option
-we compiler option
-Weffc++ compiler option
-Werror-all compiler option
-Werror compiler option
-Wextra-tokens compiler option
-Wformat compiler option
-Wformat-security compiler option
whole program analysis
Windows* compiler options
vmg
GA
ftemplate-depth, Qtemplate-depth
Gh
Qinline-dllimport
opt-report-help, Qopt-report-help
w
wn, Qwn
inline-level, Ob
traceback
tcollect, Qtcollect
use-intel-optimized-headers, Quse-intel-optimized-headers
ftrapuv, Qtrapuv
MD
hotpatch
par-runtime-control, Qpar-runtime-control
J
opt-prefetch, Qopt-prefetch
Tc
mserialize-volatile, Qserialize-volatile
prof-data-order, Qprof-data-order
Gz
Fr
openmp-link, Qopenmp-link
openmp-stubs, Qopenmp-stubs
Ot
MF, QMF
Fm
Gr
Zx
arch
opt-report, Qopt-report
S
ax, Qax
openmp-profile, Qopenmp-profile
IPF-flt-eval-method0, QIPF-flt-eval-method0
fp-port, Qfp-port
fixed
opt-report-file, Qopt-report-file
FD
tbb, Qtbb
tcheck, Qtcheck
P
unroll, Qunroll
openmp-threadprivate, Qopenmp-threadprivate
fkeep-static-consts, Qkeep-static-consts
fp-relaxed, Qfp-relaxed
Qsfalign
openmp-lib, Qopenmp-lib
par-num-threads, Qpar-num-threads
inline-min-size, Qinline-min-size
C
LD
Od
opt-report-phase, Qopt-report-phase
inline-factor, Qinline-factor
rcd, Qrcd
Gd
multibyte-chars, Qmultibyte-chars
Os
prof-src-root, Qprof-src-root
Oa
Werror, WX
ip-no-inlining, Qip-no-inlining
ipo-S, Qipo-S
F (Windows*)
Ox
fast-transcendentals, Qfast-transcendentals
Qcxx-features
prof-file, Qprof-file
inline-max-per-compile, Qinline-max-per-compile
noBool
A-, QA-
global-hoist, Qglobal-hoist
par-report, Qpar-report
diag, Qdiag
par-affinity, Qpar-affinity
QIA64-fr32
Qmspp
use-asm, Quse-asm
vmv
MD, QMD
vec-guard-write, Qvec-guard-write
Weffc++, Qeffc++
fast
diag-id-numbers, Qdiag-id-numbers
M, QM
Yd
MG, QMG
opt-streaming-stores, Qopt-streaming-stores
help-pragma, Qhelp-pragma
vec-threshold, Qvec-threshold
G5, G6, G7
Og
opt-loadpair, Qopt-loadpair
prof-func-order, Qprof-func-order
X
E
opt-prefetch-next-iteration, Qopt-prefetch-next-iteration
G2, G2-p9000
par-threshold, Qpar-threshold
restrict, Qrestrict
Zl
Gf
Qoption
ip-no-pinlining, Qip-no-pinlining
Op
save-temps, Qsave-temps
diag-error-limit, Qdiag-error-limit
ipp, Qipp
FC
homeparams
vmb
Qpar-adjust-stack
diag-file-append, Qdiag-file-append
ipo, Qipo
complex-limited-range, Qcomplex-limited-range
Fp
alias-const, Qalias-const
Wp64
help
inline-max-per-routine, Qinline-max-per-routine
IPF-fltacc, QIPF-fltacc
we, Qwe
prof-src-dir, Qprof-src-dir
vmm
fstack-security-check, GS
Qpchi
Qchkstk
fbuiltin, Oi
fomit-frame-pointer, Oy
inline-forceinline, Qinline-forceinline
tprofile, Qtprofile
FI
Qcov-gen
mcmodel
inline-debug-info, Qinline-debug-info
prof-hotness-threshold, Qprof-hotness-threshold
inline-max-total-size, Qinline-max-total-size
Ge
EP
ww, Qww
c99, Qc99
ftz, Qftz
parallel, Qparallel
ivdep-parallel, Qivdep-parallel
Gs
pch-create, Yc
RTC
fp-model, fp
Qlong-double
MM, QMM
openmp-report, Qopenmp-report
pc, Qpc
Qlocation
fp-speculation, Qfp-speculation
fma, Qfma
link
prec-div, Qprec-div
vec-report, Qvec-report
MMD, QMMD
Quse-msasm-symbols
GT
w, W
g, Zi, Z7
dD, QdD
rct, Qrct
no-bss-init, Qnobss-init
prof-dir, Qprof-dir
unroll-aggressive, Qunroll-aggressive
sox, Qsox
GF
MT
std, Qstd
Ze
map-opts, Qmap-opts
prof-gen, Qprof-gen
ip, Qip
Qnopic
c
V (Linux* and Mac OS* X)
opt-jump-tables, Qopt-jump-tables
diag-enable sc-parallel, Qdiag-enable:sc-parallel
TC
mkl, Qmkl
fnsplit, Qfnsplit
A, QA
GR
V (Windows*)
tcollect-filter, Qtcollect-filter
minstruction, Qinstruction
Zg
MT, QMT
Za
showIncludes
Wport
opt-mod-versioning, Qopt-mod-versioning
Tp
As
fargument-alias, Qalias-args
U
prof-use, Qprof-use
ffreestanding, Qfreestanding
inline-calloc, Qinline-calloc
par-schedule, Qpar-schedule
bigobj
GX
ansi-alias, Qansi-alias
vec, Qvec
opt-block-factor, Qopt-block-factor
falign-functions, Qfnalign
prof-src-root-cwd, Qprof-src-root-cwd
Werror-all
x, Qx
Qms
opt-ra-region-strategy, Qopt-ra-region-strategy
I
opt-class-analysis, Qopt-class-analysis
diag-enable sc-include, Qdiag-enable:sc-include
Fe
opt-subscript-in-range, Qopt-subscript-in-range
inline-max-size, Qinline-max-size
ipo-jobs, Qipo-jobs
opt-prefetch-issue-excl-hint, Qopt-prefetch-issue-excl-hint
dM, QdM
Qvc
wd, Qwd
Wcontext-limit, Qcontext-limit
diag-dump, Qdiag-dump
ipo-separate, Qipo-separate
dN, QdN
H (Windows*)
scalar-rep, Qscalar-rep
Kc++, TP
Fo
vms
wo, Qwo
Zc
H, QH
EH
YX
Zs
Fa
vd
ZI
debug (Windows* OS)
Qsafeseh
FR
openmp-task, Qopenmp-task
wr, Qwr
Wall
opt-report-routine, Qopt-report-routine
Ow
finstrument-functions, Qinstrument-functions
mp1, Qprec
prec-sqrt, Qprec-sqrt
opt-multi-version-aggressive, Qopt-multi-version-aggressive
ML
openmp, Qopenmp
Gm
Zd
opt-prefetch-initial-values, Qopt-prefetch-initial-values
multiple-processes, MP
Wcheck
Yu
O
ipo-c, Qipo-c
u (Windows*)
Ap64
diag-file, Qdiag-file
FA
WL
auto-ilp32, Qauto-ilp32
GZ
diag-once, Qdiag-once
fp-stack-check, Qfp-stack-check
Qcov-file
opt-mem-bandwidth, Qopt-mem-bandwidth
Zp
Y-
Qcov-dir
D
Gy
logo
GH
/Ap64
/arch
/As
/bigobj
/c
/C
/D
/debug
/E
/EHa
/EHc
/EHs
/EP
/F
/Fa
/FA
/fast
/FC
/FD
/Fe
/FI
/fixed
/Fm
/Fo
/fp
/Fp
/Fr
/FR
/G2
/G5
/G6
/G7
/GA
/Gd
/Ge
/Gf
/GF
/Gh
/GH
/Gm
/Gr
/GR
/Gs
/GS
/GT
/GX
/Gy
/Gz
/GZ
/H
/help
/homeparams
/hotpatch
/I
/J
/LD
/link
/MD
/ML
/MP
/MT
/noBool
/nologo
/O
/Oa
/Ob
/Od
/Og
/Oi
/Op
/Os
/Ot
/Ow
/Ox
/Oy
/P
/prof-func-order
/QA
/QA-
/Qalias-args
/Qalias-const
/Qansi-alias
/Qauto-ilp32
/Qax
/Qc99
/Qchkstk
/Qcomplex-limited-range
/Qcontext-limit
/Qcov-dir
/Qcov-file
/Qcov-gen
/Qcxx-features
/QdD
/Qdiag
/Qdiag-dump
/Qdiag-enable:sc-include
/Qdiag-enable:sc-parallel
/Qdiag-error-limit
/Qdiag-file
/Qdiag-file-append
/Qdiag-id-numbers
/Qdiag-once
/QdM
/QdN
/Qeffc++
/Qfast-transcendentals
/Qfma
/Qfnalign
/Qfnsplit
/Qfp-port
/Qfp-relaxed
/Qfp-speculation
/Qfp-stack-check
/Qfreestanding
/Qftz
/Qglobal-hoist
/QH
/Qhelp-pragma
/QIA64-fr32
/Qinline-calloc
/Qinline-debug-info
/Qinline-dllimport
/Qinline-factor
/Qinline-forceinline
/Qinline-max-per-compile
/Qinline-max-per-routine
/Qinline-max-size
/Qinline-max-total-size
/Qinline-min-size
/Qinstruction
/Qinstrument-functions
/Qip
/QIPF-fltacc
/QIPF-flt-eval-method0
/QIPF-fma
/QIPF-fp-relaxed
/Qip-no-inlining
/Qip-no-pinlining
/Qipo
/Qipo-c
/Qipo-jobs
/Qipo-S
/Qipo-separate
/Qipp
/Qivdep-parallel
/Qkeep-static-consts
/Qlocation
/Qlong-double
/QM
/Qmap-opts
/Qmcmodel
/QMD
/QMF
/QMG
/Qmkl
/QMM
/QMMD
/Qms
/Qmspp
/QMT
/Qmultibyte-chars
/Qnobss-init
/Qnopic
/Qopenmp
/Qopenmp-lib
/Qopenmp-link
/Qopenmp-profile
/Qopenmp-report
/Qopenmp-stubs
/Qopenmp-task
/Qopenmp-threadprivate
/Qopt-block-factor
/Qopt-class-analysis
/Qoption
/Qopt-jump-tables
/Qopt-loadpair
/Qopt-mem-bandwidth
/Qopt-mod-versioning
/Qopt-multi-version-aggressive
/Qopt-prefetch
/Qopt-prefetch-initial-values
/Qopt-prefetch-issue-excl-hint
/Qopt-prefetch-next-iteration
/Qopt-ra-region-strategy
/Qopt-report
/Qopt-report-file
/Qopt-report-help
/Qopt-report-phase
/Qopt-report-routine
/Qopt-streaming-stores
/Qopt-subscript-in-range
/Qpar-adjust-stack
/Qpar-affinity
/Qparallel
/Qpar-num-threads
/Qpar-report
/Qpar-runtime-control
/Qpar-schedule
/Qpar-threshold
/Qpc
/Qpchi
/Qprec
/Qprec_div
/Qprec-sqrt
/Qprof-data-order
/Qprof-dir
/Qprof-file
/Qprof-gen
/Qprof-hotness-threshold
/Qprof-src-dir
/Qprof-src-root
/Qprof-src-root-cwd
/Qprof-use
/Qrcd
/Qrct
/Qrestrict
/Qsafeseh
/Qsave-temps
/Qscalar-rep
/Qserialize-volatile
/Qsfalign
/Qsox
/Qstd
/Qtbb
/Qtcheck
/Qtcollect
/Qtcollect-filter
/Qtemplate-depth
/Qtprofile
/Qtrapuv
/Qunroll
/Qunroll-aggressive
/Quse-asm
/Quse-intel-optimized-headers
/Quse-msasm-symbols
/QV
/Qvc
/Qvec
/Qvec-guard-write
/Qvec-report
/Qvec-threshold
/Qwd
/Qwe
/Qwn
/Qwo
/Qwr
/Qww
/Qx
/RTC
/S
/showIncludes
/Tc
/TC
/Tp
/TP
/traceback
/U
/u (W*)
/V (W*)
/vd
/vmb
/vmg
/vmm
/vms
/vmv
/w
/W
/Wall
/Wcheck
/WL
/Wp64
/Wport
/X
/Y-
/Yc
/Yd
/Yu
/YX
/Z7
/Za
/Zc
/Zd
/Ze
/Zg
/Zi
/ZI
/Zl
/Zp
/Zs
/Zx
-Werror-all
-WX
-Winline compiler option
-Wl compiler option
-Wmain compiler option
-Wmissing-declarations compiler option
-Wmissing-prototypes compiler option
-wn compiler option
-Wnon-virtual-dtor compiler option
-wo compiler option
worker thread
worksharing
Overview of Parallelism Method
Auto-parallelization Overview
OpenMP* Directives and Clauses Summary
-Wp64 compiler option
-Wp compiler option
-Wpointer-arith compiler option
-Wpragma-once compiler option
-wr compiler option
-Wreorder compiler option
-Wreturn-type compiler option
-Wshadow compiler option
-Wstrict-prototypes compiler option
-Wtrigraphs compiler option
-Wuninitialized compiler option
-Wunknown-pragmas compiler option
-Wunused-function compiler option
-Wunused-variable compiler option
-ww compiler option
-Wwrite-strings compiler option
-x (type) compiler option
-x compiler option
Targeting IA-32 and Intel(R) 64 Architecture Processors Automatically
x, Qx
-X compiler option
xiar
Creating a Library from IPO Objects
IPO-Related Performance Issues
xild
Creating a Library from IPO Objects
Interprocedural Optimization (IPO) Overview
IPO-Related Performance Issues
xilib
xilibtool
xilink
Creating a Library from IPO Objects
Interprocedural Optimization (IPO) Overview
IPO-Related Performance Issues
-Xlinker compiler option
-Zp compiler option