ic91_fp.xml SPEC CPU2006 Flags Description for the Intel(R) Compiler v9.1
HITACHI Flags Description.

]]>
icc Invoke the Intel C compiler for EM64T

]]> icpc Invoke the Intel C++ compiler for EM64T

]]> ifort Invoke the Intel Fortran compiler for EM64T

]]> -fast enable -xP -O3 -ipo -no-prec-div -static

]]> -prof_gen Instrument program for profiling for the first phase of two-phase profile guided otimization. This instrumentation gathers information about a program's execution paths and data values but does not gather information from hardware performance counters. The profile instrumentation also gathers data for optimizations which are unique to profile-feedback optimization.

]]> -prof_use Instructs the compiler to produce a profile-optimized executable and merges available dynamic information (.dyn) files into a pgopti.dpi file. If you perform multiple executions of the instrumented program, -prof_use merges the dynamic information files again and overwrites the previous pgopti.dpi file. Without any other options, the current directory is searched for .dyn files

]]> -parallel enable the auto-parallelizer to generate multi-threaded code for loops that can be safely executed in parallel

]]> -O3 Enable -O2 plus more aggressive optimizations that may not improve performance for all programs. On Linux platforms, -O3 sets the -fp flag.

]]> -O2 Enable optimizations of defaults level. -O2 includes -O1 optimizations and in addition enables inlining of intrinsics and more speed optimizations.

]]> -O1 Optimize for maximum speed, but disable some optimizations which increase code size for a small speed benefit. Includes inline expansion except for intrinsic functions, global optimizations, string pooling optimizations. On Linux platforms, -O1 sets the following:

-unroll0 -fno-builtin -mno-ieee-fp -fomit-frame-pointer -ffunction-sections

]]> -unroll_n Set maximum number of times to unroll loops. Use n=0 to disable loop unroller.

]]> -fno-builtin disable inline expansion of intrinsic functions

]]> -mno-ieee-fp Enables improved floating-point consistency. Floating-point operations are not reordered and the result of each floating-point operation is stored in the target variable rather than being kept in the floating- point processor for use in a subsequent calculation. This is the same as specifying -fltconsistency or -mp.

The default, -mno-ieee-fp, provides better accuracy and run-time per- formance at the expense of less consistent floating-point results.

]]> -fomit-frame-pointer enable using EBP as general purpose register

]]> -ffunction-sections separate functions for the linker (COMDAT)

]]> -fp disable using EBP as general purpose register

]]> -xP generate specialized code to run exclusively on processors indicated by Intel Core(TM) Duo processors, Intel Core(TM) Solo processors, Intel Pentium 4 and compatible Intel processors with Streaming SIMD Extensions 3 (SSE3) instruction support

]]> -ipo enable multi-file Interprocedural Optimizations (between files)

]]> -no-prec-div improve speed of floating-point divides and disable improved precision of floating-point divides

]]> -static prevents linking with shared libraries

]]> -nofor_main do not link against Fortran main object Used when linking Fortran objects with C main program

]]>