CPU2006 Flag Description
Bull SAS Bull Escala PL1650R+ (2200 MHz, 16 CPU)

Base Optimization Flags

C benchmarks

• • -qlanglvl=extc99
  • 
  • CC, LD

  • Allows most any c dialect.

• • -O5
  • 
  • COPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • COPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -D_ILS_MACROS
  • 
  • COPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -qipa=noobject
  • 
  • EXTRA_CFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

C++ benchmarks

• • -O5
  • 
  • CXXOPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • CXXOPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -D_ILS_MACROS
  • 
  • CXXOPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -qrtti=all
  • 
  • CXXOPTIMIZE

  • Cause the C++ compiler to generate Run Time Type Identification code

• • -qipa=noobject
  • 
  • EXTRA_CXXFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

Fortran benchmarks

• • -O5
  • 
  • FOPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • FOPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -qsmallstack=dynlenonheap
  • 
  • FOPTIMIZE

  • Causes the Fortran compiler to allocate dynamic arrays on the heap instead of the stack

• • -qipa=noobject
  • 
  • EXTRA_FFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

Benchmarks using both Fortran and C

• • -qlanglvl=extc99
  • 
  • CC

  • Allows most any c dialect.

• • -O5
  • 
  • COPTIMIZE, FOPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • COPTIMIZE, FOPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -D_ILS_MACROS
  • 
  • COPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -qsmallstack=dynlenonheap
  • 
  • FOPTIMIZE

  • Causes the Fortran compiler to allocate dynamic arrays on the heap instead of the stack

• • -qipa=noobject
  • 
  • EXTRA_CFLAGS, EXTRA_FFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

Peak Optimization Flags

C benchmarks

433.milc

• • -qlanglvl=extc99
  • 
  • CC, LD

  • Allows most any c dialect.

• • -qpdf1
  • 
  • PASS1_CFLAGS, PASS1_LDFLAGS

  • The option used in the first pass of a profile directed feedback compile that causes pdf information to be generated.

• • -qpdf2
  • 
  • PASS2_CFLAGS, PASS2_LDFLAGS

  • The option used in the second pass of a profile directed feedback compile that causes pdf information to be utilized during optimization.

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -D_ILS_MACROS
  • 
  • OPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -qalign=natural
  • 
  • OPTIMIZE

  •            Specifies what aggregate alignment rules the
                    compiler uses for file compilation, where the
                    alignment options are:
    
                    bit_packed
                         The compiler uses the bit_packed alignment
                         rules.
                    full
                         The compiler uses the RISC System/6000
                         alignment rules. This is the same as power.
                    mac68k
                         The compiler uses the Macintosh alignment
                         rules.  This suboption is valid only for 32-
                         bit compilations.
                    natural
                         The compiler maps structure members to their
                         natural boundaries.
                    packed
                         The compiler uses the packed alignment rules.
                    power
                         The compiler uses the RISC System/6000
                         alignment rules.
                    twobyte
                         The compiler uses the Macintosh alignment
                         rules.  This suboption is valid only for 32-
                         bit compilations.  The mac68k option is the
                         same as twobyte.
    
                    The default is -qalign=full.
    

• • -qipa=noobject
  • 
  • EXTRA_CFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

470.lbm

• • -qlanglvl=extc99
  • 
  • CC, LD

  • Allows most any c dialect.

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -D_ILS_MACROS
  • 
  • OPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -qipa=noobject
  • 
  • EXTRA_CFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

482.sphinx3

• • -qlanglvl=extc99
  • 
  • CC, LD

  • Allows most any c dialect.

• • -qpdf1
  • 
  • PASS1_CFLAGS, PASS1_LDFLAGS

  • The option used in the first pass of a profile directed feedback compile that causes pdf information to be generated.

• • -qpdf2
  • 
  • PASS2_CFLAGS, PASS2_LDFLAGS

  • The option used in the second pass of a profile directed feedback compile that causes pdf information to be utilized during optimization.

• • -O4
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes interprocedural anaylisis on all of the objects presented on the "link" step.

    -O4 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=1
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -D_ILS_MACROS
  • 
  • OPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -qipa=noobject
  • 
  • EXTRA_CFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

C++ benchmarks

444.namd

• • -qpdf1
  • 
  • PASS1_CXXFLAGS, PASS1_LDFLAGS

  • The option used in the first pass of a profile directed feedback compile that causes pdf information to be generated.

• • -qpdf2
  • 
  • PASS2_CXXFLAGS, PASS2_LDFLAGS

  • The option used in the second pass of a profile directed feedback compile that causes pdf information to be utilized during optimization.

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -D_ILS_MACROS
  • 
  • OPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -qipa=noobject
  • 
  • EXTRA_CXXFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

447.dealII

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -D_ILS_MACROS
  • 
  • OPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -qrtti=all
  • 
  • OPTIMIZE

  • Cause the C++ compiler to generate Run Time Type Identification code

• • -D__IBM_FAST_VECTOR
  • 
  • CXXOPTIMIZE

  • The __IBM_FAST_VECTOR macro defines a different iterator for the std::vector template class. This iterator results in faster code, but is not compatible with code using the default iterator for a std::vector template class. All uses of std::vector for a data type must use the same iterator. Add -D__IBM_FAST_VECTOR to the compile line, or "#define __IBM_FAST_VECTOR 1" to your source code to use the faster iterator for std::vector template class. You must compile all sources with this macro.

• • -qipa=noobject
  • 
  • EXTRA_CXXFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

450.soplex

• • -O4
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes interprocedural anaylisis on all of the objects presented on the "link" step.

    -O4 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=1
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -D_ILS_MACROS
  • 
  • OPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -qipa=noobject
  • 
  • EXTRA_CXXFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

453.povray

• • -qpdf1
  • 
  • PASS1_CXXFLAGS, PASS1_LDFLAGS

  • The option used in the first pass of a profile directed feedback compile that causes pdf information to be generated.

• • -qpdf2
  • 
  • PASS2_CXXFLAGS, PASS2_LDFLAGS

  • The option used in the second pass of a profile directed feedback compile that causes pdf information to be utilized during optimization.

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -D_ILS_MACROS
  • 
  • OPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -q64
  • 
  • OPTIMIZE

  • Generates 64 bit ABI binaries.

• • -qalign=natural
  • 
  • OPTIMIZE

  •            Specifies what aggregate alignment rules the
                    compiler uses for file compilation, where the
                    alignment options are:
    
                    bit_packed
                         The compiler uses the bit_packed alignment
                         rules.
                    full
                         The compiler uses the RISC System/6000
                         alignment rules. This is the same as power.
                    mac68k
                         The compiler uses the Macintosh alignment
                         rules.  This suboption is valid only for 32-
                         bit compilations.
                    natural
                         The compiler maps structure members to their
                         natural boundaries.
                    packed
                         The compiler uses the packed alignment rules.
                    power
                         The compiler uses the RISC System/6000
                         alignment rules.
                    twobyte
                         The compiler uses the Macintosh alignment
                         rules.  This suboption is valid only for 32-
                         bit compilations.  The mac68k option is the
                         same as twobyte.
    
                    The default is -qalign=full.
    

• • -lmass
  • 
  • OPTIMIZE

  • Link the mathematical acceleration subsystem libraries (MASS), which contain libraries of tuned mathematical intrinsic functions.

• • -qipa=noobject
  • 
  • EXTRA_CXXFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

Fortran benchmarks

410.bwaves

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -qsmallstack=dynlenonheap
  • 
  • FOPTIMIZE

  • Causes the Fortran compiler to allocate dynamic arrays on the heap instead of the stack

• • -qipa=noobject
  • 
  • EXTRA_FFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

416.gamess

• • -qpdf1
  • 
  • PASS1_FFLAGS, PASS1_LDFLAGS

  • The option used in the first pass of a profile directed feedback compile that causes pdf information to be generated.

• • -qpdf2
  • 
  • PASS2_FFLAGS, PASS2_LDFLAGS

  • The option used in the second pass of a profile directed feedback compile that causes pdf information to be utilized during optimization.

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -qessl
  • 
  • OPTIMIZE

  • Specifies that, if either -lessl or -lesslsmp are also specified, then Engineering and Scientific Subroutine Library (ESSL) routines should be used in place of some Fortran 90 intrinsic procedures when there is a safe opportunity to do so.

• • -lessl
  • 
  • OPTIMIZE

  • Link the Engineering and Scientifc Subroutine Library (ESSL).

• • -qipa=noobject
  • 
  • EXTRA_FFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

434.zeusmp

• • -qpdf1
  • 
  • PASS1_FFLAGS, PASS1_LDFLAGS

  • The option used in the first pass of a profile directed feedback compile that causes pdf information to be generated.

• • -qpdf2
  • 
  • PASS2_FFLAGS, PASS2_LDFLAGS

  • The option used in the second pass of a profile directed feedback compile that causes pdf information to be utilized during optimization.

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -qipa=noobject
  • 
  • EXTRA_FFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

437.leslie3d

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -qipa=noobject
  • 
  • EXTRA_FFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

459.GemsFDTD

• • Same as 437.leslie3d

465.tonto

• • -qpdf1
  • 
  • PASS1_FFLAGS, PASS1_LDFLAGS

  • The option used in the first pass of a profile directed feedback compile that causes pdf information to be generated.

• • -qpdf2
  • 
  • PASS2_FFLAGS, PASS2_LDFLAGS

  • The option used in the second pass of a profile directed feedback compile that causes pdf information to be utilized during optimization.

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -lmass
  • 
  • OPTIMIZE

  • Link the mathematical acceleration subsystem libraries (MASS), which contain libraries of tuned mathematical intrinsic functions.

• • -qipa=noobject
  • 
  • EXTRA_FFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

Benchmarks using both Fortran and C

435.gromacs

• • -qlanglvl=extc99
  • 
  • CC

  • Allows most any c dialect.

• • -qpdf1
  • 
  • PASS1_CFLAGS, PASS1_FFLAGS, PASS1_LDFLAGS

  • The option used in the first pass of a profile directed feedback compile that causes pdf information to be generated.

• • -qpdf2
  • 
  • PASS2_CFLAGS, PASS2_FFLAGS, PASS2_LDFLAGS

  • The option used in the second pass of a profile directed feedback compile that causes pdf information to be utilized during optimization.

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -D_ILS_MACROS
  • 
  • COPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -qipa=noobject
  • 
  • EXTRA_CFLAGS, EXTRA_FFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

436.cactusADM

• • -qlanglvl=extc99
  • 
  • CC

  • Allows most any c dialect.

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -D_ILS_MACROS
  • 
  • COPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -qipa=noobject
  • 
  • EXTRA_CFLAGS, EXTRA_FFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

454.calculix

• • Same as 435.gromacs

481.wrf

• • -qlanglvl=extc99
  • 
  • CC

  • Allows most any c dialect.

• • -O5
  • 
  • OPTIMIZE

  • Perform optimizations for maximum performance. This includes maximum interprocedural anaylisis on all of the objects presented on the "link" step. This level of optimization will increase the compiler's memory usage and compile time requirements.

    -O5 is equivalent to the following flags

  • Includes:
    • -O3
      • -O
      • -qhot
    • -qipa=level=2
    • -qarch=auto
    • -qtune=auto
• • -qlargepage
  • 
  • OPTIMIZE

  • Indicates that a program, designed to execute in a large page memory environment, can take advantage of large 16 MB pages provided on POWER4 and higher based systems.

• • -lmass
  • 
  • OPTIMIZE

  • Link the mathematical acceleration subsystem libraries (MASS), which contain libraries of tuned mathematical intrinsic functions.

• • -qsmallstack=dynlenonheap
  • 
  • OPTIMIZE

  • Causes the Fortran compiler to allocate dynamic arrays on the heap instead of the stack

• • -D_ILS_MACROS
  • 
  • COPTIMIZE

  • Causes AIX to define "ischar()" (and friends) as macro's and no subroutines.

• • -qipa=noobject
  • 
  • EXTRA_CFLAGS, EXTRA_FFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed

• • -blpdata
  • 
  • EXTRA_LDFLAGS

  • Sets the bit in the file's XCOFF header indicating that this executable will request the use of large pages when they are available on the system and when the user has an appropriate privilege

• • -qipa=threads
  • 
  • EXTRA_LDFLAGS

  • level=1 turns on

    level=2 turns on

    noobject supression of actual code generation as each source file is processed