CPU2006 Flag Description
ASUS Computer International Asus M2N32-SLI Deluxe (AMD Athlon 64 FX-62)

Base Optimization Flags

C benchmarks

• • -arch:SSE2
  • 
  • COPTIMIZE

  • Optimizes for Intel Pentium 4 and compatible processors with Streaming SIMD Extensions 2 (SSE2).

• • -Qprec-div-
  • 
  • COPTIMIZE
  • (disable/enable[default] -Qprec-div[-])

    -Qprec-dev improves precision of floating-point divides. It has a slight impact on speed. -Qprec-dev- disables this option and enables optimizations that give slightly less precise results than full IEEE division.

    When you specify -Qprec-dev- along with some optimizations, such as -xN and -xB (Linux) or /QxN and /QxB (Windows), the compiler may change floating-point division computations into multiplication by the reciprocal of the denominator. For example, A/B is computed as A * (1/B) to improve the speed of the computation.

    However, sometimes the value produced by this transformation is not as accurate as full IEEE division. When it is important to have fully precise IEEE division, do not use -Qprec-dev- which will enable the default -Qprec-dev and the result is more accurate, with some loss of performance.

• • -O3
  • 
  • COPTIMIZE

  • Enables O2 optimizations plus more aggressive optimizations, such as prefetching, scalar replacement, and loop and memory access transformations. Enables optimizations for maximum speed, such as:
    - Loop unrolling, including instruction scheduling
    - Code replication to eliminate branches
    - Padding the size of certain power-of-two arrays to allow more efficient cache use.
    On IA-32 and Intel EM64T processors, when O3 is used with options -ax or -x (Linux) or with options /Qax or /Qx (Windows), the compiler performs more aggressive data dependency analysis than for O2, which may result in longer compilation times.
    The O3 optimizations may not cause higher performance unless loop and memory access transformations take place. The optimizations may slow down code in some cases compared to O2 optimizations.
    The O3 option is recommended for applications that have loops that heavily use floating-point calculations and process large data sets. On IA-32 Windows platforms, -O3 sets the following:

    /GF (/Qvc7 and above), /Gf (/Qvc6 and below), and /Ob2

  • Includes:
    • -GF
    • -Gf
    • -Ob_n
    • -O2
      • -Oi-
      • -Gs
      • -Oy
      • -Gy
      • -Os
      • -GF
      • -Gf
      • -Ob_n
      • -Og
      • -O1
        • -Qunroll_n
        • -Oi-
        • -Op-
        • -Oy
        • -Gy
        • -Os
        • -GF
        • -Gf
        • -Ob_n
        • -Og
• • -Qipo
  • 
  • COPTIMIZE

  • Multi-file ip optimizations that includes:
    - inline function expansion
    - interprocedural constant propogation
    - dead code elimination
    - propagation of function characteristics
    - passing arguments in registers
    - loop-invariant code motion

• • /F950000000
  • 
  • EXTRA_LDFLAGS

  • set the stack reserve amount specified to the linker

• • shlw32m.lib
  • 
  • EXTRA_LIBS

  • MicroQuill SmartHeap Library 7.4 available from http://www.microquill.com/

• • -link /FORCE:MULTIPLE
  • 
  • LDOUT

  • Enable SmartHeap library usage by forcing the linker to ignore multiple definitions

C++ benchmarks

• • -arch:SSE2
  • 
  • CXXOPTIMIZE

  • Optimizes for Intel Pentium 4 and compatible processors with Streaming SIMD Extensions 2 (SSE2).

• • -Qprec-div-
  • 
  • CXXOPTIMIZE
  • (disable/enable[default] -Qprec-div[-])

    -Qprec-dev improves precision of floating-point divides. It has a slight impact on speed. -Qprec-dev- disables this option and enables optimizations that give slightly less precise results than full IEEE division.

    When you specify -Qprec-dev- along with some optimizations, such as -xN and -xB (Linux) or /QxN and /QxB (Windows), the compiler may change floating-point division computations into multiplication by the reciprocal of the denominator. For example, A/B is computed as A * (1/B) to improve the speed of the computation.

    However, sometimes the value produced by this transformation is not as accurate as full IEEE division. When it is important to have fully precise IEEE division, do not use -Qprec-dev- which will enable the default -Qprec-dev and the result is more accurate, with some loss of performance.

• • -O3
  • 
  • CXXOPTIMIZE

  • Enables O2 optimizations plus more aggressive optimizations, such as prefetching, scalar replacement, and loop and memory access transformations. Enables optimizations for maximum speed, such as:
    - Loop unrolling, including instruction scheduling
    - Code replication to eliminate branches
    - Padding the size of certain power-of-two arrays to allow more efficient cache use.
    On IA-32 and Intel EM64T processors, when O3 is used with options -ax or -x (Linux) or with options /Qax or /Qx (Windows), the compiler performs more aggressive data dependency analysis than for O2, which may result in longer compilation times.
    The O3 optimizations may not cause higher performance unless loop and memory access transformations take place. The optimizations may slow down code in some cases compared to O2 optimizations.
    The O3 option is recommended for applications that have loops that heavily use floating-point calculations and process large data sets. On IA-32 Windows platforms, -O3 sets the following:

    /GF (/Qvc7 and above), /Gf (/Qvc6 and below), and /Ob2

  • Includes:
    • -GF
    • -Gf
    • -Ob_n
    • -O2
      • -Oi-
      • -Gs
      • -Oy
      • -Gy
      • -Os
      • -GF
      • -Gf
      • -Ob_n
      • -Og
      • -O1
        • -Qunroll_n
        • -Oi-
        • -Op-
        • -Oy
        • -Gy
        • -Os
        • -GF
        • -Gf
        • -Ob_n
        • -Og
• • -Qipo
  • 
  • CXXOPTIMIZE

  • Multi-file ip optimizations that includes:
    - inline function expansion
    - interprocedural constant propogation
    - dead code elimination
    - propagation of function characteristics
    - passing arguments in registers
    - loop-invariant code motion

• • -Oi-
  • 
  • CXXOPTIMIZE

  • Disables inline expansion of all intrinsic functions.

• • -Qcxx_features
  • 
  • CXXOPTIMIZE

  • Enable C++ Exception Handling and RTTI
    This option has the same effect as specifying /GX /GR.

  • Includes:
    • -GX
    • -GR
• • /F950000000
  • 
  • EXTRA_LDFLAGS

  • set the stack reserve amount specified to the linker

• • shlw32m.lib
  • 
  • EXTRA_LIBS

  • MicroQuill SmartHeap Library 7.4 available from http://www.microquill.com/

• • -link /FORCE:MULTIPLE
  • 
  • LDOUT

  • Enable SmartHeap library usage by forcing the linker to ignore multiple definitions

Fortran benchmarks

• • -arch:SSE2
  • 
  • FOPTIMIZE

  • Optimizes for Intel Pentium 4 and compatible processors with Streaming SIMD Extensions 2 (SSE2).

• • -Qprec-div-
  • 
  • FOPTIMIZE
  • (disable/enable[default] -Qprec-div[-])

    -Qprec-dev improves precision of floating-point divides. It has a slight impact on speed. -Qprec-dev- disables this option and enables optimizations that give slightly less precise results than full IEEE division.

    When you specify -Qprec-dev- along with some optimizations, such as -xN and -xB (Linux) or /QxN and /QxB (Windows), the compiler may change floating-point division computations into multiplication by the reciprocal of the denominator. For example, A/B is computed as A * (1/B) to improve the speed of the computation.

    However, sometimes the value produced by this transformation is not as accurate as full IEEE division. When it is important to have fully precise IEEE division, do not use -Qprec-dev- which will enable the default -Qprec-dev and the result is more accurate, with some loss of performance.

• • -O3
  • 
  • FOPTIMIZE

  • Enables O2 optimizations plus more aggressive optimizations, such as prefetching, scalar replacement, and loop and memory access transformations. Enables optimizations for maximum speed, such as:
    - Loop unrolling, including instruction scheduling
    - Code replication to eliminate branches
    - Padding the size of certain power-of-two arrays to allow more efficient cache use.
    On IA-32 and Intel EM64T processors, when O3 is used with options -ax or -x (Linux) or with options /Qax or /Qx (Windows), the compiler performs more aggressive data dependency analysis than for O2, which may result in longer compilation times.
    The O3 optimizations may not cause higher performance unless loop and memory access transformations take place. The optimizations may slow down code in some cases compared to O2 optimizations.
    The O3 option is recommended for applications that have loops that heavily use floating-point calculations and process large data sets. On IA-32 Windows platforms, -O3 sets the following:

    /GF (/Qvc7 and above), /Gf (/Qvc6 and below), and /Ob2

  • Includes:
    • -GF
    • -Gf
    • -Ob_n
    • -O2
      • -Oi-
      • -Gs
      • -Oy
      • -Gy
      • -Os
      • -GF
      • -Gf
      • -Ob_n
      • -Og
      • -O1
        • -Qunroll_n
        • -Oi-
        • -Op-
        • -Oy
        • -Gy
        • -Os
        • -GF
        • -Gf
        • -Ob_n
        • -Og
• • -Qipo
  • 
  • FOPTIMIZE

  • Multi-file ip optimizations that includes:
    - inline function expansion
    - interprocedural constant propogation
    - dead code elimination
    - propagation of function characteristics
    - passing arguments in registers
    - loop-invariant code motion

• • -Oi-
  • 
  • FOPTIMIZE

  • Disables inline expansion of all intrinsic functions.

• • /F950000000
  • 
  • EXTRA_LDFLAGS

  • set the stack reserve amount specified to the linker

• • -link /FORCE:MULTIPLE
  • 
  • LDOUT

  • Enable SmartHeap library usage by forcing the linker to ignore multiple definitions

Benchmarks using both Fortran and C

• • -arch:SSE2
  • 
  • COPTIMIZE, FOPTIMIZE

  • Optimizes for Intel Pentium 4 and compatible processors with Streaming SIMD Extensions 2 (SSE2).

• • -Qprec-div-
  • 
  • COPTIMIZE, FOPTIMIZE
  • (disable/enable[default] -Qprec-div[-])

    -Qprec-dev improves precision of floating-point divides. It has a slight impact on speed. -Qprec-dev- disables this option and enables optimizations that give slightly less precise results than full IEEE division.

    When you specify -Qprec-dev- along with some optimizations, such as -xN and -xB (Linux) or /QxN and /QxB (Windows), the compiler may change floating-point division computations into multiplication by the reciprocal of the denominator. For example, A/B is computed as A * (1/B) to improve the speed of the computation.

    However, sometimes the value produced by this transformation is not as accurate as full IEEE division. When it is important to have fully precise IEEE division, do not use -Qprec-dev- which will enable the default -Qprec-dev and the result is more accurate, with some loss of performance.

• • -O3
  • 
  • COPTIMIZE, FOPTIMIZE

  • Enables O2 optimizations plus more aggressive optimizations, such as prefetching, scalar replacement, and loop and memory access transformations. Enables optimizations for maximum speed, such as:
    - Loop unrolling, including instruction scheduling
    - Code replication to eliminate branches
    - Padding the size of certain power-of-two arrays to allow more efficient cache use.
    On IA-32 and Intel EM64T processors, when O3 is used with options -ax or -x (Linux) or with options /Qax or /Qx (Windows), the compiler performs more aggressive data dependency analysis than for O2, which may result in longer compilation times.
    The O3 optimizations may not cause higher performance unless loop and memory access transformations take place. The optimizations may slow down code in some cases compared to O2 optimizations.
    The O3 option is recommended for applications that have loops that heavily use floating-point calculations and process large data sets. On IA-32 Windows platforms, -O3 sets the following:

    /GF (/Qvc7 and above), /Gf (/Qvc6 and below), and /Ob2

  • Includes:
    • -GF
    • -Gf
    • -Ob_n
    • -O2
      • -Oi-
      • -Gs
      • -Oy
      • -Gy
      • -Os
      • -GF
      • -Gf
      • -Ob_n
      • -Og
      • -O1
        • -Qunroll_n
        • -Oi-
        • -Op-
        • -Oy
        • -Gy
        • -Os
        • -GF
        • -Gf
        • -Ob_n
        • -Og
• • -Qipo
  • 
  • COPTIMIZE, FOPTIMIZE

  • Multi-file ip optimizations that includes:
    - inline function expansion
    - interprocedural constant propogation
    - dead code elimination
    - propagation of function characteristics
    - passing arguments in registers
    - loop-invariant code motion

• • -Oi-
  • 
  • FOPTIMIZE

  • Disables inline expansion of all intrinsic functions.

• • /F950000000
  • 
  • EXTRA_LDFLAGS

  • set the stack reserve amount specified to the linker

• • -link /FORCE:MULTIPLE
  • 
  • LDOUT

  • Enable SmartHeap library usage by forcing the linker to ignore multiple definitions