CPU2006 Flag Description
Hewlett-Packard Company ProLiant ML350 G5 (1.60 GHz, Intel Xeon processor E5310)

Base Optimization Flags

C benchmarks

• • -fast
  • 
  • COPTIMIZE

  • The -fast option enhances execution speed across the entire program by including the following options that can improve run-time performance:

    -O3   (maximum speed and high-level optimizations)

    -ipo (enables interprocedural optimizations across files)

    -xP  (generate code specialized for Intel Pentium 4 processor and compatible Intel processors with Streaming SIMD Extensions 3)

    -no-prec-div (disable -prec-div) where -prec-div improves precision of FP divides (some speed impact)

    -static (statically link libraries during compilation)

    To override one of the options set by /fast, specify that option after the -fast option on the command line. The options set by /fast may change from release to release.

  • Includes:
    • -O3
      • -fp
      • -O2
        • -O1
          • -unroll_n
          • -fno-builtin
          • -mno-ieee-fp
          • -fomit-frame-pointer
          • -ffunction-sections
    • -ipo
    • -xP
    • -static
    • -no-prec-div

C++ benchmarks

• • -xP
  • 
  • CXXOPTIMIZE

  • The -xN and -xP options target your program to run on Intel Pentium 4 and compatible Intel processors. The resulting code might contain unconditional use of features that are not supported on other processors. Programs, where the function main() is compiled with this option, will detect non compatible processors and generate an error message during execution. This option also enables new optimizations in addition to Intel processor specific optimizations.

    These options also enable advanced data layout and code restructuring optimizations to improve memory accesses for Intel processors.

• • -O3
  • 
  • CXXOPTIMIZE

  • Builds on -01 and -02 optimizations by enabling high-level optimization. This level does not guarantee higher performance unless loop and memory access transformation take place. In conjunction with -axK/-xK and -axW/-xW, this switch causes the compiler to perform more aggressive data dependency analysis than for -O2. This may result in longer compilation times. On Linux platforms, -O3 sets the following:

    -fp

  • Includes:
    • -fp
    • -O2
      • -O1
        • -unroll_n
        • -fno-builtin
        • -mno-ieee-fp
        • -fomit-frame-pointer
        • -ffunction-sections
• • -ipo
  • 
  • 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

• • -no-prec-div
  • 
  • CXXOPTIMIZE
  • (disable -prec-div)

    Allows the compiler to perform optimizations in FP divides that may impact precision while improving speed.

• • -L/root/compiler/smartheap/SmartHeap_8.1/lib -lsmartheap
  • 
  • EXTRA_CXXLIBS

  • -L -lsmartheap ,
    when used as an EXTRA_CLIB or EXTRA_CXXLIB variable, results in linking with MicroQuill's SmartHeap 8.1 (32-bit) library for Linux. This is a library that optimizes calls to new, delete, malloc and free.

Peak Optimization Flags

C benchmarks

400.perlbench

• • basepeak = yes

401.bzip2

• • -fast
  • 
  • COPTIMIZE, OPTIMIZE

  • The -fast option enhances execution speed across the entire program by including the following options that can improve run-time performance:

    -O3   (maximum speed and high-level optimizations)

    -ipo (enables interprocedural optimizations across files)

    -xP  (generate code specialized for Intel Pentium 4 processor and compatible Intel processors with Streaming SIMD Extensions 3)

    -no-prec-div (disable -prec-div) where -prec-div improves precision of FP divides (some speed impact)

    -static (statically link libraries during compilation)

    To override one of the options set by /fast, specify that option after the -fast option on the command line. The options set by /fast may change from release to release.

  • Includes:
    • -O3
      • -fp
      • -O2
        • -O1
          • -unroll_n
          • -fno-builtin
          • -mno-ieee-fp
          • -fomit-frame-pointer
          • -ffunction-sections
    • -ipo
    • -xP
    • -static
    • -no-prec-div
• • -auto_ilp32
  • 
  • COPTIMIZE

  • This option instructs the compiler to analyze the program to determine if there are 64-bit pointers which can be safely shrunk into 32-bit pointers. In order for this option to be effective the compiler must be able to optimize using the -ipo option, and must be able to analyze all library/external calls the program makes. This option imposes the following restrictions on the program:
    The program cannot malloc any objects greater than 2**31 bytes in size.
    If the program does not satisfy this restriction, unpredictable behavior may occur.

403.gcc

• • basepeak = yes

429.mcf

• • -prof_gen
  • 
  • PASS1_CFLAGS, PASS1_LDFLAGS

  • 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
  • 
  • PASS2_CFLAGS, PASS2_LDFLAGS

  • 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

• • -fast
  • 
  • COPTIMIZE, OPTIMIZE

  • The -fast option enhances execution speed across the entire program by including the following options that can improve run-time performance:

    -O3   (maximum speed and high-level optimizations)

    -ipo (enables interprocedural optimizations across files)

    -xP  (generate code specialized for Intel Pentium 4 processor and compatible Intel processors with Streaming SIMD Extensions 3)

    -no-prec-div (disable -prec-div) where -prec-div improves precision of FP divides (some speed impact)

    -static (statically link libraries during compilation)

    To override one of the options set by /fast, specify that option after the -fast option on the command line. The options set by /fast may change from release to release.

  • Includes:
    • -O3
      • -fp
      • -O2
        • -O1
          • -unroll_n
          • -fno-builtin
          • -mno-ieee-fp
          • -fomit-frame-pointer
          • -ffunction-sections
    • -ipo
    • -xP
    • -static
    • -no-prec-div
• • -auto_ilp32
  • 
  • COPTIMIZE

  • This option instructs the compiler to analyze the program to determine if there are 64-bit pointers which can be safely shrunk into 32-bit pointers. In order for this option to be effective the compiler must be able to optimize using the -ipo option, and must be able to analyze all library/external calls the program makes. This option imposes the following restrictions on the program:
    The program cannot malloc any objects greater than 2**31 bytes in size.
    If the program does not satisfy this restriction, unpredictable behavior may occur.

445.gobmk

• • Same as 429.mcf

456.hmmer

• • Same as 429.mcf

458.sjeng

• • Same as 429.mcf

462.libquantum

• • Same as 429.mcf

464.h264ref

• • Same as 429.mcf

C++ benchmarks

471.omnetpp

• • -prof_gen
  • 
  • PASS1_CXXFLAGS, PASS1_LDFLAGS

  • 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
  • 
  • PASS2_CXXFLAGS, PASS2_LDFLAGS

  • 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

• • -xP
  • 
  • OPTIMIZE

  • The -xN and -xP options target your program to run on Intel Pentium 4 and compatible Intel processors. The resulting code might contain unconditional use of features that are not supported on other processors. Programs, where the function main() is compiled with this option, will detect non compatible processors and generate an error message during execution. This option also enables new optimizations in addition to Intel processor specific optimizations.

    These options also enable advanced data layout and code restructuring optimizations to improve memory accesses for Intel processors.

• • -O3
  • 
  • OPTIMIZE

  • Builds on -01 and -02 optimizations by enabling high-level optimization. This level does not guarantee higher performance unless loop and memory access transformation take place. In conjunction with -axK/-xK and -axW/-xW, this switch causes the compiler to perform more aggressive data dependency analysis than for -O2. This may result in longer compilation times. On Linux platforms, -O3 sets the following:

    -fp

  • Includes:
    • -fp
    • -O2
      • -O1
        • -unroll_n
        • -fno-builtin
        • -mno-ieee-fp
        • -fomit-frame-pointer
        • -ffunction-sections
• • -ipo
  • 
  • OPTIMIZE

  • 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

• • -no-prec-div
  • 
  • OPTIMIZE
  • (disable -prec-div)

    Allows the compiler to perform optimizations in FP divides that may impact precision while improving speed.

• • -fast
  • 
  • CXXOPTIMIZE

  • The -fast option enhances execution speed across the entire program by including the following options that can improve run-time performance:

    -O3   (maximum speed and high-level optimizations)

    -ipo (enables interprocedural optimizations across files)

    -xP  (generate code specialized for Intel Pentium 4 processor and compatible Intel processors with Streaming SIMD Extensions 3)

    -no-prec-div (disable -prec-div) where -prec-div improves precision of FP divides (some speed impact)

    -static (statically link libraries during compilation)

    To override one of the options set by /fast, specify that option after the -fast option on the command line. The options set by /fast may change from release to release.

  • Includes:
    • -O3
      • -fp
      • -O2
        • -O1
          • -unroll_n
          • -fno-builtin
          • -mno-ieee-fp
          • -fomit-frame-pointer
          • -ffunction-sections
    • -ipo
    • -xP
    • -static
    • -no-prec-div
• • -auto_ilp32
  • 
  • CXXOPTIMIZE

  • This option instructs the compiler to analyze the program to determine if there are 64-bit pointers which can be safely shrunk into 32-bit pointers. In order for this option to be effective the compiler must be able to optimize using the -ipo option, and must be able to analyze all library/external calls the program makes. This option imposes the following restrictions on the program:
    The program cannot malloc any objects greater than 2**31 bytes in size.
    If the program does not satisfy this restriction, unpredictable behavior may occur.

• • -L/root/compiler/smartheap/SmartHeap_8.1/lib -lsmartheap
  • 
  • EXTRA_CXXLIBS

  • -L -lsmartheap ,
    when used as an EXTRA_CLIB or EXTRA_CXXLIB variable, results in linking with MicroQuill's SmartHeap 8.1 (32-bit) library for Linux. This is a library that optimizes calls to new, delete, malloc and free.

473.astar

• • -prof_gen
  • 
  • PASS1_CXXFLAGS, PASS1_LDFLAGS

  • 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
  • 
  • PASS2_CXXFLAGS, PASS2_LDFLAGS

  • 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

• • -fast
  • 
  • CXXOPTIMIZE, OPTIMIZE

  • The -fast option enhances execution speed across the entire program by including the following options that can improve run-time performance:

    -O3   (maximum speed and high-level optimizations)

    -ipo (enables interprocedural optimizations across files)

    -xP  (generate code specialized for Intel Pentium 4 processor and compatible Intel processors with Streaming SIMD Extensions 3)

    -no-prec-div (disable -prec-div) where -prec-div improves precision of FP divides (some speed impact)

    -static (statically link libraries during compilation)

    To override one of the options set by /fast, specify that option after the -fast option on the command line. The options set by /fast may change from release to release.

  • Includes:
    • -O3
      • -fp
      • -O2
        • -O1
          • -unroll_n
          • -fno-builtin
          • -mno-ieee-fp
          • -fomit-frame-pointer
          • -ffunction-sections
    • -ipo
    • -xP
    • -static
    • -no-prec-div
• • -auto_ilp32
  • 
  • CXXOPTIMIZE

  • This option instructs the compiler to analyze the program to determine if there are 64-bit pointers which can be safely shrunk into 32-bit pointers. In order for this option to be effective the compiler must be able to optimize using the -ipo option, and must be able to analyze all library/external calls the program makes. This option imposes the following restrictions on the program:
    The program cannot malloc any objects greater than 2**31 bytes in size.
    If the program does not satisfy this restriction, unpredictable behavior may occur.

• • -L/root/compiler/smartheap/SmartHeap_8.1/lib -lsmartheap
  • 
  • EXTRA_CXXLIBS

  • -L -lsmartheap ,
    when used as an EXTRA_CLIB or EXTRA_CXXLIB variable, results in linking with MicroQuill's SmartHeap 8.1 (32-bit) library for Linux. This is a library that optimizes calls to new, delete, malloc and free.

483.xalancbmk

• • basepeak = yes