CPU2017 Result Flag Description

Last updated: $LastChangedDate: 2017-12-19 12:35:29 -0400 (Tue, 19 Dec 2017) $ revision $LastChangedRevision: 003 $

Base Compiler Invocation

C benchmarks

- /opt/ibm/xlC/13.1.5/bin/xlc
- CC, LD
- Invoke the IBM XL C compiler.
  - xlc
  - xlc_r
  - xlc_at
  - xlc_r_at
  32-bit binaries are produced by default on big-endian Linux. Only 64-bit compilation is supported on little-endian Linux. The xlc_r invocation is thread-safe version of xlc compiler. The xlc_at and xlc_r_at invocations link with the IBM Advanced Toolchain libraries.
- -qlanglvl=extc99
- CC, LD
- Compilation conforms to the ISO C99 standard and accepts implementation-specific language extensions.

C++ benchmarks

- /opt/ibm/xlC/13.1.5/bin/xlC
- CXX, LD
- Invoke the IBM XL C++ compiler.
  - xlC
  - xlC_r
  - xlC_at
  - xlC_r_at
  32-bit binaries are produced by default on big-endian Linux. Only 64-bit compilation is supported on little-endian Linux. The xlC_r invocation is thread-safe version of xlC compiler. The xlC_at and xlC_r_at invocations link with the IBM Advanced Toolchain libraries.

Fortran benchmarks

- /opt/ibm/xlf/15.1.5/bin/xlf95
- FC, LD
- Invoke the IBM XL Fortran compiler.
  - xlf95
  - xlf95_r
  - xlf95_at
  - xlf95_r_at
  32-bit binaries are produced by default on big-endian Linux. Only 64-bit compilation is supported on little-endian Linux. The xlf95_r invocation is thread-safe version of xlf95 compiler. The xlf95_at and xlf95_r_at invocations link with the IBM Advanced Toolchain libraries.

Benchmarks using both Fortran and C

- /opt/ibm/xlf/15.1.5/bin/xlf95
- FC, LD
- Invoke the IBM XL Fortran compiler.
  - xlf95
  - xlf95_r
  - xlf95_at
  - xlf95_r_at
  32-bit binaries are produced by default on big-endian Linux. Only 64-bit compilation is supported on little-endian Linux. The xlf95_r invocation is thread-safe version of xlf95 compiler. The xlf95_at and xlf95_r_at invocations link with the IBM Advanced Toolchain libraries.
- /opt/ibm/xlC/13.1.5/bin/xlc
- CC
- Invoke the IBM XL C compiler.
  - xlc
  - xlc_r
  - xlc_at
  - xlc_r_at
  32-bit binaries are produced by default on big-endian Linux. Only 64-bit compilation is supported on little-endian Linux. The xlc_r invocation is thread-safe version of xlc compiler. The xlc_at and xlc_r_at invocations link with the IBM Advanced Toolchain libraries.
- -qlanglvl=extc99
- CC
- Compilation conforms to the ISO C99 standard and accepts implementation-specific language extensions.

Benchmarks using both C and C++

- /opt/ibm/xlC/13.1.5/bin/xlC
- CXX, LD
- Invoke the IBM XL C++ compiler.
  - xlC
  - xlC_r
  - xlC_at
  - xlC_r_at
  32-bit binaries are produced by default on big-endian Linux. Only 64-bit compilation is supported on little-endian Linux. The xlC_r invocation is thread-safe version of xlC compiler. The xlC_at and xlC_r_at invocations link with the IBM Advanced Toolchain libraries.
- /opt/ibm/xlC/13.1.5/bin/xlc
- CC
- Invoke the IBM XL C compiler.
  - xlc
  - xlc_r
  - xlc_at
  - xlc_r_at
  32-bit binaries are produced by default on big-endian Linux. Only 64-bit compilation is supported on little-endian Linux. The xlc_r invocation is thread-safe version of xlc compiler. The xlc_at and xlc_r_at invocations link with the IBM Advanced Toolchain libraries.
- -qlanglvl=extc99
- CC
- Compilation conforms to the ISO C99 standard and accepts implementation-specific language extensions.

Benchmarks using Fortran, C, and C++

- /opt/ibm/xlC/13.1.5/bin/xlC
- CXX, LD
- Invoke the IBM XL C++ compiler.
  - xlC
  - xlC_r
  - xlC_at
  - xlC_r_at
  32-bit binaries are produced by default on big-endian Linux. Only 64-bit compilation is supported on little-endian Linux. The xlC_r invocation is thread-safe version of xlC compiler. The xlC_at and xlC_r_at invocations link with the IBM Advanced Toolchain libraries.
- /opt/ibm/xlC/13.1.5/bin/xlc
- CC
- Invoke the IBM XL C compiler.
  - xlc
  - xlc_r
  - xlc_at
  - xlc_r_at
  32-bit binaries are produced by default on big-endian Linux. Only 64-bit compilation is supported on little-endian Linux. The xlc_r invocation is thread-safe version of xlc compiler. The xlc_at and xlc_r_at invocations link with the IBM Advanced Toolchain libraries.
- -qlanglvl=extc99
- CC
- Compilation conforms to the ISO C99 standard and accepts implementation-specific language extensions.
- /opt/ibm/xlf/15.1.5/bin/xlf95
- FC
- Invoke the IBM XL Fortran compiler.
  - xlf95
  - xlf95_r
  - xlf95_at
  - xlf95_r_at
  32-bit binaries are produced by default on big-endian Linux. Only 64-bit compilation is supported on little-endian Linux. The xlf95_r invocation is thread-safe version of xlf95 compiler. The xlf95_at and xlf95_r_at invocations link with the IBM Advanced Toolchain libraries.

Base Portability Flags

503.bwaves_r

- -qfixed
- FPORTABILITY
- Indicates that the input fortran source program is in fixed form.
- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.

507.cactuBSSN_r

- -DSPEC_NO_UNDERSCORE
- CPORTABILITY
- If defined uses Fortran symbol names ABC as abc
- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.

508.namd_r

- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.

510.parest_r

- -qnoxlcompatmacros
- CXXPORTABILITY
- Do not use the XL compiler compat macros.
- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.

511.povray_r

- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.

519.lbm_r

- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.

521.wrf_r

- -DSPEC_NOUNDERSCORE
- CPORTABILITY
- This macro indicates that C functions called from Fortran should not have an underscore added to their names.
- -DSPEC_IBMXL
- FPPPORTABILITY
- This macro defines "flush_" instead of the default "flush" routine.
- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.
- -qufmt=be
- EXTRA_FPORTABILITY
- Sets the byte order for I/O operations on unformatted data files.
  <suboption> must be one of the following suboptions:
  - be : Specifies that I/O operations on unformatted data files use big-endian byte order.
  - le : Specifies that I/O operations on unformatted data files use little-endian byte order.
  Default: -qufmt=le

526.blender_r

- -qchars=unsigned
- PORTABILITY
- -qchars=signed : Causes the compiler to treat the type "char" as signed instead of the default of unsigned.
  
  -qchars=unsigned : Causes the compiler to treat the type "char" as unsigned. This is the default.
  Note: this particular portability flag is included for 526.blender_r per the recommendation in its documentation - see http://www.spec.org/cpu2017/Docs/benchmarks/526.blender_r.html.
- -D__BOOL_DEFINED
- CXXPORTABILITY
- Some systems need to see alternate definitions for boolean types. This flag enables their use.
- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.

527.cam4_r

- -DSPEC_NO_UNDERSCORE
- CPORTABILITY
- Fortran to C symbol naming. C symbol names are lower case without underscores. symbol
- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.

538.imagick_r

- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.

544.nab_r

- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.

549.fotonik3d_r

- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.

554.roms_r

- -DSPEC_LP64
- EXTRA_PORTABILITY
- This option is used to indicate that the host system's integers are 32-bits wide, and longs and pointers are 64-bits wide. Not all benchmarks recognize this macro, but the preferred practice for data model selection applies the flags to all benchmarks; this flag description is a placeholder for those benchmarks that do not recognize this macro.

Base Optimization Flags

C benchmarks

- -O5
- OPTIMIZE
- Perform optimizations for maximum performance. This includes maximum interprocedural analysis 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 provides all of the functionality of the -O4 option, but also provides the functionality of the -qipa=level=2 option.
  -O5 is equivalent to the following flags :
  - -O4
  - -qipa=level=2
- Includes:
  - -O4
    - -O3
      
      -O2
      
      -O
      
      -qhot=level=0
    - -qipa=level=1
    - -qarch=auto
    - -qtune=auto
    - -qsimd=auto
  - -qipa=level=2
- -q64
- OPTIMIZE
- Generates 64-bit ABI binaries. The default is to generate 64-bit ABI binaries on little-endian Linux.
- -qinline=40
- OPTIMIZE
- The inline option specifies the threshold and limit of inlined functions. Example : -qinline=40.
- -qipa=threads
- OPTIMIZE
- The threads suboption allows the IPA optimizer to run portions of the optimization process in parallel threads,
  which can speed up the compilation process on multi-processor systems. All the available threads, or the number specified by N, may be used.
  N must be a positive integer.
  Specifying nothreads does not run any parallel threads; this is equivalent to running one serial thread. This option does not affect the code in the final binary created.
- -qsimd=noauto
- OPTIMIZE
- - -qsimd : enables the generation of vector instructions for processors that support them.
  - -qnosimd : disables the generation of vector instructions.
  - Default : whether -qsimd is specified or not, -qsimd=auto is implied at the -O3 or higher optimization level; -qsimd=noauto is implied at the -O2 or lower optimization level.

C++ benchmarks

- -O5
- OPTIMIZE
- Perform optimizations for maximum performance. This includes maximum interprocedural analysis 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 provides all of the functionality of the -O4 option, but also provides the functionality of the -qipa=level=2 option.
  -O5 is equivalent to the following flags :
  - -O4
  - -qipa=level=2
- Includes:
  - -O4
    - -O3
      
      -O2
      
      -O
      
      -qhot=level=0
    - -qipa=level=1
    - -qarch=auto
    - -qtune=auto
    - -qsimd=auto
  - -qipa=level=2
- -q64
- OPTIMIZE
- Generates 64-bit ABI binaries. The default is to generate 64-bit ABI binaries on little-endian Linux.
- -qinline=40
- OPTIMIZE
- The inline option specifies the threshold and limit of inlined functions. Example : -qinline=40.
- -qipa=threads
- OPTIMIZE
- The threads suboption allows the IPA optimizer to run portions of the optimization process in parallel threads,
  which can speed up the compilation process on multi-processor systems. All the available threads, or the number specified by N, may be used.
  N must be a positive integer.
  Specifying nothreads does not run any parallel threads; this is equivalent to running one serial thread. This option does not affect the code in the final binary created.
- -qsimd=noauto
- OPTIMIZE
- - -qsimd : enables the generation of vector instructions for processors that support them.
  - -qnosimd : disables the generation of vector instructions.
  - Default : whether -qsimd is specified or not, -qsimd=auto is implied at the -O3 or higher optimization level; -qsimd=noauto is implied at the -O2 or lower optimization level.

Fortran benchmarks

- -O5
- OPTIMIZE
- Perform optimizations for maximum performance. This includes maximum interprocedural analysis 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 provides all of the functionality of the -O4 option, but also provides the functionality of the -qipa=level=2 option.
  -O5 is equivalent to the following flags :
  - -O4
  - -qipa=level=2
- Includes:
  - -O4
    - -O3
      
      -O2
      
      -O
      
      -qhot=level=0
    - -qipa=level=1
    - -qarch=auto
    - -qtune=auto
    - -qsimd=auto
  - -qipa=level=2
- -q64
- OPTIMIZE
- Generates 64-bit ABI binaries. The default is to generate 64-bit ABI binaries on little-endian Linux.
- -qinline=40
- OPTIMIZE
- The inline option specifies the threshold and limit of inlined functions. Example : -qinline=40.
- -qipa=threads
- OPTIMIZE
- The threads suboption allows the IPA optimizer to run portions of the optimization process in parallel threads,
  which can speed up the compilation process on multi-processor systems. All the available threads, or the number specified by N, may be used.
  N must be a positive integer.
  Specifying nothreads does not run any parallel threads; this is equivalent to running one serial thread. This option does not affect the code in the final binary created.
- -qsimd=noauto
- OPTIMIZE
- - -qsimd : enables the generation of vector instructions for processors that support them.
  - -qnosimd : disables the generation of vector instructions.
  - Default : whether -qsimd is specified or not, -qsimd=auto is implied at the -O3 or higher optimization level; -qsimd=noauto is implied at the -O2 or lower optimization level.
- -qsmallstack=dynlenonheap
- FOPTIMIZE
- Causes the Fortran compiler to allocate dynamic arrays on the heap instead of the stack.

Benchmarks using both Fortran and C

- -O5
- OPTIMIZE
- Perform optimizations for maximum performance. This includes maximum interprocedural analysis 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 provides all of the functionality of the -O4 option, but also provides the functionality of the -qipa=level=2 option.
  -O5 is equivalent to the following flags :
  - -O4
  - -qipa=level=2
- Includes:
  - -O4
    - -O3
      
      -O2
      
      -O
      
      -qhot=level=0
    - -qipa=level=1
    - -qarch=auto
    - -qtune=auto
    - -qsimd=auto
  - -qipa=level=2
- -q64
- OPTIMIZE
- Generates 64-bit ABI binaries. The default is to generate 64-bit ABI binaries on little-endian Linux.
- -qinline=40
- OPTIMIZE
- The inline option specifies the threshold and limit of inlined functions. Example : -qinline=40.
- -qipa=threads
- OPTIMIZE
- The threads suboption allows the IPA optimizer to run portions of the optimization process in parallel threads,
  which can speed up the compilation process on multi-processor systems. All the available threads, or the number specified by N, may be used.
  N must be a positive integer.
  Specifying nothreads does not run any parallel threads; this is equivalent to running one serial thread. This option does not affect the code in the final binary created.
- -qsimd=noauto
- OPTIMIZE
- - -qsimd : enables the generation of vector instructions for processors that support them.
  - -qnosimd : disables the generation of vector instructions.
  - Default : whether -qsimd is specified or not, -qsimd=auto is implied at the -O3 or higher optimization level; -qsimd=noauto is implied at the -O2 or lower optimization level.
- -qsmallstack=dynlenonheap
- FOPTIMIZE
- Causes the Fortran compiler to allocate dynamic arrays on the heap instead of the stack.

Benchmarks using both C and C++

- -O5
- OPTIMIZE
- Perform optimizations for maximum performance. This includes maximum interprocedural analysis 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 provides all of the functionality of the -O4 option, but also provides the functionality of the -qipa=level=2 option.
  -O5 is equivalent to the following flags :
  - -O4
  - -qipa=level=2
- Includes:
  - -O4
    - -O3
      
      -O2
      
      -O
      
      -qhot=level=0
    - -qipa=level=1
    - -qarch=auto
    - -qtune=auto
    - -qsimd=auto
  - -qipa=level=2
- -q64
- OPTIMIZE
- Generates 64-bit ABI binaries. The default is to generate 64-bit ABI binaries on little-endian Linux.
- -qinline=40
- OPTIMIZE
- The inline option specifies the threshold and limit of inlined functions. Example : -qinline=40.
- -qipa=threads
- OPTIMIZE
- The threads suboption allows the IPA optimizer to run portions of the optimization process in parallel threads,
  which can speed up the compilation process on multi-processor systems. All the available threads, or the number specified by N, may be used.
  N must be a positive integer.
  Specifying nothreads does not run any parallel threads; this is equivalent to running one serial thread. This option does not affect the code in the final binary created.
- -qsimd=noauto
- OPTIMIZE
- - -qsimd : enables the generation of vector instructions for processors that support them.
  - -qnosimd : disables the generation of vector instructions.
  - Default : whether -qsimd is specified or not, -qsimd=auto is implied at the -O3 or higher optimization level; -qsimd=noauto is implied at the -O2 or lower optimization level.

Benchmarks using Fortran, C, and C++

- -O5
- OPTIMIZE
- Perform optimizations for maximum performance. This includes maximum interprocedural analysis 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 provides all of the functionality of the -O4 option, but also provides the functionality of the -qipa=level=2 option.
  -O5 is equivalent to the following flags :
  - -O4
  - -qipa=level=2
- Includes:
  - -O4
    - -O3
      
      -O2
      
      -O
      
      -qhot=level=0
    - -qipa=level=1
    - -qarch=auto
    - -qtune=auto
    - -qsimd=auto
  - -qipa=level=2
- -q64
- OPTIMIZE
- Generates 64-bit ABI binaries. The default is to generate 64-bit ABI binaries on little-endian Linux.
- -qinline=40
- OPTIMIZE
- The inline option specifies the threshold and limit of inlined functions. Example : -qinline=40.
- -qipa=threads
- OPTIMIZE
- The threads suboption allows the IPA optimizer to run portions of the optimization process in parallel threads,
  which can speed up the compilation process on multi-processor systems. All the available threads, or the number specified by N, may be used.
  N must be a positive integer.
  Specifying nothreads does not run any parallel threads; this is equivalent to running one serial thread. This option does not affect the code in the final binary created.
- -qsimd=noauto
- OPTIMIZE
- - -qsimd : enables the generation of vector instructions for processors that support them.
  - -qnosimd : disables the generation of vector instructions.
  - Default : whether -qsimd is specified or not, -qsimd=auto is implied at the -O3 or higher optimization level; -qsimd=noauto is implied at the -O2 or lower optimization level.
- -qsmallstack=dynlenonheap
- FOPTIMIZE
- Causes the Fortran compiler to allocate dynamic arrays on the heap instead of the stack.

Implicitly Included Flags

This section contains descriptions of flags that were included implicitly by other flags, but which do not have a permanent home at SPEC.

Shell, Environment, and Other Software Settings

Operating System Tuning Parameters

Firmware / BIOS / Microcode Settings

For questions about the meanings of these flags, please contact the tester.
For other inquiries, please contact info@spec.org
Copyright 2017-2018 Standard Performance Evaluation Corporation
Tested with SPEC CPU2017 v1.0.1.
Report generated on 2018-10-31 17:14:35 by SPEC CPU2017 flags formatter v5178.

	Indicates that the flag description came from the user flags file.
	Indicates that the flag description came from the suite-wide flags file.
	Indicates that the flag description came from a per-benchmark flags file.

CPU2017 Flag DescriptionYadro Yadro Vesnin (2.92 GHz, 40 cores, RHEL 7.4)

Base Compiler Invocation

Base Portability Flags

Base Optimization Flags

Implicitly Included Flags

CPU2017 Flag Description
Yadro Yadro Vesnin (2.92 GHz, 40 cores, RHEL 7.4)