CPU2017 Flag Description
Supermicro A+ Server 4023S-TRT (H11DSi-NT , AMD EPYC 7371)

Base Optimization Flags

C benchmarks

• • -flto
  • 
  • COPTIMIZE, EXTRA_LDFLAGS

  • Generate output files in LLVM formats suitable for link time optimization. When used with -S this generates LLVM intermediate language assembly files, otherwise this generates LLVM bitcode format object files (which may be passed to the linker depending on the stage selection options).

• • -Wl,-plugin-opt=-merge-constant
  • 
  • EXTRA_LDFLAGS

  • This optimization merges duplicate constant uses into a register to reduce instruction width.

• • -Wl,-plugin-opt=-lsr-in-nested-loop
  • 
  • EXTRA_LDFLAGS

  • Enables loop strength reduction for nested loop structures. By default, the compiler will do loop strength reduction only for the innermost loop.

• • -Wl,-plugin-opt=-disable-vect-cmp
  • 
  • EXTRA_LDFLAGS

  • Certain loops with breaks may be vectorized by default at -O2 and above. In some extreme situations this may result in unsafe behavior. Use this option to disable vectorization of such loops.

• • -O3
  • 
  • COPTIMIZE

  • Like -O2, except that it enables optimizations that take longer to perform or that may generate larger code (in an attempt to make the program run faster).

    If multiple "O" options are used, with or without level numbers, the last such option is the one that is effective.

  • Includes:
    • -O2
      • -O1
• • -ffast-math
  • 
  • COPTIMIZE

  • Enables a range of optimizations that provide faster, though sometimes less precise, mathematical operations that may not conform to the IEEE-754 specifications. When this option is specified, the __STDC_IEC_559__ macro is ignored even if set by the system headers.

• • -march=znver1
  • 
  • COPTIMIZE

  • Specify that Clang should generate code for a specific processor family member and later. For example, if you specify -march=znver1, the compiler is allowed to generate instructions that are valid on AMD Zen processors, but which may not exist on earlier products.

• • -fstruct-layout=2
  • 
  • COPTIMIZE

  • This option enables transformation of the layout of arrays of structure types and their fields to improve the cache locality. Aggressive analysis and transformations are performed at higher levels. This option is effective only with -flto as whole program analysis is required to perform this optimization.

    Possible values:

    • 1: Use when the allocated size of the array of structures is unknown at compile time.
    • 2: Use when the allocated size of the array of structures is known to fall within 64KB and 4GB.
    • 3: Use when the allocated size of the array of structures is known to be less than 64KB.
• • -mllvm -unroll-threshold=100
  • 
  • COPTIMIZE

  • Sets the limit at which loops will be unrolled. For example, if unroll threshold is set to 100 then only loops with 100 or fewer instructions will be unrolled.

• • -fremap-arrays
  • 
  • COPTIMIZE

  • This option enables an optimization that transforms the data layout of a single dimensional array to provide better cache locality by analysing the access patterns.

• • -mno-avx2
  • 
  • COPTIMIZE

  • This option restricts the optimization and code generation to first-generation AVX instructions.

• • -mllvm -inline-threshold=1000
  • 
  • COPTIMIZE

  • Sets the compiler's inlining threshold level to the value passed as the argument. The inline threshold is used in the inliner heuristics to decide which functions should be inlined.

• • -mllvm -disable-vect-cmp
  • 
  • COPTIMIZE

  • Certain loops with breaks may be vectorized by default at -O2 and above. In some extreme situations this may result in unsafe behavior. Use this option to disable vectorization of such loops.

• • -z muldefs
  • 
  • LDOPTIMIZE

  • Instructs the linker to use the first definition encountered for a symbol, and ignore all others.

• • -ljemalloc
  • 
  • EXTRA_LIBS

  • Use the jemalloc library, which is a general purpose malloc(3) implementation that emphasizes fragmentation avoidance and scalable concurrency support.

C++ benchmarks

• • -flto
  • 
  • CXXOPTIMIZE, EXTRA_LDFLAGS

  • Generate output files in LLVM formats suitable for link time optimization. When used with -S this generates LLVM intermediate language assembly files, otherwise this generates LLVM bitcode format object files (which may be passed to the linker depending on the stage selection options).

• • -Wl,-plugin-opt=-merge-constant
  • 
  • EXTRA_LDFLAGS

  • This optimization merges duplicate constant uses into a register to reduce instruction width.

• • -Wl,-plugin-opt=-lsr-in-nested-loop
  • 
  • EXTRA_LDFLAGS

  • Enables loop strength reduction for nested loop structures. By default, the compiler will do loop strength reduction only for the innermost loop.

• • -Wl,-plugin-opt=-disable-vect-cmp
  • 
  • EXTRA_LDFLAGS

  • Certain loops with breaks may be vectorized by default at -O2 and above. In some extreme situations this may result in unsafe behavior. Use this option to disable vectorization of such loops.

• • -O3
  • 
  • CXXOPTIMIZE

  • Like -O2, except that it enables optimizations that take longer to perform or that may generate larger code (in an attempt to make the program run faster).

    If multiple "O" options are used, with or without level numbers, the last such option is the one that is effective.

  • Includes:
    • -O2
      • -O1
• • -march=znver1
  • 
  • CXXOPTIMIZE

  • Specify that Clang should generate code for a specific processor family member and later. For example, if you specify -march=znver1, the compiler is allowed to generate instructions that are valid on AMD Zen processors, but which may not exist on earlier products.

• • -mllvm -unroll-threshold=100
  • 
  • CXXOPTIMIZE

  • Sets the limit at which loops will be unrolled. For example, if unroll threshold is set to 100 then only loops with 100 or fewer instructions will be unrolled.

• • -finline-aggressive
  • 
  • CXXOPTIMIZE

  • Sets the compiler's inlining heuristics to an aggressive level by increasing the inline thresholds.

• • -fremap-arrays
  • 
  • CXXOPTIMIZE

  • This option enables an optimization that transforms the data layout of a single dimensional array to provide better cache locality by analysing the access patterns.

• • -mllvm -inline-threshold=1000
  • 
  • CXXOPTIMIZE

  • Sets the compiler's inlining threshold level to the value passed as the argument. The inline threshold is used in the inliner heuristics to decide which functions should be inlined.

• • -mllvm -disable-vect-cmp
  • 
  • CXXOPTIMIZE

  • Certain loops with breaks may be vectorized by default at -O2 and above. In some extreme situations this may result in unsafe behavior. Use this option to disable vectorization of such loops.

• • -z muldefs
  • 
  • LDOPTIMIZE

  • Instructs the linker to use the first definition encountered for a symbol, and ignore all others.

• • -ljemalloc
  • 
  • EXTRA_LIBS

  • Use the jemalloc library, which is a general purpose malloc(3) implementation that emphasizes fragmentation avoidance and scalable concurrency support.

Fortran benchmarks

• • -flto
  • 
  • EXTRA_LDFLAGS

  • Generate output files in LLVM formats suitable for link time optimization. When used with -S this generates LLVM intermediate language assembly files, otherwise this generates LLVM bitcode format object files (which may be passed to the linker depending on the stage selection options).

• • -Wl,-plugin-opt=-merge-constant
  • 
  • EXTRA_LDFLAGS

  • This optimization merges duplicate constant uses into a register to reduce instruction width.

• • -Wl,-plugin-opt=-lsr-in-nested-loop
  • 
  • EXTRA_LDFLAGS

  • Enables loop strength reduction for nested loop structures. By default, the compiler will do loop strength reduction only for the innermost loop.

• • -Wl,-plugin-opt=-disable-vect-cmp
  • 
  • EXTRA_LDFLAGS

  • Certain loops with breaks may be vectorized by default at -O2 and above. In some extreme situations this may result in unsafe behavior. Use this option to disable vectorization of such loops.

• • -O3
  • 
  • FOPTIMIZE

  • Like -O2, except that it enables optimizations that take longer to perform or that may generate larger code (in an attempt to make the program run faster).

    If multiple "O" options are used, with or without level numbers, the last such option is the one that is effective.

  • Includes:
    • -O2
      • -O1
• • -mavx
  • 
  • FOPTIMIZE

  • Generate code for processors that include the AVX extensions.

• • -madx
  • 
  • FOPTIMIZE

  • This option enables generation of the adx instruction.

• • -funroll-loops
  • 
  • FOPTIMIZE

  • This option instructs the compiler to unroll loops wherever possible.

• • -ffast-math
  • 
  • FOPTIMIZE

  • Enables a range of optimizations that provide faster, though sometimes less precise, mathematical operations that may not conform to the IEEE-754 specifications. When this option is specified, the __STDC_IEC_559__ macro is ignored even if set by the system headers.

• • -z muldefs
  • 
  • LDOPTIMIZE

  • Instructs the linker to use the first definition encountered for a symbol, and ignore all others.

• • -Ofast
  • 
  • EXTRA_FFLAGS

  • Enables all the optimizations from -O3 along with other aggressive optimizations that may violate strict compliance with language standards. Refer to the AOCC options document for the language you're using for more detailed documentation of optimizations enabled under -Ofast.

• • -fdefault-integer-8
  • 
  • EXTRA_FFLAGS

  • Sets the default integer and logical types to an 8 byte type. It does not promote variables with explicit KIND declarations.

• • -fplugin=dragonegg.so
  • 
  • EXTRA_FFLAGS

  • Load compiler plugin code from the dragonegg.so file.

• • -fplugin-arg-dragonegg-llvm-option=-lsr-in-nested-loop
  • 
  • EXTRA_FFLAGS

  • Enables loop strength reduction for nested loop structures. By default, the compiler will do loop strength reduction only for the innermost loop.

• • -fplugin-arg-dragonegg-llvm-option=-enable-iv-split
  • 
  • EXTRA_FFLAGS

  • Enables splitting of long live ranges of loop induction variables which span loop boundaries. This helps reduce register pressure and can help avoid needless spills to memory and reloads from memory.

• • -fplugin-arg-dragonegg-llvm-option=-merge-constant
  • 
  • EXTRA_FFLAGS

  • This optimization merges duplicate constant uses into a register to reduce instruction width.

• • -fplugin-arg-dragonegg-llvm-option=-inline-threshold:1000
  • 
  • EXTRA_FFLAGS

  • Sets the compiler's inlining threshold level to the value passed as the argument. The inline threshold is used in the inliner heuristics to decide which functions should be inlined.

• • -fplugin-arg-dragonegg-llvm-option=-disable-vect-cmp
  • 
  • EXTRA_FFLAGS

  • Certain loops with breaks may be vectorized by default at -O2 and above. In some extreme situations this may result in unsafe behavior. Use this option to disable vectorization of such loops.

• • -ljemalloc
  • 
  • EXTRA_LIBS

  • Use the jemalloc library, which is a general purpose malloc(3) implementation that emphasizes fragmentation avoidance and scalable concurrency support.

• • -lgfortran
  • 
  • EXTRA_FLIBS

  • Instructs the compiler to link with the gfortran Fortran runtime libraries.

• • -lamdlibm
  • 
  • EXTRA_FLIBS

  • Instructs the compiler to link with AMD-supported optimized math library.

Peak Optimization Flags

C benchmarks

500.perlbench_r

• • -flto
  • 
  • COPTIMIZE, EXTRA_LDFLAGS

  • Generate output files in LLVM formats suitable for link time optimization. When used with -S this generates LLVM intermediate language assembly files, otherwise this generates LLVM bitcode format object files (which may be passed to the linker depending on the stage selection options).

• • -Wl,-plugin-opt=-merge-constant
  • 
  • EXTRA_LDFLAGS

  • This optimization merges duplicate constant uses into a register to reduce instruction width.

• • -Wl,-plugin-opt=-lsr-in-nested-loop
  • 
  • EXTRA_LDFLAGS

  • Enables loop strength reduction for nested loop structures. By default, the compiler will do loop strength reduction only for the innermost loop.

• • -fprofile-instr-generate
  • 
  • PASS1_CFLAGS, PASS1_LDFLAGS

  • Turns on LLVM's instrumenation based profiling.

• • -fprofile-instr-use
  • 
  • PASS2_CFLAGS, PASS2_LDFLAGS

  • Uses the profiling files generated from a program compiled with -fprofile-instr-generate to guide optimization decisions.

• • -Ofast
  • 
  • COPTIMIZE

  • Enables all the optimizations from -O3 along with other aggressive optimizations that may violate strict compliance with language standards. Refer to the AOCC options document for the language you're using for more detailed documentation of optimizations enabled under -Ofast.

• • -march=znver1
  • 
  • COPTIMIZE

  • Specify that Clang should generate code for a specific processor family member and later. For example, if you specify -march=znver1, the compiler is allowed to generate instructions that are valid on AMD Zen processors, but which may not exist on earlier products.

• • -fstruct-layout=3
  • 
  • COPTIMIZE

  • This option enables transformation of the layout of arrays of structure types and their fields to improve the cache locality. Aggressive analysis and transformations are performed at higher levels. This option is effective only with -flto as whole program analysis is required to perform this optimization.

    Possible values:

    • 1: Use when the allocated size of the array of structures is unknown at compile time.
    • 2: Use when the allocated size of the array of structures is known to fall within 64KB and 4GB.
    • 3: Use when the allocated size of the array of structures is known to be less than 64KB.
• • -mllvm -vectorize-memory-aggressively
  • 
  • COPTIMIZE

  • This option avoids runtime memory dependency checks to enable aggressive vectorization.

• • -mno-avx2
  • 
  • COPTIMIZE

  • This option restricts the optimization and code generation to first-generation AVX instructions.

• • -mllvm -unroll-threshold=100
  • 
  • COPTIMIZE

  • Sets the limit at which loops will be unrolled. For example, if unroll threshold is set to 100 then only loops with 100 or fewer instructions will be unrolled.

• • -fremap-arrays
  • 
  • COPTIMIZE

  • This option enables an optimization that transforms the data layout of a single dimensional array to provide better cache locality by analysing the access patterns.

• • -mllvm -inline-threshold=1000
  • 
  • COPTIMIZE

  • Sets the compiler's inlining threshold level to the value passed as the argument. The inline threshold is used in the inliner heuristics to decide which functions should be inlined.

• • -ljemalloc
  • 
  • EXTRA_LIBS

  • Use the jemalloc library, which is a general purpose malloc(3) implementation that emphasizes fragmentation avoidance and scalable concurrency support.

502.gcc_r

• • -m32
  • 
  • CC, LD

  • Generate code for a 32-bit environment. The 32-bit environment sets int, long and pointer to 32 bits and generates code that runs on any i386 system. The compiler generates x86 or IA32 32-bit ABI. The default on a 32-bit host is 32-bit ABI. The default on a 64-bit host is 64-bit ABI if the target platform specified is 64-bit, otherwise the default is 32-bit.

• • -flto
  • 
  • COPTIMIZE, EXTRA_LDFLAGS

  • Generate output files in LLVM formats suitable for link time optimization. When used with -S this generates LLVM intermediate language assembly files, otherwise this generates LLVM bitcode format object files (which may be passed to the linker depending on the stage selection options).

• • -Wl,-plugin-opt=-merge-constant
  • 
  • EXTRA_LDFLAGS

  • This optimization merges duplicate constant uses into a register to reduce instruction width.

• • -Wl,-plugin-opt=-lsr-in-nested-loop
  • 
  • EXTRA_LDFLAGS

  • Enables loop strength reduction for nested loop structures. By default, the compiler will do loop strength reduction only for the innermost loop.

• • -Ofast
  • 
  • COPTIMIZE

  • Enables all the optimizations from -O3 along with other aggressive optimizations that may violate strict compliance with language standards. Refer to the AOCC options document for the language you're using for more detailed documentation of optimizations enabled under -Ofast.

• • -march=znver1
  • 
  • COPTIMIZE

  • Specify that Clang should generate code for a specific processor family member and later. For example, if you specify -march=znver1, the compiler is allowed to generate instructions that are valid on AMD Zen processors, but which may not exist on earlier products.

• • -fstruct-layout=3
  • 
  • COPTIMIZE

  • This option enables transformation of the layout of arrays of structure types and their fields to improve the cache locality. Aggressive analysis and transformations are performed at higher levels. This option is effective only with -flto as whole program analysis is required to perform this optimization.

    Possible values:

    • 1: Use when the allocated size of the array of structures is unknown at compile time.
    • 2: Use when the allocated size of the array of structures is known to fall within 64KB and 4GB.
    • 3: Use when the allocated size of the array of structures is known to be less than 64KB.
• • -mllvm -vectorize-memory-aggressively
  • 
  • COPTIMIZE

  • This option avoids runtime memory dependency checks to enable aggressive vectorization.

• • -mno-avx2
  • 
  • COPTIMIZE

  • This option restricts the optimization and code generation to first-generation AVX instructions.

• • -mllvm -unroll-threshold=100
  • 
  • COPTIMIZE

  • Sets the limit at which loops will be unrolled. For example, if unroll threshold is set to 100 then only loops with 100 or fewer instructions will be unrolled.

• • -fremap-arrays
  • 
  • COPTIMIZE

  • This option enables an optimization that transforms the data layout of a single dimensional array to provide better cache locality by analysing the access patterns.

• • -mllvm -inline-threshold=1000
  • 
  • COPTIMIZE

  • Sets the compiler's inlining threshold level to the value passed as the argument. The inline threshold is used in the inliner heuristics to decide which functions should be inlined.

• • -fgnu89-inline
  • 
  • EXTRA_COPTIMIZE

  • Tells GCC to use the GNU semantics for "inline" functions, that is, the behavior prior to the C99 standard. This switch may resolve duplicate symbol errors, as noted in the 502.gcc_r benchmark description.

• • -ljemalloc
  • 
  • EXTRA_LIBS

  • Use the jemalloc library, which is a general purpose malloc(3) implementation that emphasizes fragmentation avoidance and scalable concurrency support.

505.mcf_r

• • -flto
  • 
  • COPTIMIZE, EXTRA_LDFLAGS

  • Generate output files in LLVM formats suitable for link time optimization. When used with -S this generates LLVM intermediate language assembly files, otherwise this generates LLVM bitcode format object files (which may be passed to the linker depending on the stage selection options).

• • -Wl,-plugin-opt=-merge-constant
  • 
  • EXTRA_LDFLAGS

  • This optimization merges duplicate constant uses into a register to reduce instruction width.

• • -Wl,-plugin-opt=-lsr-in-nested-loop
  • 
  • EXTRA_LDFLAGS

  • Enables loop strength reduction for nested loop structures. By default, the compiler will do loop strength reduction only for the innermost loop.

• • -Ofast
  • 
  • COPTIMIZE

  • Enables all the optimizations from -O3 along with other aggressive optimizations that may violate strict compliance with language standards. Refer to the AOCC options document for the language you're using for more detailed documentation of optimizations enabled under -Ofast.

• • -march=znver1
  • 
  • COPTIMIZE

  • Specify that Clang should generate code for a specific processor family member and later. For example, if you specify -march=znver1, the compiler is allowed to generate instructions that are valid on AMD Zen processors, but which may not exist on earlier products.

• • -fstruct-layout=3
  • 
  • COPTIMIZE

  • This option enables transformation of the layout of arrays of structure types and their fields to improve the cache locality. Aggressive analysis and transformations are performed at higher levels. This option is effective only with -flto as whole program analysis is required to perform this optimization.

    Possible values:

    • 1: Use when the allocated size of the array of structures is unknown at compile time.
    • 2: Use when the allocated size of the array of structures is known to fall within 64KB and 4GB.
    • 3: Use when the allocated size of the array of structures is known to be less than 64KB.
• • -mllvm -vectorize-memory-aggressively
  • 
  • COPTIMIZE

  • This option avoids runtime memory dependency checks to enable aggressive vectorization.

• • -mno-avx2
  • 
  • COPTIMIZE

  • This option restricts the optimization and code generation to first-generation AVX instructions.

• • -mllvm -unroll-threshold=100
  • 
  • COPTIMIZE

  • Sets the limit at which loops will be unrolled. For example, if unroll threshold is set to 100 then only loops with 100 or fewer instructions will be unrolled.

• • -fremap-arrays
  • 
  • COPTIMIZE

  • This option enables an optimization that transforms the data layout of a single dimensional array to provide better cache locality by analysing the access patterns.

• • -mllvm -inline-threshold=1000
  • 
  • COPTIMIZE

  • Sets the compiler's inlining threshold level to the value passed as the argument. The inline threshold is used in the inliner heuristics to decide which functions should be inlined.

• • -ljemalloc
  • 
  • EXTRA_LIBS

  • Use the jemalloc library, which is a general purpose malloc(3) implementation that emphasizes fragmentation avoidance and scalable concurrency support.

525.x264_r

• • Same as 500.perlbench_r

557.xz_r

• • Same as 505.mcf_r

C++ benchmarks

520.omnetpp_r

• • -flto
  • 
  • CXXOPTIMIZE, EXTRA_LDFLAGS

  • Generate output files in LLVM formats suitable for link time optimization. When used with -S this generates LLVM intermediate language assembly files, otherwise this generates LLVM bitcode format object files (which may be passed to the linker depending on the stage selection options).

• • -Wl,-plugin-opt=-merge-constant
  • 
  • EXTRA_LDFLAGS

  • This optimization merges duplicate constant uses into a register to reduce instruction width.

• • -Wl,-plugin-opt=-lsr-in-nested-loop
  • 
  • EXTRA_LDFLAGS

  • Enables loop strength reduction for nested loop structures. By default, the compiler will do loop strength reduction only for the innermost loop.

• • -Ofast
  • 
  • CXXOPTIMIZE

  • Enables all the optimizations from -O3 along with other aggressive optimizations that may violate strict compliance with language standards. Refer to the AOCC options document for the language you're using for more detailed documentation of optimizations enabled under -Ofast.

• • -march=znver1
  • 
  • CXXOPTIMIZE

  • Specify that Clang should generate code for a specific processor family member and later. For example, if you specify -march=znver1, the compiler is allowed to generate instructions that are valid on AMD Zen processors, but which may not exist on earlier products.

• • -finline-aggressive
  • 
  • CXXOPTIMIZE

  • Sets the compiler's inlining heuristics to an aggressive level by increasing the inline thresholds.

• • -mllvm -unroll-threshold=100
  • 
  • CXXOPTIMIZE

  • Sets the limit at which loops will be unrolled. For example, if unroll threshold is set to 100 then only loops with 100 or fewer instructions will be unrolled.

• • -fremap-arrays
  • 
  • CXXOPTIMIZE

  • This option enables an optimization that transforms the data layout of a single dimensional array to provide better cache locality by analysing the access patterns.

• • -mllvm -inline-threshold=1000
  • 
  • CXXOPTIMIZE

  • Sets the compiler's inlining threshold level to the value passed as the argument. The inline threshold is used in the inliner heuristics to decide which functions should be inlined.

• • -ljemalloc
  • 
  • EXTRA_LIBS

  • Use the jemalloc library, which is a general purpose malloc(3) implementation that emphasizes fragmentation avoidance and scalable concurrency support.

523.xalancbmk_r

• • -m32
  • 
  • CXX, LD

  • Generate code for a 32-bit environment. The 32-bit environment sets int, long and pointer to 32 bits and generates code that runs on any i386 system. The compiler generates x86 or IA32 32-bit ABI. The default on a 32-bit host is 32-bit ABI. The default on a 64-bit host is 64-bit ABI if the target platform specified is 64-bit, otherwise the default is 32-bit.

• • -flto
  • 
  • CXXOPTIMIZE, EXTRA_LDFLAGS

  • Generate output files in LLVM formats suitable for link time optimization. When used with -S this generates LLVM intermediate language assembly files, otherwise this generates LLVM bitcode format object files (which may be passed to the linker depending on the stage selection options).

• • -Wl,-plugin-opt=-merge-constant
  • 
  • EXTRA_LDFLAGS

  • This optimization merges duplicate constant uses into a register to reduce instruction width.

• • -Wl,-plugin-opt=-lsr-in-nested-loop
  • 
  • EXTRA_LDFLAGS

  • Enables loop strength reduction for nested loop structures. By default, the compiler will do loop strength reduction only for the innermost loop.

• • -Ofast
  • 
  • CXXOPTIMIZE

  • Enables all the optimizations from -O3 along with other aggressive optimizations that may violate strict compliance with language standards. Refer to the AOCC options document for the language you're using for more detailed documentation of optimizations enabled under -Ofast.

• • -march=znver1
  • 
  • CXXOPTIMIZE

  • Specify that Clang should generate code for a specific processor family member and later. For example, if you specify -march=znver1, the compiler is allowed to generate instructions that are valid on AMD Zen processors, but which may not exist on earlier products.

• • -finline-aggressive
  • 
  • CXXOPTIMIZE

  • Sets the compiler's inlining heuristics to an aggressive level by increasing the inline thresholds.

• • -mllvm -unroll-threshold=100
  • 
  • CXXOPTIMIZE

  • Sets the limit at which loops will be unrolled. For example, if unroll threshold is set to 100 then only loops with 100 or fewer instructions will be unrolled.

• • -fremap-arrays
  • 
  • CXXOPTIMIZE

  • This option enables an optimization that transforms the data layout of a single dimensional array to provide better cache locality by analysing the access patterns.

• • -mllvm -inline-threshold=1000
  • 
  • CXXOPTIMIZE

  • Sets the compiler's inlining threshold level to the value passed as the argument. The inline threshold is used in the inliner heuristics to decide which functions should be inlined.

• • -ljemalloc
  • 
  • EXTRA_LIBS

  • Use the jemalloc library, which is a general purpose malloc(3) implementation that emphasizes fragmentation avoidance and scalable concurrency support.

531.deepsjeng_r

• • Same as 520.omnetpp_r

541.leela_r

• • -flto
  • 
  • CXXOPTIMIZE, EXTRA_LDFLAGS

  • Generate output files in LLVM formats suitable for link time optimization. When used with -S this generates LLVM intermediate language assembly files, otherwise this generates LLVM bitcode format object files (which may be passed to the linker depending on the stage selection options).

• • -Wl,-plugin-opt=-merge-constant
  • 
  • EXTRA_LDFLAGS

  • This optimization merges duplicate constant uses into a register to reduce instruction width.

• • -Wl,-plugin-opt=-lsr-in-nested-loop
  • 
  • EXTRA_LDFLAGS

  • Enables loop strength reduction for nested loop structures. By default, the compiler will do loop strength reduction only for the innermost loop.

• • -fprofile-instr-generate
  • 
  • PASS1_CXXFLAGS, PASS1_LDFLAGS

  • Turns on LLVM's instrumenation based profiling.

• • -fprofile-instr-use
  • 
  • PASS2_CXXFLAGS, PASS2_LDFLAGS

  • Uses the profiling files generated from a program compiled with -fprofile-instr-generate to guide optimization decisions.

• • -Ofast
  • 
  • CXXOPTIMIZE

  • Enables all the optimizations from -O3 along with other aggressive optimizations that may violate strict compliance with language standards. Refer to the AOCC options document for the language you're using for more detailed documentation of optimizations enabled under -Ofast.

• • -march=znver1
  • 
  • CXXOPTIMIZE

  • Specify that Clang should generate code for a specific processor family member and later. For example, if you specify -march=znver1, the compiler is allowed to generate instructions that are valid on AMD Zen processors, but which may not exist on earlier products.

• • -mllvm -unroll-count=8
  • 
  • CXXOPTIMIZE

  • The unroll count can be specified explicitly with -unroll_count=<value> where <value> is a positive integer. If this value is greater than the trip count, the loop will be fully unrolled.

• • -mllvm -unroll-threshold=100
  • 
  • CXXOPTIMIZE

  • Sets the limit at which loops will be unrolled. For example, if unroll threshold is set to 100 then only loops with 100 or fewer instructions will be unrolled.

• • -ljemalloc
  • 
  • EXTRA_LIBS

  • Use the jemalloc library, which is a general purpose malloc(3) implementation that emphasizes fragmentation avoidance and scalable concurrency support.

Fortran benchmarks

548.exchange2_r

• • basepeak = yes