Implementation notes: aarch64, supercoplxc, crypto_decode/761x4591

Computer: supercoplxc
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_decode
Primitive: 761x4591
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
97604876 0 017438 800 760int16clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082820190816
104804888 0 017374 800 760int16clang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082820190816
104804868 0 017406 800 760int16clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019082820190816
104804868 0 017406 800 760int16clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082820190816
104804868 0 017406 800 760int16clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082820190816
158407100 0 019662 800 760portableclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082820190816
165607100 0 019638 800 760portableclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019082820190816
165607100 0 019638 800 760portableclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082820190816
165607100 0 019638 800 760portableclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082820190816
166407120 0 019606 800 760portableclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082820190816
361603604 0 015912 880 736portablegcc_-funroll-loops_-O2_-fomit-frame-pointer2019082820190816
361603604 0 016489 888 752portablegcc_-funroll-loops_-O3_-fomit-frame-pointer2019082820190816
379203312 0 015616 880 736int16gcc_-funroll-loops_-O2_-fomit-frame-pointer2019082820190816
379203312 0 016193 888 752int16gcc_-funroll-loops_-O3_-fomit-frame-pointer2019082820190816
380802344 0 011744 864 728int16gcc_-funroll-loops_-Os_-fomit-frame-pointer2019082820190816
380802344 0 011744 864 728int16gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
386402344 0 011680 864 728int16gcc_-Os_-fomit-frame-pointer2019082820190816
386402344 0 011680 864 728int16gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
390403212 0 015536 880 736int16gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
390403212 0 015993 888 752int16gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
392802896 0 014113 888 752int16gcc_-O3_-fomit-frame-pointer2019082820190816
395202468 0 012424 880 736int16gcc_-O2_-fomit-frame-pointer2019082820190816
419202372 0 012272 880 736int16gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
419202796 0 014009 888 752int16gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
427203524 0 015848 880 736portablegcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
427203524 0 016305 888 752portablegcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
443203268 0 016872 880 736int16gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
444003268 0 016872 880 736int16gcc_-funroll-loops_-O_-fomit-frame-pointer2019082820190816
444802452 0 012624 880 736int16gcc_-O_-fomit-frame-pointer2019082820190816
444802452 0 012624 880 736int16gcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
452802716 0 013929 888 752portablegcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
455202284 0 012184 880 736portablegcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
456002796 0 014017 888 752portablegcc_-O3_-fomit-frame-pointer2019082820190816
459202376 0 012328 880 736portablegcc_-O2_-fomit-frame-pointer2019082820190816
767201568 0 010984 864 728portablegcc_-funroll-loops_-Os_-fomit-frame-pointer2019082820190816
767201568 0 010984 864 728portablegcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
783201496 0 010856 864 728portablegcc_-Os_-fomit-frame-pointer2019082820190816
783201496 0 010856 864 728portablegcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
871201348 0 012585 888 752refgcc_-O3_-fomit-frame-pointer2019082820190816
876801348 0 012569 888 752refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
879202668 0 015441 888 752refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
882402988 0 016600 880 736portablegcc_-funroll-loops_-O_-fomit-frame-pointer2019082820190816
882402988 0 016600 880 736portablegcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
888801688 0 011880 880 736portablegcc_-O_-fomit-frame-pointer2019082820190816
888801688 0 011880 880 736portablegcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
892802664 0 015553 888 752refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019082820190816
894401284 0 013758 800 760refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082820190816
906402548 0 014856 880 736refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
922402544 0 014848 880 736refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019082820190816
947201292 0 011248 880 736refgcc_-O2_-fomit-frame-pointer2019082820190816
952001292 0 011192 880 736refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
971201344 0 013902 800 760refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082820190816
995201340 0 013870 800 760refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082820190816
996001340 0 013870 800 760refclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019082820190816
996001340 0 013870 800 760refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082820190816
1066401056 0 010448 864 728refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019082820190816
1067201056 0 010384 864 728refgcc_-Os_-fomit-frame-pointer2019082820190816
1067201056 0 010384 864 728refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
1067201056 0 010448 864 728refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
1212801896 0 015488 880 736refgcc_-funroll-loops_-O_-fomit-frame-pointer2019082820190816
1212801896 0 015488 880 736refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
1224001136 0 011312 880 736refgcc_-O_-fomit-frame-pointer2019082820190816
1224001136 0 011312 880 736refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
2059206760 0 019224 864 736int16gcc2019082820190816
2059206760 0 019224 864 736int16gcc_-funroll-loops2019082820190816
2060006760 0 019224 864 736int16cc2019082820190816
2942403160 0 015632 864 736portablecc2019082820190816
2942403160 0 015632 864 736portablegcc2019082820190816
2942403160 0 015632 864 736portablegcc_-funroll-loops2019082820190816
4314402756 0 015208 864 736refcc2019082820190816
4314402756 0 015208 864 736refgcc_-funroll-loops2019082820190816
4319202756 0 015208 864 736refgcc2019082820190816

Compiler output

Implementation: crypto_decode/761x4591/avx
Compiler: cc
decode.c: decode.c:3:10: fatal error: immintrin.h: No such file or directory
decode.c: #include <immintrin.h>
decode.c: ^~~~~~~~~~~~~
decode.c: compilation terminated.

Number of similar (compiler,implementation) pairs: 19, namely:
CompilerImplementations
cc avx
gcc avx
gcc -O2 -fomit-frame-pointer avx
gcc -O3 -fomit-frame-pointer avx
gcc -O -fomit-frame-pointer avx
gcc -Os -fomit-frame-pointer avx
gcc -fno-schedule-insns -O2 -fomit-frame-pointer avx
gcc -fno-schedule-insns -O3 -fomit-frame-pointer avx
gcc -fno-schedule-insns -O -fomit-frame-pointer avx
gcc -fno-schedule-insns -Os -fomit-frame-pointer avx
gcc -funroll-loops avx
gcc -funroll-loops -O2 -fomit-frame-pointer avx
gcc -funroll-loops -O3 -fomit-frame-pointer avx
gcc -funroll-loops -O -fomit-frame-pointer avx
gcc -funroll-loops -Os -fomit-frame-pointer avx
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer avx
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer avx
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer avx
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer avx

Compiler output

Implementation: crypto_decode/761x4591/avx
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
decode.c: In file included from decode.c:3:
decode.c: In file included from /usr/lib/llvm-7/lib/clang/7.0.1/include/immintrin.h:28:
decode.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:64:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
decode.c: return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
decode.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:143:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
decode.c: return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
decode.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:173:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
decode.c: return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
decode.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:203:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
decode.c: return (__m64)__builtin_ia32_packuswb((__v4hi)__m1, (__v4hi)__m2);
decode.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:230:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
decode.c: return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
decode.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:253:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
decode.c: return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
decode.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:274:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
decode.c: return (__m64)__builtin_ia32_punpckhdq((__v2si)__m1, (__v2si)__m2);
decode.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
decode.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:301:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
decode.c: return (__m64)__builtin_ia32_punpcklbw((__v8qi)__m1, (__v8qi)__m2);
decode.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments avx
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments avx
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments avx
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments avx
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx