Implementation notes: aarch64, supercoplxc, crypto_decode/857x1723

Computer: supercoplxc
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_decode
Primitive: 857x1723
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
92005096 0 017654 800 760int16clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082820190816
101605096 0 017582 800 760int16clang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082820190816
101605088 0 017622 800 760int16clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019082820190816
101605088 0 017622 800 760int16clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082820190816
101605088 0 017622 800 760int16clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082820190816
168808304 0 020862 800 760portableclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082820190816
184808324 0 020806 800 760portableclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082820190816
184808324 0 020862 800 760portableclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019082820190816
184808324 0 020862 800 760portableclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082820190816
184808324 0 020862 800 760portableclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082820190816
389602216 0 011624 864 728int16gcc_-funroll-loops_-Os_-fomit-frame-pointer2019082820190816
389602216 0 011624 864 728int16gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
392803692 0 014921 888 752int16gcc_-O3_-fomit-frame-pointer2019082820190816
392803692 0 016465 888 752int16gcc_-funroll-loops_-O3_-fomit-frame-pointer2019082820190816
395203600 0 016289 888 752int16gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
407203140 0 015328 880 736int16gcc_-funroll-loops_-O2_-fomit-frame-pointer2019082820190816
408803040 0 015264 880 736int16gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
410402316 0 012264 880 736int16gcc_-O2_-fomit-frame-pointer2019082820190816
418402216 0 011560 864 728int16gcc_-Os_-fomit-frame-pointer2019082820190816
418402216 0 011560 864 728int16gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
436803600 0 014817 888 752int16gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
452002240 0 012136 880 736int16gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
487203084 0 016592 880 736int16gcc_-funroll-loops_-O_-fomit-frame-pointer2019082820190816
487203084 0 016592 880 736int16gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
488002304 0 012480 880 736int16gcc_-O_-fomit-frame-pointer2019082820190816
488002304 0 012480 880 736int16gcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
492804324 0 017097 888 752portablegcc_-funroll-loops_-O3_-fomit-frame-pointer2019082820190816
496804088 0 015321 888 752portablegcc_-O3_-fomit-frame-pointer2019082820190816
499204252 0 016937 888 752portablegcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
504004016 0 015233 888 752portablegcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
513603188 0 015368 880 736portablegcc_-funroll-loops_-O2_-fomit-frame-pointer2019082820190816
520003124 0 015344 880 736portablegcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
521602276 0 012232 880 736portablegcc_-O2_-fomit-frame-pointer2019082820190816
522402236 0 012136 880 736portablegcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
877601508 0 010936 864 728portablegcc_-funroll-loops_-Os_-fomit-frame-pointer2019082820190816
877601508 0 010936 864 728portablegcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
887201444 0 010800 864 728portablegcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
888001444 0 010800 864 728portablegcc_-Os_-fomit-frame-pointer2019082820190816
976801364 0 012601 888 752refgcc_-O3_-fomit-frame-pointer2019082820190816
985601364 0 012585 888 752refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
985602716 0 015393 888 752refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
1000801352 0 013830 800 760refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082820190816
1004002712 0 015473 888 752refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019082820190816
1019202596 0 016120 880 736portablegcc_-funroll-loops_-O_-fomit-frame-pointer2019082820190816
1019202596 0 016120 880 736portablegcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
1022401660 0 011840 880 736portablegcc_-O_-fomit-frame-pointer2019082820190816
1022401660 0 011840 880 736portablegcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
1023202620 0 014832 880 736refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
1037602616 0 014792 880 736refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019082820190816
1084801412 0 013974 800 760refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082820190816
1089601300 0 011256 880 736refgcc_-O2_-fomit-frame-pointer2019082820190816
1094401300 0 011200 880 736refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
1110401408 0 013934 800 760refclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019082820190816
1110401408 0 013934 800 760refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082820190816
1110401408 0 013934 800 760refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082820190816
1226401064 0 010392 864 728refgcc_-Os_-fomit-frame-pointer2019082820190816
1226401064 0 010392 864 728refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
1226401064 0 010456 864 728refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019082820190816
1227201064 0 010456 864 728refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
1380001968 0 015464 880 736refgcc_-funroll-loops_-O_-fomit-frame-pointer2019082820190816
1380001968 0 015464 880 736refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
1391201144 0 011320 880 736refgcc_-O_-fomit-frame-pointer2019082820190816
1391201144 0 011320 880 736refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
2202406384 0 018848 864 736int16cc2019082820190816
2202406384 0 018848 864 736int16gcc2019082820190816
2203206384 0 018848 864 736int16gcc_-funroll-loops2019082820190816
3344802980 0 015456 864 736portablecc2019082820190816
3344802980 0 015456 864 736portablegcc2019082820190816
3344802980 0 015456 864 736portablegcc_-funroll-loops2019082820190816
4890402776 0 015224 864 736refcc2019082820190816
4890402776 0 015224 864 736refgcc2019082820190816
4890402776 0 015224 864 736refgcc_-funroll-loops2019082820190816

Compiler output

Implementation: crypto_decode/857x1723/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/857x1723/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