Implementation notes: aarch64, supercoplxc, crypto_decode/857x5167

Computer: supercoplxc
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_decode
Primitive: 857x5167
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
104005664 0 018222 800 760int16clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082820190816
112005660 0 018142 800 760int16clang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082820190816
112005648 0 018182 800 760int16clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019082820190816
112005648 0 018182 800 760int16clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082820190816
112005648 0 018182 800 760int16clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082820190816
171208104 0 020662 800 760portableclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082820190816
180008124 0 020606 800 760portableclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082820190816
180008112 0 020646 800 760portableclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019082820190816
180008112 0 020646 800 760portableclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082820190816
180008112 0 020646 800 760portableclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082820190816
412003764 0 015968 880 736portablegcc_-funroll-loops_-O2_-fomit-frame-pointer2019082820190816
412003756 0 016545 888 752portablegcc_-funroll-loops_-O3_-fomit-frame-pointer2019082820190816
428003628 0 015832 880 736int16gcc_-funroll-loops_-O2_-fomit-frame-pointer2019082820190816
428003628 0 016409 888 752int16gcc_-funroll-loops_-O3_-fomit-frame-pointer2019082820190816
428002272 0 011680 864 728int16gcc_-funroll-loops_-Os_-fomit-frame-pointer2019082820190816
428002272 0 011680 864 728int16gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
433603544 0 015792 880 736int16gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
433603544 0 016249 888 752int16gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
434402272 0 011616 864 728int16gcc_-Os_-fomit-frame-pointer2019082820190816
434402272 0 011616 864 728int16gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
440803224 0 014449 888 752int16gcc_-O3_-fomit-frame-pointer2019082820190816
444002380 0 012336 880 736int16gcc_-O2_-fomit-frame-pointer2019082820190816
476003116 0 014329 888 752int16gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
477602300 0 012200 880 736int16gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
479203708 0 016417 888 752portablegcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
480003708 0 015960 880 736portablegcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
500003564 0 017104 880 736int16gcc_-funroll-loops_-O_-fomit-frame-pointer2019082820190816
500003564 0 017104 880 736int16gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
500802332 0 012504 880 736int16gcc_-O_-fomit-frame-pointer2019082820190816
500802332 0 012504 880 736int16gcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
511202888 0 014097 888 752portablegcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
512802196 0 012096 880 736portablegcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
514402956 0 014177 888 752portablegcc_-O3_-fomit-frame-pointer2019082820190816
518402252 0 012208 880 736portablegcc_-O2_-fomit-frame-pointer2019082820190816
863201508 0 010936 864 728portablegcc_-funroll-loops_-Os_-fomit-frame-pointer2019082820190816
863201508 0 010936 864 728portablegcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
880801444 0 010800 864 728portablegcc_-Os_-fomit-frame-pointer2019082820190816
880801444 0 010800 864 728portablegcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
981601348 0 012585 888 752refgcc_-O3_-fomit-frame-pointer2019082820190816
985601348 0 012569 888 752refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
988002620 0 015329 888 752refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
993602856 0 016400 880 736portablegcc_-funroll-loops_-O_-fomit-frame-pointer2019082820190816
993602856 0 016400 880 736portablegcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
1000001632 0 011824 880 736portablegcc_-O_-fomit-frame-pointer2019082820190816
1000001632 0 011824 880 736portablegcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
1003202616 0 015401 888 752refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019082820190816
1004801304 0 013782 800 760refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082820190816
1018402548 0 014792 880 736refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
1036802544 0 014744 880 736refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019082820190816
1065601292 0 011248 880 736refgcc_-O2_-fomit-frame-pointer2019082820190816
1071201292 0 011192 880 736refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
1091201364 0 013926 800 760refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082820190816
1118401360 0 013886 800 760refclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019082820190816
1118401360 0 013886 800 760refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082820190816
1118401360 0 013886 800 760refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082820190816
1198401056 0 010384 864 728refgcc_-Os_-fomit-frame-pointer2019082820190816
1198401056 0 010384 864 728refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
1198401056 0 010448 864 728refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019082820190816
1198401056 0 010448 864 728refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
1364001896 0 015424 880 736refgcc_-funroll-loops_-O_-fomit-frame-pointer2019082820190816
1364801896 0 015424 880 736refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
1376001136 0 011312 880 736refgcc_-O_-fomit-frame-pointer2019082820190816
1376001136 0 011312 880 736refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
2335206452 0 018920 864 736int16cc2019082820190816
2335206452 0 018920 864 736int16gcc2019082820190816
2335206452 0 018920 864 736int16gcc_-funroll-loops2019082820190816
3316003028 0 015504 864 736portablecc2019082820190816
3316003028 0 015504 864 736portablegcc2019082820190816
3316003028 0 015504 864 736portablegcc_-funroll-loops2019082820190816
4855202756 0 015208 864 736refcc2019082820190816
4855202756 0 015208 864 736refgcc2019082820190816
4857602756 0 015208 864 736refgcc_-funroll-loops2019082820190816

Compiler output

Implementation: crypto_decode/857x5167/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/857x5167/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