Implementation notes: aarch64, supercoplxc, crypto_decode/653x4621

Computer: supercoplxc
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_decode
Primitive: 653x4621
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
81605872 0 018430 800 760int16clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082820190816
88005836 0 018374 800 760int16clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082820190816
88805848 0 018334 800 760int16clang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082820190816
88805836 0 018374 800 760int16clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019082820190816
88805836 0 018374 800 760int16clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082820190816
132806832 0 019390 800 760portableclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082820190816
140006868 0 019350 800 760portableclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082820190816
140006856 0 019390 800 760portableclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019082820190816
140006856 0 019390 800 760portableclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082820190816
140006856 0 019390 800 760portableclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082820190816
304803284 0 016065 888 752portablegcc_-funroll-loops_-O3_-fomit-frame-pointer2019082820190816
306403272 0 015472 880 736portablegcc_-funroll-loops_-O2_-fomit-frame-pointer2019082820190816
328002184 0 011592 864 728int16gcc_-funroll-loops_-Os_-fomit-frame-pointer2019082820190816
328002184 0 011592 864 728int16gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
332802184 0 011528 864 728int16gcc_-Os_-fomit-frame-pointer2019082820190816
332802184 0 011528 864 728int16gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
336003912 0 015129 888 752int16gcc_-O3_-fomit-frame-pointer2019082820190816
340004024 0 016224 880 736int16gcc_-funroll-loops_-O2_-fomit-frame-pointer2019082820190816
340004024 0 016801 888 752int16gcc_-funroll-loops_-O3_-fomit-frame-pointer2019082820190816
340003960 0 016208 880 736int16gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
340003960 0 016665 888 752int16gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
341602260 0 012216 880 736int16gcc_-O2_-fomit-frame-pointer2019082820190816
356003856 0 015057 888 752int16gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
357602212 0 012112 880 736int16gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
364003204 0 015921 888 752portablegcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
368803204 0 015464 880 736portablegcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
378404012 0 017544 880 736int16gcc_-funroll-loops_-O_-fomit-frame-pointer2019082820190816
378404012 0 017544 880 736int16gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
379202236 0 012408 880 736int16gcc_-O_-fomit-frame-pointer2019082820190816
379202236 0 012408 880 736int16gcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
389602500 0 013713 888 752portablegcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
390402036 0 011936 880 736portablegcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
392002560 0 013785 888 752portablegcc_-O3_-fomit-frame-pointer2019082820190816
394402084 0 012040 880 736portablegcc_-O2_-fomit-frame-pointer2019082820190816
660801452 0 010880 864 728portablegcc_-funroll-loops_-Os_-fomit-frame-pointer2019082820190816
660801452 0 010880 864 728portablegcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
672001388 0 010744 864 728portablegcc_-Os_-fomit-frame-pointer2019082820190816
672001388 0 010744 864 728portablegcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
750401404 0 012641 888 752refgcc_-O3_-fomit-frame-pointer2019082820190816
755201404 0 012625 888 752refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
756802624 0 015337 888 752refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082820190816
757602660 0 016208 880 736portablegcc_-funroll-loops_-O_-fomit-frame-pointer2019082820190816
757602660 0 016208 880 736portablegcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
762401564 0 011752 880 736portablegcc_-O_-fomit-frame-pointer2019082820190816
762401564 0 011752 880 736portablegcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
768002040 0 014518 800 760refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082820190816
768802620 0 015409 888 752refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019082820190816
780002628 0 014872 880 736refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
793602624 0 014824 880 736refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019082820190816
816001292 0 011248 880 736refgcc_-O2_-fomit-frame-pointer2019082820190816
820801292 0 011192 880 736refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082820190816
833602100 0 014662 800 760refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082820190816
853602096 0 014622 800 760refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082820190816
854402096 0 014622 800 760refclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019082820190816
854402096 0 014622 800 760refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082820190816
917601056 0 010384 864 728refgcc_-Os_-fomit-frame-pointer2019082820190816
917601056 0 010384 864 728refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
917601056 0 010448 864 728refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019082820190816
917601056 0 010448 864 728refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082820190816
1042401996 0 015528 880 736refgcc_-funroll-loops_-O_-fomit-frame-pointer2019082820190816
1042401996 0 015528 880 736refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
1052801136 0 011312 880 736refgcc_-O_-fomit-frame-pointer2019082820190816
1052801136 0 011312 880 736refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082820190816
1771206084 0 018552 864 736int16cc2019082820190816
1771206084 0 018552 864 736int16gcc2019082820190816
1772006084 0 018552 864 736int16gcc_-funroll-loops2019082820190816
2525602860 0 015336 864 736portablecc2019082820190816
2525602860 0 015336 864 736portablegcc2019082820190816
2525602860 0 015336 864 736portablegcc_-funroll-loops2019082820190816
3708002756 0 015208 864 736refcc2019082820190816
3708002756 0 015208 864 736refgcc2019082820190816
3708002756 0 015208 864 736refgcc_-funroll-loops2019082820190816

Compiler output

Implementation: crypto_decode/653x4621/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/653x4621/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