Implementation notes: aarch64, hikey960, crypto_kem/lotus128

Computer: hikey960
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_kem
Primitive: lotus128

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1123826	24896 0 8	41831 880 1584	`opt`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
1381950	66437 0 8	83894 976 1600	`opt`	`gcc_-O3_-fomit-frame-pointer`	20191209	20190816
1465200	54493 0 8	73598 976 1600	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191209	20190816
1486191	49825 0 8	67262 976 1600	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191209	20190816
1936494	78433 0 8	97518 976 1600	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191209	20190816
2149686	30037 0 8	48902 976 1568	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191209	20190816
2289375	54289 0 8	73366 976 1600	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191209	20190816
2371761	22949 0 8	41774 976 1568	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191209	20190816
2414250	15480 0 8	32415 880 1584	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
2452007	15480 0 8	32415 880 1584	`ref`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
2578581	49857 0 8	67326 976 1600	`ref`	`gcc_-O3_-fomit-frame-pointer`	20191209	20190816
2830500	24896 0 8	41831 880 1584	`opt`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
3449435	15480 0 8	32415 880 1584	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
3482528	6505 0 8	21666 960 1568	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191209	20190816
3531286	16380 0 8	33295 880 1584	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
3554775	78753 0 8	97862 976 1600	`opt`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191209	20190816
3771225	66345 0 8	83782 976 1600	`opt`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191209	20190816
3796656	68561 0 8	86014 976 1600	`opt`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20191209	20190816
4012650	30201 0 8	49022 976 1568	`opt`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191209	20190816
4062600	26241 0 8	45326 976 1568	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191209	20190816
4212450	47765 0 8	65214 976 1600	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20191209	20190816
4778550	22061 0 8	41150 976 1568	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191209	20190816
4799939	22061 0 8	41150 976 1568	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191209	20190816
4904014	22825 0 8	41694 976 1568	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191209	20190816
5752575	24896 0 8	41831 880 1584	`opt`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
5885775	8893 0 8	28822 976 1568	`opt`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20191209	20190816
5919075	8857 0 8	24654 976 1568	`opt`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191209	20190816
5969025	8525 0 8	24414 976 1568	`opt`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20191209	20190816
6044676	25796 0 8	42711 880 1584	`opt`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
6168825	8157 0 8	23298 960 1568	`opt`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20191209	20190816
6172246	8209 0 8	23370 960 1568	`opt`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191209	20190816
6501825	6505 0 8	21666 960 1568	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191209	20190816
6568425	6949 0 8	26878 976 1568	`ref`	`gcc_-O2_-fomit-frame-pointer`	20191209	20190816
6752386	6989 0 8	26918 976 1568	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20191209	20190816
6768225	6817 0 8	22702 976 1568	`ref`	`gcc_-O_-fomit-frame-pointer`	20191209	20190816
7035470	6441 0 8	21586 960 1568	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191209	20190816
7230762	26241 0 8	45326 976 1568	`opt`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191209	20190816
7497252	8889 0 8	28822 976 1568	`opt`	`gcc_-O2_-fomit-frame-pointer`	20191209	20190816
7941402	8137 0 8	23282 960 1568	`opt`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191209	20190816
8305605	8513 0 8	24398 976 1568	`opt`	`gcc_-O_-fomit-frame-pointer`	20191209	20190816
8660925	6501 0 8	21642 960 1568	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20191209	20190816
14370676	8209 0 8	23370 960 1568	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191209	20190816
14893425	8137 0 8	23282 960 1568	`opt`	`gcc_-Os_-fomit-frame-pointer`	20191209	20190816
15498849	8513 0 8	24398 976 1568	`opt`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191209	20190816
15742575	6441 0 8	21586 960 1568	`ref`	`gcc_-Os_-fomit-frame-pointer`	20191209	20190816
16133850	6917 0 8	22710 976 1568	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191209	20190816
18375482	6817 0 8	22702 976 1568	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191209	20190816
19180800	6833 0 8	22726 976 1568	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20191209	20190816
30369600	22272 0 8	41210 960 1568	`opt`	`gcc_-funroll-loops`	20191209	20190816
38610286	22272 0 8	41210 960 1568	`opt`	`gcc`	20191209	20190816
42621180	22272 0 8	41210 960 1568	`opt`	`cc`	20191209	20190816
42621180	16676 0 8	35618 960 1568	`ref`	`cc`	20191209	20190816
145896498	16676 0 8	35618 960 1568	`ref`	`gcc_-funroll-loops`	20191209	20190816
182433920	16676 0 8	35618 960 1568	`ref`	`gcc`	20191209	20190816

Compiler output

Implementation: avx2
Security model: unknown
Compiler: cc

lwe-arithmetics_avx2.c: lwe-arithmetics_avx2.c:10:23: fatal error: immintrin.h: No such file or directory
lwe-arithmetics_avx2.c: #include <immintrin.h>
lwe-arithmetics_avx2.c: ^
lwe-arithmetics_avx2.c: compilation terminated.

Number of similar (compiler,implementation) pairs: 23, namely:

Compiler	Implementations
cc	avx2
gcc	avx2
gcc -O2 -fomit-frame-pointer	avx2
gcc -O3 -fomit-frame-pointer	avx2
gcc -O -fomit-frame-pointer	avx2
gcc -Os -fomit-frame-pointer	avx2
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	avx2
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	avx2
gcc -fno-schedule-insns -O -fomit-frame-pointer	avx2
gcc -fno-schedule-insns -Os -fomit-frame-pointer	avx2
gcc -funroll-loops	avx2
gcc -funroll-loops -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -O -fomit-frame-pointer	avx2
gcc -funroll-loops -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	avx2
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	avx2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

lwe-arithmetics_avx2.c: In file included from lwe-arithmetics_avx2.c:10:
lwe-arithmetics_avx2.c: In file included from /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/immintrin.h:27:
lwe-arithmetics_avx2.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/mmintrin.h:45:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/mmintrin.h:69:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/mmintrin.h:75:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/mmintrin.h:81:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_packuswb((__v4hi)__m1, (__v4hi)__m2);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/mmintrin.h:87:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/mmintrin.h:93:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/mmintrin.h:99:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_punpckhdq((__v2si)__m1, (__v2si)__m2);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/mmintrin.h:105:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_punpcklbw((__v8qi)__m1, (__v8qi)__m2);
lwe-arithmetics_avx2.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	avx2
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	avx2
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	avx2
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	avx2