Implementation notes: aarch64, hikey960, crypto_kem/lotus256

Computer: hikey960
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_kem
Primitive: lotus256

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1696653	68777 0 8	86230 976 1600	`opt`	`gcc_-O3_-fomit-frame-pointer`	20191209	20190816
2569697	25860 0 8	42767 880 1584	`opt`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
2609675	81685 0 8	100758 976 1600	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191209	20190816
2656017	68661 0 8	86094 976 1600	`opt`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191209	20190816
3130576	70893 0 8	88342 976 1600	`opt`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20191209	20190816
4343787	16240 0 8	33143 880 1584	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
4803525	24960 0 8	41887 880 1584	`opt`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
4845150	24960 0 8	41887 880 1584	`opt`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
4870125	82045 0 8	101150 976 1600	`opt`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191209	20190816
4903425	24960 0 8	41887 880 1584	`opt`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
5114963	55833 0 8	74910 976 1600	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191209	20190816
5429329	56061 0 8	75166 976 1600	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191209	20190816
5469525	15340 0 8	32263 880 1584	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
5486175	15340 0 8	32263 880 1584	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
5552775	15340 0 8	32263 880 1584	`ref`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
6660779	49853 0 8	67318 976 1600	`ref`	`gcc_-O3_-fomit-frame-pointer`	20191209	20190816
7115283	22669 0 8	41534 976 1568	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191209	20190816
7186347	8965 0 8	28894 976 1568	`opt`	`gcc_-O2_-fomit-frame-pointer`	20191209	20190816
7248528	8585 0 8	24470 976 1568	`opt`	`gcc_-O_-fomit-frame-pointer`	20191209	20190816
7541667	8269 0 8	23434 960 1568	`opt`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191209	20190816
7837909	22793 0 8	41614 976 1568	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191209	20190816
9099225	30089 0 8	48910 976 1568	`opt`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191209	20190816
9377062	8933 0 8	24726 976 1568	`opt`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191209	20190816
9895451	49813 0 8	67246 976 1600	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191209	20190816
10647675	48497 0 8	65942 976 1600	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20191209	20190816
10951751	7021 0 8	26950 976 1568	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20191209	20190816
11236995	6469 0 8	21610 960 1568	`ref`	`gcc_-Os_-fomit-frame-pointer`	20191209	20190816
12587400	22001 0 8	41086 976 1568	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191209	20190816
13744575	8597 0 8	24486 976 1568	`opt`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20191209	20190816
14144175	8269 0 8	23434 960 1568	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191209	20190816
14310675	29917 0 8	48774 976 1568	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191209	20190816
16142175	6949 0 8	22742 976 1568	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191209	20190816
16366950	6841 0 8	22726 976 1568	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191209	20190816
17588340	26237 0 8	45326 976 1568	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191209	20190816
18245515	6533 0 8	21698 960 1568	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191209	20190816
18392101	8197 0 8	23338 960 1568	`opt`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191209	20190816
18620864	22001 0 8	41086 976 1568	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191209	20190816
19453770	8197 0 8	23338 960 1568	`opt`	`gcc_-Os_-fomit-frame-pointer`	20191209	20190816
20284393	26237 0 8	45326 976 1568	`opt`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191209	20190816
20354625	6533 0 8	21698 960 1568	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191209	20190816
22260798	6529 0 8	21674 960 1568	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20191209	20190816
22668975	6857 0 8	22750 976 1568	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20191209	20190816
22976245	6469 0 8	21610 960 1568	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191209	20190816
32176125	8969 0 8	28894 976 1568	`opt`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20191209	20190816
39032288	6981 0 8	26910 976 1568	`ref`	`gcc_-O2_-fomit-frame-pointer`	20191209	20190816
41192885	8217 0 8	23362 960 1568	`opt`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20191209	20190816
41875617	8585 0 8	24470 976 1568	`opt`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191209	20190816
53273911	6841 0 8	22726 976 1568	`ref`	`gcc_-O_-fomit-frame-pointer`	20191209	20190816
67723875	16656 0 8	35594 960 1568	`ref`	`gcc`	20191209	20190816
69646950	16656 0 8	35594 960 1568	`ref`	`gcc_-funroll-loops`	20191209	20190816
76831425	22368 0 8	41306 960 1568	`opt`	`gcc`	20191209	20190816
77352703	22368 0 8	41306 960 1568	`opt`	`cc`	20191209	20190816
245079973	16656 0 8	35594 960 1568	`ref`	`cc`	20191209	20190816
277089300	22368 0 8	41306 960 1568	`opt`	`gcc_-funroll-loops`	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