Implementation notes: aarch64, rockpi4, crypto_kem/lotus192

Computer: rockpi4
Architecture: aarch64
CPU ID: unknown CPU ID
SUPERCOP version: 20190816
Operation: crypto_kem
Primitive: lotus192

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1696191	36133 0 8	54622 952 1584	`opt`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20191213	20190816
1727579	35733 0 8	54110 952 1584	`opt`	`gcc_-O3_-fomit-frame-pointer`	20191213	20190816
1769705	35513 0 8	53870 952 1584	`opt`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191213	20190816
2641548	37248 0 8	56543 864 1600	`opt`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20191213	20190816
2674588	37532 0 8	56895 864 1600	`opt`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191213	20190816
2727039	26661 0 8	44958 952 1584	`ref`	`gcc_-O3_-fomit-frame-pointer`	20191213	20190816
2731169	45829 0 8	65526 952 1584	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191213	20190816
2735299	31257 0 8	50910 952 1584	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191213	20190816
2834419	26365 0 8	44638 952 1584	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191213	20190816
2987642	37524 0 8	56831 864 1600	`opt`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191213	20190816
2993837	37532 0 8	56895 864 1600	`opt`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191213	20190816
3360581	22752 0 8	42047 864 1600	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20191213	20190816
3423770	31021 0 8	50646 952 1584	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191213	20190816
3668679	22852 0 8	42159 864 1600	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191213	20190816
3674048	22860 0 8	42223 864 1600	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191213	20190816
3690568	22860 0 8	42223 864 1600	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191213	20190816
3714935	22860 0 8	42223 864 1600	`ref`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191213	20190816
4310894	46113 0 8	65854 952 1584	`opt`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191213	20190816
5819996	29397 0 8	49830 952 1568	`opt`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191213	20190816
5880707	26929 0 8	45342 952 1584	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20191213	20190816
6375481	23353 0 8	43718 952 1568	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191213	20190816
6592719	11313 0 8	28470 952 1568	`opt`	`gcc_-O2_-fomit-frame-pointer`	20191213	20190816
6853322	10773 0 8	27982 952 1568	`opt`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191213	20190816
7634305	37532 0 8	56895 864 1600	`opt`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191213	20190816
7736316	10173 0 8	26510 936 1568	`opt`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191213	20190816
7776790	10173 0 8	26510 936 1568	`opt`	`gcc_-Os_-fomit-frame-pointer`	20191213	20190816
7987007	23353 0 8	43718 952 1568	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191213	20190816
8086127	10277 0 8	26662 936 1568	`opt`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191213	20190816
8091083	23917 0 8	43126 952 1568	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191213	20190816
8687868	8309 0 8	25446 952 1568	`ref`	`gcc_-O_-fomit-frame-pointer`	20191213	20190816
9077327	10277 0 8	26662 936 1568	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191213	20190816
9425486	7849 0 8	24110 936 1568	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20191213	20190816
9539061	7829 0 8	24094 936 1568	`ref`	`gcc_-Os_-fomit-frame-pointer`	20191213	20190816
9873591	7921 0 8	24238 936 1568	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191213	20190816
9878547	8513 0 8	25542 952 1568	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191213	20190816
10598819	7829 0 8	24094 936 1568	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191213	20190816
13463800	32629 0 8	51854 952 1568	`opt`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191213	20190816
13543509	32513 0 8	51798 952 1568	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191213	20190816
18050991	24009 0 8	43126 952 1568	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191213	20190816
20360074	29397 0 8	49830 952 1568	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191213	20190816
23244466	11417 0 8	28710 952 1568	`opt`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20191213	20190816
23292787	10193 0 8	26526 936 1568	`opt`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20191213	20190816
23773932	8545 0 8	25614 952 1568	`ref`	`gcc_-O2_-fomit-frame-pointer`	20191213	20190816
23775171	8621 0 8	25822 952 1568	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20191213	20190816
23894941	7921 0 8	24238 936 1568	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191213	20190816
24160087	11281 0 8	28398 952 1568	`opt`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191213	20190816
24718463	10745 0 8	27966 952 1568	`opt`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20191213	20190816
24753155	10773 0 8	27982 952 1568	`opt`	`gcc_-O_-fomit-frame-pointer`	20191213	20190816
26414241	8309 0 8	25446 952 1568	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191213	20190816
27071737	8321 0 8	25462 952 1568	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20191213	20190816
55196624	17968 0 8	38062 936 1568	`ref`	`cc`	20191213	20190816
59546753	23972 0 8	44150 936 1568	`opt`	`cc`	20191213	20190816
151494182	23972 0 8	44150 936 1568	`opt`	`gcc`	20191213	20190816
151637493	23972 0 8	44150 936 1568	`opt`	`gcc_-funroll-loops`	20191213	20190816
168380926	17968 0 8	38062 936 1568	`ref`	`gcc_-funroll-loops`	20191213	20190816
168431312	17968 0 8	38062 936 1568	`ref`	`gcc`	20191213	20190816

Compiler output

Implementation: avx2
Security model: unknown
Compiler: cc

lwe-arithmetics_avx2.c: lwe-arithmetics_avx2.c:10:10: 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-7/lib/clang/7.0.1/include/immintrin.h:28:
lwe-arithmetics_avx2.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
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.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
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.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
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.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
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_packuswb((__v4hi)__m1, (__v4hi)__m2);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.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
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.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
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.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
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_punpckhdq((__v2si)__m1, (__v2si)__m2);
lwe-arithmetics_avx2.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lwe-arithmetics_avx2.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
lwe-arithmetics_avx2.c: return (__m64)__builtin_ia32_punpcklbw((__v8qi)__m1, (__v8qi)__m2);
lwe-arithmetics_avx2.c: ...

Number of similar (compiler,implementation) pairs: 5, 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
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2