Implementation notes: aarch64, hikey960, crypto_kem/lotus192

Computer: hikey960
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_kem
Primitive: lotus192

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1447929	49345 0 8	66790 976 1600	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191209	20190816
1794366	24920 0 8	41855 880 1584	`opt`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
2078622	15880 0 8	32815 880 1584	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
2156175	69637 0 8	87094 976 1600	`opt`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20191209	20190816
2197800	67401 0 8	84862 976 1600	`opt`	`gcc_-O3_-fomit-frame-pointer`	20191209	20190816
2510289	55541 0 8	74646 976 1600	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191209	20190816
2584953	15880 0 8	32815 880 1584	`ref`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
2647350	49405 0 8	66870 976 1600	`ref`	`gcc_-O3_-fomit-frame-pointer`	20191209	20190816
2990960	81013 0 8	100126 976 1600	`opt`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191209	20190816
3110338	67289 0 8	84734 976 1600	`opt`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191209	20190816
3158262	16780 0 8	33695 880 1584	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
3321675	24920 0 8	41855 880 1584	`opt`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
3404925	24920 0 8	41855 880 1584	`opt`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
3549158	55325 0 8	74398 976 1600	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191209	20190816
3729059	22773 0 8	41598 976 1568	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191209	20190816
5337063	6521 0 8	21682 960 1568	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191209	20190816
5701940	80685 0 8	99766 976 1600	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191209	20190816
7500825	21961 0 8	41046 976 1568	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191209	20190816
8839908	30917 0 8	49742 976 1568	`opt`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191209	20190816
9179415	25820 0 8	42735 880 1584	`opt`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
9277098	9185 0 8	29118 976 1568	`opt`	`gcc_-O2_-fomit-frame-pointer`	20191209	20190816
9407250	8769 0 8	24654 976 1568	`opt`	`gcc_-O_-fomit-frame-pointer`	20191209	20190816
9573750	8401 0 8	23546 960 1568	`opt`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191209	20190816
9715275	8457 0 8	23618 960 1568	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191209	20190816
9730756	8401 0 8	23546 960 1568	`opt`	`gcc_-Os_-fomit-frame-pointer`	20191209	20190816
9780183	22657 0 8	41526 976 1568	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191209	20190816
10032830	15880 0 8	32815 880 1584	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191209	20190816
10064925	8421 0 8	23562 960 1568	`opt`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20191209	20190816
10209386	6473 0 8	21618 960 1568	`ref`	`gcc_-Os_-fomit-frame-pointer`	20191209	20190816
10468360	27109 0 8	46198 976 1568	`opt`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191209	20190816
10692178	6801 0 8	22686 976 1568	`ref`	`gcc_-O_-fomit-frame-pointer`	20191209	20190816
10827963	6801 0 8	22686 976 1568	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191209	20190816
12739656	6521 0 8	21682 960 1568	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191209	20190816
12960297	6977 0 8	26910 976 1568	`ref`	`gcc_-O2_-fomit-frame-pointer`	20191209	20190816
13037695	9153 0 8	24950 976 1568	`opt`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191209	20190816
13166318	8777 0 8	24670 976 1568	`opt`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20191209	20190816
13621393	8769 0 8	24654 976 1568	`opt`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191209	20190816
13943438	6945 0 8	22742 976 1568	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191209	20190816
14465031	30769 0 8	49630 976 1568	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191209	20190816
15022409	7009 0 8	26942 976 1568	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20191209	20190816
15831889	48145 0 8	65606 976 1600	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20191209	20190816
15893476	6805 0 8	22694 976 1568	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20191209	20190816
21560177	27109 0 8	46198 976 1568	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191209	20190816
21988966	9189 0 8	29118 976 1568	`opt`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20191209	20190816
22552425	8457 0 8	23618 960 1568	`opt`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191209	20190816
24342300	21961 0 8	41046 976 1568	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191209	20190816
26714925	6473 0 8	21618 960 1568	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191209	20190816
26751438	6533 0 8	21674 960 1568	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20191209	20190816
48326625	22692 0 8	41634 960 1568	`opt`	`gcc_-funroll-loops`	20191209	20190816
51723225	22692 0 8	41634 960 1568	`opt`	`cc`	20191209	20190816
55203075	16724 0 8	35666 960 1568	`ref`	`cc`	20191209	20190816
55580213	16724 0 8	35666 960 1568	`ref`	`gcc_-funroll-loops`	20191209	20190816
72707074	22692 0 8	41634 960 1568	`opt`	`gcc`	20191209	20190816
78728969	16724 0 8	35666 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