Implementation notes: aarch64, hikey960, crypto_kem/ntskem1264

Computer: hikey960
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_kem
Primitive: ntskem1264

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
479682	54781 6228 16	71138 7088 1600	`opt`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191210	20190816
732600	60932 6228 16	78169 7192 1616	`opt`	`gcc_-O3_-fomit-frame-pointer`	20191210	20190816
763938	54781 6228 16	71138 7088 1600	`opt`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191210	20190816
765900	40360 6228 16	55953 7184 1584	`opt`	`gcc_-O2_-fomit-frame-pointer`	20191210	20190816
772821	81144 6228 16	100001 7192 1616	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191210	20190816
874125	59917 6228 16	76258 7088 1600	`opt`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191210	20190816
907425	54781 6228 16	71138 7088 1600	`opt`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191210	20190816
949050	37949 6228 16	52876 7168 1584	`opt`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191210	20190816
951017	59504 6228 16	78145 7184 1584	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191210	20190816
957375	37861 6228 16	52772 7168 1584	`opt`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20191210	20190816
1110835	40264 6228 16	55865 7184 1584	`opt`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20191210	20190816
1140525	37949 6228 16	52876 7168 1584	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191210	20190816
1332000	62088 6228 16	79289 7192 1616	`opt`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191210	20190816
1469539	59144 6228 16	77745 7184 1584	`opt`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191210	20190816
1573425	62984 6228 16	80193 7192 1616	`opt`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20191210	20190816
1673325	80344 6228 16	99209 7192 1616	`opt`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191210	20190816
1892079	40776 6228 16	56329 7184 1584	`opt`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191210	20190816
2422575	41460 6228 16	57113 7184 1584	`opt`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20191210	20190816
2497800	37861 6228 16	52772 7168 1584	`opt`	`gcc_-Os_-fomit-frame-pointer`	20191210	20190816
2514452	59680 6228 16	78529 7184 1584	`opt`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191210	20190816
2593549	41344 6228 16	56993 7184 1584	`opt`	`gcc_-O_-fomit-frame-pointer`	20191210	20190816
3602462	36572 76 16	53737 1032 1616	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191210	20190816
3846339	24097 76 16	40522 936 1600	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191210	20190816
3970701	34364 76 16	52969 1032 1584	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191210	20190816
4059988	32400 76 16	51225 1032 1584	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191210	20190816
4352670	19144 76 16	34769 1032 1584	`ref`	`gcc_-O_-fomit-frame-pointer`	20191210	20190816
4361553	19180 76 16	34809 1032 1584	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20191210	20190816
4545450	493164 6228 16	511821 7168 1584	`opt`	`gcc_-funroll-loops`	20191210	20190816
4725951	59680 6228 16	78529 7184 1584	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191210	20190816
4761900	41344 6228 16	56993 7184 1584	`opt`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191210	20190816
4845150	37861 6228 16	52772 7168 1584	`opt`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191210	20190816
5472324	493164 6228 16	511821 7168 1584	`opt`	`gcc`	20191210	20190816
7151175	29113 76 16	45530 936 1600	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191210	20190816
7334325	24097 76 16	40522 936 1600	`ref`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191210	20190816
7434225	34568 76 16	53137 1032 1584	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191210	20190816
7568334	19480 76 16	35057 1032 1584	`ref`	`gcc_-O2_-fomit-frame-pointer`	20191210	20190816
7593312	32400 76 16	51225 1032 1584	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191210	20190816
7780163	36616 76 16	53817 1032 1616	`ref`	`gcc_-O3_-fomit-frame-pointer`	20191210	20190816
8458200	16857 76 16	31764 1016 1584	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191210	20190816
8549775	16821 76 16	31708 1016 1584	`ref`	`gcc_-Os_-fomit-frame-pointer`	20191210	20190816
8707950	16821 76 16	31708 1016 1584	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191210	20190816
9225777	19392 76 16	34929 1032 1584	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191210	20190816
10184603	53924 76 16	72737 1032 1616	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191210	20190816
10242099	19144 76 16	34769 1032 1584	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191210	20190816
10712898	16805 76 16	31692 1016 1584	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20191210	20190816
13394925	54108 76 16	72953 1032 1616	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191210	20190816
14893425	38664 76 16	55833 1032 1616	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20191210	20190816
15151500	24097 76 16	40522 936 1600	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191210	20190816
15903002	19496 76 16	35073 1032 1584	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20191210	20190816
17524125	16857 76 16	31764 1016 1584	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191210	20190816
30916292	493164 6228 16	511821 7168 1584	`opt`	`cc`	20191210	20190816
54281357	36600 76 16	55237 1016 1584	`ref`	`gcc`	20191210	20190816
61314680	36600 76 16	55237 1016 1584	`ref`	`cc`	20191210	20190816
107188924	36600 76 16	55237 1016 1584	`ref`	`gcc_-funroll-loops`	20191210	20190816

Compiler output

Implementation: avx2
Security model: unknown
Compiler: cc

bitslice_bma_128.c: In file included from bitslice_bma_128.c:17:0:
bitslice_bma_128.c: bitslice_bma_128.h:18:23: fatal error: immintrin.h: No such file or directory
bitslice_bma_128.c: #include <immintrin.h>
bitslice_bma_128.c: ^
bitslice_bma_128.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

bitslice_bma_128.c: In file included from bitslice_bma_128.c:17:
bitslice_bma_128.c: In file included from ./bitslice_bma_128.h:18:
bitslice_bma_128.c: In file included from /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/immintrin.h:27:
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_packuswb((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhdq((__v2si)__m1, (__v2si)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.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

Compiler output

Implementation: sse2
Security model: unknown
Compiler: cc

bitslice_bma_128.c: In file included from bitslice_bma_128.c:18:0:
bitslice_bma_128.c: bitslice_bma_128.h:18:23: fatal error: immintrin.h: No such file or directory
bitslice_bma_128.c: #include <immintrin.h>
bitslice_bma_128.c: ^
bitslice_bma_128.c: compilation terminated.

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

Compiler	Implementations
cc	sse2
gcc	sse2
gcc -O2 -fomit-frame-pointer	sse2
gcc -O3 -fomit-frame-pointer	sse2
gcc -O -fomit-frame-pointer	sse2
gcc -Os -fomit-frame-pointer	sse2
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	sse2
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	sse2
gcc -fno-schedule-insns -O -fomit-frame-pointer	sse2
gcc -fno-schedule-insns -Os -fomit-frame-pointer	sse2
gcc -funroll-loops	sse2
gcc -funroll-loops -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -O -fomit-frame-pointer	sse2
gcc -funroll-loops -Os -fomit-frame-pointer	sse2
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	sse2
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	sse2
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	sse2
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	sse2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	sse2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	sse2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	sse2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	sse2

Compiler output

Implementation: sse2
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

bitslice_bma_128.c: In file included from bitslice_bma_128.c:18:
bitslice_bma_128.c: In file included from ./bitslice_bma_128.h:18:
bitslice_bma_128.c: In file included from /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/immintrin.h:27:
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_packuswb((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhdq((__v2si)__m1, (__v2si)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: ...

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

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	sse2
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	sse2
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	sse2
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	sse2