Implementation notes: aarch64, supercoplxc, crypto_kem/ntskem1264

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

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1989680	76108 6228 16	95691 7168 1600	`opt`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191130	20190816
2196640	60340 6228 16	78619 7168 1600	`opt`	`gcc_-O3_-fomit-frame-pointer`	20191130	20190816
2232080	64720 6228 16	83851 7160 1576	`opt`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191130	20190816
2262720	44976 6228 16	62059 7160 1576	`opt`	`gcc_-O2_-fomit-frame-pointer`	20191130	20190816
2265520	75376 6228 16	94931 7168 1600	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191130	20190816
2350400	74677 6228 16	93302 7072 1600	`opt`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191130	20190816
2366000	80133 6228 16	98782 7072 1600	`opt`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20191130	20190816
2386800	74393 6228 16	93070 7072 1600	`opt`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191130	20190816
2388400	63736 6228 16	82947 7160 1576	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191130	20190816
2394480	59868 6228 16	78091 7168 1600	`opt`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191130	20190816
2434720	74393 6228 16	93070 7072 1600	`opt`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191130	20190816
2539200	44128 6228 16	61155 7160 1576	`opt`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191130	20190816
2719920	74393 6228 16	93070 7072 1600	`opt`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191130	20190816
2784720	41145 6228 16	57408 7144 1560	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191130	20190816
2839760	41145 6228 16	57408 7144 1560	`opt`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191130	20190816
3014400	41029 6228 16	57240 7144 1560	`opt`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191130	20190816
3146240	64348 6228 16	84667 7160 1576	`opt`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191130	20190816
3152160	64348 6228 16	84667 7160 1576	`opt`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191130	20190816
3228480	45572 6228 16	62675 7160 1576	`opt`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191130	20190816
3272000	41029 6228 16	57240 7144 1560	`opt`	`gcc_-Os_-fomit-frame-pointer`	20191130	20190816
16084800	32377 76 16	51246 920 1600	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20191130	20190816
16437600	37756 76 16	56843 1008 1576	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191130	20190816
16688960	50912 76 16	70499 1008 1600	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191130	20190816
16696240	35992 76 16	54235 1008 1600	`ref`	`gcc_-O3_-fomit-frame-pointer`	20191130	20190816
16743200	50452 76 16	70027 1008 1600	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191130	20190816
16894160	32609 76 16	51502 920 1600	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191130	20190816
16930080	32609 76 16	51502 920 1600	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191130	20190816
16990160	32953 76 16	51798 920 1600	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191130	20190816
17096320	32609 76 16	51502 920 1600	`ref`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191130	20190816
17623200	37528 76 16	56699 1008 1576	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191130	20190816
19047200	23304 76 16	40355 1008 1576	`ref`	`gcc_-O2_-fomit-frame-pointer`	20191130	20190816
19206400	35724 76 16	53923 1008 1600	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191130	20190816
21466960	35192 76 16	55491 1008 1576	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191130	20190816
21581040	35192 76 16	55491 1008 1576	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191130	20190816
21747120	23244 76 16	40243 1008 1576	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191130	20190816
22516400	19957 76 16	36192 992 1560	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191130	20190816
22792960	19957 76 16	36192 992 1560	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191130	20190816
23696720	19853 76 16	36040 992 1560	`ref`	`gcc_-Os_-fomit-frame-pointer`	20191130	20190816
23804240	19853 76 16	36040 992 1560	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191130	20190816
24641120	23020 76 16	40075 1008 1576	`ref`	`gcc_-O_-fomit-frame-pointer`	20191130	20190816
24729920	23020 76 16	40075 1008 1576	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191130	20190816
92696720	39452 76 16	59627 992 1576	`ref`	`cc`	20191130	20190816
93129840	39452 76 16	59627 992 1576	`ref`	`gcc_-funroll-loops`	20191130	20190816
93251200	39452 76 16	59627 992 1576	`ref`	`gcc`	20191130	20190816

Test failure

Implementation: opt
Security model: unknown
Compiler: gcc -O -fomit-frame-pointer

error 111
crypto_kem_keypair returns nonzero

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
gcc -O -fomit-frame-pointer	opt

Compiler output

Implementation: avx2
Security model: unknown
Compiler: cc

bitslice_bma_128.c: In file included from bitslice_bma_128.c:17:
bitslice_bma_128.c: bitslice_bma_128.h:18:10: 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: 19, 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

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-7/lib/clang/7.0.1/include/immintrin.h:28:
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_packuswb((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhdq((__v2si)__m1, (__v2si)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.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

Compiler output

Implementation: opt
Security model: unknown
Compiler: cc

keccak.c: cc: fatal error: Killed signal terminated program cc1
keccak.c: compilation terminated.

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
cc	opt

Compiler output

Implementation: opt
Security model: unknown
Compiler: gcc

keccak.c: gcc: fatal error: Killed signal terminated program cc1
keccak.c: compilation terminated.

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
gcc	opt
gcc -funroll-loops	opt

Compiler output

Implementation: sse2
Security model: unknown
Compiler: cc

bitslice_bma_128.c: In file included from bitslice_bma_128.c:18:
bitslice_bma_128.c: bitslice_bma_128.h:18:10: 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: 19, 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

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-7/lib/clang/7.0.1/include/immintrin.h:28:
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_packuswb((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhdq((__v2si)__m1, (__v2si)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.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
bitslice_bma_128.c: ...

Number of similar (compiler,implementation) pairs: 5, 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
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	sse2