Implementation notes: aarch64, supercoplxc, crypto_aead/tiaoxinv1

Computer: supercoplxc
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_aead
Primitive: tiaoxinv1

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
95760	36212 32 0	51345 960 880	`table`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190925	20190816
98240	36272 32 0	50057 960 880	`table`	`gcc_-O3_-fomit-frame-pointer`	20190925	20190816
98240	36376 32 0	50985 952 864	`table`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190925	20190816
99040	36352 32 0	48921 952 864	`table`	`gcc_-O2_-fomit-frame-pointer`	20190925	20190816
100240	35672 32 0	50825 960 880	`table`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190925	20190816
102480	35204 32 0	49953 952 864	`table`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190925	20190816
128560	27760 32 0	39609 936 856	`table`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190925	20190816
128560	27760 32 0	39609 936 856	`table`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190925	20190816
138240	35624 32 0	49441 960 880	`table`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190925	20190816
139040	35200 32 0	47761 952 864	`table`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190925	20190816
149520	27944 32 0	40697 952 864	`table`	`gcc_-O_-fomit-frame-pointer`	20190925	20190816
149520	27944 32 0	40697 952 864	`table`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190925	20190816
149600	28796 32 0	44769 952 864	`table`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190925	20190816
149600	28796 32 0	44769 952 864	`table`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190925	20190816
160800	27760 32 0	39553 936 856	`table`	`gcc_-Os_-fomit-frame-pointer`	20190925	20190816
161600	27760 32 0	39553 936 856	`table`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190925	20190816
445280	65640 32 0	86713 936 864	`table`	`cc`	20190925	20190816
445280	65640 32 0	86713 936 864	`table`	`gcc`	20190925	20190816
445280	65640 32 0	86713 936 864	`table`	`gcc_-funroll-loops`	20190925	20190816
5093520	18008 304 0	35697 1224 864	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190925	20190816
5130320	17500 304 0	35337 1224 864	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190925	20190816
5401440	9920 304 0	28129 1232 880	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190925	20190816
5466560	9568 304 0	27809 1232 880	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190925	20190816
5587760	9492 304 0	26345 1232 880	`ref`	`gcc_-O3_-fomit-frame-pointer`	20190925	20190816
6153600	9136 304 0	26033 1232 880	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190925	20190816
6670000	8804 304 0	27817 1224 864	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190925	20190816
6781600	8804 304 0	27817 1224 864	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190925	20190816
11159440	6964 304 0	22609 1224 864	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190925	20190816
11189920	6972 304 0	22625 1224 864	`ref`	`gcc_-O2_-fomit-frame-pointer`	20190925	20190816
12126560	5032 304 0	20817 1224 864	`ref`	`gcc_-O_-fomit-frame-pointer`	20190925	20190816
12133200	5032 304 0	20817 1224 864	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190925	20190816
17777840	4200 304 0	18841 1208 856	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190925	20190816
17849600	4200 304 0	18841 1208 856	`ref`	`gcc_-Os_-fomit-frame-pointer`	20190925	20190816
18887840	4184 304 0	18873 1208 856	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190925	20190816
18890320	4184 304 0	18873 1208 856	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190925	20190816
45728480	6716 304 0	28857 1208 864	`ref`	`gcc`	20190925	20190816
45744720	6716 304 0	28857 1208 864	`ref`	`gcc_-funroll-loops`	20190925	20190816
46071840	6716 304 0	28857 1208 864	`ref`	`cc`	20190925	20190816

Test failure

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

error 111
crypto_aead_decrypt returns nonzero

Number of similar (compiler,implementation) pairs: 10, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	ref
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	ref
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	ref
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	ref
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref
clang -O3 -fomit-frame-pointer -Qunused-arguments	table
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	table
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	table
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	table
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	table

Compiler output

Implementation: aesnim
Security model: unknown
Compiler: cc

tiaoxin-optimized.c: tiaoxin-optimized.c:20:10: fatal error: xmmintrin.h: No such file or directory
tiaoxin-optimized.c: #include <xmmintrin.h>
tiaoxin-optimized.c: ^~~~~~~~~~~~~
tiaoxin-optimized.c: compilation terminated.

Number of similar (compiler,implementation) pairs: 38, namely:

Compiler	Implementations
cc	aesnim
gcc	aesnim
gcc -O2 -fomit-frame-pointer	aesnim
gcc -O3 -fomit-frame-pointer	aesnim
gcc -O -fomit-frame-pointer	aesnim
gcc -Os -fomit-frame-pointer	aesnim
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	aesnim
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	aesnim
gcc -fno-schedule-insns -O -fomit-frame-pointer	aesnim
gcc -fno-schedule-insns -Os -fomit-frame-pointer	aesnim
gcc -funroll-loops	aesnim
gcc -funroll-loops -O2 -fomit-frame-pointer	aesnim
gcc -funroll-loops -O3 -fomit-frame-pointer	aesnim
gcc -funroll-loops -O -fomit-frame-pointer	aesnim
gcc -funroll-loops -Os -fomit-frame-pointer	aesnim
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	aesnim
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	aesnim
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	aesnim
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	aesnim
cc	opt
gcc	opt
gcc -O2 -fomit-frame-pointer	opt
gcc -O3 -fomit-frame-pointer	opt
gcc -O -fomit-frame-pointer	opt
gcc -Os -fomit-frame-pointer	opt
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	opt
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	opt
gcc -fno-schedule-insns -O -fomit-frame-pointer	opt
gcc -fno-schedule-insns -Os -fomit-frame-pointer	opt
gcc -funroll-loops	opt
gcc -funroll-loops -O2 -fomit-frame-pointer	opt
gcc -funroll-loops -O3 -fomit-frame-pointer	opt
gcc -funroll-loops -O -fomit-frame-pointer	opt
gcc -funroll-loops -Os -fomit-frame-pointer	opt
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	opt
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	opt
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	opt
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	opt

Compiler output

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

tiaoxin-optimized.c: In file included from tiaoxin-optimized.c:20:
tiaoxin-optimized.c: In file included from /usr/lib/llvm-7/lib/clang/7.0.1/include/xmmintrin.h:27:
tiaoxin-optimized.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
tiaoxin-optimized.c: return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tiaoxin-optimized.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
tiaoxin-optimized.c: return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tiaoxin-optimized.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
tiaoxin-optimized.c: return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tiaoxin-optimized.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
tiaoxin-optimized.c: return (__m64)__builtin_ia32_packuswb((__v4hi)__m1, (__v4hi)__m2);
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tiaoxin-optimized.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
tiaoxin-optimized.c: return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tiaoxin-optimized.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
tiaoxin-optimized.c: return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tiaoxin-optimized.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
tiaoxin-optimized.c: return (__m64)__builtin_ia32_punpckhdq((__v2si)__m1, (__v2si)__m2);
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tiaoxin-optimized.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
tiaoxin-optimized.c: return (__m64)__builtin_ia32_punpcklbw((__v8qi)__m1, (__v8qi)__m2);
tiaoxin-optimized.c: ...

Number of similar (compiler,implementation) pairs: 10, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	aesnim
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	aesnim
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	aesnim
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	aesnim
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	aesnim
clang -O3 -fomit-frame-pointer -Qunused-arguments	opt
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	opt
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	opt
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	opt
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	opt