Implementation notes: amd64, shoe, crypto_aead/tiaoxinv1

Computer: shoe
Microarchitecture: amd64; Broadwell+AES (306d4)
Architecture: amd64
CPU ID: GenuineIntel-000306d4-bfebfbff
SUPERCOP version: 20240716
Operation: crypto_aead
Primitive: tiaoxinv1

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
2058	10212 0 0	32696 780 1080	`T:aesnim`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2059	10228 0 0	30936 780 1080	`T:aesnim`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2116	10222 0 0	30576 780 1080	`T:aesnim`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2146	6781 0 0	25515 756 1048	`T:aesnim`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2157	9779 0 0	29222 804 1016	`T:aesnim`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2158	9884 0 0	32816 812 1048	`T:aesnim`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2167	9868 0 0	32704 812 1048	`T:aesnim`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2203	9901 0 0	29542 804 1016	`T:aesnim`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2636	10477 0 0	32977 788 1080	`T:opt`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2717	9685 0 0	30449 788 1080	`T:opt`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2730	10560 0 0	30977 788 1080	`T:opt`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2818	7077 0 0	25892 764 1048	`T:opt`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2830	10659 0 0	30083 812 1016	`T:opt`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2891	10182 0 0	29915 812 1016	`T:opt`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
31619	33854 32 0	47944 820 1080	`T:table`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
36433	51975 32 0	66336 820 1080	`T:table`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
40640	53652 32 0	69736 820 1080	`T:table`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
47968	38253 32 0	51123 796 1048	`T:table`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
56536	57279 32 0	73576 852 1016	`T:table`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
56950	56398 32 0	69782 844 1016	`T:table`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
57788	58604 32 0	75384 852 1048	`T:table`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
58465	58529 32 0	75528 852 1048	`T:table`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
58716	57828 32 0	71630 844 1016	`T:table`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2292228	11125 320 0	33600 1108 1080	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
3670561	7552 320 0	28272 1108 1080	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
3853113	5251 304 0	24670 1116 1016	`T:ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
4122475	5979 304 0	25686 1116 1016	`T:ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
4175338	6027 320 0	26376 1108 1080	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
13150262	4718 320 0	23475 1084 1048	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625

Test failure

error 111
crypto_aead_encrypt is nondeterministic

Number of similar (implementation,compiler) pairs: 5, namely:

Implementation	Compiler
`T:opt`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`T:opt`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`T:ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`T:ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`T:ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

Compiler output

tiaoxin-optimized.c: tiaoxin-optimized.c:126:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'ssse3'
tiaoxin-optimized.c:         W0 = _mm_shuffle_epi8( W0 , perm  );
tiaoxin-optimized.c:              ^
tiaoxin-optimized.c: tiaoxin-optimized.c:127:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'ssse3'
tiaoxin-optimized.c:         W1 = _mm_shuffle_epi8( W1 , perm  );
tiaoxin-optimized.c:              ^
tiaoxin-optimized.c: tiaoxin-optimized.c:137:2: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'aes'
tiaoxin-optimized.c:         UPDATE( T3 , T4 , T6, Z0 , Z1 , Z0 );
tiaoxin-optimized.c:         ^
tiaoxin-optimized.c: tiaoxin-optimized.c:47:46: note: expanded from macro 'UPDATE'
tiaoxin-optimized.c: #define UPDATE( T3 , T4 , T6 , M0 , M1 , M2 )\
tiaoxin-optimized.c:                                              ^
tiaoxin-optimized.c: tiaoxin-optimized.c:40:41: note: expanded from macro '\
tiaoxin-optimized.c: RT3'
tiaoxin-optimized.c: #define RT3( T , M ) tmp  = T[0];T[0] = enc(T[2],M);T[2] = T[1];T[1] = enc(tmp,Z0);T[0] = xor(T[0], tmp);
tiaoxin-optimized.c:                                         ^
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: note: expanded from macro 'enc'
tiaoxin-optimized.c: #define enc(a,b)        _mm_aesenc_si128(a,b)
tiaoxin-optimized.c:                         ^
tiaoxin-optimized.c: tiaoxin-optimized.c:137:2: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'aes'
tiaoxin-optimized.c: tiaoxin-optimized.c:47:46: note: expanded from macro 'UPDATE'
tiaoxin-optimized.c: #define UPDATE( T3 , T4 , T6 , M0 , M1 , M2 )\
tiaoxin-optimized.c:                                              ^
tiaoxin-optimized.c: tiaoxin-optimized.c:40:72: note: expanded from macro '\
tiaoxin-optimized.c: RT3'
tiaoxin-optimized.c: ...

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

Implementation	Compiler
`T:aesnim`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

Compiler output

tiaoxin-optimized.c: tiaoxin-optimized.c:129:2: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'aes'
tiaoxin-optimized.c:         UPDATE( T3 , T4 , T6, Z0 , Z1 , Z0 );
tiaoxin-optimized.c:         ^
tiaoxin-optimized.c: tiaoxin-optimized.c:46:46: note: expanded from macro 'UPDATE'
tiaoxin-optimized.c: #define UPDATE( T3 , T4 , T6 , M0 , M1 , M2 )\
tiaoxin-optimized.c:                                              ^
tiaoxin-optimized.c: tiaoxin-optimized.c:39:41: note: expanded from macro '\
tiaoxin-optimized.c: RT3'
tiaoxin-optimized.c: #define RT3( T , M ) tmp  = T[0];T[0] = enc(T[2],tmp);T[0] = xor(T[0], M);T[2] = T[1];T[1] = enc(tmp,Z0);
tiaoxin-optimized.c:                                         ^
tiaoxin-optimized.c: tiaoxin-optimized.c:29:19: note: expanded from macro 'enc'
tiaoxin-optimized.c: #define enc(a,b)        _mm_aesenc_si128(a,b)
tiaoxin-optimized.c:                         ^
tiaoxin-optimized.c: tiaoxin-optimized.c:129:2: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'aes'
tiaoxin-optimized.c: tiaoxin-optimized.c:46:46: note: expanded from macro 'UPDATE'
tiaoxin-optimized.c: #define UPDATE( T3 , T4 , T6 , M0 , M1 , M2 )\
tiaoxin-optimized.c:                                              ^
tiaoxin-optimized.c: tiaoxin-optimized.c:39:94: note: expanded from macro '\
tiaoxin-optimized.c: RT3'
tiaoxin-optimized.c: #define RT3( T , M ) tmp  = T[0];T[0] = enc(T[2],tmp);T[0] = xor(T[0], M);T[2] = T[1];T[1] = enc(tmp,Z0);
tiaoxin-optimized.c:                                                                                              ^
tiaoxin-optimized.c: tiaoxin-optimized.c:29:19: note: expanded from macro 'enc'
tiaoxin-optimized.c: #define enc(a,b)        _mm_aesenc_si128(a,b)
tiaoxin-optimized.c:                         ^
tiaoxin-optimized.c: tiaoxin-optimized.c:129:2: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'aes'
tiaoxin-optimized.c: ...

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

Implementation	Compiler
`T:opt`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`