Implementation notes: x86, hydra1, crypto_aead/tiaoxinv2

Computer: hydra1
Architecture: x86
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: tiaoxinv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
65613	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161023	20161009
65712	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20161023	20161009
65742	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161023	20161009
66472	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20161023	20161009
66861	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161023	20161009
66869	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20161023	20161009
67077	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20161023	20161009
67227	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20161023	20161009
67309	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161023	20161009
67363	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20161023	20161009
67824	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20161023	20161009
67887	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20161023	20161009
68055	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20161023	20161009
68126	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20161023	20161009
68360	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20161023	20161009
68376	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20161023	20161009
68443	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20161023	20161009
68458	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20161023	20161009
68461	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20161023	20161009
68515	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20161023	20161009
68531	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161023	20161009
68549	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161023	20161009
68564	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20161023	20161009
68587	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20161023	20161009
68640	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161023	20161009
68715	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161023	20161009
68715	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161023	20161009
68730	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20161023	20161009
68781	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161023	20161009
68782	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20161023	20161009
68848	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161023	20161009
68877	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161023	20161009
68888	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20161023	20161009
68976	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161023	20161009
68984	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20161023	20161009
69072	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161023	20161009
69281	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161023	20161009
69459	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161023	20161009
69506	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161023	20161009
69520	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161023	20161009
69693	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161023	20161009
69702	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20161023	20161009
69832	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20161023	20161009
69930	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20161023	20161009
70094	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161023	20161009
70116	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161023	20161009
70235	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20161023	20161009
70357	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20161023	20161009
70382	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20161023	20161009
70421	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161023	20161009
70466	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161023	20161009
70477	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20161023	20161009
70490	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20161023	20161009
70496	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20161023	20161009
70517	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20161023	20161009
70526	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161023	20161009
70551	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161023	20161009
70573	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20161023	20161009
70584	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20161023	20161009
70590	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20161023	20161009
70674	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20161023	20161009
70693	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20161023	20161009
70710	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20161023	20161009
70713	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20161023	20161009
70726	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20161023	20161009
70773	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161023	20161009
70776	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20161023	20161009
70778	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20161023	20161009
70790	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20161023	20161009
70790	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20161023	20161009
70816	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161023	20161009
70840	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161023	20161009
70872	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161023	20161009
70879	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20161023	20161009
70921	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20161023	20161009
70942	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20161023	20161009
70958	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20161023	20161009
70965	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20161023	20161009
70974	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20161023	20161009
71007	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161023	20161009
71079	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20161023	20161009
71086	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20161023	20161009
71114	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20161023	20161009
71141	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161023	20161009
71150	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20161023	20161009
71166	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20161023	20161009
71166	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161023	20161009
71168	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161023	20161009
71258	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161023	20161009
71296	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161023	20161009
71302	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20161023	20161009
71320	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20161023	20161009
71355	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20161023	20161009
71381	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20161023	20161009
71632	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161023	20161009
71698	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20161023	20161009
71891	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161023	20161009
72020	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20161023	20161009
72096	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20161023	20161009
72216	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20161023	20161009
72436	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20161023	20161009
72499	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161023	20161009
72546	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161023	20161009
72602	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20161023	20161009
72784	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20161023	20161009
72851	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20161023	20161009
73035	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20161023	20161009
73166	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161023	20161009
73357	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20161023	20161009
73813	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161023	20161009
73946	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161023	20161009
73958	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20161023	20161009
74007	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20161023	20161009
74203	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20161023	20161009
74205	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161023	20161009
74285	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161023	20161009
74321	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161023	20161009
74337	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161023	20161009
74344	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161023	20161009
74363	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20161023	20161009
74368	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20161023	20161009
74394	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20161023	20161009
74422	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20161023	20161009
74425	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20161023	20161009
74571	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20161023	20161009
74590	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20161023	20161009
74615	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161023	20161009
74624	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20161023	20161009
74640	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20161023	20161009
74688	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20161023	20161009
74723	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20161023	20161009
74726	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161023	20161009
74750	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20161023	20161009
74778	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161023	20161009
74782	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161023	20161009
74861	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20161023	20161009
74893	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20161023	20161009
75085	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20161023	20161009
75256	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20161023	20161009
75432	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20161023	20161009
75472	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161023	20161009
75480	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20161023	20161009
75535	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20161023	20161009
75614	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161023	20161009
76936	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20161023	20161009
76944	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20161023	20161009
77348	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20161023	20161009
77811	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20161023	20161009
78590	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161023	20161009
78654	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161023	20161009
78654	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161023	20161009
78668	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161023	20161009
78771	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161023	20161009
79472	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20161023	20161009
79669	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161023	20161009
79755	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20161023	20161009
81171	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161023	20161009
81219	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161023	20161009
81364	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161023	20161009
81453	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161023	20161009

Test failure

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 19, namely:

Compiler	Implementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	nim ref
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	nim ref
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	nim ref
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	nim ref
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	nim ref
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	nim ref
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	ref
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	nim ref
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	nim ref
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	nim ref

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

tiaoxin-optimized.c: tiaoxin-optimized.c: In function 'tiaoxin_optimized_encrypt':
tiaoxin-optimized.c: tiaoxin-optimized.c:108:10: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
tiaoxin-optimized.c: __m128i Z0 = constant8( 0x42,0x8a,0x2f,0x98,0xd7,0x28,0xae,0x22,0x71,0x37,0x44,0x91,0x23,0xef,0x65,0xcd );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
tiaoxin-optimized.c: from tiaoxin-optimized.c:20:
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_xor_si128 (__m128i __A, __m128i __B)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:28:19: error: called from here
tiaoxin-optimized.c: #define xor(a,b) _mm_xor_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:42:127: note: in expansion of macro 'xor'
tiaoxin-optimized.c: #define RT6( T , M ) tmp = T[0];T[0] = enc(T[5],M);T[5] = T[4];T[4] = T[3];T[3] = T[2];T[2] = T[1];T[1] = enc(tmp,Z0);T[0] = xor(T[0], tmp);
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:50:1: note: in expansion of macro 'RT6'
tiaoxin-optimized.c: RT6( T6, M2 );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:151:2: note: in expansion of macro 'UPDATE'
tiaoxin-optimized.c: UPDATE( T3 , T4 , T6, Z0 , Z1 , Z0 );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: In file included from tiaoxin-optimized.c:22:0:
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '_mm_aesenc_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: ...

Number of similar (compiler,implementation) pairs: 88, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer	nim
gcc -m32 -O2 -fomit-frame-pointer	nim
gcc -m32 -O3 -fomit-frame-pointer	nim
gcc -m32 -O -fomit-frame-pointer	nim
gcc -m32 -Os -fomit-frame-pointer	nim
gcc -m32 -march=athlon -O2 -fomit-frame-pointer	nim
gcc -m32 -march=athlon -O3 -fomit-frame-pointer	nim
gcc -m32 -march=athlon -O -fomit-frame-pointer	nim
gcc -m32 -march=athlon -Os -fomit-frame-pointer	nim
gcc -m32 -march=i386 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=i386 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=i386 -O -fomit-frame-pointer	nim
gcc -m32 -march=i386 -Os -fomit-frame-pointer	nim
gcc -m32 -march=i486 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=i486 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=i486 -O -fomit-frame-pointer	nim
gcc -m32 -march=i486 -Os -fomit-frame-pointer	nim
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=k6-2 -O -fomit-frame-pointer	nim
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer	nim
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=k6-3 -O -fomit-frame-pointer	nim
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer	nim
gcc -m32 -march=k6 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=k6 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=k6 -O -fomit-frame-pointer	nim
gcc -m32 -march=k6 -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer	nim
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentium2 -O -fomit-frame-pointer	nim
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentium -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentium -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentium -O -fomit-frame-pointer	nim
gcc -m32 -march=pentium -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer	nim
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer	nim

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 61, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	nim
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=core2 -O -fomit-frame-pointer	nim
gcc -m32 -march=core2 -Os -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	nim
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=corei7 -O -fomit-frame-pointer	nim
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	nim
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=k8 -O -fomit-frame-pointer	nim
gcc -m32 -march=k8 -Os -fomit-frame-pointer	nim
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer	nim
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer	nim
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer	nim
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer	nim
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	nim
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	nim
gcc -m32 -march=nocona -O -fomit-frame-pointer	nim
gcc -m32 -march=nocona -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	nim
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	nim
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	nim
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	nim
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	nim
gcc -m32 -march=prescott -O -fomit-frame-pointer	nim
gcc -m32 -march=prescott -Os -fomit-frame-pointer	nim

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer

tiaoxin-optimized.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
tiaoxin-optimized.c: from tiaoxin-optimized.c:20:
tiaoxin-optimized.c: tiaoxin-optimized.c: In function 'tiaoxin_optimized_encrypt':
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_xor_si128 (__m128i __A, __m128i __B)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:28:19: error: called from here
tiaoxin-optimized.c: #define xor(a,b) _mm_xor_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:42:127: note: in expansion of macro 'xor'
tiaoxin-optimized.c: #define RT6( T , M ) tmp = T[0];T[0] = enc(T[5],M);T[5] = T[4];T[4] = T[3];T[3] = T[2];T[2] = T[1];T[1] = enc(tmp,Z0);T[0] = xor(T[0], tmp);
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:50:1: note: in expansion of macro 'RT6'
tiaoxin-optimized.c: RT6( T6, M2 );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:151:2: note: in expansion of macro 'UPDATE'
tiaoxin-optimized.c: UPDATE( T3 , T4 , T6, Z0 , Z1 , Z0 );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: In file included from tiaoxin-optimized.c:22:0:
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '_mm_aesenc_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: error: called from here
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: ...

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentium3 -O -fomit-frame-pointer	nim
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer	nim

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

tiaoxin-optimized.c: In file included from tiaoxin-optimized.c:22:0:
tiaoxin-optimized.c: tiaoxin-optimized.c: In function 'tiaoxin_optimized_encrypt':
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '_mm_aesenc_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: error: called from here
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:42:108: note: in expansion of macro 'enc'
tiaoxin-optimized.c: #define RT6( T , M ) tmp = T[0];T[0] = enc(T[5],M);T[5] = T[4];T[4] = T[3];T[3] = T[2];T[2] = T[1];T[1] = enc(tmp,Z0);T[0] = xor(T[0], tmp);
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:50:1: note: in expansion of macro 'RT6'
tiaoxin-optimized.c: RT6( T6, M2 );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:151:2: note: in expansion of macro 'UPDATE'
tiaoxin-optimized.c: UPDATE( T3 , T4 , T6, Z0 , Z1 , Z0 );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: In file included from tiaoxin-optimized.c:22:0:
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '_mm_aesenc_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: error: called from here
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:42:41: note: in expansion of macro 'enc'
tiaoxin-optimized.c: ...
tiaoxin-optimized.c: In file included from tiaoxin-optimized.c:22:0:
tiaoxin-optimized.c: tiaoxin-optimized.c: In function 'tiaoxin_optimized_encrypt':
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '_mm_aesenc_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: error: called from here
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:42:108: note: in expansion of macro 'enc'
tiaoxin-optimized.c: #define RT6( T , M ) tmp = T[0];T[0] = enc(T[5],M);T[5] = T[4];T[4] = T[3];T[3] = T[2];T[2] = T[1];T[1] = enc(tmp,Z0);T[0] = xor(T[0], tmp);
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:50:1: note: in expansion of macro 'RT6'
tiaoxin-optimized.c: RT6( T6, M2 );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:151:2: note: in expansion of macro 'UPDATE'
tiaoxin-optimized.c: UPDATE( T3 , T4 , T6, Z0 , Z1 , Z0 );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: In file included from tiaoxin-optimized.c:22:0:
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '_mm_aesenc_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: error: called from here
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:42:41: note: in expansion of macro 'enc'
tiaoxin-optimized.c: ...

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

Compiler	Implementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer	nim
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer	nim
gcc -m32 -march=barcelona -O -fomit-frame-pointer	nim
gcc -m32 -march=barcelona -Os -fomit-frame-pointer	nim