Implementation notes: x86, h4e450, crypto_aead/tiaoxinv2

Computer: h4e450
Architecture: x86
CPU ID: AuthenticAMD-00500f20-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: tiaoxinv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
87029	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20171012	20170725
87134	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20171012	20170725
87149	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20171012	20170725
87400	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20171012	20170725
87605	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20171012	20170725
87842	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20171012	20170725
87918	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20171012	20170725
87970	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20171012	20170725
88383	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20171012	20170725
88454	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20171012	20170725
88616	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20171012	20170725
88644	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20171012	20170725
88787	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20171012	20170725
88792	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20171012	20170725
88811	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20171012	20170725
88887	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20171012	20170725
88911	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20171012	20170725
88987	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20171012	20170725
89020	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20171012	20170725
89143	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20171012	20170725
89186	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20171012	20170725
89409	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20171012	20170725
89433	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20171012	20170725
89499	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20171012	20170725
89533	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20171012	20170725
89642	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20171012	20170725
89652	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20171012	20170725
89661	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20171012	20170725
89704	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20171012	20170725
89718	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20171012	20170725
89728	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20171012	20170725
89789	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20171012	20170725
89861	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20171012	20170725
89898	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20171012	20170725
89899	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20171012	20170725
89993	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20171012	20170725
90022	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20171012	20170725
90197	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20171012	20170725
90331	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20171012	20170725
90350	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20171012	20170725
90364	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20171012	20170725
90411	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20171012	20170725
90564	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20171012	20170725
90639	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20171012	20170725
90739	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20171012	20170725
90763	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20171012	20170725
90772	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20171012	20170725
90787	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20171012	20170725
90820	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20171012	20170725
90858	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20171012	20170725
90877	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20171012	20170725
90896	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20171012	20170725
91006	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20171012	20170725
91024	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20171012	20170725
91029	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20171012	20170725
91039	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20171012	20170725
91043	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20171012	20170725
91076	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20171012	20170725
91086	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20171012	20170725
91086	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20171012	20170725
91114	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20171012	20170725
91191	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20171012	20170725
91219	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20171012	20170725
91243	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20171012	20170725
91452	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20171012	20170725
91480	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20171012	20170725
91504	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20171012	20170725
91514	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20171012	20170725
91514	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20171012	20170725
91642	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20171012	20170725
91694	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20171012	20170725
91832	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20171012	20170725
91846	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20171012	20170725
91850	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20171012	20170725
91960	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20171012	20170725
91979	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20171012	20170725
92017	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20171012	20170725
92046	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20171012	20170725
92079	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20171012	20170725
92089	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20171012	20170725
92126	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20171012	20170725
92136	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20171012	20170725
92141	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20171012	20170725
92164	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20171012	20170725
92164	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20171012	20170725
92184	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20171012	20170725
92359	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20171012	20170725
92730	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20171012	20170725
92744	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20171012	20170725
92829	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20171012	20170725
92910	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20171012	20170725
92915	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20171012	20170725
92953	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20171012	20170725
92962	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20171012	20170725
92986	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20171012	20170725
93071	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20171012	20170725
93171	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20171012	20170725
93200	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20171012	20170725
93275	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20171012	20170725
93352	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20171012	20170725
93399	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20171012	20170725
93409	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20171012	20170725
93466	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20171012	20170725
93608	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20171012	20170725
93732	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20171012	20170725
93736	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20171012	20170725
93784	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20171012	20170725
93837	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20171012	20170725
94102	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20171012	20170725
94254	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20171012	20170725
94378	`ref`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20171012	20170725
94611	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20171012	20170725
94682	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20171012	20170725
94734	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20171012	20170725
94796	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20171012	20170725
94852	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20171012	20170725
94853	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20171012	20170725
94947	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20171012	20170725
95057	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20171012	20170725
95081	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20171012	20170725
95095	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20171012	20170725
95128	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20171012	20170725
95143	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20171012	20170725
95147	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20171012	20170725
95247	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20171012	20170725
95266	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20171012	20170725
95276	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20171012	20170725
95988	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20171012	20170725
96335	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20171012	20170725
96501	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20171012	20170725
97104	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20171012	20170725
97413	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20171012	20170725
97532	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20171012	20170725
97727	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20171012	20170725
97940	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20171012	20170725
98486	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20171012	20170725
98505	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20171012	20170725
98591	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20171012	20170725
98600	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20171012	20170725
100087	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20171012	20170725
100187	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20171012	20170725
100467	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20171012	20170725
100558	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20171012	20170725
100658	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20171012	20170725
100667	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20171012	20170725
100923	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20171012	20170725
101317	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20171012	20170725
102030	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20171012	20170725
102187	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20171012	20170725
102999	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20171012	20170725
103199	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20171012	20170725
104709	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20171012	20170725
104757	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20171012	20170725
104908	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20171012	20170725
104941	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20171012	20170725
105041	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20171012	20170725
105104	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20171012	20170725
107032	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20171012	20170725
107132	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20171012	20170725
107288	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20171012	20170725
107616	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20171012	20170725

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: 18, 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=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