Implementation notes: x86, h2atom, crypto_aead/tiaoxinv2

Computer: h2atom
Architecture: x86
CPU ID: GenuineIntel-000106ca-bfe9fbff
SUPERCOP version: 20161009
Operation: crypto_aead
Primitive: tiaoxinv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
111090	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161207	20161009
111550	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161207	20161009
115360	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161207	20161009
115420	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20161207	20161009
115520	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20161207	20161009
116170	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20161207	20161009
116330	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161207	20161009
116510	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161207	20161009
118240	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20161207	20161009
119760	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161207	20161009
119980	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20161207	20161009
123330	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20161207	20161009
124880	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20161207	20161009
125310	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20161207	20161009
126260	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161207	20161009
126560	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20161207	20161009
126980	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161207	20161009
127890	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161207	20161009
128030	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20161207	20161009
128810	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161207	20161009
134650	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161207	20161009
138560	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161207	20161009
138880	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20161207	20161009
138930	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20161207	20161009
139200	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161207	20161009
139490	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20161207	20161009
139560	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161207	20161009
139670	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20161207	20161009
139870	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20161207	20161009
140420	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161207	20161009
141080	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20161207	20161009
141090	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161207	20161009
141100	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161207	20161009
141100	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161207	20161009
141320	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20161207	20161009
141360	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161207	20161009
141370	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161207	20161009
141510	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161207	20161009
141510	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20161207	20161009
141570	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161207	20161009
141650	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161207	20161009
142370	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161207	20161009
142490	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20161207	20161009
142560	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20161207	20161009
142580	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20161207	20161009
142790	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20161207	20161009
142890	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20161207	20161009
142980	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161207	20161009
143010	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161207	20161009
143110	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161207	20161009
143140	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20161207	20161009
143170	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161207	20161009
143260	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20161207	20161009
143360	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161207	20161009
143650	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161207	20161009
143660	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161207	20161009
143690	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20161207	20161009
144070	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20161207	20161009
144080	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20161207	20161009
144170	`ref`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20161207	20161009
144400	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20161207	20161009
144400	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20161207	20161009
144710	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20161207	20161009
144820	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20161207	20161009
144940	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161207	20161009
145040	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161207	20161009
146120	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20161207	20161009
146240	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20161207	20161009
147170	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161207	20161009
147260	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20161207	20161009
147860	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20161207	20161009
147880	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161207	20161009
148170	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20161207	20161009
148510	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20161207	20161009
148660	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20161207	20161009
148680	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20161207	20161009
148810	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161207	20161009
148880	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161207	20161009
149570	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20161207	20161009
149920	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20161207	20161009
149960	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20161207	20161009
150270	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20161207	20161009
150310	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20161207	20161009
150750	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20161207	20161009
150770	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20161207	20161009
150890	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20161207	20161009
151470	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20161207	20161009
151500	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20161207	20161009
151660	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20161207	20161009
151780	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161207	20161009
151810	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20161207	20161009
151810	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20161207	20161009
152090	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161207	20161009
152150	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20161207	20161009
152210	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20161207	20161009
152380	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161207	20161009
152400	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20161207	20161009
152690	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20161207	20161009
152750	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20161207	20161009
152820	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20161207	20161009
152970	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161207	20161009
153340	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161207	20161009
153550	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20161207	20161009
153620	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161207	20161009
153630	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161207	20161009
153990	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161207	20161009
154750	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161207	20161009
154810	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20161207	20161009
154840	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20161207	20161009
155420	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20161207	20161009
155650	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20161207	20161009
155740	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20161207	20161009
155790	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20161207	20161009
155800	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20161207	20161009
156090	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20161207	20161009
156150	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161207	20161009
156180	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161207	20161009
156500	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161207	20161009
156770	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161207	20161009
156820	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20161207	20161009
156840	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161207	20161009
157080	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20161207	20161009
157100	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20161207	20161009
157120	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20161207	20161009
157380	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20161207	20161009
157390	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20161207	20161009
157570	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20161207	20161009
157680	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20161207	20161009
157800	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20161207	20161009
157880	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20161207	20161009
157890	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20161207	20161009
157950	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20161207	20161009
158120	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20161207	20161009
158120	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20161207	20161009
158120	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20161207	20161009
158360	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20161207	20161009
158480	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20161207	20161009
158560	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161207	20161009
158630	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161207	20161009
158670	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20161207	20161009
158800	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20161207	20161009
161900	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20161207	20161009
162120	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20161207	20161009
162350	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20161207	20161009
162380	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20161207	20161009
165920	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20161207	20161009
166100	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161207	20161009
166790	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20161207	20161009
166810	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161207	20161009
167740	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161207	20161009
167750	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20161207	20161009
167820	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20161207	20161009
167910	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161207	20161009
168580	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20161207	20161009
168580	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161207	20161009
168800	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20161207	20161009
169060	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161207	20161009
170930	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161207	20161009
170930	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161207	20161009
171540	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161207	20161009
171580	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161207	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: 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