Implementation notes: amd64, skylake, crypto_aead/aes128n12t8silcv3

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: aes128n12t8silcv3

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
17630	`aesni`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
17690	`aesni`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
17692	`aesni`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
17802	`aesni`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
17804	`aesni`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
18660	`aesni`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
18708	`aesni`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
18726	`aesni`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
18852	`aesni`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
18986	`aesni`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
19010	`aesni`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
19012	`aesni`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
19022	`aesni`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
19052	`aesni`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
19502	`aesni`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
19546	`aesni`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
19558	`aesni`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
19564	`aesni`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
19566	`aesni`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
19606	`aesni`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
19616	`aesni`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
19618	`aesni`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
19724	`aesni`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
19768	`aesni`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
117080	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
117384	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
117568	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
118128	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
118170	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
118368	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
118410	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
118464	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
118904	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
118906	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
119050	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
119242	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
119448	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
119716	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
119808	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
119992	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
120054	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
120130	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
120524	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
121298	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
121382	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
121538	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
121628	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
121706	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
121802	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
121820	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
121828	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
122062	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
122174	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
122186	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
122210	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
122216	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
122264	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
122284	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
122300	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
122378	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
122436	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
122440	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
122442	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
122468	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
122670	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
122694	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
122708	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
122848	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
122900	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
122994	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
123036	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
123224	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
123432	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
123480	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
123504	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
123534	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
123814	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
123832	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
123870	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
123902	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
123940	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
123956	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
123964	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
124028	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
124110	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
124180	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
124218	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
124388	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
124390	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
124484	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
124514	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
124540	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
124636	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
124700	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
124846	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
124922	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
124986	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
125002	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
125286	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
125294	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
125436	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
125656	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
125824	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
125874	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
126004	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
126004	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
126252	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
126348	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
126374	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
126764	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
126766	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
126800	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
126884	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
126932	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
127004	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
127246	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
127474	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
127644	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
127698	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
127828	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
127912	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
128072	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
128246	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
128654	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
129026	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
129596	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
129882	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
132920	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
133802	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
133854	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
134412	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
136828	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
136988	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
137150	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
137186	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
137670	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
137714	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
137872	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
138698	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
138704	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
139282	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
140240	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
310102	`ref`	`cc`	20161216	20161026
312138	`ref`	`gcc -funroll-loops`	20161216	20161026
314858	`ref`	`gcc`	20161216	20161026

Compiler output

Implementation: crypto_aead/aes128n12t8silcv3/aesni
Compiler: cc

encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: encrypt.c: In function 'crypto_aead_aes128n12t8silcv3_aesni_encrypt':
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:69:1: error: inlining failed in call to always_inline '_mm_aesenclast_si128': target specific option mismatch
encrypt.c: _mm_aesenclast_si128 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:41:0:
encrypt.c: aes.h:67:8: note: called from here
encrypt.c: out = _mm_aesenclast_si128(out, roundkeys[10]);\
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:107:5: note: in expansion of macro 'AES128_encrypt'
encrypt.c: AES128_encrypt(estate, estate);
encrypt.c: ^~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '_mm_aesenc_si128': target specific option mismatch
encrypt.c: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
encrypt.c: ^~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:41:0:
encrypt.c: aes.h:66:8: note: called from here
encrypt.c: out = _mm_aesenc_si128(out, roundkeys[9]); \
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:107:5: note: in expansion of macro 'AES128_encrypt'
encrypt.c: AES128_encrypt(estate, estate);
encrypt.c: ^~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '_mm_aesenc_si128': target specific option mismatch
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
cc	aesni
gcc	aesni
gcc -funroll-loops	aesni

Compiler output

Implementation: crypto_aead/aes128n12t8silcv3/aesni
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: In file included from encrypt.c:41:
encrypt.c: ./aes.h:30:2: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
encrypt.c: EXPAND_ASSIST(x0, x1, x2, x0, 1); roundkeys[1] = x0;
encrypt.c: ^
encrypt.c: ./aes.h:13:7: note: expanded from macro 'EXPAND_ASSIST'
encrypt.c: v2 = _mm_aeskeygenassist_si128(v4, aes_const); \
encrypt.c: ^
encrypt.c: /usr/bin/../lib/clang/3.9.0/include/__wmmintrin_aes.h:147:12: note: expanded from macro '_mm_aeskeygenassist_si128'
encrypt.c: (__m128i)__builtin_ia32_aeskeygenassist128((__v2di)(__m128i)(C), (int)(R))
encrypt.c: ^
encrypt.c: In file included from encrypt.c:41:
encrypt.c: ./aes.h:31:2: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
encrypt.c: EXPAND_ASSIST(x0, x1, x2, x0, 2); roundkeys[2] = x0;
encrypt.c: ^
encrypt.c: ./aes.h:13:7: note: expanded from macro 'EXPAND_ASSIST'
encrypt.c: v2 = _mm_aeskeygenassist_si128(v4, aes_const); \
encrypt.c: ^
encrypt.c: /usr/bin/../lib/clang/3.9.0/include/__wmmintrin_aes.h:147:12: note: expanded from macro '_mm_aeskeygenassist_si128'
encrypt.c: (__m128i)__builtin_ia32_aeskeygenassist128((__v2di)(__m128i)(C), (int)(R))
encrypt.c: ^
encrypt.c: In file included from encrypt.c:41:
encrypt.c: ./aes.h:32:2: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
encrypt.c: EXPAND_ASSIST(x0, x1, x2, x0, 4); roundkeys[3] = x0;
encrypt.c: ^
encrypt.c: ./aes.h:13:7: note: expanded from macro 'EXPAND_ASSIST'
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	aesni
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	aesni
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	aesni
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	aesni
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	aesni
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	aesni

Compiler output

Implementation: crypto_aead/aes128n12t8silcv3/aesni
Compiler: gcc -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 84, namely:

Compiler	Implementations
gcc -O2 -fomit-frame-pointer	aesni
gcc -O3 -fomit-frame-pointer	aesni
gcc -O -fomit-frame-pointer	aesni
gcc -Os -fomit-frame-pointer	aesni
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	aesni
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	aesni
gcc -fno-schedule-insns -O -fomit-frame-pointer	aesni
gcc -fno-schedule-insns -Os -fomit-frame-pointer	aesni
gcc -funroll-loops -O2 -fomit-frame-pointer	aesni
gcc -funroll-loops -O3 -fomit-frame-pointer	aesni
gcc -funroll-loops -O -fomit-frame-pointer	aesni
gcc -funroll-loops -Os -fomit-frame-pointer	aesni
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	aesni
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	aesni
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	aesni
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -O -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	aesni
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	aesni
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	aesni
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	aesni
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	aesni
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	aesni
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	aesni
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	aesni
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	aesni
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	aesni
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	aesni
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	aesni
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	aesni
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	aesni
gcc -m64 -O2 -fomit-frame-pointer	aesni
gcc -m64 -O3 -fomit-frame-pointer	aesni
gcc -m64 -O -fomit-frame-pointer	aesni
gcc -m64 -Os -fomit-frame-pointer	aesni
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	aesni
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	aesni
gcc -m64 -march=core2 -O -fomit-frame-pointer	aesni
gcc -m64 -march=core2 -Os -fomit-frame-pointer	aesni
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	aesni
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	aesni
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	aesni
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	aesni
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	aesni
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	aesni
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	aesni
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	aesni
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	aesni
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	aesni
gcc -m64 -march=corei7 -O -fomit-frame-pointer	aesni
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	aesni
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	aesni
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	aesni
gcc -m64 -march=k8 -O -fomit-frame-pointer	aesni
gcc -m64 -march=k8 -Os -fomit-frame-pointer	aesni
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	aesni
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	aesni
gcc -m64 -march=nocona -O -fomit-frame-pointer	aesni
gcc -m64 -march=nocona -Os -fomit-frame-pointer	aesni
gcc -march=barcelona -O2 -fomit-frame-pointer	aesni
gcc -march=barcelona -O3 -fomit-frame-pointer	aesni
gcc -march=barcelona -O -fomit-frame-pointer	aesni
gcc -march=barcelona -Os -fomit-frame-pointer	aesni
gcc -march=k8 -O2 -fomit-frame-pointer	aesni
gcc -march=k8 -O3 -fomit-frame-pointer	aesni
gcc -march=k8 -O -fomit-frame-pointer	aesni
gcc -march=k8 -Os -fomit-frame-pointer	aesni
gcc -march=nocona -O2 -fomit-frame-pointer	aesni
gcc -march=nocona -O3 -fomit-frame-pointer	aesni
gcc -march=nocona -O -fomit-frame-pointer	aesni
gcc -march=nocona -Os -fomit-frame-pointer	aesni

Compiler output

Implementation: crypto_aead/aes128n12t8silcv3/aesni
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: aes.h: In function 'AES128_KeyExpansion':
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:87:1: error: inlining failed in call to always_inline '_mm_aeskeygenassist_si128': target specific option mismatch
encrypt.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:41:0:
encrypt.c: aes.h:13:5: note: called from here
encrypt.c: v2 = _mm_aeskeygenassist_si128(v4, aes_const); \
encrypt.c: ^
encrypt.c: aes.h:39:2: note: in expansion of macro 'EXPAND_ASSIST'
encrypt.c: EXPAND_ASSIST(x0, x1, x2, x0, 54); roundkeys[10] = x0;
encrypt.c: ^~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:87:1: error: inlining failed in call to always_inline '_mm_aeskeygenassist_si128': target specific option mismatch
encrypt.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:41:0:
encrypt.c: aes.h:13:5: note: called from here
encrypt.c: v2 = _mm_aeskeygenassist_si128(v4, aes_const); \
encrypt.c: ^
encrypt.c: aes.h:38:2: note: in expansion of macro 'EXPAND_ASSIST'
encrypt.c: EXPAND_ASSIST(x0, x1, x2, x0, 27); roundkeys[9] = x0;
encrypt.c: ^~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:87:1: error: inlining failed in call to always_inline '_mm_aeskeygenassist_si128': target specific option mismatch
encrypt.c: ...
encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: aes.h: In function 'AES128_KeyExpansion':
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:87:1: error: inlining failed in call to always_inline '_mm_aeskeygenassist_si128': target specific option mismatch
encrypt.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:41:0:
encrypt.c: aes.h:13:5: note: called from here
encrypt.c: v2 = _mm_aeskeygenassist_si128(v4, aes_const); \
encrypt.c: ^
encrypt.c: aes.h:39:2: note: in expansion of macro 'EXPAND_ASSIST'
encrypt.c: EXPAND_ASSIST(x0, x1, x2, x0, 54); roundkeys[10] = x0;
encrypt.c: ^~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:87:1: error: inlining failed in call to always_inline '_mm_aeskeygenassist_si128': target specific option mismatch
encrypt.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:41:0:
encrypt.c: aes.h:13:5: note: called from here
encrypt.c: v2 = _mm_aeskeygenassist_si128(v4, aes_const); \
encrypt.c: ^
encrypt.c: aes.h:38:2: note: in expansion of macro 'EXPAND_ASSIST'
encrypt.c: EXPAND_ASSIST(x0, x1, x2, x0, 27); roundkeys[9] = x0;
encrypt.c: ^~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:87:1: error: inlining failed in call to always_inline '_mm_aeskeygenassist_si128': target specific option mismatch
encrypt.c: ...

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	aesni
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	aesni
gcc -m64 -march=barcelona -O -fomit-frame-pointer	aesni
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	aesni