Implementation notes: amd64, skylake, crypto_aead/aes128n8t8clocv2

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: aes128n8t8clocv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
17414	`aesni`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
17422	`aesni`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
17446	`aesni`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
17490	`aesni`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
17500	`aesni`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
17578	`aesni`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
17582	`aesni`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
17666	`aesni`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
17744	`aesni`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
17782	`aesni`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
17830	`aesni`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
17834	`aesni`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
17836	`aesni`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
18002	`aesni`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
18038	`aesni`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
18044	`aesni`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
18110	`aesni`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
18120	`aesni`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
18150	`aesni`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
18274	`aesni`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
18302	`aesni`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
18306	`aesni`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
18312	`aesni`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
18380	`aesni`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
110034	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
110410	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
110594	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
110624	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
111162	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
111264	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
111292	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
111466	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
111512	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
111596	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
111900	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
111938	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
111938	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
111986	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
111988	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
112042	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
112324	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
112330	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
112368	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
112376	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
112588	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
112720	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
112828	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
112936	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
113100	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
113142	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
113186	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
113268	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
113420	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
113542	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
113560	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
113568	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
113728	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
113754	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
113798	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
113818	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
113818	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
113820	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
113886	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
113900	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
113908	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
113914	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
113974	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
113980	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
113980	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
114098	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
114204	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
114224	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
114274	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
114360	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
114402	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
114402	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
114418	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
114482	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
114562	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
114742	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
114810	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
115000	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
115172	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
115324	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
115382	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
115458	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
115460	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
115464	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
115640	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
115686	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
116028	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
116156	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
116326	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
116388	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
116722	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
116738	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
116946	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
117018	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
117150	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
117340	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
117830	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
117870	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
117968	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
118010	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
118080	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
118192	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
118202	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
118250	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
118366	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
118404	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
118410	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
118446	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
118496	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
118502	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
118568	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
118604	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
118610	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
118646	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
118756	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
118792	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
118848	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
119006	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
119174	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
119350	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
119362	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
119410	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
119484	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
119518	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
119758	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
119940	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
120054	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
120178	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
120182	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
120186	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
120346	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
120458	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
120822	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
120984	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
121146	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
121282	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
121606	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
122314	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
227008	`ref`	`cc`	20161216	20161026
227074	`ref`	`gcc`	20161216	20161026
234752	`ref`	`gcc -funroll-loops`	20161216	20161026

Compiler output

Implementation: crypto_aead/aes128n8t8clocv2/aesni
Compiler: cc

encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: encrypt.c: In function 'crypto_aead_aes128n8t8clocv2_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:38:0:
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:143:5: 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:38:0:
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:143:5: 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/aes128n8t8clocv2/aesni
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: In file included from encrypt.c:38:
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:38:
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:38:
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/aes128n8t8clocv2/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/aes128n8t8clocv2/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:38:0:
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:38:0:
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:38:0:
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:38:0:
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