Implementation notes: amd64, skylake, crypto_aead/aes128n12t8clocv2

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: aes128n12t8clocv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
17400	`aesni`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
17436	`aesni`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
17492	`aesni`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
17498	`aesni`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
17538	`aesni`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
17588	`aesni`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
17590	`aesni`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
17742	`aesni`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
17776	`aesni`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
17784	`aesni`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
17830	`aesni`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
17832	`aesni`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
17838	`aesni`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
18052	`aesni`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
18062	`aesni`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
18094	`aesni`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
18100	`aesni`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
18240	`aesni`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
18240	`aesni`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
18306	`aesni`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
18308	`aesni`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
18320	`aesni`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
18324	`aesni`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
18430	`aesni`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
110162	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
110302	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
110462	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
110586	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
110746	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
111294	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
111316	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
111606	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
111738	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
111780	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
111786	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
111826	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
111854	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
111900	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
112026	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
112086	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
112138	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
112218	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
112504	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
112576	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
112680	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
113020	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
113042	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
113168	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
113190	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
113226	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
113252	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
113282	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
113300	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
113310	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
113322	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
113326	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
113326	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
113352	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
113364	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
113420	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
113462	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
113514	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
113542	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
113544	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
113594	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
113600	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
113760	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
113860	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
113864	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
113916	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
113968	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
114080	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
114086	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
114098	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
114104	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
114150	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
114230	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
114268	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
114388	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
114450	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
114482	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
114764	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
114848	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
114886	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
115222	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
115270	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
115408	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
115524	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
115566	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
115628	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
116074	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
116114	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
116130	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
116424	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
116886	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
116890	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
117008	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
117036	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
117248	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
117258	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
117604	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
117866	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
117950	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
118090	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
118104	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
118120	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
118208	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
118274	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
118396	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
118486	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
118502	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
118544	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
118706	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
118832	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
118866	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
118876	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
118884	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
118890	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
118920	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
118924	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
118948	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
119072	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
119186	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
119206	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
119208	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
119214	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
119324	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
119364	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
119612	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
119908	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
120036	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
120168	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
120458	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
121036	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
121100	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
121260	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
121362	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
121586	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
122138	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
122578	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
122778	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
123502	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
227434	`ref`	`gcc`	20161216	20161026
227520	`ref`	`cc`	20161216	20161026
230494	`ref`	`gcc -funroll-loops`	20161216	20161026

Compiler output

Implementation: crypto_aead/aes128n12t8clocv2/aesni
Compiler: cc

encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: encrypt.c: In function 'crypto_aead_aes128n12t8clocv2_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:37:0:
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:142:5: 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:37:0:
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:142:5: 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/aes128n12t8clocv2/aesni
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: In file included from encrypt.c:37:
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:37:
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:37:
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/aes128n12t8clocv2/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/aes128n12t8clocv2/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:37:0:
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:37:0:
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:37:0:
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:37:0:
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