Implementation notes: amd64, skylake, crypto_aead/aes128n12t8silcv2

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: aes128n12t8silcv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
17610	`aesni`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
17666	`aesni`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
17710	`aesni`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
17720	`aesni`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
17722	`aesni`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
17730	`aesni`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
17732	`aesni`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
17756	`aesni`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
17764	`aesni`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
17788	`aesni`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
17814	`aesni`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
17840	`aesni`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
17846	`aesni`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
17850	`aesni`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
17852	`aesni`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
17882	`aesni`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
17924	`aesni`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
17990	`aesni`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
18002	`aesni`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
18016	`aesni`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
18670	`aesni`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
18670	`aesni`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
18742	`aesni`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
18920	`aesni`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
116682	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
117612	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
117692	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
117758	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
117818	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
117940	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
118528	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
118560	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
119646	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
119654	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
119700	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
120012	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
120026	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
120156	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
120238	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
120272	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
120286	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
120428	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
120480	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
120482	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
120960	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
121082	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
121226	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
121328	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
121382	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
121386	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
121442	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
121628	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
121736	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
121738	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
121772	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
121776	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
121876	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
121884	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
121884	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
122054	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
122078	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
122096	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
122154	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
122388	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
122420	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
122438	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
122522	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
122568	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
122594	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
122718	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
122772	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
122822	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
122892	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
122912	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
122918	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
122956	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
122968	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
123092	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
123110	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
123238	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
123354	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
123388	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
123468	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
123474	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
123516	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
123600	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
123756	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
123760	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
123846	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
124114	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
124376	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
124480	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
124570	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
124652	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
124770	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
124780	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
124844	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
124860	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
125074	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
125162	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
125592	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
125748	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
125772	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
125860	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
125906	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
125940	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
125964	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
126420	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
126534	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
126628	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
126720	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
127044	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
127152	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
127182	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
127558	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
127740	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
128172	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
128468	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
128490	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
128668	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
128890	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
128936	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
128978	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
129006	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
129008	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
129014	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
129014	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
129066	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
129282	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
130004	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
130312	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
130498	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
130498	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
130564	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
130768	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
130936	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
131716	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
132372	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
133022	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
133158	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
136870	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
137382	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
311856	`ref`	`cc`	20161216	20161026
312016	`ref`	`gcc`	20161216	20161026
312976	`ref`	`gcc -funroll-loops`	20161216	20161026

Compiler output

Implementation: crypto_aead/aes128n12t8silcv2/aesni
Compiler: cc

encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: encrypt.c: In function 'crypto_aead_aes128n12t8silcv2_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/aes128n12t8silcv2/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/aes128n12t8silcv2/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/aes128n12t8silcv2/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