Implementation notes: amd64, skylake, crypto_aead/aes128n8t8silcv2

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: aes128n8t8silcv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
17616	`aesni`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
17670	`aesni`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
17722	`aesni`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
17728	`aesni`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
17740	`aesni`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
17742	`aesni`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
17744	`aesni`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
17750	`aesni`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
17770	`aesni`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
17772	`aesni`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
17802	`aesni`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
17822	`aesni`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
17846	`aesni`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
17848	`aesni`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
17854	`aesni`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
17874	`aesni`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
17880	`aesni`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
17894	`aesni`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
17928	`aesni`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
18004	`aesni`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
18670	`aesni`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
18726	`aesni`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
18746	`aesni`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
18776	`aesni`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
117214	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
117646	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
117838	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
117912	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
118202	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
118242	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
118466	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
119216	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
119310	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
119314	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
119394	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
119496	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
119536	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
119616	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
119716	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
119858	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
119960	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
120136	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
120196	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
120250	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
120704	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
121014	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
121364	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
121370	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
121556	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
121722	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
121766	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
121776	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
121812	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
121888	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
122176	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
122188	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
122210	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
122218	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
122228	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
122232	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
122250	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
122306	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
122330	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
122476	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
122500	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
122622	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
122626	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
122658	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
122672	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
122726	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
122786	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
122800	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
122976	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
122984	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
123086	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
123260	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
123264	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
123678	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
123808	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
123966	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
124006	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
124054	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
124210	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
124284	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
124572	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
124686	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
124742	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
124810	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
124894	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
124946	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
124978	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
125050	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
125070	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
125116	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
125336	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
125346	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
125588	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
125668	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
125760	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
125914	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
126038	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
126042	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
126106	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
126184	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
126198	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
126262	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
126556	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
126730	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
126896	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
126998	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
127052	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
127188	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
127220	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
127550	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
127614	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
127638	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
127652	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
127664	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
127668	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
127668	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
127720	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
127736	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
127758	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
127856	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
127864	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
127934	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
127952	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
128030	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
128046	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
128122	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
128296	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
128340	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
128366	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
128544	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
129618	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
129672	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
131444	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
132078	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
132434	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
134160	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
138486	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
141132	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
312228	`ref`	`gcc`	20161216	20161026
313318	`ref`	`cc`	20161216	20161026
314748	`ref`	`gcc -funroll-loops`	20161216	20161026

Compiler output

Implementation: crypto_aead/aes128n8t8silcv2/aesni
Compiler: cc

encrypt.c: In file included from encrypt.c:7:0:
encrypt.c: encrypt.c: In function 'crypto_aead_aes128n8t8silcv2_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:42:0:
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:108:5: 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:42:0:
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:108:5: 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/aes128n8t8silcv2/aesni
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: In file included from encrypt.c:42:
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:42:
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:42:
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/aes128n8t8silcv2/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/aes128n8t8silcv2/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:42:0:
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:42:0:
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:42:0:
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:42:0:
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