Implementation notes: amd64, skylake, crypto_aead/kiasueq128v1

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: kiasueq128v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
7150	`opt`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
7152	`opt`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
7154	`opt`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
7164	`opt`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
7170	`opt`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
7172	`opt`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
7178	`opt`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
7188	`opt`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
7196	`opt`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
7202	`opt`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
7204	`opt`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
7206	`opt`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
7264	`opt`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
7306	`opt`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
7404	`opt`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
7422	`opt`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
7426	`opt`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
7436	`opt`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
7438	`opt`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
7440	`opt`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
8740	`opt`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
8762	`opt`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
9188	`opt`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
9234	`opt`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
90702	`bitslice`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
90718	`bitslice`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
90740	`bitslice`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
90780	`bitslice`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
90818	`bitslice`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
90826	`bitslice`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
90884	`bitslice`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
90942	`bitslice`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
90946	`bitslice`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
90970	`bitslice`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
91038	`bitslice`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
91076	`bitslice`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
91132	`bitslice`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
91152	`bitslice`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
91180	`bitslice`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
91180	`bitslice`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
91184	`bitslice`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
91186	`bitslice`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
91242	`bitslice`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
91258	`bitslice`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
91278	`bitslice`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
91290	`bitslice`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
91344	`bitslice`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
91418	`bitslice`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
91600	`bitslice`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
91708	`bitslice`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
91746	`bitslice`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
91792	`bitslice`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
91800	`bitslice`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
92050	`bitslice`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
92120	`bitslice`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
92132	`bitslice`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
92158	`bitslice`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
92168	`bitslice`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
92242	`bitslice`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
92268	`bitslice`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
92324	`bitslice`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
92408	`bitslice`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
92662	`bitslice`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
92664	`bitslice`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
92674	`bitslice`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
92690	`bitslice`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
92852	`bitslice`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
92926	`bitslice`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
93082	`bitslice`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
93084	`bitslice`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
93212	`bitslice`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
93260	`bitslice`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
93266	`bitslice`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
93298	`bitslice`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
93322	`bitslice`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
93362	`bitslice`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
93414	`bitslice`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
93414	`bitslice`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
93428	`bitslice`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
93452	`bitslice`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
93488	`bitslice`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
93554	`bitslice`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
93606	`bitslice`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
93610	`bitslice`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
93646	`bitslice`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
93656	`bitslice`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
93738	`bitslice`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
93754	`bitslice`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
93778	`bitslice`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
93804	`bitslice`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
93806	`bitslice`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
93828	`bitslice`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
93912	`bitslice`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
94144	`bitslice`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
94226	`bitslice`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
94300	`bitslice`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
94398	`bitslice`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
94434	`bitslice`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
94688	`bitslice`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
94704	`bitslice`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
94732	`bitslice`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
94766	`bitslice`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
94962	`bitslice`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
95244	`bitslice`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
95300	`bitslice`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
95328	`bitslice`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
95394	`bitslice`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
95460	`bitslice`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
95962	`bitslice`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
96254	`bitslice`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
96292	`bitslice`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
96296	`bitslice`	`gcc -O -fomit-frame-pointer`	20161216	20161026
97250	`bitslice`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
97694	`bitslice`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
97802	`bitslice`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
104444	`bitslice`	`gcc`	20161216	20161026
105050	`bitslice`	`cc`	20161216	20161026
107368	`bitslice`	`gcc -funroll-loops`	20161216	20161026
114986	`bitslice`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
115340	`bitslice`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
115390	`bitslice`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
115542	`bitslice`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
115636	`bitslice`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
115798	`bitslice`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
115818	`bitslice`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
115986	`bitslice`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
116026	`bitslice`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
116104	`bitslice`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
116110	`bitslice`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
116230	`bitslice`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
116394	`bitslice`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
116422	`bitslice`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
116430	`bitslice`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
116562	`bitslice`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
116568	`bitslice`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
116638	`bitslice`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
116658	`bitslice`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
116798	`bitslice`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
117014	`bitslice`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
117022	`bitslice`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
117094	`bitslice`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
117162	`bitslice`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
119282	`bitslice`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
120416	`bitslice`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
126750	`bitslice`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
235160	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
235908	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
237242	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
237648	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
237770	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
238060	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
238288	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
238726	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
239498	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
239800	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
240356	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
240686	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
241566	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
242214	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
242936	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
243002	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
243256	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
243624	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
243680	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
244488	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
244500	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
244652	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
244924	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
245814	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
247840	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
253258	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
253744	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
257102	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
257268	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
258366	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
258670	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
259370	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
259544	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
260086	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
261810	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
262434	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
267112	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
267126	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
268100	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
268478	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
268578	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
268690	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
268952	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
268968	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
269136	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
269144	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
269232	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
269396	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
269658	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
269690	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
269796	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
269802	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
269864	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
269896	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
270498	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
270686	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
270846	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
271050	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
271290	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
271952	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
272118	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
272686	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
272908	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
273252	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
273466	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
273730	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
273758	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
274180	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
274408	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
274628	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
274630	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
274692	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
274966	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
274988	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
275386	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
275526	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
275554	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
275648	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
275878	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
275894	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
275948	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
276366	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
276706	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
276876	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
277532	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
277954	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
278104	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
278306	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
278926	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
279322	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
279540	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
279796	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
280652	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
280700	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
281322	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
281700	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
282282	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
282372	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
282976	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
283030	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
283536	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
284352	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
285072	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
285850	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
286262	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
286580	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
287696	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
288568	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
288752	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
288784	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
288868	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
288890	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
289314	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
290138	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
292314	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
292756	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
294356	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
296238	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
663244	`ref`	`cc`	20161216	20161026
669048	`ref`	`gcc`	20161216	20161026
672708	`ref`	`gcc -funroll-loops`	20161216	20161026

Compiler output

Implementation: crypto_aead/kiasueq128v1/opt
Compiler: cc

kiasu.c: In file included from kiasu.c:28:0:
kiasu.c: kiasu.c: In function 'set_decryption_key':
kiasu.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:77:1: error: inlining failed in call to always_inline '_mm_aesimc_si128': target specific option mismatch
kiasu.c: _mm_aesimc_si128 (__m128i __X)
kiasu.c: ^~~~~~~~~~~~~~~~
kiasu.c: In file included from kiasu.c:30:0:
kiasu.c: aes_ni.macros:5:23: note: called from here
kiasu.c: #define mc_inv(a) _mm_aesimc_si128(a)
kiasu.c: ^~~~~~~~~~~~~~~~~~~
kiasu.c: kiasu.c:70:77: note: in expansion of macro 'mc_inv'
kiasu.c: tmp = assist128(tmp, _mm_aeskeygenassist_si128(tmp,0x1b)); subkeys[1] = mc_inv(tmp);
kiasu.c: ^~~~~~
kiasu.c: In file included from kiasu.c:28:0:
kiasu.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:77:1: error: inlining failed in call to always_inline '_mm_aesimc_si128': target specific option mismatch
kiasu.c: _mm_aesimc_si128 (__m128i __X)
kiasu.c: ^~~~~~~~~~~~~~~~
kiasu.c: In file included from kiasu.c:30:0:
kiasu.c: aes_ni.macros:5:23: note: called from here
kiasu.c: #define mc_inv(a) _mm_aesimc_si128(a)
kiasu.c: ^~~~~~~~~~~~~~~~~~~
kiasu.c: kiasu.c:69:77: note: in expansion of macro 'mc_inv'
kiasu.c: tmp = assist128(tmp, _mm_aeskeygenassist_si128(tmp,0x80)); subkeys[2] = mc_inv(tmp);
kiasu.c: ^~~~~~
kiasu.c: In file included from kiasu.c:28:0:
kiasu.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:77:1: error: inlining failed in call to always_inline '_mm_aesimc_si128': target specific option mismatch
kiasu.c: ...

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

Compiler	Implementations
cc	opt
gcc	opt
gcc -funroll-loops	opt

Compiler output

Implementation: crypto_aead/kiasueq128v1/opt
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

kiasu.c: kiasu.c:119:45: warning: implicit conversion from 'int' to 'char' changes value from 128 to -128 [-Wconstant-conversion]
kiasu.c: const __m128i MSB_XLS1 = constant8( (0x8 kiasu.c: ~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: ./aes_ni.macros:13:171: note: expanded from macro 'constant8'
kiasu.c: #define constant8(b15,b14,b13,b12,b11,b10,b9,b8,b7,b6,b5,b4,b3,b2,b1,b0) _mm_set_epi8 ((b0),(b1),(b2),(b3),(b4),(b5),(b6),(b7),(b8),(b9),(b10),(b11),(b12),(b13),(b14),(b15))
kiasu.c: ~~~~~~~~~~~~ ^~~
kiasu.c: kiasu.c:120:45: warning: implicit conversion from 'int' to 'char' changes value from 144 to -112 [-Wconstant-conversion]
kiasu.c: const __m128i MSB_XLS2 = constant8( (0x9 kiasu.c: ~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: ./aes_ni.macros:13:171: note: expanded from macro 'constant8'
kiasu.c: #define constant8(b15,b14,b13,b12,b11,b10,b9,b8,b7,b6,b5,b4,b3,b2,b1,b0) _mm_set_epi8 ((b0),(b1),(b2),(b3),(b4),(b5),(b6),(b7),(b8),(b9),(b10),(b11),(b12),(b13),(b14),(b15))
kiasu.c: ~~~~~~~~~~~~ ^~~
kiasu.c: kiasu.c:133:12: error: always_inline function '_mm_aesimc_si128' requires target feature 'aes', but would be inlined into function 'XLS' that is compiled without support for 'aes'
kiasu.c: dTweak = mc_inv(Tweak);
kiasu.c: ^
kiasu.c: ./aes_ni.macros:5:23: note: expanded from macro 'mc_inv'
kiasu.c: #define mc_inv(a) _mm_aesimc_si128(a)
kiasu.c: ^
kiasu.c: kiasu.c:135:22: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'XLS' that is compiled without support for 'aes'
kiasu.c: if( Direction){ AES( State , subkeys , Tweak ); }
kiasu.c: ^
kiasu.c: ./aes_ni.macros:21:5: note: expanded from macro 'AES'
kiasu.c: s = enc( s , xor( subkeys[1] , tw ) );\
kiasu.c: ^
kiasu.c: ./aes_ni.macros:1:18: note: expanded from macro 'enc'
kiasu.c: ...

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

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

Compiler output

Implementation: crypto_aead/kiasueq128v1/opt
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments

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

Compiler	Implementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	opt
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	opt
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	opt
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	opt

Compiler output

Implementation: crypto_aead/kiasueq128v1/opt
Compiler: gcc -O2 -fomit-frame-pointer

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

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

Compiler output

Implementation: crypto_aead/kiasueq128v1/opt
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

kiasu.c: In file included from kiasu.c:28:0:
kiasu.c: kiasu.c: In function 'set_encryption_key':
kiasu.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
kiasu.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
kiasu.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: kiasu.c:54:19: note: called from here
kiasu.c: subkeys[10] = assist128(subkeys[9], _mm_aeskeygenassist_si128(subkeys[9],0x36));
kiasu.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: In file included from kiasu.c:28:0:
kiasu.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
kiasu.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
kiasu.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: kiasu.c:53:19: note: called from here
kiasu.c: subkeys[ 9] = assist128(subkeys[8], _mm_aeskeygenassist_si128(subkeys[8],0x1b));
kiasu.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: In file included from kiasu.c:28:0:
kiasu.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
kiasu.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
kiasu.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: kiasu.c:52:19: note: called from here
kiasu.c: subkeys[ 8] = assist128(subkeys[7], _mm_aeskeygenassist_si128(subkeys[7],0x80));
kiasu.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: In file included from kiasu.c:28:0:
kiasu.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
kiasu.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
kiasu.c: ...
kiasu.c: In file included from kiasu.c:28:0:
kiasu.c: kiasu.c: In function 'set_encryption_key':
kiasu.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
kiasu.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
kiasu.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: kiasu.c:54:19: note: called from here
kiasu.c: subkeys[10] = assist128(subkeys[9], _mm_aeskeygenassist_si128(subkeys[9],0x36));
kiasu.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: In file included from kiasu.c:28:0:
kiasu.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
kiasu.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
kiasu.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: kiasu.c:53:19: note: called from here
kiasu.c: subkeys[ 9] = assist128(subkeys[8], _mm_aeskeygenassist_si128(subkeys[8],0x1b));
kiasu.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: In file included from kiasu.c:28:0:
kiasu.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
kiasu.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
kiasu.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: kiasu.c:52:19: note: called from here
kiasu.c: subkeys[ 8] = assist128(subkeys[7], _mm_aeskeygenassist_si128(subkeys[7],0x80));
kiasu.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
kiasu.c: In file included from kiasu.c:28:0:
kiasu.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
kiasu.c: _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
kiasu.c: ...

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

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