Implementation notes: amd64, skylake, crypto_aead/kiasuneq128v1

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: kiasuneq128v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
4640	`opt`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
4642	`opt`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
4642	`opt`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
4644	`opt`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
4648	`opt`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
4650	`opt`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
4650	`opt`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
4658	`opt`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
4658	`opt`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
4658	`opt`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
4728	`opt`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
4730	`opt`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
4732	`opt`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
4754	`opt`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
4756	`opt`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
4864	`opt`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
4878	`opt`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
4888	`opt`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
4890	`opt`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
4892	`opt`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
60894	`bitslice`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
60902	`bitslice`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
60922	`bitslice`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
60938	`bitslice`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
60952	`bitslice`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
60962	`bitslice`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
60968	`bitslice`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
60978	`bitslice`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
60990	`bitslice`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
61002	`bitslice`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
61046	`bitslice`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
61060	`bitslice`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
61070	`bitslice`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
61082	`bitslice`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
61090	`bitslice`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
61100	`bitslice`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
61198	`bitslice`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
61200	`bitslice`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
61212	`bitslice`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
61254	`bitslice`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
61268	`bitslice`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
61296	`bitslice`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
61300	`bitslice`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
61322	`bitslice`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
61398	`bitslice`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
61448	`bitslice`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
61484	`bitslice`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
61568	`bitslice`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
61604	`bitslice`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
61672	`bitslice`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
61718	`bitslice`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
61844	`bitslice`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
61868	`bitslice`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
61892	`bitslice`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
61936	`bitslice`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
62002	`bitslice`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
62018	`bitslice`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
62028	`bitslice`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
62034	`bitslice`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
62100	`bitslice`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
62182	`bitslice`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
62240	`bitslice`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
62266	`bitslice`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
62290	`bitslice`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
62332	`bitslice`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
62394	`bitslice`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
62432	`bitslice`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
62478	`bitslice`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
62506	`bitslice`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
62612	`bitslice`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
62682	`bitslice`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
62790	`bitslice`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
62876	`bitslice`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
62930	`bitslice`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
63118	`bitslice`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
63132	`bitslice`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
63204	`bitslice`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
63206	`bitslice`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
63224	`bitslice`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
63248	`bitslice`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
63248	`bitslice`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
63300	`bitslice`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
63334	`bitslice`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
63456	`bitslice`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
63470	`bitslice`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
63522	`bitslice`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
63530	`bitslice`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
63542	`bitslice`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
63598	`bitslice`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
63636	`bitslice`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
63774	`bitslice`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
63994	`bitslice`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
64186	`bitslice`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
64196	`bitslice`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
64200	`bitslice`	`gcc -O -fomit-frame-pointer`	20161216	20161026
64220	`bitslice`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
64282	`bitslice`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
64328	`bitslice`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
64384	`bitslice`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
64408	`bitslice`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
64428	`bitslice`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
64652	`bitslice`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
64678	`bitslice`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
64814	`bitslice`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
64860	`bitslice`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
65050	`bitslice`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
65440	`bitslice`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
65710	`bitslice`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
65836	`bitslice`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
68212	`bitslice`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
68482	`bitslice`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
72400	`bitslice`	`cc`	20161216	20161026
72410	`bitslice`	`gcc`	20161216	20161026
74076	`bitslice`	`gcc -funroll-loops`	20161216	20161026
78494	`bitslice`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
78602	`bitslice`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
78918	`bitslice`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
78972	`bitslice`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
79006	`bitslice`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
79034	`bitslice`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
79110	`bitslice`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
79162	`bitslice`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
79256	`bitslice`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
79262	`bitslice`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
79320	`bitslice`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
79320	`bitslice`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
79378	`bitslice`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
79430	`bitslice`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
79506	`bitslice`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
79562	`bitslice`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
79686	`bitslice`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
79716	`bitslice`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
79972	`bitslice`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
80034	`bitslice`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
80274	`bitslice`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
80568	`bitslice`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
80842	`bitslice`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
81154	`bitslice`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
81736	`bitslice`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
82102	`bitslice`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
83624	`bitslice`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
152600	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
152722	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
153850	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
154482	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
156070	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
156094	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
156260	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
156264	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
156498	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
156708	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
157468	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
157732	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
158128	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
158238	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
158428	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
158678	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
158694	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
158722	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
159630	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
159714	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
160542	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
161454	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
162090	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
162110	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
162806	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
162816	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
163256	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
163344	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
164164	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
165044	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
165130	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
166358	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
166390	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
166856	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
167376	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
170036	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
172234	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
172384	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
172742	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
172786	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
172908	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
172966	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
173014	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
173028	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
173052	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
173686	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
173798	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
173930	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
174048	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
174180	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
174192	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
174432	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
174484	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
174498	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
174684	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
174938	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
174954	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
175074	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
175130	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
175136	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
175146	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
175166	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
175382	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
175460	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
175508	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
175578	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
175610	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
175686	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
175766	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
175826	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
175890	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
175920	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
175934	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
176020	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
176110	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
176548	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
176662	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
176696	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
176752	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
176914	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
176946	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
177104	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
177314	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
177440	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
177908	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
178374	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
178478	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
178596	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
178700	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
178786	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
178986	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
179258	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
179260	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
180014	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
180874	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
180988	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
181206	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
181434	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
181622	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
181794	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
181916	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
182472	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
182566	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
182610	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
182650	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
182706	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
182742	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
182754	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
182936	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
182950	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
183034	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
183444	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
184644	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
185618	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
185774	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
185982	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
186062	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
186466	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
414328	`ref`	`cc`	20161216	20161026
416082	`ref`	`gcc -funroll-loops`	20161216	20161026
416378	`ref`	`gcc`	20161216	20161026

Compiler output

Implementation: crypto_aead/kiasuneq128v1/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:71:77: 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:70:77: 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/kiasuneq128v1/opt
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

kiasu.c: kiasu.c:91:50: warning: implicit conversion from 'int' to 'char' changes value from 192 to -64 [-Wconstant-conversion]
kiasu.c: const __m128i MSB_AD_LAST = constant8( (0x6 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:94:56: warning: implicit conversion from 'int' to 'char' changes value from 128 to -128 [-Wconstant-conversion]
kiasu.c: const __m128i MSB_M_LAST_NONZERO = constant8( (0x4 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:95:49: warning: implicit conversion from 'int' to 'char' changes value from 160 to -96 [-Wconstant-conversion]
kiasu.c: const __m128i MSB_CHKSUM = constant8( (0x5 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:130:4: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'kiasu_aead_encrypt' that is compiled without support for 'aes'
kiasu.c: 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/kiasuneq128v1/opt
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments

kiasu.c: kiasu.c:91:50: warning: implicit conversion from 'int' to 'char' changes value from 192 to -64 [-Wconstant-conversion]
kiasu.c: const __m128i MSB_AD_LAST = constant8( (0x6 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:94:56: warning: implicit conversion from 'int' to 'char' changes value from 128 to -128 [-Wconstant-conversion]
kiasu.c: const __m128i MSB_M_LAST_NONZERO = constant8( (0x4 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:95:49: warning: implicit conversion from 'int' to 'char' changes value from 160 to -96 [-Wconstant-conversion]
kiasu.c: const __m128i MSB_CHKSUM = constant8( (0x5 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:331:50: warning: implicit conversion from 'int' to 'char' changes value from 192 to -64 [-Wconstant-conversion]
kiasu.c: const __m128i MSB_AD_LAST = constant8( (0x6 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:334:56: warning: implicit conversion from 'int' to 'char' changes value from 128 to -128 [-Wconstant-conversion]
kiasu.c: ...

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/kiasuneq128v1/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/kiasuneq128v1/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:55:19: 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:54:19: 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:53:19: 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:55:19: 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:54:19: 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:53:19: 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