Implementation notes: amd64, skylake, crypto_aead/norx6441v2

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: norx6441v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
14826	`ymm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
14840	`ymm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
14882	`ymm`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
14884	`ymm`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
14894	`ymm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
14932	`ymm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
15128	`ymm`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
15138	`ymm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
15172	`ymm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
16452	`ymm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
16454	`ymm`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
16480	`ymm`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
16658	`ymm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
17490	`ymm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
17528	`ymm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
17604	`ymm`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
18728	`xmm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
18758	`xmm`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
18826	`xmm`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
18838	`xmm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
18874	`xmm`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
19098	`xmm`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
19100	`xmm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
19226	`xmm`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
19378	`xmm`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
19420	`xmm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
19422	`xmm`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
19436	`xmm`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
19448	`xmm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
19474	`xmm`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
19490	`xmm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
19506	`xmm`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
19512	`xmm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
19536	`xmm`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
19574	`xmm`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
19574	`xmm`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
19670	`xmm`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
19694	`xmm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
19698	`xmm`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
19788	`xmm`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
19830	`xmm`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
19848	`xmm`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
19858	`xmm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
19966	`xmm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
19972	`xmm`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
20022	`xmm`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
20098	`xmm`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
20196	`xmm`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
20240	`xmm`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
20316	`xmm`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
20774	`xmm`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
20958	`xmm`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
21096	`xmm`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
21170	`xmm`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
22110	`xmm`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
22192	`xmm`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
22284	`xmm`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
22288	`xmm`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
24768	`xmm`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
24880	`xmm`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
24944	`xmm`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
25038	`xmm`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
25504	`xmm`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
25530	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
25576	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
25714	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
25738	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
25804	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
25806	`xmm`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
25810	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
25834	`xmm`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
25858	`xmm`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
25894	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
25922	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
25932	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
25942	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
25956	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
25958	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
26024	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
26028	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
26034	`xmm`	`gcc -O -fomit-frame-pointer`	20161216	20161026
26034	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
26036	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
26050	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
26066	`xmm`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
26068	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
26074	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
26084	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
26084	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
26084	`xmm`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
26092	`xmm`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
26094	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
26094	`xmm`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
26128	`xmm`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
26128	`xmm`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
26218	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
26254	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
26266	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
26300	`xmm`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
26320	`xmm`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
26332	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
26366	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
26370	`xmm`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
26376	`xmm`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
26450	`xmm`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
26468	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
26470	`xmm`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
26476	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
26478	`xmm`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
26518	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
26538	`xmm`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
26540	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
26556	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
26576	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
26590	`xmm`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
26608	`xmm`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
26662	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
26706	`xmm`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
26716	`xmm`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
26724	`xmm`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
26728	`xmm`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
26736	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
26748	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
26748	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
26760	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
26766	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
26784	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
26786	`xmm`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
26808	`xmm`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
26810	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
26828	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
26918	`xmm`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
26930	`xmm`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
26940	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
26946	`xmm`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
26980	`xmm`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
26986	`xmm`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
26986	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
27024	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
27034	`xmm`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
27044	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
27056	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
27060	`xmm`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
27094	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
27098	`xmm`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
27118	`xmm`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
27152	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
27168	`xmm`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
27172	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
27194	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
27210	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
27218	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
27228	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
27234	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
27256	`xmm`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
27272	`xmm`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
27284	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
27298	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
27354	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
27398	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
27404	`xmm`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
27434	`xmm`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
27436	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
27440	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
27450	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
27480	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
27506	`xmm`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
27518	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
27526	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
27536	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
27592	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
27668	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
27714	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
27784	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
27788	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
27794	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
27794	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
27850	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
27872	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
27898	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
27914	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
27970	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
27972	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
27974	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
27992	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
28018	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
28020	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
28030	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
28056	`xmm`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
28144	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
28170	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
28176	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
28204	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
28210	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
28236	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
28240	`xmm`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
28252	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
28276	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
28308	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
28326	`xmm`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
28372	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
28376	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
28424	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
28434	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
28446	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
28480	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
28522	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
28530	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
28594	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
28704	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
28732	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
28756	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
28764	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
28766	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
28796	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
28798	`xmm`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
28818	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
28828	`xmm`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
28862	`xmm`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
28940	`xmm`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
28944	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
28948	`xmm`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
28948	`xmm`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
28962	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
28964	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
29006	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
29034	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
29056	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
29070	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
29154	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
29180	`xmm`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
29536	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
29580	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
29688	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
29796	`xmm`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
29826	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
29832	`xmm`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
29840	`xmm`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
29960	`xmm`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
30008	`xmm`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
30206	`xmm`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
30318	`xmm`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
32860	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
32872	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
32890	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
33180	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
40848	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
40884	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
41336	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
41402	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
64270	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
65006	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
146766	`ref`	`gcc -funroll-loops`	20161216	20161026
147012	`ref`	`gcc`	20161216	20161026
148982	`ref`	`cc`	20161216	20161026
192664	`xmm`	`gcc -funroll-loops`	20161216	20161026
196400	`xmm`	`gcc`	20161216	20161026
197376	`xmm`	`cc`	20161216	20161026

Compiler output

Implementation: crypto_aead/norx6441v2/ymm
Compiler: cc

norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:43:0,
norx.c: from norx.c:25:
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:290:28: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: _mm256_castsi128_si256(LOADU128(NONCE)), 0x0F); \
norx.c: ^
norx.c: norx.c:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
norx.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
norx.c: ^~~~~~~~~~~~~~~~
norx.c: norx.c:294:7: note: called from here
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ^
norx.c: norx.c:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:41:0,
norx.c: from norx.c:25:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avxintrin.h:1270:1: error: inlining failed in call to always_inline '_mm256_set_epi64x': target specific option mismatch
norx.c: _mm256_set_epi64x (long long __A, long long __B, long long __C,
norx.c: ^~~~~~~~~~~~~~~~~
norx.c: norx.c:72:19: note: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ...

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

Compiler	Implementations
cc	ymm
gcc	ymm
gcc -funroll-loops	ymm

Compiler output

Implementation: crypto_aead/norx6441v2/ymm
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

norx.c: norx.c:388:5: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^
norx.c: norx.c:289:28: note: expanded from macro 'INITIALISE'
norx.c: A = _mm256_blend_epi32(_mm256_set_epi64x(U3, U2, 0, 0), \
norx.c: ^
norx.c: norx.c:388:5: error: always_inline function '_mm256_castsi128_si256' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:290:28: note: expanded from macro 'INITIALISE'
norx.c: _mm256_castsi128_si256(LOADU128(NONCE)), 0x0F); \
norx.c: ^
norx.c: norx.c:388:5: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:291:9: note: expanded from macro 'INITIALISE'
norx.c: B = LOADU(KEY); \
norx.c: ^
norx.c: norx.c:53:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:388:5: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:292:9: note: expanded from macro 'INITIALISE'
norx.c: C = _mm256_set_epi64x(U11, U10, U9, U8); \
norx.c: ^
norx.c: norx.c:388:5: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:293:9: note: expanded from macro 'INITIALISE'
norx.c: D = _mm256_set_epi64x(U15, U14, U13, U12); \
norx.c: ^
norx.c: ...

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

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

Compiler output

Implementation: crypto_aead/norx6441v2/ymm
Compiler: clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments

norx.c: norx.c:388:5: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'avx2'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^
norx.c: norx.c:294:9: note: expanded from macro 'INITIALISE'
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ^
norx.c: norx.c:72:19: note: expanded from macro 'XOR'
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ^
norx.c: norx.c:388:5: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'avx2'
norx.c: norx.c:295:5: note: expanded from macro 'INITIALISE'
norx.c: PERMUTE(A, B, C, D); \
norx.c: ^
norx.c: norx.c:209:9: note: expanded from macro 'PERMUTE'
norx.c: F(A, B, C, D); \
norx.c: ^
norx.c: norx.c:197:5: note: expanded from macro 'F'
norx.c: G(A, B, C, D); \
norx.c: ^
norx.c: norx.c:109:14: note: expanded from macro 'G'
norx.c: t0 = XOR( A, B); \
norx.c: ^
norx.c: norx.c:72:19: note: expanded from macro 'XOR'
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ^
norx.c: ...

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	ymm
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	ymm

Compiler output

Implementation: crypto_aead/norx6441v2/ymm
Compiler: gcc -O2 -fomit-frame-pointer

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

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

Compiler output

Implementation: crypto_aead/norx6441v2/ymm
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:289:7: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: A = _mm256_blend_epi32(_mm256_set_epi64x(U3, U2, 0, 0), \
norx.c: ^
norx.c: norx.c:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:43:0,
norx.c: from norx.c:25:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
norx.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
norx.c: ^~~~~~~~~~~~~~~~
norx.c: norx.c:294:7: note: called from here
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ^
norx.c: norx.c:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:41:0,
norx.c: from norx.c:25:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avxintrin.h:1270:1: error: inlining failed in call to always_inline '_mm256_set_epi64x': target specific option mismatch
norx.c: _mm256_set_epi64x (long long __A, long long __B, long long __C,
norx.c: ^~~~~~~~~~~~~~~~~
norx.c: norx.c:72:19: note: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ...
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:289:7: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: A = _mm256_blend_epi32(_mm256_set_epi64x(U3, U2, 0, 0), \
norx.c: ^
norx.c: norx.c:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:43:0,
norx.c: from norx.c:25:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
norx.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
norx.c: ^~~~~~~~~~~~~~~~
norx.c: norx.c:294:7: note: called from here
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ^
norx.c: norx.c:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:41:0,
norx.c: from norx.c:25:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avxintrin.h:1270:1: error: inlining failed in call to always_inline '_mm256_set_epi64x': target specific option mismatch
norx.c: _mm256_set_epi64x (long long __A, long long __B, long long __C,
norx.c: ^~~~~~~~~~~~~~~~~
norx.c: norx.c:72:19: note: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ...

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

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

Compiler output

Implementation: crypto_aead/norx6441v2/ymm
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer

norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:43:0,
norx.c: from norx.c:25:
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
norx.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
norx.c: ^~~~~~~~~~~~~~~~
norx.c: norx.c:294:7: note: called from here
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ^
norx.c: norx.c:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:43:0,
norx.c: from norx.c:25:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avx2intrin.h:971:1: error: inlining failed in call to always_inline '_mm256_blend_epi32': target specific option mismatch
norx.c: _mm256_blend_epi32 (__m256i __X, __m256i __Y, const int __M)
norx.c: ^~~~~~~~~~~~~~~~~~
norx.c: norx.c:289:7: note: called from here
norx.c: A = _mm256_blend_epi32(_mm256_set_epi64x(U3, U2, 0, 0), \
norx.c: ^
norx.c: norx.c:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:43:0,
norx.c: from norx.c:25:
norx.c: ...

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	ymm
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	ymm
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	ymm
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	ymm
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	ymm
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	ymm