Implementation notes: amd64, skylake, crypto_aead/norx6441v1

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: norx6441v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
17366	`ymm`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
17396	`ymm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
17428	`ymm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
17606	`ymm`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
17614	`ymm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
17620	`ymm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
17658	`ymm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
17670	`ymm`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
17708	`ymm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
19114	`ymm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
19114	`ymm`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
19152	`ymm`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
19204	`ymm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
20364	`ymm`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
20400	`ymm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
20400	`ymm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
21642	`xmm`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
21644	`xmm`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
21672	`xmm`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
21690	`xmm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
21708	`xmm`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
21712	`xmm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
21752	`xmm`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
21756	`xmm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
21776	`xmm`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
21812	`xmm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
21824	`xmm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
22052	`xmm`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
22058	`xmm`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
22184	`xmm`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
22276	`xmm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
22344	`xmm`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
22396	`xmm`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
22412	`xmm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
22420	`xmm`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
22464	`xmm`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
22782	`xmm`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
22782	`xmm`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
22796	`xmm`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
22876	`xmm`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
22980	`xmm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
23060	`xmm`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
23158	`xmm`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
23160	`xmm`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
23364	`xmm`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
23520	`xmm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
23588	`xmm`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
23600	`xmm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
23690	`xmm`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
23714	`xmm`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
23826	`xmm`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
23832	`xmm`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
23920	`xmm`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
24032	`xmm`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
24936	`xmm`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
25002	`xmm`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
25126	`xmm`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
25126	`xmm`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
27148	`xmm`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
27160	`xmm`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
27236	`xmm`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
27302	`xmm`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
28804	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
28874	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
28874	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
29024	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
29112	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
29192	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
29196	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
29222	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
29234	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
29434	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
29492	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
29516	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
29546	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
29554	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
29612	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
29626	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
29628	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
29682	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
29690	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
29700	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
29750	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
29820	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
29820	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
29822	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
29848	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
29874	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
29908	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
29918	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
29982	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
29998	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
30014	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
30020	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
30020	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
30020	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
30028	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
30038	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
30052	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
30058	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
30076	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
30100	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
30104	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
30108	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
30118	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
30124	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
30188	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
30192	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
30196	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
30198	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
30212	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
30254	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
30288	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
30298	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
30312	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
30342	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
30346	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
30390	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
30510	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
30574	`xmm`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
30576	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
30578	`xmm`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
30582	`xmm`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
30598	`xmm`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
30612	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
30636	`xmm`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
30656	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
30682	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
30704	`xmm`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
30714	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
30746	`xmm`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
30770	`xmm`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
30792	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
30800	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
30802	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
30806	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
30834	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
30860	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
30864	`xmm`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
30874	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
30906	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
30926	`xmm`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
31024	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
31042	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
31042	`xmm`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
31048	`xmm`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
31090	`xmm`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
31110	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
31128	`xmm`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
31138	`xmm`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
31178	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
31188	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
31200	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
31228	`xmm`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
31228	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
31230	`xmm`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
31238	`xmm`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
31254	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
31284	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
31286	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
31304	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
31324	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
31326	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
31330	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
31336	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
31340	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
31342	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
31368	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
31370	`xmm`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
31376	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
31406	`xmm`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
31410	`xmm`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
31426	`xmm`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
31492	`xmm`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
31496	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
31506	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
31508	`xmm`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
31522	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
31522	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
31536	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
31538	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
31554	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
31576	`xmm`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
31588	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
31600	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
31638	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
31640	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
31690	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
31694	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
31704	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
31738	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
31758	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
31766	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
31852	`xmm`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
31858	`xmm`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
31906	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
31912	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
31936	`xmm`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
31942	`xmm`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
31958	`xmm`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
31998	`xmm`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
32028	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
32042	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
32044	`xmm`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
32058	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
32068	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
32104	`xmm`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
32182	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
32232	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
32244	`xmm`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
32262	`xmm`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
32266	`xmm`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
32282	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
32288	`xmm`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
32294	`xmm`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
32300	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
32302	`xmm`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
32302	`xmm`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
32320	`xmm`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
32330	`xmm`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
32330	`xmm`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
32370	`xmm`	`gcc -O -fomit-frame-pointer`	20161216	20161026
32384	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
32412	`xmm`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
32444	`xmm`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
32520	`xmm`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
32524	`xmm`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
32530	`xmm`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
32552	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
32588	`xmm`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
32674	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
32724	`xmm`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
32778	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
32862	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
33348	`xmm`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
33354	`xmm`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
33362	`xmm`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
33452	`xmm`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
33468	`xmm`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
33498	`xmm`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
33502	`xmm`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
33616	`xmm`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
40676	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
40690	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
40934	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
40948	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
48968	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
48994	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
49392	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
49426	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
71858	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
72722	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
165906	`ref`	`cc`	20161216	20161026
166876	`ref`	`gcc`	20161216	20161026
167078	`ref`	`gcc -funroll-loops`	20161216	20161026
232994	`xmm`	`gcc`	20161216	20161026
234482	`xmm`	`cc`	20161216	20161026
237806	`xmm`	`gcc -funroll-loops`	20161216	20161026

Compiler output

Implementation: crypto_aead/norx6441v1/ymm
Compiler: cc

norx.c: norx.c: In function 'block_copy':
norx.c: norx.c:48:24: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: #define STOREU(out, x) _mm256_storeu_si256((__m256i*)(out), (x))
norx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
norx.c: norx.c:302:9: note: in expansion of macro 'STOREU'
norx.c: STOREU(out + 0, LOADU(in + 0));
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 /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:48,
norx.c: from norx.c:26:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avxintrin.h:900:1: error: inlining failed in call to always_inline '_mm256_storeu_si256': target specific option mismatch
norx.c: _mm256_storeu_si256 (__m256i *__P, __m256i __A)
norx.c: ^~~~~~~~~~~~~~~~~~~
norx.c: norx.c:48:24: note: called from here
norx.c: #define STOREU(out, x) _mm256_storeu_si256((__m256i*)(out), (x))
norx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
norx.c: norx.c:303:9: note: in expansion of macro 'STOREU'
norx.c: STOREU(out + 32, LOADU(in + 32));
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 /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:48,
norx.c: from norx.c:26:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avxintrin.h:894:1: error: inlining failed in call to always_inline '_mm256_loadu_si256': target specific option mismatch
norx.c: _mm256_loadu_si256 (__m256i const *__P)
norx.c: ^~~~~~~~~~~~~~~~~~
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/norx6441v1/ymm
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

norx.c: norx.c:350:24: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'sse4.2'
norx.c: const __m256i K = LOADU(k + 0);
norx.c: ^
norx.c: norx.c:47:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:355:5: error: always_inline function '_mm256_castsi128_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'sse4.2'
norx.c: INITIALIZE(A, B, C, D, N, K);
norx.c: ^
norx.c: norx.c:270:9: note: expanded from macro 'INITIALIZE'
norx.c: A = _mm256_castsi128_si256(N); \
norx.c: ^
norx.c: norx.c:355:5: error: always_inline function '_mm256_castsi128_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:271:9: note: expanded from macro 'INITIALIZE'
norx.c: A = _mm256_inserti128_si256(A, _mm_set_epi64x(U1, U0), 1); \
norx.c: ^
norx.c: /usr/bin/../lib/clang/3.9.0/include/avx2intrin.h:976:44: note: expanded from macro '_mm256_inserti128_si256'
norx.c: (__v4di)_mm256_castsi128_si256((__m128i)(V2)), \
norx.c: ^
norx.c: norx.c:355:5: error: always_inline function '_mm256_undefined_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:272:9: note: expanded from macro 'INITIALIZE'
norx.c: A = _mm256_permute4x64_epi64(A, _MM_SHUFFLE(3, 1, 0, 2)); \
norx.c: ^
norx.c: /usr/bin/../lib/clang/3.9.0/include/avx2intrin.h:959:44: note: expanded from macro '_mm256_permute4x64_epi64'
norx.c: (__v4di)_mm256_undefined_si256(), \
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/norx6441v1/ymm
Compiler: clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments

norx.c: norx.c:355:5: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'avx2'
norx.c: INITIALIZE(A, B, C, D, N, K);
norx.c: ^
norx.c: norx.c:276:9: note: expanded from macro 'INITIALIZE'
norx.c: D = XOR(D, _mm256_set_epi64x(0, NORX_PARAMETER, 0, 0)); \
norx.c: ^
norx.c: norx.c:66:19: note: expanded from macro 'XOR'
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ^
norx.c: norx.c:355:5: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'avx2'
norx.c: norx.c:277:5: note: expanded from macro 'INITIALIZE'
norx.c: PERMUTE(A, B, C, D); \
norx.c: ^
norx.c: norx.c:202:9: note: expanded from macro 'PERMUTE'
norx.c: F(A, B, C, D); \
norx.c: ^
norx.c: norx.c:189:5: note: expanded from macro 'F'
norx.c: G(A, B, C, D); \
norx.c: ^
norx.c: norx.c:100:14: note: expanded from macro 'G'
norx.c: t0 = XOR( A, B); \
norx.c: ^
norx.c: norx.c:66:19: 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/norx6441v1/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/norx6441v1/ymm
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

norx.c: norx.c: In function 'crypto_aead_norx6441v1_ymm_encrypt':
norx.c: norx.c:350:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: const __m256i K = LOADU(k + 0);
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 /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:48,
norx.c: from norx.c:26:
norx.c: norx.c: In function 'block_copy':
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avxintrin.h:900:1: error: inlining failed in call to always_inline '_mm256_storeu_si256': target specific option mismatch
norx.c: _mm256_storeu_si256 (__m256i *__P, __m256i __A)
norx.c: ^~~~~~~~~~~~~~~~~~~
norx.c: norx.c:48:24: note: called from here
norx.c: #define STOREU(out, x) _mm256_storeu_si256((__m256i*)(out), (x))
norx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
norx.c: norx.c:303:9: note: in expansion of macro 'STOREU'
norx.c: STOREU(out + 32, LOADU(in + 32));
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 /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:48,
norx.c: from norx.c:26:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avxintrin.h:894:1: error: inlining failed in call to always_inline '_mm256_loadu_si256': target specific option mismatch
norx.c: _mm256_loadu_si256 (__m256i const *__P)
norx.c: ^~~~~~~~~~~~~~~~~~
norx.c: norx.c:48:24: note: called from here
norx.c: #define STOREU(out, x) _mm256_storeu_si256((__m256i*)(out), (x))
norx.c: ...
norx.c: norx.c: In function 'crypto_aead_norx6441v1_ymm_encrypt':
norx.c: norx.c:350:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: const __m256i K = LOADU(k + 0);
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 /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:48,
norx.c: from norx.c:26:
norx.c: norx.c: In function 'block_copy':
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avxintrin.h:900:1: error: inlining failed in call to always_inline '_mm256_storeu_si256': target specific option mismatch
norx.c: _mm256_storeu_si256 (__m256i *__P, __m256i __A)
norx.c: ^~~~~~~~~~~~~~~~~~~
norx.c: norx.c:48:24: note: called from here
norx.c: #define STOREU(out, x) _mm256_storeu_si256((__m256i*)(out), (x))
norx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
norx.c: norx.c:303:9: note: in expansion of macro 'STOREU'
norx.c: STOREU(out + 32, LOADU(in + 32));
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 /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:48,
norx.c: from norx.c:26:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avxintrin.h:894:1: error: inlining failed in call to always_inline '_mm256_loadu_si256': target specific option mismatch
norx.c: _mm256_loadu_si256 (__m256i const *__P)
norx.c: ^~~~~~~~~~~~~~~~~~
norx.c: norx.c:48:24: note: called from here
norx.c: #define STOREU(out, x) _mm256_storeu_si256((__m256i*)(out), (x))
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/norx6441v1/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 /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:48,
norx.c: from norx.c:26:
norx.c: norx.c: In function 'crypto_aead_norx6441v1_ymm_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:276:7: note: called from here
norx.c: D = XOR(D, _mm256_set_epi64x(0, NORX_PARAMETER, 0, 0)); \
norx.c: ^
norx.c: norx.c:355:5: note: in expansion of macro 'INITIALIZE'
norx.c: INITIALIZE(A, B, C, D, N, K);
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 /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:48,
norx.c: from norx.c:26:
norx.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/avx2intrin.h:1068:1: error: inlining failed in call to always_inline '_mm256_permute4x64_epi64': target specific option mismatch
norx.c: _mm256_permute4x64_epi64 (__m256i __X, const int __M)
norx.c: ^~~~~~~~~~~~~~~~~~~~~~~~
norx.c: norx.c:272:7: note: called from here
norx.c: A = _mm256_permute4x64_epi64(A, _MM_SHUFFLE(3, 1, 0, 2)); \
norx.c: ^
norx.c: norx.c:355:5: note: in expansion of macro 'INITIALIZE'
norx.c: INITIALIZE(A, B, C, D, N, K);
norx.c: ^~~~~~~~~~
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