Implementation notes: amd64, skylake, crypto_aead/norx6461v1

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: norx6461v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
26248	`ymm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
26266	`ymm`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
26276	`ymm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
26278	`ymm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
26300	`ymm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
26314	`ymm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
26330	`ymm`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
26438	`ymm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
26606	`ymm`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
28630	`ymm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
28630	`ymm`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
28810	`ymm`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
28878	`ymm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
30534	`ymm`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
30652	`ymm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
30840	`ymm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
32420	`xmm`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
32436	`xmm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
32446	`xmm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
32450	`xmm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
32586	`xmm`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
32592	`xmm`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
32600	`xmm`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
32608	`xmm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
32670	`xmm`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
32758	`xmm`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
32846	`xmm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
32906	`xmm`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
33082	`xmm`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
33098	`xmm`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
33102	`xmm`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
33106	`xmm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
33106	`xmm`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
33126	`xmm`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
33182	`xmm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
33640	`xmm`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
33954	`xmm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
34156	`xmm`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
34172	`xmm`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
34214	`xmm`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
34250	`xmm`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
34256	`xmm`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
34260	`xmm`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
34328	`xmm`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
34350	`xmm`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
34974	`xmm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
34978	`xmm`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
35050	`xmm`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
35116	`xmm`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
35168	`xmm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
35456	`xmm`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
35490	`xmm`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
35502	`xmm`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
35504	`xmm`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
37486	`xmm`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
37526	`xmm`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
37864	`xmm`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
38080	`xmm`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
40690	`xmm`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
40886	`xmm`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
40916	`xmm`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
40916	`xmm`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
41540	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
41568	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
41620	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
41716	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
41842	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
42026	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
42274	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
42288	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
42306	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
42310	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
42318	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
42356	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
42364	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
42550	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
42566	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
42664	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
42746	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
42828	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
42906	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
43218	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
43218	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
43250	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
43252	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
43254	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
43256	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
43278	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
43292	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
43304	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
43306	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
43308	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
43312	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
43320	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
43346	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
43402	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
43420	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
43436	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
43448	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
43486	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
43498	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
43534	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
43576	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
43696	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
43710	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
43806	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
43830	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
43854	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
43876	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
43884	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
43894	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
43922	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
43926	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
43946	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
43952	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
43974	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
43978	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
43996	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
44002	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
44156	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
44190	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
44208	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
44214	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
44220	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
44228	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
44270	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
44374	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
44382	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
44432	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
44590	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
44704	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
44712	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
44992	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
45026	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
45028	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
45034	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
45036	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
45070	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
45076	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
45082	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
45104	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
45156	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
45182	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
45212	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
45286	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
45314	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
45340	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
45348	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
45380	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
45412	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
45450	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
45486	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
45494	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
45512	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
45526	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
45526	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
45550	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
45654	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
45680	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
45688	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
45698	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
45894	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
45952	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
45956	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
46032	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
46094	`xmm`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
46148	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
46238	`xmm`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
46252	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
46298	`xmm`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
46324	`xmm`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
46330	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
46462	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
46524	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
46538	`xmm`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
46642	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
46652	`xmm`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
46676	`xmm`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
46694	`xmm`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
46696	`xmm`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
46708	`xmm`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
46720	`xmm`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
46748	`xmm`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
46750	`xmm`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
46754	`xmm`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
46770	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
46802	`xmm`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
46826	`xmm`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
46844	`xmm`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
46848	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
46954	`xmm`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
46964	`xmm`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
46992	`xmm`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
47020	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
47158	`xmm`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
47164	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
47340	`xmm`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
47356	`xmm`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
47572	`xmm`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
47728	`xmm`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
47842	`xmm`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
47870	`xmm`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
48100	`xmm`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
48122	`xmm`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
48212	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
48242	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
48250	`xmm`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
48390	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
48418	`xmm`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
48522	`xmm`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
48524	`xmm`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
48534	`xmm`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
48550	`xmm`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
48616	`xmm`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
48666	`xmm`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
48670	`xmm`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
48674	`xmm`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
48686	`xmm`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
48696	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
48720	`xmm`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
48728	`xmm`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
48740	`xmm`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
48756	`xmm`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
48844	`xmm`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
48896	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
48904	`xmm`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
48922	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
48958	`xmm`	`gcc -O -fomit-frame-pointer`	20161216	20161026
49016	`xmm`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
49036	`xmm`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
49104	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
49134	`xmm`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
49166	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
49396	`xmm`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
49546	`xmm`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
49612	`xmm`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
49930	`xmm`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
49974	`xmm`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
50012	`xmm`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
50040	`xmm`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
50080	`xmm`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
50330	`xmm`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
58852	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
58880	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
58898	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
59286	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
72118	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
72174	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
72694	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
73156	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
106550	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
107314	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
237458	`ref`	`cc`	20161216	20161026
238508	`ref`	`gcc`	20161216	20161026
239840	`ref`	`gcc -funroll-loops`	20161216	20161026
344676	`xmm`	`gcc`	20161216	20161026
346096	`xmm`	`cc`	20161216	20161026
351284	`xmm`	`gcc -funroll-loops`	20161216	20161026

Compiler output

Implementation: crypto_aead/norx6461v1/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/norx6461v1/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_norx6461v1_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_norx6461v1_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_norx6461v1_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_norx6461v1_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/norx6461v1/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_norx6461v1_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_norx6461v1_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/norx6461v1/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/norx6461v1/ymm
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

norx.c: norx.c: In function 'crypto_aead_norx6461v1_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_norx6461v1_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/norx6461v1/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_norx6461v1_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