Implementation notes: amd64, skylake, crypto_aead/norx6461v2

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: norx6461v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
22364	`ymm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
22390	`ymm`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
22426	`ymm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
22474	`ymm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
22546	`ymm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
22732	`ymm`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
22770	`ymm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
22774	`ymm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
22842	`ymm`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
24726	`ymm`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
24748	`ymm`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
24888	`ymm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
24930	`ymm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
26178	`ymm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
26294	`ymm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
26720	`ymm`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
28106	`xmm`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
28154	`xmm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
28156	`xmm`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
28164	`xmm`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
28648	`xmm`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
28654	`xmm`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
28654	`xmm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
28662	`xmm`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
28678	`xmm`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
28684	`xmm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
28698	`xmm`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
28718	`xmm`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
28764	`xmm`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
28834	`xmm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
28882	`xmm`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
28890	`xmm`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
28918	`xmm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
28974	`xmm`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
29008	`xmm`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
29010	`xmm`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
29018	`xmm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
29090	`xmm`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
29108	`xmm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
29186	`xmm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
29194	`xmm`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
29234	`xmm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
29258	`xmm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
29352	`xmm`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
29596	`xmm`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
29684	`xmm`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
29748	`xmm`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
29754	`xmm`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
30102	`xmm`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
30134	`xmm`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
30694	`xmm`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
30842	`xmm`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
30942	`xmm`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
31358	`xmm`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
33226	`xmm`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
33372	`xmm`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
33454	`xmm`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
33612	`xmm`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
36096	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
36142	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
36372	`xmm`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
36390	`xmm`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
36470	`xmm`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
36532	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
36606	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
36612	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
36676	`xmm`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
36776	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
36848	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
36966	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
37020	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
37244	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
37254	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
37254	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
37318	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
37414	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
37504	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
37518	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
37532	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
37534	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
37558	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
37616	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
37626	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
37646	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
37668	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
37676	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
37748	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
37824	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
37840	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
37934	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
38136	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
38156	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
38258	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
38262	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
38354	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
38448	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
38532	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
38618	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
38676	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
38738	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
38754	`xmm`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
38816	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
38820	`xmm`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
38820	`xmm`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
38852	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
38874	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
38882	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
38922	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
38962	`xmm`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
38970	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
38986	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
39014	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
39020	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
39026	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
39058	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
39084	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
39096	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
39186	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
39202	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
39206	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
39216	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
39228	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
39260	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
39278	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
39348	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
39378	`xmm`	`gcc -O -fomit-frame-pointer`	20161216	20161026
39390	`xmm`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
39392	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
39448	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
39456	`xmm`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
39488	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
39512	`xmm`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
39516	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
39534	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
39536	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
39544	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
39558	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
39564	`xmm`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
39572	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
39572	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
39586	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
39598	`xmm`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
39668	`xmm`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
39670	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
39742	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
39752	`xmm`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
39764	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
39796	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
39806	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
39820	`xmm`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
39836	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
39860	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
39862	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
39932	`xmm`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
39934	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
39936	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
39962	`xmm`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
39974	`xmm`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
39982	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
39986	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
40056	`xmm`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
40058	`xmm`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
40060	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
40090	`xmm`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
40170	`xmm`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
40204	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
40226	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
40326	`xmm`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
40394	`xmm`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
40434	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
40490	`xmm`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
40502	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
40540	`xmm`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
40550	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
40586	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
40638	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
40662	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
40792	`xmm`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
40832	`xmm`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
40862	`xmm`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
40864	`xmm`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
40886	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
40888	`xmm`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
40922	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
40926	`xmm`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
40962	`xmm`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
40996	`xmm`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
41074	`xmm`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
41076	`xmm`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
41110	`xmm`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
41124	`xmm`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
41146	`xmm`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
41166	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
41174	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
41178	`xmm`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
41190	`xmm`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
41212	`xmm`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
41236	`xmm`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
41274	`xmm`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
41462	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
41478	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
41610	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
41618	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
41632	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
41672	`xmm`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
41730	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
41738	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
41740	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
41746	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
41764	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
41766	`xmm`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
41772	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
41774	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
41798	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
41798	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
41800	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
41834	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
41854	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
41870	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
41884	`xmm`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
42102	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
42196	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
42218	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
42278	`xmm`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
42398	`xmm`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
42492	`xmm`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
42512	`xmm`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
42526	`xmm`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
42560	`xmm`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
42804	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
43002	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
43160	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
43204	`xmm`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
43534	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
43656	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
43960	`xmm`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
44016	`xmm`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
44026	`xmm`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
44030	`xmm`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
44062	`xmm`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
44400	`xmm`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
44776	`xmm`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
48304	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
48312	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
48600	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
49546	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
59994	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
60434	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
60668	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
61354	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
95398	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
96522	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
210452	`ref`	`gcc -funroll-loops`	20161216	20161026
211262	`ref`	`gcc`	20161216	20161026
213956	`ref`	`cc`	20161216	20161026
280322	`xmm`	`cc`	20161216	20161026
288376	`xmm`	`gcc -funroll-loops`	20161216	20161026
302726	`xmm`	`gcc`	20161216	20161026

Compiler output

Implementation: crypto_aead/norx6461v2/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/norx6461v2/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/norx6461v2/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/norx6461v2/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/norx6461v2/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/norx6461v2/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