Implementation notes: amd64, hydra1, crypto_aead/norx6441v1

Computer: hydra1
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: norx6441v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
38424	`xmm`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
38432	`xmm`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
38434	`xmm`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
38434	`xmm`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
38872	`xmm`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
38877	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
38888	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
38888	`xmm`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
40099	`xmm`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
40099	`xmm`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
40101	`xmm`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
40101	`xmm`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
42281	`xmm`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161020	20161009
42322	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
42472	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
42472	`xmm`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
42646	`xmm`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
42648	`xmm`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161020	20161009
42656	`xmm`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161020	20161009
42661	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
42715	`xmm`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161020	20161009
42725	`xmm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161020	20161009
42740	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
42762	`xmm`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
42766	`xmm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161020	20161009
42772	`xmm`	`gcc -march=k8 -O -fomit-frame-pointer`	20161020	20161009
42781	`xmm`	`gcc -m64 -O -fomit-frame-pointer`	20161020	20161009
42792	`xmm`	`gcc -O -fomit-frame-pointer`	20161020	20161009
42805	`xmm`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
42810	`xmm`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
42832	`xmm`	`gcc -march=nocona -O -fomit-frame-pointer`	20161020	20161009
42834	`xmm`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
43824	`xmm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
43824	`xmm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
46885	`xmm`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
46885	`xmm`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
46886	`xmm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161020	20161009
46887	`xmm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161020	20161009
46889	`xmm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161020	20161009
46890	`xmm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161020	20161009
46891	`xmm`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
46892	`xmm`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
47050	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
47077	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161020	20161009
47091	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161020	20161009
47245	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
47248	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
47261	`xmm`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
47261	`xmm`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
47560	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
47616	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
47779	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
47808	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
47848	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161020	20161009
47880	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
47911	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161020	20161009
47960	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
47971	`ref`	`gcc -O3 -fomit-frame-pointer`	20161020	20161009
47981	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161020	20161009
48112	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
48136	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
48458	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161020	20161009
48467	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161020	20161009
48469	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161020	20161009
48469	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161020	20161009
48533	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
48536	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
48554	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
48576	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
48696	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
48701	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
48728	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
48733	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
48744	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
48768	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
48776	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
48787	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
48808	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161020	20161009
48808	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161020	20161009
48893	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161020	20161009
48894	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
48896	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161020	20161009
48923	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161020	20161009
48927	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161020	20161009
48928	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
48934	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161020	20161009
48939	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161020	20161009
48953	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
48971	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161020	20161009
48987	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
48989	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
49014	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161020	20161009
49015	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161020	20161009
49024	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161020	20161009
49024	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
49051	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
49058	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
49072	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
49077	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161020	20161009
49098	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
49102	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
49237	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161020	20161009
49271	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
49416	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
49424	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161020	20161009
49458	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
49458	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161020	20161009
49461	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
49464	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
49467	`ref`	`gcc -Os -fomit-frame-pointer`	20161020	20161009
49469	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161020	20161009
49472	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161020	20161009
49477	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
49480	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
49482	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
49485	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
49487	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161020	20161009
49512	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161020	20161009
49733	`ref`	`gcc -O2 -fomit-frame-pointer`	20161020	20161009
49733	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
49738	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
49751	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161020	20161009
50338	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
50355	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
50400	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
50469	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161020	20161009
50485	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161020	20161009
50507	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161020	20161009
50572	`xmm`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
50572	`xmm`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
50573	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161020	20161009
50707	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
50723	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
50768	`ref`	`gcc -O -fomit-frame-pointer`	20161020	20161009
50769	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
50803	`xmm`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
50803	`xmm`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
50819	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161020	20161009
50894	`xmm`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
50896	`xmm`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
50912	`xmm`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
50917	`xmm`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
50939	`xmm`	`gcc -O2 -fomit-frame-pointer`	20161020	20161009
50939	`xmm`	`gcc -O3 -fomit-frame-pointer`	20161020	20161009
50939	`xmm`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
50939	`xmm`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
50939	`xmm`	`gcc -m64 -O2 -fomit-frame-pointer`	20161020	20161009
50939	`xmm`	`gcc -m64 -O3 -fomit-frame-pointer`	20161020	20161009
51026	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
51088	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
51207	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
51207	`xmm`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
51212	`xmm`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161020	20161009
51212	`xmm`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161020	20161009
51213	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
51226	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
51226	`xmm`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
51235	`xmm`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161020	20161009
51235	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
51235	`xmm`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161020	20161009
51242	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
51296	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161020	20161009
58517	`xmm`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
58520	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
59670	`xmm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161020	20161009
59670	`xmm`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
59670	`xmm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161020	20161009
59672	`xmm`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
63832	`xmm`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161020	20161009
63834	`xmm`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
63837	`xmm`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
63842	`xmm`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
63843	`xmm`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161020	20161009
64198	`xmm`	`gcc -Os -fomit-frame-pointer`	20161020	20161009
64198	`xmm`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
64198	`xmm`	`gcc -m64 -Os -fomit-frame-pointer`	20161020	20161009
64198	`xmm`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
64198	`xmm`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
67077	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
67117	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
67124	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
67218	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
71936	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
71957	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
273560	`ref`	`gcc -funroll-loops`	20161020	20161009
273657	`ref`	`cc`	20161020	20161009
273926	`ref`	`gcc`	20161020	20161009
441682	`xmm`	`gcc -funroll-loops`	20161020	20161009
442026	`xmm`	`gcc`	20161020	20161009
442116	`xmm`	`cc`	20161020	20161009

Test failure

Implementation: crypto_aead/norx6441v1/xmm
Compiler: gcc -m64 -march=core2 -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 14, namely:

Compiler	Implementations
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	xmm
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	ref xmm
gcc -m64 -march=core2 -O -fomit-frame-pointer	xmm
gcc -m64 -march=core2 -Os -fomit-frame-pointer	xmm
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	xmm
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	xmm
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	xmm
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	xmm
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	xmm
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	xmm
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	xmm
gcc -m64 -march=corei7 -O -fomit-frame-pointer	xmm
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	xmm

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-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/x86intrin.h:46,
norx.c: from norx.c:26:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: 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-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/x86intrin.h:46,
norx.c: from norx.c:26:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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/lib/llvm-3.8/bin/../lib/clang/3.8.0/include/avx2intrin.h:892:44: 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_setzero_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/lib/llvm-3.8/bin/../lib/clang/3.8.0/include/avx2intrin.h:877:44: note: expanded from macro '_mm256_permute4x64_epi64'
norx.c: (__v4di)_mm256_setzero_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 -march=native -fomit-frame-pointer -Qunused-arguments

norx.c: norx.c:350:24: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'xsave'
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 'xsave', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'xsave'
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 'xsave', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'xsave'
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/lib/llvm-3.8/bin/../lib/clang/3.8.0/include/avx2intrin.h:892:44: 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_setzero_si256' requires target feature 'xsave', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'xsave'
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/lib/llvm-3.8/bin/../lib/clang/3.8.0/include/avx2intrin.h:877:44: note: expanded from macro '_mm256_permute4x64_epi64'
norx.c: (__v4di)_mm256_setzero_si256(), \
norx.c: ...

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

Compiler	Implementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	ymm
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ymm

Compiler output

Implementation: crypto_aead/norx6441v1/ymm
Compiler: gcc -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 89, 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 -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 -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 -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=native -mtune=native -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	ymm
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	ymm
gcc -m64 -march=native -mtune=native -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=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	ymm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	ymm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	ymm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	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-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/x86intrin.h:46,
norx.c: from norx.c:26:
norx.c: norx.c: In function 'block_copy':
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: 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-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/x86intrin.h:46,
norx.c: from norx.c:26:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: 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-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/x86intrin.h:46,
norx.c: from norx.c:26:
norx.c: norx.c: In function 'block_copy':
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: 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-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/x86intrin.h:46,
norx.c: from norx.c:26:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: 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