Implementation notes: amd64, hydra1, crypto_aead/norx6461v1

Computer: hydra1
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: norx6461v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
57393	`xmm`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
57394	`xmm`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
57394	`xmm`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
57394	`xmm`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
58296	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
58297	`xmm`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
58315	`xmm`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
58316	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
59866	`xmm`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
59867	`xmm`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
59872	`xmm`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
59888	`xmm`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
62992	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
62999	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
63002	`xmm`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
63032	`xmm`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161020	20161009
63230	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
63262	`xmm`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161020	20161009
63327	`xmm`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161020	20161009
63327	`xmm`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161020	20161009
63328	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
63416	`xmm`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
63443	`xmm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161020	20161009
63453	`xmm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161020	20161009
63464	`xmm`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
63483	`xmm`	`gcc -O -fomit-frame-pointer`	20161020	20161009
63499	`xmm`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
63503	`xmm`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
63520	`xmm`	`gcc -march=k8 -O -fomit-frame-pointer`	20161020	20161009
63528	`xmm`	`gcc -m64 -O -fomit-frame-pointer`	20161020	20161009
63560	`xmm`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
63582	`xmm`	`gcc -march=nocona -O -fomit-frame-pointer`	20161020	20161009
65558	`xmm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
65590	`xmm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
66258	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
66274	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161020	20161009
66317	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161020	20161009
67370	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161020	20161009
67408	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
67461	`ref`	`gcc -O3 -fomit-frame-pointer`	20161020	20161009
68883	`ref`	`gcc -O2 -fomit-frame-pointer`	20161020	20161009
68885	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161020	20161009
68904	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
68989	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
69005	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
69051	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161020	20161009
69056	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
69072	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
69098	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161020	20161009
69174	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
69189	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
69202	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161020	20161009
69211	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161020	20161009
69232	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161020	20161009
69256	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161020	20161009
69448	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
69469	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
69504	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
69531	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161020	20161009
69541	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161020	20161009
69554	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
69556	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161020	20161009
69579	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
69586	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161020	20161009
69595	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
69607	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
69640	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161020	20161009
69648	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161020	20161009
69877	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
69989	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
70279	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
70279	`xmm`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
70283	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
70293	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
70293	`xmm`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
70318	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
70323	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
70323	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
70424	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161020	20161009
70426	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
70437	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
70439	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
70440	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161020	20161009
70581	`xmm`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
70581	`xmm`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
70581	`xmm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161020	20161009
70600	`xmm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161020	20161009
70603	`xmm`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
70605	`xmm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161020	20161009
70605	`xmm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161020	20161009
70608	`xmm`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
70651	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
70674	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
70928	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
70961	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
71085	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161020	20161009
71091	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
71094	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161020	20161009
71122	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
71160	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
71163	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161020	20161009
71173	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
71176	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161020	20161009
71197	`ref`	`gcc -Os -fomit-frame-pointer`	20161020	20161009
71197	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
71205	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
71232	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
71243	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161020	20161009
71293	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
71304	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
71304	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161020	20161009
71309	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161020	20161009
71341	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161020	20161009
72035	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
72104	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
72923	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
73010	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
73104	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
73134	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
73136	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161020	20161009
73163	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
73573	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
73622	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
73984	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
73990	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161020	20161009
73994	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
73997	`ref`	`gcc -O -fomit-frame-pointer`	20161020	20161009
73997	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
73997	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161020	20161009
74034	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
74037	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161020	20161009
74046	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161020	20161009
74352	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
74368	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161020	20161009
74421	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161020	20161009
74432	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161020	20161009
74456	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161020	20161009
74468	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161020	20161009
75544	`xmm`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
75549	`xmm`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
75990	`xmm`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
75990	`xmm`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
76316	`xmm`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
76341	`xmm`	`gcc -O2 -fomit-frame-pointer`	20161020	20161009
76341	`xmm`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
76342	`xmm`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
76344	`xmm`	`gcc -O3 -fomit-frame-pointer`	20161020	20161009
76344	`xmm`	`gcc -m64 -O2 -fomit-frame-pointer`	20161020	20161009
76344	`xmm`	`gcc -m64 -O3 -fomit-frame-pointer`	20161020	20161009
76352	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
76352	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
76353	`xmm`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
76398	`xmm`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
76398	`xmm`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
76400	`xmm`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
76400	`xmm`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
76953	`xmm`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161020	20161009
76953	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
76953	`xmm`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161020	20161009
76975	`xmm`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161020	20161009
76976	`xmm`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161020	20161009
77003	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
87512	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
87512	`xmm`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
89318	`xmm`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
89320	`xmm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161020	20161009
89320	`xmm`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
89320	`xmm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161020	20161009
95461	`xmm`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161020	20161009
95461	`xmm`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
95461	`xmm`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
95464	`xmm`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
95464	`xmm`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161020	20161009
96029	`xmm`	`gcc -Os -fomit-frame-pointer`	20161020	20161009
96029	`xmm`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
96032	`xmm`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
96032	`xmm`	`gcc -m64 -Os -fomit-frame-pointer`	20161020	20161009
96034	`xmm`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
98291	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
98297	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
98308	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
98384	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
105435	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
105616	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
392686	`ref`	`gcc`	20161020	20161009
392816	`ref`	`gcc -funroll-loops`	20161020	20161009
392862	`ref`	`cc`	20161020	20161009
653385	`xmm`	`gcc`	20161020	20161009
653400	`xmm`	`gcc -funroll-loops`	20161020	20161009
653520	`xmm`	`cc`	20161020	20161009

Test failure

Implementation: crypto_aead/norx6461v1/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/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-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/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/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_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/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/norx6461v1/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_norx6461v1_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_norx6461v1_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_norx6461v1_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_norx6461v1_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/norx6461v1/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/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-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_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-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