Implementation notes: amd64, hydra1, crypto_aead/norx6461v2

Computer: hydra1
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: norx6461v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
50058	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
50058	`xmm`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
50080	`xmm`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
50082	`xmm`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
50259	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
50275	`xmm`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
51498	`xmm`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161020	20161009
51501	`xmm`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161020	20161009
51509	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
51522	`xmm`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161020	20161009
51531	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
51536	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
51552	`xmm`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
52051	`xmm`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
52071	`xmm`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161020	20161009
52336	`xmm`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
52344	`xmm`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
53330	`xmm`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
53330	`xmm`	`gcc -march=k8 -O -fomit-frame-pointer`	20161020	20161009
53352	`xmm`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
53358	`xmm`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
53358	`xmm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161020	20161009
53364	`xmm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161020	20161009
53366	`xmm`	`gcc -O -fomit-frame-pointer`	20161020	20161009
53371	`xmm`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
53389	`xmm`	`gcc -m64 -O -fomit-frame-pointer`	20161020	20161009
53486	`xmm`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
53496	`xmm`	`gcc -march=nocona -O -fomit-frame-pointer`	20161020	20161009
54392	`xmm`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
54392	`xmm`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
54397	`xmm`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
54402	`xmm`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
56661	`xmm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
56677	`xmm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
58032	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161020	20161009
58038	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161020	20161009
58048	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
58698	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
58719	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161020	20161009
58722	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161020	20161009
58744	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
58773	`ref`	`gcc -O3 -fomit-frame-pointer`	20161020	20161009
58784	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161020	20161009
59276	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
59306	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161020	20161009
59306	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161020	20161009
59308	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
59325	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
59349	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
59790	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
59815	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
59874	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
59909	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
59915	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
59976	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
60069	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
60101	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
60518	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
60576	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161020	20161009
60630	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161020	20161009
60642	`xmm`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
60643	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
60653	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161020	20161009
60666	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161020	20161009
60667	`xmm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161020	20161009
60670	`xmm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161020	20161009
60674	`xmm`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
60675	`xmm`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
60688	`ref`	`gcc -O2 -fomit-frame-pointer`	20161020	20161009
60702	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161020	20161009
61200	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
61216	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
61224	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
61229	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
61250	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
61317	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
61364	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
61369	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
61422	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
61422	`xmm`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161020	20161009
61494	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
61496	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161020	20161009
61528	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
61538	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161020	20161009
61689	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161020	20161009
61739	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
62054	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
62064	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161020	20161009
62077	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161020	20161009
62092	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
62112	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
62117	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
62160	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
62176	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
62176	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161020	20161009
62560	`xmm`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
62560	`xmm`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161020	20161009
62560	`xmm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161020	20161009
62565	`xmm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161020	20161009
63734	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
63765	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161020	20161009
64453	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161020	20161009
64456	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161020	20161009
64563	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161020	20161009
64568	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161020	20161009
64829	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161020	20161009
64829	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161020	20161009
64830	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161020	20161009
64843	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
64845	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161020	20161009
64848	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161020	20161009
64856	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
64861	`ref`	`gcc -O -fomit-frame-pointer`	20161020	20161009
64867	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161020	20161009
64870	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
64878	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161020	20161009
64888	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161020	20161009
64919	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161020	20161009
64920	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161020	20161009
64923	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161020	20161009
64955	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161020	20161009
65622	`xmm`	`gcc -m64 -O3 -fomit-frame-pointer`	20161020	20161009
65623	`xmm`	`gcc -O3 -fomit-frame-pointer`	20161020	20161009
65624	`xmm`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
65648	`xmm`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
65648	`xmm`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
66181	`xmm`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161020	20161009
66181	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161020	20161009
66181	`xmm`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161020	20161009
66192	`xmm`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
66194	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161020	20161009
66426	`xmm`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161020	20161009
66426	`xmm`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161020	20161009
66429	`xmm`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
66441	`xmm`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
66443	`xmm`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
66816	`xmm`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
66829	`xmm`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161020	20161009
66832	`xmm`	`gcc -O2 -fomit-frame-pointer`	20161020	20161009
66837	`xmm`	`gcc -m64 -O2 -fomit-frame-pointer`	20161020	20161009
66842	`xmm`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161020	20161009
67008	`ref`	`gcc -Os -fomit-frame-pointer`	20161020	20161009
67010	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161020	20161009
67072	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
67316	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161020	20161009
67328	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161020	20161009
67331	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161020	20161009
67333	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161020	20161009
67828	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
67835	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161020	20161009
68018	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
68040	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161020	20161009
68072	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
68186	`xmm`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
68188	`xmm`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
68221	`xmm`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
68222	`xmm`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
68342	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
68440	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
68469	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
68482	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161020	20161009
68597	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
76673	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
76711	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
76726	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
76880	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
79402	`xmm`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
79435	`xmm`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
79709	`xmm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161020	20161009
79712	`xmm`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
79731	`xmm`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161020	20161009
79762	`xmm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161020	20161009
84317	`xmm`	`gcc -Os -fomit-frame-pointer`	20161020	20161009
84320	`xmm`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
84322	`xmm`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
84326	`xmm`	`gcc -m64 -Os -fomit-frame-pointer`	20161020	20161009
84334	`xmm`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
85024	`xmm`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
85025	`xmm`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161020	20161009
85026	`xmm`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161020	20161009
85038	`xmm`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161020	20161009
85058	`xmm`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161020	20161009
86897	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161020	20161009
86957	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161020	20161009
345111	`ref`	`gcc -funroll-loops`	20161020	20161009
345314	`ref`	`cc`	20161020	20161009
345472	`ref`	`gcc`	20161020	20161009
560090	`xmm`	`gcc`	20161020	20161009
560139	`xmm`	`cc`	20161020	20161009
560473	`xmm`	`gcc -funroll-loops`	20161020	20161009

Test failure

Implementation: crypto_aead/norx6461v2/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/norx6461v2/ymm
Compiler: cc

norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/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-linux-gnu/5/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: error: 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-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from norx.c:25:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: 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 -march=native -fomit-frame-pointer -Qunused-arguments

norx.c: norx.c:388:5: error: always_inline function '_mm256_set_epi64x' requires target feature 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
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 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
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 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
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 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
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 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
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: 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/norx6461v2/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/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-linux-gnu/5/include/immintrin.h:43:0,
norx.c: from norx.c:25:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: 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-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from norx.c:25:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: 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-linux-gnu/5/include/immintrin.h:43:0,
norx.c: from norx.c:25:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: 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-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from norx.c:25:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/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: error: 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