Implementation notes: amd64, hydra1, crypto_aead/hs1sivhiv2

Computer: hydra1
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: hs1sivhiv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
33341	`faster`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
33342	`faster`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161016	20161009
33342	`faster`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
33362	`faster`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
33536	`faster`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161016	20161009
33541	`faster`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
34333	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
34391	`faster`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
34442	`faster`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161016	20161009
34448	`faster`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161016	20161009
34469	`faster`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161016	20161009
34595	`faster`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
34605	`faster`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
34606	`faster`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161016	20161009
34611	`faster`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161016	20161009
34611	`faster`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
34618	`faster`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
34653	`faster`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
34668	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
34858	`faster`	`gcc -m64 -O3 -fomit-frame-pointer`	20161016	20161009
34866	`faster`	`gcc -O3 -fomit-frame-pointer`	20161016	20161009
34882	`faster`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161016	20161009
34912	`faster`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
34922	`faster`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
34933	`faster`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
34946	`faster`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
34955	`faster`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161016	20161009
34958	`faster`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161016	20161009
34968	`faster`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161016	20161009
34970	`faster`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
34998	`faster`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
35016	`faster`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
35037	`faster`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
35217	`faster`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
35238	`faster`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
35250	`faster`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161016	20161009
35256	`faster`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161016	20161009
35261	`faster`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
35262	`faster`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
35485	`faster`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
35490	`faster`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
35512	`faster`	`gcc -m64 -O2 -fomit-frame-pointer`	20161016	20161009
35517	`faster`	`gcc -O2 -fomit-frame-pointer`	20161016	20161009
35517	`faster`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161016	20161009
35592	`faster`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
35782	`faster`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
35794	`faster`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161016	20161009
35794	`faster`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161016	20161009
35809	`faster`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
35819	`faster`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161016	20161009
35832	`faster`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
35898	`faster`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
35933	`faster`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
35944	`faster`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161016	20161009
35945	`faster`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
35956	`faster`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
35966	`faster`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161016	20161009
35968	`faster`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
36005	`faster`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
36021	`faster`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
36032	`faster`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
36040	`faster`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161016	20161009
36059	`faster`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161016	20161009
36072	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
36084	`faster`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
36092	`faster`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161016	20161009
36108	`faster`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
36142	`faster`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
36171	`faster`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161016	20161009
36174	`faster`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161016	20161009
36218	`faster`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
36222	`faster`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
36272	`faster`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
36280	`faster`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161016	20161009
36285	`faster`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
36285	`faster`	`gcc -march=k8 -O -fomit-frame-pointer`	20161016	20161009
36312	`faster`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161016	20161009
36332	`faster`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
36404	`faster`	`gcc -m64 -Os -fomit-frame-pointer`	20161016	20161009
36414	`faster`	`gcc -march=nocona -O -fomit-frame-pointer`	20161016	20161009
36433	`faster`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161016	20161009
36435	`faster`	`gcc -Os -fomit-frame-pointer`	20161016	20161009
36524	`faster`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
36997	`faster`	`gcc -O -fomit-frame-pointer`	20161016	20161009
37014	`faster`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161016	20161009
37104	`faster`	`gcc -m64 -O -fomit-frame-pointer`	20161016	20161009
57182	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161016	20161009
57203	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161016	20161009
57238	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161016	20161009
57849	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
57917	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
57917	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
58424	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
59518	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
59536	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
60647	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
60659	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
60661	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161016	20161009
61141	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161016	20161009
61334	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
61360	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161016	20161009
61413	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
61477	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161016	20161009
61563	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
61669	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
62604	`ref`	`gcc -O3 -fomit-frame-pointer`	20161016	20161009
62612	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161016	20161009
62630	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161016	20161009
62704	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
62803	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
62897	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
63157	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
65652	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161016	20161009
65662	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
65773	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
66061	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161016	20161009
66068	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161016	20161009
66334	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
66396	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
67213	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
67240	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
79190	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
82877	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
83017	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
83645	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
84088	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
84267	`ref`	`gcc -O2 -fomit-frame-pointer`	20161016	20161009
84299	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161016	20161009
84317	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161016	20161009
84680	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
84832	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161016	20161009
85720	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161016	20161009
85796	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161016	20161009
86220	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161016	20161009
87120	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
87189	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161016	20161009
87202	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161016	20161009
87229	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
87565	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161016	20161009
87614	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161016	20161009
87669	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161016	20161009
87693	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161016	20161009
90192	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161016	20161009
90192	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
90211	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161016	20161009
91389	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
91405	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161016	20161009
91429	`ref`	`gcc -Os -fomit-frame-pointer`	20161016	20161009
91429	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
91440	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161016	20161009
91581	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161016	20161009
92354	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
92661	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161016	20161009
92683	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161016	20161009
92701	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161016	20161009
92958	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
93578	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
93686	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161016	20161009
94227	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
96709	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161016	20161009
96952	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
97283	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
98123	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
98253	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161016	20161009
98314	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
98344	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161016	20161009
98479	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
99294	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161016	20161009
99629	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
99669	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161016	20161009
99717	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161016	20161009
99757	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161016	20161009
99822	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161016	20161009
100189	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
100479	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
100480	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
101309	`ref`	`gcc -O -fomit-frame-pointer`	20161016	20161009
101346	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
101440	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161016	20161009
101493	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161016	20161009
101517	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161016	20161009
101640	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
102352	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161016	20161009
106573	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161016	20161009
188696	`faster`	`gcc -funroll-loops`	20161016	20161009
188698	`faster`	`cc`	20161016	20161009
188938	`faster`	`gcc`	20161016	20161009
760493	`ref`	`gcc -funroll-loops`	20161016	20161009
762639	`ref`	`gcc`	20161016	20161009
772842	`ref`	`cc`	20161016	20161009

Test failure

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-sse
Compiler: gcc -m64 -march=core2 -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 27, namely:

Compiler	Implementations
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	dolbeau/amd64-sse faster
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	dolbeau/amd64-sse faster ref
gcc -m64 -march=core2 -O -fomit-frame-pointer	dolbeau/amd64-sse faster
gcc -m64 -march=core2 -Os -fomit-frame-pointer	dolbeau/amd64-sse faster
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	dolbeau/amd64-sse faster
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	dolbeau/amd64-sse faster
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	dolbeau/amd64-sse faster
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	dolbeau/amd64-sse faster
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	dolbeau/amd64-sse faster
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	dolbeau/amd64-sse faster
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	dolbeau/amd64-sse faster
gcc -m64 -march=corei7 -O -fomit-frame-pointer	dolbeau/amd64-sse faster
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	dolbeau/amd64-sse faster

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-sse
Compiler: cc

Number of similar (compiler,implementation) pairs: 79, namely:

Compiler	Implementations
cc	dolbeau/amd64-sse
gcc	dolbeau/amd64-sse
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops	dolbeau/amd64-sse
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/amd64-sse
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/amd64-sse
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/amd64-sse
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/amd64-sse
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-sse

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx2
Compiler: cc

Number of similar (compiler,implementation) pairs: 92, namely:

Compiler	Implementations
cc	dolbeau/amd64-avx2
gcc	dolbeau/amd64-avx2
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops	dolbeau/amd64-avx2
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx2
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx2

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx512
Compiler: cc

Number of similar (compiler,implementation) pairs: 92, namely:

Compiler	Implementations
cc	dolbeau/amd64-avx512
gcc	dolbeau/amd64-avx512
gcc -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops	dolbeau/amd64-avx512
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=k8 -Os -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/amd64-avx512
gcc -march=nocona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -march=nocona -Os -fomit-frame-pointer	dolbeau/amd64-avx512

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-sse
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: In file included from encrypt.c:192:
encrypt.c: ./c256.h:98:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor368' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 0, 4, 8,12);
encrypt.c: ^
encrypt.c: ./c256.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: ./c256.h:12:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ^
encrypt.c: ./c256.h:98:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor368' that is compiled without support for 'ssse3'
encrypt.c: ./c256.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: ./c256.h:14:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ^
encrypt.c: ./c256.h:99:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor368' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 1, 5, 9,13);
encrypt.c: ^
encrypt.c: ./c256.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: ./c256.h:12:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-sse
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-sse
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sse

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx2
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: encrypt.c:90:2: error: "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^
encrypt.c: 1 error generated.

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx2
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx2

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx512
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: encrypt.c:90:2: error: "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^
encrypt.c: encrypt.c:342:15: error: invalid input constraint 'Yz' in asm
encrypt.c: : [a] "Yz" (a)
encrypt.c: ^
encrypt.c: encrypt.c:505:26: warning: implicit declaration of function '_mm512_loadu_si512' is invalid in C99 [-Wimplicit-function-declaration]
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^
encrypt.c: encrypt.c:505:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:506:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv4 = _mm512_loadu_si512((const __m512i*)(nhkey+ 4)); // 1
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:507:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv8 = _mm512_loadu_si512((const __m512i*)(nhkey+ 8)); // 1, 2
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:508:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv12 = _mm512_loadu_si512((const __m512i*)(nhkey+12)); // 1, 2
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:509:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i kv16 = _mm512_loadu_si512((const __m512i*)(nhkey+16)); // 2, 3
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:510:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx512
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-avx512
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-avx512

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-sse
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: c256.h: In function 'chacha_noxor368':
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h:14:84: error: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ^
encrypt.c: c256.h:17:36: note: in expansion of macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: c256.h:105:7: note: in expansion of macro 'VEC4_QUARTERROUND'
encrypt.c: VEC4_QUARTERROUND( 3, 4, 9,14);
encrypt.c: ^
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h:12:84: error: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ^
encrypt.c: ...
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: c256.h: In function 'chacha_noxor368':
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h:14:84: error: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ^
encrypt.c: c256.h:17:36: note: in expansion of macro 'VEC4_QUARTERROUND_SHUFFLE'
encrypt.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
encrypt.c: ^
encrypt.c: c256.h:105:7: note: in expansion of macro 'VEC4_QUARTERROUND'
encrypt.c: VEC4_QUARTERROUND( 3, 4, 9,14);
encrypt.c: ^
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h:12:84: error: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ^
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-sse
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-sse

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx2
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^
encrypt.c: In file included from encrypt.c:195:0:
encrypt.c: c368.h: In function 'chacha_noxor368':
encrypt.c: c368.h:110:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i rot16 = _mm256_set_epi8(13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2,13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2);
encrypt.c: ^
encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX2 to work"
encrypt.c: #error "This code requires AVX2 to work"
encrypt.c: ^
encrypt.c: In file included from encrypt.c:195:0:
encrypt.c: c368.h: In function 'chacha_noxor368':
encrypt.c: c368.h:110:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i rot16 = _mm256_set_epi8(13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2,13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2);
encrypt.c: ^

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx2
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx2

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/amd64-avx512
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^
encrypt.c: encrypt.c: In function '_mm512_reduce_add_epi64':
encrypt.c: encrypt.c:329:20: note: The ABI for passing parameters with 64-byte alignment has changed in GCC 4.6
encrypt.c: unsigned long long _mm512_reduce_add_epi64 (__m512i a) {
encrypt.c: ^
encrypt.c: In file included from encrypt.c:195:0:
encrypt.c: c368.h: In function 'chacha_noxor368':
encrypt.c: c368.h:110:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i rot16 = _mm256_set_epi8(13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2,13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2);
encrypt.c: ^
encrypt.c: encrypt.c: In function 'prf_hash2_3':
encrypt.c: encrypt.c:505:19: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^
encrypt.c: encrypt.c:90:2: error: #error "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^
encrypt.c: encrypt.c: In function '_mm512_reduce_add_epi64':
encrypt.c: encrypt.c:329:20: note: The ABI for passing parameters with 64-byte alignment has changed in GCC 4.6
encrypt.c: unsigned long long _mm512_reduce_add_epi64 (__m512i a) {
encrypt.c: ^
encrypt.c: In file included from encrypt.c:195:0:
encrypt.c: c368.h: In function 'chacha_noxor368':
encrypt.c: c368.h:110:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i rot16 = _mm256_set_epi8(13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2,13,12,15,14,9,8,11,10,5,4,7,6,1,0,3,2);
encrypt.c: ^
encrypt.c: encrypt.c: In function 'prf_hash2_3':
encrypt.c: encrypt.c:505:19: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
encrypt.c: __m512i kv0 = _mm512_loadu_si512((const __m512i*)(nhkey+ 0)); // 1
encrypt.c: ^

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=barcelona -O -fomit-frame-pointer	dolbeau/amd64-avx512
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	dolbeau/amd64-avx512