Implementation notes: amd64, hydra1, crypto_aead/hs1sivv2

Computer: hydra1
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: hs1sivv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
21206	`faster`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
21349	`faster`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
21366	`faster`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161016	20161009
21485	`faster`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
21496	`faster`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161016	20161009
21525	`faster`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
21904	`faster`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161016	20161009
21909	`faster`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
21924	`faster`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
21924	`faster`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161016	20161009
22064	`faster`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
22070	`faster`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
22088	`faster`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161016	20161009
22090	`faster`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161016	20161009
22107	`faster`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161016	20161009
22123	`faster`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
22133	`faster`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
22144	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
22150	`faster`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
22166	`faster`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161016	20161009
22197	`faster`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
22198	`faster`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161016	20161009
22200	`faster`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161016	20161009
22203	`faster`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161016	20161009
22217	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
22240	`faster`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
22253	`faster`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161016	20161009
22267	`faster`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
22322	`faster`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
22341	`faster`	`gcc -m64 -O3 -fomit-frame-pointer`	20161016	20161009
22346	`faster`	`gcc -O3 -fomit-frame-pointer`	20161016	20161009
22349	`faster`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161016	20161009
22355	`faster`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161016	20161009
22371	`faster`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
22376	`faster`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
22460	`faster`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
22466	`faster`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
22504	`faster`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161016	20161009
22513	`faster`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
22515	`faster`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
22528	`faster`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
22539	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
22568	`faster`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
22608	`faster`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
22629	`faster`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161016	20161009
22645	`faster`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
22651	`faster`	`gcc -O -fomit-frame-pointer`	20161016	20161009
22674	`faster`	`gcc -march=k8 -O -fomit-frame-pointer`	20161016	20161009
22678	`faster`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
22680	`faster`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
22682	`faster`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
22685	`faster`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161016	20161009
22690	`faster`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
22691	`faster`	`gcc -m64 -O -fomit-frame-pointer`	20161016	20161009
22693	`faster`	`gcc -O2 -fomit-frame-pointer`	20161016	20161009
22693	`faster`	`gcc -m64 -O2 -fomit-frame-pointer`	20161016	20161009
22704	`faster`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
22718	`faster`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161016	20161009
22768	`faster`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
22776	`faster`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
22794	`faster`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
22798	`faster`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161016	20161009
22802	`faster`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
22822	`faster`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161016	20161009
22870	`faster`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
22952	`faster`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
22978	`faster`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
22987	`faster`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
23005	`faster`	`gcc -march=nocona -O -fomit-frame-pointer`	20161016	20161009
23011	`faster`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
23037	`faster`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
23059	`faster`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161016	20161009
23061	`faster`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
23066	`faster`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161016	20161009
23069	`faster`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
23072	`faster`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161016	20161009
23077	`faster`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161016	20161009
23083	`faster`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
23093	`faster`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161016	20161009
23157	`faster`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161016	20161009
23166	`faster`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161016	20161009
23205	`faster`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161016	20161009
23211	`faster`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
23253	`faster`	`gcc -Os -fomit-frame-pointer`	20161016	20161009
23269	`faster`	`gcc -m64 -Os -fomit-frame-pointer`	20161016	20161009
23272	`faster`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
42105	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
42163	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
42173	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
42216	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
42261	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161016	20161009
42418	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
42441	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
42467	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
42525	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
42550	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
42582	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161016	20161009
42600	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161016	20161009
42605	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161016	20161009
42607	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161016	20161009
42710	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
43860	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
43898	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
44574	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161016	20161009
44592	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
44594	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161016	20161009
44606	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
44723	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
44740	`ref`	`gcc -O3 -fomit-frame-pointer`	20161016	20161009
44757	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
44776	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
44813	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
44819	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161016	20161009
44939	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161016	20161009
44941	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161016	20161009
44952	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
44957	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161016	20161009
45021	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
45373	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
45408	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
51092	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161016	20161009
57816	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161016	20161009
57829	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
57861	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161016	20161009
57877	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
58637	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
58674	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
58958	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
58981	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
60640	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161016	20161009
60841	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161016	20161009
60846	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161016	20161009
60909	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
61000	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161016	20161009
61166	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
61280	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161016	20161009
62984	`ref`	`gcc -O2 -fomit-frame-pointer`	20161016	20161009
63008	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161016	20161009
63544	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161016	20161009
63731	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161016	20161009
63797	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161016	20161009
64018	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161016	20161009
64026	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161016	20161009
66653	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
66677	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
66690	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
66717	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161016	20161009
67158	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
67302	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
67304	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161016	20161009
67309	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161016	20161009
67315	`ref`	`gcc -Os -fomit-frame-pointer`	20161016	20161009
67482	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
67514	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161016	20161009
67514	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161016	20161009
67515	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161016	20161009
67654	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
67668	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
67838	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161016	20161009
67843	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161016	20161009
67922	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161016	20161009
68029	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
68512	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
71621	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
72672	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
74253	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
74787	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161016	20161009
74880	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
76886	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161016	20161009
77077	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
77184	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
77352	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161016	20161009
77525	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161016	20161009
77592	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
77747	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161016	20161009
79899	`ref`	`gcc -O -fomit-frame-pointer`	20161016	20161009
80211	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161016	20161009
80381	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161016	20161009
80382	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161016	20161009
80446	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161016	20161009
80491	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161016	20161009
80563	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161016	20161009
80589	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161016	20161009
84173	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
122293	`faster`	`gcc -funroll-loops`	20161016	20161009
123019	`faster`	`gcc`	20161016	20161009
123824	`faster`	`cc`	20161016	20161009
506646	`ref`	`cc`	20161016	20161009
507358	`ref`	`gcc`	20161016	20161009
509134	`ref`	`gcc -funroll-loops`	20161016	20161009

Test failure

Implementation: crypto_aead/hs1sivv2/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/hs1sivv2/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/hs1sivv2/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/hs1sivv2/dolbeau/amd64-avx512
Compiler: cc

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
cc	dolbeau/amd64-avx512
gcc	dolbeau/amd64-avx512
gcc -funroll-loops	dolbeau/amd64-avx512

Compiler output

Implementation: crypto_aead/hs1sivv2/dolbeau/amd64-sse
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: In file included from encrypt.c:190:
encrypt.c: ./c176.h:99:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor176' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 0, 4, 8,12);
encrypt.c: ^
encrypt.c: ./c176.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: ./c176.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: ./c176.h:99:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor176' that is compiled without support for 'ssse3'
encrypt.c: ./c176.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: ./c176.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: ./c176.h:100:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor176' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 1, 5, 9,13);
encrypt.c: ^
encrypt.c: ./c176.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: ./c176.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/hs1sivv2/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/hs1sivv2/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:334:15: error: invalid input constraint 'Yz' in asm
encrypt.c: : [a] "Yz" (a)
encrypt.c: ^
encrypt.c: encrypt.c:482:26: 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:482:19: 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:483:19: 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:484:19: 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:485:19: 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:486:19: 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
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:487:19: 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/hs1sivv2/dolbeau/amd64-avx512
Compiler: gcc -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 89, namely:

Compiler	Implementations
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 -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/hs1sivv2/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: c176.h: In function 'chacha_noxor176':
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:190:0:
encrypt.c: c176.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: c176.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: c176.h:106:7: 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:190:0:
encrypt.c: c176.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: c176.h: In function 'chacha_noxor176':
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:190:0:
encrypt.c: c176.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: c176.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: c176.h:106:7: 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:190:0:
encrypt.c: c176.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/hs1sivv2/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: encrypt.c: In function 'prf_hash2_2':
encrypt.c: encrypt.c:425:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i kv0 = _mm256_loadu_si256((const __m256i*)(nhkey+ 0)); // 1
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: encrypt.c: In function 'prf_hash2_2':
encrypt.c: encrypt.c:425:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i kv0 = _mm256_loadu_si256((const __m256i*)(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-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/hs1sivv2/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:321:20: 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: encrypt.c: In function 'prf_hash2_2':
encrypt.c: encrypt.c:482:19: 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:501:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i inv0 = _mm256_inserti128_si256(_mm256_castsi128_si256(inv0lo), inv0lo, 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:321:20: 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: encrypt.c: In function 'prf_hash2_2':
encrypt.c: encrypt.c:482:19: 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:501:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
encrypt.c: __m256i inv0 = _mm256_inserti128_si256(_mm256_castsi128_si256(inv0lo), inv0lo, 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