Implementation notes: amd64, h5nano, crypto_aead/aes128gcmv1

Computer: h5nano
Architecture: amd64
CPU ID: CentaurHauls-000006f8-afc9fbff
SUPERCOP version: 20141014
Operation: crypto_aead
Primitive: aes128gcmv1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
128755	`openssl`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140709	20140622
128805	`openssl`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140709	20140622
128810	`openssl`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141016	20141014
128810	`openssl`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140709	20140622
128810	`openssl`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140709	20140622
128810	`openssl`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140709	20140622
128815	`openssl`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140709	20140622
128815	`openssl`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140709	20140622
128815	`openssl`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140709	20140622
128815	`openssl`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140709	20140622
128825	`openssl`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140709	20140622
128830	`openssl`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140709	20140622
128830	`openssl`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140709	20140622
128835	`openssl`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140709	20140622
128835	`openssl`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140709	20140622
128835	`openssl`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140709	20140622
128835	`openssl`	`gcc -march=nocona -O -fomit-frame-pointer`	20140709	20140622
128840	`openssl`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140709	20140622
128840	`openssl`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140709	20140622
128840	`openssl`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140709	20140622
128845	`openssl`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140709	20140622
128850	`openssl`	`gcc -m64 -O -fomit-frame-pointer`	20140709	20140622
128850	`openssl`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140709	20140622
128855	`openssl`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140709	20140622
128855	`openssl`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140709	20140622
128855	`openssl`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140709	20140622
128860	`openssl`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140709	20140622
128860	`openssl`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140709	20140622
128860	`openssl`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140709	20140622
128865	`openssl`	`gcc -Os -fomit-frame-pointer`	20140709	20140622
128865	`openssl`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140709	20140622
128865	`openssl`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140709	20140622
128870	`openssl`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140709	20140622
128875	`openssl`	`gcc -O -fomit-frame-pointer`	20140709	20140622
128875	`openssl`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140709	20140622
128875	`openssl`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140709	20140622
128880	`openssl`	`clang -O3 -fomit-frame-pointer`	20140709	20140622
128880	`openssl`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140709	20140622
128880	`openssl`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140709	20140622
128885	`openssl`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140709	20140622
128885	`openssl`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140709	20140622
128885	`openssl`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140709	20140622
128890	`openssl`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140709	20140622
128895	`openssl`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140709	20140622
128895	`openssl`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140709	20140622
128895	`openssl`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140709	20140622
128900	`openssl`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140709	20140622
128900	`openssl`	`gcc -m64 -O3 -fomit-frame-pointer`	20140709	20140622
128900	`openssl`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140709	20140622
128905	`openssl`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140709	20140622
128905	`openssl`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140709	20140622
128905	`openssl`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140709	20140622
128910	`openssl`	`gcc -O3 -fomit-frame-pointer`	20140709	20140622
128915	`openssl`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140709	20140622
128915	`openssl`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140709	20140622
128915	`openssl`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140709	20140622
128915	`openssl`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140709	20140622
128915	`openssl`	`gcc -m64 -O2 -fomit-frame-pointer`	20140709	20140622
128915	`openssl`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140709	20140622
128920	`openssl`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140709	20140622
128920	`openssl`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140709	20140622
128920	`openssl`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140709	20140622
128925	`openssl`	`cc`	20140709	20140622
128925	`openssl`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140709	20140622
128925	`openssl`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140709	20140622
128925	`openssl`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140709	20140622
128925	`openssl`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140709	20140622
128930	`openssl`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140709	20140622
128930	`openssl`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140709	20140622
128930	`openssl`	`gcc -m64 -Os -fomit-frame-pointer`	20140709	20140622
128930	`openssl`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140709	20140622
128930	`openssl`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140709	20140622
128935	`openssl`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140709	20140622
128935	`openssl`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140709	20140622
128935	`openssl`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140709	20140622
128935	`openssl`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140709	20140622
128940	`openssl`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140709	20140622
128940	`openssl`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140709	20140622
128940	`openssl`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140709	20140622
128940	`openssl`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140709	20140622
128940	`openssl`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140709	20140622
128950	`openssl`	`gcc -O2 -fomit-frame-pointer`	20140709	20140622
128950	`openssl`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140709	20140622
128950	`openssl`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140709	20140622
128950	`openssl`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140709	20140622
128955	`openssl`	`gcc`	20140709	20140622
128960	`openssl`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140709	20140622
128965	`openssl`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140709	20140622
128970	`openssl`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140709	20140622
128975	`openssl`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140709	20140622
128980	`openssl`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140709	20140622
128985	`openssl`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140709	20140622
128990	`openssl`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140709	20140622
129000	`openssl`	`gcc -funroll-loops`	20140709	20140622
129000	`openssl`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140709	20140622
129005	`openssl`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140709	20140622
129015	`openssl`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140709	20140622
129025	`openssl`	`gcc -march=k8 -O -fomit-frame-pointer`	20140709	20140622
129040	`openssl`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20141016	20141014
129315	`openssl`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140709	20140622
14087305	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20140710	20140622
14088515	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20140710	20140622
14100320	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20140710	20140622
14252270	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20140710	20140622
14574165	`ref`	`gcc -O3 -fomit-frame-pointer`	20140710	20140622
14574325	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20140709	20140622
14574365	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20140710	20140622
14642930	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20140710	20140622
14654035	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20140710	20140622
14672940	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20140709	20140622
14676880	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20140709	20140622
14677095	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20140709	20140622
14681220	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20140709	20140622
14795390	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20140709	20140622
14989870	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20140710	20140622
16309910	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20140710	20140622
16322395	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140709	20140622
16325410	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20140710	20140622
16337860	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20140710	20140622
16899150	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20140710	20140622
16899315	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20140710	20140622
16914090	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20140710	20140622
16917910	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20140710	20140622
26370980	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20140710	20140622
26371695	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20140710	20140622
26372025	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20140710	20140622
26372205	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20140710	20140622
26385780	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20140710	20140622
28002745	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140710	20140622
28002925	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20140710	20140622
28790100	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer`	20140710	20140622
28790330	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20141016	20141014
28790430	`ref`	`clang -O3 -fwrapv -mavx2 -fpolly -funroll-loops -fvectorize -fslp-vectorize -fslp-vectorize-aggressive -fomit-frame-pointer`	20140710	20140622
28790505	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer`	20141016	20141014
28815290	`ref`	`clang -O3 -fomit-frame-pointer`	20140710	20140622
28975235	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20140710	20140622
28982880	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20140710	20140622
29330510	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20140710	20140622
29330670	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20140710	20140622
29596525	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20140710	20140622
29607735	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20140710	20140622
29780590	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20140710	20140622
29796530	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20140710	20140622
30219665	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20140710	20140622
30223190	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20140710	20140622
30224630	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20140710	20140622
35058800	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20140709	20140622
35058815	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20140709	20140622
35058930	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20140709	20140622
35058945	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20140709	20140622
35059020	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20140709	20140622
35125320	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20140710	20140622
35125325	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20140710	20140622
35125350	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20140709	20140622
35125350	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20140710	20140622
35129290	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20140710	20140622
35129295	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20140710	20140622
35134560	`ref`	`gcc -Os -fomit-frame-pointer`	20140710	20140622
35144665	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20140710	20140622
35144920	`ref`	`gcc -O2 -fomit-frame-pointer`	20140710	20140622
35146320	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20140709	20140622
35148355	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20140709	20140622
35148535	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20140710	20140622
35170185	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20140710	20140622
35174340	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20140710	20140622
35174450	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20140709	20140622
35177555	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20140710	20140622
35186415	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20140709	20140622
35186675	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20140709	20140622
35186705	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20140709	20140622
35186730	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20140709	20140622
35186760	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20140709	20140622
35200170	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20140710	20140622
35200310	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20140710	20140622
35215085	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20140710	20140622
35215180	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20140710	20140622
35317650	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20140710	20140622
35317810	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20140710	20140622
35317885	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20140710	20140622
35321660	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20140710	20140622
35325335	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20140710	20140622
35338215	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20140710	20140622
35339500	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20140710	20140622
35583760	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20140710	20140622
35583930	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20140710	20140622
35641055	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20140709	20140622
35641230	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20140710	20140622
35641310	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20140710	20140622
35644520	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20140710	20140622
35786530	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20140709	20140622
35786550	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20140710	20140622
35786580	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20140709	20140622
35786605	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20140709	20140622
35786625	`ref`	`gcc -O -fomit-frame-pointer`	20140710	20140622
35786630	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20140709	20140622
35786680	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20140709	20140622
35788815	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20140710	20140622
105811960	`ref`	`gcc`	20140710	20140622
105813130	`ref`	`cc`	20140710	20140622
105814910	`ref`	`gcc -funroll-loops`	20140710	20140622

Compiler output

Implementation: crypto_aead/aes128gcmv1/openssl
Compiler: clang -O3 -fomit-frame-pointer

try.c: try-anything.c:110:19: warning: if statement has empty body [-Wempty-body]
try.c: ;
try.c: ^
try.c: 1 warning generated.
try.c: try-anything.c:110:19: warning: if statement has empty body [-Wempty-body]
try.c: ;
try.c: ^
try.c: 1 warning generated.

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

Compiler	Implementations
clang -O3 -fomit-frame-pointer	openssl ref

Compiler output

Implementation: crypto_aead/aes128gcmv1/openssl
Compiler: clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer