Implementation notes: amd64, glyme, crypto_aead/hs1sivlov2

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: hs1sivlov2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
8356	`faster`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
8356	`faster`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
8796	`faster`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
8800	`faster`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
8800	`faster`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
8932	`faster`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
8960	`faster`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
8964	`faster`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
8964	`faster`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
8964	`faster`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
8964	`faster`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
9032	`faster`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
9280	`dolbeau/amd64-sse`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
9280	`dolbeau/amd64-sse`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
9584	`faster`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
9592	`faster`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
9596	`faster`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170204	20170105
9608	`faster`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170204	20170105
9620	`faster`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
9628	`faster`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
9628	`faster`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
9644	`faster`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
9648	`faster`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
9648	`faster`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
9652	`faster`	`gcc -O3 -fomit-frame-pointer`	20170204	20170105
9660	`faster`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
9660	`faster`	`gcc -m64 -O3 -fomit-frame-pointer`	20170204	20170105
9672	`faster`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
9672	`faster`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
9684	`faster`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
9684	`faster`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
9700	`faster`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170204	20170105
9700	`faster`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
9700	`faster`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
9704	`faster`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170204	20170105
9704	`faster`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
9708	`faster`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
9716	`faster`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
9728	`faster`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
9732	`faster`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
9768	`faster`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
9784	`faster`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
9784	`faster`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170204	20170105
9792	`faster`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
9796	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
9800	`faster`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170204	20170105
9804	`faster`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
9804	`faster`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170204	20170105
9804	`faster`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170204	20170105
9808	`faster`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
9836	`faster`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
9840	`faster`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
9848	`faster`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
9852	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
9872	`dolbeau/amd64-sse`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
9872	`dolbeau/amd64-sse`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
9876	`dolbeau/amd64-sse`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
9880	`dolbeau/amd64-sse`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
9880	`dolbeau/amd64-sse`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
9896	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
9896	`faster`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
9920	`dolbeau/amd64-sse`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
9948	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
9948	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
9948	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
9960	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
9984	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
9996	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
10172	`faster`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
10176	`faster`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
10176	`faster`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
10176	`faster`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
10184	`faster`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
10192	`faster`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
10192	`dolbeau/amd64-sse`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
10204	`dolbeau/amd64-sse`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
10204	`dolbeau/amd64-sse`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
10264	`faster`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
10272	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
10276	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
10276	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
10308	`faster`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
10312	`faster`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
10344	`faster`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
10344	`faster`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
10352	`faster`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
10356	`faster`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
10372	`faster`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
10468	`faster`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
10468	`faster`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
10488	`faster`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
10496	`faster`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
10544	`faster`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
10548	`faster`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
10552	`faster`	`gcc -m64 -O2 -fomit-frame-pointer`	20170204	20170105
10556	`faster`	`gcc -O2 -fomit-frame-pointer`	20170204	20170105
10564	`faster`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
10576	`faster`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
10600	`faster`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
10660	`faster`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
10680	`faster`	`gcc -O -fomit-frame-pointer`	20170204	20170105
10680	`faster`	`gcc -m64 -O -fomit-frame-pointer`	20170204	20170105
10720	`faster`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
10728	`faster`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
10768	`faster`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
10812	`faster`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
10820	`faster`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
10820	`faster`	`gcc -march=k8 -O -fomit-frame-pointer`	20170204	20170105
10824	`faster`	`gcc -m64 -Os -fomit-frame-pointer`	20170204	20170105
10828	`faster`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
10832	`faster`	`gcc -Os -fomit-frame-pointer`	20170204	20170105
10876	`faster`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
10884	`faster`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170204	20170105
10900	`faster`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
10900	`faster`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
10904	`faster`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170204	20170105
10908	`faster`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
10916	`faster`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
10916	`faster`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
10940	`faster`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
10944	`faster`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
10944	`faster`	`gcc -march=nocona -O -fomit-frame-pointer`	20170204	20170105
12684	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
12688	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
12688	`dolbeau/amd64-sse`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
12800	`dolbeau/amd64-sse`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
12804	`dolbeau/amd64-sse`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
12824	`dolbeau/amd64-sse`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
27236	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
27256	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
27632	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
27672	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
27700	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
27708	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
27712	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
27764	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
28068	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
28072	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
28256	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
28264	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
28272	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170204	20170105
28272	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
28332	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170204	20170105
30056	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
30100	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
30200	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170204	20170105
30200	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170204	20170105
30212	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
30280	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
30336	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
30760	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
30760	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
30968	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
31000	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
31340	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
31352	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
31360	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
31360	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
31396	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
31396	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
33624	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
33768	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
33812	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
33828	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
34016	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
34032	`ref`	`gcc -O3 -fomit-frame-pointer`	20170204	20170105
34192	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20170204	20170105
38108	`faster`	`cc`	20170204	20170105
40576	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
40608	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
40612	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170204	20170105
40616	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170204	20170105
40684	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
40872	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
40900	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170204	20170105
41084	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170204	20170105
41180	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
42520	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
42684	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
43808	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
43988	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
45276	`faster`	`gcc`	20170204	20170105
45280	`faster`	`gcc -funroll-loops`	20170204	20170105
45456	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
45488	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
47408	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
47428	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
47792	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
47808	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
47808	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
47828	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
49400	`ref`	`gcc -O2 -fomit-frame-pointer`	20170204	20170105
49416	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20170204	20170105
49440	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
49992	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
50108	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
50904	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20170204	20170105
51192	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
52804	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20170204	20170105
52856	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
53876	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
54084	`ref`	`gcc -O -fomit-frame-pointer`	20170204	20170105
54088	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20170204	20170105
54796	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
54840	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
54844	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
54844	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
54848	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
54856	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
57036	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
57048	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
57060	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
57100	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
57104	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
57104	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
57528	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
57584	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
57592	`ref`	`gcc -Os -fomit-frame-pointer`	20170204	20170105
57592	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
57596	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20170204	20170105
57616	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
57660	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
57996	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
57996	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
58000	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
58036	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
58044	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
58056	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170204	20170105
58080	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170204	20170105
58692	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
58692	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
59208	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
59212	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
304916	`ref`	`gcc -funroll-loops`	20170204	20170105
312748	`ref`	`gcc`	20170204	20170105
341456	`ref`	`cc`	20170204	20170105

Compiler output

Implementation: crypto_aead/hs1sivlov2/dolbeau/amd64-sse
Compiler: cc

encrypt.c: In file included from encrypt.c:190:
encrypt.c: ./c128.h:99:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor128' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 0, 4, 8,12);
encrypt.c: ^
encrypt.c: ./c128.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: ./c128.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: ./c128.h:99:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor128' that is compiled without support for 'ssse3'
encrypt.c: ./c128.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: ./c128.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: ./c128.h:100:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'chacha_noxor128' that is compiled without support for 'ssse3'
encrypt.c: VEC4_QUARTERROUND( 1, 5, 9,13);
encrypt.c: ^
encrypt.c: ./c128.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: ./c128.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: 5, namely:

Compiler	Implementations
cc	dolbeau/amd64-sse
clang -O3 -fomit-frame-pointer -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/hs1sivlov2/dolbeau/amd64-avx2
Compiler: cc

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: 7, namely:

Compiler	Implementations
cc	dolbeau/amd64-avx2
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/hs1sivlov2/dolbeau/amd64-avx512
Compiler: cc

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:329:15: error: invalid input constraint 'Yz' in asm
encrypt.c: : [a] "Yz" (a)
encrypt.c: ^
encrypt.c: encrypt.c:460:26: 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:460:19: 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:461:19: 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:462:19: 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
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:463:19: 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
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:465:19: error: initializing '__m512i' (vector of 8 'long long' values) with an expression of incompatible type 'int'
encrypt.c: __m512i inv = _mm512_loadu_si512((const __m512i*)(in+ 0));
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:467:11: warning: implicit declaration of function '_mm512_unpacklo_epi32' is invalid in C99 [-Wimplicit-function-declaration]
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 7, namely:

Compiler	Implementations
cc	dolbeau/amd64-avx512
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/hs1sivlov2/dolbeau/amd64-sse
Compiler: gcc

Number of similar (compiler,implementation) pairs: 70, namely:

Compiler	Implementations
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=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=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/hs1sivlov2/dolbeau/amd64-avx2
Compiler: gcc

Number of similar (compiler,implementation) pairs: 94, namely:

Compiler	Implementations
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 -O3 -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 -O3 -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 -O3 -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/hs1sivlov2/dolbeau/amd64-avx512
Compiler: gcc

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

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

Compiler output

Implementation: crypto_aead/hs1sivlov2/dolbeau/amd64-avx512
Compiler: gcc -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 92, 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 -O3 -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 -O3 -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 -O3 -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/hs1sivlov2/dolbeau/amd64-sse
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: c128.h: In function 'chacha_noxor128':
encrypt.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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: c128.h:14:84: note: 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: c128.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: c128.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/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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: c128.h:12:84: note: 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/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: c128.h: In function 'chacha_noxor128':
encrypt.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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: c128.h:14:84: note: 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: c128.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: c128.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/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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: c128.h:12:84: note: 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/hs1sivlov2/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_1':
encrypt.c: encrypt.c:403:19: 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_1':
encrypt.c: encrypt.c:403:19: 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/hs1sivlov2/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:316:20: 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_1':
encrypt.c: encrypt.c:460:19: 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:476:19: 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:316:20: 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_1':
encrypt.c: encrypt.c:460:19: 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:476:19: 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