Implementation notes: amd64, skylake, crypto_hashblocks/sha256

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_hashblocks
Primitive: sha256

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
17666	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161215	20161026
17680	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161215	20161026
17706	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161215	20161026
17752	`inplace`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161215	20161026
17756	`inplace`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161215	20161026
17810	`inplace`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161215	20161026
17812	`inplace`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161215	20161026
17816	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161215	20161026
17818	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161215	20161026
17822	`inplace`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161215	20161026
17824	`inplace`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161215	20161026
17862	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161215	20161026
19566	`inplace`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161215	20161026
19598	`inplace`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161215	20161026
19618	`inplace`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161215	20161026
19716	`inplace`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161215	20161026
19720	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161215	20161026
19720	`inplace`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161215	20161026
19728	`inplace`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161215	20161026
19744	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161215	20161026
19756	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161215	20161026
19768	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161215	20161026
19774	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161215	20161026
19804	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161215	20161026
20060	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
20080	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161215	20161026
20164	`inplace`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
20186	`inplace`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161215	20161026
22492	`inplace`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161215	20161026
22512	`inplace`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161215	20161026
22872	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161215	20161026
22886	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161215	20161026
22900	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161215	20161026
22958	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161215	20161026
22998	`inplace`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161215	20161026
23014	`inplace`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161215	20161026
23060	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161215	20161026
23078	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161215	20161026
23090	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161215	20161026
23100	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161215	20161026
23104	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161215	20161026
23110	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161215	20161026
23174	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161215	20161026
23192	`inplace`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161215	20161026
23192	`inplace`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161215	20161026
23248	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161215	20161026
23270	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161215	20161026
23274	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161215	20161026
23286	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161215	20161026
23300	`inplace`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161215	20161026
23308	`inplace`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161215	20161026
23312	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161215	20161026
23322	`inplace`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161215	20161026
23324	`inplace`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161215	20161026
23332	`inplace`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161215	20161026
23332	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161215	20161026
23346	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161215	20161026
23420	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161215	20161026
23426	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161215	20161026
23430	`inplace`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161215	20161026
23444	`inplace`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161215	20161026
23464	`inplace`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161215	20161026
23480	`inplace`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161215	20161026
23498	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161215	20161026
23498	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161215	20161026
23506	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161215	20161026
23508	`inplace`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161215	20161026
23510	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161215	20161026
23518	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161215	20161026
23518	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161215	20161026
23526	`inplace`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161215	20161026
23564	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161215	20161026
23568	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161215	20161026
23570	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161215	20161026
23572	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161215	20161026
23578	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161215	20161026
23584	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161215	20161026
23586	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161215	20161026
23598	`ref`	`gcc -Os -fomit-frame-pointer`	20161215	20161026
23618	`inplace`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161215	20161026
23618	`inplace`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161215	20161026
23618	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161215	20161026
23630	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161215	20161026
23648	`inplace`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161215	20161026
23648	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161215	20161026
23654	`inplace`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161215	20161026
23674	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161215	20161026
23682	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161215	20161026
23688	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161215	20161026
23694	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161215	20161026
23696	`inplace`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161215	20161026
23700	`inplace`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161215	20161026
23702	`inplace`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161215	20161026
23704	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161215	20161026
23706	`inplace`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161215	20161026
23708	`inplace`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161215	20161026
23720	`inplace`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161215	20161026
23744	`inplace`	`gcc -m64 -Os -fomit-frame-pointer`	20161215	20161026
23752	`inplace`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161215	20161026
23756	`inplace`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161215	20161026
23758	`inplace`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161215	20161026
23760	`inplace`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161215	20161026
23762	`inplace`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161215	20161026
23766	`inplace`	`gcc -Os -fomit-frame-pointer`	20161215	20161026
23782	`inplace`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161215	20161026
23800	`inplace`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161215	20161026
23804	`inplace`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161215	20161026
23838	`inplace`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161215	20161026
23858	`inplace`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161215	20161026
23878	`inplace`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161215	20161026
23888	`inplace`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161215	20161026
24024	`inplace`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161215	20161026
24260	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161215	20161026
24262	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161215	20161026
24276	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161215	20161026
24280	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161215	20161026
24344	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161215	20161026
24348	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161215	20161026
24350	`ref`	`gcc -O3 -fomit-frame-pointer`	20161215	20161026
24356	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161215	20161026
24360	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161215	20161026
24510	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161215	20161026
24536	`ref`	`gcc -O2 -fomit-frame-pointer`	20161215	20161026
24538	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161215	20161026
24538	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161215	20161026
24548	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161215	20161026
24552	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161215	20161026
24552	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161215	20161026
24554	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161215	20161026
24558	`inplace`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161215	20161026
24564	`inplace`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161215	20161026
24574	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161215	20161026
24580	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161215	20161026
24588	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161215	20161026
24602	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161215	20161026
24606	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161215	20161026
24608	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161215	20161026
24612	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161215	20161026
24620	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161215	20161026
24640	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161215	20161026
24642	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161215	20161026
24654	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161215	20161026
24654	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161215	20161026
24656	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161215	20161026
24666	`inplace`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161215	20161026
24710	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161215	20161026
24716	`inplace`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161215	20161026
24720	`inplace`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161215	20161026
24744	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161215	20161026
24762	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161215	20161026
24766	`inplace`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161215	20161026
24782	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161215	20161026
24782	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161215	20161026
24790	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161215	20161026
24794	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161215	20161026
24804	`inplace`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161215	20161026
24834	`inplace`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161215	20161026
24836	`inplace`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161215	20161026
24844	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161215	20161026
24848	`inplace`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161215	20161026
24866	`inplace`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161215	20161026
24870	`inplace`	`gcc -O3 -fomit-frame-pointer`	20161215	20161026
24870	`inplace`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161215	20161026
24870	`inplace`	`gcc -m64 -O3 -fomit-frame-pointer`	20161215	20161026
24882	`inplace`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161215	20161026
24902	`inplace`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161215	20161026
24980	`inplace`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161215	20161026
24980	`inplace`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161215	20161026
24988	`inplace`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161215	20161026
25004	`inplace`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161215	20161026
25022	`inplace`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161215	20161026
25046	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161215	20161026
25066	`inplace`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161215	20161026
25088	`inplace`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161215	20161026
25090	`inplace`	`gcc -O2 -fomit-frame-pointer`	20161215	20161026
25096	`inplace`	`gcc -m64 -O2 -fomit-frame-pointer`	20161215	20161026
25144	`inplace`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161215	20161026
25162	`inplace`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161215	20161026
25164	`inplace`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161215	20161026
25166	`inplace`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161215	20161026
25176	`inplace`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161215	20161026
25178	`inplace`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161215	20161026
25182	`inplace`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161215	20161026
25204	`inplace`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161215	20161026
25206	`inplace`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161215	20161026
25206	`inplace`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161215	20161026
25292	`inplace`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161215	20161026
25316	`inplace`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161215	20161026
25326	`inplace`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161215	20161026
25328	`inplace`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161215	20161026
25424	`inplace`	`gcc -march=k8 -O -fomit-frame-pointer`	20161215	20161026
25434	`inplace`	`gcc -march=nocona -O -fomit-frame-pointer`	20161215	20161026
25482	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161215	20161026
25484	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161215	20161026
25614	`inplace`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161215	20161026
25800	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161215	20161026
25816	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161215	20161026
25832	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161215	20161026
25886	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161215	20161026
25898	`inplace`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161215	20161026
25900	`inplace`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161215	20161026
25902	`inplace`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161215	20161026
25908	`inplace`	`gcc -m64 -O -fomit-frame-pointer`	20161215	20161026
25918	`inplace`	`gcc -O -fomit-frame-pointer`	20161215	20161026
25918	`inplace`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161215	20161026
25918	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161215	20161026
25926	`inplace`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161215	20161026
25964	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161215	20161026
25968	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161215	20161026
25976	`ref`	`gcc -O -fomit-frame-pointer`	20161215	20161026
25990	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161215	20161026
26018	`inplace`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161215	20161026
26038	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161215	20161026
26054	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161215	20161026
26054	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161215	20161026
26066	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161215	20161026
26166	`inplace`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161215	20161026
26208	`inplace`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161215	20161026
26704	`inplace`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161215	20161026
26766	`inplace`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161215	20161026
26918	`inplace`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
26926	`inplace`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
26926	`inplace`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161215	20161026
26952	`inplace`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161215	20161026
26968	`inplace`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161215	20161026
27000	`inplace`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
27004	`inplace`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
27022	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161215	20161026
27024	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161215	20161026
27028	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
27028	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161215	20161026
27030	`inplace`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
27036	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
27036	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
27054	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
27068	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161215	20161026
38102	`inplace`	`cc`	20161215	20161026
38122	`inplace`	`gcc -funroll-loops`	20161215	20161026
38182	`inplace`	`gcc`	20161215	20161026
46086	`ref`	`gcc`	20161215	20161026
46150	`ref`	`gcc -funroll-loops`	20161215	20161026
46444	`ref`	`cc`	20161215	20161026

Compiler output

Implementation: crypto_hashblocks/sha256/dolbeau/amd64-sha
Compiler: cc

blocks.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:35:0,
blocks.c: from blocks.c:37:
blocks.c: blocks.c: In function 'crypto_hashblocks_sha256_dolbeau_amd64_sha':
blocks.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
blocks.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
blocks.c: ^~~~~~~~~~~~~~~~
blocks.c: blocks.c:86:5: note: called from here
blocks.c: d1 = _mm_shuffle_epi8(d1, vperm);
blocks.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:35:0,
blocks.c: from blocks.c:37:
blocks.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
blocks.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
blocks.c: ^~~~~~~~~~~~~~~~
blocks.c: blocks.c:85:5: note: called from here
blocks.c: d0 = _mm_shuffle_epi8(d0, vperm);
blocks.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:35:0,
blocks.c: from blocks.c:37:
blocks.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
blocks.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
blocks.c: ^~~~~~~~~~~~~~~~
blocks.c: blocks.c:86:5: note: called from here
blocks.c: d1 = _mm_shuffle_epi8(d1, vperm);
blocks.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: ...

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

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

Compiler output

Implementation: crypto_hashblocks/sha256/dolbeau/amd64-sha
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

blocks.c: blocks.c:85:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'ssse3'
blocks.c: d0 = _mm_shuffle_epi8(d0, vperm);
blocks.c: ^
blocks.c: blocks.c:86:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'ssse3'
blocks.c: d1 = _mm_shuffle_epi8(d1, vperm);
blocks.c: ^
blocks.c: blocks.c:97:7: error: '__builtin_ia32_palignr128' needs target feature ssse3
blocks.c: d0 = _mm_alignr_epi8(d0, d1, 0x08);
blocks.c: ^
blocks.c: /usr/bin/../lib/clang/3.9.0/include/tmmintrin.h:161:12: note: expanded from macro '_mm_alignr_epi8'
blocks.c: (__m128i)__builtin_ia32_palignr128((__v16qi)(__m128i)(a), \
blocks.c: ^
blocks.c: blocks.c:113:8: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'ssse3'
blocks.c: i0 = _mm_shuffle_epi8(i0, vperm);
blocks.c: ^
blocks.c: blocks.c:114:8: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'ssse3'
blocks.c: i1 = _mm_shuffle_epi8(i1, vperm);
blocks.c: ^
blocks.c: blocks.c:115:8: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'ssse3'
blocks.c: i2 = _mm_shuffle_epi8(i2, vperm);
blocks.c: ^
blocks.c: blocks.c:116:8: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'ssse3'
blocks.c: i3 = _mm_shuffle_epi8(i3, vperm);
blocks.c: ^
blocks.c: blocks.c:176:3: error: always_inline function '_mm_sha256rnds2_epu32' requires target feature 'sha', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'sha'
blocks.c: ...

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

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

Compiler output

Implementation: crypto_hashblocks/sha256/dolbeau/amd64-sha
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments

blocks.c: blocks.c:176:3: error: always_inline function '_mm_sha256rnds2_epu32' requires target feature 'sha', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'sha'
blocks.c: DO16ROUNDS(i0, i1, i2, i3, c0, c1, c2, c3);
blocks.c: ^
blocks.c: blocks.c:129:8: note: expanded from macro 'DO16ROUNDS'
blocks.c: x1 = _mm_sha256rnds2_epu32(s1, s0, h0); \
blocks.c: ^
blocks.c: blocks.c:176:3: error: always_inline function '_mm_sha256rnds2_epu32' requires target feature 'sha', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'sha'
blocks.c: blocks.c:131:8: note: expanded from macro 'DO16ROUNDS'
blocks.c: x0 = _mm_sha256rnds2_epu32(s0, x1, h0); \
blocks.c: ^
blocks.c: blocks.c:176:3: error: always_inline function '_mm_sha256rnds2_epu32' requires target feature 'sha', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'sha'
blocks.c: blocks.c:134:8: note: expanded from macro 'DO16ROUNDS'
blocks.c: s1 = _mm_sha256rnds2_epu32(x1, x0, h1); \
blocks.c: ^
blocks.c: blocks.c:176:3: error: always_inline function '_mm_sha256rnds2_epu32' requires target feature 'sha', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'sha'
blocks.c: blocks.c:136:8: note: expanded from macro 'DO16ROUNDS'
blocks.c: s0 = _mm_sha256rnds2_epu32(x0, s1, h1); \
blocks.c: ^
blocks.c: blocks.c:176:3: error: always_inline function '_mm_sha256rnds2_epu32' requires target feature 'sha', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'sha'
blocks.c: blocks.c:139:8: note: expanded from macro 'DO16ROUNDS'
blocks.c: x1 = _mm_sha256rnds2_epu32(s1, s0, h0); \
blocks.c: ^
blocks.c: blocks.c:176:3: error: always_inline function '_mm_sha256rnds2_epu32' requires target feature 'sha', but would be inlined into function 'crypto_hashblocks_sha256_dolbeau_amd64_sha' that is compiled without support for 'sha'
blocks.c: blocks.c:141:8: note: expanded from macro 'DO16ROUNDS'
blocks.c: x0 = _mm_sha256rnds2_epu32(s0, x1, h0); \
blocks.c: ...

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

Compiler	Implementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-sha
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-sha
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-sha
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-sha
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	dolbeau/amd64-sha
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/amd64-sha

Compiler output

Implementation: crypto_hashblocks/sha256/dolbeau/amd64-sha
Compiler: gcc -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 68, namely:

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

Compiler output

Implementation: crypto_hashblocks/sha256/dolbeau/amd64-sha
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

blocks.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:37:0,
blocks.c: from blocks.c:37:
blocks.c: blocks.c: In function 'crypto_hashblocks_sha256_dolbeau_amd64_sha':
blocks.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/smmintrin.h:166:1: error: inlining failed in call to always_inline '_mm_blend_epi16': target specific option mismatch
blocks.c: _mm_blend_epi16 (__m128i __X, __m128i __Y, const int __M)
blocks.c: ^~~~~~~~~~~~~~~
blocks.c: blocks.c:98:5: note: called from here
blocks.c: d1 = _mm_blend_epi16(d1, s0, 0xf0);
blocks.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:35:0,
blocks.c: from blocks.c:37:
blocks.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/tmmintrin.h:185:1: error: inlining failed in call to always_inline '_mm_alignr_epi8': target specific option mismatch
blocks.c: _mm_alignr_epi8(__m128i __X, __m128i __Y, const int __N)
blocks.c: ^~~~~~~~~~~~~~~
blocks.c: blocks.c:97:5: note: called from here
blocks.c: d0 = _mm_alignr_epi8(d0, d1, 0x08);
blocks.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:35:0,
blocks.c: from blocks.c:37:
blocks.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
blocks.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
blocks.c: ^~~~~~~~~~~~~~~~
blocks.c: blocks.c:86:5: note: called from here
blocks.c: d1 = _mm_shuffle_epi8(d1, vperm);
blocks.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: ...
blocks.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:37:0,
blocks.c: from blocks.c:37:
blocks.c: blocks.c: In function 'crypto_hashblocks_sha256_dolbeau_amd64_sha':
blocks.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/smmintrin.h:166:1: error: inlining failed in call to always_inline '_mm_blend_epi16': target specific option mismatch
blocks.c: _mm_blend_epi16 (__m128i __X, __m128i __Y, const int __M)
blocks.c: ^~~~~~~~~~~~~~~
blocks.c: blocks.c:98:5: note: called from here
blocks.c: d1 = _mm_blend_epi16(d1, s0, 0xf0);
blocks.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:35:0,
blocks.c: from blocks.c:37:
blocks.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/tmmintrin.h:185:1: error: inlining failed in call to always_inline '_mm_alignr_epi8': target specific option mismatch
blocks.c: _mm_alignr_epi8(__m128i __X, __m128i __Y, const int __N)
blocks.c: ^~~~~~~~~~~~~~~
blocks.c: blocks.c:97:5: note: called from here
blocks.c: d0 = _mm_alignr_epi8(d0, d1, 0x08);
blocks.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:35:0,
blocks.c: from blocks.c:37:
blocks.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
blocks.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
blocks.c: ^~~~~~~~~~~~~~~~
blocks.c: blocks.c:86:5: note: called from here
blocks.c: d1 = _mm_shuffle_epi8(d1, vperm);
blocks.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: ...

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

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

Compiler output

Implementation: crypto_hashblocks/sha256/dolbeau/amd64-sha
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer

blocks.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:71:0,
blocks.c: from blocks.c:37:
blocks.c: blocks.c: In function 'crypto_hashblocks_sha256_dolbeau_amd64_sha':
blocks.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/shaintrin.h:87:1: error: inlining failed in call to always_inline '_mm_sha256rnds2_epu32': target specific option mismatch
blocks.c: _mm_sha256rnds2_epu32 (__m128i __A, __m128i __B, __m128i __C)
blocks.c: ^~~~~~~~~~~~~~~~~~~~~
blocks.c: blocks.c:146:6: note: called from here
blocks.c: s0 = _mm_sha256rnds2_epu32(x0, s1, h1)
blocks.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: blocks.c:188:3: note: in expansion of macro 'DO16ROUNDS'
blocks.c: DO16ROUNDS(j0, j1, j2, j3, cc, cd, ce, cf);
blocks.c: ^~~~~~~~~~
blocks.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:71:0,
blocks.c: from blocks.c:37:
blocks.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/shaintrin.h:87:1: error: inlining failed in call to always_inline '_mm_sha256rnds2_epu32': target specific option mismatch
blocks.c: _mm_sha256rnds2_epu32 (__m128i __A, __m128i __B, __m128i __C)
blocks.c: ^~~~~~~~~~~~~~~~~~~~~
blocks.c: blocks.c:144:6: note: called from here
blocks.c: s1 = _mm_sha256rnds2_epu32(x1, x0, h1); \
blocks.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: blocks.c:188:3: note: in expansion of macro 'DO16ROUNDS'
blocks.c: DO16ROUNDS(j0, j1, j2, j3, cc, cd, ce, cf);
blocks.c: ^~~~~~~~~~
blocks.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/immintrin.h:71:0,
blocks.c: from blocks.c:37:
blocks.c: ...

Number of similar (compiler,implementation) pairs: 32, namely:

Compiler	Implementations
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=corei7 -O -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	dolbeau/amd64-sha
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/amd64-sha
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/amd64-sha
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/amd64-sha
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/amd64-sha

Compiler output

Implementation: crypto_hashblocks/sha256/dolbeau/amd64-sha
Compiler: gcc -m64 -march=core2 -O2 -fomit-frame-pointer

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

Compiler	Implementations
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core2 -O -fomit-frame-pointer	dolbeau/amd64-sha
gcc -m64 -march=core2 -Os -fomit-frame-pointer	dolbeau/amd64-sha