Implementation notes: amd64, hydra1, crypto_aead/hs1sivlov2

Computer: hydra1
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: hs1sivlov2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
12592	`faster`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
12603	`faster`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161016	20161009
12621	`faster`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
12624	`faster`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161016	20161009
12632	`faster`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
12640	`faster`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
12677	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
12696	`faster`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
12698	`faster`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
12707	`faster`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
12711	`faster`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161016	20161009
12730	`faster`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161016	20161009
12781	`faster`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
12782	`faster`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
12800	`faster`	`gcc -m64 -O3 -fomit-frame-pointer`	20161016	20161009
12800	`faster`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
12808	`faster`	`gcc -O3 -fomit-frame-pointer`	20161016	20161009
12815	`faster`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
12815	`faster`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
12827	`faster`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
12829	`faster`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
12830	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
12833	`faster`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
12835	`faster`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161016	20161009
12837	`faster`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161016	20161009
12846	`faster`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161016	20161009
12858	`faster`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161016	20161009
12899	`faster`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161016	20161009
12901	`faster`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
12938	`faster`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161016	20161009
12952	`faster`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161016	20161009
13053	`faster`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
13082	`faster`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
13083	`faster`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161016	20161009
13083	`faster`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161016	20161009
13096	`faster`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161016	20161009
13109	`faster`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
13123	`faster`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161016	20161009
13161	`faster`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
13196	`faster`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
13216	`faster`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
13219	`faster`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
13232	`faster`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
13240	`faster`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161016	20161009
13525	`faster`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
13598	`faster`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
13606	`faster`	`gcc -m64 -O2 -fomit-frame-pointer`	20161016	20161009
13613	`faster`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
13632	`faster`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
13635	`faster`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
13640	`faster`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
13646	`faster`	`gcc -O2 -fomit-frame-pointer`	20161016	20161009
13650	`faster`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161016	20161009
13665	`faster`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
13674	`faster`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161016	20161009
13677	`faster`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161016	20161009
13686	`faster`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161016	20161009
13688	`faster`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161016	20161009
13707	`faster`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
13709	`faster`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
13757	`faster`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
13773	`faster`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
13788	`faster`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
13838	`faster`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161016	20161009
13856	`faster`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161016	20161009
13864	`faster`	`gcc -Os -fomit-frame-pointer`	20161016	20161009
13867	`faster`	`gcc -m64 -Os -fomit-frame-pointer`	20161016	20161009
13870	`faster`	`gcc -O -fomit-frame-pointer`	20161016	20161009
13870	`faster`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161016	20161009
13875	`faster`	`gcc -m64 -O -fomit-frame-pointer`	20161016	20161009
13888	`faster`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
13888	`faster`	`gcc -march=k8 -O -fomit-frame-pointer`	20161016	20161009
13891	`faster`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
13912	`faster`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
13926	`faster`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
13954	`faster`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
13955	`faster`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
13963	`faster`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
13970	`faster`	`gcc -march=nocona -O -fomit-frame-pointer`	20161016	20161009
13973	`faster`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
13981	`faster`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161016	20161009
13987	`faster`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
13989	`faster`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
14010	`faster`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161016	20161009
14016	`faster`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161016	20161009
14045	`faster`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161016	20161009
28952	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
28963	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
28992	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
29010	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
29014	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
29022	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161016	20161009
29344	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
29356	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
30578	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
30611	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
30759	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161016	20161009
30976	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161016	20161009
30997	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161016	20161009
31123	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161016	20161009
31238	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161016	20161009
31376	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
31414	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161016	20161009
31714	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161016	20161009
31770	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161016	20161009
31784	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
31834	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161016	20161009
31979	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
32202	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
32259	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
32323	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
32438	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
32848	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
33075	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161016	20161009
33125	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161016	20161009
33171	`ref`	`gcc -O3 -fomit-frame-pointer`	20161016	20161009
33404	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161016	20161009
33421	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161016	20161009
33498	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161016	20161009
33784	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
33835	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161016	20161009
43296	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161016	20161009
43552	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161016	20161009
43663	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161016	20161009
44015	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161016	20161009
44512	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161016	20161009
44541	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
44544	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
44597	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161016	20161009
44621	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161016	20161009
44768	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161016	20161009
44787	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
44899	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
45099	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
45237	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
45277	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161016	20161009
49749	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161016	20161009
49765	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161016	20161009
49893	`ref`	`gcc -O2 -fomit-frame-pointer`	20161016	20161009
49925	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161016	20161009
50098	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
50134	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161016	20161009
50167	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161016	20161009
50198	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161016	20161009
50301	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161016	20161009
53821	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161016	20161009
53845	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
53853	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161016	20161009
53909	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
54517	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
54526	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161016	20161009
54546	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
54550	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161016	20161009
54874	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
54893	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161016	20161009
54909	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
54931	`ref`	`gcc -Os -fomit-frame-pointer`	20161016	20161009
54936	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
55346	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161016	20161009
55347	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161016	20161009
55354	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161016	20161009
55419	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161016	20161009
55542	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
56278	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161016	20161009
56838	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161016	20161009
58704	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161016	20161009
58776	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161016	20161009
58925	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161016	20161009
59131	`ref`	`gcc -O -fomit-frame-pointer`	20161016	20161009
59189	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161016	20161009
59242	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
59301	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161016	20161009
59350	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161016	20161009
59384	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
59466	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161016	20161009
59487	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161016	20161009
59517	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161016	20161009
59605	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161016	20161009
59624	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161016	20161009
59715	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161016	20161009
60607	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161016	20161009
60701	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161016	20161009
60731	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161016	20161009
61064	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161016	20161009
68880	`faster`	`gcc -funroll-loops`	20161016	20161009
69127	`faster`	`gcc`	20161016	20161009
69381	`faster`	`cc`	20161016	20161009
359024	`ref`	`gcc -funroll-loops`	20161016	20161009
362755	`ref`	`gcc`	20161016	20161009
363884	`ref`	`cc`	20161016	20161009

Test failure

Implementation: crypto_aead/hs1sivlov2/dolbeau/amd64-sse
Compiler: gcc -m64 -march=core2 -O2 -fomit-frame-pointer

error 111

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

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

Compiler output

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

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

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

Compiler output

Implementation: crypto_aead/hs1sivlov2/dolbeau/amd64-avx2
Compiler: cc

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

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

Compiler output

Implementation: crypto_aead/hs1sivlov2/dolbeau/amd64-avx512
Compiler: cc

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

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

Compiler output

Implementation: crypto_aead/hs1sivlov2/dolbeau/amd64-sse
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

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: 6, namely:

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

Compiler output

Implementation: crypto_aead/hs1sivlov2/dolbeau/amd64-avx2
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

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

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

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

Compiler output

Implementation: crypto_aead/hs1sivlov2/dolbeau/amd64-avx512
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: encrypt.c:90:2: error: "This code requires AVX512F to work"
encrypt.c: #error "This code requires AVX512F to work"
encrypt.c: ^
encrypt.c: encrypt.c: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: 6, namely:

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

Compiler output

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

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

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

Compiler output

Implementation: crypto_aead/hs1sivlov2/dolbeau/amd64-sse
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: c128.h: In function 'chacha_noxor128':
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:190:0:
encrypt.c: c128.h:14:84: error: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ^
encrypt.c: 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/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:190:0:
encrypt.c: c128.h:12:84: error: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ^
encrypt.c: ...
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: c128.h: In function 'chacha_noxor128':
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:190:0:
encrypt.c: c128.h:14:84: error: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
encrypt.c: ^
encrypt.c: 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/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:32:0,
encrypt.c: from encrypt.c:54:
encrypt.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:190:0:
encrypt.c: c128.h:12:84: error: called from here
encrypt.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
encrypt.c: ^
encrypt.c: ...

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

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

Compiler output

Implementation: crypto_aead/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