Implementation notes: amd64, h3neo, crypto_aead/hs1sivlov2

Computer: h3neo
Architecture: amd64
CPU ID: AuthenticAMD-00100f63-078bfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: hs1sivlov2
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
19489? ? ?? ? ?fasterclang_-O3_-fomit-frame-pointer_-Qunused-arguments2016102720161009
19513? ? ?? ? ?fasterclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102720161009
19674? ? ?? ? ?fasterclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2016102720161009
19700? ? ?? ? ?fasterclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102720161009
19706? ? ?? ? ?fasterclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102720161009
19766? ? ?? ? ?fasterclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102720161009
19790? ? ?? ? ?fastergcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2016102720161009
19800? ? ?? ? ?fastergcc_-funroll-loops_-O3_-fomit-frame-pointer2016102720161009
19802? ? ?? ? ?fastergcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2016102720161009
19802? ? ?? ? ?fastergcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2016102720161009
19814? ? ?? ? ?fastergcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2016102720161009
19895? ? ?? ? ?fastergcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2016102720161009
19927? ? ?? ? ?fastergcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2016102720161009
19932? ? ?? ? ?fastergcc_-funroll-loops_-O2_-fomit-frame-pointer2016102720161009
19936? ? ?? ? ?fastergcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2016102720161009
19936? ? ?? ? ?fastergcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2016102720161009
19949? ? ?? ? ?fastergcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2016102720161009
19967? ? ?? ? ?fastergcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016102720161009
19972? ? ?? ? ?fastergcc_-m64_-march=k8_-O3_-fomit-frame-pointer2016102720161009
19991? ? ?? ? ?fastergcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2016102720161009
20018? ? ?? ? ?fastergcc_-m64_-O3_-fomit-frame-pointer2016102720161009
20019? ? ?? ? ?fastergcc_-march=k8_-O3_-fomit-frame-pointer2016102720161009
20028? ? ?? ? ?fastergcc_-O3_-fomit-frame-pointer2016102720161009
20033? ? ?? ? ?fastergcc_-march=barcelona_-O3_-fomit-frame-pointer2016102720161009
20035? ? ?? ? ?fastergcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016102720161009
20113? ? ?? ? ?fastergcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016102720161009
20133? ? ?? ? ?fastergcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2016102720161009
20204? ? ?? ? ?fastergcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2016102720161009
20215? ? ?? ? ?fastergcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2016102720161009
20247? ? ?? ? ?fastergcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016102720161009
20262? ? ?? ? ?fastergcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2016102720161009
20334? ? ?? ? ?fastergcc_-march=nocona_-O3_-fomit-frame-pointer2016102720161009
20335? ? ?? ? ?fastergcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2016102720161009
20704? ? ?? ? ?fastergcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2016102720161009
20706? ? ?? ? ?fastergcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2016102720161009
20711? ? ?? ? ?fastergcc_-funroll-loops_-O_-fomit-frame-pointer2016102720161009
20716? ? ?? ? ?fastergcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2016102720161009
20730? ? ?? ? ?fastergcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2016102720161009
20784? ? ?? ? ?fastergcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2016102720161009
20811? ? ?? ? ?fastergcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2016102720161009
20843? ? ?? ? ?fastergcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2016102720161009
20864? ? ?? ? ?fastergcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2016102720161009
20864? ? ?? ? ?fastergcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2016102720161009
20868? ? ?? ? ?fastergcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2016102720161009
21157? ? ?? ? ?fastergcc_-march=barcelona_-O2_-fomit-frame-pointer2016102720161009
21158? ? ?? ? ?fastergcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016102720161009
21160? ? ?? ? ?fastergcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016102720161009
21160? ? ?? ? ?fastergcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2016102720161009
21170? ? ?? ? ?fastergcc_-m64_-march=k8_-O2_-fomit-frame-pointer2016102720161009
21180? ? ?? ? ?fastergcc_-march=k8_-O2_-fomit-frame-pointer2016102720161009
21264? ? ?? ? ?fastergcc_-m64_-O2_-fomit-frame-pointer2016102720161009
21277? ? ?? ? ?fastergcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2016102720161009
21289? ? ?? ? ?fastergcc_-march=nocona_-O2_-fomit-frame-pointer2016102720161009
21294? ? ?? ? ?fastergcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2016102720161009
21301? ? ?? ? ?fastergcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2016102720161009
21315? ? ?? ? ?fastergcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016102720161009
21316? ? ?? ? ?fastergcc_-O2_-fomit-frame-pointer2016102720161009
21325? ? ?? ? ?fastergcc_-march=barcelona_-Os_-fomit-frame-pointer2016102720161009
21328? ? ?? ? ?fastergcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016102720161009
21343? ? ?? ? ?fastergcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2016102720161009
21388? ? ?? ? ?fastergcc_-Os_-fomit-frame-pointer2016102720161009
21398? ? ?? ? ?fastergcc_-m64_-Os_-fomit-frame-pointer2016102720161009
21398? ? ?? ? ?fastergcc_-m64_-march=k8_-Os_-fomit-frame-pointer2016102720161009
21426? ? ?? ? ?fastergcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2016102720161009
21429? ? ?? ? ?fastergcc_-march=k8_-Os_-fomit-frame-pointer2016102720161009
21435? ? ?? ? ?fastergcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2016102720161009
21478? ? ?? ? ?fastergcc_-fno-schedule-insns_-O_-fomit-frame-pointer2016102720161009
21556? ? ?? ? ?fastergcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2016102720161009
21585? ? ?? ? ?fastergcc_-march=nocona_-Os_-fomit-frame-pointer2016102720161009
21587? ? ?? ? ?fastergcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2016102720161009
21665? ? ?? ? ?fastergcc_-m64_-march=k8_-O_-fomit-frame-pointer2016102720161009
21681? ? ?? ? ?fastergcc_-march=k8_-O_-fomit-frame-pointer2016102720161009
21681? ? ?? ? ?fastergcc_-march=nocona_-O_-fomit-frame-pointer2016102720161009
21718? ? ?? ? ?fastergcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2016102720161009
21718? ? ?? ? ?fastergcc_-m64_-march=nocona_-O_-fomit-frame-pointer2016102720161009
21736? ? ?? ? ?fastergcc_-O_-fomit-frame-pointer2016102720161009
21743? ? ?? ? ?fastergcc_-m64_-O_-fomit-frame-pointer2016102720161009
21767? ? ?? ? ?fastergcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2016102720161009
21799? ? ?? ? ?fastergcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2016102720161009
21835? ? ?? ? ?fastergcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016102720161009
21838? ? ?? ? ?fastergcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2016102720161009
21962? ? ?? ? ?fastergcc_-funroll-loops_-Os_-fomit-frame-pointer2016102720161009
22047? ? ?? ? ?fastergcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2016102720161009
22049? ? ?? ? ?fastergcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2016102720161009
22056? ? ?? ? ?fastergcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2016102720161009
22058? ? ?? ? ?fastergcc_-march=barcelona_-O_-fomit-frame-pointer2016102720161009
29247? ? ?? ? ?refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102720161009
29286? ? ?? ? ?refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102720161009
29294? ? ?? ? ?refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2016102720161009
29340? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2016102720161009
29397? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2016102720161009
29410? ? ?? ? ?refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102720161009
29823? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2016102720161009
29858? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016102720161009
30663? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2016102720161009
30821? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2016102720161009
30874? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2016102720161009
31071? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2016102720161009
31256? ? ?? ? ?refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2016102720161009
31268? ? ?? ? ?refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2016102720161009
31441? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2016102720161009
32058? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2016102720161009
32071? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2016102720161009
32076? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2016102720161009
32086? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2016102720161009
32346? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2016102720161009
32355? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2016102720161009
32790? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2016102720161009
32855? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2016102720161009
32859? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2016102720161009
32871? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2016102720161009
32885? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016102720161009
33043? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2016102720161009
33675? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2016102720161009
33701? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2016102720161009
33709? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2016102720161009
33822? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2016102720161009
33891? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2016102720161009
33915? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2016102720161009
33953? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2016102720161009
40052? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2016102720161009
43431? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2016102720161009
44188? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2016102720161009
44517? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2016102720161009
45104? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2016102720161009
45124? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2016102720161009
45130? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2016102720161009
45179? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2016102720161009
45364? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2016102720161009
45375? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2016102720161009
45466? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2016102720161009
45701? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2016102720161009
45776? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2016102720161009
45779? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2016102720161009
45925? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2016102720161009
50373? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2016102720161009
50454? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2016102720161009
50473? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2016102720161009
50483? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2016102720161009
50560? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2016102720161009
50725? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2016102720161009
50847? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2016102720161009
51056? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2016102720161009
54580? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016102720161009
54876? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2016102720161009
54932? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2016102720161009
54948? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2016102720161009
55245? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2016102720161009
55265? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2016102720161009
55514? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2016102720161009
57467? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2016102720161009
57489? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2016102720161009
57545? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2016102720161009
58244? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2016102720161009
59367? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2016102720161009
59478? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2016102720161009
59554? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2016102720161009
59758? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2016102720161009
59833? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2016102720161009
59858? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2016102720161009
59995? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2016102720161009
60143? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2016102720161009
60214? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2016102720161009
60483? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2016102720161009
60598? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2016102720161009
60631? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2016102720161009
60649? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2016102720161009
60662? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2016102720161009
60675? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2016102720161009
60870? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2016102720161009
61094? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2016102720161009
61452? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2016102720161009
61647? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2016102720161009
63522? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2016102720161009
63529? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2016102720161009
63575? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2016102720161009
64532? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2016102720161009
64607? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2016102720161009
64799? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2016102720161009
64949? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2016102720161009
68440? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2016102720161009
70363? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2016102720161009
74892? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2016102720161009
75009? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2016102720161009
84900? ? ?? ? ?fastergcc2016102720161009
85087? ? ?? ? ?fastercc2016102720161009
85507? ? ?? ? ?fastergcc_-funroll-loops2016102720161009
355987? ? ?? ? ?refgcc_-funroll-loops2016102720161009
362211? ? ?? ? ?refgcc2016102720161009
366484? ? ?? ? ?refcc2016102720161009

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:
CompilerImplementations
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
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: 79, namely:
CompilerImplementations
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
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: 92, namely:
CompilerImplementations
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
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: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
encrypt.c: from encrypt.c:54:
encrypt.c: encrypt.c:476:50: 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: 3, namely:
CompilerImplementations
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:
CompilerImplementations
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:
CompilerImplementations
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:
CompilerImplementations
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
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: 89, namely:
CompilerImplementations
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:
CompilerImplementations
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:
CompilerImplementations
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:
CompilerImplementations
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