Implementation notes: amd64, hydra1, crypto_aead/joltikneq9696v1

Computer: hydra1
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: joltikneq9696v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
9228470	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161017	20161009
9228515	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161017	20161009
9228536	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161018	20161009
9228672	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161018	20161009
9228757	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161017	20161009
9229747	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161017	20161009
9230136	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161018	20161009
9237582	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161018	20161009
9238039	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161017	20161009
9319839	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161017	20161009
9319879	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161017	20161009
9360467	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161017	20161009
9360870	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161017	20161009
9360960	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161017	20161009
9360967	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161017	20161009
9361008	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161017	20161009
9363219	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161018	20161009
9363352	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161017	20161009
9363374	`ref`	`gcc -O3 -fomit-frame-pointer`	20161017	20161009
9384454	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161017	20161009
12395226	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161018	20161009
12421440	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161017	20161009
12421482	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161017	20161009
12422251	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161017	20161009
13042443	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161018	20161009
13042781	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161017	20161009
15854094	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161017	20161009
15854289	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161018	20161009
15984819	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161018	20161009
15986744	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161017	20161009
15987122	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161017	20161009
15987478	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161018	20161009
16014885	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161018	20161009
16060777	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161017	20161009
16060856	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161017	20161009
16678797	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161018	20161009
16680008	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161017	20161009
16733696	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161018	20161009
16777165	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161018	20161009
16789219	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161017	20161009
16811891	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161017	20161009
16935024	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161018	20161009
16983744	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161017	20161009
17159190	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161017	20161009
21258784	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161017	20161009
21261416	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161017	20161009
21283981	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161017	20161009
22195450	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161017	20161009
22298965	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161017	20161009
22349065	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161017	20161009
22349293	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161017	20161009
22498782	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161017	20161009
22883490	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161017	20161009
22886423	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161017	20161009
22984456	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161017	20161009
23052912	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161018	20161009
23056357	`ref`	`gcc -O2 -fomit-frame-pointer`	20161017	20161009
23135528	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161017	20161009
23306341	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161017	20161009
23649873	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161017	20161009
23650902	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161017	20161009
24098552	`ref`	`gcc -O -fomit-frame-pointer`	20161017	20161009
24099918	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161017	20161009
24234410	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161017	20161009
24234437	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161017	20161009
24234948	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161017	20161009
24322202	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161017	20161009
24343176	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161017	20161009
24382393	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161018	20161009
24534508	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161017	20161009
25471794	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161017	20161009
25472099	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161017	20161009
25472229	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161017	20161009
25473357	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161017	20161009
26098922	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161017	20161009
26111632	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161017	20161009
26113258	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161017	20161009
26114127	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161018	20161009
26114304	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161017	20161009
26117627	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161018	20161009
26458384	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161018	20161009
26664074	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161017	20161009
26669619	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161018	20161009
31573696	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161017	20161009
31573932	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161017	20161009
32496535	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161017	20161009
32500115	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161017	20161009
32502823	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161017	20161009
32503105	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161017	20161009
32503232	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161017	20161009
32509235	`ref`	`gcc -Os -fomit-frame-pointer`	20161017	20161009
32509839	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161017	20161009
32509930	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161017	20161009
32511929	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161017	20161009
32517053	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161017	20161009
32649216	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161018	20161009
32657162	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161017	20161009
32667170	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161017	20161009
70083083	`ref`	`gcc -funroll-loops`	20161017	20161009
70130165	`ref`	`gcc`	20161017	20161009
70660824	`ref`	`cc`	20161018	20161009

Test failure

Implementation: crypto_aead/joltikneq9696v1/vperm
Compiler: gcc -m64 -march=core2 -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 14, namely:

Compiler	Implementations
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	vperm
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	ref vperm
gcc -m64 -march=core2 -O -fomit-frame-pointer	vperm
gcc -m64 -march=core2 -Os -fomit-frame-pointer	vperm
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	vperm
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	vperm
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	vperm
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	vperm
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	vperm
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	vperm
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	vperm
gcc -m64 -march=corei7 -O -fomit-frame-pointer	vperm
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	vperm

Compiler output

Implementation: crypto_aead/joltikneq9696v1/vperm
Compiler: cc

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

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

Compiler output

Implementation: crypto_aead/joltikneq9696v1/vperm
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

joltik.c: joltik.c:29:3: error: "This implementation requires either SSSE3 or AVX2 instruction sets."
joltik.c: #error "This implementation requires either SSSE3 or AVX2 instruction sets."
joltik.c: ^
joltik.c: 1 error generated.

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

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

Compiler output

Implementation: crypto_aead/joltikneq9696v1/vperm
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

joltik.c: joltik.c:29:3: error: #error "This implementation requires either SSSE3 or AVX2 instruction sets."
joltik.c: #error "This implementation requires either SSSE3 or AVX2 instruction sets."
joltik.c: ^
joltik.c: joltik.c:29:3: error: #error "This implementation requires either SSSE3 or AVX2 instruction sets."
joltik.c: #error "This implementation requires either SSSE3 or AVX2 instruction sets."
joltik.c: ^

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	vperm
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	vperm
gcc -m64 -march=barcelona -O -fomit-frame-pointer	vperm
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	vperm