Implementation notes: amd64, hydra1, crypto_aead/joltikneq12864v1

Computer: hydra1
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_aead
Primitive: joltikneq12864v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
9217959	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161017	20161009
9218198	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161017	20161009
9218248	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161017	20161009
9219590	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161017	20161009
9219629	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161017	20161009
9219786	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161017	20161009
9220020	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161017	20161009
9273890	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161017	20161009
9274371	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161017	20161009
9324176	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161017	20161009
9324372	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161017	20161009
9357029	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161017	20161009
9357538	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161017	20161009
9357909	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161017	20161009
9357960	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161017	20161009
9358214	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161017	20161009
9360128	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161017	20161009
9360208	`ref`	`gcc -O3 -fomit-frame-pointer`	20161017	20161009
9360727	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161017	20161009
9379837	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161017	20161009
12391976	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161017	20161009
12419570	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161017	20161009
12419848	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161017	20161009
12419867	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161017	20161009
13040741	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161017	20161009
13040762	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161017	20161009
15859799	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161017	20161009
15859834	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161017	20161009
15979513	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161017	20161009
15979753	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161017	20161009
16028760	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161017	20161009
16028927	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161017	20161009
16051976	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161017	20161009
16052027	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161017	20161009
16052773	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161017	20161009
16542080	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161017	20161009
16547146	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161017	20161009
16740072	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161017	20161009
16931158	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161017	20161009
16931248	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161017	20161009
16934119	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161017	20161009
17005816	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161017	20161009
17017626	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161017	20161009
17097754	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161017	20161009
21075766	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161017	20161009
21075945	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161017	20161009
21254594	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161017	20161009
21254715	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161017	20161009
21254983	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161017	20161009
21258306	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161017	20161009
21278677	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161017	20161009
21380426	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161017	20161009
22420714	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161017	20161009
22424643	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161017	20161009
22500431	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161017	20161009
22766189	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161017	20161009
22849768	`ref`	`gcc -O -fomit-frame-pointer`	20161017	20161009
22956920	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161017	20161009
22961198	`ref`	`gcc -O2 -fomit-frame-pointer`	20161017	20161009
22961814	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161017	20161009
22998611	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161017	20161009
23062006	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161017	20161009
23542790	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161017	20161009
23556998	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161017	20161009
23563312	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161017	20161009
23609413	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161017	20161009
23631048	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161017	20161009
23666725	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161017	20161009
23666960	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161017	20161009
23686394	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161017	20161009
24952915	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161017	20161009
24953006	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161017	20161009
24953288	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161017	20161009
24953439	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161017	20161009
25702626	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161017	20161009
25705712	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161017	20161009
25911931	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161017	20161009
25912009	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161017	20161009
25912155	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161017	20161009
25919579	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161017	20161009
25919783	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161017	20161009
25924404	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161017	20161009
25933083	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161017	20161009
26635189	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161017	20161009
26650899	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161017	20161009
27579240	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161017	20161009
27583272	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161017	20161009
27583858	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161017	20161009
27584347	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161017	20161009
27585955	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161017	20161009
27693544	`ref`	`gcc -Os -fomit-frame-pointer`	20161017	20161009
27724938	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161017	20161009
27726359	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161017	20161009
27729618	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161017	20161009
27731589	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161017	20161009
27732436	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161017	20161009
27736310	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161017	20161009
27742478	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161017	20161009
71159771	`ref`	`cc`	20161017	20161009
71255360	`ref`	`gcc`	20161017	20161009
71430946	`ref`	`gcc -funroll-loops`	20161017	20161009

Test failure

Implementation: crypto_aead/joltikneq12864v1/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/joltikneq12864v1/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/joltikneq12864v1/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/joltikneq12864v1/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