Implementation notes: amd64, glyme, crypto_aead/joltikneq9696v1

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: joltikneq9696v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
424044	`vperm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
424088	`vperm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
424132	`vperm`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
424300	`vperm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
424316	`vperm`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
424352	`vperm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
424380	`vperm`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
424428	`vperm`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
424480	`vperm`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
424500	`vperm`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
424624	`vperm`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
424740	`vperm`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
425504	`vperm`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
425544	`vperm`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
425548	`vperm`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
425552	`vperm`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
425576	`vperm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
425584	`vperm`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
425584	`vperm`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
425592	`vperm`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
425592	`vperm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
425668	`vperm`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
426248	`vperm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
426292	`vperm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
426524	`vperm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
426548	`vperm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
8559368	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
8560088	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
8599640	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
8601236	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20170204	20170105
8603296	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
8603648	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
8603932	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
8605536	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170204	20170105
8605668	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
8606040	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
8606380	`ref`	`gcc -O3 -fomit-frame-pointer`	20170204	20170105
8607140	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
8608432	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
8609344	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
8612108	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170204	20170105
8626640	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
8627148	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
8642644	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
8656996	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
8659952	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
8778972	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
8778988	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
8782896	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
8782972	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
10019400	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
10021948	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
10691276	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
10701628	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
10709096	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
10717796	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
13621360	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170204	20170105
13642340	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
13664740	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
13667936	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
13680828	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
13683188	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
13690292	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
13701760	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
13742252	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170204	20170105
15329820	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
15404780	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
15519852	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170204	20170105
15520172	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
15520232	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170204	20170105
15560168	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
15560172	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170204	20170105
16263688	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170204	20170105
16264580	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
17454352	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
17454968	`ref`	`gcc -O2 -fomit-frame-pointer`	20170204	20170105
17455244	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20170204	20170105
17465428	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
17468712	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
17471296	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
17512448	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
17565256	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
17571864	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
17573540	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
17574108	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
17591868	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
17597740	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
18179680	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
18199132	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
19279652	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
19279900	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
19279968	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
19280768	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
19281940	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
19293532	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170204	20170105
19325128	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170204	20170105
19379424	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
19430164	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20170204	20170105
19438760	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
19438768	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
19438808	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
19438816	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
19453092	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
19482524	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
19541924	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
19547148	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
19573008	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
19573192	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
19580512	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
19582628	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
19585264	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
19624688	`ref`	`gcc -Os -fomit-frame-pointer`	20170204	20170105
19627144	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
19634488	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
19634516	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
19650076	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20170204	20170105
19979596	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
19990992	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
19994884	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
20032528	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
20048808	`ref`	`gcc -O -fomit-frame-pointer`	20170204	20170105
20048992	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20170204	20170105
20439920	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
20441156	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
20997816	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
21002104	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20170204	20170105
21411880	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
21413888	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
59196660	`ref`	`gcc -funroll-loops`	20170204	20170105
60118456	`ref`	`gcc`	20170204	20170105
65810576	`ref`	`cc`	20170204	20170105

Compiler output

Implementation: crypto_aead/joltikneq9696v1/vperm
Compiler: cc

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: 5, namely:

Compiler	Implementations
cc	vperm
clang -O3 -fomit-frame-pointer -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

Number of similar (compiler,implementation) pairs: 70, namely:

Compiler	Implementations
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=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=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: 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