Implementation notes: amd64, glyme, crypto_aead/joltikneq8048v1

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: joltikneq8048v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
272948	`vperm`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
272956	`vperm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
273144	`vperm`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
273304	`vperm`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
274380	`vperm`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
274676	`vperm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
274708	`vperm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
274772	`vperm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
274788	`vperm`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
274812	`vperm`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
274840	`vperm`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
274848	`vperm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
274904	`vperm`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
274932	`vperm`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
274956	`vperm`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
275060	`vperm`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
275324	`vperm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
275384	`vperm`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
275400	`vperm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
275460	`vperm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
279256	`vperm`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
279264	`vperm`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
279384	`vperm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
279388	`vperm`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
279452	`vperm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
281112	`vperm`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
3882292	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
3884380	`ref`	`gcc -O3 -fomit-frame-pointer`	20170204	20170105
3884644	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20170204	20170105
3885328	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
3885356	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
3885376	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
3885836	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
3886324	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
3888216	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
3888456	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
3893028	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170204	20170105
3894664	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
3894940	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
3895160	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
3895660	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170204	20170105
3898028	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
3898096	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
3898292	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
3899116	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
3899756	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
3962776	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
3965628	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
3967736	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
3969208	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
4478008	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
4478224	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
4713360	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
4713440	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
4713476	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
4728300	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
6687544	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
6718160	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
6741416	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170204	20170105
6751972	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
6760104	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
6770820	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
6772344	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170204	20170105
6772996	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
6788824	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
7872372	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170204	20170105
7900132	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
8090152	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
8091080	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
8295092	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
8295748	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170204	20170105
8298880	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170204	20170105
8313752	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170204	20170105
8341068	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
8582276	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
8586268	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
8598608	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
8634272	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
8637132	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
8637448	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
8638284	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
8638536	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
8638932	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
8639092	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
8640220	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20170204	20170105
8646556	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
8669616	`ref`	`gcc -O2 -fomit-frame-pointer`	20170204	20170105
9231196	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
9299168	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
9624388	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
9631080	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20170204	20170105
9632464	`ref`	`gcc -Os -fomit-frame-pointer`	20170204	20170105
9632488	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
9635092	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
9635772	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
9640172	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170204	20170105
9640372	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
9658760	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
9677820	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
9694304	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
9700212	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
9702196	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
9702968	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
9703448	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
9706208	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
9744580	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
9754840	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170204	20170105
9842332	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
9847968	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
9855908	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
9903652	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
9918640	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
9919120	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
10649752	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
10649952	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
10650340	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
10652436	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
10658676	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
10695608	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
10862352	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20170204	20170105
10864360	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
10927824	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20170204	20170105
10933440	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
11844808	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
11845784	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
11846776	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
11849100	`ref`	`gcc -O -fomit-frame-pointer`	20170204	20170105
11874080	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20170204	20170105
29758772	`ref`	`gcc`	20170204	20170105
29783440	`ref`	`gcc -funroll-loops`	20170204	20170105
33320728	`ref`	`cc`	20170204	20170105

Compiler output

Implementation: crypto_aead/joltikneq8048v1/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/joltikneq8048v1/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/joltikneq8048v1/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