Implementation notes: amd64, glyme, crypto_aead/joltikneq12864v1

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: joltikneq12864v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
356364	`vperm`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
359368	`vperm`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
359700	`vperm`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
359980	`vperm`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
360520	`vperm`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
361836	`vperm`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
361868	`vperm`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
362264	`vperm`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
362756	`vperm`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
362784	`vperm`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
362824	`vperm`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
362864	`vperm`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
363456	`vperm`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
363496	`vperm`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
363552	`vperm`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
364344	`vperm`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
364348	`vperm`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
364368	`vperm`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
364396	`vperm`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
364576	`vperm`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
364672	`vperm`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
364812	`vperm`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
365084	`vperm`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
365100	`vperm`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
365156	`vperm`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
365352	`vperm`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
8531276	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170204	20170105
8533452	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170204	20170105
8594788	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
8594992	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
8605452	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
8605568	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170204	20170105
8605748	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20170204	20170105
8607816	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170204	20170105
8608464	`ref`	`gcc -O3 -fomit-frame-pointer`	20170204	20170105
8608892	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170204	20170105
8611284	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
8613652	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
8622544	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170204	20170105
8629480	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
8630008	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170204	20170105
8631212	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170204	20170105
8635424	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170204	20170105
8642464	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
8642728	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170204	20170105
8646568	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170204	20170105
8764636	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
8771304	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
8782332	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
8783400	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170204	20170105
10009092	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
10010748	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
10689796	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
10690916	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
10691436	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170204	20170105
10713868	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170204	20170105
13642148	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
13683512	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
13690520	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
13692336	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
13698448	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
13707912	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
13710720	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
13739952	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170204	20170105
13745588	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170204	20170105
15447084	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170204	20170105
15460996	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170204	20170105
15488808	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
15806112	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
15809916	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170204	20170105
15810328	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
16089760	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
16404320	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
16442240	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170204	20170105
17461176	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20170204	20170105
17462752	`ref`	`gcc -O2 -fomit-frame-pointer`	20170204	20170105
17465228	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
17468260	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
17470820	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170204	20170105
17568580	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170204	20170105
17569824	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170204	20170105
17579748	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170204	20170105
17673808	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170204	20170105
17677792	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170204	20170105
17678148	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170204	20170105
17692916	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170204	20170105
17706196	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170204	20170105
17953804	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
18203352	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170204	20170105
19035172	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
19047684	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
19091112	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170204	20170105
19148492	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
19151340	`ref`	`gcc -Os -fomit-frame-pointer`	20170204	20170105
19235672	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20170204	20170105
19242800	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
19243232	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170204	20170105
19245952	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170204	20170105
19251200	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
19431920	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20170204	20170105
19500856	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170204	20170105
19573728	`ref`	`gcc -O -fomit-frame-pointer`	20170204	20170105
19731504	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170204	20170105
19736156	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170204	20170105
19872252	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170204	20170105
19978976	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
20127536	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170204	20170105
20160456	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
20644964	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20170204	20170105
20845536	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170204	20170105
20871952	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
20884092	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170204	20170105
21232388	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
21382488	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170204	20170105
21713184	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170204	20170105
21720236	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
21722244	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170204	20170105
21733164	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170204	20170105
21749488	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170204	20170105
21749708	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170204	20170105
21773704	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170204	20170105
21902704	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170204	20170105
21939844	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170204	20170105
21945480	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
21959928	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170204	20170105
21967504	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170204	20170105
22011248	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170204	20170105
58917480	`ref`	`gcc`	20170204	20170105
59395008	`ref`	`gcc -funroll-loops`	20170204	20170105
67868752	`ref`	`cc`	20170204	20170105

Compiler output

Implementation: crypto_aead/joltikneq12864v1/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/joltikneq12864v1/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/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