Implementation notes: amd64, skylake, crypto_aead/aes256otrpv2

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: aes256otrpv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
112186	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
112200	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
112314	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
112772	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
113054	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
113518	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
113718	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
113792	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
113806	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
113920	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
114156	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
114342	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
114384	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
114546	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
114816	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
115056	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
115120	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
115130	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
115156	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
115190	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
115222	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
115230	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
115362	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
116976	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
117274	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
117840	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
118392	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
118400	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
118454	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
118476	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
118552	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
118580	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
118734	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
118812	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
118842	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
119506	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
121484	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
121582	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
121606	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
121662	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
121664	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
121716	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
121720	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
121814	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
122922	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
123590	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
123626	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
123650	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
123714	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
123752	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
123788	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
124652	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
124772	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
124800	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
124828	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
124844	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
124980	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
125060	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
125132	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
125276	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
125942	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
126078	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
127292	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
129570	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
129632	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
129634	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
129682	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
129712	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
129740	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
130276	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
130430	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
131380	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
131550	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
131698	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
132122	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
135688	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
135740	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
135744	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
135748	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
135802	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
135960	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
136606	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
136998	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
137552	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
137784	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
137822	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
137942	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
138936	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
139488	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
139562	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
139608	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
139642	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
139654	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
139656	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
139754	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
140162	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
140350	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
140742	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
140942	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
141190	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
141240	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
141296	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
141308	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
141318	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
141422	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
141424	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
141644	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
141794	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
141802	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
141914	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
142040	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
142054	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
143596	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
143660	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
194330	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
194388	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
197836	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
198454	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
392036	`ref`	`gcc`	20161216	20161026
392880	`ref`	`gcc -funroll-loops`	20161216	20161026
394162	`ref`	`cc`	20161216	20161026

Compiler output

Implementation: crypto_aead/aes256otrpv2/ref
Compiler: cc

OTR.c: OTR.c:51:7: warning: built-in function 'gamma' declared as non-function
OTR.c: uint8 gamma[BLOCK]={0}, gamma2[BLOCK]={0}, Q[BLOCK]={0};
OTR.c: ^~~~~

Number of similar (compiler,implementation) pairs: 107, namely:

Compiler	Implementations
cc	ref
gcc	ref
gcc -O2 -fomit-frame-pointer	ref
gcc -O3 -fomit-frame-pointer	ref
gcc -O -fomit-frame-pointer	ref
gcc -Os -fomit-frame-pointer	ref
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	ref
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	ref
gcc -fno-schedule-insns -O -fomit-frame-pointer	ref
gcc -fno-schedule-insns -Os -fomit-frame-pointer	ref
gcc -funroll-loops	ref
gcc -funroll-loops -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -O -fomit-frame-pointer	ref
gcc -funroll-loops -Os -fomit-frame-pointer	ref
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	ref
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	ref
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	ref
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	ref
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	ref
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	ref
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	ref
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	ref
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	ref
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	ref
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	ref
gcc -m64 -O2 -fomit-frame-pointer	ref
gcc -m64 -O3 -fomit-frame-pointer	ref
gcc -m64 -O -fomit-frame-pointer	ref
gcc -m64 -Os -fomit-frame-pointer	ref
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	ref
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	ref
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	ref
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	ref
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	ref
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -O -fomit-frame-pointer	ref
gcc -m64 -march=core2 -Os -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	ref
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	ref
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	ref
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	ref
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	ref
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	ref
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=corei7 -O -fomit-frame-pointer	ref
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	ref
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	ref
gcc -m64 -march=k8 -O -fomit-frame-pointer	ref
gcc -m64 -march=k8 -Os -fomit-frame-pointer	ref
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	ref
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	ref
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	ref
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	ref
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	ref
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	ref
gcc -m64 -march=nocona -O -fomit-frame-pointer	ref
gcc -m64 -march=nocona -Os -fomit-frame-pointer	ref
gcc -march=barcelona -O2 -fomit-frame-pointer	ref
gcc -march=barcelona -O3 -fomit-frame-pointer	ref
gcc -march=barcelona -O -fomit-frame-pointer	ref
gcc -march=barcelona -Os -fomit-frame-pointer	ref
gcc -march=k8 -O2 -fomit-frame-pointer	ref
gcc -march=k8 -O3 -fomit-frame-pointer	ref
gcc -march=k8 -O -fomit-frame-pointer	ref
gcc -march=k8 -Os -fomit-frame-pointer	ref
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	ref
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	ref
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	ref
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	ref
gcc -march=nocona -O2 -fomit-frame-pointer	ref
gcc -march=nocona -O3 -fomit-frame-pointer	ref
gcc -march=nocona -O -fomit-frame-pointer	ref
gcc -march=nocona -Os -fomit-frame-pointer	ref

Compiler output

Implementation: crypto_aead/aes256otrpv2/ref
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

OTR.c: OTR.c:51:7: warning: built-in function 'gamma' declared as non-function
OTR.c: uint8 gamma[BLOCK]={0}, gamma2[BLOCK]={0}, Q[BLOCK]={0};
OTR.c: ^~~~~
OTR.c: OTR.c:51:7: warning: built-in function 'gamma' declared as non-function
OTR.c: uint8 gamma[BLOCK]={0}, gamma2[BLOCK]={0}, Q[BLOCK]={0};
OTR.c: ^~~~~

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

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