Implementation notes: amd64, skylake, crypto_aead/aes128otrsv2

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: aes128otrsv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
83546	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
84002	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
84062	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
84440	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
84526	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
85116	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
85132	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
85292	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
85294	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
85492	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
85822	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
85926	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
86196	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
86200	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
86410	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
86492	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
86598	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
86798	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
86884	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
86974	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
87206	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
87308	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
87320	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
87424	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
87690	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
87742	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
87796	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
87834	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
87848	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
87916	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
88002	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
88018	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
88100	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
88630	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
88982	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
88992	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
89220	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
89294	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
89434	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
89644	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
89708	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
89984	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
90098	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
90362	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
90386	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
90428	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
90774	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
90926	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
91168	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
91238	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
91238	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
91248	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
91354	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
91480	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
91480	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
91892	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
92142	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
92164	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
92344	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
92558	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
92744	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
93624	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
94318	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
94690	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
94720	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
94812	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
94830	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
94836	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
95374	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
95646	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
95688	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
96254	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
96258	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
96358	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
96514	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
99108	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
99446	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
99490	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
100266	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
100698	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
100848	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
101138	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
101202	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
101206	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
101554	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
101632	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
101816	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
101864	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
101870	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
102414	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
102440	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
102692	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
102748	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
103036	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
103204	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
103362	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
103758	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
103784	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
103834	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
103854	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
103898	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
103908	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
103940	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
104026	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
104028	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
104038	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
104098	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
104126	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
104258	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
104300	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
105610	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
105646	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
106112	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
106400	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
145018	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
146348	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
150334	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
153680	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
285030	`ref`	`cc`	20161216	20161026
285878	`ref`	`gcc -funroll-loops`	20161216	20161026
288276	`ref`	`gcc`	20161216	20161026

Compiler output

Implementation: crypto_aead/aes128otrsv2/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/aes128otrsv2/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