Implementation notes: amd64, skylake, crypto_aead/aes256otrsv2

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: aes256otrsv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
106698	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161216	20161026
107070	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161216	20161026
107260	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161216	20161026
107318	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161216	20161026
107906	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161216	20161026
108426	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
108616	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
108626	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
108766	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161216	20161026
109004	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161216	20161026
109156	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161216	20161026
109252	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161216	20161026
110030	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
110112	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
110194	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
110600	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
110772	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161216	20161026
110854	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161216	20161026
110930	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
110932	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161216	20161026
110948	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161216	20161026
111214	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
111266	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
111304	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
111396	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161216	20161026
111478	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161216	20161026
111714	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
111744	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161216	20161026
111918	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
111932	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
112082	`ref`	`gcc -O3 -fomit-frame-pointer`	20161216	20161026
112618	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
112626	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161216	20161026
113268	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161216	20161026
113346	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
113362	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
114168	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161216	20161026
114230	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161216	20161026
114314	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
114576	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
114776	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161216	20161026
114798	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161216	20161026
114828	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161216	20161026
114898	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
114922	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161216	20161026
115064	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
115168	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161216	20161026
115216	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161216	20161026
115430	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
115528	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161216	20161026
115586	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161216	20161026
116034	`ref`	`gcc -O2 -fomit-frame-pointer`	20161216	20161026
116114	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
116266	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161216	20161026
116356	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161216	20161026
116364	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
116430	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161216	20161026
116504	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161216	20161026
116578	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161216	20161026
116948	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161216	20161026
117650	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161216	20161026
118020	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161216	20161026
119180	`ref`	`gcc -O -fomit-frame-pointer`	20161216	20161026
119470	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161216	20161026
119824	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
119890	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161216	20161026
120264	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161216	20161026
120558	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161216	20161026
120604	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161216	20161026
123656	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161216	20161026
123764	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161216	20161026
123918	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161216	20161026
124342	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161216	20161026
124396	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161216	20161026
124424	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161216	20161026
124492	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161216	20161026
124492	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161216	20161026
124590	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161216	20161026
124876	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
125010	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
125964	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
126352	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
126382	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161216	20161026
126808	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
127172	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
127576	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161216	20161026
127664	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161216	20161026
127796	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
127906	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
128008	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
128262	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
128652	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
128674	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161216	20161026
128764	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
129158	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
129474	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161216	20161026
129496	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161216	20161026
129540	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
129586	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
129656	`ref`	`gcc -Os -fomit-frame-pointer`	20161216	20161026
129740	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
129824	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161216	20161026
129880	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
129890	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161216	20161026
129924	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161216	20161026
130012	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161216	20161026
130138	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161216	20161026
130202	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161216	20161026
130314	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161216	20161026
130472	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161216	20161026
130484	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161216	20161026
130536	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161216	20161026
132262	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161216	20161026
132278	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161216	20161026
187036	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
189876	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
191462	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161216	20161026
194308	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161216	20161026
344684	`ref`	`cc`	20161216	20161026
344774	`ref`	`gcc`	20161216	20161026
346748	`ref`	`gcc -funroll-loops`	20161216	20161026

Compiler output

Implementation: crypto_aead/aes256otrsv2/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/aes256otrsv2/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