Implementation notes: amd64, skylake, crypto_aead/tiaoxinv2

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: tiaoxinv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
1906	`nim`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161217	20161026
1906	`nim`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161217	20161026
1906	`nim`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161217	20161026
1906	`nim`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161217	20161026
1908	`nim`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161217	20161026
1910	`nim`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161217	20161026
1914	`nim`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161217	20161026
1918	`nim`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161217	20161026
1920	`nim`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161217	20161026
1924	`nim`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161217	20161026
1940	`nim`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161217	20161026
1940	`nim`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161217	20161026
1942	`nim`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161217	20161026
1942	`nim`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161217	20161026
1942	`nim`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161217	20161026
1956	`nim`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161217	20161026
1960	`nim`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161217	20161026
1966	`nim`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161217	20161026
1966	`nim`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161217	20161026
1974	`nim`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161217	20161026
1978	`nim`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161217	20161026
1982	`nim`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
1988	`nim`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
1994	`nim`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
30718	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161217	20161026
30852	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161217	20161026
30894	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161217	20161026
30958	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161217	20161026
31006	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161217	20161026
31036	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161217	20161026
31042	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161217	20161026
31144	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161217	20161026
31172	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161217	20161026
31186	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161217	20161026
31188	`ref`	`gcc -Os -fomit-frame-pointer`	20161217	20161026
31202	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161217	20161026
31202	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161217	20161026
31284	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161217	20161026
31300	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161217	20161026
31328	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161217	20161026
31338	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161217	20161026
31344	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161217	20161026
31380	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161217	20161026
31418	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161217	20161026
31436	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161217	20161026
31440	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161217	20161026
31490	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161217	20161026
31496	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161217	20161026
31558	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161217	20161026
31558	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161217	20161026
31562	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161217	20161026
31572	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161217	20161026
31578	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161217	20161026
31578	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161217	20161026
31596	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161217	20161026
31598	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161217	20161026
31602	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161217	20161026
31614	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161217	20161026
31632	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161217	20161026
31660	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161217	20161026
31676	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161217	20161026
31684	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161217	20161026
31696	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161217	20161026
31698	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161217	20161026
31714	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161217	20161026
31716	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161217	20161026
31726	`ref`	`gcc -O -fomit-frame-pointer`	20161217	20161026
31762	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161217	20161026
31818	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161217	20161026
31826	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161217	20161026
31848	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161217	20161026
31860	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161217	20161026
31882	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161217	20161026
31884	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161217	20161026
31948	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161217	20161026
31954	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161217	20161026
31960	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161217	20161026
31972	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161217	20161026
31972	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161217	20161026
32052	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161217	20161026
32072	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161217	20161026
32098	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161217	20161026
32104	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161217	20161026
32148	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161217	20161026
32174	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161217	20161026
32192	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161217	20161026
32214	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161217	20161026
32220	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161217	20161026
32224	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161217	20161026
32268	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161217	20161026
32282	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161217	20161026
32300	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161217	20161026
32334	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161217	20161026
32352	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161217	20161026
32356	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161217	20161026
32368	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161217	20161026
32376	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161217	20161026
32408	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161217	20161026
32424	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161217	20161026
32510	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161217	20161026
32580	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161217	20161026
32620	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161217	20161026
32628	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161217	20161026
32660	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161217	20161026
32662	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161217	20161026
32680	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161217	20161026
32750	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161217	20161026
32788	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161217	20161026
32828	`ref`	`gcc -O2 -fomit-frame-pointer`	20161217	20161026
32834	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161217	20161026
32840	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161217	20161026
32846	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161217	20161026
32928	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161217	20161026
32946	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161217	20161026
33062	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161217	20161026
33078	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161217	20161026
33106	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161217	20161026
33228	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161217	20161026
33270	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161217	20161026
33358	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161217	20161026
33372	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161217	20161026
33378	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161217	20161026
33410	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161217	20161026
33412	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161217	20161026
33438	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161217	20161026
33476	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161217	20161026
33770	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161217	20161026
33782	`ref`	`gcc -O3 -fomit-frame-pointer`	20161217	20161026
33972	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161217	20161026
34456	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161217	20161026
34604	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161217	20161026
35616	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161217	20161026
59010	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
59680	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
59790	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161217	20161026
59808	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
60078	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161217	20161026
60176	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161217	20161026
60494	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
60790	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
62814	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161217	20161026
64500	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
65904	`ref`	`gcc -funroll-loops`	20161217	20161026
67304	`ref`	`cc`	20161217	20161026
68244	`ref`	`gcc`	20161217	20161026

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: cc

Number of similar (compiler,implementation) pairs: 87, namely:

Compiler	Implementations
cc	nim
gcc	nim
gcc -O2 -fomit-frame-pointer	nim
gcc -O3 -fomit-frame-pointer	nim
gcc -O -fomit-frame-pointer	nim
gcc -Os -fomit-frame-pointer	nim
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	nim
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	nim
gcc -fno-schedule-insns -O -fomit-frame-pointer	nim
gcc -fno-schedule-insns -Os -fomit-frame-pointer	nim
gcc -funroll-loops	nim
gcc -funroll-loops -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -O -fomit-frame-pointer	nim
gcc -funroll-loops -Os -fomit-frame-pointer	nim
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	nim
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	nim
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	nim
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	nim
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	nim
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	nim
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	nim
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	nim
gcc -m64 -O2 -fomit-frame-pointer	nim
gcc -m64 -O3 -fomit-frame-pointer	nim
gcc -m64 -O -fomit-frame-pointer	nim
gcc -m64 -Os -fomit-frame-pointer	nim
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	nim
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	nim
gcc -m64 -march=core2 -O -fomit-frame-pointer	nim
gcc -m64 -march=core2 -Os -fomit-frame-pointer	nim
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	nim
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	nim
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	nim
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	nim
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	nim
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	nim
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	nim
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	nim
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	nim
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	nim
gcc -m64 -march=corei7 -O -fomit-frame-pointer	nim
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	nim
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	nim
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	nim
gcc -m64 -march=k8 -O -fomit-frame-pointer	nim
gcc -m64 -march=k8 -Os -fomit-frame-pointer	nim
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	nim
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	nim
gcc -m64 -march=nocona -O -fomit-frame-pointer	nim
gcc -m64 -march=nocona -Os -fomit-frame-pointer	nim
gcc -march=barcelona -O2 -fomit-frame-pointer	nim
gcc -march=barcelona -O3 -fomit-frame-pointer	nim
gcc -march=barcelona -O -fomit-frame-pointer	nim
gcc -march=barcelona -Os -fomit-frame-pointer	nim
gcc -march=k8 -O2 -fomit-frame-pointer	nim
gcc -march=k8 -O3 -fomit-frame-pointer	nim
gcc -march=k8 -O -fomit-frame-pointer	nim
gcc -march=k8 -Os -fomit-frame-pointer	nim
gcc -march=nocona -O2 -fomit-frame-pointer	nim
gcc -march=nocona -O3 -fomit-frame-pointer	nim
gcc -march=nocona -O -fomit-frame-pointer	nim
gcc -march=nocona -Os -fomit-frame-pointer	nim

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

tiaoxin-optimized.c: tiaoxin-optimized.c:126:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'ssse3'
tiaoxin-optimized.c: W0 = _mm_shuffle_epi8( W0 , perm );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:127:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'ssse3'
tiaoxin-optimized.c: W1 = _mm_shuffle_epi8( W1 , perm );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:137:2: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'aes'
tiaoxin-optimized.c: UPDATE( T3 , T4 , T6, Z0 , Z1 , Z0 );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:47:46: note: expanded from macro 'UPDATE'
tiaoxin-optimized.c: #define UPDATE( T3 , T4 , T6 , M0 , M1 , M2 )\
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:40:41: note: expanded from macro '\
tiaoxin-optimized.c: RT3'
tiaoxin-optimized.c: #define RT3( T , M ) tmp = T[0];T[0] = enc(T[2],M);T[2] = T[1];T[1] = enc(tmp,Z0);T[0] = xor(T[0], tmp);
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: note: expanded from macro 'enc'
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:137:2: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'aes'
tiaoxin-optimized.c: tiaoxin-optimized.c:47:46: note: expanded from macro 'UPDATE'
tiaoxin-optimized.c: #define UPDATE( T3 , T4 , T6 , M0 , M1 , M2 )\
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:40:72: note: expanded from macro '\
tiaoxin-optimized.c: RT3'
tiaoxin-optimized.c: ...

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

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	nim
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	nim
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	nim
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	nim

Compiler output

Implementation: crypto_aead/tiaoxinv2/ref
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

tiaoxin-tablebased.c: tiaoxin-tablebased.c:257:12: warning: comparison of unsigned expression tiaoxin-tablebased.c: if( clen tiaoxin-tablebased.c: ~~~~ ^ ~
tiaoxin-tablebased.c: 1 warning generated.

Number of similar (compiler,implementation) pairs: 10, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	ref
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	ref
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	ref
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	ref
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	ref
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	ref
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments

tiaoxin-optimized.c: tiaoxin-optimized.c:375:11: warning: comparison of unsigned expression tiaoxin-optimized.c: if( clen tiaoxin-optimized.c: ~~~~ ^ ~
tiaoxin-optimized.c: 1 warning generated.

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

Compiler	Implementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	nim
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	nim
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	nim
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	nim

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments

tiaoxin-optimized.c: tiaoxin-optimized.c:137:2: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'aes'
tiaoxin-optimized.c: UPDATE( T3 , T4 , T6, Z0 , Z1 , Z0 );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:47:46: note: expanded from macro 'UPDATE'
tiaoxin-optimized.c: #define UPDATE( T3 , T4 , T6 , M0 , M1 , M2 )\
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:40:41: note: expanded from macro '\
tiaoxin-optimized.c: RT3'
tiaoxin-optimized.c: #define RT3( T , M ) tmp = T[0];T[0] = enc(T[2],M);T[2] = T[1];T[1] = enc(tmp,Z0);T[0] = xor(T[0], tmp);
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: note: expanded from macro 'enc'
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:137:2: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'aes'
tiaoxin-optimized.c: tiaoxin-optimized.c:47:46: note: expanded from macro 'UPDATE'
tiaoxin-optimized.c: #define UPDATE( T3 , T4 , T6 , M0 , M1 , M2 )\
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:40:72: note: expanded from macro '\
tiaoxin-optimized.c: RT3'
tiaoxin-optimized.c: #define RT3( T , M ) tmp = T[0];T[0] = enc(T[2],M);T[2] = T[1];T[1] = enc(tmp,Z0);T[0] = xor(T[0], tmp);
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: note: expanded from macro 'enc'
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:137:2: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'tiaoxin_optimized_encrypt' that is compiled without support for 'aes'
tiaoxin-optimized.c: ...

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	nim
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	nim

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

tiaoxin-optimized.c: In file included from tiaoxin-optimized.c:22:0:
tiaoxin-optimized.c: tiaoxin-optimized.c: In function 'tiaoxin_optimized_encrypt':
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '_mm_aesenc_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: note: called from here
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~~~~~~
tiaoxin-optimized.c: tiaoxin-optimized.c:42:108: note: in expansion of macro 'enc'
tiaoxin-optimized.c: #define RT6( T , M ) tmp = T[0];T[0] = enc(T[5],M);T[5] = T[4];T[4] = T[3];T[3] = T[2];T[2] = T[1];T[1] = enc(tmp,Z0);T[0] = xor(T[0], tmp);
tiaoxin-optimized.c: ^~~
tiaoxin-optimized.c: tiaoxin-optimized.c:50:1: note: in expansion of macro 'RT6'
tiaoxin-optimized.c: RT6( T6, M2 );
tiaoxin-optimized.c: ^~~
tiaoxin-optimized.c: tiaoxin-optimized.c:151:2: note: in expansion of macro 'UPDATE'
tiaoxin-optimized.c: UPDATE( T3 , T4 , T6, Z0 , Z1 , Z0 );
tiaoxin-optimized.c: ^~~~~~
tiaoxin-optimized.c: In file included from tiaoxin-optimized.c:22:0:
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '_mm_aesenc_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: note: called from here
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~~~~~~
tiaoxin-optimized.c: tiaoxin-optimized.c:42:41: note: in expansion of macro 'enc'
tiaoxin-optimized.c: ...
tiaoxin-optimized.c: In file included from tiaoxin-optimized.c:22:0:
tiaoxin-optimized.c: tiaoxin-optimized.c: In function 'tiaoxin_optimized_encrypt':
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '_mm_aesenc_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: note: called from here
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~~~~~~
tiaoxin-optimized.c: tiaoxin-optimized.c:42:108: note: in expansion of macro 'enc'
tiaoxin-optimized.c: #define RT6( T , M ) tmp = T[0];T[0] = enc(T[5],M);T[5] = T[4];T[4] = T[3];T[3] = T[2];T[2] = T[1];T[1] = enc(tmp,Z0);T[0] = xor(T[0], tmp);
tiaoxin-optimized.c: ^~~
tiaoxin-optimized.c: tiaoxin-optimized.c:50:1: note: in expansion of macro 'RT6'
tiaoxin-optimized.c: RT6( T6, M2 );
tiaoxin-optimized.c: ^~~
tiaoxin-optimized.c: tiaoxin-optimized.c:151:2: note: in expansion of macro 'UPDATE'
tiaoxin-optimized.c: UPDATE( T3 , T4 , T6, Z0 , Z1 , Z0 );
tiaoxin-optimized.c: ^~~~~~
tiaoxin-optimized.c: In file included from tiaoxin-optimized.c:22:0:
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:61:1: error: inlining failed in call to always_inline '_mm_aesenc_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_aesenc_si128 (__m128i __X, __m128i __Y)
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~
tiaoxin-optimized.c: tiaoxin-optimized.c:30:19: note: called from here
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^~~~~~~~~~~~~~~~~~~~~
tiaoxin-optimized.c: tiaoxin-optimized.c:42:41: note: in expansion of macro 'enc'
tiaoxin-optimized.c: ...

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

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