Implementation notes: amd64, glyme, crypto_aead/tiaoxinv2

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: tiaoxinv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
3972	`nim`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170205	20170105
3972	`nim`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170205	20170105
3972	`nim`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170205	20170105
3972	`nim`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170205	20170105
4164	`nim`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170205	20170105
4164	`nim`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170205	20170105
4176	`nim`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
4180	`nim`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
4880	`nim`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170205	20170105
4880	`nim`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170205	20170105
53100	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20170205	20170105
53140	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
53144	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
53392	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
54072	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20170205	20170105
55180	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
55180	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
55196	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
55200	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
55224	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
55224	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20170205	20170105
55272	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
55288	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20170205	20170105
55440	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20170205	20170105
55448	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20170205	20170105
55448	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20170205	20170105
55448	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20170205	20170105
55460	`ref`	`gcc -O -fomit-frame-pointer`	20170205	20170105
55460	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20170205	20170105
55484	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20170205	20170105
55488	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20170205	20170105
55532	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20170205	20170105
55540	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20170205	20170105
55544	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20170205	20170105
55544	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
55544	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
55552	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20170205	20170105
55552	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20170205	20170105
55560	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
55564	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20170205	20170105
55588	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20170205	20170105
55592	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
55612	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
55632	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20170205	20170105
55632	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20170205	20170105
55644	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
55656	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
55660	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20170205	20170105
55664	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
55664	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
55668	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20170205	20170105
55684	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20170205	20170105
55684	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20170205	20170105
55700	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20170205	20170105
55700	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
55700	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
55700	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20170205	20170105
55724	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
55788	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20170205	20170105
55940	`ref`	`gcc -Os -fomit-frame-pointer`	20170205	20170105
56160	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20170205	20170105
56244	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
56252	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
56372	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
56372	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
56400	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20170205	20170105
56416	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
56428	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
56444	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20170205	20170105
56448	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20170205	20170105
56448	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20170205	20170105
56452	`ref`	`gcc -O2 -fomit-frame-pointer`	20170205	20170105
56452	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20170205	20170105
56460	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
56504	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
56508	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20170205	20170105
56556	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20170205	20170105
56560	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20170205	20170105
56584	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20170205	20170105
56672	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20170205	20170105
56676	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
56688	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20170205	20170105
56892	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20170205	20170105
56892	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20170205	20170105
56908	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20170205	20170105
56908	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20170205	20170105
56924	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20170205	20170105
56924	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20170205	20170105
57772	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20170205	20170105
58056	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20170205	20170105
58076	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20170205	20170105
58080	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20170205	20170105
58080	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20170205	20170105
58220	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20170205	20170105
58436	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20170205	20170105
58440	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20170205	20170105
58464	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20170205	20170105
58468	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20170205	20170105
58560	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20170205	20170105
58584	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20170205	20170105
59040	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20170205	20170105
59040	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20170205	20170105
59044	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20170205	20170105
59636	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20170205	20170105
59816	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20170205	20170105
60228	`ref`	`gcc -O3 -fomit-frame-pointer`	20170205	20170105
78728	`ref`	`cc`	20170205	20170105
79120	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
79652	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
80192	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20170205	20170105
80456	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
80728	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
81092	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20170205	20170105
82112	`ref`	`gcc`	20170205	20170105
82412	`ref`	`gcc -funroll-loops`	20170205	20170105

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: cc

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: 5, namely:

Compiler	Implementations
cc	nim
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: cc

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: 7, namely:

Compiler	Implementations
cc	ref
clang -O3 -fomit-frame-pointer -Qunused-arguments	ref
clang -O3 -fwrapv -march=native -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: 2, namely:

Compiler	Implementations
clang -O3 -fwrapv -march=native -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: gcc

Number of similar (compiler,implementation) pairs: 86, namely:

Compiler	Implementations
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: 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/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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