Implementation notes: x86, rumba7, crypto_aead/tiaoxinv2

Computer: rumba7
Architecture: x86
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: tiaoxinv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
2400	`nim`	`gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer`	20180529	20171218
2400	`nim`	`gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer`	20180529	20171218
2430	`nim`	`gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer`	20180529	20171218
2430	`nim`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20180529	20171218
2430	`nim`	`gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer`	20180529	20171218
2490	`nim`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20180529	20171218
2520	`nim`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20180529	20171218
2640	`nim`	`gcc -m32 -march=core-avx-i -O -fomit-frame-pointer`	20180529	20171218
2640	`nim`	`gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer`	20180529	20171218
2640	`nim`	`gcc -m32 -march=corei7-avx -O -fomit-frame-pointer`	20180529	20171218
2640	`nim`	`gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer`	20180529	20171218
2670	`nim`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20180529	20171218
2670	`nim`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20180529	20171218
2700	`nim`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20180529	20171218
2700	`nim`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20180529	20171218
2700	`nim`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20180529	20171218
36930	`ref`	`gcc -m32 -march=corei7-avx -O -fomit-frame-pointer`	20180529	20171218
37200	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20180529	20171218
37230	`ref`	`gcc -m32 -march=core-avx-i -O -fomit-frame-pointer`	20180529	20171218
37350	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20180529	20171218
37770	`ref`	`gcc -m32 -march=core-avx2 -O -fomit-frame-pointer`	20180529	20171218
37800	`ref`	`gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer`	20180529	20171218
37800	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20180529	20171218
37830	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20180529	20171218
37950	`ref`	`gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer`	20180529	20171218
37980	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20180529	20171218
37980	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20180529	20171218
38010	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20180529	20171218
38010	`ref`	`gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer`	20180529	20171218
38070	`ref`	`gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer`	20180529	20171218
38100	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20180529	20171218
38130	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20180529	20171218
38160	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20180529	20171218
38160	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20180529	20171218
38190	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20180529	20171218
38220	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20180529	20171218
38220	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20180529	20171218
38250	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20180529	20171218
38250	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20180529	20171218
38250	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20180529	20171218
38280	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20180529	20171218
38310	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20180529	20171218
38340	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20180529	20171218
38370	`ref`	`gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer`	20180529	20171218
38400	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20180529	20171218
38400	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20180529	20171218
38460	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20180529	20171218
38490	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20180529	20171218
38520	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20180529	20171218
38520	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20180529	20171218
38580	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20180529	20171218
38580	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20180529	20171218
38580	`ref`	`gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer`	20180529	20171218
38580	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20180529	20171218
38640	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20180529	20171218
38700	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20180529	20171218
38730	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20180529	20171218
38790	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20180529	20171218
38820	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20180529	20171218
38850	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20180529	20171218
38940	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20180529	20171218
38970	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20180529	20171218
38970	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20180529	20171218
39090	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20180529	20171218
39120	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20180529	20171218
39150	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20180529	20171218
39150	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20180529	20171218
39180	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20180529	20171218
39210	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20180529	20171218
39240	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20180529	20171218
39360	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20180529	20171218
39450	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20180529	20171218
39450	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20180529	20171218
39480	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20180529	20171218
39570	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20180529	20171218
39780	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20180529	20171218
39870	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20180529	20171218
39870	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20180529	20171218
39930	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20180529	20171218
39930	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20180529	20171218
39960	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20180529	20171218
39990	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20180529	20171218
40110	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20180529	20171218
40230	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20180529	20171218
40620	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20180529	20171218
40980	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20180529	20171218
41250	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20180529	20171218
42060	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20180529	20171218
42780	`ref`	`gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer`	20180529	20171218
42930	`ref`	`gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer`	20180529	20171218
43080	`ref`	`gcc -m32 -march=corei7 -O3 -fomit-frame-pointer`	20180529	20171218
43110	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20180529	20171218
43140	`ref`	`gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer`	20180529	20171218
43260	`ref`	`gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20180529	20171218
43290	`ref`	`gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20180529	20171218
43710	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20180529	20171218
43740	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20180529	20171218
43950	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20180529	20171218
43950	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20180529	20171218
44130	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20180529	20171218
44340	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20180529	20171218
44460	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20180529	20171218
44490	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20180529	20171218
44520	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20180529	20171218
44760	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20180529	20171218
44910	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20180529	20171218
44940	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20180529	20171218
45150	`ref`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20180529	20171218
45420	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20180529	20171218
45480	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20180529	20171218
45480	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20180529	20171218
45690	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20180529	20171218
45690	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20180529	20171218
45960	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20180529	20171218
45960	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20180529	20171218
45960	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20180529	20171218
45990	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20180529	20171218
46050	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20180529	20171218
46260	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20180529	20171218
46560	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20180529	20171218
46560	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20180529	20171218
46620	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20180529	20171218
46680	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20180529	20171218
46710	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20180529	20171218
46710	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20180529	20171218
46710	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20180529	20171218
46770	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20180529	20171218
46770	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20180529	20171218
46860	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20180529	20171218
46980	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20180529	20171218
47010	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20180529	20171218
47040	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20180529	20171218
47040	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20180529	20171218
47070	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20180529	20171218
47100	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20180529	20171218
47130	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20180529	20171218
47160	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20180529	20171218
47190	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20180529	20171218
47220	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20180529	20171218
47250	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20180529	20171218
47250	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20180529	20171218
47250	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20180529	20171218
47370	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20180529	20171218
47400	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20180529	20171218
47400	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20180529	20171218
47430	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20180529	20171218
47460	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20180529	20171218
47550	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20180529	20171218
47580	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20180529	20171218
47610	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20180529	20171218
47640	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20180529	20171218
47640	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20180529	20171218
47640	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20180529	20171218
47850	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20180529	20171218
47910	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20180529	20171218
48000	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20180529	20171218
48060	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20180529	20171218
48120	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20180529	20171218
48180	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20180529	20171218
48210	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20180529	20171218
48480	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20180529	20171218
48600	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20180529	20171218
48660	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20180529	20171218
48750	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20180529	20171218
49050	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20180529	20171218
49050	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20180529	20171218
49350	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20180529	20171218
49410	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20180529	20171218
49530	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20180529	20171218
49680	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20180529	20171218
49710	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20180529	20171218
49770	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20180529	20171218
49800	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20180529	20171218
50040	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20180529	20171218
50190	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20180529	20171218
50310	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20180529	20171218
50850	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20180529	20171218
51300	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20180529	20171218
51510	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20180529	20171218
51660	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20180529	20171218
55470	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20180529	20171218
55530	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20180529	20171218
56070	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20180529	20171218
56430	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20180529	20171218
57300	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20180529	20171218
57780	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20180529	20171218
57960	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20180529	20171218
58140	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20180529	20171218
58350	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20180529	20171218
58560	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20180529	20171218
59370	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20180529	20171218
59520	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20180529	20171218

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

tiaoxin-optimized.c: tiaoxin-optimized.c: In function 'tiaoxin_optimized_encrypt':
tiaoxin-optimized.c: tiaoxin-optimized.c:108:10: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
tiaoxin-optimized.c: __m128i Z0 = constant8( 0x42,0x8a,0x2f,0x98,0xd7,0x28,0xae,0x22,0x71,0x37,0x44,0x91,0x23,0xef,0x65,0xcd );
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
tiaoxin-optimized.c: from tiaoxin-optimized.c:20:
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_xor_si128 (__m128i __A, __m128i __B)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:28:19: error: called from here
tiaoxin-optimized.c: #define xor(a,b) _mm_xor_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:42:127: note: in expansion of macro 'xor'
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-linux-gnu/5/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: ...

Number of similar (compiler,implementation) pairs: 88, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer	nim
gcc -m32 -O2 -fomit-frame-pointer	nim
gcc -m32 -O3 -fomit-frame-pointer	nim
gcc -m32 -O -fomit-frame-pointer	nim
gcc -m32 -Os -fomit-frame-pointer	nim
gcc -m32 -march=athlon -O2 -fomit-frame-pointer	nim
gcc -m32 -march=athlon -O3 -fomit-frame-pointer	nim
gcc -m32 -march=athlon -O -fomit-frame-pointer	nim
gcc -m32 -march=athlon -Os -fomit-frame-pointer	nim
gcc -m32 -march=i386 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=i386 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=i386 -O -fomit-frame-pointer	nim
gcc -m32 -march=i386 -Os -fomit-frame-pointer	nim
gcc -m32 -march=i486 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=i486 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=i486 -O -fomit-frame-pointer	nim
gcc -m32 -march=i486 -Os -fomit-frame-pointer	nim
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=k6-2 -O -fomit-frame-pointer	nim
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer	nim
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=k6-3 -O -fomit-frame-pointer	nim
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer	nim
gcc -m32 -march=k6 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=k6 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=k6 -O -fomit-frame-pointer	nim
gcc -m32 -march=k6 -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer	nim
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentium2 -O -fomit-frame-pointer	nim
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentium -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentium -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentium -O -fomit-frame-pointer	nim
gcc -m32 -march=pentium -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer	nim
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer	nim

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 60, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	nim
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=core2 -O -fomit-frame-pointer	nim
gcc -m32 -march=core2 -Os -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	nim
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	nim
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=corei7 -O -fomit-frame-pointer	nim
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	nim
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=k8 -O -fomit-frame-pointer	nim
gcc -m32 -march=k8 -Os -fomit-frame-pointer	nim
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	nim
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	nim
gcc -m32 -march=nocona -O -fomit-frame-pointer	nim
gcc -m32 -march=nocona -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	nim
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	nim
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	nim
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	nim
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	nim
gcc -m32 -march=prescott -O -fomit-frame-pointer	nim
gcc -m32 -march=prescott -Os -fomit-frame-pointer	nim

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer

tiaoxin-optimized.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
tiaoxin-optimized.c: from tiaoxin-optimized.c:20:
tiaoxin-optimized.c: tiaoxin-optimized.c: In function 'tiaoxin_optimized_encrypt':
tiaoxin-optimized.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
tiaoxin-optimized.c: _mm_xor_si128 (__m128i __A, __m128i __B)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:28:19: error: called from here
tiaoxin-optimized.c: #define xor(a,b) _mm_xor_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: tiaoxin-optimized.c:42:127: note: in expansion of macro 'xor'
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-linux-gnu/5/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: error: called from here
tiaoxin-optimized.c: #define enc(a,b) _mm_aesenc_si128(a,b)
tiaoxin-optimized.c: ^
tiaoxin-optimized.c: ...

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer	nim
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer	nim
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer	nim
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer	nim
gcc -m32 -march=pentium3 -O -fomit-frame-pointer	nim
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer	nim

Compiler output

Implementation: crypto_aead/tiaoxinv2/nim
Compiler: gcc -m32 -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-linux-gnu/5/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: error: 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-linux-gnu/5/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: error: 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-linux-gnu/5/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: error: 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-linux-gnu/5/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: error: 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 -m32 -march=barcelona -O2 -fomit-frame-pointer	nim
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer	nim
gcc -m32 -march=barcelona -O -fomit-frame-pointer	nim
gcc -m32 -march=barcelona -Os -fomit-frame-pointer	nim