Implementation notes: x86, hydra1, crypto_hash/fugue512

Computer: hydra1
Architecture: x86
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20161220
Operation: crypto_hash
Primitive: fugue512

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
110125	`sphlib`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20161011	20161009
110181	`sphlib`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161011	20161009
110450	`sphlib`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161011	20161009
110454	`sphlib`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20161011	20161009
110483	`sphlib`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161011	20161009
110653	`sphlib`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161011	20161009
110659	`sphlib`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20161011	20161009
111139	`sphlib`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20161011	20161009
111176	`sphlib`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20161011	20161009
111206	`sphlib`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161011	20161009
111230	`sphlib`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20161011	20161009
111237	`sphlib`	`gcc -m32 -Os -fomit-frame-pointer`	20161011	20161009
111256	`sphlib`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20161011	20161009
111259	`sphlib`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20161011	20161009
111278	`sphlib`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161011	20161009
111597	`sphlib`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20161011	20161009
111674	`sphlib`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161011	20161009
111674	`sphlib`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20161011	20161009
111706	`sphlib`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161011	20161009
111925	`sphlib`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20161011	20161009
111965	`sphlib`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20161011	20161009
112040	`sphlib`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161011	20161009
112050	`sphlib`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20161011	20161009
112076	`sphlib`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20161011	20161009
112194	`sphlib`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20161011	20161009
112221	`sphlib`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20161011	20161009
112280	`sphlib`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161011	20161009
112448	`sphlib`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20161011	20161009
112517	`sphlib`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20161011	20161009
113736	`sphlib`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161011	20161009
113741	`sphlib`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161011	20161009
113976	`sphlib`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20161011	20161009
114149	`sphlib`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20161011	20161009
114165	`sphlib`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20161011	20161009
114211	`sphlib`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161011	20161009
114259	`sphlib`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161011	20161009
114274	`sphlib`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20161011	20161009
118287	`sphlib`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20161011	20161009
118542	`sphlib`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20161011	20161009
118608	`sphlib`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20161011	20161009
118813	`sphlib`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161011	20161009
118832	`sphlib`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161011	20161009
119085	`sphlib`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20161011	20161009
119403	`sphlib`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20161011	20161009
119424	`sphlib`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20161011	20161009
119517	`sphlib`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161011	20161009
119574	`sphlib`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20161011	20161009
119640	`sphlib`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161011	20161009
119723	`sphlib`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20161011	20161009
119781	`sphlib`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20161011	20161009
119848	`sphlib`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161011	20161009
119946	`sphlib`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161011	20161009
120152	`sphlib`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161011	20161009
120261	`sphlib`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161011	20161009
120277	`sphlib`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161011	20161009
120285	`sphlib`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20161011	20161009
120335	`sphlib`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161011	20161009
120363	`sphlib`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161011	20161009
120364	`sphlib`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20161011	20161009
120392	`sphlib`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161011	20161009
120419	`sphlib`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20161011	20161009
120822	`sphlib`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20161011	20161009
120920	`sphlib`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161011	20161009
120923	`sphlib`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20161011	20161009
121032	`sphlib`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161011	20161009
121050	`sphlib`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20161011	20161009
121074	`sphlib`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20161011	20161009
121131	`sphlib`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20161011	20161009
121152	`sphlib`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20161011	20161009
121181	`sphlib`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161011	20161009
121193	`sphlib`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20161011	20161009
121202	`sphlib`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161011	20161009
121533	`sphlib`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161011	20161009
121661	`sphlib`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20161011	20161009
121686	`sphlib`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20161011	20161009
121738	`sphlib`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20161011	20161009
121760	`sphlib`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20161011	20161009
121776	`sphlib`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161011	20161009
121779	`sphlib`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20161011	20161009
121830	`sphlib`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161011	20161009
121888	`sphlib`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20161011	20161009
121957	`sphlib`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20161011	20161009
121977	`sphlib`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20161011	20161009
122019	`sphlib`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20161011	20161009
122026	`sphlib`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161011	20161009
122048	`sphlib`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20161011	20161009
122166	`sphlib`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20161011	20161009
122170	`sphlib`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20161011	20161009
122178	`sphlib`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20161011	20161009
122333	`sphlib`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20161011	20161009
122538	`sphlib`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161011	20161009
122608	`sphlib`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161011	20161009
122731	`sphlib`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161011	20161009
122779	`sphlib`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20161011	20161009
122795	`sphlib`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20161011	20161009
122799	`sphlib`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161011	20161009
122833	`sphlib`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161011	20161009
122835	`sphlib`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161011	20161009
122839	`sphlib`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20161011	20161009
122840	`sphlib`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161011	20161009
122843	`sphlib`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161011	20161009
122854	`sphlib`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20161011	20161009
122863	`sphlib`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161011	20161009
122885	`sphlib`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161011	20161009
122929	`sphlib`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20161011	20161009
123290	`sphlib`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161011	20161009
123390	`sphlib`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161011	20161009
124219	`sphlib`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20161011	20161009
124226	`sphlib`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20161011	20161009
124308	`sphlib`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20161011	20161009
124701	`sphlib`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20161011	20161009
124800	`sphlib`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161011	20161009
124851	`sphlib`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20161011	20161009
125073	`sphlib`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20161011	20161009
125090	`sphlib`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20161011	20161009
125421	`sphlib`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20161011	20161009
125527	`sphlib`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20161011	20161009
125589	`sphlib`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161011	20161009
125603	`sphlib`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20161011	20161009
125804	`sphlib`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161011	20161009
125886	`sphlib`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20161011	20161009
126040	`sphlib`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161011	20161009
126061	`sphlib`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20161011	20161009
126472	`sphlib`	`gcc -m32 -O2 -fomit-frame-pointer`	20161011	20161009
126648	`sphlib`	`gcc -m32 -O3 -fomit-frame-pointer`	20161011	20161009
128451	`sphlib`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20161011	20161009
128469	`sphlib`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20161011	20161009
128739	`sphlib`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20161011	20161009
129022	`sphlib`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20161011	20161009
130401	`sphlib`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20161011	20161009
130405	`sphlib`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20161011	20161009
130947	`sphlib`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20161011	20161009
130978	`sphlib`	`gcc -m32 -O -fomit-frame-pointer`	20161011	20161009
130978	`sphlib`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20161011	20161009
131049	`sphlib`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161011	20161009
131154	`sphlib`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20161011	20161009
131349	`sphlib`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20161011	20161009
131570	`sphlib`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20161011	20161009
131725	`sphlib`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20161011	20161009
134798	`sphlib`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161011	20161009
134898	`sphlib`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161011	20161009
134960	`sphlib`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161011	20161009
134976	`sphlib`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161011	20161009
135048	`sphlib`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20161011	20161009
135246	`sphlib`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20161011	20161009
135594	`sphlib`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161011	20161009
135645	`sphlib`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20161011	20161009
136014	`sphlib`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20161011	20161009
136189	`sphlib`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161011	20161009
136368	`sphlib`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20161011	20161009
136368	`sphlib`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161011	20161009
136515	`sphlib`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161011	20161009
136747	`sphlib`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20161011	20161009
136749	`sphlib`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161011	20161009
136877	`sphlib`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161011	20161009
138160	`sphlib`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20161011	20161009
139125	`sphlib`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161011	20161009
139134	`sphlib`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20161011	20161009
139136	`sphlib`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161011	20161009
139181	`sphlib`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20161011	20161009

Test failure

Implementation: crypto_hash/fugue512/ccalik/aesni
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 41, namely:

Compiler	Implementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	ccalik/aesni ccalik/vperm sphlib
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	ccalik/aesni ccalik/vperm sphlib
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	ccalik/aesni ccalik/vperm sphlib
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	ccalik/aesni ccalik/vperm sphlib
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	ccalik/aesni ccalik/vperm sphlib
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	ccalik/aesni ccalik/vperm sphlib
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	ccalik/vperm sphlib
gcc -m32 -march=core2 -O -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=core2 -Os -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	ccalik/aesni ccalik/vperm sphlib
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	ccalik/aesni ccalik/vperm sphlib
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	ccalik/aesni ccalik/vperm sphlib
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=corei7 -O -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	ccalik/vperm

Compiler output

Implementation: crypto_hash/fugue512/ccalik/aesni
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

hash.c: hash.c: In function 'Compress256':
hash.c: hash.c:156:5: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
hash.c: t1 = _mm_shuffle_epi32(s0, _MM_SHUFFLE(3, 3, 0, 3));\
hash.c: ^
hash.c: hash.c:448:4: note: in expansion of macro 'TIX256'
hash.c: TIX256(pmsg, ctx->gt;state[1], ctx->gt;state[0], ctx->gt;state[6], ctx->gt;state[8], _t0, _t1, _t2);
hash.c: ^
hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:31,
hash.c: from hash_api.h:29,
hash.c: from hash.c:20:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1268:1: error: inlining failed in call to always_inline '_mm_and_si128': target specific option mismatch
hash.c: _mm_and_si128 (__m128i __A, __m128i __B)
hash.c: ^
hash.c: hash.c:139:7: error: called from here
hash.c: s0 = _mm_and_si128(s0, M128(_maskd3n))
hash.c: ^
hash.c: hash.c:349:2: note: in expansion of macro 'UNPACK_S0'
hash.c: UNPACK_S0(s0, s1, _t3)
hash.c: ^
hash.c: hash.c:449:4: note: in expansion of macro 'SUBROUND256_2'
hash.c: SUBROUND256_2(ctx->gt;state[8], ctx->gt;state[9], ctx->gt;state[7], ctx->gt;state[2], ctx->gt;state[7], ctx->gt;state[8], ctx->gt;state[6], ctx->gt;state[1]);
hash.c: ^
hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:31,
hash.c: ...

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

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

Compiler output

Implementation: crypto_hash/fugue512/ccalik/vperm
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

hash.c: hash.c: In function 'Compress256':
hash.c: hash.c:165:5: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
hash.c: t1 = _mm_shuffle_epi32(s0, _MM_SHUFFLE(3, 3, 0, 3));\
hash.c: ^
hash.c: hash.c:447:4: note: in expansion of macro 'TIX256'
hash.c: TIX256(pmsg, ctx->gt;state[1], ctx->gt;state[0], ctx->gt;state[6], ctx->gt;state[8], _t0, _t1, _t2);
hash.c: ^
hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:31,
hash.c: from hash_api.h:29,
hash.c: from hash.c:20:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1268:1: error: inlining failed in call to always_inline '_mm_and_si128': target specific option mismatch
hash.c: _mm_and_si128 (__m128i __A, __m128i __B)
hash.c: ^
hash.c: hash.c:138:7: error: called from here
hash.c: s0 = _mm_and_si128(s0, M128(_maskd3n))
hash.c: ^
hash.c: hash.c:348:2: note: in expansion of macro 'UNPACK_S0'
hash.c: UNPACK_S0(s0, s1, _t3)
hash.c: ^
hash.c: hash.c:448:4: note: in expansion of macro 'SUBROUND256_2'
hash.c: SUBROUND256_2(ctx->gt;state[8], ctx->gt;state[9], ctx->gt;state[7], ctx->gt;state[2], ctx->gt;state[7], ctx->gt;state[8], ctx->gt;state[6], ctx->gt;state[1]);
hash.c: ^
hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:31,
hash.c: ...

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

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

Compiler output

Implementation: crypto_hash/fugue512/ccalik/vperm
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 48, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	ccalik/vperm
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=k8 -O -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=k8 -Os -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=nocona -O -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=nocona -Os -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=prescott -O -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=prescott -Os -fomit-frame-pointer	ccalik/vperm

Compiler output

Implementation: crypto_hash/fugue512/ccalik/aesni
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 48, namely:

Compiler	Implementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer	ccalik/aesni
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=k8 -O2 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=k8 -O3 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=k8 -O -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=k8 -Os -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=nocona -O2 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=nocona -O3 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=nocona -O -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=nocona -Os -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=pentium-m -O -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=pentium4 -O -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=prescott -O2 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=prescott -O3 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=prescott -O -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=prescott -Os -fomit-frame-pointer	ccalik/aesni

Compiler output

Implementation: crypto_hash/fugue512/ccalik/vperm
Compiler: gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer

hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:31,
hash.c: from hash_api.h:29,
hash.c: from hash.c:20:
hash.c: hash.c: In function 'Compress256':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1268:1: error: inlining failed in call to always_inline '_mm_and_si128': target specific option mismatch
hash.c: _mm_and_si128 (__m128i __A, __m128i __B)
hash.c: ^
hash.c: hash.c:138:7: error: called from here
hash.c: s0 = _mm_and_si128(s0, M128(_maskd3n))
hash.c: ^
hash.c: hash.c:348:2: note: in expansion of macro 'UNPACK_S0'
hash.c: UNPACK_S0(s0, s1, _t3)
hash.c: ^
hash.c: hash.c:448:4: note: in expansion of macro 'SUBROUND256_2'
hash.c: SUBROUND256_2(ctx->gt;state[8], ctx->gt;state[9], ctx->gt;state[7], ctx->gt;state[2], ctx->gt;state[7], ctx->gt;state[8], ctx->gt;state[6], ctx->gt;state[1]);
hash.c: ^
hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:31,
hash.c: from hash_api.h:29,
hash.c: from hash.c:20:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1539:1: error: inlining failed in call to always_inline '_mm_castps_si128': target specific option mismatch
hash.c: _mm_castps_si128(__m128 __A)
hash.c: ^
hash.c: hash.c:137:7: error: called from here
hash.c: ...

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

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

Compiler output

Implementation: crypto_hash/fugue512/ccalik/aesni
Compiler: gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer

hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:31,
hash.c: from hash_api.h:29,
hash.c: from hash.c:20:
hash.c: hash.c: In function 'Compress256':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1268:1: error: inlining failed in call to always_inline '_mm_and_si128': target specific option mismatch
hash.c: _mm_and_si128 (__m128i __A, __m128i __B)
hash.c: ^
hash.c: hash.c:139:7: error: called from here
hash.c: s0 = _mm_and_si128(s0, M128(_maskd3n))
hash.c: ^
hash.c: hash.c:349:2: note: in expansion of macro 'UNPACK_S0'
hash.c: UNPACK_S0(s0, s1, _t3)
hash.c: ^
hash.c: hash.c:449:4: note: in expansion of macro 'SUBROUND256_2'
hash.c: SUBROUND256_2(ctx->gt;state[8], ctx->gt;state[9], ctx->gt;state[7], ctx->gt;state[2], ctx->gt;state[7], ctx->gt;state[8], ctx->gt;state[6], ctx->gt;state[1]);
hash.c: ^
hash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:31,
hash.c: from hash_api.h:29,
hash.c: from hash.c:20:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/emmintrin.h:1539:1: error: inlining failed in call to always_inline '_mm_castps_si128': target specific option mismatch
hash.c: _mm_castps_si128(__m128 __A)
hash.c: ^
hash.c: hash.c:138:7: error: called from here
hash.c: ...

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

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

Compiler output

Implementation: crypto_hash/fugue512/ccalik/vperm
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

hash.c: In file included from hash_api.h:29:0,
hash.c: from hash.c:20:
hash.c: hash.c: In function 'Compress256':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
hash.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: ^
hash.c: hash.c:300:6: error: called from here
hash.c: t0 = _mm_shuffle_epi8(t0, M128(_supermix4c));\
hash.c: ^
hash.c: hash.c:268:2: note: in expansion of macro 'POSTSUPERMIX'
hash.c: POSTSUPERMIX(t0, t1, t2, t3, t4);\
hash.c: ^
hash.c: hash.c:347:2: note: in expansion of macro 'SUPERMIX'
hash.c: SUPERMIX(_t2, _t3, _t0, _t1, s0);\
hash.c: ^
hash.c: hash.c:448:4: note: in expansion of macro 'SUBROUND256_2'
hash.c: SUBROUND256_2(ctx->gt;state[8], ctx->gt;state[9], ctx->gt;state[7], ctx->gt;state[2], ctx->gt;state[7], ctx->gt;state[8], ctx->gt;state[6], ctx->gt;state[1]);
hash.c: ^
hash.c: In file included from hash_api.h:29:0,
hash.c: from hash.c:20:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
hash.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: ^
hash.c: hash.c:297:6: error: called from here
hash.c: t0 = _mm_shuffle_epi8(t0, M128(_supermix4b));\
hash.c: ...
hash.c: In file included from hash_api.h:29:0,
hash.c: from hash.c:20:
hash.c: hash.c: In function 'Compress256':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
hash.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: ^
hash.c: hash.c:300:6: error: called from here
hash.c: t0 = _mm_shuffle_epi8(t0, M128(_supermix4c));\
hash.c: ^
hash.c: hash.c:268:2: note: in expansion of macro 'POSTSUPERMIX'
hash.c: POSTSUPERMIX(t0, t1, t2, t3, t4);\
hash.c: ^
hash.c: hash.c:347:2: note: in expansion of macro 'SUPERMIX'
hash.c: SUPERMIX(_t2, _t3, _t0, _t1, s0);\
hash.c: ^
hash.c: hash.c:448:4: note: in expansion of macro 'SUBROUND256_2'
hash.c: SUBROUND256_2(ctx->gt;state[8], ctx->gt;state[9], ctx->gt;state[7], ctx->gt;state[2], ctx->gt;state[7], ctx->gt;state[8], ctx->gt;state[6], ctx->gt;state[1]);
hash.c: ^
hash.c: In file included from hash_api.h:29:0,
hash.c: from hash.c:20:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
hash.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: ^
hash.c: hash.c:297:6: error: called from here
hash.c: t0 = _mm_shuffle_epi8(t0, M128(_supermix4b));\
hash.c: ...

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

Compiler	Implementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=barcelona -O -fomit-frame-pointer	ccalik/vperm
gcc -m32 -march=barcelona -Os -fomit-frame-pointer	ccalik/vperm

Compiler output

Implementation: crypto_hash/fugue512/ccalik/aesni
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

hash.c: In file included from hash_api.h:29:0,
hash.c: from hash.c:20:
hash.c: hash.c: In function 'Compress256':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
hash.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: ^
hash.c: hash.c:301:6: error: called from here
hash.c: t0 = _mm_shuffle_epi8(t0, M128(_supermix4c));\
hash.c: ^
hash.c: hash.c:254:2: note: in expansion of macro 'POSTSUPERMIX'
hash.c: POSTSUPERMIX(t0, t1, t2, t3, t4)
hash.c: ^
hash.c: hash.c:348:2: note: in expansion of macro 'SUPERMIX'
hash.c: SUPERMIX(_t2, _t3, _t0, _t1, s0);\
hash.c: ^
hash.c: hash.c:449:4: note: in expansion of macro 'SUBROUND256_2'
hash.c: SUBROUND256_2(ctx->gt;state[8], ctx->gt;state[9], ctx->gt;state[7], ctx->gt;state[2], ctx->gt;state[7], ctx->gt;state[8], ctx->gt;state[6], ctx->gt;state[1]);
hash.c: ^
hash.c: In file included from hash_api.h:29:0,
hash.c: from hash.c:20:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
hash.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: ^
hash.c: hash.c:298:6: error: called from here
hash.c: t0 = _mm_shuffle_epi8(t0, M128(_supermix4b));\
hash.c: ...
hash.c: In file included from hash_api.h:29:0,
hash.c: from hash.c:20:
hash.c: hash.c: In function 'Compress256':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
hash.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: ^
hash.c: hash.c:301:6: error: called from here
hash.c: t0 = _mm_shuffle_epi8(t0, M128(_supermix4c));\
hash.c: ^
hash.c: hash.c:254:2: note: in expansion of macro 'POSTSUPERMIX'
hash.c: POSTSUPERMIX(t0, t1, t2, t3, t4)
hash.c: ^
hash.c: hash.c:348:2: note: in expansion of macro 'SUPERMIX'
hash.c: SUPERMIX(_t2, _t3, _t0, _t1, s0);\
hash.c: ^
hash.c: hash.c:449:4: note: in expansion of macro 'SUBROUND256_2'
hash.c: SUBROUND256_2(ctx->gt;state[8], ctx->gt;state[9], ctx->gt;state[7], ctx->gt;state[2], ctx->gt;state[7], ctx->gt;state[8], ctx->gt;state[6], ctx->gt;state[1]);
hash.c: ^
hash.c: In file included from hash_api.h:29:0,
hash.c: from hash.c:20:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
hash.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
hash.c: ^
hash.c: hash.c:298:6: error: called from here
hash.c: t0 = _mm_shuffle_epi8(t0, M128(_supermix4b));\
hash.c: ...

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

Compiler	Implementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=barcelona -O -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=barcelona -Os -fomit-frame-pointer	ccalik/aesni

Compiler output

Implementation: crypto_hash/fugue512/ccalik/aesni
Compiler: gcc -m32 -march=core2 -O2 -fomit-frame-pointer

hash.c: In file included from hash.c:26:0:
hash.c: hash.c: In function 'Compress256':
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:69:1: error: inlining failed in call to always_inline '_mm_aesenclast_si128': target specific option mismatch
hash.c: _mm_aesenclast_si128 (__m128i __X, __m128i __Y)
hash.c: ^
hash.c: hash.c:250:8: error: called from here
hash.c: _t2 = _mm_aesenclast_si128(_t2, M128(_zero))
hash.c: ^
hash.c: hash.c:347:2: note: in expansion of macro 'SUBSTITUTE'
hash.c: SUBSTITUTE(s0, _t1, _t2, _t3, _t0);\
hash.c: ^
hash.c: hash.c:449:4: note: in expansion of macro 'SUBROUND256_2'
hash.c: SUBROUND256_2(ctx->gt;state[8], ctx->gt;state[9], ctx->gt;state[7], ctx->gt;state[2], ctx->gt;state[7], ctx->gt;state[8], ctx->gt;state[6], ctx->gt;state[1]);
hash.c: ^
hash.c: In file included from hash.c:26:0:
hash.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/wmmintrin.h:69:1: error: inlining failed in call to always_inline '_mm_aesenclast_si128': target specific option mismatch
hash.c: _mm_aesenclast_si128 (__m128i __X, __m128i __Y)
hash.c: ^
hash.c: hash.c:250:8: error: called from here
hash.c: _t2 = _mm_aesenclast_si128(_t2, M128(_zero))
hash.c: ^
hash.c: hash.c:340:2: note: in expansion of macro 'SUBSTITUTE'
hash.c: SUBSTITUTE(r0, _t1, _t2, _t3, _t0);\
hash.c: ^
hash.c: hash.c:449:4: note: in expansion of macro 'SUBROUND256_2'
hash.c: ...

Number of similar (compiler,implementation) pairs: 13, namely:

Compiler	Implementations
gcc -m32 -march=core2 -O2 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=core2 -O3 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=core2 -O -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=core2 -Os -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=corei7 -O -fomit-frame-pointer	ccalik/aesni
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	ccalik/aesni