Implementation notes: x86, h2atom, crypto_aead/twine80n6t4clocv2

Computer: h2atom
Architecture: x86
CPU ID: GenuineIntel-000106ca-bfe9fbff
SUPERCOP version: 20161009
Operation: crypto_aead
Primitive: twine80n6t4clocv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
553270	`vperm`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161207	20161009
557630	`vperm`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20161207	20161009
560270	`vperm`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161207	20161009
563080	`vperm`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20161207	20161009
584400	`vperm`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20161207	20161009
607570	`vperm`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20161207	20161009
611990	`vperm`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20161207	20161009
618190	`vperm`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20161207	20161009
3966640	`ref`	`gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer`	20161207	20161009
3966660	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161207	20161009
4117560	`ref`	`gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer`	20161207	20161009
4146090	`ref`	`gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer`	20161207	20161009
4146260	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161207	20161009
4146320	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161207	20161009
4184540	`ref`	`gcc -funroll-loops -m32 -O3 -fomit-frame-pointer`	20161207	20161009
4242830	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161207	20161009
4242950	`ref`	`gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer`	20161207	20161009
4260560	`ref`	`gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer`	20161207	20161009
4260760	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161207	20161009
4260760	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161207	20161009
4332480	`ref`	`gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer`	20161207	20161009
4332700	`ref`	`gcc -funroll-loops -m32 -O2 -fomit-frame-pointer`	20161207	20161009
4355080	`ref`	`gcc -m32 -march=athlon -O3 -fomit-frame-pointer`	20161207	20161009
4359900	`ref`	`gcc -m32 -O3 -fomit-frame-pointer`	20161207	20161009
4377170	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161207	20161009
4377860	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161207	20161009
4378120	`ref`	`gcc -m32 -march=k6 -O2 -fomit-frame-pointer`	20161207	20161009
4378130	`ref`	`gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer`	20161207	20161009
4380130	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161207	20161009
4381460	`ref`	`gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer`	20161207	20161009
4381990	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161207	20161009
4396940	`ref`	`gcc -m32 -march=i386 -O3 -fomit-frame-pointer`	20161207	20161009
4420660	`ref`	`gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer`	20161207	20161009
4421200	`ref`	`gcc -m32 -march=k6 -O3 -fomit-frame-pointer`	20161207	20161009
4425170	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161207	20161009
4426770	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161207	20161009
4438640	`ref`	`gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer`	20161207	20161009
4449350	`ref`	`gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer`	20161207	20161009
4453980	`ref`	`gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161207	20161009
4465960	`ref`	`gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer`	20161207	20161009
4467680	`ref`	`gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer`	20161207	20161009
4474220	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161207	20161009
4474250	`ref`	`gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer`	20161207	20161009
4476500	`ref`	`gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer`	20161207	20161009
4477050	`ref`	`gcc -funroll-loops -m32 -Os -fomit-frame-pointer`	20161207	20161009
4478970	`ref`	`gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer`	20161207	20161009
4503600	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161207	20161009
4503700	`ref`	`gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer`	20161207	20161009
4507920	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161207	20161009
4511430	`ref`	`gcc -m32 -march=i386 -O2 -fomit-frame-pointer`	20161207	20161009
4513280	`ref`	`gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer`	20161207	20161009
4558410	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161207	20161009
4563530	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161207	20161009
4565820	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161207	20161009
4565890	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161207	20161009
4567280	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161207	20161009
4602120	`ref`	`gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161207	20161009
4602420	`ref`	`gcc -m32 -march=corei7 -O2 -fomit-frame-pointer`	20161207	20161009
4606270	`ref`	`gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161207	20161009
4627030	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161207	20161009
4627040	`ref`	`gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer`	20161207	20161009
4627490	`ref`	`gcc -m32 -march=core2 -O2 -fomit-frame-pointer`	20161207	20161009
4671260	`ref`	`gcc -m32 -O2 -fomit-frame-pointer`	20161207	20161009
4722930	`ref`	`gcc -m32 -march=k8 -O2 -fomit-frame-pointer`	20161207	20161009
4726130	`ref`	`gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer`	20161207	20161009
4727670	`ref`	`gcc -m32 -march=athlon -O2 -fomit-frame-pointer`	20161207	20161009
4745870	`ref`	`gcc -m32 -march=barcelona -O2 -fomit-frame-pointer`	20161207	20161009
4785110	`ref`	`gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer`	20161207	20161009
4786290	`ref`	`gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer`	20161207	20161009
4791910	`ref`	`gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer`	20161207	20161009
4792130	`ref`	`gcc -m32 -march=pentium -O2 -fomit-frame-pointer`	20161207	20161009
4815370	`ref`	`gcc -m32 -march=prescott -O2 -fomit-frame-pointer`	20161207	20161009
4815880	`ref`	`gcc -m32 -march=nocona -O2 -fomit-frame-pointer`	20161207	20161009
4850740	`ref`	`gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer`	20161207	20161009
4850750	`ref`	`gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer`	20161207	20161009
4851240	`ref`	`gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer`	20161207	20161009
4851240	`ref`	`gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer`	20161207	20161009
4858430	`ref`	`gcc -m32 -march=pentium -O3 -fomit-frame-pointer`	20161207	20161009
4867260	`ref`	`gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer`	20161207	20161009
4924730	`ref`	`gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161207	20161009
4962230	`ref`	`gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer`	20161207	20161009
4962660	`ref`	`gcc -m32 -march=pentium-m -Os -fomit-frame-pointer`	20161207	20161009
4962940	`ref`	`gcc -m32 -march=pentium2 -Os -fomit-frame-pointer`	20161207	20161009
4963940	`ref`	`gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161207	20161009
4964280	`ref`	`gcc -m32 -march=pentium3 -Os -fomit-frame-pointer`	20161207	20161009
5006260	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161207	20161009
5007570	`ref`	`gcc -m32 -march=k6-2 -Os -fomit-frame-pointer`	20161207	20161009
5007690	`ref`	`gcc -m32 -march=k6 -Os -fomit-frame-pointer`	20161207	20161009
5008160	`ref`	`gcc -m32 -march=k6-3 -Os -fomit-frame-pointer`	20161207	20161009
5020040	`ref`	`gcc -m32 -march=corei7 -Os -fomit-frame-pointer`	20161207	20161009
5020230	`ref`	`gcc -m32 -march=core2 -Os -fomit-frame-pointer`	20161207	20161009
5020540	`ref`	`gcc -m32 -march=barcelona -Os -fomit-frame-pointer`	20161207	20161009
5020670	`ref`	`gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161207	20161009
5020740	`ref`	`gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161207	20161009
5021850	`ref`	`gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer`	20161207	20161009
5021950	`ref`	`gcc -m32 -march=athlon -Os -fomit-frame-pointer`	20161207	20161009
5035410	`ref`	`gcc -m32 -Os -fomit-frame-pointer`	20161207	20161009
5037920	`ref`	`gcc -m32 -march=k8 -Os -fomit-frame-pointer`	20161207	20161009
5046210	`ref`	`gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer`	20161207	20161009
5046530	`ref`	`gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer`	20161207	20161009
5124930	`ref`	`gcc -m32 -march=prescott -O3 -fomit-frame-pointer`	20161207	20161009
5125260	`ref`	`gcc -m32 -march=nocona -O3 -fomit-frame-pointer`	20161207	20161009
5168720	`ref`	`gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer`	20161207	20161009
5192730	`ref`	`gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161207	20161009
5200060	`ref`	`gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer`	20161207	20161009
5204830	`ref`	`gcc -m32 -march=i486 -O2 -fomit-frame-pointer`	20161207	20161009
5213390	`ref`	`gcc -m32 -march=pentium -Os -fomit-frame-pointer`	20161207	20161009
5267220	`ref`	`gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer`	20161207	20161009
5276850	`ref`	`gcc -m32 -march=k6 -O -fomit-frame-pointer`	20161207	20161009
5276930	`ref`	`gcc -m32 -march=k6-2 -O -fomit-frame-pointer`	20161207	20161009
5277190	`ref`	`gcc -m32 -march=k6-3 -O -fomit-frame-pointer`	20161207	20161009
5283110	`ref`	`gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer`	20161207	20161009
5283510	`ref`	`gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer`	20161207	20161009
5283580	`ref`	`gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer`	20161207	20161009
5286700	`ref`	`gcc -m32 -march=pentium4 -O -fomit-frame-pointer`	20161207	20161009
5297190	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer`	20161207	20161009
5307800	`ref`	`gcc -m32 -march=i386 -O -fomit-frame-pointer`	20161207	20161009
5309010	`ref`	`gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer`	20161207	20161009
5312230	`ref`	`gcc -m32 -march=core2 -O3 -fomit-frame-pointer`	20161207	20161009
5318430	`ref`	`gcc -m32 -march=k8 -O -fomit-frame-pointer`	20161207	20161009
5318740	`ref`	`gcc -m32 -march=athlon -O -fomit-frame-pointer`	20161207	20161009
5320620	`ref`	`gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer`	20161207	20161009
5320690	`ref`	`gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer`	20161207	20161009
5326170	`ref`	`gcc -m32 -march=barcelona -O -fomit-frame-pointer`	20161207	20161009
5326530	`ref`	`gcc -m32 -march=pentium-m -O -fomit-frame-pointer`	20161207	20161009
5327160	`ref`	`gcc -m32 -march=pentium3 -O -fomit-frame-pointer`	20161207	20161009
5329550	`ref`	`gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer`	20161207	20161009
5329570	`ref`	`gcc -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161207	20161009
5331100	`ref`	`gcc -m32 -march=pentium2 -O -fomit-frame-pointer`	20161207	20161009
5333740	`ref`	`gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer`	20161207	20161009
5334150	`ref`	`gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer`	20161207	20161009
5336540	`ref`	`gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer`	20161207	20161009
5337450	`ref`	`gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer`	20161207	20161009
5337670	`ref`	`gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer`	20161207	20161009
5338010	`ref`	`gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer`	20161207	20161009
5341250	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer`	20161207	20161009
5344380	`ref`	`gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer`	20161207	20161009
5344570	`ref`	`gcc -m32 -march=i386 -Os -fomit-frame-pointer`	20161207	20161009
5344650	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161207	20161009
5344760	`ref`	`gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer`	20161207	20161009
5344860	`ref`	`gcc -m32 -march=pentium4 -Os -fomit-frame-pointer`	20161207	20161009
5344910	`ref`	`gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer`	20161207	20161009
5344960	`ref`	`gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer`	20161207	20161009
5344990	`ref`	`gcc -m32 -march=prescott -Os -fomit-frame-pointer`	20161207	20161009
5345000	`ref`	`gcc -m32 -march=nocona -Os -fomit-frame-pointer`	20161207	20161009
5346040	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer`	20161207	20161009
5351350	`ref`	`gcc -m32 -march=prescott -O -fomit-frame-pointer`	20161207	20161009
5351950	`ref`	`gcc -m32 -march=nocona -O -fomit-frame-pointer`	20161207	20161009
5352790	`ref`	`gcc -m32 -march=i486 -Os -fomit-frame-pointer`	20161207	20161009
5358690	`ref`	`gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer`	20161207	20161009
5358870	`ref`	`gcc -m32 -march=core2 -O -fomit-frame-pointer`	20161207	20161009
5359350	`ref`	`gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161207	20161009
5360100	`ref`	`gcc -m32 -O -fomit-frame-pointer`	20161207	20161009
5360170	`ref`	`gcc -m32 -march=corei7 -O -fomit-frame-pointer`	20161207	20161009
5360850	`ref`	`gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer`	20161207	20161009
5362750	`ref`	`gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer`	20161207	20161009
5363100	`ref`	`gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer`	20161207	20161009
5371600	`ref`	`gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161207	20161009
5371800	`ref`	`gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer`	20161207	20161009
5373800	`ref`	`gcc -funroll-loops -m32 -O -fomit-frame-pointer`	20161207	20161009
5374980	`ref`	`gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer`	20161207	20161009
5551250	`ref`	`gcc -m32 -march=i486 -O -fomit-frame-pointer`	20161207	20161009
5562080	`ref`	`gcc -m32 -march=pentium -O -fomit-frame-pointer`	20161207	20161009
5562260	`ref`	`gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer`	20161207	20161009
5595970	`ref`	`gcc -m32 -march=k8 -O3 -fomit-frame-pointer`	20161207	20161009
5605790	`ref`	`gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer`	20161207	20161009
5624360	`ref`	`gcc -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161207	20161009
5627150	`ref`	`gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer`	20161207	20161009
5728820	`ref`	`gcc -m32 -march=i486 -O3 -fomit-frame-pointer`	20161207	20161009

Test failure

Implementation: crypto_aead/twine80n6t4clocv2/ref
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 27, namely:

Compiler	Implementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer	ref vperm
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer	ref vperm
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer	ref vperm
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer	ref vperm
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer	ref vperm
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer	ref vperm
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	vperm
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer	vperm
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer	vperm
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer	vperm
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer	vperm
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer	vperm
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer	ref vperm
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer	ref vperm
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer	ref vperm
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer	vperm
gcc -m32 -march=corei7 -O -fomit-frame-pointer	vperm
gcc -m32 -march=corei7 -Os -fomit-frame-pointer	vperm

Compiler output

Implementation: crypto_aead/twine80n6t4clocv2/vperm
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer

encrypt.c: In file included from encrypt.c:3:0:
encrypt.c: twine.h: In function 'Encode':
encrypt.c: twine.h:57:25: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
encrypt.c: #define XOR(x,y) _mm_xor_si128((x),(y)) /* exclusive-OR of 128-bit words x and y */
encrypt.c: ^
encrypt.c: twine.h:80:24: note: in expansion of macro 'XOR'
encrypt.c: #define SHUFFLE4(x) XOR( \
encrypt.c: ^
encrypt.c: twine.h:76:26: note: in expansion of macro 'SHUFFLE4'
encrypt.c: #define LOADS(p) SHUFFLE4(LOAD64(p)) /* load 64-bit word from memory address p, and shuffle it */
encrypt.c: ^
encrypt.c: twine.h:227:15: note: in expansion of macro 'LOADS'
encrypt.c: word state = LOADS(text);
encrypt.c: ^
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
encrypt.c: from twine.h:4,
encrypt.c: from encrypt.c:3:
encrypt.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
encrypt.c: _mm_xor_si128 (__m128i __A, __m128i __B)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:3:0:
encrypt.c: twine.h:177:8: error: called from here
encrypt.c: right = XOR(right, _tmp); \
encrypt.c: ^
encrypt.c: twine.h:228:2: note: in expansion of macro 'twine80_enc'
encrypt.c: ...

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

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

Compiler output

Implementation: crypto_aead/twine80n6t4clocv2/vperm
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 44, namely:

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

Compiler output

Implementation: crypto_aead/twine80n6t4clocv2/vperm
Compiler: gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer

encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
encrypt.c: from twine.h:4,
encrypt.c: from encrypt.c:3:
encrypt.c: twine.h: In function 'Encode':
encrypt.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
encrypt.c: _mm_xor_si128 (__m128i __A, __m128i __B)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:3:0:
encrypt.c: twine.h:177:8: error: called from here
encrypt.c: right = XOR(right, _tmp); \
encrypt.c: ^
encrypt.c: twine.h:228:2: note: in expansion of macro 'twine80_enc'
encrypt.c: twine80_enc(state);
encrypt.c: ^
encrypt.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/xmmintrin.h:1249:0,
encrypt.c: from twine.h:4,
encrypt.c: from encrypt.c:3:
encrypt.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
encrypt.c: _mm_and_si128 (__m128i __A, __m128i __B)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:3:0:
encrypt.c: twine.h:176:7: error: called from here
encrypt.c: _tmp = MASK4L(_tmp); \
encrypt.c: ^
encrypt.c: twine.h:228:2: note: in expansion of macro 'twine80_enc'
encrypt.c: ...

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

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

Compiler output

Implementation: crypto_aead/twine80n6t4clocv2/vperm
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: In file included from twine.h:7:0,
encrypt.c: from encrypt.c:3:
encrypt.c: twine.h: In function 'Encode':
encrypt.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
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:3:0:
encrypt.c: twine.h:174:7: error: called from here
encrypt.c: _tmp = PSHUFB(state, _tmp); \
encrypt.c: ^
encrypt.c: twine.h:228:2: note: in expansion of macro 'twine80_enc'
encrypt.c: twine80_enc(state);
encrypt.c: ^
encrypt.c: In file included from twine.h:7:0,
encrypt.c: from encrypt.c:3:
encrypt.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
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:3:0:
encrypt.c: twine.h:171:8: error: called from here
encrypt.c: right = PSHUFB(state, right); \
encrypt.c: ^
encrypt.c: twine.h:228:2: note: in expansion of macro 'twine80_enc'
encrypt.c: twine80_enc(state);
encrypt.c: ^
encrypt.c: ...
encrypt.c: In file included from twine.h:7:0,
encrypt.c: from encrypt.c:3:
encrypt.c: twine.h: In function 'Encode':
encrypt.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
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:3:0:
encrypt.c: twine.h:174:7: error: called from here
encrypt.c: _tmp = PSHUFB(state, _tmp); \
encrypt.c: ^
encrypt.c: twine.h:228:2: note: in expansion of macro 'twine80_enc'
encrypt.c: twine80_enc(state);
encrypt.c: ^
encrypt.c: In file included from twine.h:7:0,
encrypt.c: from encrypt.c:3:
encrypt.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
encrypt.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
encrypt.c: ^
encrypt.c: In file included from encrypt.c:3:0:
encrypt.c: twine.h:171:8: error: called from here
encrypt.c: right = PSHUFB(state, right); \
encrypt.c: ^
encrypt.c: twine.h:228:2: note: in expansion of macro 'twine80_enc'
encrypt.c: twine80_enc(state);
encrypt.c: ^
encrypt.c: ...

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

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