Implementation notes: x86, titan0, crypto_sign/sphincsf128shake256robust

Computer: titan0
Architecture: x86
CPU ID: GenuineIntel-000306c3-bfebfbff
SUPERCOP version: 20190803
Operation: crypto_sign
Primitive: sphincsf128shake256robust
TimeImplementationCompilerBenchmark dateSUPERCOP version
420341728avx2gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2019080820190803
428669628avx2gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2019080820190803
641090792avx2gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2019080820190803
641193928avx2gcc -m32 -march=core-avx2 -O -fomit-frame-pointer2019080820190803
653964508avx2gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2019080820190803
654672796avx2gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2019080820190803
697558468avx2gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2019080820190803
698185928avx2gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2019080820190803
1312729380refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2019080820190803
1314180600refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2019080820190803
1314672384refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2019080820190803
1332031344refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2019080820190803
1333860580refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2019080820190803
1362995456refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2019080820190803
1390693728refgcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2019080820190803
1390874608refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2019080820190803
1425718304refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2019080820190803
1505737120refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2019080820190803
1506007100refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2019080820190803
1508368260refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2019080820190803
1508385888refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2019080820190803
1508816904refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2019080820190803
1528879556refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2019080820190803
1529411100refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2019080820190803
1544502524refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2019080820190803
1556109696refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2019080820190803
1556307432refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2019080820190803
1557652048refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2019080820190803
1567816064refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2019080820190803
1568117988refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2019080820190803
1568207288refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2019080820190803
1568228312refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2019080820190803
1582513188refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2019080820190803
1619439204refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2019080820190803
1636623096refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2019080820190803
1641520204refgcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2019080820190803
1679003152refgcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2019080820190803
1679070244refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2019080820190803
1686649704refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2019080820190803
1694190592refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2019080820190803
1718513912refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2019080820190803
1718597920refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2019080820190803
1775306400refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2019080820190803
1775758908refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2019080820190803
1781951720refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2019080820190803
1802254748refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2019080820190803
1876316568refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2019080820190803
1882786420refgcc -m32 -march=core-avx2 -O -fomit-frame-pointer2019080820190803
1883592184refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2019080820190803
1887076892refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2019080820190803
1889758496refgcc -m32 -O3 -fomit-frame-pointer2019080820190803
1894356668refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2019080820190803
1901022076refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2019080820190803
1906478056refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2019080820190803
1907280660refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2019080820190803
1914215824refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2019080820190803
1914279016refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2019080820190803
1915794144refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2019080820190803
1915901068refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2019080820190803
1924533548refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2019080820190803
1929637396refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2019080820190803
1937335264refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2019080820190803
1943443804refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2019080820190803
1944538560refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2019080820190803
1945513980refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2019080820190803
1945594420refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2019080820190803
1947628268refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2019080820190803
1949002408refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2019080820190803
1950208604refgcc -funroll-loops -m32 -O -fomit-frame-pointer2019080820190803
1953424100refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2019080820190803
1955914488refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2019080820190803
1955934672refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2019080820190803
1956664436refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2019080820190803
1980107996refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2019080820190803
1980246928refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2019080820190803
1985125236refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2019080820190803
1987966356refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2019080820190803
1990092612refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2019080820190803
1999248496refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2019080820190803
2000407704refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2019080820190803
2001327608refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2019080820190803
2001669856refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2019080820190803
2002116940refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2019080820190803
2013268616refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2019080820190803
2013466268refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2019080820190803
2018065596refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2019080820190803
2026264540refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2019080820190803
2026754640refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2019080820190803
2029039428refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2019080820190803
2029609016refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2019080820190803
2029869456refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2019080820190803
2033852880refgcc -m32 -march=k8 -O -fomit-frame-pointer2019080820190803
2039582504refgcc -m32 -march=prescott -O -fomit-frame-pointer2019080820190803
2046627876refgcc -m32 -march=prescott -Os -fomit-frame-pointer2019080820190803
2047985212refgcc -m32 -march=nocona -Os -fomit-frame-pointer2019080820190803
2048699344refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2019080820190803
2051102172refgcc -m32 -march=nocona -O -fomit-frame-pointer2019080820190803
2052461240refgcc -m32 -march=core2 -Os -fomit-frame-pointer2019080820190803
2052491908refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2019080820190803
2054226412refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2019080820190803
2055630880refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2019080820190803
2065069012refgcc -m32 -march=barcelona -O -fomit-frame-pointer2019080820190803
2070863996refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2019080820190803
2071295276refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2019080820190803
2072449424refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2019080820190803
2072661852refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2019080820190803
2072881400refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2019080820190803
2073091544refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2019080820190803
2075814992refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2019080820190803
2076717600refgcc -m32 -march=core2 -O -fomit-frame-pointer2019080820190803
2077295008refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2019080820190803
2080246284refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2019080820190803
2081331880refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2019080820190803
2081976596refgcc -m32 -march=corei7 -O -fomit-frame-pointer2019080820190803
2096245000refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2019080820190803
2096408840refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2019080820190803
2100670460refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2019080820190803
2101959516refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2019080820190803
2102059956refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2019080820190803
2103962000refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2019080820190803
2105740368refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2019080820190803
2120843108refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2019080820190803
2146842028refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2019080820190803
2150653396refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2019080820190803
2187426496refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2019080820190803
2188794476refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2019080820190803
2188897780refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2019080820190803
2203148836refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2019080820190803
2203445728refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2019080820190803
2203654572refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2019080820190803
2227528748refgcc -m32 -march=i386 -Os -fomit-frame-pointer2019080820190803
2230054272refgcc -m32 -march=i486 -Os -fomit-frame-pointer2019080820190803
2230883444refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2019080820190803
2231174084refgcc -m32 -march=k6 -Os -fomit-frame-pointer2019080820190803
2231470296refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2019080820190803
2236086488refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2019080820190803
2236348212refgcc -m32 -march=pentium -Os -fomit-frame-pointer2019080820190803
2236360224refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2019080820190803
2238324296refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2019080820190803
2266235036refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2019080820190803
2266754124refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2019080820190803
2267604308refgcc -m32 -march=athlon -Os -fomit-frame-pointer2019080820190803
2269304176refgcc -m32 -Os -fomit-frame-pointer2019080820190803
2270576468refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2019080820190803
2295556332refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2019080820190803
2307987208refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2019080820190803
2310153776refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2019080820190803
2311991464refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2019080820190803
2324948740refgcc -m32 -march=k6 -O -fomit-frame-pointer2019080820190803
2326136188refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2019080820190803
2326715240refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2019080820190803
2351620436refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2019080820190803
2354338200refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2019080820190803
2366594480refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2019080820190803
2375176336refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2019080820190803
2375377132refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2019080820190803
2379164220refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2019080820190803
2408950144refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2019080820190803
2419870756refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2019080820190803
2425899444refgcc -m32 -march=i386 -O -fomit-frame-pointer2019080820190803
2436227864refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2019080820190803
2449041540refgcc -m32 -march=athlon -O -fomit-frame-pointer2019080820190803
2452452160refgcc -m32 -march=i486 -O -fomit-frame-pointer2019080820190803
2458753728refgcc -m32 -O -fomit-frame-pointer2019080820190803
2500881416refgcc -m32 -O2 -fomit-frame-pointer2019080820190803
2506886636refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2019080820190803
2508104052refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2019080820190803
2508752748refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2019080820190803
2512499024refgcc -m32 -march=pentium -O -fomit-frame-pointer2019080820190803
2518921212refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2019080820190803
2526425112refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2019080820190803
2527001192refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2019080820190803
4246352316refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2019080820190803
4309432460refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2019080820190803
4549507772refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2019080820190803
4566130480refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2019080820190803
4738584824refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2019080820190803
4786539512refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2019080820190803
4910242980refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2019080820190803
5012107072refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2019080820190803
5065458356refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2019080820190803
5111117760refgcc -m32 -march=k8 -Os -fomit-frame-pointer2019080820190803
5183806704refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2019080820190803
5244614344refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2019080820190803

Compiler output

Implementation: crypto_sign/sphincsf128shake256robust/avx2
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 156, namely:
CompilerImplementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer avx2
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer avx2
gcc -m32 -O2 -fomit-frame-pointer avx2
gcc -m32 -O3 -fomit-frame-pointer avx2
gcc -m32 -O -fomit-frame-pointer avx2
gcc -m32 -Os -fomit-frame-pointer avx2
gcc -m32 -march=athlon -O2 -fomit-frame-pointer avx2
gcc -m32 -march=athlon -O3 -fomit-frame-pointer avx2
gcc -m32 -march=athlon -O -fomit-frame-pointer avx2
gcc -m32 -march=athlon -Os -fomit-frame-pointer avx2
gcc -m32 -march=core2 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=core2 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=core2 -O -fomit-frame-pointer avx2
gcc -m32 -march=core2 -Os -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer avx2
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer avx2
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=corei7 -O -fomit-frame-pointer avx2
gcc -m32 -march=corei7 -Os -fomit-frame-pointer avx2
gcc -m32 -march=i386 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=i386 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=i386 -O -fomit-frame-pointer avx2
gcc -m32 -march=i386 -Os -fomit-frame-pointer avx2
gcc -m32 -march=i486 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=i486 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=i486 -O -fomit-frame-pointer avx2
gcc -m32 -march=i486 -Os -fomit-frame-pointer avx2
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=k6-2 -O -fomit-frame-pointer avx2
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer avx2
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=k6-3 -O -fomit-frame-pointer avx2
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer avx2
gcc -m32 -march=k6 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=k6 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=k6 -O -fomit-frame-pointer avx2
gcc -m32 -march=k6 -Os -fomit-frame-pointer avx2
gcc -m32 -march=k8 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=k8 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=k8 -O -fomit-frame-pointer avx2
gcc -m32 -march=k8 -Os -fomit-frame-pointer avx2
gcc -m32 -march=nocona -O2 -fomit-frame-pointer avx2
gcc -m32 -march=nocona -O3 -fomit-frame-pointer avx2
gcc -m32 -march=nocona -O -fomit-frame-pointer avx2
gcc -m32 -march=nocona -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentium-m -O -fomit-frame-pointer avx2
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer avx2
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentium2 -O -fomit-frame-pointer avx2
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentium3 -O -fomit-frame-pointer avx2
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentium4 -O -fomit-frame-pointer avx2
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentium -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentium -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentium -O -fomit-frame-pointer avx2
gcc -m32 -march=pentium -Os -fomit-frame-pointer avx2
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer avx2
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer avx2
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer avx2
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer avx2
gcc -m32 -march=prescott -O2 -fomit-frame-pointer avx2
gcc -m32 -march=prescott -O3 -fomit-frame-pointer avx2
gcc -m32 -march=prescott -O -fomit-frame-pointer avx2
gcc -m32 -march=prescott -Os -fomit-frame-pointer avx2

Compiler output

Implementation: crypto_sign/sphincsf128shake256robust/avx2
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ...
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer avx2
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer avx2
gcc -m32 -march=barcelona -O -fomit-frame-pointer avx2
gcc -m32 -march=barcelona -Os -fomit-frame-pointer avx2

Compiler output

Implementation: crypto_sign/sphincsf128shake256robust/avx2
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:142:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+2], lanes2 ),\
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 8, namely:
CompilerImplementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer avx2
gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer avx2
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer avx2
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer avx2
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer avx2
gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer avx2
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer avx2
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer avx2