Implementation notes: x86, samba, crypto_sign/sphincsf192shake256simple

Computer: samba
Architecture: x86
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20190803
Operation: crypto_sign
Primitive: sphincsf192shake256simple
TimeImplementationCompilerBenchmark dateSUPERCOP version
300279500avx2gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2019080820190803
300297330avx2gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2019080820190803
448902446avx2gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2019080820190803
450777414avx2gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2019080820190803
454676847avx2gcc -m32 -march=core-avx2 -O -fomit-frame-pointer2019080820190803
458066593avx2gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2019080820190803
474593254avx2gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2019080820190803
474629339avx2gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2019080820190803
896316127refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2019080820190803
896677670refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2019080820190803
896835348refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2019080820190803
902608962refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2019080820190803
912541863refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2019080820190803
912871564refgcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2019080820190803
926370770refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2019080820190803
947869079refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2019080820190803
1006650839refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2019080820190803
1013790686refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2019080820190803
1016924959refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2019080820190803
1024882308refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2019080820190803
1042024889refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2019080820190803
1042044815refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2019080820190803
1046719121refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2019080820190803
1046766395refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2019080820190803
1047943000refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2019080820190803
1065882371refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2019080820190803
1066019635refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2019080820190803
1075678627refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2019080820190803
1077067178refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2019080820190803
1082349510refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2019080820190803
1082376104refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2019080820190803
1082413738refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2019080820190803
1083400189refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2019080820190803
1083519421refgcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2019080820190803
1084391587refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2019080820190803
1091860639refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2019080820190803
1091871873refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2019080820190803
1108893260refgcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2019080820190803
1109002036refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2019080820190803
1114334799refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2019080820190803
1114586526refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2019080820190803
1114900554refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2019080820190803
1139044397refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2019080820190803
1139117387refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2019080820190803
1139281819refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2019080820190803
1150299444refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2019080820190803
1150386641refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2019080820190803
1150494032refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2019080820190803
1151963297refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2019080820190803
1151987355refgcc -m32 -march=nocona -Os -fomit-frame-pointer2019080820190803
1152013024refgcc -m32 -march=prescott -Os -fomit-frame-pointer2019080820190803
1161015831refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2019080820190803
1161038478refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2019080820190803
1162163184refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2019080820190803
1172445351refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2019080820190803
1175627063refgcc -m32 -march=core2 -Os -fomit-frame-pointer2019080820190803
1182307806refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2019080820190803
1199281856refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2019080820190803
1202075224refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2019080820190803
1232454887refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2019080820190803
1232755339refgcc -m32 -march=core-avx2 -O -fomit-frame-pointer2019080820190803
1263752893refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2019080820190803
1269418717refgcc -m32 -O3 -fomit-frame-pointer2019080820190803
1274820811refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2019080820190803
1276041659refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2019080820190803
1276170377refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2019080820190803
1279618109refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2019080820190803
1281165527refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2019080820190803
1282193435refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2019080820190803
1292594809refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2019080820190803
1295157156refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2019080820190803
1295335990refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2019080820190803
1297172521refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2019080820190803
1297368178refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2019080820190803
1299310294refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2019080820190803
1299798444refgcc -funroll-loops -m32 -O -fomit-frame-pointer2019080820190803
1313315400refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2019080820190803
1313564986refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2019080820190803
1314139795refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2019080820190803
1314577754refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2019080820190803
1314963465refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2019080820190803
1318816258refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2019080820190803
1319031279refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2019080820190803
1319117564refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2019080820190803
1321672891refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2019080820190803
1321858655refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2019080820190803
1322297964refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2019080820190803
1334868486refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2019080820190803
1336097471refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2019080820190803
1339046694refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2019080820190803
1339786732refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2019080820190803
1352040451refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2019080820190803
1354639889refgcc -m32 -march=core2 -O -fomit-frame-pointer2019080820190803
1354669065refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2019080820190803
1354711192refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2019080820190803
1354938545refgcc -m32 -march=k8 -O -fomit-frame-pointer2019080820190803
1356140883refgcc -m32 -march=corei7 -O -fomit-frame-pointer2019080820190803
1356207623refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2019080820190803
1356317867refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2019080820190803
1359448611refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2019080820190803
1359813705refgcc -m32 -march=prescott -O -fomit-frame-pointer2019080820190803
1359946327refgcc -m32 -march=nocona -O -fomit-frame-pointer2019080820190803
1360587429refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2019080820190803
1360654732refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2019080820190803
1362191623refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2019080820190803
1366020030refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2019080820190803
1366949214refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2019080820190803
1374540913refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2019080820190803
1377608280refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2019080820190803
1377842000refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2019080820190803
1378921021refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2019080820190803
1380434150refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2019080820190803
1382757430refgcc -m32 -march=barcelona -O -fomit-frame-pointer2019080820190803
1387824262refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2019080820190803
1387934160refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2019080820190803
1407155320refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2019080820190803
1407281469refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2019080820190803
1407431280refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2019080820190803
1434170944refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2019080820190803
1434379998refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2019080820190803
1438829103refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2019080820190803
1438895955refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2019080820190803
1439927756refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2019080820190803
1439973814refgcc -m32 -march=pentium -Os -fomit-frame-pointer2019080820190803
1443388966refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2019080820190803
1443395288refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2019080820190803
1443673893refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2019080820190803
1446723575refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2019080820190803
1446960923refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2019080820190803
1451567615refgcc -m32 -march=athlon -Os -fomit-frame-pointer2019080820190803
1451590945refgcc -m32 -Os -fomit-frame-pointer2019080820190803
1451613137refgcc -m32 -march=i386 -Os -fomit-frame-pointer2019080820190803
1452482500refgcc -m32 -march=i486 -Os -fomit-frame-pointer2019080820190803
1453432883refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2019080820190803
1458332766refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2019080820190803
1458523060refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2019080820190803
1458617682refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2019080820190803
1460047163refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2019080820190803
1460285690refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2019080820190803
1461892443refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2019080820190803
1464201966refgcc -m32 -march=k6 -Os -fomit-frame-pointer2019080820190803
1464239391refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2019080820190803
1464283292refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2019080820190803
1464671490refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2019080820190803
1464869145refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2019080820190803
1464912071refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2019080820190803
1467139040refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2019080820190803
1467244079refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2019080820190803
1538611224refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2019080820190803
1539475261refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2019080820190803
1539494802refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2019080820190803
1539554932refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2019080820190803
1539678832refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2019080820190803
1539822928refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2019080820190803
1562540329refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2019080820190803
1562681258refgcc -m32 -march=k6 -O -fomit-frame-pointer2019080820190803
1562842857refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2019080820190803
1575636058refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2019080820190803
1579822631refgcc -m32 -O -fomit-frame-pointer2019080820190803
1587740137refgcc -m32 -march=athlon -O -fomit-frame-pointer2019080820190803
1590851512refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2019080820190803
1593099686refgcc -m32 -O2 -fomit-frame-pointer2019080820190803
1606670421refgcc -m32 -march=i386 -O -fomit-frame-pointer2019080820190803
1608854267refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2019080820190803
1611701879refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2019080820190803
1611817617refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2019080820190803
1612586437refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2019080820190803
1624721232refgcc -m32 -march=i486 -O -fomit-frame-pointer2019080820190803
1637188232refgcc -m32 -march=pentium -O -fomit-frame-pointer2019080820190803
1637297018refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2019080820190803
1721236448refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2019080820190803
1721629867refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2019080820190803
2916848304refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2019080820190803
2948619982refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2019080820190803
3143085707refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2019080820190803
3158362945refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2019080820190803
3305413778refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2019080820190803
3314673379refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2019080820190803
3377619848refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2019080820190803
3409998790refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2019080820190803
3542596977refgcc -m32 -march=k8 -Os -fomit-frame-pointer2019080820190803
3559272279refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2019080820190803
3581850256refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2019080820190803
3629797131refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2019080820190803

Compiler output

Implementation: crypto_sign/sphincsf192shake256simple/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/sphincsf192shake256simple/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/sphincsf192shake256simple/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