Implementation notes: x86, titan0, crypto_sign/sphincsf192shake256simple

Computer: titan0
Architecture: x86
CPU ID: GenuineIntel-000306c3-bfebfbff
SUPERCOP version: 20190803
Operation: crypto_sign
Primitive: sphincsf192shake256simple
TimeImplementationCompilerBenchmark dateSUPERCOP version
317125176avx2gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2019080820190803
319114024avx2gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2019080820190803
480941736avx2gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2019080820190803
484240252avx2gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2019080820190803
494832184avx2gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2019080820190803
497471192avx2gcc -m32 -march=core-avx2 -O -fomit-frame-pointer2019080820190803
501985044avx2gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2019080820190803
502050684avx2gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2019080820190803
919272828refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2019080820190803
919466224refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2019080820190803
920103876refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2019080820190803
933495100refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2019080820190803
960471624refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2019080820190803
971987824refgcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2019080820190803
972095008refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2019080820190803
984383848refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2019080820190803
1018301196refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2019080820190803
1057746420refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2019080820190803
1059979956refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2019080820190803
1064166212refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2019080820190803
1064767068refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2019080820190803
1068485716refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2019080820190803
1082595792refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2019080820190803
1085999364refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2019080820190803
1086668532refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2019080820190803
1086769172refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2019080820190803
1087022144refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2019080820190803
1106359000refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2019080820190803
1113092564refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2019080820190803
1113149228refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2019080820190803
1113939332refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2019080820190803
1114142412refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2019080820190803
1115837716refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2019080820190803
1147515896refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2019080820190803
1147700772refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2019080820190803
1149109092refgcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2019080820190803
1149167288refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2019080820190803
1157425684refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2019080820190803
1172861264refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2019080820190803
1189133792refgcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2019080820190803
1236552428refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2019080820190803
1238878540refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2019080820190803
1265327328refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2019080820190803
1265368928refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2019080820190803
1271478504refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2019080820190803
1272747460refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2019080820190803
1301483796refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2019080820190803
1311908660refgcc -m32 -march=core-avx2 -O -fomit-frame-pointer2019080820190803
1312839060refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2019080820190803
1319445388refgcc -m32 -O3 -fomit-frame-pointer2019080820190803
1324233540refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2019080820190803
1333834492refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2019080820190803
1333893268refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2019080820190803
1337807184refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2019080820190803
1338120592refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2019080820190803
1338642312refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2019080820190803
1339633460refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2019080820190803
1339932920refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2019080820190803
1348977920refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2019080820190803
1352249064refgcc -funroll-loops -m32 -O -fomit-frame-pointer2019080820190803
1360905024refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2019080820190803
1361793836refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2019080820190803
1362165576refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2019080820190803
1364725136refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2019080820190803
1366625612refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2019080820190803
1367463560refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2019080820190803
1368387688refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2019080820190803
1369778984refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2019080820190803
1370137284refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2019080820190803
1370693896refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2019080820190803
1371021908refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2019080820190803
1373003732refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2019080820190803
1373230728refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2019080820190803
1375704032refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2019080820190803
1377722900refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2019080820190803
1381031068refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2019080820190803
1391609368refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2019080820190803
1393759656refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2019080820190803
1398122184refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2019080820190803
1398651184refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2019080820190803
1404096488refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2019080820190803
1407776988refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2019080820190803
1410109544refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2019080820190803
1415881208refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2019080820190803
1416005352refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2019080820190803
1416108240refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2019080820190803
1416204016refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2019080820190803
1416358500refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2019080820190803
1418582372refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2019080820190803
1419218760refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2019080820190803
1433016464refgcc -m32 -march=prescott -O -fomit-frame-pointer2019080820190803
1434144376refgcc -m32 -march=nocona -O -fomit-frame-pointer2019080820190803
1436053908refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2019080820190803
1436683176refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2019080820190803
1438305808refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2019080820190803
1446711236refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2019080820190803
1453178408refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2019080820190803
1453380780refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2019080820190803
1453593144refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2019080820190803
1456441128refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2019080820190803
1458382044refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2019080820190803
1460085332refgcc -m32 -march=core2 -Os -fomit-frame-pointer2019080820190803
1463693904refgcc -m32 -march=core2 -O -fomit-frame-pointer2019080820190803
1463703296refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2019080820190803
1463910088refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2019080820190803
1463915152refgcc -m32 -march=k8 -O -fomit-frame-pointer2019080820190803
1463915652refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2019080820190803
1464157240refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2019080820190803
1465224148refgcc -m32 -march=corei7 -O -fomit-frame-pointer2019080820190803
1466888296refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2019080820190803
1469239060refgcc -m32 -march=barcelona -O -fomit-frame-pointer2019080820190803
1475302244refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2019080820190803
1475810172refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2019080820190803
1484933544refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2019080820190803
1486295176refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2019080820190803
1486441664refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2019080820190803
1496415472refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2019080820190803
1496645312refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2019080820190803
1497402880refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2019080820190803
1503020336refgcc -m32 -march=nocona -Os -fomit-frame-pointer2019080820190803
1504228428refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2019080820190803
1504460592refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2019080820190803
1504830004refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2019080820190803
1504936560refgcc -m32 -march=prescott -Os -fomit-frame-pointer2019080820190803
1527812828refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2019080820190803
1527979236refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2019080820190803
1538525964refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2019080820190803
1557906596refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2019080820190803
1559553380refgcc -m32 -march=athlon -Os -fomit-frame-pointer2019080820190803
1560402816refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2019080820190803
1560572884refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2019080820190803
1561125316refgcc -m32 -Os -fomit-frame-pointer2019080820190803
1561460736refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2019080820190803
1561667184refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2019080820190803
1562986700refgcc -m32 -march=k6 -Os -fomit-frame-pointer2019080820190803
1564449472refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2019080820190803
1570095452refgcc -m32 -march=i386 -Os -fomit-frame-pointer2019080820190803
1571007756refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2019080820190803
1573244056refgcc -m32 -march=pentium -Os -fomit-frame-pointer2019080820190803
1574320268refgcc -m32 -march=i486 -Os -fomit-frame-pointer2019080820190803
1577871304refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2019080820190803
1584602616refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2019080820190803
1585390988refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2019080820190803
1586823756refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2019080820190803
1594308632refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2019080820190803
1605910832refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2019080820190803
1630027672refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2019080820190803
1631364060refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2019080820190803
1632578628refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2019080820190803
1634231392refgcc -m32 -march=k6 -O -fomit-frame-pointer2019080820190803
1634800864refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2019080820190803
1635603408refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2019080820190803
1636454744refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2019080820190803
1638600756refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2019080820190803
1672551420refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2019080820190803
1675508388refgcc -m32 -march=i386 -O -fomit-frame-pointer2019080820190803
1675701084refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2019080820190803
1679023472refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2019080820190803
1679717448refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2019080820190803
1680309060refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2019080820190803
1690239344refgcc -m32 -march=athlon -O -fomit-frame-pointer2019080820190803
1694417388refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2019080820190803
1698445780refgcc -m32 -march=i486 -O -fomit-frame-pointer2019080820190803
1698590840refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2019080820190803
1699667404refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2019080820190803
1699989536refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2019080820190803
1709701732refgcc -m32 -O2 -fomit-frame-pointer2019080820190803
1727166868refgcc -m32 -O -fomit-frame-pointer2019080820190803
1742384568refgcc -m32 -march=pentium -O -fomit-frame-pointer2019080820190803
1746374600refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2019080820190803
1780821872refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2019080820190803
1787594260refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2019080820190803
2951815028refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2019080820190803
2988521568refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2019080820190803
3159725356refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2019080820190803
3180277516refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2019080820190803
3293368688refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2019080820190803
3331358884refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2019080820190803
3408455688refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2019080820190803
3427911328refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2019080820190803
3545925512refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2019080820190803
3591107000refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2019080820190803
3593869892refgcc -m32 -march=k8 -Os -fomit-frame-pointer2019080820190803
3637431952refgcc -m32 -march=barcelona -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