Implementation notes: amd64, genji262, crypto_sign/sphincsf256shake256

Computer: genji262
Architecture: amd64
CPU ID: AuthenticAMD-00800f12-178bfbff
SUPERCOP version: 20180818
Operation: crypto_sign
Primitive: sphincsf256shake256
TimeImplementationCompilerBenchmark dateSUPERCOP version
929607844avx2gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018082020180818
956814320avx2gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018082020180818
959493634avx2gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018082020180818
1072072078refgcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018082020180818
1072864694refgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018082020180818
1075494728refgcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018082020180818
1192402442refgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2018082020180818
1196489558refgcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer2018082020180818
1197314690refgcc -m64 -march=corei7 -O3 -fomit-frame-pointer2018082020180818
1202053424refgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2018082020180818
1202560040refgcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2018082020180818
1202595944refgcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2018082020180818
1202987566refgcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018082020180818
1204878708refgcc -m64 -march=core2 -O3 -fomit-frame-pointer2018082020180818
1205291164refgcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer2018082020180818
1208165530refgcc -funroll-loops -O3 -fomit-frame-pointer2018082020180818
1211207624refgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2018082020180818
1211819620refgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2018082020180818
1212129204refgcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2018082020180818
1220391348avx2gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018082020180818
1221490974avx2gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018082020180818
1227807218refgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2018082020180818
1229844374refgcc -m64 -march=barcelona -O3 -fomit-frame-pointer2018082020180818
1230462024refgcc -m64 -march=k8 -O3 -fomit-frame-pointer2018082020180818
1231269358refgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2018082020180818
1234411090refgcc -m64 -O3 -fomit-frame-pointer2018082020180818
1234897224refgcc -fno-schedule-insns -O3 -fomit-frame-pointer2018082020180818
1235581336avx2gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018082020180818
1240390404refgcc -march=barcelona -O3 -fomit-frame-pointer2018082020180818
1244347060refgcc -march=k8 -O3 -fomit-frame-pointer2018082020180818
1244555466refgcc -O3 -fomit-frame-pointer2018082020180818
1245188934refgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2018082020180818
1250039318refgcc -m64 -march=nocona -O3 -fomit-frame-pointer2018082020180818
1260594786refgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2018082020180818
1264305438refgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2018082020180818
1266318086refgcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2018082020180818
1267194874refgcc -march=nocona -O3 -fomit-frame-pointer2018082020180818
1267283798refgcc -funroll-loops -O2 -fomit-frame-pointer2018082020180818
1267750088refgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2018082020180818
1277490082refgcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2018082020180818
1281906208refgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2018082020180818
1284576634refgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2018082020180818
1295262980refgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2018082020180818
1297612910refgcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2018082020180818
1305415342refgcc -funroll-loops -m64 -O -fomit-frame-pointer2018082020180818
1307806346refgcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2018082020180818
1310119404refgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2018082020180818
1315499416refgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2018082020180818
1317511492refgcc -funroll-loops -O -fomit-frame-pointer2018082020180818
1317795644avx2gcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018082020180818
1322187284refgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2018082020180818
1336408634refgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2018082020180818
1339330938avx2gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018082020180818
1362451354avx2gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018082020180818
1378258376avx2gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018082020180818
1382423812avx2gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018082020180818
1436668200avx2gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018082020180818
1440401050refgcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018082020180818
1475791878refgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018082020180818
1517788800refgcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018082020180818
1531278408refgcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018082020180818
1561431410refgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018082020180818
1568105660refgcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018082020180818
1571792134refgcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018082020180818
1597667346refgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018082020180818
1599639360refgcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2018082020180818
1605020934refgcc -m64 -march=barcelona -O2 -fomit-frame-pointer2018082020180818
1607416734refgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2018082020180818
1610027980refgcc -march=barcelona -O2 -fomit-frame-pointer2018082020180818
1623554042refgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2018082020180818
1624562016refgcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2018082020180818
1643121392refgcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018082020180818
1646085254refgcc -m64 -march=core-avx-i -Os -fomit-frame-pointer2018082020180818
1652700742refgcc -m64 -march=core2 -O2 -fomit-frame-pointer2018082020180818
1656522186refgcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2018082020180818
1659844208refgcc -m64 -march=corei7-avx -Os -fomit-frame-pointer2018082020180818
1663901492refgcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018082020180818
1673428878refgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2018082020180818
1681087760refgcc -fno-schedule-insns -O2 -fomit-frame-pointer2018082020180818
1691628818refgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2018082020180818
1697736458refgcc -m64 -march=barcelona -O -fomit-frame-pointer2018082020180818
1698962518refgcc -m64 -O2 -fomit-frame-pointer2018082020180818
1699209666refgcc -funroll-loops -Os -fomit-frame-pointer2018082020180818
1703201456refgcc -funroll-loops -m64 -Os -fomit-frame-pointer2018082020180818
1705204072refgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2018082020180818
1705496760refgcc -m64 -march=k8 -O2 -fomit-frame-pointer2018082020180818
1707899820refgcc -march=barcelona -O -fomit-frame-pointer2018082020180818
1709628052refgcc -O2 -fomit-frame-pointer2018082020180818
1709764606refgcc -fno-schedule-insns -Os -fomit-frame-pointer2018082020180818
1715085966refgcc -m64 -march=core2 -O -fomit-frame-pointer2018082020180818
1716790790refgcc -m64 -march=corei7 -O2 -fomit-frame-pointer2018082020180818
1720711784refgcc -march=k8 -O2 -fomit-frame-pointer2018082020180818
1732049308refgcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2018082020180818
1732922202refgcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2018082020180818
1736294450refgcc -m64 -march=core-avx-i -O -fomit-frame-pointer2018082020180818
1737287948refgcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer2018082020180818
1738324676refgcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer2018082020180818
1739997072refgcc -m64 -Os -fomit-frame-pointer2018082020180818
1740241096refgcc -Os -fomit-frame-pointer2018082020180818
1740648052refgcc -m64 -march=corei7-avx -O -fomit-frame-pointer2018082020180818
1743196906refgcc -m64 -march=corei7 -Os -fomit-frame-pointer2018082020180818
1744368560refgcc -fno-schedule-insns -O -fomit-frame-pointer2018082020180818
1750321760refgcc -m64 -march=nocona -O2 -fomit-frame-pointer2018082020180818
1756468934refgcc -O -fomit-frame-pointer2018082020180818
1758857386refgcc -march=nocona -O2 -fomit-frame-pointer2018082020180818
1759183030refgcc -m64 -march=core2 -Os -fomit-frame-pointer2018082020180818
1759547218refgcc -m64 -march=nocona -O -fomit-frame-pointer2018082020180818
1761207690refgcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2018082020180818
1762982232refgcc -m64 -march=k8 -O -fomit-frame-pointer2018082020180818
1764429282refgcc -m64 -march=k8 -Os -fomit-frame-pointer2018082020180818
1764671568refgcc -m64 -march=corei7 -O -fomit-frame-pointer2018082020180818
1766369462refgcc -march=k8 -Os -fomit-frame-pointer2018082020180818
1766515322refgcc -march=k8 -O -fomit-frame-pointer2018082020180818
1768660036refgcc -m64 -march=barcelona -Os -fomit-frame-pointer2018082020180818
1768781058refgcc -m64 -O -fomit-frame-pointer2018082020180818
1770779252refgcc -march=nocona -O -fomit-frame-pointer2018082020180818
1771627088refgcc -march=barcelona -Os -fomit-frame-pointer2018082020180818
1773722940refgcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018082020180818
1792497564refgcc -march=nocona -Os -fomit-frame-pointer2018082020180818
1795508616refgcc -m64 -march=nocona -Os -fomit-frame-pointer2018082020180818
6147433270refcc2018082020180818
6190216384refgcc -funroll-loops2018082020180818
6207481874refgcc2018082020180818

Compiler output

Implementation: crypto_sign/sphincsf256shake256/avx2
Compiler: cc
KeccakP-1600-times4-SIMD256.c: In file included from KeccakP-1600-times4-SIMD256.c:19:0:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/smmintrin.h:31:3: error: #error "SSE4.1 instruction set not enabled"
KeccakP-1600-times4-SIMD256.c: # error "SSE4.1 instruction set not enabled"
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: In file included from KeccakP-1600-times4-SIMD256.c:20:0:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/wmmintrin.h:34:3: error: #error "AES/PCLMUL instructions not enabled"
KeccakP-1600-times4-SIMD256.c: # error "AES/PCLMUL instructions not enabled"
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:35:1: error: unknown type name '__m256i'
KeccakP-1600-times4-SIMD256.c: typedef __m256i V256;
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:58:67: error: '__m256' undeclared (first use in this function)
KeccakP-1600-times4-SIMD256.c: #define PERM128( a, b, c ) (V256)_mm256_permute2f128_ps((__m256)(a), (__m256)(b), c)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:70:48: note: in expansion of macro 'PERM128'
KeccakP-1600-times4-SIMD256.c: #define INTLEAVE() lanesL01 = PERM128( lanes0, lanes2, 0x20 ), \
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:139:33: note: in expansion of macro 'INTLEAVE'
KeccakP-1600-times4-SIMD256.c: INTLEAVE(),\
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: KeccakP-1600-times4-SIMD256.c:58:67: note: each undeclared identifier is reported only once for each function it appears in
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
cc avx2

Compiler output

Implementation: crypto_sign/sphincsf256shake256/avx2
Compiler: gcc
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 /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/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 /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/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: 86, namely:
CompilerImplementations
gcc avx2
gcc -O2 -fomit-frame-pointer avx2
gcc -O3 -fomit-frame-pointer avx2
gcc -O -fomit-frame-pointer avx2
gcc -Os -fomit-frame-pointer avx2
gcc -fno-schedule-insns -O2 -fomit-frame-pointer avx2
gcc -fno-schedule-insns -O3 -fomit-frame-pointer avx2
gcc -fno-schedule-insns -O -fomit-frame-pointer avx2
gcc -fno-schedule-insns -Os -fomit-frame-pointer avx2
gcc -funroll-loops avx2
gcc -funroll-loops -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -O -fomit-frame-pointer avx2
gcc -funroll-loops -Os -fomit-frame-pointer avx2
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer avx2
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer avx2
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer avx2
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer avx2
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer avx2
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer avx2
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer avx2
gcc -m64 -O2 -fomit-frame-pointer avx2
gcc -m64 -O3 -fomit-frame-pointer avx2
gcc -m64 -O -fomit-frame-pointer avx2
gcc -m64 -Os -fomit-frame-pointer avx2
gcc -m64 -march=core2 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=core2 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=core2 -O -fomit-frame-pointer avx2
gcc -m64 -march=core2 -Os -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer avx2
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=corei7 -O -fomit-frame-pointer avx2
gcc -m64 -march=corei7 -Os -fomit-frame-pointer avx2
gcc -m64 -march=k8 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=k8 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=k8 -O -fomit-frame-pointer avx2
gcc -m64 -march=k8 -Os -fomit-frame-pointer avx2
gcc -m64 -march=nocona -O2 -fomit-frame-pointer avx2
gcc -m64 -march=nocona -O3 -fomit-frame-pointer avx2
gcc -m64 -march=nocona -O -fomit-frame-pointer avx2
gcc -m64 -march=nocona -Os -fomit-frame-pointer avx2
gcc -march=barcelona -O2 -fomit-frame-pointer avx2
gcc -march=barcelona -O3 -fomit-frame-pointer avx2
gcc -march=barcelona -O -fomit-frame-pointer avx2
gcc -march=barcelona -Os -fomit-frame-pointer avx2
gcc -march=k8 -O2 -fomit-frame-pointer avx2
gcc -march=k8 -O3 -fomit-frame-pointer avx2
gcc -march=k8 -O -fomit-frame-pointer avx2
gcc -march=k8 -Os -fomit-frame-pointer avx2
gcc -march=nocona -O2 -fomit-frame-pointer avx2
gcc -march=nocona -O3 -fomit-frame-pointer avx2
gcc -march=nocona -O -fomit-frame-pointer avx2
gcc -march=nocona -Os -fomit-frame-pointer avx2

Compiler output

Implementation: crypto_sign/sphincsf256shake256/avx2
Compiler: gcc -m64 -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 /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/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 /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/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 /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/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 /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/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 -m64 -march=barcelona -O2 -fomit-frame-pointer avx2
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer avx2
gcc -m64 -march=barcelona -O -fomit-frame-pointer avx2
gcc -m64 -march=barcelona -Os -fomit-frame-pointer avx2

Compiler output

Implementation: crypto_sign/sphincsf256shake256/avx2
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
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: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/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 /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs_robin_ib/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/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 -m64 -march=core-avx-i -O2 -fomit-frame-pointer avx2
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer avx2
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer avx2
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer avx2
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer avx2
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer avx2
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer avx2
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer avx2