Implementation notes: x86, kizomba, crypto_sign/sphincss128shake256

Computer: kizomba
Architecture: x86
CPU ID: GenuineIntel-000906e9-bfebfbff
SUPERCOP version: 20181216
Operation: crypto_sign
Primitive: sphincss128shake256
TimeImplementationCompilerBenchmark dateSUPERCOP version
4837893450avx2gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2018090220180818
5288971298avx2gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2018090220180818
7820216549avx2gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2018090220180818
8351387181avx2gcc -m32 -march=core-avx2 -O -fomit-frame-pointer2018090220180818
8369991264avx2gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2018090220180818
8525537603avx2gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2018090220180818
10246455889avx2gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2018090220180818
18194277530avx2gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2018090220180818
18352218399refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2018090220180818
18375633236refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2018090220180818
18397266665refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018090220180818
18564748605refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2018090220180818
18767822030refgcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2018090220180818
18869578889refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2018090320180818
19164449540refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2018090220180818
19170183286refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2018090220180818
20631991966refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2018090320180818
20829894597refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2018090220180818
20960526000refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2018090220180818
20963561821refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2018090220180818
20973287363refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2018090220180818
20980399434refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2018090220180818
21072528397refgcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2018090220180818
21183095677refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2018090320180818
21302089150refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2018090220180818
21303688815refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2018090220180818
21325890224refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2018090320180818
21331815592refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2018090320180818
21521468670refgcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2018090220180818
21698564360refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2018090220180818
21700612010refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2018090220180818
21755493292refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018090220180818
21764571044refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2018090220180818
21774914926refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2018090220180818
21849255393refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018090220180818
21850817141refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2018090220180818
21854315633refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2018090220180818
22666346234refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2018090220180818
22672485960refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2018090320180818
22678695681refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2018090320180818
22684006296refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2018090320180818
22769066163refgcc -m32 -march=nocona -Os -fomit-frame-pointer2018090220180818
22769761053refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2018090220180818
22772156790refgcc -m32 -march=prescott -Os -fomit-frame-pointer2018090220180818
22819138946refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2018090320180818
22828233383refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2018090320180818
22990072163refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2018090320180818
22992514684refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2018090320180818
22993845113refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2018090220180818
22995101022refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2018090320180818
23026471329refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2018090320180818
23055315827refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2018090320180818
23059702918refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2018090320180818
23105059444refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2018090320180818
23119344417refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2018090320180818
23161741619refgcc -m32 -march=core2 -Os -fomit-frame-pointer2018090220180818
23811863841refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2018090220180818
23881427766refgcc -m32 -march=core-avx2 -O -fomit-frame-pointer2018090220180818
24062257578refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2018090220180818
25490321178refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2018090220180818
25529616765refgcc -m32 -march=barcelona -O -fomit-frame-pointer2018090220180818
25560790943refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2018090220180818
25560913228refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2018090220180818
25595433295refgcc -m32 -march=k8 -O -fomit-frame-pointer2018090220180818
25684400061refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2018090220180818
25791102448refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2018090220180818
25840255184refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2018090320180818
25844623325refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2018090320180818
25901495010refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2018090320180818
25956530115refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2018090220180818
25962573582refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2018090220180818
25964389940refgcc -m32 -march=corei7 -O -fomit-frame-pointer2018090220180818
25991729786refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2018090220180818
26007750162refgcc -m32 -march=nocona -O -fomit-frame-pointer2018090220180818
26009531851refgcc -m32 -march=prescott -O -fomit-frame-pointer2018090220180818
26075146786refgcc -m32 -O3 -fomit-frame-pointer2018090220180818
26191561851refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2018090220180818
26194184312refgcc -m32 -march=core2 -O -fomit-frame-pointer2018090220180818
26196822022refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2018090220180818
26219194016refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2018090320180818
26332910871refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2018090220180818
26335179806refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2018090220180818
26387920932refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2018090320180818
26446039528refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2018090220180818
27260979581refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2018090320180818
27321946462refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2018090320180818
27324332052refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2018090320180818
27485080580refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2018090320180818
27586848137refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2018090320180818
27621646162refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2018090320180818
27870982282refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2018090320180818
27874568040refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2018090320180818
27892615181refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2018090320180818
27965547095refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2018090320180818
27969427959refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2018090320180818
27970240476refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2018090320180818
27984190101refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2018090320180818
28073473025refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2018090320180818
28098558048refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2018090320180818
28121162878refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2018090320180818
28121204518refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2018090320180818
28125631914refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2018090320180818
28187157807refgcc -funroll-loops -m32 -O -fomit-frame-pointer2018090320180818
28544640153refgcc -m32 -march=k6 -Os -fomit-frame-pointer2018090220180818
28549357476refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2018090220180818
28554293256refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2018090220180818
28622915536refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2018090220180818
28628732541refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2018090320180818
28657967478refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2018090220180818
28658223091refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2018090320180818
28680804482refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2018090320180818
28683904262refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2018090320180818
28691433547refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2018090320180818
28941792728refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2018090320180818
28960881571refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2018090320180818
28962711530refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2018090320180818
29030078939refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2018090320180818
29045879103refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2018090320180818
29056967724refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2018090320180818
29058384543refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2018090320180818
29064511635refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2018090320180818
29069640716refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2018090320180818
29143091395refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2018090320180818
29156608219refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2018090320180818
29176307071refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2018090320180818
29177979510refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2018090320180818
29218172836refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2018090320180818
29287503674refgcc -m32 -march=i486 -Os -fomit-frame-pointer2018090320180818
29289156951refgcc -m32 -march=i386 -Os -fomit-frame-pointer2018090320180818
29541847304refgcc -m32 -march=athlon -Os -fomit-frame-pointer2018090220180818
29596240470refgcc -m32 -Os -fomit-frame-pointer2018090220180818
29644940107refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2018090320180818
29647995304refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2018090320180818
29651066051refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2018090320180818
29670934974refgcc -m32 -march=pentium -Os -fomit-frame-pointer2018090320180818
30007029640refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2018090320180818
30009110248refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2018090320180818
30028695026refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2018090320180818
30030200699refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2018090320180818
30030231183refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2018090320180818
30368228823refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2018090220180818
30375231393refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2018090320180818
30378233581refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2018090220180818
30757210907refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2018090320180818
30761451857refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2018090320180818
30811901002refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2018090220180818
30827620917refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2018090320180818
31222897705refgcc -m32 -O -fomit-frame-pointer2018090220180818
31432434855refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2018090220180818
31433738417refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2018090220180818
31436886235refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2018090220180818
31624395625refgcc -m32 -O2 -fomit-frame-pointer2018090220180818
31671566371refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2018090220180818
31716041341refgcc -m32 -march=athlon -O -fomit-frame-pointer2018090220180818
31919852524refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2018090220180818
31929054923refgcc -m32 -march=k6 -O -fomit-frame-pointer2018090220180818
31933619491refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2018090220180818
32142959595refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2018090320180818
32449897095refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2018090320180818
32501797250refgcc -m32 -march=i386 -O -fomit-frame-pointer2018090320180818
32516660687refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2018090320180818
32519911002refgcc -m32 -march=pentium -O -fomit-frame-pointer2018090320180818
32700784552refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2018090320180818
32713540752refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2018090220180818
32747520133refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2018090320180818
32831346978refgcc -m32 -march=i486 -O -fomit-frame-pointer2018090320180818
33564841778refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2018090320180818
33569359592refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2018090320180818
59809028976refgcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer2018090320180818
60386256474refgcc -m32 -march=barcelona -O3 -fomit-frame-pointer2018090220180818
64417428329refgcc -m32 -march=k8 -O3 -fomit-frame-pointer2018090220180818
64441739279refgcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer2018090320180818
66961646602refgcc -m32 -march=barcelona -Os -fomit-frame-pointer2018090220180818
67229277492refgcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2018090220180818
67642376095refgcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer2018090320180818
69154270612refgcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer2018090320180818
69333890839refgcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2018090220180818
69504735994refgcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer2018090320180818
70569427890refgcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer2018090320180818
70645430286refgcc -m32 -march=k8 -Os -fomit-frame-pointer2018090220180818
72710383899refgcc -m32 -march=barcelona -O2 -fomit-frame-pointer2018090220180818
73633920887refgcc -m32 -march=k8 -O2 -fomit-frame-pointer2018090220180818

Test failure

Implementation: crypto_sign/sphincss128shake256/ref
Compiler: gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 2, namely:
CompilerImplementations
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer ref
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer ref

Compiler output

Implementation: crypto_sign/sphincss128shake256/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/sphincss128shake256/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/sphincss128shake256/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