Implementation notes: x86, kizomba, crypto_sign/sphincss192shake256

Computer: kizomba
Architecture: x86
CPU ID: GenuineIntel-000906e9-bfebfbff
SUPERCOP version: 20181216
Operation: crypto_sign
Primitive: sphincss192shake256
TimeImplementationCompilerBenchmark dateSUPERCOP version
10001594565avx2gcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2018092120180818
10868713159avx2gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2018092120180818
15553194069avx2gcc -m32 -march=core-avx2 -O -fomit-frame-pointer2018092120180818
16435737373avx2gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2018092120180818
16619282985avx2gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2018092120180818
17933311066avx2gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2018092120180818
20200363125avx2gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer2018092120180818
37197039811avx2gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer2018092120180818
37321902476refgcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018092120180818
37322763383refgcc -m32 -march=corei7 -O3 -fomit-frame-pointer2018092120180818
37325094581refgcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer2018092120180818
37761731139refgcc -m32 -march=core2 -O3 -fomit-frame-pointer2018092120180818
38130840758refgcc -m32 -march=core-avx2 -O3 -fomit-frame-pointer2018092120180818
38152244363refgcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer2018092220180818
38901487208refgcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer2018092120180818
39048972155refgcc -m32 -march=pentium-m -O3 -fomit-frame-pointer2018092120180818
41976733922refgcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer2018092220180818
42454920702refgcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer2018092120180818
42463654464refgcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer2018092120180818
42517532184refgcc -m32 -march=pentium4 -O3 -fomit-frame-pointer2018092120180818
42758861807refgcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer2018092120180818
42885279424refgcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer2018092120180818
42885293238refgcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer2018092120180818
43227169959refgcc -m32 -march=prescott -O3 -fomit-frame-pointer2018092120180818
43227324185refgcc -m32 -march=nocona -O3 -fomit-frame-pointer2018092120180818
43242468629refgcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer2018092220180818
43242925120refgcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer2018092220180818
43813497300refgcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer2018092220180818
44046307759refgcc -m32 -march=corei7-avx -Os -fomit-frame-pointer2018092120180818
44058676416refgcc -m32 -march=core-avx-i -Os -fomit-frame-pointer2018092120180818
44075030945refgcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer2018092120180818
44092710746refgcc -m32 -march=corei7 -O2 -fomit-frame-pointer2018092120180818
44096880568refgcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018092120180818
44231676323refgcc -m32 -march=core-avx2 -Os -fomit-frame-pointer2018092120180818
44492575206refgcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018092120180818
44492773318refgcc -m32 -march=corei7 -Os -fomit-frame-pointer2018092120180818
44495930639refgcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer2018092120180818
45865467833refgcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer2018092220180818
45874616439refgcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer2018092220180818
45895107585refgcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer2018092220180818
46484095286refgcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer2018092220180818
46508389696refgcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer2018092220180818
46524147954refgcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer2018092220180818
46679049100refgcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer2018092220180818
46681487768refgcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer2018092220180818
46790943080refgcc -m32 -march=core2 -Os -fomit-frame-pointer2018092120180818
46820861748refgcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer2018092220180818
47042808117refgcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer2018092220180818
47069492582refgcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer2018092220180818
47071702774refgcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer2018092220180818
47127481282refgcc -m32 -march=pentium-m -Os -fomit-frame-pointer2018092120180818
47137711824refgcc -m32 -march=prescott -Os -fomit-frame-pointer2018092120180818
47139480462refgcc -m32 -march=pentium4 -Os -fomit-frame-pointer2018092120180818
47149793861refgcc -m32 -march=nocona -Os -fomit-frame-pointer2018092120180818
47172594986refgcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer2018092220180818
47308563588refgcc -m32 -march=core2 -O2 -fomit-frame-pointer2018092120180818
48473055851refgcc -m32 -march=native -mtune=native -O -fomit-frame-pointer2018092120180818
48795620337refgcc -m32 -march=core-avx2 -O -fomit-frame-pointer2018092120180818
49051690730refgcc -m32 -march=pentium-m -O2 -fomit-frame-pointer2018092120180818
51688471087refgcc -m32 -march=prescott -O2 -fomit-frame-pointer2018092120180818
51690052131refgcc -m32 -march=nocona -O2 -fomit-frame-pointer2018092120180818
51809540665refgcc -m32 -march=pentium4 -O -fomit-frame-pointer2018092120180818
51958959354refgcc -m32 -march=barcelona -O -fomit-frame-pointer2018092120180818
52120644952refgcc -m32 -march=k8 -O -fomit-frame-pointer2018092120180818
52506750960refgcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer2018092220180818
52511162105refgcc -m32 -march=athlon -O3 -fomit-frame-pointer2018092120180818
52536105339refgcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer2018092220180818
52546788807refgcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer2018092220180818
52640213210refgcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer2018092120180818
52642715482refgcc -m32 -march=core2 -O -fomit-frame-pointer2018092120180818
52644109781refgcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer2018092120180818
52647446377refgcc -m32 -march=pentium4 -O2 -fomit-frame-pointer2018092120180818
52933320954refgcc -m32 -march=pentium-m -O -fomit-frame-pointer2018092120180818
53036365135refgcc -m32 -march=prescott -O -fomit-frame-pointer2018092120180818
53055245293refgcc -m32 -march=nocona -O -fomit-frame-pointer2018092120180818
53104605871refgcc -m32 -O3 -fomit-frame-pointer2018092120180818
53306018391refgcc -m32 -march=k6-2 -O3 -fomit-frame-pointer2018092120180818
53320224800refgcc -m32 -march=k6-3 -O3 -fomit-frame-pointer2018092120180818
53331325189refgcc -funroll-loops -m32 -O3 -fomit-frame-pointer2018092220180818
53453927125refgcc -m32 -march=core-avx-i -O -fomit-frame-pointer2018092120180818
53460484382refgcc -m32 -march=corei7 -O -fomit-frame-pointer2018092120180818
53470145365refgcc -m32 -march=corei7-avx -O -fomit-frame-pointer2018092120180818
53584690909refgcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer2018092220180818
53929670768refgcc -m32 -march=k6 -O3 -fomit-frame-pointer2018092120180818
55228960117refgcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer2018092320180818
55395719229refgcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer2018092320180818
55663741349refgcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer2018092220180818
55670937304refgcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer2018092220180818
55755483867refgcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer2018092220180818
56031205943refgcc -m32 -march=i386 -O3 -fomit-frame-pointer2018092220180818
56522586154refgcc -m32 -march=i486 -O3 -fomit-frame-pointer2018092220180818
56739515502refgcc -funroll-loops -m32 -O -fomit-frame-pointer2018092220180818
56862416911refgcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer2018092220180818
56863912270refgcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer2018092220180818
56866424363refgcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer2018092220180818
57036580445refgcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer2018092220180818
57047406411refgcc -funroll-loops -m32 -O2 -fomit-frame-pointer2018092220180818
57090560455refgcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer2018092220180818
57105945310refgcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer2018092220180818
57109071070refgcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer2018092220180818
57205199849refgcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer2018092220180818
57213137365refgcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer2018092220180818
57213784478refgcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer2018092220180818
57218204474refgcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer2018092220180818
57908871982refgcc -m32 -march=pentium3 -O3 -fomit-frame-pointer2018092120180818
58059363682refgcc -m32 -march=pentium2 -O3 -fomit-frame-pointer2018092220180818
58063248258refgcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer2018092220180818
58466042296refgcc -m32 -march=k6 -Os -fomit-frame-pointer2018092120180818
58481082675refgcc -m32 -march=k6-3 -Os -fomit-frame-pointer2018092120180818
58496644889refgcc -m32 -march=k6-2 -Os -fomit-frame-pointer2018092120180818
58856600827refgcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer2018092320180818
58866456195refgcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2018092220180818
58950027704refgcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer2018092220180818
58951229464refgcc -funroll-loops -m32 -Os -fomit-frame-pointer2018092220180818
59123151233refgcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer2018092320180818
59130417899refgcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer2018092320180818
59205131855refgcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer2018092320180818
59230344738refgcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer2018092320180818
59232989639refgcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer2018092320180818
59311026583refgcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer2018092220180818
59313921322refgcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer2018092220180818
59330315389refgcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer2018092220180818
59467643867refgcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer2018092320180818
59687093895refgcc -m32 -march=i486 -Os -fomit-frame-pointer2018092220180818
59694644597refgcc -m32 -march=i386 -Os -fomit-frame-pointer2018092220180818
60021031290refgcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer2018092320180818
60070955014refgcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer2018092320180818
60268640335refgcc -m32 -march=pentium -Os -fomit-frame-pointer2018092220180818
60289938651refgcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer2018092220180818
60355999528refgcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer2018092220180818
60361047411refgcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer2018092220180818
60363582437refgcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer2018092220180818
60491444300refgcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer2018092320180818
60493591224refgcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer2018092320180818
60941604905refgcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer2018092220180818
60953059726refgcc -m32 -march=pentium -O3 -fomit-frame-pointer2018092220180818
61695854438refgcc -m32 -march=athlon -Os -fomit-frame-pointer2018092120180818
61816274064refgcc -m32 -Os -fomit-frame-pointer2018092120180818
61863898047refgcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer2018092220180818
61866772335refgcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer2018092220180818
61870718824refgcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer2018092220180818
62411297863refgcc -m32 -march=pentiumpro -Os -fomit-frame-pointer2018092220180818
62424814022refgcc -m32 -march=pentium2 -Os -fomit-frame-pointer2018092220180818
62433112137refgcc -m32 -march=pentium3 -Os -fomit-frame-pointer2018092220180818
62674097071refgcc -m32 -march=pentium3 -O -fomit-frame-pointer2018092220180818
62675691300refgcc -m32 -march=pentium2 -O -fomit-frame-pointer2018092220180818
62682175746refgcc -m32 -march=pentiumpro -O -fomit-frame-pointer2018092220180818
62985161994refgcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2018092320180818
62993896500refgcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer2018092320180818
63521452271refgcc -m32 -O -fomit-frame-pointer2018092120180818
63867167460refgcc -m32 -O2 -fomit-frame-pointer2018092120180818
64050708929refgcc -m32 -march=k6-3 -O2 -fomit-frame-pointer2018092120180818
64071823093refgcc -m32 -march=k6-2 -O2 -fomit-frame-pointer2018092120180818
64080424594refgcc -m32 -march=k6 -O2 -fomit-frame-pointer2018092120180818
64179154724refgcc -m32 -march=athlon -O2 -fomit-frame-pointer2018092120180818
64580430264refgcc -m32 -march=athlon -O -fomit-frame-pointer2018092120180818
64873328805refgcc -m32 -march=k6 -O -fomit-frame-pointer2018092120180818
64877767159refgcc -m32 -march=k6-2 -O -fomit-frame-pointer2018092120180818
64891848089refgcc -m32 -march=k6-3 -O -fomit-frame-pointer2018092120180818
65459085486refgcc -m32 -march=i386 -O2 -fomit-frame-pointer2018092220180818
65547002322refgcc -m32 -march=i486 -O2 -fomit-frame-pointer2018092220180818
66041925914refgcc -m32 -march=pentium -O -fomit-frame-pointer2018092220180818
66046650534refgcc -m32 -march=pentium-mmx -O -fomit-frame-pointer2018092220180818
66332400545refgcc -m32 -march=i386 -O -fomit-frame-pointer2018092220180818
66891080968refgcc -m32 -march=i486 -O -fomit-frame-pointer2018092220180818
67093165986refgcc -m32 -march=pentium3 -O2 -fomit-frame-pointer2018092220180818
67095615639refgcc -m32 -march=pentium2 -O2 -fomit-frame-pointer2018092220180818
67125852280refgcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer2018092220180818
68883397746refgcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer2018092220180818
68893918705refgcc -m32 -march=pentium -O2 -fomit-frame-pointer2018092220180818

Test failure

Implementation: crypto_sign/sphincss192shake256/ref
Compiler: gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer
error 142
Alarm clock

Number of similar (compiler,implementation) pairs: 11, namely:
CompilerImplementations
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer ref
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer ref
gcc -m32 -march=k8 -O2 -fomit-frame-pointer ref
gcc -m32 -march=k8 -O3 -fomit-frame-pointer ref
gcc -m32 -march=k8 -Os -fomit-frame-pointer ref
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer ref
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer ref

Test failure

Implementation: crypto_sign/sphincss192shake256/ref
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer
error 142
Alarm clock
error 142
Alarm clock

Number of similar (compiler,implementation) pairs: 3, namely:
CompilerImplementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer ref
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer ref
gcc -m32 -march=barcelona -Os -fomit-frame-pointer ref

Compiler output

Implementation: crypto_sign/sphincss192shake256/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/sphincss192shake256/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/sphincss192shake256/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