Implementation notes: amd64, genji262, crypto_sign/sphincss256shake256

Computer: genji262
Architecture: amd64
CPU ID: AuthenticAMD-00800f12-178bfbff
SUPERCOP version: 20180818
Operation: crypto_sign
Primitive: sphincss256shake256
TimeImplementationCompilerBenchmark dateSUPERCOP version
7548628648avx2gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018082120180818
7800844766avx2gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018082120180818
7822465596avx2gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018082120180818
8588528982refgcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018082120180818
8763913466refgcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018082120180818
8778875116refgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018082120180818
9648572164refgcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer2018082120180818
9694948648refgcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018082120180818
9776758904refgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2018082120180818
9781210472refgcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer2018082120180818
9786748378refgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2018082120180818
9812979462refgcc -m64 -march=corei7 -O3 -fomit-frame-pointer2018082120180818
9813900118refgcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2018082120180818
9835155924refgcc -m64 -march=core2 -O3 -fomit-frame-pointer2018082120180818
9840627588refgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2018082120180818
9864463510refgcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2018082120180818
9937333780avx2gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018082120180818
9993129652avx2gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018082120180818
10006465964refgcc -m64 -march=barcelona -O3 -fomit-frame-pointer2018082120180818
10013340942avx2gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018082120180818
10014885738refgcc -march=k8 -O3 -fomit-frame-pointer2018082120180818
10032016654refgcc -fno-schedule-insns -O3 -fomit-frame-pointer2018082120180818
10074487104refgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2018082120180818
10083210060refgcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2018082120180818
10097395924refgcc -m64 -O3 -fomit-frame-pointer2018082120180818
10132934680refgcc -m64 -march=k8 -O3 -fomit-frame-pointer2018082120180818
10133063534refgcc -funroll-loops -O3 -fomit-frame-pointer2018082120180818
10144723600refgcc -O3 -fomit-frame-pointer2018082120180818
10145080836refgcc -march=barcelona -O3 -fomit-frame-pointer2018082120180818
10154021350refgcc -march=nocona -O3 -fomit-frame-pointer2018082120180818
10176410618refgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2018082120180818
10187313620refgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2018082120180818
10212586912refgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2018082120180818
10232782978refgcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2018082120180818
10287332110refgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2018082120180818
10299920818refgcc -m64 -march=nocona -O3 -fomit-frame-pointer2018082120180818
10322819210avx2gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018082120180818
10440594890refgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2018082120180818
10490150220refgcc -funroll-loops -O2 -fomit-frame-pointer2018082120180818
10501057182refgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2018082120180818
10519631826refgcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2018082120180818
10532521648refgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2018082120180818
10545968730avx2gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018082120180818
10565285368refgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2018082120180818
10641848030refgcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2018082120180818
10670541332avx2gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018082120180818
10687661424refgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2018082120180818
10735551266refgcc -funroll-loops -m64 -O -fomit-frame-pointer2018082120180818
10747625636refgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2018082120180818
10874517962avx2gcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018082120180818
10901708114refgcc -funroll-loops -O -fomit-frame-pointer2018082120180818
10949586406refgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2018082120180818
10959075732avx2gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018082120180818
10963468296refgcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2018082120180818
10971606580refgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2018082120180818
10992439172refgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2018082120180818
11045197482avx2gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018082120180818
11944992290refgcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018082120180818
12055734218refgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018082120180818
12286177948refgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018082120180818
12398183028refgcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018082120180818
12448525760refgcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018082120180818
12721269858refgcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018082120180818
12813698128refgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018082120180818
12994364702refgcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018082120180818
13131865252refgcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018082120180818
13292940870refgcc -fno-schedule-insns -O -fomit-frame-pointer2018082120180818
13411343022refgcc -m64 -O2 -fomit-frame-pointer2018082120180818
13459049846refgcc -m64 -O -fomit-frame-pointer2018082120180818
13467677410refgcc -fno-schedule-insns -O2 -fomit-frame-pointer2018082120180818
13487693340refgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2018082120180818
13499587772refgcc -O -fomit-frame-pointer2018082120180818
13500679236refgcc -m64 -march=corei7-avx -O -fomit-frame-pointer2018082120180818
13502202472refgcc -O2 -fomit-frame-pointer2018082120180818
13510661450refgcc -funroll-loops -Os -fomit-frame-pointer2018082120180818
13515549256refgcc -m64 -march=core-avx-i -O -fomit-frame-pointer2018082120180818
13528276806refgcc -m64 -march=barcelona -O2 -fomit-frame-pointer2018082120180818
13556445518refgcc -m64 -march=k8 -O -fomit-frame-pointer2018082120180818
13621306534refgcc -funroll-loops -m64 -Os -fomit-frame-pointer2018082120180818
13638340782refgcc -m64 -march=barcelona -O -fomit-frame-pointer2018082120180818
13674161490refgcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2018082120180818
13681232488refgcc -m64 -march=corei7 -O2 -fomit-frame-pointer2018082120180818
13727618388refgcc -march=k8 -O -fomit-frame-pointer2018082120180818
13735158316refgcc -march=barcelona -O2 -fomit-frame-pointer2018082120180818
13841403752refgcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2018082120180818
13844537916refgcc -march=k8 -Os -fomit-frame-pointer2018082120180818
13855314616refgcc -march=barcelona -O -fomit-frame-pointer2018082120180818
13872539296refgcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018082120180818
13878898616refgcc -m64 -march=k8 -Os -fomit-frame-pointer2018082120180818
13890396432refgcc -m64 -march=barcelona -Os -fomit-frame-pointer2018082120180818
13893668470refgcc -m64 -march=core2 -Os -fomit-frame-pointer2018082120180818
13903555468refgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2018082120180818
13919710024refgcc -march=barcelona -Os -fomit-frame-pointer2018082120180818
13940681502refgcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2018082120180818
13957130748refgcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2018082120180818
14001919624refgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2018082120180818
14015389014refgcc -m64 -march=core2 -O2 -fomit-frame-pointer2018082120180818
14021378492refgcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018082120180818
14092792934refgcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer2018082120180818
14119122424refgcc -m64 -march=k8 -O2 -fomit-frame-pointer2018082120180818
14132356414refgcc -march=k8 -O2 -fomit-frame-pointer2018082120180818
14213747372refgcc -m64 -march=nocona -O -fomit-frame-pointer2018082120180818
14267793254refgcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2018082120180818
14318482354refgcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer2018082120180818
14326940848refgcc -m64 -march=nocona -Os -fomit-frame-pointer2018082120180818
14362907328refgcc -march=nocona -O -fomit-frame-pointer2018082120180818
14393235538refgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2018082120180818
14403281838refgcc -m64 -march=corei7 -O -fomit-frame-pointer2018082120180818
14411117314refgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2018082120180818
14428240530refgcc -march=nocona -Os -fomit-frame-pointer2018082120180818
14456690864refgcc -m64 -march=core2 -O -fomit-frame-pointer2018082120180818
14465918434refgcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2018082120180818
14518242596refgcc -m64 -march=core-avx-i -Os -fomit-frame-pointer2018082120180818
14553359700refgcc -m64 -march=corei7-avx -Os -fomit-frame-pointer2018082120180818
14926810360refgcc -m64 -march=corei7 -Os -fomit-frame-pointer2018082120180818
14966115142refgcc -m64 -Os -fomit-frame-pointer2018082120180818
14972907070refgcc -fno-schedule-insns -Os -fomit-frame-pointer2018082120180818
14999249408refgcc -m64 -march=nocona -O2 -fomit-frame-pointer2018082120180818
15033177280refgcc -march=nocona -O2 -fomit-frame-pointer2018082120180818
15145340628refgcc -Os -fomit-frame-pointer2018082120180818
48971026280refcc2018082120180818
49030405468refgcc2018082120180818
49245574400refgcc -funroll-loops2018082120180818

Compiler output

Implementation: crypto_sign/sphincss256shake256/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/sphincss256shake256/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/sphincss256shake256/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/sphincss256shake256/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