Implementation notes: amd64, genji262, crypto_sign/sphincsf128shake256

Computer: genji262
Architecture: amd64
CPU ID: AuthenticAMD-00800f12-178bfbff
SUPERCOP version: 20180818
Operation: crypto_sign
Primitive: sphincsf128shake256
TimeImplementationCompilerBenchmark dateSUPERCOP version
337120960avx2gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018082020180818
341524678avx2gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018082020180818
341693506avx2gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018082020180818
371517806refgcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018082020180818
371749752refgcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018082020180818
376176306refgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018082020180818
416330398refgcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2018082020180818
416918766refgcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer2018082020180818
417546866refgcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer2018082020180818
417939566refgcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018082020180818
418289674refgcc -m64 -march=corei7 -O3 -fomit-frame-pointer2018082020180818
421987280refgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2018082020180818
422838878avx2gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018082020180818
423167756avx2gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018082020180818
424989158refgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2018082020180818
425010520refgcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2018082020180818
426088036refgcc -m64 -march=core2 -O3 -fomit-frame-pointer2018082020180818
427077530refgcc -funroll-loops -O3 -fomit-frame-pointer2018082020180818
431143724refgcc -march=barcelona -O3 -fomit-frame-pointer2018082020180818
431539108refgcc -m64 -march=barcelona -O3 -fomit-frame-pointer2018082020180818
431901712refgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2018082020180818
432213914refgcc -march=k8 -O3 -fomit-frame-pointer2018082020180818
432442582refgcc -m64 -march=k8 -O3 -fomit-frame-pointer2018082020180818
432598694refgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2018082020180818
432728318refgcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2018082020180818
433594392refgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2018082020180818
433923776refgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2018082020180818
434647598refgcc -O3 -fomit-frame-pointer2018082020180818
435555538refgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2018082020180818
436356382refgcc -m64 -O3 -fomit-frame-pointer2018082020180818
436833958refgcc -funroll-loops -O2 -fomit-frame-pointer2018082020180818
438219078refgcc -march=nocona -O3 -fomit-frame-pointer2018082020180818
438661102refgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2018082020180818
440517198refgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2018082020180818
440933702refgcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2018082020180818
441580568avx2gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018082020180818
444158132avx2gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018082020180818
444368606refgcc -m64 -march=nocona -O3 -fomit-frame-pointer2018082020180818
444407458refgcc -fno-schedule-insns -O3 -fomit-frame-pointer2018082020180818
445935006refgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2018082020180818
447741778refgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2018082020180818
448964538avx2gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018082020180818
449171404refgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2018082020180818
449904576refgcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2018082020180818
450063702refgcc -funroll-loops -O -fomit-frame-pointer2018082020180818
450248612refgcc -funroll-loops -m64 -O -fomit-frame-pointer2018082020180818
451977790refgcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2018082020180818
452561494refgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2018082020180818
455587198refgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2018082020180818
460249460refgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2018082020180818
463237280refgcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2018082020180818
465493160avx2gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018082020180818
465519824avx2gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018082020180818
466045184refgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2018082020180818
469372266avx2gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018082020180818
472335424refgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2018082020180818
496971618refgcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018082020180818
497830630avx2gcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018082020180818
508553782refgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018082020180818
518880846refgcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018082020180818
523001138refgcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018082020180818
524543426refgcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018082020180818
544065104refgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018082020180818
552540472refgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2018082020180818
554817604refgcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018082020180818
555665110refgcc -funroll-loops -m64 -Os -fomit-frame-pointer2018082020180818
556123040refgcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018082020180818
559778736refgcc -m64 -march=core2 -Os -fomit-frame-pointer2018082020180818
560229010refgcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018082020180818
561377058refgcc -funroll-loops -Os -fomit-frame-pointer2018082020180818
561597652refgcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2018082020180818
562708410refgcc -march=k8 -Os -fomit-frame-pointer2018082020180818
564053732refgcc -m64 -march=k8 -Os -fomit-frame-pointer2018082020180818
565235308refgcc -fno-schedule-insns -O -fomit-frame-pointer2018082020180818
565736820refgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018082020180818
566180472refgcc -Os -fomit-frame-pointer2018082020180818
566506688refgcc -m64 -O -fomit-frame-pointer2018082020180818
566691422refgcc -O -fomit-frame-pointer2018082020180818
567080030refgcc -m64 -march=corei7 -Os -fomit-frame-pointer2018082020180818
569043266refgcc -march=k8 -O -fomit-frame-pointer2018082020180818
569078136refgcc -m64 -march=barcelona -Os -fomit-frame-pointer2018082020180818
570496212refgcc -m64 -march=k8 -O -fomit-frame-pointer2018082020180818
570845440refgcc -m64 -march=barcelona -O2 -fomit-frame-pointer2018082020180818
572530156refgcc -fno-schedule-insns -Os -fomit-frame-pointer2018082020180818
574180068refgcc -march=barcelona -O2 -fomit-frame-pointer2018082020180818
574322408refgcc -fno-schedule-insns -O2 -fomit-frame-pointer2018082020180818
574324278refgcc -m64 -Os -fomit-frame-pointer2018082020180818
574715658refgcc -march=barcelona -O -fomit-frame-pointer2018082020180818
574864664refgcc -march=barcelona -Os -fomit-frame-pointer2018082020180818
576149904refgcc -m64 -march=barcelona -O -fomit-frame-pointer2018082020180818
578114504refgcc -m64 -O2 -fomit-frame-pointer2018082020180818
578399668refgcc -O2 -fomit-frame-pointer2018082020180818
581345974refgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2018082020180818
582285308refgcc -march=nocona -Os -fomit-frame-pointer2018082020180818
582501876refgcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer2018082020180818
582931206refgcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018082020180818
583373472refgcc -m64 -march=nocona -Os -fomit-frame-pointer2018082020180818
584896290refgcc -m64 -march=core2 -O2 -fomit-frame-pointer2018082020180818
584922404refgcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer2018082020180818
585667434refgcc -m64 -march=corei7 -O2 -fomit-frame-pointer2018082020180818
585701600refgcc -march=k8 -O2 -fomit-frame-pointer2018082020180818
585789094refgcc -m64 -march=k8 -O2 -fomit-frame-pointer2018082020180818
586441020refgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2018082020180818
589742582refgcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2018082020180818
590760566refgcc -m64 -march=corei7 -O -fomit-frame-pointer2018082020180818
593267796refgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2018082020180818
596912668refgcc -march=nocona -O -fomit-frame-pointer2018082020180818
597100746refgcc -m64 -march=corei7-avx -Os -fomit-frame-pointer2018082020180818
597127476refgcc -m64 -march=corei7-avx -O -fomit-frame-pointer2018082020180818
597524972refgcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2018082020180818
597667488refgcc -m64 -march=nocona -O -fomit-frame-pointer2018082020180818
598391640refgcc -m64 -march=core-avx-i -O -fomit-frame-pointer2018082020180818
598775694refgcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2018082020180818
598792832refgcc -m64 -march=core-avx-i -Os -fomit-frame-pointer2018082020180818
599469948refgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2018082020180818
599796406refgcc -m64 -march=core2 -O -fomit-frame-pointer2018082020180818
600971734refgcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2018082020180818
607062346refgcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2018082020180818
619255604refgcc -m64 -march=nocona -O2 -fomit-frame-pointer2018082020180818
622055192refgcc -march=nocona -O2 -fomit-frame-pointer2018082020180818
2097649752refgcc2018082020180818
2097892236refcc2018082020180818
2099767736refgcc -funroll-loops2018082020180818

Compiler output

Implementation: crypto_sign/sphincsf128shake256/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/sphincsf128shake256/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/sphincsf128shake256/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/sphincsf128shake256/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