Implementation notes: amd64, bolero, crypto_sign/sphincsf192shake256

Computer: bolero
Architecture: amd64
CPU ID: GenuineIntel-000406f1-bfebfbff
SUPERCOP version: 20190110
Operation: crypto_sign
Primitive: sphincsf192shake256
TimeImplementationCompilerBenchmark dateSUPERCOP version
366823112avx2clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2018091920180818
368165392avx2clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018091920180818
374532536avx2clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments2018091920180818
374536056avx2clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments2018091920180818
379658208avx2gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018091920180818
380110700avx2gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018091920180818
382396356avx2gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018091920180818
498975384avx2gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018091920180818
499182200avx2gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018091920180818
507515996avx2gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018091920180818
569106824avx2gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018091920180818
569634548avx2gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018091920180818
580857968avx2gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018091920180818
585517164avx2gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018091920180818
591027964avx2gcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018091920180818
593188452avx2gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018091920180818
606994336refclang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2018091920180818
607180356refclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018091920180818
614124332refgcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018091920180818
614135892refgcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018091920180818
623051636refgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018091920180818
756354180refclang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018091920180818
756368652refclang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018091920180818
756401844refclang -O3 -fomit-frame-pointer -Qunused-arguments2018091920180818
756437060refclang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018091920180818
766108256refgcc -m64 -march=core2 -O3 -fomit-frame-pointer2018091920180818
767970500refclang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments2018091920180818
768162752refgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018091920180818
768733104refclang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments2018091920180818
768864836refclang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments2018091920180818
769199176refclang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments2018091920180818
770058516refgcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer2018091920180818
772436288refgcc -m64 -march=corei7 -O3 -fomit-frame-pointer2018091920180818
774185380refgcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer2018091920180818
777220636refgcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018091920180818
778365180refgcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2018091920180818
787937272refgcc -funroll-loops -O3 -fomit-frame-pointer2018091920180818
788060336refgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2018091920180818
788138972refgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2018091920180818
790131988refgcc -m64 -march=barcelona -O3 -fomit-frame-pointer2018091920180818
790175872refgcc -march=barcelona -O3 -fomit-frame-pointer2018091920180818
793378740refgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2018091920180818
793395824refgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2018091920180818
794981396refgcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2018091920180818
795113432refgcc -fno-schedule-insns -O3 -fomit-frame-pointer2018091920180818
795481080refgcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2018091920180818
795584720refgcc -O3 -fomit-frame-pointer2018091920180818
796060308refgcc -m64 -O3 -fomit-frame-pointer2018091920180818
796983596refgcc -m64 -march=nocona -O3 -fomit-frame-pointer2018091920180818
797335776refgcc -march=nocona -O3 -fomit-frame-pointer2018091920180818
798203076refgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2018091920180818
798328172refgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2018091920180818
800356504refgcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018091920180818
805250584refgcc -march=k8 -O3 -fomit-frame-pointer2018091920180818
805447612refgcc -m64 -march=k8 -O3 -fomit-frame-pointer2018091920180818
805499364refgcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018091920180818
808065368refgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2018091920180818
808184500refgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2018091920180818
808569044refgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2018091920180818
808574256refgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2018091920180818
810354468refgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2018091920180818
810356360refgcc -funroll-loops -O2 -fomit-frame-pointer2018091920180818
810561040refgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2018091920180818
817996996refgcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2018091920180818
818205220refgcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2018091920180818
833101684refgcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018091920180818
833274996refgcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018091920180818
841803984refgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2018091920180818
841809460refgcc -funroll-loops -O -fomit-frame-pointer2018091920180818
841813624refgcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018091920180818
841857560refgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2018091920180818
841934356refgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2018091920180818
841996340refgcc -funroll-loops -m64 -O -fomit-frame-pointer2018091920180818
842253704refgcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018091920180818
845637316refgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018091920180818
847990584refgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2018091920180818
848797308refgcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2018091920180818
848887236refgcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2018091920180818
851496284refgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2018091920180818
863398300refgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018091920180818
924153928refgcc -O2 -fomit-frame-pointer2018091920180818
924690056refgcc -fno-schedule-insns -O2 -fomit-frame-pointer2018091920180818
924799184refgcc -m64 -O2 -fomit-frame-pointer2018091920180818
925184404refgcc -march=k8 -O2 -fomit-frame-pointer2018091920180818
930442168refgcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018091920180818
932226176refgcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer2018091920180818
933100560refgcc -m64 -march=corei7 -O2 -fomit-frame-pointer2018091920180818
933164564refgcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer2018091920180818
934263472refgcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2018091920180818
934378524refgcc -m64 -march=core2 -O2 -fomit-frame-pointer2018091920180818
941334864refgcc -m64 -march=k8 -O2 -fomit-frame-pointer2018091920180818
951518648refgcc -march=barcelona -O2 -fomit-frame-pointer2018091920180818
952106040refgcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2018091920180818
952109288refgcc -m64 -march=core2 -Os -fomit-frame-pointer2018091920180818
952133916refgcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018091920180818
952343000refgcc -m64 -march=corei7 -Os -fomit-frame-pointer2018091920180818
953651800refgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2018091920180818
955138064refgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2018091920180818
955652900refgcc -m64 -march=barcelona -Os -fomit-frame-pointer2018091920180818
955735496refgcc -march=barcelona -Os -fomit-frame-pointer2018091920180818
956702532refgcc -march=k8 -Os -fomit-frame-pointer2018091920180818
956804540refgcc -m64 -march=k8 -Os -fomit-frame-pointer2018091920180818
957248264refgcc -Os -fomit-frame-pointer2018091920180818
957300356refgcc -m64 -Os -fomit-frame-pointer2018091920180818
957330136refgcc -fno-schedule-insns -Os -fomit-frame-pointer2018091920180818
959376676refgcc -m64 -march=barcelona -O2 -fomit-frame-pointer2018091920180818
973459848refgcc -m64 -march=nocona -O2 -fomit-frame-pointer2018091920180818
977285640refgcc -march=nocona -O2 -fomit-frame-pointer2018091920180818
984944916refgcc -m64 -march=corei7-avx -Os -fomit-frame-pointer2018091920180818
987704952refgcc -m64 -march=core-avx-i -Os -fomit-frame-pointer2018091920180818
989777040refgcc -m64 -march=core2 -O -fomit-frame-pointer2018091920180818
990062748refgcc -m64 -march=core-avx-i -O -fomit-frame-pointer2018091920180818
990203992refgcc -march=nocona -O -fomit-frame-pointer2018091920180818
990549740refgcc -m64 -march=corei7 -O -fomit-frame-pointer2018091920180818
991242172refgcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2018091920180818
991600212refgcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2018091920180818
991853672refgcc -m64 -march=nocona -O -fomit-frame-pointer2018091920180818
992117616refgcc -march=nocona -Os -fomit-frame-pointer2018091920180818
992321856refgcc -m64 -march=nocona -Os -fomit-frame-pointer2018091920180818
992381644refgcc -m64 -march=corei7-avx -O -fomit-frame-pointer2018091920180818
998949140refgcc -fno-schedule-insns -O -fomit-frame-pointer2018091920180818
999601200refgcc -m64 -O -fomit-frame-pointer2018091920180818
1005280760refgcc -O -fomit-frame-pointer2018091920180818
1026185868refgcc -funroll-loops -m64 -Os -fomit-frame-pointer2018091920180818
1026781212refgcc -funroll-loops -Os -fomit-frame-pointer2018091920180818
1027423324refgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2018091920180818
1027676264refgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2018091920180818
1027923404refgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2018091920180818
1033141444refgcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2018091920180818
1033521720refgcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2018091920180818
1034680216refgcc -m64 -march=k8 -O -fomit-frame-pointer2018091920180818
1038241332refgcc -march=k8 -O -fomit-frame-pointer2018091920180818
1042784932refgcc -march=barcelona -O -fomit-frame-pointer2018091920180818
1043282284refgcc -m64 -march=barcelona -O -fomit-frame-pointer2018091920180818
2863503396refgcc -funroll-loops2018091920180818
2867556256refgcc2018091920180818
2868815188refcc2018091920180818

Compiler output

Implementation: crypto_sign/sphincsf192shake256/avx2
Compiler: cc
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/5/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/5/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: error: 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/5/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/5/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: 87, namely:
CompilerImplementations
cc avx2
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/sphincsf192shake256/avx2
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'sse4.2'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:42: note: expanded from macro 'Xor_In4'
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:44:37: note: expanded from macro 'LOAD256u'
KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'sse4.2'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:136:42: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: lanes1 = LOAD256u( curData1[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:44:37: note: expanded from macro 'LOAD256u'
KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'sse4.2'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:137:42: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: lanes2 = LOAD256u( curData2[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:44:37: note: expanded from macro 'LOAD256u'
KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'sse4.2'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:138:42: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments avx2
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx2
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx2
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx2

Compiler output

Implementation: crypto_sign/sphincsf192shake256/avx2
Compiler: clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx2'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:140:33: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+0], lanes0 ),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: expanded from macro 'XOReq256'
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:146:9: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx2'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:141:33: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+1], lanes1 ),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: expanded from macro 'XOReq256'
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:146:9: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx2'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:142:33: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+2], lanes2 ),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: expanded from macro 'XOReq256'
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:146:9: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx2'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 2, namely:
CompilerImplementations
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments avx2
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments avx2

Compiler output

Implementation: crypto_sign/sphincsf192shake256/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 /usr/lib/gcc/x86_64-linux-gnu/5/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/5/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: error: 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/5/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/5/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/5/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/5/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: error: 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/5/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/5/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/sphincsf192shake256/avx2
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer
KeccakP-1600-times4-SIMD256.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/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/5/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: error: 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/5/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/5/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: error: 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