Implementation notes: amd64, bolero, crypto_kem/newhope1024cca

Computer: bolero
Architecture: amd64
CPU ID: GenuineIntel-000406f1-bfebfbff
SUPERCOP version: 20181209
Operation: crypto_kem
Primitive: newhope1024cca
TimeImplementationCompilerBenchmark dateSUPERCOP version
417448avx2clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018102020180818
418164avx2gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018102020180818
419632avx2clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2018102020180818
422984avx2gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018102020180818
423016avx2gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018102020180818
433240avx2clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments2018102020180818
433384avx2clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments2018102020180818
493420avx2gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018102020180818
502308avx2gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018102020180818
504408avx2gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018102020180818
541176avx2gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018102020180818
541260avx2gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018102020180818
541852avx2gcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018102020180818
566884avx2gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018102020180818
575028avx2gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018102020180818
576576avx2gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018102020180818
828972refgcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018102020180818
828976refgcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018102020180818
866548refclang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2018102020180818
868744refclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018102020180818
900128refgcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2018102020180818
900288refgcc -m64 -march=corei7 -O3 -fomit-frame-pointer2018102020180818
918064refgcc -m64 -march=core2 -O3 -fomit-frame-pointer2018102020180818
920276refgcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer2018102020180818
920844refgcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2018102020180818
921148refgcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2018102020180818
922400refgcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer2018102020180818
934612refgcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018102020180818
939620refclang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments2018102020180818
940304refclang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments2018102020180818
941632refgcc -O3 -fomit-frame-pointer2018102020180818
942604refgcc -fno-schedule-insns -O3 -fomit-frame-pointer2018102020180818
943504refgcc -m64 -O3 -fomit-frame-pointer2018102020180818
945264refgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2018102020180818
945880refgcc -m64 -march=k8 -O3 -fomit-frame-pointer2018102020180818
946000refgcc -funroll-loops -O3 -fomit-frame-pointer2018102020180818
946736refclang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments2018102020180818
947464refgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2018102020180818
952324refgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2018102020180818
952488refgcc -m64 -march=barcelona -O3 -fomit-frame-pointer2018102020180818
953000refclang -O3 -fomit-frame-pointer -Qunused-arguments2018102020180818
954296refclang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments2018102020180818
958300refgcc -march=barcelona -O3 -fomit-frame-pointer2018102020180818
959656refgcc -march=k8 -O3 -fomit-frame-pointer2018102020180818
960048refclang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018102020180818
960460refclang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018102020180818
961864refgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2018102020180818
963788refclang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018102020180818
979920refgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2018102020180818
987356refgcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2018102020180818
988588refgcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2018102020180818
990948refgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2018102020180818
1001008refgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2018102020180818
1009456refgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018102020180818
1013168refgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2018102020180818
1013984refgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2018102020180818
1016480refgcc -funroll-loops -O2 -fomit-frame-pointer2018102020180818
1018956refgcc -m64 -march=nocona -O3 -fomit-frame-pointer2018102020180818
1023124refgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2018102020180818
1023488refgcc -march=nocona -O3 -fomit-frame-pointer2018102020180818
1065576refgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2018102020180818
1066468refgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2018102020180818
1115752refgcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018102020180818
1117976refgcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018102020180818
1143788refgcc -funroll-loops -m64 -O -fomit-frame-pointer2018102020180818
1144988refgcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2018102020180818
1145020refgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2018102020180818
1148820refgcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2018102020180818
1151992refgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2018102020180818
1154308refgcc -funroll-loops -O -fomit-frame-pointer2018102020180818
1164864refgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2018102020180818
1199904refgcc -m64 -march=barcelona -O2 -fomit-frame-pointer2018102020180818
1200948refgcc -march=barcelona -O2 -fomit-frame-pointer2018102020180818
1201228refgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018102020180818
1202484refgcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer2018102020180818
1203732refgcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer2018102020180818
1203952refgcc -m64 -O2 -fomit-frame-pointer2018102020180818
1212128refgcc -m64 -march=corei7 -O2 -fomit-frame-pointer2018102020180818
1217204refgcc -O2 -fomit-frame-pointer2018102020180818
1221640refgcc -fno-schedule-insns -O2 -fomit-frame-pointer2018102020180818
1230912refgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018102020180818
1233484refgcc -m64 -march=k8 -O2 -fomit-frame-pointer2018102020180818
1233984refgcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018102020180818
1236604refgcc -m64 -march=core2 -O2 -fomit-frame-pointer2018102020180818
1238012refgcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2018102020180818
1238108refgcc -march=k8 -O2 -fomit-frame-pointer2018102020180818
1262416refgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2018102020180818
1263496refgcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018102020180818
1263900refgcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018102020180818
1269268refgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2018102020180818
1295940refgcc -m64 -march=nocona -O2 -fomit-frame-pointer2018102020180818
1312856refgcc -march=nocona -O2 -fomit-frame-pointer2018102020180818
1341316refgcc -m64 -O -fomit-frame-pointer2018102020180818
1341424refgcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2018102020180818
1343864refgcc -m64 -march=corei7 -O -fomit-frame-pointer2018102020180818
1344248refgcc -O -fomit-frame-pointer2018102020180818
1344276refgcc -m64 -march=core-avx-i -O -fomit-frame-pointer2018102020180818
1344452refgcc -fno-schedule-insns -O -fomit-frame-pointer2018102020180818
1348152refgcc -m64 -march=corei7-avx -O -fomit-frame-pointer2018102020180818
1353528refgcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2018102020180818
1355180refgcc -m64 -march=core2 -O -fomit-frame-pointer2018102020180818
1364636refgcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018102020180818
1373164refgcc -march=barcelona -O -fomit-frame-pointer2018102020180818
1374688refgcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018102020180818
1376864refgcc -m64 -march=barcelona -O -fomit-frame-pointer2018102020180818
1380348refgcc -march=k8 -O -fomit-frame-pointer2018102020180818
1381032refgcc -m64 -march=k8 -O -fomit-frame-pointer2018102020180818
1428104refgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018102020180818
1431924refgcc -m64 -march=core-avx-i -Os -fomit-frame-pointer2018102020180818
1435948refgcc -m64 -march=corei7-avx -Os -fomit-frame-pointer2018102020180818
1478472refgcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2018102020180818
1478888refgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2018102020180818
1480412refgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2018102020180818
1480692refgcc -funroll-loops -m64 -Os -fomit-frame-pointer2018102020180818
1481560refgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2018102020180818
1483020refgcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018102020180818
1484504refgcc -m64 -march=corei7 -Os -fomit-frame-pointer2018102020180818
1484560refgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2018102020180818
1485160refgcc -march=k8 -Os -fomit-frame-pointer2018102020180818
1487576refgcc -Os -fomit-frame-pointer2018102020180818
1487696refgcc -m64 -Os -fomit-frame-pointer2018102020180818
1488568refgcc -march=barcelona -Os -fomit-frame-pointer2018102020180818
1488624refgcc -funroll-loops -Os -fomit-frame-pointer2018102020180818
1488652refgcc -m64 -march=k8 -Os -fomit-frame-pointer2018102020180818
1489700refgcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2018102020180818
1491716refgcc -m64 -march=core2 -Os -fomit-frame-pointer2018102020180818
1491836refgcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2018102020180818
1493952refgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2018102020180818
1494816refgcc -fno-schedule-insns -Os -fomit-frame-pointer2018102020180818
1497724refgcc -m64 -march=barcelona -Os -fomit-frame-pointer2018102020180818
1497736refgcc -m64 -march=nocona -O -fomit-frame-pointer2018102020180818
1499328refgcc -m64 -march=nocona -Os -fomit-frame-pointer2018102020180818
1516448refgcc -march=nocona -O -fomit-frame-pointer2018102020180818
1534184refgcc -march=nocona -Os -fomit-frame-pointer2018102020180818
4163784refgcc -funroll-loops2018102020180818
4164608refgcc2018102020180818
4181320refcc2018102020180818

Compiler output

Implementation: crypto_kem/newhope1024cca/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_kem/newhope1024cca/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_kem/newhope1024cca/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_kem/newhope1024cca/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_kem/newhope1024cca/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