Implementation notes: amd64, rumba5, crypto_sign/sphincss256shake256

Computer: rumba5
Architecture: amd64
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20181216
Operation: crypto_sign
Primitive: sphincss256shake256
TimeImplementationCompilerBenchmark dateSUPERCOP version
9038489888avx2gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018091320180818
9106631392avx2gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018091320180818
9145873184avx2gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018091320180818
9499992768avx2clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018091320180818
9505356928avx2clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments2018091320180818
9506037792avx2clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments2018091320180818
9517951520avx2clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2018091320180818
9977457568refgcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018091320180818
10014573408refgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018091320180818
10024901664refgcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018091320180818
10106406656refclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018091320180818
10114524064refclang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2018091320180818
11414727008refclang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018091320180818
11425835296refclang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018091320180818
11427575744refclang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2018091320180818
11467056064refgcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2018091320180818
11476493088refgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2018091320180818
11500957088refgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2018091320180818
11520157792refclang -O3 -fomit-frame-pointer -Qunused-arguments2018091320180818
11714637376refgcc -march=k8 -O3 -fomit-frame-pointer2018091320180818
11765185728refgcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer2018091320180818
11766274560refgcc -march=barcelona -O3 -fomit-frame-pointer2018091320180818
11766614208refgcc -m64 -march=barcelona -O3 -fomit-frame-pointer2018091320180818
11770491584refgcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer2018091320180818
11776853248refgcc -m64 -march=k8 -O3 -fomit-frame-pointer2018091320180818
11813941408refgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2018091320180818
11815696480refgcc -m64 -march=corei7 -O3 -fomit-frame-pointer2018091320180818
11838476736refgcc -m64 -march=core2 -O3 -fomit-frame-pointer2018091320180818
11849758432refgcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2018091320180818
11897229216refgcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018091320180818
11897472096refclang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments2018091320180818
11951951840refclang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments2018091320180818
11955415552refclang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments2018091320180818
11958131232refclang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments2018091320180818
11986716864refgcc -fno-schedule-insns -O3 -fomit-frame-pointer2018091320180818
11990734624refgcc -O3 -fomit-frame-pointer2018091320180818
11994951840avx2gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018091320180818
11995078656refgcc -m64 -O3 -fomit-frame-pointer2018091320180818
12105787360refgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2018091320180818
12108284544refgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2018091320180818
12328571296avx2gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018091320180818
12329850208refgcc -march=nocona -O3 -fomit-frame-pointer2018091320180818
12333761952refgcc -m64 -march=nocona -O3 -fomit-frame-pointer2018091320180818
12481510816avx2gcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018091320180818
12493264128avx2gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018091320180818
12539433856avx2gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018091320180818
12614357120avx2gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018091320180818
12687415424avx2gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018091320180818
12814000672refgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2018091320180818
12848324704refgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2018091320180818
12854198112refgcc -funroll-loops -O2 -fomit-frame-pointer2018091320180818
12861595488refgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2018091320180818
12881400128refgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2018091320180818
12895148640refgcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2018091320180818
12902780768refgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2018091320180818
12903597088refgcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2018091320180818
12906673312refgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2018091320180818
13314824608refgcc -funroll-loops -O -fomit-frame-pointer2018091320180818
13316381600refgcc -funroll-loops -m64 -O -fomit-frame-pointer2018091320180818
13339320480refgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2018091320180818
13378551648avx2gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018091320180818
13388044928avx2gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018091320180818
13400000768refgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2018091320180818
13402395616refgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2018091320180818
13463683136refgcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2018091320180818
13464871872refgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2018091320180818
13476364512refgcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2018091320180818
13476648576refgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2018091320180818
13507135904refgcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2018091320180818
13521102848refgcc -funroll-loops -O3 -fomit-frame-pointer2018091320180818
13602535872refgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2018091320180818
13936460096refgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018091320180818
14475294016refgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018091320180818
14542706400refgcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018091320180818
14641473184refgcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018091320180818
14708308768refgcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018091320180818
14718768960refgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018091320180818
14810812256refgcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018091320180818
15020774656refgcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018091320180818
15293463456refgcc -m64 -march=barcelona -O2 -fomit-frame-pointer2018091320180818
15349538912refgcc -march=barcelona -O2 -fomit-frame-pointer2018091320180818
15467180256refgcc -m64 -march=k8 -O2 -fomit-frame-pointer2018091320180818
15495185216refgcc -march=k8 -O2 -fomit-frame-pointer2018091320180818
15941566496refgcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018091320180818
15988644992refgcc -m64 -march=corei7 -O2 -fomit-frame-pointer2018091320180818
16023307104refgcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer2018091320180818
16028180096refgcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2018091320180818
16036868512refgcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer2018091320180818
16038360832refgcc -m64 -march=core2 -O2 -fomit-frame-pointer2018091320180818
16041969216refgcc -fno-schedule-insns -O2 -fomit-frame-pointer2018091320180818
16044746336refgcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018091320180818
16045875552refgcc -O2 -fomit-frame-pointer2018091320180818
16058948704refgcc -m64 -O2 -fomit-frame-pointer2018091320180818
16362818400refgcc -m64 -march=nocona -O2 -fomit-frame-pointer2018091320180818
16362835488refgcc -march=nocona -O2 -fomit-frame-pointer2018091320180818
16411612512refgcc -m64 -march=k8 -O -fomit-frame-pointer2018091320180818
16435303104refgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2018091320180818
16437007136refgcc -funroll-loops -m64 -Os -fomit-frame-pointer2018091320180818
16457307744refgcc -funroll-loops -Os -fomit-frame-pointer2018091320180818
16457496032refgcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2018091320180818
16470148608refgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2018091320180818
16471900768refgcc -march=k8 -O -fomit-frame-pointer2018091320180818
16475447648refgcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2018091320180818
16494889600refgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2018091320180818
16506435296refgcc -m64 -march=nocona -Os -fomit-frame-pointer2018091320180818
16507374560refgcc -march=nocona -Os -fomit-frame-pointer2018091320180818
16949581216refgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2018091320180818
16956062656refgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2018091320180818
17080339008refgcc -m64 -march=core-avx-i -O -fomit-frame-pointer2018091320180818
17092221344refgcc -m64 -march=corei7-avx -O -fomit-frame-pointer2018091320180818
17106219776refgcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2018091320180818
17121002976refgcc -m64 -march=core2 -O -fomit-frame-pointer2018091320180818
17140639840refgcc -m64 -march=corei7 -O -fomit-frame-pointer2018091320180818
17141463840refgcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2018091320180818
17173949216refgcc -march=nocona -O -fomit-frame-pointer2018091320180818
17199346592refgcc -m64 -march=nocona -O -fomit-frame-pointer2018091320180818
17605504448refgcc -m64 -O -fomit-frame-pointer2018091320180818
17606133536refgcc -fno-schedule-insns -O -fomit-frame-pointer2018091320180818
17611718880refgcc -O -fomit-frame-pointer2018091320180818
17757216096refgcc -m64 -march=corei7-avx -Os -fomit-frame-pointer2018091320180818
17777664000refgcc -m64 -march=core-avx-i -Os -fomit-frame-pointer2018091320180818
17781634368refgcc -march=barcelona -O -fomit-frame-pointer2018091320180818
17797044416refgcc -m64 -march=barcelona -O -fomit-frame-pointer2018091320180818
18452172256refgcc -fno-schedule-insns -Os -fomit-frame-pointer2018091320180818
18456054496refgcc -m64 -Os -fomit-frame-pointer2018091320180818
18468876224refgcc -m64 -march=barcelona -Os -fomit-frame-pointer2018091320180818
18474107808refgcc -Os -fomit-frame-pointer2018091320180818
18491360544refgcc -m64 -march=k8 -Os -fomit-frame-pointer2018091320180818
18538828032refgcc -march=k8 -Os -fomit-frame-pointer2018091320180818
18544008640refgcc -m64 -march=core2 -Os -fomit-frame-pointer2018091320180818
18558050144refgcc -m64 -march=corei7 -Os -fomit-frame-pointer2018091320180818
18559723840refgcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2018091320180818
18603675840refgcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018091320180818
20011425856refgcc -march=barcelona -Os -fomit-frame-pointer2018091320180818
55761639456refgcc2018091320180818
55796035136refgcc -funroll-loops2018091320180818
55806979968refcc2018091320180818

Compiler output

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