Implementation notes: amd64, manny613, crypto_sign/dilithium4

Computer: manny613
Architecture: amd64
CPU ID: GenuineIntel-000306e4-bfebfbff
SUPERCOP version: 20180818
Operation: crypto_sign
Primitive: dilithium4
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
3151240? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2018082920180818
3151484? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2018082920180818
3206200? ? ?? ? ?refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2018082920180818
3207384? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2018082920180818
3212732? ? ?? ? ?refgcc_-funroll-loops_-O2_-fomit-frame-pointer2018082920180818
3227336? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2018082920180818
3227680? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2018082920180818
3231968? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2018082920180818
3232296? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2018082920180818
3237100? ? ?? ? ?refgcc_-march=barcelona_-O3_-fomit-frame-pointer2018082920180818
3248028? ? ?? ? ?refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2018082920180818
3303932? ? ?? ? ?refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2018082920180818
3304832? ? ?? ? ?refgcc_-funroll-loops_-O3_-fomit-frame-pointer2018082920180818
3305492? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2018082920180818
3336968? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2018082920180818
3344320? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2018082920180818
3429224? ? ?? ? ?refgcc_-march=k8_-O3_-fomit-frame-pointer2018082920180818
3438544? ? ?? ? ?refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2018082920180818
3515024? ? ?? ? ?refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2018082920180818
3519300? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2018082920180818
3521016? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2018082920180818
3521304? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2018082920180818
3526208? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2018082920180818
3632416? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2018082920180818
3632824? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2018082920180818
3636084? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2018082920180818
3637976? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2018082920180818
3639352? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2018082920180818
3645620? ? ?? ? ?refgcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2018082920180818
3657808? ? ?? ? ?reficc_-no-vec2018082920180818
3665128? ? ?? ? ?refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2018082920180818
3670104? ? ?? ? ?reficc_-xSSE4.1_-O2_-fomit-frame-pointer2018082920180818
3670928? ? ?? ? ?refgcc_-funroll-loops_-O_-fomit-frame-pointer2018082920180818
3671356? ? ?? ? ?refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2018082920180818
3673560? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2018082920180818
3720192? ? ?? ? ?refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2018082920180818
3721904? ? ?? ? ?refgcc_-O3_-fomit-frame-pointer2018082920180818
3726760? ? ?? ? ?refgcc_-m64_-O3_-fomit-frame-pointer2018082920180818
3730124? ? ?? ? ?reficc_-xSSE4.2_-O3_-fomit-frame-pointer2018082920180818
3733720? ? ?? ? ?reficc_-xSSE4.1_-O3_-fomit-frame-pointer2018082920180818
3752872? ? ?? ? ?refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2018082920180818
3757236? ? ?? ? ?refgcc_-march=barcelona_-O2_-fomit-frame-pointer2018082920180818
3757716? ? ?? ? ?reficc_-xCORE-AVX-I_-O2_-fomit-frame-pointer2018082920180818
3762044? ? ?? ? ?reficc_-xAVX_-O2_-fomit-frame-pointer2018082920180818
3767636? ? ?? ? ?reficc2018082920180818
3807040? ? ?? ? ?reficc_-xSSE4.2_-O2_-fomit-frame-pointer2018082920180818
3821664? ? ?? ? ?refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2018082920180818
3826320? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2018082920180818
3830516? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2018082920180818
3888756? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2018082920180818
3890956? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2018082920180818
3891500? ? ?? ? ?refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2018082920180818
3891540? ? ?? ? ?refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2018082920180818
3892752? ? ?? ? ?reficc_-xAVX_-O3_-fomit-frame-pointer2018082920180818
3892832? ? ?? ? ?reficc_-xCORE-AVX-I_-O3_-fomit-frame-pointer2018082920180818
3917460? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2018082920180818
3955632? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2018082920180818
3956068? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2018082920180818
3965972? ? ?? ? ?refgcc_-O2_-fomit-frame-pointer2018082920180818
3970776? ? ?? ? ?refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2018082920180818
3976324? ? ?? ? ?refgcc_-m64_-O2_-fomit-frame-pointer2018082920180818
4050440? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2018082920180818
4051440? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2018082920180818
4069976? ? ?? ? ?refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2018082920180818
4071336? ? ?? ? ?refgcc_-march=k8_-O2_-fomit-frame-pointer2018082920180818
4071428? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2018082920180818
4076620? ? ?? ? ?refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2018082920180818
4077356? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2018082920180818
4079528? ? ?? ? ?refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2018082920180818
4081352? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2018082920180818
4108792? ? ?? ? ?refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2018082920180818
4109384? ? ?? ? ?refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2018082920180818
4137576? ? ?? ? ?refgcc_-march=barcelona_-O_-fomit-frame-pointer2018082920180818
4144952? ? ?? ? ?refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2018082920180818
4151872? ? ?? ? ?refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2018082920180818
4153900? ? ?? ? ?refgcc_-m64_-Os_-fomit-frame-pointer2018082920180818
4167332? ? ?? ? ?refgcc_-Os_-fomit-frame-pointer2018082920180818
4184604? ? ?? ? ?refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2018082920180818
4188552? ? ?? ? ?refgcc_-march=nocona_-O3_-fomit-frame-pointer2018082920180818
4202684? ? ?? ? ?refgcc_-march=k8_-O_-fomit-frame-pointer2018082920180818
4203868? ? ?? ? ?refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2018082920180818
4221004? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2018082920180818
4221624? ? ?? ? ?refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2018082920180818
4224336? ? ?? ? ?refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2018082920180818
4229484? ? ?? ? ?refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2018082920180818
4231616? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2018082920180818
4242084? ? ?? ? ?refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2018082920180818
4242968? ? ?? ? ?refgcc_-march=barcelona_-Os_-fomit-frame-pointer2018082920180818
4268880? ? ?? ? ?refgcc_-march=k8_-Os_-fomit-frame-pointer2018082920180818
4274392? ? ?? ? ?refgcc_-O_-fomit-frame-pointer2018082920180818
4275928? ? ?? ? ?refgcc_-march=nocona_-Os_-fomit-frame-pointer2018082920180818
4277284? ? ?? ? ?refgcc_-m64_-O_-fomit-frame-pointer2018082920180818
4280316? ? ?? ? ?refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2018082920180818
4312756? ? ?? ? ?refgcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2018082920180818
4312808? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2018082920180818
4315680? ? ?? ? ?refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2018082920180818
4318160? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2018082920180818
4318632? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2018082920180818
4318792? ? ?? ? ?refgcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2018082920180818
4320840? ? ?? ? ?refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2018082920180818
4324288? ? ?? ? ?refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2018082920180818
4324500? ? ?? ? ?refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2018082920180818
4332796? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2018082920180818
4356488? ? ?? ? ?refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2018082920180818
4367116? ? ?? ? ?refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2018082920180818
4369388? ? ?? ? ?refgcc_-funroll-loops_-Os_-fomit-frame-pointer2018082920180818
4373980? ? ?? ? ?refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2018082920180818
4423768? ? ?? ? ?refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2018082920180818
4458832? ? ?? ? ?refgcc_-march=nocona_-O2_-fomit-frame-pointer2018082920180818
4468740? ? ?? ? ?refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2018082920180818
4500636? ? ?? ? ?refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2018082920180818
4811012? ? ?? ? ?refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2018082920180818
4818412? ? ?? ? ?refgcc_-march=nocona_-O_-fomit-frame-pointer2018082920180818
5934388? ? ?? ? ?refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2018082920180818
13403920? ? ?? ? ?refgcc2018082920180818
13419428? ? ?? ? ?refgcc_-funroll-loops2018082920180818
13753240? ? ?? ? ?refcc2018082920180818

Test failure

Implementation: avx2
Security model: unknown
Compiler: gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 16, namely:
CompilerImplementations
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer avx2
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer avx2
icc avx2
icc -no-vec avx2
icc -xAVX -O2 -fomit-frame-pointer avx2
icc -xAVX -O3 -fomit-frame-pointer avx2
icc -xCORE-AVX-I -O2 -fomit-frame-pointer avx2
icc -xCORE-AVX-I -O3 -fomit-frame-pointer avx2
icc -xSSE4.1 -O2 -fomit-frame-pointer avx2
icc -xSSE4.1 -O3 -fomit-frame-pointer avx2
icc -xSSE4.2 -O2 -fomit-frame-pointer avx2
icc -xSSE4.2 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer ref
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer ref
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer ref

Compiler output

Implementation: avx2
Security model: unknown
Compiler: cc
KeccakP-1600-times4-SIMD256.c: In file included from KeccakP-1600-times4-SIMD256.c:19:0:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/smmintrin.h:31:3: error: #error "SSE4.1 instruction set not enabled"
KeccakP-1600-times4-SIMD256.c: # error "SSE4.1 instruction set not enabled"
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: In file included from KeccakP-1600-times4-SIMD256.c:20:0:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/wmmintrin.h:34:3: error: #error "AES/PCLMUL instructions not enabled"
KeccakP-1600-times4-SIMD256.c: # error "AES/PCLMUL instructions not enabled"
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:35:1: error: unknown type name '__m256i'
KeccakP-1600-times4-SIMD256.c: typedef __m256i V256;
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:58:67: error: '__m256' undeclared (first use in this function)
KeccakP-1600-times4-SIMD256.c: #define PERM128( a, b, c ) (V256)_mm256_permute2f128_ps((__m256)(a), (__m256)(b), c)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:70:48: note: in expansion of macro 'PERM128'
KeccakP-1600-times4-SIMD256.c: #define INTLEAVE() lanesL01 = PERM128( lanes0, lanes2, 0x20 ), \
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:139:33: note: in expansion of macro 'INTLEAVE'
KeccakP-1600-times4-SIMD256.c: INTLEAVE(),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:58:67: note: each undeclared identifier is reported only once for each function it appears in
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
cc avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: gcc
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 86, namely:
CompilerImplementations
gcc avx2
gcc -O2 -fomit-frame-pointer avx2
gcc -O3 -fomit-frame-pointer avx2
gcc -O -fomit-frame-pointer avx2
gcc -Os -fomit-frame-pointer avx2
gcc -fno-schedule-insns -O2 -fomit-frame-pointer avx2
gcc -fno-schedule-insns -O3 -fomit-frame-pointer avx2
gcc -fno-schedule-insns -O -fomit-frame-pointer avx2
gcc -fno-schedule-insns -Os -fomit-frame-pointer avx2
gcc -funroll-loops avx2
gcc -funroll-loops -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -O -fomit-frame-pointer avx2
gcc -funroll-loops -Os -fomit-frame-pointer avx2
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer avx2
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer avx2
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer avx2
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer avx2
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer avx2
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer avx2
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer avx2
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer avx2
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer avx2
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer avx2
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer avx2
gcc -m64 -O2 -fomit-frame-pointer avx2
gcc -m64 -O3 -fomit-frame-pointer avx2
gcc -m64 -O -fomit-frame-pointer avx2
gcc -m64 -Os -fomit-frame-pointer avx2
gcc -m64 -march=core2 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=core2 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=core2 -O -fomit-frame-pointer avx2
gcc -m64 -march=core2 -Os -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer avx2
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer avx2
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=corei7 -O -fomit-frame-pointer avx2
gcc -m64 -march=corei7 -Os -fomit-frame-pointer avx2
gcc -m64 -march=k8 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=k8 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=k8 -O -fomit-frame-pointer avx2
gcc -m64 -march=k8 -Os -fomit-frame-pointer avx2
gcc -m64 -march=nocona -O2 -fomit-frame-pointer avx2
gcc -m64 -march=nocona -O3 -fomit-frame-pointer avx2
gcc -m64 -march=nocona -O -fomit-frame-pointer avx2
gcc -m64 -march=nocona -Os -fomit-frame-pointer avx2
gcc -march=barcelona -O2 -fomit-frame-pointer avx2
gcc -march=barcelona -O3 -fomit-frame-pointer avx2
gcc -march=barcelona -O -fomit-frame-pointer avx2
gcc -march=barcelona -Os -fomit-frame-pointer avx2
gcc -march=k8 -O2 -fomit-frame-pointer avx2
gcc -march=k8 -O3 -fomit-frame-pointer avx2
gcc -march=k8 -O -fomit-frame-pointer avx2
gcc -march=k8 -Os -fomit-frame-pointer avx2
gcc -march=nocona -O2 -fomit-frame-pointer avx2
gcc -march=nocona -O3 -fomit-frame-pointer avx2
gcc -march=nocona -O -fomit-frame-pointer avx2
gcc -march=nocona -Os -fomit-frame-pointer avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ...
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer avx2
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer avx2
gcc -m64 -march=barcelona -O -fomit-frame-pointer avx2
gcc -m64 -march=barcelona -Os -fomit-frame-pointer avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:142:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+2], lanes2 ),\
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 16, 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
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer avx2
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer avx2
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer avx2
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer avx2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv avx2