Implementation notes: amd64, manny1024, crypto_stream/simon128256ctr

Computer: manny1024
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20170904
Operation: crypto_stream
Primitive: simon128256ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
3922? ? ?? ? ?avx2icc_-xCORE-AVX512_-O2_-fomit-frame-pointer2017091720170904
3982? ? ?? ? ?avx2icc_-xCORE-AVX512_-O3_-fomit-frame-pointer2017091720170904
5684? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017091720170904
5684? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017091720170904
5710? ? ?? ? ?avx2icc2017091720170904
5716? ? ?? ? ?avx2icc_-xCORE-AVX2_-O2_-fomit-frame-pointer2017091720170904
5718? ? ?? ? ?avx2icc_-no-vec2017091720170904
5814? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O3_-fomit-frame-pointer2017091720170904
5896? ? ?? ? ?avx2icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer2017091720170904
5958? ? ?? ? ?avx2icc_-xCORE-AVX2_-O3_-fomit-frame-pointer2017091720170904
6016? ? ?? ? ?avx2icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer2017091720170904
6168? ? ?? ? ?avx2icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer2017091720170904
6318? ? ?? ? ?avx2icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer2017091720170904
8306? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O2_-fomit-frame-pointer2017091720170904
8336? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017091720170904
8340? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017091720170904
8380? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017091720170904
8412? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017091720170904
8416? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017091720170904
8422? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017091720170904
8562? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O_-fomit-frame-pointer2017091720170904
8814? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-Os_-fomit-frame-pointer2017091720170904
9404? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2017091720170904
9412? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O3_-fomit-frame-pointer2017091720170904
9416? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2017091720170904
9430? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017091720170904
9490? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017091720170904
10100? ? ?? ? ?sse4gcc_-m64_-march=core2_-O3_-fomit-frame-pointer2017091720170904
10116? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2017091720170904
10188? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2017091720170904
10310? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2017091720170904
11960? ? ?? ? ?sse4icc_-xCORE-AVX512_-O3_-fomit-frame-pointer2017091720170904
12264? ? ?? ? ?sse4icc_-xCORE-AVX512_-O2_-fomit-frame-pointer2017091720170904
13040? ? ?? ? ?sse4icc2017091720170904
13374? ? ?? ? ?sse4icc_-no-vec2017091720170904
13580? ? ?? ? ?sse4gcc_-m64_-march=core2_-O_-fomit-frame-pointer2017091720170904
13638? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017091720170904
13648? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017091720170904
13712? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017091720170904
13886? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2017091720170904
13910? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O2_-fomit-frame-pointer2017091720170904
13922? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2017091720170904
14098? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017091720170904
14468? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017091720170904
14592? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2017091720170904
14592? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2017091720170904
14616? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017091720170904
14626? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O_-fomit-frame-pointer2017091720170904
14658? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017091720170904
14684? ? ?? ? ?sse4gcc_-m64_-march=core2_-O2_-fomit-frame-pointer2017091720170904
14736? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017091720170904
14902? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017091720170904
15046? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017091720170904
15154? ? ?? ? ?sse4gcc_-m64_-march=core2_-Os_-fomit-frame-pointer2017091720170904
15174? ? ?? ? ?sse4gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017091720170904
15284? ? ?? ? ?sse4icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer2017091720170904
15386? ? ?? ? ?sse4icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer2017091720170904
15418? ? ?? ? ?sse4icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer2017091720170904
15512? ? ?? ? ?sse4icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer2017091720170904
15548? ? ?? ? ?sse4icc_-xCORE-AVX2_-O2_-fomit-frame-pointer2017091720170904
15572? ? ?? ? ?sse4icc_-xCORE-AVX2_-O3_-fomit-frame-pointer2017091720170904
15764? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017091720170904
15778? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017091720170904
15986? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017091720170904
16120? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2017091720170904
16158? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-Os_-fomit-frame-pointer2017091720170904
16194? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2017091720170904
16838? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017091720170904

Compiler output

Implementation: crypto_stream/simon128256ctr/sse4
Compiler: cc
stream.c: In file included from Intrinsics_SSE4_128block.h:5:0,
stream.c: from Simon128256SSE4.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/smmintrin.h:31:3: error: #error "SSE4.1 instruction set not enabled"
stream.c: # error "SSE4.1 instruction set not enabled"
stream.c: ^
stream.c: In file included from Simon128256SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_128block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:24:82: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out,u64 nonce[],u128 rk[][8],u64 key[],int numbytes);
stream.c: ^
stream.c: Intrinsics_SSE4_128block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:26:112: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline))int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[][8], u64 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_SSE4_128block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:27:25: note: in expansion of macro 'u128'
stream.c: int ExpandKeyBS(u64 K[],u128 rk[][8]);
stream.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
cc sse4

Compiler output

Implementation: crypto_stream/simon128256ctr/avx2
Compiler: cc
stream.c: In file included from Simon128256AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:24:46: note: in expansion of macro 'u256'
stream.c: int Encrypt(unsigned char *out, u64 nonce[], u256 rk[][8], u64 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:26:75: note: in expansion of macro 'u256'
stream.c: int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u256 rk[][8], u64 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:27:25: note: in expansion of macro 'u256'
stream.c: int ExpandKeyBS(u64 K[],u256 rk[][8]);
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:28:27: note: in expansion of macro 'u256'
stream.c: int ExpandKeyNBS(u64 K[], u256 rk[][8], u64 key[]);
stream.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
cc avx2

Compiler output

Implementation: crypto_stream/simon128256ctr/sse4
Compiler: gcc
stream.c: In file included from /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/smmintrin.h:32:0,
stream.c: from Intrinsics_SSE4_128block.h:5,
stream.c: from Simon128256SSE4.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
stream.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128256SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_128block.h:15:13: note: called from here
stream.c: #define XOR _mm_xor_si128
stream.c:
stream.c: Simon128256SSE4.h:24:41: note: in expansion of macro 'XOR'
stream.c: #define RD(U,V,k) (V=XOR(V,ROL(U,2)), V=XOR(V,AND(ROL(U,1),ROL8(U))), V=XOR(V,k))
stream.c: ^~~
stream.c: Simon128256SSE4.h:26:25: note: in expansion of macro 'RD'
stream.c: #define Sx2(U,V,rk,s) (RD(U[0],V[0],rk[s][0]))
stream.c: ^~
stream.c: Simon128256SSE4.h:32:43: note: in expansion of macro 'Sx2'
stream.c: #define R2x2(X,Y,rk,r,s) (Sx2(X,Y,rk,r), Sx2(Y,X,rk,s))
stream.c: ^~~
stream.c: Simon128256SSE4.h:50:10: note: in expansion of macro 'R2x2'
stream.c: R2x##n(X,Y,rk,70,71))
stream.c: ^~~
stream.c: ...
Number of similar (compiler,implementation) pairs: 70, namely:
CompilerImplementations
gcc sse4
gcc -O2 -fomit-frame-pointer sse4
gcc -O3 -fomit-frame-pointer sse4
gcc -O -fomit-frame-pointer sse4
gcc -Os -fomit-frame-pointer sse4
gcc -fno-schedule-insns -O2 -fomit-frame-pointer sse4
gcc -fno-schedule-insns -O3 -fomit-frame-pointer sse4
gcc -fno-schedule-insns -O -fomit-frame-pointer sse4
gcc -fno-schedule-insns -Os -fomit-frame-pointer sse4
gcc -funroll-loops sse4
gcc -funroll-loops -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -O -fomit-frame-pointer sse4
gcc -funroll-loops -Os -fomit-frame-pointer sse4
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer sse4
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -O -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -Os -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer sse4
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer sse4
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer sse4
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer sse4
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer sse4
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer sse4
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer sse4
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer sse4
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer sse4
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer sse4
gcc -m64 -O2 -fomit-frame-pointer sse4
gcc -m64 -O3 -fomit-frame-pointer sse4
gcc -m64 -O -fomit-frame-pointer sse4
gcc -m64 -Os -fomit-frame-pointer sse4
gcc -m64 -march=k8 -O2 -fomit-frame-pointer sse4
gcc -m64 -march=k8 -O3 -fomit-frame-pointer sse4
gcc -m64 -march=k8 -O -fomit-frame-pointer sse4
gcc -m64 -march=k8 -Os -fomit-frame-pointer sse4
gcc -m64 -march=nocona -O2 -fomit-frame-pointer sse4
gcc -m64 -march=nocona -O3 -fomit-frame-pointer sse4
gcc -m64 -march=nocona -O -fomit-frame-pointer sse4
gcc -m64 -march=nocona -Os -fomit-frame-pointer sse4
gcc -march=barcelona -O2 -fomit-frame-pointer sse4
gcc -march=barcelona -O3 -fomit-frame-pointer sse4
gcc -march=barcelona -O -fomit-frame-pointer sse4
gcc -march=barcelona -Os -fomit-frame-pointer sse4
gcc -march=k8 -O2 -fomit-frame-pointer sse4
gcc -march=k8 -O3 -fomit-frame-pointer sse4
gcc -march=k8 -O -fomit-frame-pointer sse4
gcc -march=k8 -Os -fomit-frame-pointer sse4
gcc -march=nocona -O2 -fomit-frame-pointer sse4
gcc -march=nocona -O3 -fomit-frame-pointer sse4
gcc -march=nocona -O -fomit-frame-pointer sse4
gcc -march=nocona -Os -fomit-frame-pointer sse4

Compiler output

Implementation: crypto_stream/simon128256ctr/avx2
Compiler: gcc
stream.c: In file included from Simon128256AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:25:21: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
stream.c: #define SET1(X,c) (X=SET(c,c,c,c))
stream.c: ~~^~~~~~~~~~~~~~
stream.c: stream.c:128:3: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET4(Y[0],nonce[0]);
stream.c: ^~~~
stream.c: In file included from /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_128block.h:5,
stream.c: from Simon128256AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/avx2intrin.h:126:1: error: inlining failed in call to always_inline '_mm256_add_epi64': target specific option mismatch
stream.c: _mm256_add_epi64 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128256AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:17:13: note: called from here
stream.c: #define ADD _mm256_add_epi64
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:26:38: note: in expansion of macro 'ADD'
stream.c: #define SET4(X,c) (X=SET(c,c,c,c), X=ADD(X,_q))
stream.c: ^~~
stream.c: stream.c:128:24: note: in expansion of macro 'SET4'
stream.c: ...
Number of similar (compiler,implementation) pairs: 2, namely:
CompilerImplementations
gcc avx2
gcc -funroll-loops avx2

Compiler output

Implementation: crypto_stream/simon128256ctr/avx2
Compiler: gcc -O2 -fomit-frame-pointer
stream.c: In file included from Simon128256AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:25:21: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
stream.c: #define SET1(X,c) (X=SET(c,c,c,c))
stream.c: ~~^~~~~~~~~~~~~~
stream.c: stream.c:128:3: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET4(Y[0],nonce[0]);
stream.c: ^~~~
stream.c: In file included from /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_128block.h:5,
stream.c: from Simon128256AVX2.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Transpose':
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
stream.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128256AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:15:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c:
stream.c: stream.c:412:10: note: in expansion of macro 'XOR'
stream.c: T[6] = XOR(T[6], SL(W[3],1));
stream.c: ^~~
stream.c: ...
Number of similar (compiler,implementation) pairs: 84, namely:
CompilerImplementations
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 -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_stream/simon128256ctr/sse4
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/smmintrin.h:32:0,
stream.c: from Intrinsics_SSE4_128block.h:5,
stream.c: from Simon128256SSE4.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
stream.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128256SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_128block.h:15:13: note: called from here
stream.c: #define XOR _mm_xor_si128
stream.c:
stream.c: Simon128256SSE4.h:24:41: note: in expansion of macro 'XOR'
stream.c: #define RD(U,V,k) (V=XOR(V,ROL(U,2)), V=XOR(V,AND(ROL(U,1),ROL8(U))), V=XOR(V,k))
stream.c: ^~~
stream.c: Simon128256SSE4.h:26:25: note: in expansion of macro 'RD'
stream.c: #define Sx2(U,V,rk,s) (RD(U[0],V[0],rk[s][0]))
stream.c: ^~
stream.c: Simon128256SSE4.h:32:43: note: in expansion of macro 'Sx2'
stream.c: #define R2x2(X,Y,rk,r,s) (Sx2(X,Y,rk,r), Sx2(Y,X,rk,s))
stream.c: ^~~
stream.c: Simon128256SSE4.h:50:10: note: in expansion of macro 'R2x2'
stream.c: R2x##n(X,Y,rk,70,71))
stream.c: ^~~
stream.c: ...
stream.c: In file included from /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/smmintrin.h:32:0,
stream.c: from Intrinsics_SSE4_128block.h:5,
stream.c: from Simon128256SSE4.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/tmmintrin.h:136:1: error: inlining failed in call to always_inline '_mm_shuffle_epi8': target specific option mismatch
stream.c: _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128256SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_128block.h:15:13: note: called from here
stream.c: #define XOR _mm_xor_si128
stream.c:
stream.c: Simon128256SSE4.h:24:41: note: in expansion of macro 'XOR'
stream.c: #define RD(U,V,k) (V=XOR(V,ROL(U,2)), V=XOR(V,AND(ROL(U,1),ROL8(U))), V=XOR(V,k))
stream.c: ^~~
stream.c: Simon128256SSE4.h:26:25: note: in expansion of macro 'RD'
stream.c: #define Sx2(U,V,rk,s) (RD(U[0],V[0],rk[s][0]))
stream.c: ^~
stream.c: Simon128256SSE4.h:32:43: note: in expansion of macro 'Sx2'
stream.c: #define R2x2(X,Y,rk,r,s) (Sx2(X,Y,rk,r), Sx2(Y,X,rk,s))
stream.c: ^~~
stream.c: Simon128256SSE4.h:50:10: note: in expansion of macro 'R2x2'
stream.c: R2x##n(X,Y,rk,70,71))
stream.c: ^~~
stream.c: ...
Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer sse4
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer sse4
gcc -m64 -march=barcelona -O -fomit-frame-pointer sse4
gcc -m64 -march=barcelona -Os -fomit-frame-pointer sse4

Compiler output

Implementation: crypto_stream/simon128256ctr/avx2
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from Simon128256AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:25:21: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
stream.c: #define SET1(X,c) (X=SET(c,c,c,c))
stream.c: ~~^~~~~~~~~~~~~~
stream.c: stream.c:128:3: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET4(Y[0],nonce[0]);
stream.c: ^~~~
stream.c: In file included from /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_128block.h:5,
stream.c: from Simon128256AVX2.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Transpose':
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
stream.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128256AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:15:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c:
stream.c: stream.c:412:10: note: in expansion of macro 'XOR'
stream.c: T[6] = XOR(T[6], SL(W[3],1));
stream.c: ^~~
stream.c: ...
stream.c: In file included from Simon128256AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:25:21: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
stream.c: #define SET1(X,c) (X=SET(c,c,c,c))
stream.c: ~~^~~~~~~~~~~~~~
stream.c: stream.c:128:3: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET4(Y[0],nonce[0]);
stream.c: ^~~~
stream.c: In file included from /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_128block.h:5,
stream.c: from Simon128256AVX2.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Transpose':
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
stream.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128256AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:15:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c:
stream.c: stream.c:412:10: note: in expansion of macro 'XOR'
stream.c: T[6] = XOR(T[6], SL(W[3],1));
stream.c: ^~~
stream.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_stream/simon128256ctr/avx2
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer
stream.c: In file included from /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_128block.h:5,
stream.c: from Simon128256AVX2.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Transpose':
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
stream.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128256AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:15:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c:
stream.c: stream.c:412:10: note: in expansion of macro 'XOR'
stream.c: T[6] = XOR(T[6], SL(W[3],1));
stream.c: ^~~
stream.c: In file included from /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_128block.h:5,
stream.c: from Simon128256AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/avx2intrin.h:696:1: error: inlining failed in call to always_inline '_mm256_slli_epi64': target specific option mismatch
stream.c: _mm256_slli_epi64 (__m256i __A, int __B)
stream.c: ^~~~~~~~~~~~~~~~~
stream.c: In file included from Simon128256AVX2.h:17:0,
stream.c: from stream.c:20:
stream.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