Implementation notes: amd64, manny1024, crypto_stream/simon128128ctr

Computer: manny1024
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20170904
Operation: crypto_stream
Primitive: simon128128ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
3274? ? ?? ? ?avx2icc_-xCORE-AVX512_-O3_-fomit-frame-pointer2017091720170904
3280? ? ?? ? ?avx2icc_-xCORE-AVX512_-O2_-fomit-frame-pointer2017091720170904
4558? ? ?? ? ?avx2icc2017091720170904
4574? ? ?? ? ?avx2icc_-no-vec2017091720170904
4584? ? ?? ? ?avx2icc_-xCORE-AVX2_-O2_-fomit-frame-pointer2017091720170904
4594? ? ?? ? ?avx2icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer2017091720170904
4662? ? ?? ? ?avx2icc_-xCORE-AVX2_-O3_-fomit-frame-pointer2017091720170904
4708? ? ?? ? ?avx2icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer2017091720170904
4740? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017091720170904
4746? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O3_-fomit-frame-pointer2017091720170904
4756? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017091720170904
5044? ? ?? ? ?avx2icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer2017091720170904
5072? ? ?? ? ?avx2icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer2017091720170904
6944? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O2_-fomit-frame-pointer2017091720170904
7078? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017091720170904
7088? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017091720170904
7106? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017091720170904
7130? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017091720170904
7154? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017091720170904
7174? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017091720170904
7260? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O_-fomit-frame-pointer2017091720170904
7326? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-Os_-fomit-frame-pointer2017091720170904
8082? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2017091720170904
8082? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2017091720170904
8106? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017091720170904
8108? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017091720170904
8164? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O3_-fomit-frame-pointer2017091720170904
8588? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2017091720170904
8592? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2017091720170904
8610? ? ?? ? ?sse4gcc_-m64_-march=core2_-O3_-fomit-frame-pointer2017091720170904
8618? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2017091720170904
10872? ? ?? ? ?sse4icc_-xCORE-AVX512_-O2_-fomit-frame-pointer2017091720170904
10988? ? ?? ? ?sse4icc_-xCORE-AVX512_-O3_-fomit-frame-pointer2017091720170904
11120? ? ?? ? ?sse4icc_-no-vec2017091720170904
11152? ? ?? ? ?sse4icc2017091720170904
11672? ? ?? ? ?sse4gcc_-m64_-march=core2_-O_-fomit-frame-pointer2017091720170904
11688? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017091720170904
11716? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017091720170904
11734? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017091720170904
12082? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017091720170904
12214? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2017091720170904
12252? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2017091720170904
12398? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O2_-fomit-frame-pointer2017091720170904
12706? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017091720170904
12710? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017091720170904
12754? ? ?? ? ?sse4gcc_-m64_-march=core2_-O2_-fomit-frame-pointer2017091720170904
12808? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2017091720170904
12820? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017091720170904
12834? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017091720170904
12874? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O_-fomit-frame-pointer2017091720170904
12986? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2017091720170904
13210? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017091720170904
13224? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017091720170904
13546? ? ?? ? ?sse4icc_-xCORE-AVX2_-O2_-fomit-frame-pointer2017091720170904
13554? ? ?? ? ?sse4icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer2017091720170904
13568? ? ?? ? ?sse4icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer2017091720170904
13570? ? ?? ? ?sse4icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer2017091720170904
13702? ? ?? ? ?sse4icc_-xCORE-AVX2_-O3_-fomit-frame-pointer2017091720170904
13730? ? ?? ? ?sse4icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer2017091720170904
13852? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017091720170904
13884? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017091720170904
14202? ? ?? ? ?sse4gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017091720170904
14210? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2017091720170904
14212? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017091720170904
14214? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017091720170904
14222? ? ?? ? ?sse4gcc_-m64_-march=core2_-Os_-fomit-frame-pointer2017091720170904
14280? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2017091720170904
14380? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-Os_-fomit-frame-pointer2017091720170904

Compiler output

Implementation: crypto_stream/simon128128ctr/sse4
Compiler: cc
stream.c: In file included from Intrinsics_SSE4_128block.h:5:0,
stream.c: from Simon128128SSE4.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 Simon128128SSE4.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:23:82: 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:25:113: 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:26:25: 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/simon128128ctr/avx2
Compiler: cc
stream.c: In file included from Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:9:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:25:46: 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:9:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:27:75: 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:9:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:28:25: note: in expansion of macro 'u256'
stream.c: int ExpandKeyBS(u64 K[],u256 rk[][8]);
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:9:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:29:27: 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/simon128128ctr/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 Simon128128SSE4.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 Simon128128SSE4.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: Simon128128SSE4.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: Simon128128SSE4.h:26:22: note: in expansion of macro 'RD'
stream.c: #define Sx2(U,V,k) (RD(U[0],V[0],k))
stream.c: ^~
stream.c: Simon128128SSE4.h:31:47: note: in expansion of macro 'Sx2'
stream.c: #define R2x2(X,Y,rk,r,s) (Sx2(X,Y,rk[r][0]), Sx2(Y,X,rk[s][0]))
stream.c: ^~~
stream.c: Simon128128SSE4.h:47:76: note: in expansion of macro 'R2x2'
stream.c: R2x##n(X,Y,rk,60,61), R2x##n(X,Y,rk,62,63), R2x##n(X,Y,rk,64,65), R2x##n(X,Y,rk,66,67))
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/simon128128ctr/avx2
Compiler: gcc
stream.c: In file included from Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:24:21: 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:130:3: 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 Simon128128AVX2.h:17,
stream.c: from stream.c:21:
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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:16:13: note: called from here
stream.c: #define ADD _mm256_add_epi64
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:25:38: 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:130:24: 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/simon128128ctr/avx2
Compiler: gcc -O2 -fomit-frame-pointer
stream.c: In file included from Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:24:21: 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:130:3: 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 Simon128128AVX2.h:17,
stream.c: from stream.c:21:
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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:14:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c:
stream.c: stream.c:414:10: 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/simon128128ctr/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 Simon128128SSE4.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 Simon128128SSE4.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: Simon128128SSE4.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: Simon128128SSE4.h:26:22: note: in expansion of macro 'RD'
stream.c: #define Sx2(U,V,k) (RD(U[0],V[0],k))
stream.c: ^~
stream.c: Simon128128SSE4.h:31:47: note: in expansion of macro 'Sx2'
stream.c: #define R2x2(X,Y,rk,r,s) (Sx2(X,Y,rk[r][0]), Sx2(Y,X,rk[s][0]))
stream.c: ^~~
stream.c: Simon128128SSE4.h:47:76: note: in expansion of macro 'R2x2'
stream.c: R2x##n(X,Y,rk,60,61), R2x##n(X,Y,rk,62,63), R2x##n(X,Y,rk,64,65), R2x##n(X,Y,rk,66,67))
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 Simon128128SSE4.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 Simon128128SSE4.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: Simon128128SSE4.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: Simon128128SSE4.h:26:22: note: in expansion of macro 'RD'
stream.c: #define Sx2(U,V,k) (RD(U[0],V[0],k))
stream.c: ^~
stream.c: Simon128128SSE4.h:31:47: note: in expansion of macro 'Sx2'
stream.c: #define R2x2(X,Y,rk,r,s) (Sx2(X,Y,rk[r][0]), Sx2(Y,X,rk[s][0]))
stream.c: ^~~
stream.c: Simon128128SSE4.h:47:76: note: in expansion of macro 'R2x2'
stream.c: R2x##n(X,Y,rk,60,61), R2x##n(X,Y,rk,62,63), R2x##n(X,Y,rk,64,65), R2x##n(X,Y,rk,66,67))
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/simon128128ctr/avx2
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:24:21: 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:130:3: 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 Simon128128AVX2.h:17,
stream.c: from stream.c:21:
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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:14:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c:
stream.c: stream.c:414:10: 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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:24:21: 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:130:3: 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 Simon128128AVX2.h:17,
stream.c: from stream.c:21:
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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:14:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c:
stream.c: stream.c:414:10: 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/simon128128ctr/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 Simon128128AVX2.h:17,
stream.c: from stream.c:21:
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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:14:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c:
stream.c: stream.c:414:10: 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 Simon128128AVX2.h:17,
stream.c: from stream.c:21:
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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
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