Implementation notes: amd64, gsm2, crypto_stream/simon128256ctr

Computer: gsm2
Architecture: amd64
CPU ID: GenuineIntel-000306e4-bfebfbff
SUPERCOP version: 20170725
Operation: crypto_stream
Primitive: simon128256ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
16832? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017080520170725
17388? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017080520170725
17588? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2017080520170725
17620? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2017080520170725
17624? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2017080520170725
19820? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2017080520170725
20932? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2017080520170725
21632? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2017080520170725
28448? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017080520170725
29512? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017080520170725
29760? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017080520170725
30612? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017080520170725
30696? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2017080520170725
30776? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2017080520170725
31372? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2017080520170725
31620? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017080520170725
31668? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2017080520170725
32040? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2017080520170725
32548? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017080520170725
32872? ? ?? ? ?sse4gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017080520170725
33148? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017080520170725
33196? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017080520170725
33340? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017080520170725
33732? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017080520170725
33860? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017080520170725
34460? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017080520170725
36316? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017080520170725
36744? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017080520170725

Test failure

Implementation: crypto_stream/simon128256ctr/avx2
Compiler: gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 6, namely:
CompilerImplementations
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer avx2 sse4
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer avx2 sse4
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer avx2 sse4

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-linux-gnu/4.8/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: 75, namely:
CompilerImplementations
cc sse4
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=core2 -O2 -fomit-frame-pointer sse4
gcc -m64 -march=core2 -O3 -fomit-frame-pointer sse4
gcc -m64 -march=core2 -O -fomit-frame-pointer sse4
gcc -m64 -march=core2 -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: 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: 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_stream/simon128256ctr/sse4
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
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-linux-gnu/4.8/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: ...
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-linux-gnu/4.8/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: 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: 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: ...
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: 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 Simon128256AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:26:37: error: incompatible types when assigning to type '__m256i' from type 'int'
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: SET1(X[0],nonce[1]); SET4(Y[0],nonce[0]);
stream.c: ^
stream.c: In file included from stream.c:20:0:
stream.c: Simon128256AVX2.h:24:21: error: incompatible types when assigning to type '__m256i' from type 'int'
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: Simon128256AVX2.h:26:25: note: in expansion of macro 'RD'
stream.c: #define Sx4(U,V,rk,s) (RD(U[0],V[0],rk[s][0]))
stream.c: ^
stream.c: Simon128256AVX2.h:32:28: note: in expansion of macro 'Sx4'
stream.c: #define R2x4(X,Y,rk,r,s) (Sx4(X,Y,rk,r), Sx4(Y,X,rk,s))
stream.c: ^
stream.c: Simon128256AVX2.h:45:24: note: in expansion of macro 'R2x4'
stream.c: #define Enc(X,Y,rk,n) (R2x##n(X,Y,rk,0,1), R2x##n(X,Y,rk,2,3), R2x##n(X,Y,rk,4,5), R2x##n(X,Y,rk,6,7), R2x##n(X,Y,rk,8,9), \
stream.c: ^
stream.c: stream.c:130:21: note: in expansion of macro 'Enc'
stream.c: if (numbytes==64) Enc(X,Y,rk,4);
stream.c: ^
stream.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