Implementation notes: amd64, hydra9, crypto_stream/simon6496ctr

Computer: hydra9
Architecture: amd64
CPU ID: AuthenticAMD-00610f01-178bfbff
SUPERCOP version: 20171218
Operation: crypto_stream
Primitive: simon6496ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
6563? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2017090220170725
6602? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2017090220170725
6631? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2017090220170725
8901? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017090220170725
8914? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2017090220170725
8930? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017090220170725
8967? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2017090220170725
9939? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017090220170725
9946? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017090220170725
10387? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2017090220170725
10416? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2017090220170725
10889? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017090220170725
10891? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017090220170725
10935? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017090220170725
11290? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017090220170725
11346? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2017090220170725
11352? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017090220170725
11368? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2017090220170725
11483? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017090220170725
11501? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017090220170725
11515? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017090220170725
11537? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2017090220170725
11665? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017090220170725
11672? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017090220170725
11683? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017090220170725
11774? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2017090220170725
11913? ? ?? ? ?sse4gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017090220170725
12299? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017090220170725

Test failure

Implementation: crypto_stream/simon6496ctr/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/simon6496ctr/sse4
Compiler: cc
stream.c: In file included from Intrinsics_SSE4_64block.h:5:0,
stream.c: from Simon6496SSE4.h:16,
stream.c: from stream.c:21:
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 Simon6496SSE4.h:16:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:25:82: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out,u32 nonce[],u128 rk[][8],u32 key[],int numbytes);
stream.c: ^
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:27:113: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt_Xor(unsigned char *out, const unsigned char *in, u32 nonce[], u128 rk[][8], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:28:25: note: in expansion of macro 'u128'
stream.c: int ExpandKeyBS(u32 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/simon6496ctr/avx2
Compiler: cc
stream.c: In file included from Simon6496AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_64block.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, u32 nonce[], u256 rk[][8], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX2_64block.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, u32 nonce[], u256 rk[][8], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX2_64block.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(u32 K[],u256 rk[][8]);
stream.c: ^
stream.c: Intrinsics_AVX2_64block.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(u32 K[], u256 rk[][8], u32 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/simon6496ctr/sse4
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from Intrinsics_SSE4_64block.h:5:0,
stream.c: from Simon6496SSE4.h:16,
stream.c: from stream.c:21:
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 Simon6496SSE4.h:16:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:25:82: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out,u32 nonce[],u128 rk[][8],u32 key[],int numbytes);
stream.c: ^
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:27:113: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt_Xor(unsigned char *out, const unsigned char *in, u32 nonce[], u128 rk[][8], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:28:25: note: in expansion of macro 'u128'
stream.c: int ExpandKeyBS(u32 K[],u128 rk[][8]);
stream.c: ...
stream.c: In file included from Intrinsics_SSE4_64block.h:5:0,
stream.c: from Simon6496SSE4.h:16,
stream.c: from stream.c:21:
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 Simon6496SSE4.h:16:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:25:82: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out,u32 nonce[],u128 rk[][8],u32 key[],int numbytes);
stream.c: ^
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:27:113: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt_Xor(unsigned char *out, const unsigned char *in, u32 nonce[], u128 rk[][8], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:28:25: note: in expansion of macro 'u128'
stream.c: int ExpandKeyBS(u32 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/simon6496ctr/avx2
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from Simon6496AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_64block.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, u32 nonce[], u256 rk[][8], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX2_64block.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, u32 nonce[], u256 rk[][8], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX2_64block.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(u32 K[],u256 rk[][8]);
stream.c: ^
stream.c: Intrinsics_AVX2_64block.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(u32 K[], u256 rk[][8], u32 key[]);
stream.c: ...
stream.c: In file included from Simon6496AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_64block.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, u32 nonce[], u256 rk[][8], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX2_64block.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, u32 nonce[], u256 rk[][8], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX2_64block.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(u32 K[],u256 rk[][8]);
stream.c: ^
stream.c: Intrinsics_AVX2_64block.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(u32 K[], u256 rk[][8], u32 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/simon6496ctr/avx2
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer
stream.c: In file included from Simon6496AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_64block.h:26:45: error: incompatible types when assigning to type '__m256i' from type 'int'
stream.c: #define SET8(X,c) (X=SET(c,c,c,c,c,c,c,c), X=ADD(X,_q))
stream.c: ^
stream.c: stream.c:148:24: note: in expansion of macro 'SET8'
stream.c: SET1(X[0],nonce[1]); SET8(Y[0],nonce[0]);
stream.c: ^
stream.c: In file included from stream.c:20:0:
stream.c: Simon6496AVX2.h:23:21: 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: Simon6496AVX2.h:25:22: note: in expansion of macro 'RD'
stream.c: #define Sx8(U,V,k) (RD(U[0],V[0],k))
stream.c: ^
stream.c: Simon6496AVX2.h:30:28: note: in expansion of macro 'Sx8'
stream.c: #define R2x8(X,Y,rk,r,s) (Sx8(X,Y,rk[r][0]), Sx8(Y,X,rk[s][0]))
stream.c: ^
stream.c: Simon6496AVX2.h:42:24: note: in expansion of macro 'R2x8'
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:150:21: note: in expansion of macro 'Enc'
stream.c: if (numbytes==64) Enc(X,Y,rk,8);
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