Implementation notes: amd64, gsm2, crypto_stream/speck64128ctr

Computer: gsm2
Architecture: amd64
CPU ID: GenuineIntel-000306e4-bfebfbff
SUPERCOP version: 20170725
Operation: crypto_stream
Primitive: speck64128ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
3552? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2017080520170725
5292? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017080520170725
5392? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017080520170725
5396? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017080520170725
5524? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2017080520170725
5596? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2017080520170725
5596? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017080520170725
5600? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2017080520170725
5600? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017080520170725
5608? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2017080520170725
5676? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017080520170725
5712? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2017080520170725
5712? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2017080520170725
5884? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017080520170725
5976? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2017080520170725
5984? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017080520170725
6012? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2017080520170725
6036? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017080520170725
6064? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017080520170725
6124? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2017080520170725
6340? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017080520170725
6400? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017080520170725
6452? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2017080520170725
6508? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017080520170725
6520? ? ?? ? ?sse4gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017080520170725
6840? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017080520170725
7148? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017080520170725
9888? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017080520170725

Test failure

Implementation: crypto_stream/speck64128ctr/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/speck64128ctr/sse4
Compiler: cc
stream.c: In file included from Intrinsics_SSE4_64block.h:5:0,
stream.c: from Speck64128SSE4.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 Speck64128SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:24:84: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out, u32 nonce[], u128 rk[], 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:26:113: 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[], 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:27:24: note: in expansion of macro 'u128'
stream.c: int ExpandKey(u32 K[], u128 rk[], u32 key[]);
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/speck64128ctr/avx2
Compiler: cc
stream.c: In file included from Speck64128AVX2.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:24:84: note: in expansion of macro 'u256'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out, u32 nonce[], u256 rk[], 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:26:113: note: in expansion of macro 'u256'
stream.c: inline __attribute__((always_inline)) int Encrypt_Xor(unsigned char *out, const unsigned char *in, u32 nonce[], u256 rk[], 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:27:24: note: in expansion of macro 'u256'
stream.c: int ExpandKey(u32 K[], u256 rk[], u32 key[]);
stream.c: ^
stream.c: stream.c: In function 'crypto_stream_speck64128ctr_avx2':
stream.c: Intrinsics_AVX2_64block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:42:3: note: in expansion of macro 'u256'
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/speck64128ctr/avx512
Compiler: cc
stream.c: In file included from Speck64128AVX512.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:23:84: note: in expansion of macro 'u512'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out, u32 nonce[], u512 rk[], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:25:113: note: in expansion of macro 'u512'
stream.c: inline __attribute__((always_inline)) int Encrypt_Xor(unsigned char *out, const unsigned char *in, u32 nonce[], u512 rk[], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:26:24: note: in expansion of macro 'u512'
stream.c: int ExpandKey(u32 K[], u512 rk[], u32 key[]);
stream.c: ^
stream.c: stream.c: In function 'crypto_stream_speck64128ctr_avx512':
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:41:3: note: in expansion of macro 'u512'
stream.c: ...
Number of similar (compiler,implementation) pairs: 106, namely:
CompilerImplementations
cc avx512
gcc avx512
gcc -O2 -fomit-frame-pointer avx512
gcc -O3 -fomit-frame-pointer avx512
gcc -O -fomit-frame-pointer avx512
gcc -Os -fomit-frame-pointer avx512
gcc -fno-schedule-insns -O2 -fomit-frame-pointer avx512
gcc -fno-schedule-insns -O3 -fomit-frame-pointer avx512
gcc -fno-schedule-insns -O -fomit-frame-pointer avx512
gcc -fno-schedule-insns -Os -fomit-frame-pointer avx512
gcc -funroll-loops avx512
gcc -funroll-loops -O2 -fomit-frame-pointer avx512
gcc -funroll-loops -O3 -fomit-frame-pointer avx512
gcc -funroll-loops -O -fomit-frame-pointer avx512
gcc -funroll-loops -Os -fomit-frame-pointer avx512
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer avx512
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer avx512
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer avx512
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -O -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -Os -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer avx512
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer avx512
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer avx512
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer avx512
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer avx512
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer avx512
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer avx512
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer avx512
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer avx512
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer avx512
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer avx512
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer avx512
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer avx512
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer avx512
gcc -m64 -O2 -fomit-frame-pointer avx512
gcc -m64 -O3 -fomit-frame-pointer avx512
gcc -m64 -O -fomit-frame-pointer avx512
gcc -m64 -Os -fomit-frame-pointer avx512
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer avx512
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer avx512
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer avx512
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer avx512
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer avx512
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer avx512
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer avx512
gcc -m64 -march=core2 -O2 -fomit-frame-pointer avx512
gcc -m64 -march=core2 -O3 -fomit-frame-pointer avx512
gcc -m64 -march=core2 -O -fomit-frame-pointer avx512
gcc -m64 -march=core2 -Os -fomit-frame-pointer avx512
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer avx512
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer avx512
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer avx512
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer avx512
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer avx512
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer avx512
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer avx512
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer avx512
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer avx512
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer avx512
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer avx512
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer avx512
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer avx512
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer avx512
gcc -m64 -march=corei7 -O -fomit-frame-pointer avx512
gcc -m64 -march=corei7 -Os -fomit-frame-pointer avx512
gcc -m64 -march=k8 -O2 -fomit-frame-pointer avx512
gcc -m64 -march=k8 -O3 -fomit-frame-pointer avx512
gcc -m64 -march=k8 -O -fomit-frame-pointer avx512
gcc -m64 -march=k8 -Os -fomit-frame-pointer avx512
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer avx512
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer avx512
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer avx512
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer avx512
gcc -m64 -march=nocona -O2 -fomit-frame-pointer avx512
gcc -m64 -march=nocona -O3 -fomit-frame-pointer avx512
gcc -m64 -march=nocona -O -fomit-frame-pointer avx512
gcc -m64 -march=nocona -Os -fomit-frame-pointer avx512
gcc -march=barcelona -O2 -fomit-frame-pointer avx512
gcc -march=barcelona -O3 -fomit-frame-pointer avx512
gcc -march=barcelona -O -fomit-frame-pointer avx512
gcc -march=barcelona -Os -fomit-frame-pointer avx512
gcc -march=k8 -O2 -fomit-frame-pointer avx512
gcc -march=k8 -O3 -fomit-frame-pointer avx512
gcc -march=k8 -O -fomit-frame-pointer avx512
gcc -march=k8 -Os -fomit-frame-pointer avx512
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv avx512
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv avx512
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv avx512
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv avx512
gcc -march=nocona -O2 -fomit-frame-pointer avx512
gcc -march=nocona -O3 -fomit-frame-pointer avx512
gcc -march=nocona -O -fomit-frame-pointer avx512
gcc -march=nocona -Os -fomit-frame-pointer avx512

Compiler output

Implementation: crypto_stream/speck64128ctr/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 Speck64128SSE4.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 Speck64128SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:24:84: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out, u32 nonce[], u128 rk[], 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:26:113: 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[], 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:27:24: note: in expansion of macro 'u128'
stream.c: int ExpandKey(u32 K[], u128 rk[], u32 key[]);
stream.c: ...
stream.c: In file included from Intrinsics_SSE4_64block.h:5:0,
stream.c: from Speck64128SSE4.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 Speck64128SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:24:84: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out, u32 nonce[], u128 rk[], 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:26:113: 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[], 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:27:24: note: in expansion of macro 'u128'
stream.c: int ExpandKey(u32 K[], u128 rk[], u32 key[]);
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/speck64128ctr/avx2
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from Speck64128AVX2.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:24:84: note: in expansion of macro 'u256'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out, u32 nonce[], u256 rk[], 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:26:113: note: in expansion of macro 'u256'
stream.c: inline __attribute__((always_inline)) int Encrypt_Xor(unsigned char *out, const unsigned char *in, u32 nonce[], u256 rk[], 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:27:24: note: in expansion of macro 'u256'
stream.c: int ExpandKey(u32 K[], u256 rk[], u32 key[]);
stream.c: ^
stream.c: stream.c: In function 'crypto_stream_speck64128ctr_avx2':
stream.c: Intrinsics_AVX2_64block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:42:3: note: in expansion of macro 'u256'
stream.c: ...
stream.c: In file included from Speck64128AVX2.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:24:84: note: in expansion of macro 'u256'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out, u32 nonce[], u256 rk[], 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:26:113: note: in expansion of macro 'u256'
stream.c: inline __attribute__((always_inline)) int Encrypt_Xor(unsigned char *out, const unsigned char *in, u32 nonce[], u256 rk[], 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:27:24: note: in expansion of macro 'u256'
stream.c: int ExpandKey(u32 K[], u256 rk[], u32 key[]);
stream.c: ^
stream.c: stream.c: In function 'crypto_stream_speck64128ctr_avx2':
stream.c: Intrinsics_AVX2_64block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:42:3: note: in expansion of macro 'u256'
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/speck64128ctr/avx512
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from Speck64128AVX512.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:23:84: note: in expansion of macro 'u512'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out, u32 nonce[], u512 rk[], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:25:113: note: in expansion of macro 'u512'
stream.c: inline __attribute__((always_inline)) int Encrypt_Xor(unsigned char *out, const unsigned char *in, u32 nonce[], u512 rk[], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:26:24: note: in expansion of macro 'u512'
stream.c: int ExpandKey(u32 K[], u512 rk[], u32 key[]);
stream.c: ^
stream.c: stream.c: In function 'crypto_stream_speck64128ctr_avx512':
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:41:3: note: in expansion of macro 'u512'
stream.c: ...
stream.c: In file included from Speck64128AVX512.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:23:84: note: in expansion of macro 'u512'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out, u32 nonce[], u512 rk[], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:25:113: note: in expansion of macro 'u512'
stream.c: inline __attribute__((always_inline)) int Encrypt_Xor(unsigned char *out, const unsigned char *in, u32 nonce[], u512 rk[], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:26:24: note: in expansion of macro 'u512'
stream.c: int ExpandKey(u32 K[], u512 rk[], u32 key[]);
stream.c: ^
stream.c: stream.c: In function 'crypto_stream_speck64128ctr_avx512':
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:41:3: note: in expansion of macro 'u512'
stream.c: ...
Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer avx512
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer avx512
gcc -m64 -march=barcelona -O -fomit-frame-pointer avx512
gcc -m64 -march=barcelona -Os -fomit-frame-pointer avx512

Compiler output

Implementation: crypto_stream/speck64128ctr/avx2
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer
stream.c: In file included from Speck64128AVX2.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:150:24: 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: Speck64128AVX2.h:23:20: error: incompatible types when assigning to type '__m256i' from type 'int'
stream.c: #define R(X,Y,k) (X=XOR(ADD(ROR8(X),Y),k), Y=XOR(ROL(Y,3),X))
stream.c: ^
stream.c: Speck64128AVX2.h:25:22: note: in expansion of macro 'R'
stream.c: #define Rx8(X,Y,k) (R(X[0],Y[0],k))
stream.c: ^
stream.c: Speck64128AVX2.h:45:23: note: in expansion of macro 'Rx8'
stream.c: #define Enc(X,Y,k,n) (Rx##n(X,Y,k[0]), Rx##n(X,Y,k[1]), Rx##n(X,Y,k[2]), Rx##n(X,Y,k[3]), Rx##n(X,Y,k[4]), Rx##n(X,Y,k[5]), Rx##n(X,Y,k[6]), Rx##n(X,Y,k[7]), \
stream.c: ^
stream.c: stream.c:152:21: note: in expansion of macro 'Enc'
stream.c: if (numbytes==64) Enc(X,Y,rk,8);
stream.c: ^
stream.c: Speck64128AVX2.h:23:45: error: incompatible types when assigning to type '__m256i' from type 'int'
stream.c: #define R(X,Y,k) (X=XOR(ADD(ROR8(X),Y),k), Y=XOR(ROL(Y,3),X))
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