Implementation notes: amd64, manny1024, crypto_stream/speck6496ctr

Computer: manny1024
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20170904
Operation: crypto_stream
Primitive: speck6496ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
944? ? ?? ? ?avx512gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017091720170904
946? ? ?? ? ?avx512gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017091720170904
946? ? ?? ? ?avx512gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017091720170904
948? ? ?? ? ?avx512gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017091720170904
948? ? ?? ? ?avx512gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017091720170904
950? ? ?? ? ?avx512gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017091720170904
976? ? ?? ? ?avx512gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017091720170904
982? ? ?? ? ?avx512gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017091720170904
1640? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017091720170904
1646? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017091720170904
1648? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O_-fomit-frame-pointer2017091720170904
1656? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017091720170904
1658? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017091720170904
1660? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017091720170904
1662? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017091720170904
1666? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017091720170904
1696? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-Os_-fomit-frame-pointer2017091720170904
1704? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O2_-fomit-frame-pointer2017091720170904
1706? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O3_-fomit-frame-pointer2017091720170904
1730? ? ?? ? ?avx512icc_-xCORE-AVX512_-O2_-fomit-frame-pointer2017091720170904
1734? ? ?? ? ?avx512icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer2017091720170904
1750? ? ?? ? ?avx512icc_-xCORE-AVX2_-O2_-fomit-frame-pointer2017091720170904
1826? ? ?? ? ?avx512icc_-xCORE-AVX512_-O3_-fomit-frame-pointer2017091720170904
1838? ? ?? ? ?avx512icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer2017091720170904
1858? ? ?? ? ?avx512icc_-xCORE-AVX2_-O3_-fomit-frame-pointer2017091720170904
1892? ? ?? ? ?avx512icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer2017091720170904
1898? ? ?? ? ?avx512icc2017091720170904
1898? ? ?? ? ?avx512icc_-no-vec2017091720170904
1950? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017091720170904
2010? ? ?? ? ?avx512icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer2017091720170904
2790? ? ?? ? ?sse4icc_-xCORE-AVX512_-O2_-fomit-frame-pointer2017091720170904
2826? ? ?? ? ?sse4icc_-xCORE-AVX512_-O3_-fomit-frame-pointer2017091720170904
3118? ? ?? ? ?avx2icc_-xCORE-AVX2_-O3_-fomit-frame-pointer2017091720170904
3140? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017091720170904
3142? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017091720170904
3150? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O_-fomit-frame-pointer2017091720170904
3160? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017091720170904
3162? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017091720170904
3166? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2017091720170904
3166? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2017091720170904
3166? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017091720170904
3166? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017091720170904
3168? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017091720170904
3168? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017091720170904
3202? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2017091720170904
3206? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2017091720170904
3208? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2017091720170904
3210? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2017091720170904
3210? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2017091720170904
3210? ? ?? ? ?sse4icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer2017091720170904
3216? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2017091720170904
3216? ? ?? ? ?sse4icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer2017091720170904
3216? ? ?? ? ?sse4icc_-xCORE-AVX2_-O2_-fomit-frame-pointer2017091720170904
3222? ? ?? ? ?sse4icc_-xCORE-AVX2_-O3_-fomit-frame-pointer2017091720170904
3228? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-Os_-fomit-frame-pointer2017091720170904
3232? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O3_-fomit-frame-pointer2017091720170904
3240? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O2_-fomit-frame-pointer2017091720170904
3240? ? ?? ? ?sse4gcc_-m64_-march=core2_-Os_-fomit-frame-pointer2017091720170904
3242? ? ?? ? ?sse4icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer2017091720170904
3244? ? ?? ? ?sse4gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017091720170904
3246? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017091720170904
3252? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017091720170904
3258? ? ?? ? ?sse4icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer2017091720170904
3292? ? ?? ? ?sse4icc2017091720170904
3312? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017091720170904
3314? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017091720170904
3318? ? ?? ? ?sse4gcc_-m64_-march=core2_-O2_-fomit-frame-pointer2017091720170904
3322? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017091720170904
3322? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017091720170904
3328? ? ?? ? ?sse4gcc_-m64_-march=core2_-O_-fomit-frame-pointer2017091720170904
3328? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017091720170904
3328? ? ?? ? ?avx2icc_-xCORE-AVX2_-O2_-fomit-frame-pointer2017091720170904
3334? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2017091720170904
3338? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2017091720170904
3338? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017091720170904
3340? ? ?? ? ?sse4gcc_-m64_-march=core2_-O3_-fomit-frame-pointer2017091720170904
3340? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2017091720170904
3356? ? ?? ? ?sse4icc_-no-vec2017091720170904
4962? ? ?? ? ?avx2icc_-xCORE-AVX512_-O3_-fomit-frame-pointer2017091720170904
5276? ? ?? ? ?avx2icc_-xCOMMON-AVX512_-O3_-fomit-frame-pointer2017091720170904
5588? ? ?? ? ?avx2icc_-xCORE-AVX512_-O2_-fomit-frame-pointer2017091720170904
5698? ? ?? ? ?avx2icc_-xCOMMON-AVX512_-O2_-fomit-frame-pointer2017091720170904
5990? ? ?? ? ?avx2icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer2017091720170904
6244? ? ?? ? ?avx2icc2017091720170904
6390? ? ?? ? ?avx2icc_-no-vec2017091720170904
6512? ? ?? ? ?avx2icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer2017091720170904

Compiler output

Implementation: crypto_stream/speck6496ctr/sse4
Compiler: cc
stream.c: In file included from Intrinsics_SSE4_64block.h:5:0,
stream.c: from Speck6496SSE4.h:16,
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 Speck6496SSE4.h:16:0,
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: 1, namely:
CompilerImplementations
cc sse4

Compiler output

Implementation: crypto_stream/speck6496ctr/avx2
Compiler: cc
stream.c: In file included from Speck6496AVX2.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_speck6496ctr_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: 1, namely:
CompilerImplementations
cc avx2

Compiler output

Implementation: crypto_stream/speck6496ctr/avx512
Compiler: cc
stream.c: In file included from Speck6496AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:24:84: 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:26:113: 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:27:24: 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_speck6496ctr_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:42:3: note: in expansion of macro 'u512'
stream.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
cc avx512

Compiler output

Implementation: crypto_stream/speck6496ctr/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_64block.h:5,
stream.c: from Speck6496SSE4.h:16,
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 Speck6496SSE4.h:16:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_64block.h:15:13: note: called from here
stream.c: #define XOR _mm_xor_si128
stream.c:
stream.c: Speck6496SSE4.h:22:21: note: in expansion of macro 'XOR'
stream.c: #define R(X,Y,k) (X=XOR(ADD(ROR8(X),Y),k), Y=XOR(ROL(Y,3),X))
stream.c: ^~~
stream.c: Speck6496SSE4.h:24:22: note: in expansion of macro 'R'
stream.c: #define Rx4(X,Y,k) (R(X[0],Y[0],k))
stream.c: ^
stream.c: Speck6496SSE4.h:46:27: note: in expansion of macro 'Rx4'
stream.c: Rx##n(X,Y,k[24]), Rx##n(X,Y,k[25]))
stream.c: ^~
stream.c: stream.c:133:21: note: in expansion of macro 'Enc'
stream.c: if (numbytes==32) Enc(X,Y,rk,4);
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/speck6496ctr/avx2
Compiler: gcc
stream.c: In file included from Speck6496AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_64block.h:25:21: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c: ~~^~~~~~~~~~~~~~~~~~~~~~
stream.c: stream.c:147:3: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET8(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_64block.h:5,
stream.c: from Speck6496AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/avx2intrin.h:119:1: error: inlining failed in call to always_inline '_mm256_add_epi32': target specific option mismatch
stream.c: _mm256_add_epi32 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Speck6496AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_64block.h:17:13: note: called from here
stream.c: #define ADD _mm256_add_epi32
stream.c: ^
stream.c: Intrinsics_AVX2_64block.h:26:46: note: in expansion of macro 'ADD'
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:147:24: note: in expansion of macro 'SET8'
stream.c: ...
Number of similar (compiler,implementation) pairs: 86, namely:
CompilerImplementations
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/speck6496ctr/avx512
Compiler: gcc
stream.c: In file included from Speck6496AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX512_64block.h:25:21: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c,c,c,c,c,c,c,c,c))
stream.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: stream.c:135:5: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET16(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:45:0,
stream.c: from Intrinsics_AVX512_64block.h:5,
stream.c: from Speck6496AVX512.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/avx512fintrin.h:5819:1: error: inlining failed in call to always_inline '_mm512_storeu_si512': target specific option mismatch
stream.c: _mm512_storeu_si512 (void *__P, __m512i __A)
stream.c: ^~~~~~~~~~~~~~~~~~~
stream.c: In file included from Speck6496AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX512_64block.h:31:18: note: called from here
stream.c: #define ST(ip,X) _mm512_storeu_si512((__m512i *)(ip),X)
stream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: Intrinsics_AVX512_64block.h:32:42: note: in expansion of macro 'ST'
stream.c: #define STORE(out,X,Y) (ST(out,LOW(Y,X)),ST(out+64,HIGH(Y,X)))
stream.c: ^~
stream.c: stream.c:138:5: note: in expansion of macro 'STORE'
stream.c: ...
Number of similar (compiler,implementation) pairs: 98, namely:
CompilerImplementations
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 -O3 -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=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=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/speck6496ctr/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_64block.h:5,
stream.c: from Speck6496SSE4.h:16,
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 Speck6496SSE4.h:16:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_64block.h:15:13: note: called from here
stream.c: #define XOR _mm_xor_si128
stream.c:
stream.c: Speck6496SSE4.h:22:21: note: in expansion of macro 'XOR'
stream.c: #define R(X,Y,k) (X=XOR(ADD(ROR8(X),Y),k), Y=XOR(ROL(Y,3),X))
stream.c: ^~~
stream.c: Speck6496SSE4.h:24:22: note: in expansion of macro 'R'
stream.c: #define Rx4(X,Y,k) (R(X[0],Y[0],k))
stream.c: ^
stream.c: Speck6496SSE4.h:46:27: note: in expansion of macro 'Rx4'
stream.c: Rx##n(X,Y,k[24]), Rx##n(X,Y,k[25]))
stream.c: ^~
stream.c: stream.c:133:21: note: in expansion of macro 'Enc'
stream.c: if (numbytes==32) Enc(X,Y,rk,4);
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_64block.h:5,
stream.c: from Speck6496SSE4.h:16,
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 Speck6496SSE4.h:16:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_64block.h:15:13: note: called from here
stream.c: #define XOR _mm_xor_si128
stream.c:
stream.c: Speck6496SSE4.h:22:21: note: in expansion of macro 'XOR'
stream.c: #define R(X,Y,k) (X=XOR(ADD(ROR8(X),Y),k), Y=XOR(ROL(Y,3),X))
stream.c: ^~~
stream.c: Speck6496SSE4.h:24:22: note: in expansion of macro 'R'
stream.c: #define Rx4(X,Y,k) (R(X[0],Y[0],k))
stream.c: ^
stream.c: Speck6496SSE4.h:46:27: note: in expansion of macro 'Rx4'
stream.c: Rx##n(X,Y,k[24]), Rx##n(X,Y,k[25]))
stream.c: ^~
stream.c: stream.c:133:21: note: in expansion of macro 'Enc'
stream.c: if (numbytes==32) Enc(X,Y,rk,4);
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/speck6496ctr/avx2
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from Speck6496AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_64block.h:25:21: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c: ~~^~~~~~~~~~~~~~~~~~~~~~
stream.c: stream.c:147:3: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET8(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_64block.h:5,
stream.c: from Speck6496AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/avx2intrin.h:119:1: error: inlining failed in call to always_inline '_mm256_add_epi32': target specific option mismatch
stream.c: _mm256_add_epi32 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Speck6496AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_64block.h:17:13: note: called from here
stream.c: #define ADD _mm256_add_epi32
stream.c: ^
stream.c: Intrinsics_AVX2_64block.h:26:46: note: in expansion of macro 'ADD'
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:147:24: note: in expansion of macro 'SET8'
stream.c: ...
stream.c: In file included from Speck6496AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_64block.h:25:21: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c: ~~^~~~~~~~~~~~~~~~~~~~~~
stream.c: stream.c:147:3: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET8(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_64block.h:5,
stream.c: from Speck6496AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/avx2intrin.h:119:1: error: inlining failed in call to always_inline '_mm256_add_epi32': target specific option mismatch
stream.c: _mm256_add_epi32 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Speck6496AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_64block.h:17:13: note: called from here
stream.c: #define ADD _mm256_add_epi32
stream.c: ^
stream.c: Intrinsics_AVX2_64block.h:26:46: note: in expansion of macro 'ADD'
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:147:24: note: in expansion of macro 'SET8'
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/speck6496ctr/avx512
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from Speck6496AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX512_64block.h:25:21: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c,c,c,c,c,c,c,c,c))
stream.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: stream.c:135:5: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET16(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:45:0,
stream.c: from Intrinsics_AVX512_64block.h:5,
stream.c: from Speck6496AVX512.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/avx512fintrin.h:5819:1: error: inlining failed in call to always_inline '_mm512_storeu_si512': target specific option mismatch
stream.c: _mm512_storeu_si512 (void *__P, __m512i __A)
stream.c: ^~~~~~~~~~~~~~~~~~~
stream.c: In file included from Speck6496AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX512_64block.h:31:18: note: called from here
stream.c: #define ST(ip,X) _mm512_storeu_si512((__m512i *)(ip),X)
stream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: Intrinsics_AVX512_64block.h:32:42: note: in expansion of macro 'ST'
stream.c: #define STORE(out,X,Y) (ST(out,LOW(Y,X)),ST(out+64,HIGH(Y,X)))
stream.c: ^~
stream.c: stream.c:138:5: note: in expansion of macro 'STORE'
stream.c: ...
stream.c: In file included from Speck6496AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX512_64block.h:25:21: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c,c,c,c,c,c,c,c,c))
stream.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: stream.c:135:5: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET16(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:45:0,
stream.c: from Intrinsics_AVX512_64block.h:5,
stream.c: from Speck6496AVX512.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/avx512fintrin.h:5819:1: error: inlining failed in call to always_inline '_mm512_storeu_si512': target specific option mismatch
stream.c: _mm512_storeu_si512 (void *__P, __m512i __A)
stream.c: ^~~~~~~~~~~~~~~~~~~
stream.c: In file included from Speck6496AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX512_64block.h:31:18: note: called from here
stream.c: #define ST(ip,X) _mm512_storeu_si512((__m512i *)(ip),X)
stream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: Intrinsics_AVX512_64block.h:32:42: note: in expansion of macro 'ST'
stream.c: #define STORE(out,X,Y) (ST(out,LOW(Y,X)),ST(out+64,HIGH(Y,X)))
stream.c: ^~
stream.c: stream.c:138:5: note: in expansion of macro 'STORE'
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/speck6496ctr/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_64block.h:5,
stream.c: from Speck6496AVX2.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/avx2intrin.h:119:1: error: inlining failed in call to always_inline '_mm256_add_epi32': target specific option mismatch
stream.c: _mm256_add_epi32 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Speck6496AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_64block.h:17:13: note: called from here
stream.c: #define ADD _mm256_add_epi32
stream.c: ^
stream.c: Intrinsics_AVX2_64block.h:26:46: note: in expansion of macro 'ADD'
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:147:24: 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 /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_64block.h:5,
stream.c: from Speck6496AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /home_nfs/bdolbeaur/gcc-6.3.0-full+isl-inca/lib/gcc/x86_64-pc-linux-gnu/6.3.0/include/avx2intrin.h:119:1: error: inlining failed in call to always_inline '_mm256_add_epi32': target specific option mismatch
stream.c: _mm256_add_epi32 (__m256i __A, __m256i __B)
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