Implementation notes: amd64, h8bobcat, crypto_stream/speck64128ctr

Computer: h8bobcat
Architecture: amd64
CPU ID: AuthenticAMD-00500f20-178bfbff
SUPERCOP version: 20171218
Operation: crypto_stream
Primitive: speck64128ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
14264? ? ?? ? ?sse4gcc_-m64_-march=core2_-Os_-fomit-frame-pointer2017091320170904
14269? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2017091320170904
14269? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2017091320170904
14269? ? ?? ? ?sse4gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2017091320170904
14279? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2017091320170904
14279? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2017091320170904
14326? ? ?? ? ?sse4clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2017091320170904
14326? ? ?? ? ?sse4clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2017091320170904
14359? ? ?? ? ?sse4gcc_-m64_-march=core2_-O2_-fomit-frame-pointer2017091320170904
14359? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2017091320170904
14359? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2017091320170904
14359? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2017091320170904
14364? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2017091320170904
14364? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2017091320170904
14364? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2017091320170904
14369? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2017091320170904
14388? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2017091320170904
14393? ? ?? ? ?sse4gcc_-m64_-march=core2_-O3_-fomit-frame-pointer2017091320170904
14393? ? ?? ? ?sse4gcc_-m64_-march=core2_-O_-fomit-frame-pointer2017091320170904
14393? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2017091320170904
14393? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2017091320170904
14393? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O_-fomit-frame-pointer2017091320170904
14393? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2017091320170904

Compiler output

Implementation: crypto_stream/speck64128ctr/sse4
Compiler: cc
stream.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:32:0,
stream.c: from Intrinsics_SSE4_64block.h:5,
stream.c: from Speck64128SSE4.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: /usr/lib/gcc/x86_64-linux-gnu/5/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 Speck64128SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_64block.h:15:13: error: called from here
stream.c: #define XOR _mm_xor_si128
stream.c: ^
stream.c: Speck64128SSE4.h:23:21: 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: Speck64128SSE4.h:25:22: note: in expansion of macro 'R'
stream.c: #define Rx4(X,Y,k) (R(X[0],Y[0],k))
stream.c: ^
stream.c: Speck64128SSE4.h:48:45: note: in expansion of macro 'Rx4'
stream.c: Rx##n(X,Y,k[24]), Rx##n(X,Y,k[25]), Rx##n(X,Y,k[26]))
stream.c: ^
stream.c: stream.c:134:21: 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: 71, 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=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: 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:150:3: 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 /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_64block.h:5,
stream.c: from Speck64128AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/5/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 Speck64128AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_64block.h:17:13: error: 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:150:24: note: in expansion of macro 'SET8'
stream.c: ...

Number of similar (compiler,implementation) pairs: 92, 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 -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 -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 -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=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 -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=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
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: 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 /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:45:0,
stream.c: from Intrinsics_AVX512_64block.h:5,
stream.c: from Speck64128AVX512.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx512fintrin.h:5818:1: 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 Speck64128AVX512.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX512_64block.h:31:18: error: 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: 92, 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=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 -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 -O -fomit-frame-pointer avx512
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer avx512
gcc -m64 -march=corei7 -O2 -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: clang -O3 -fomit-frame-pointer -Qunused-arguments
stream.c: stream.c:134:21: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'Encrypt' that is compiled without support for 'ssse3'
stream.c: if (numbytes==32) Enc(X,Y,rk,4);
stream.c: ^
stream.c: ./Speck64128SSE4.h:45:23: note: expanded from macro 'Enc'
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: <scratch space>:93:1: note: expanded from here
stream.c: Rx4
stream.c: ^
stream.c: ./Speck64128SSE4.h:25:22: note: expanded from macro 'Rx4'
stream.c: #define Rx4(X,Y,k) (R(X[0],Y[0],k))
stream.c: ^
stream.c: ./Speck64128SSE4.h:23:29: note: expanded from macro 'R'
stream.c: #define R(X,Y,k) (X=XOR(ADD(ROR8(X),Y),k), Y=XOR(ROL(Y,3),X))
stream.c: ^
stream.c: ./Intrinsics_SSE4_64block.h:40:19: note: expanded from macro 'ROR8'
stream.c: #define ROR8(X) (SHFL(X,R8))
stream.c: ^
stream.c: ./Intrinsics_SSE4_64block.h:35:14: note: expanded from macro 'SHFL'
stream.c: #define SHFL _mm_shuffle_epi8
stream.c: ^
stream.c: stream.c:134:21: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'Encrypt' that is compiled without support for 'ssse3'
stream.c: ./Speck64128SSE4.h:45:41: note: expanded from macro 'Enc'
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: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments sse4
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments sse4
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments sse4
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments sse4

Compiler output

Implementation: crypto_stream/speck64128ctr/avx512
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
stream.c: stream.c:135:5: warning: implicit declaration of function '_mm512_set_epi32' is invalid in C99 [-Wimplicit-function-declaration]
stream.c: SET1(X[0],nonce[1]); SET16(Y[0],nonce[0]);
stream.c: ^
stream.c: ./Intrinsics_AVX512_64block.h:25:22: note: expanded from macro 'SET1'
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: ./Intrinsics_AVX512_64block.h:14:13: note: expanded from macro 'SET'
stream.c: #define SET _mm512_set_epi32
stream.c: ^
stream.c: stream.c:135:5: error: assigning to '__m512i' (vector of 8 'long long' values) from incompatible type 'int'
stream.c: SET1(X[0],nonce[1]); SET16(Y[0],nonce[0]);
stream.c: ^~~~~~~~~~~~~~~~~~~
stream.c: ./Intrinsics_AVX512_64block.h:25:21: note: expanded from macro 'SET1'
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:135:26: error: assigning to '__m512i' (vector of 8 'long long' values) from incompatible type 'int'
stream.c: SET1(X[0],nonce[1]); SET16(Y[0],nonce[0]);
stream.c: ^~~~~~~~~~~~~~~~~~~~
stream.c: ./Intrinsics_AVX512_64block.h:26:21: note: expanded from macro 'SET16'
stream.c: #define SET16(X,c)(X=SET(c,c,c,c,c,c,c,c,c,c,c,c,c,c,c,c), X=ADD(X,_q16))
stream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: stream.c:135:26: error: passing 'int' to parameter of incompatible type '__m512i' (vector of 8 'long long' values)
stream.c: SET1(X[0],nonce[1]); SET16(Y[0],nonce[0]);
stream.c: ^~~~~~~~~~~~~~~~~~~~
stream.c: ./Intrinsics_AVX512_64block.h:26:68: note: expanded from macro 'SET16'
stream.c: ...

Number of similar (compiler,implementation) pairs: 6, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments avx512
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments avx512
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx512
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx512
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx512
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx512

Compiler output

Implementation: crypto_stream/speck64128ctr/avx2
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
stream.c: stream.c:332:3: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'ExpandKey' that is compiled without support for 'sse4.2'
stream.c: EK(A,B,C,D,rk,key);
stream.c: ^
stream.c: ./Speck64128AVX2.h:53:28: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,D,k,key) (RK(B,A,k,key,0), RK(C,A,k,key,1), RK(D,A,k,key,2), RK(B,A,k,key,3), RK(C,A,k,key,4), RK(D,A,k,key,5), RK(B,A,k,key,6), \
stream.c: ^
stream.c: ./Speck64128AVX2.h:51:28: note: expanded from macro 'RK'
stream.c: #define RK(X,Y,k,key,i) (SET1(k[i],Y), key[i]=Y, X=RCS(X,8), X+=Y, X^=i, Y=LCS(Y,3), Y^=X)
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:24:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi32
stream.c: ^
stream.c: stream.c:332:3: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'ExpandKey' that is compiled without support for 'sse4.2'
stream.c: ./Speck64128AVX2.h:53:46: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,D,k,key) (RK(B,A,k,key,0), RK(C,A,k,key,1), RK(D,A,k,key,2), RK(B,A,k,key,3), RK(C,A,k,key,4), RK(D,A,k,key,5), RK(B,A,k,key,6), \
stream.c: ^
stream.c: ./Speck64128AVX2.h:51:28: note: expanded from macro 'RK'
stream.c: #define RK(X,Y,k,key,i) (SET1(k[i],Y), key[i]=Y, X=RCS(X,8), X+=Y, X^=i, Y=LCS(Y,3), Y^=X)
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c: ^
stream.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments avx2
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx2
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx2
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx2

Compiler output

Implementation: crypto_stream/speck64128ctr/avx2
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments
stream.c: stream.c:332:3: error: always_inline function '_mm256_set_epi32' requires target feature 'xsave', but would be inlined into function 'ExpandKey' that is compiled without support for 'xsave'
stream.c: EK(A,B,C,D,rk,key);
stream.c: ^
stream.c: ./Speck64128AVX2.h:53:28: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,D,k,key) (RK(B,A,k,key,0), RK(C,A,k,key,1), RK(D,A,k,key,2), RK(B,A,k,key,3), RK(C,A,k,key,4), RK(D,A,k,key,5), RK(B,A,k,key,6), \
stream.c: ^
stream.c: ./Speck64128AVX2.h:51:28: note: expanded from macro 'RK'
stream.c: #define RK(X,Y,k,key,i) (SET1(k[i],Y), key[i]=Y, X=RCS(X,8), X+=Y, X^=i, Y=LCS(Y,3), Y^=X)
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:24:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi32
stream.c: ^
stream.c: stream.c:332:3: error: always_inline function '_mm256_set_epi32' requires target feature 'xsave', but would be inlined into function 'ExpandKey' that is compiled without support for 'xsave'
stream.c: ./Speck64128AVX2.h:53:46: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,D,k,key) (RK(B,A,k,key,0), RK(C,A,k,key,1), RK(D,A,k,key,2), RK(B,A,k,key,3), RK(C,A,k,key,4), RK(D,A,k,key,5), RK(B,A,k,key,6), \
stream.c: ^
stream.c: ./Speck64128AVX2.h:51:28: note: expanded from macro 'RK'
stream.c: #define RK(X,Y,k,key,i) (SET1(k[i],Y), key[i]=Y, X=RCS(X,8), X+=Y, X^=i, Y=LCS(Y,3), Y^=X)
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c: ^
stream.c: ...

Number of similar (compiler,implementation) pairs: 2, namely:
CompilerImplementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx2

Compiler output

Implementation: crypto_stream/speck64128ctr/sse4
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:32:0,
stream.c: from Intrinsics_SSE4_64block.h:5,
stream.c: from Speck64128SSE4.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: /usr/lib/gcc/x86_64-linux-gnu/5/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 Speck64128SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_64block.h:15:13: error: called from here
stream.c: #define XOR _mm_xor_si128
stream.c: ^
stream.c: Speck64128SSE4.h:23:21: 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: Speck64128SSE4.h:25:22: note: in expansion of macro 'R'
stream.c: #define Rx4(X,Y,k) (R(X[0],Y[0],k))
stream.c: ^
stream.c: Speck64128SSE4.h:48:45: note: in expansion of macro 'Rx4'
stream.c: Rx##n(X,Y,k[24]), Rx##n(X,Y,k[25]), Rx##n(X,Y,k[26]))
stream.c: ^
stream.c: stream.c:134:21: 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 /usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:32:0,
stream.c: from Intrinsics_SSE4_64block.h:5,
stream.c: from Speck64128SSE4.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: /usr/lib/gcc/x86_64-linux-gnu/5/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 Speck64128SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_64block.h:15:13: error: called from here
stream.c: #define XOR _mm_xor_si128
stream.c: ^
stream.c: Speck64128SSE4.h:23:21: 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: Speck64128SSE4.h:25:22: note: in expansion of macro 'R'
stream.c: #define Rx4(X,Y,k) (R(X[0],Y[0],k))
stream.c: ^
stream.c: Speck64128SSE4.h:48:45: note: in expansion of macro 'Rx4'
stream.c: Rx##n(X,Y,k[24]), Rx##n(X,Y,k[25]), Rx##n(X,Y,k[26]))
stream.c: ^
stream.c: stream.c:134:21: 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/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: 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:150:3: 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 /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_64block.h:5,
stream.c: from Speck64128AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/5/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 Speck64128AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_64block.h:17:13: error: 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:150:24: note: in expansion of macro 'SET8'
stream.c: ...
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: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:150:3: 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 /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_64block.h:5,
stream.c: from Speck64128AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/5/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 Speck64128AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_64block.h:17:13: error: 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:150:24: 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/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: 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 /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:45:0,
stream.c: from Intrinsics_AVX512_64block.h:5,
stream.c: from Speck64128AVX512.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx512fintrin.h:5818:1: 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 Speck64128AVX512.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX512_64block.h:31:18: error: 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 Speck64128AVX512.h:17:0,
stream.c: from stream.c:20:
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 /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:45:0,
stream.c: from Intrinsics_AVX512_64block.h:5,
stream.c: from Speck64128AVX512.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx512fintrin.h:5818:1: 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 Speck64128AVX512.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX512_64block.h:31:18: error: 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