Implementation notes: amd64, morningstar, crypto_stream/speck128128ctr

Computer: morningstar
Architecture: amd64
CPU ID: AuthenticAMD-00100f42-178bfbff
SUPERCOP version: 20170904
Operation: crypto_stream
Primitive: speck128128ctr

Compiler output

Implementation: crypto_stream/speck128128ctr/avx2
Compiler: cc
stream.c: In file included from Speck128128AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.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))
stream.c: ^
stream.c: stream.c:128:3: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET4(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_128block.h:5,
stream.c: from Speck128128AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:126:1: error: inlining failed in call to always_inline '_mm256_add_epi64': target specific option mismatch
stream.c: _mm256_add_epi64 (__m256i __A, __m256i __B)
stream.c: ^
stream.c: In file included from Speck128128AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:17:13: error: called from here
stream.c: #define ADD _mm256_add_epi64
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:26:38: note: in expansion of macro 'ADD'
stream.c: #define SET4(X,c) (X=SET(c,c,c,c), X=ADD(X,_q))
stream.c: ^
stream.c: stream.c:128:24: note: in expansion of macro 'SET4'
stream.c: ...
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/speck128128ctr/avx512
Compiler: cc
stream.c: In file included from Speck128128AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX512_128block.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))
stream.c: ^
stream.c: stream.c:135:5: 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:45:0,
stream.c: from Intrinsics_AVX512_128block.h:5,
stream.c: from Speck128128AVX512.h:17,
stream.c: from stream.c:21:
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 Speck128128AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX512_128block.h:32:18: error: called from here
stream.c: #define ST(ip,X) _mm512_storeu_si512((void *)(ip),X)
stream.c: ^
stream.c: Intrinsics_AVX512_128block.h:33:43: 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/speck128128ctr/sse4
Compiler: cc
stream.c: stream.c:99:12: error: static declaration of 'Encrypt' follows non-static declaration
stream.c: static int Encrypt(unsigned char *out, u64 nonce[], u128 rk[], u64 key[], int numbytes)
stream.c: ^
stream.c: stream.c:23:5: note: previous declaration of 'Encrypt' was here
stream.c: int Encrypt(unsigned char *out, u64 nonce[], u128 rk[], u64 key[], int numbytes);
stream.c: ^
stream.c: stream.c:212:12: error: static declaration of 'Encrypt_Xor' follows non-static declaration
stream.c: static int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[], u64 key[], int numbytes)
stream.c: ^
stream.c: stream.c:25:5: note: previous declaration of 'Encrypt_Xor' was here
stream.c: int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[], u64 key[], int numbytes);
stream.c: ^
stream.c: stream.c:253:12: error: static declaration of 'ExpandKey' follows non-static declaration
stream.c: static int ExpandKey(u64 K[], u128 rk[], u64 key[])
stream.c: ^
stream.c: stream.c:26:5: note: previous declaration of 'ExpandKey' was here
stream.c: int ExpandKey(u64 K[], u128 rk[], u64 key[]);
stream.c: ^
Number of similar (compiler,implementation) pairs: 92, 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=core2 -msse4.1 -O2 -fomit-frame-pointer sse4
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer sse4
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer sse4
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer sse4
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer sse4
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer sse4
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer sse4
gcc -m64 -march=corei7 -O -fomit-frame-pointer sse4
gcc -m64 -march=corei7 -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=native -mtune=native -O2 -fomit-frame-pointer sse4
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer sse4
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer sse4
gcc -m64 -march=native -mtune=native -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=native -mtune=native -O2 -fomit-frame-pointer -fwrapv sse4
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv sse4
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv sse4
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv 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/speck128128ctr/avx512
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
stream.c: stream.c:135:5: warning: implicit declaration of function '_mm512_set_epi64' is invalid in C99 [-Wimplicit-function-declaration]
stream.c: SET1(X[0],nonce[1]); SET8(Y[0],nonce[0]);
stream.c: ^
stream.c: ./Intrinsics_AVX512_128block.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_AVX512_128block.h:16:13: note: expanded from macro 'SET'
stream.c: #define SET _mm512_set_epi64
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]); SET8(Y[0],nonce[0]);
stream.c: ^~~~~~~~~~~~~~~~~~~
stream.c: ./Intrinsics_AVX512_128block.h:25:21: 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: 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]); SET8(Y[0],nonce[0]);
stream.c: ^~~~~~~~~~~~~~~~~~~
stream.c: ./Intrinsics_AVX512_128block.h:26:21: note: expanded from macro 'SET8'
stream.c: #define SET8(X,c) (X=SET(c,c,c,c,c,c,c,c), X=ADD(X,_q8))
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]); SET8(Y[0],nonce[0]);
stream.c: ^~~~~~~~~~~~~~~~~~~
stream.c: ./Intrinsics_AVX512_128block.h:26:52: note: expanded from macro 'SET8'
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/speck128128ctr/avx2
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
stream.c: stream.c:288:3: error: always_inline function '_mm256_set_epi64x' 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,rk,key);
stream.c: ^
stream.c: ./Speck128128AVX2.h:54:24: note: expanded from macro 'EK'
stream.c: #define EK(A,B,k,key) (RK(B,A,k,key,0), RK(B,A,k,key,1), RK(B,A,k,key,2), RK(B,A,k,key,3), RK(B,A,k,key,4), RK(B,A,k,key,5), RK(B,A,k,key,6), \
stream.c: ^
stream.c: ./Speck128128AVX2.h:52:28: 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_128block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c))
stream.c: ^
stream.c: ./Intrinsics_AVX2_128block.h:24:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi64x
stream.c: ^
stream.c: stream.c:288:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'ExpandKey' that is compiled without support for 'sse4.2'
stream.c: ./Speck128128AVX2.h:54:42: note: expanded from macro 'EK'
stream.c: #define EK(A,B,k,key) (RK(B,A,k,key,0), RK(B,A,k,key,1), RK(B,A,k,key,2), RK(B,A,k,key,3), RK(B,A,k,key,4), RK(B,A,k,key,5), RK(B,A,k,key,6), \
stream.c: ^
stream.c: ./Speck128128AVX2.h:52:28: 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_128block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(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/speck128128ctr/sse4
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
stream.c: stream.c:99:12: error: static declaration of 'Encrypt' follows non-static declaration
stream.c: static int Encrypt(unsigned char *out, u64 nonce[], u128 rk[], u64 key[], int numbytes)
stream.c: ^
stream.c: stream.c:23:5: note: previous declaration is here
stream.c: int Encrypt(unsigned char *out, u64 nonce[], u128 rk[], u64 key[], int numbytes);
stream.c: ^
stream.c: stream.c:212:12: error: static declaration of 'Encrypt_Xor' follows non-static declaration
stream.c: static int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[], u64 key[], int numbytes)
stream.c: ^
stream.c: stream.c:25:5: note: previous declaration is here
stream.c: int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[], u64 key[], int numbytes);
stream.c: ^
stream.c: stream.c:253:12: error: static declaration of 'ExpandKey' follows non-static declaration
stream.c: static int ExpandKey(u64 K[], u128 rk[], u64 key[])
stream.c: ^
stream.c: stream.c:26:5: note: previous declaration is here
stream.c: int ExpandKey(u64 K[], u128 rk[], u64 key[]);
stream.c: ^
stream.c: 3 errors generated.
Number of similar (compiler,implementation) pairs: 6, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments sse4
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments sse4
clang -march=native -O3 -fomit-frame-pointer -fwrapv -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/speck128128ctr/avx2
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments
stream.c: stream.c:288:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'xsave', but would be inlined into function 'ExpandKey' that is compiled without support for 'xsave'
stream.c: EK(A,B,rk,key);
stream.c: ^
stream.c: ./Speck128128AVX2.h:54:24: note: expanded from macro 'EK'
stream.c: #define EK(A,B,k,key) (RK(B,A,k,key,0), RK(B,A,k,key,1), RK(B,A,k,key,2), RK(B,A,k,key,3), RK(B,A,k,key,4), RK(B,A,k,key,5), RK(B,A,k,key,6), \
stream.c: ^
stream.c: ./Speck128128AVX2.h:52:28: 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_128block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c))
stream.c: ^
stream.c: ./Intrinsics_AVX2_128block.h:24:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi64x
stream.c: ^
stream.c: stream.c:288:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'xsave', but would be inlined into function 'ExpandKey' that is compiled without support for 'xsave'
stream.c: ./Speck128128AVX2.h:54:42: note: expanded from macro 'EK'
stream.c: #define EK(A,B,k,key) (RK(B,A,k,key,0), RK(B,A,k,key,1), RK(B,A,k,key,2), RK(B,A,k,key,3), RK(B,A,k,key,4), RK(B,A,k,key,5), RK(B,A,k,key,6), \
stream.c: ^
stream.c: ./Speck128128AVX2.h:52:28: 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_128block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(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/speck128128ctr/avx2
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from Speck128128AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.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))
stream.c: ^
stream.c: stream.c:128:3: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET4(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_128block.h:5,
stream.c: from Speck128128AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:126:1: error: inlining failed in call to always_inline '_mm256_add_epi64': target specific option mismatch
stream.c: _mm256_add_epi64 (__m256i __A, __m256i __B)
stream.c: ^
stream.c: In file included from Speck128128AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:17:13: error: called from here
stream.c: #define ADD _mm256_add_epi64
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:26:38: note: in expansion of macro 'ADD'
stream.c: #define SET4(X,c) (X=SET(c,c,c,c), X=ADD(X,_q))
stream.c: ^
stream.c: stream.c:128:24: note: in expansion of macro 'SET4'
stream.c: ...
stream.c: In file included from Speck128128AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.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))
stream.c: ^
stream.c: stream.c:128:3: note: in expansion of macro 'SET1'
stream.c: SET1(X[0],nonce[1]); SET4(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_128block.h:5,
stream.c: from Speck128128AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:126:1: error: inlining failed in call to always_inline '_mm256_add_epi64': target specific option mismatch
stream.c: _mm256_add_epi64 (__m256i __A, __m256i __B)
stream.c: ^
stream.c: In file included from Speck128128AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:17:13: error: called from here
stream.c: #define ADD _mm256_add_epi64
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:26:38: note: in expansion of macro 'ADD'
stream.c: #define SET4(X,c) (X=SET(c,c,c,c), X=ADD(X,_q))
stream.c: ^
stream.c: stream.c:128:24: note: in expansion of macro 'SET4'
stream.c: ...
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/speck128128ctr/avx512
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from Speck128128AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX512_128block.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))
stream.c: ^
stream.c: stream.c:135:5: 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:45:0,
stream.c: from Intrinsics_AVX512_128block.h:5,
stream.c: from Speck128128AVX512.h:17,
stream.c: from stream.c:21:
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 Speck128128AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX512_128block.h:32:18: error: called from here
stream.c: #define ST(ip,X) _mm512_storeu_si512((void *)(ip),X)
stream.c: ^
stream.c: Intrinsics_AVX512_128block.h:33:43: 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 Speck128128AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX512_128block.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))
stream.c: ^
stream.c: stream.c:135:5: 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:45:0,
stream.c: from Intrinsics_AVX512_128block.h:5,
stream.c: from Speck128128AVX512.h:17,
stream.c: from stream.c:21:
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 Speck128128AVX512.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX512_128block.h:32:18: error: called from here
stream.c: #define ST(ip,X) _mm512_storeu_si512((void *)(ip),X)
stream.c: ^
stream.c: Intrinsics_AVX512_128block.h:33:43: 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/speck128128ctr/sse4
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: stream.c:99:12: error: static declaration of 'Encrypt' follows non-static declaration
stream.c: static int Encrypt(unsigned char *out, u64 nonce[], u128 rk[], u64 key[], int numbytes)
stream.c: ^
stream.c: stream.c:23:5: note: previous declaration of 'Encrypt' was here
stream.c: int Encrypt(unsigned char *out, u64 nonce[], u128 rk[], u64 key[], int numbytes);
stream.c: ^
stream.c: stream.c:212:12: error: static declaration of 'Encrypt_Xor' follows non-static declaration
stream.c: static int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[], u64 key[], int numbytes)
stream.c: ^
stream.c: stream.c:25:5: note: previous declaration of 'Encrypt_Xor' was here
stream.c: int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[], u64 key[], int numbytes);
stream.c: ^
stream.c: stream.c:253:12: error: static declaration of 'ExpandKey' follows non-static declaration
stream.c: static int ExpandKey(u64 K[], u128 rk[], u64 key[])
stream.c: ^
stream.c: stream.c:26:5: note: previous declaration of 'ExpandKey' was here
stream.c: int ExpandKey(u64 K[], u128 rk[], u64 key[]);
stream.c: ^
stream.c: stream.c:99:12: error: static declaration of 'Encrypt' follows non-static declaration
stream.c: static int Encrypt(unsigned char *out, u64 nonce[], u128 rk[], u64 key[], int numbytes)
stream.c: ^
stream.c: stream.c:23:5: note: previous declaration of 'Encrypt' was here
stream.c: int Encrypt(unsigned char *out, u64 nonce[], u128 rk[], u64 key[], int numbytes);
stream.c: ^
stream.c: stream.c:212:12: error: static declaration of 'Encrypt_Xor' follows non-static declaration
stream.c: static int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[], u64 key[], int numbytes)
stream.c: ^
stream.c: stream.c:25:5: note: previous declaration of 'Encrypt_Xor' was here
stream.c: int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[], u64 key[], int numbytes);
stream.c: ^
stream.c: stream.c:253:12: error: static declaration of 'ExpandKey' follows non-static declaration
stream.c: static int ExpandKey(u64 K[], u128 rk[], u64 key[])
stream.c: ^
stream.c: stream.c:26:5: note: previous declaration of 'ExpandKey' was here
stream.c: int ExpandKey(u64 K[], u128 rk[], u64 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