Implementation notes: amd64, oki, crypto_stream/speck64128ctr

Computer: oki
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20181123
Operation: crypto_stream
Primitive: speck64128ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
986? ? ?? ? ?avx512gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019011020181123
988? ? ?? ? ?avx512gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2019011020181123
990? ? ?? ? ?avx512gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019011020181123
994? ? ?? ? ?avx512gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019011020181123
994? ? ?? ? ?avx512gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2019011020181123
1000? ? ?? ? ?avx512gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019011020181123
1004? ? ?? ? ?avx512gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019011020181123
1012? ? ?? ? ?avx512gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2019011020181123
1714? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019011020181123
1718? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2019011020181123
1720? ? ?? ? ?avx2clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019011020181123
1722? ? ?? ? ?avx2clang_-O3_-fwrapv_-march=x86-64_-mcpu=core-avx2_-mavx2_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019011020181123
1730? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O_-fomit-frame-pointer2019011020181123
1746? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019011020181123
1746? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019011020181123
1750? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-Os_-fomit-frame-pointer2019011020181123
1752? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2019011020181123
1752? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019011020181123
1758? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2019011020181123
1758? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019011020181123
1774? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O2_-fomit-frame-pointer2019011020181123
1774? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O3_-fomit-frame-pointer2019011020181123
3286? ? ?? ? ?sse4clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019011020181123
3286? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019011020181123
3288? ? ?? ? ?sse4clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019011020181123
3296? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2019011020181123
3306? ? ?? ? ?sse4clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019011020181123
3306? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019011020181123
3308? ? ?? ? ?sse4clang_-O3_-fwrapv_-march=x86-64_-mcpu=core-avx2_-mavx2_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019011020181123
3308? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2019011020181123
3308? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019011020181123
3310? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O_-fomit-frame-pointer2019011020181123
3312? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2019011020181123
3312? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2019011020181123
3316? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2019011020181123
3326? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2019011020181123
3326? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019011020181123
3326? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019011020181123
3330? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2019011020181123
3330? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2019011020181123
3338? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2019011020181123
3342? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2019011020181123
3344? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2019011020181123
3372? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O3_-fomit-frame-pointer2019011020181123
3384? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-Os_-fomit-frame-pointer2019011020181123
3386? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O2_-fomit-frame-pointer2019011020181123
3444? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O_-fomit-frame-pointer2019011020181123
3460? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2019011020181123
3464? ? ?? ? ?sse4gcc_-m64_-march=core2_-O_-fomit-frame-pointer2019011020181123
3464? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2019011020181123
3474? ? ?? ? ?sse4gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2019011020181123
3478? ? ?? ? ?sse4gcc_-m64_-march=core2_-Os_-fomit-frame-pointer2019011020181123
3478? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2019011020181123
3480? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2019011020181123
3484? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2019011020181123
3486? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2019011020181123
3490? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2019011020181123
3502? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2019011020181123
3506? ? ?? ? ?sse4gcc_-m64_-march=core2_-O3_-fomit-frame-pointer2019011020181123
3506? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2019011020181123
3506? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2019011020181123
3508? ? ?? ? ?sse4gcc_-m64_-march=core2_-O2_-fomit-frame-pointer2019011020181123

Compiler output

Implementation: avx2
Security model: unknown
Compiler: cc
stream.c: In file included from Speck64128AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_64block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:24:84: note: in expansion of macro 'u256'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out, u32 nonce[], u256 rk[], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX2_64block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:26:113: note: in expansion of macro 'u256'
stream.c: inline __attribute__((always_inline)) int Encrypt_Xor(unsigned char *out, const unsigned char *in, u32 nonce[], u256 rk[], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX2_64block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:27:24: note: in expansion of macro 'u256'
stream.c: int ExpandKey(u32 K[], u256 rk[], u32 key[]);
stream.c: ^
stream.c: stream.c: In function 'crypto_stream_speck64128ctr_avx2':
stream.c: Intrinsics_AVX2_64block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:42:3: note: in expansion of macro 'u256'
stream.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
cc avx2

Compiler output

Implementation: avx2
Security model: unknown
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: avx2
Security model: unknown
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments
try.c: fatal error: error in backend: Cannot select: 0x2653200: v4i64 = X86ISD::VTRUNC 0x2653030
try.c: 0x2653030: v16i32 = vselect 0x2648fa0, 0x25ece00, 0x2652f00
try.c: 0x2648fa0: v4i1 = X86ISD::PCMPGTM 0x263caf0, 0x25edbb0
try.c: 0x263caf0: v4i64 = X86ISD::VBROADCAST 0x25edf40
try.c: 0x25edf40: i64,ch = load<LD8[%uglygep72]> 0x2536dd0, 0x25d34f0, undef:i64
try.c: 0x25d34f0: i64 = add 0x263d9d0, 0x25b8600
try.c: 0x263d9d0: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0x2632690: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0x25b8600: i64 = shl 0x2631e40, Constant:i8<3>
try.c: 0x2631e40: i64,ch = CopyFromReg 0x2536dd0, Register:i64 %vreg50
try.c: 0x263de90: i64 = Register %vreg50
try.c: 0x25d6680: i8 = Constant<3>
try.c: 0x263b160: i64 = undef
try.c: 0x25edbb0: v4i64,ch = CopyFromReg 0x2536dd0, Register:v4i64 %vreg13
try.c: 0x25e9cd0: v4i64 = Register %vreg13
try.c: 0x25ece00: v16i32 = X86ISD::VBROADCAST 0x26320a0
try.c: 0x26320a0: i32,ch = load<LD4[ConstantPool]> 0x2536dd0, 0x2652b70, undef:i64
try.c: 0x2652b70: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0x25e77f0: i64 = TargetConstantPool<i32 1> 0
try.c: 0x263b160: i64 = undef
try.c: 0x2652f00: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x2652dd0: i32 = Constant<0>
try.c: 0x2652dd0: i32 = Constant<0>
try.c: 0x2652dd0: i32 = Constant<0>
try.c: 0x2652dd0: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments
stream.c: stream.c:150:24: error: always_inline function '_mm256_add_epi32' requires target feature 'avx2', but would be inlined into function 'Encrypt' that is compiled without support for 'avx2'
stream.c: SET1(X[0],nonce[1]); SET8(Y[0],nonce[0]);
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:26:46: note: expanded from macro 'SET8'
stream.c: #define SET8(X,c) (X=SET(c,c,c,c,c,c,c,c), X=ADD(X,_q))
stream.c: ^
stream.c: ./Intrinsics_AVX2_64block.h:17:13: note: expanded from macro 'ADD'
stream.c: #define ADD _mm256_add_epi32
stream.c: ^
stream.c: stream.c:152:21: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'Encrypt' that is compiled without support for 'avx2'
stream.c: if (numbytes==64) Enc(X,Y,rk,8);
stream.c: ^
stream.c: ./Speck64128AVX2.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>:120:1: note: expanded from here
stream.c: Rx8
stream.c: ^
stream.c: ./Speck64128AVX2.h:25:22: note: expanded from macro 'Rx8'
stream.c: #define Rx8(X,Y,k) (R(X[0],Y[0],k))
stream.c: ^
stream.c: ./Speck64128AVX2.h:23:21: 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_AVX2_64block.h:15:13: note: expanded from macro 'XOR'
stream.c: ...
Number of similar (compiler,implementation) pairs: 2, namely:
CompilerImplementations
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments avx2
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments
try.c: fatal error: error in backend: Cannot select: 0xc9ffb0: v4i64 = X86ISD::VTRUNC 0xc9fde0
try.c: 0xc9fde0: v16i32 = vselect 0xc9ca20, 0xc3d880, 0xc9fcb0
try.c: 0xc9ca20: v4i1 = X86ISD::PCMPGTM 0xc88890, 0xc3e630
try.c: 0xc88890: v4i64 = X86ISD::VBROADCAST 0xc3e9c0
try.c: 0xc3e9c0: i64,ch = load<LD8[%uglygep72]> 0xb82dd0, 0xc6e710, undef:i64
try.c: 0xc6e710: i64 = add 0xc89770, 0xc1e0b0
try.c: 0xc89770: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0xc34a70: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0xc1e0b0: i64 = shl 0xc34220, Constant:i8<3>
try.c: 0xc34220: i64,ch = CopyFromReg 0xb82dd0, Register:i64 %vreg50
try.c: 0xc89c30: i64 = Register %vreg50
try.c: 0xc281d0: i8 = Constant<3>
try.c: 0xc86f00: i64 = undef
try.c: 0xc3e630: v4i64,ch = CopyFromReg 0xb82dd0, Register:v4i64 %vreg13
try.c: 0xc21010: v4i64 = Register %vreg13
try.c: 0xc3d880: v16i32 = X86ISD::VBROADCAST 0xc34480
try.c: 0xc34480: i32,ch = load<LD4[ConstantPool]> 0xb82dd0, 0xc9f920, undef:i64
try.c: 0xc9f920: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0xc41ae0: i64 = TargetConstantPool<i32 1> 0
try.c: 0xc86f00: i64 = undef
try.c: 0xc9fcb0: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0xc9fb80: i32 = Constant<0>
try.c: 0xc9fb80: i32 = Constant<0>
try.c: 0xc9fb80: i32 = Constant<0>
try.c: 0xc9fb80: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: gcc
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/lib64/gcc/x86_64-suse-linux/7/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/lib64/gcc/x86_64-suse-linux/7/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: 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:150:24: 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: avx2
Security model: unknown
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/lib64/gcc/x86_64-suse-linux/7/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/lib64/gcc/x86_64-suse-linux/7/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: 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: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/lib64/gcc/x86_64-suse-linux/7/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/lib64/gcc/x86_64-suse-linux/7/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: 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: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: avx2
Security model: unknown
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer
stream.c: In file included from /usr/lib64/gcc/x86_64-suse-linux/7/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: stream.c: In function 'Encrypt':
stream.c: /usr/lib64/gcc/x86_64-suse-linux/7/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: 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:150:24: note: in expansion of macro 'SET8'
stream.c: SET1(X[0],nonce[1]); SET8(Y[0],nonce[0]);
stream.c: ^~~~
stream.c: In file included from /usr/lib64/gcc/x86_64-suse-linux/7/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/lib64/gcc/x86_64-suse-linux/7/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

Compiler output

Implementation: avx512
Security model: unknown
Compiler: cc
stream.c: In file included from Speck64128AVX512.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:23:84: note: in expansion of macro 'u512'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out, u32 nonce[], u512 rk[], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:25:113: note: in expansion of macro 'u512'
stream.c: inline __attribute__((always_inline)) int Encrypt_Xor(unsigned char *out, const unsigned char *in, u32 nonce[], u512 rk[], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:26:24: note: in expansion of macro 'u512'
stream.c: int ExpandKey(u32 K[], u512 rk[], u32 key[]);
stream.c: ^
stream.c: stream.c: In function 'crypto_stream_speck64128ctr_avx512':
stream.c: Intrinsics_AVX512_64block.h:9:14: error: unknown type name '__m512i'
stream.c: #define u512 __m512i
stream.c: ^
stream.c: stream.c:41:3: note: in expansion of macro 'u512'
stream.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
cc avx512

Compiler output

Implementation: avx512
Security model: unknown
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: 10, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments avx512
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments avx512
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments avx512
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments avx512
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments avx512
clang -O3 -fwrapv -mavx -maes -mpclmul -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: avx512
Security model: unknown
Compiler: gcc
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/lib64/gcc/x86_64-suse-linux/7/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/lib64/gcc/x86_64-suse-linux/7/include/avx512fintrin.h:5831:1: 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: 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: avx512
Security model: unknown
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/lib64/gcc/x86_64-suse-linux/7/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/lib64/gcc/x86_64-suse-linux/7/include/avx512fintrin.h:5831:1: 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: 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 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/lib64/gcc/x86_64-suse-linux/7/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/lib64/gcc/x86_64-suse-linux/7/include/avx512fintrin.h:5831:1: 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: 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: sse4
Security model: unknown
Compiler: cc
stream.c: In file included from Intrinsics_SSE4_64block.h:5:0,
stream.c: from Speck64128SSE4.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib64/gcc/x86_64-suse-linux/4.8/include/smmintrin.h:31:3: error: #error "SSE4.1 instruction set not enabled"
stream.c: # error "SSE4.1 instruction set not enabled"
stream.c: ^
stream.c: In file included from Speck64128SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:24:84: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out, u32 nonce[], u128 rk[], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:26:113: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt_Xor(unsigned char *out, const unsigned char *in, u32 nonce[], u128 rk[], u32 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_SSE4_64block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:27:24: note: in expansion of macro 'u128'
stream.c: int ExpandKey(u32 K[], u128 rk[], u32 key[]);
stream.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
cc sse4

Compiler output

Implementation: sse4
Security model: unknown
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: sse4
Security model: unknown
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments
try.c: fatal error: error in backend: Cannot select: 0x1e7cea0: v4i64 = X86ISD::VTRUNC 0x1e7ccd0
try.c: 0x1e7ccd0: v16i32 = vselect 0x1e79910, 0x1de1fb0, 0x1e7cba0
try.c: 0x1e79910: v4i1 = X86ISD::PCMPGTM 0x1e64c10, 0x1e13280
try.c: 0x1e64c10: v4i64 = X86ISD::VBROADCAST 0x1e13610
try.c: 0x1e13610: i64,ch = load<LD8[%uglygep72]> 0x1d5fdd0, 0x1e56330, undef:i64
try.c: 0x1e56330: i64 = add 0x1e65af0, 0x1dff950
try.c: 0x1e65af0: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0x1e5d2a0: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0x1dff950: i64 = shl 0x1e5ca50, Constant:i8<3>
try.c: 0x1e5ca50: i64,ch = CopyFromReg 0x1d5fdd0, Register:i64 %vreg50
try.c: 0x1e65fb0: i64 = Register %vreg50
try.c: 0x1e05cf0: i8 = Constant<3>
try.c: 0x1e62a70: i64 = undef
try.c: 0x1e13280: v4i64,ch = CopyFromReg 0x1d5fdd0, Register:v4i64 %vreg13
try.c: 0x1dfc840: v4i64 = Register %vreg13
try.c: 0x1de1fb0: v16i32 = X86ISD::VBROADCAST 0x1e5ccb0
try.c: 0x1e5ccb0: i32,ch = load<LD4[ConstantPool]> 0x1d5fdd0, 0x1e7c810, undef:i64
try.c: 0x1e7c810: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0x1dfa360: i64 = TargetConstantPool<i32 1> 0
try.c: 0x1e62a70: i64 = undef
try.c: 0x1e7cba0: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x1e7ca70: i32 = Constant<0>
try.c: 0x1e7ca70: i32 = Constant<0>
try.c: 0x1e7ca70: i32 = Constant<0>
try.c: 0x1e7ca70: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments sse4

Compiler output

Implementation: sse4
Security model: unknown
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments
try.c: fatal error: error in backend: Cannot select: 0x28162a0: v4i64 = X86ISD::VTRUNC 0x28160d0
try.c: 0x28160d0: v16i32 = vselect 0x27ea140, 0x27aded0, 0x2815fa0
try.c: 0x27ea140: v4i1 = X86ISD::PCMPGTM 0x28027c0, 0x27aec80
try.c: 0x28027c0: v4i64 = X86ISD::VBROADCAST 0x27af010
try.c: 0x27af010: i64,ch = load<LD8[%uglygep72]> 0x26fadf0, 0x27f1420, undef:i64
try.c: 0x27f1420: i64 = add 0x28036a0, 0x277c670
try.c: 0x28036a0: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0x27c65c0: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0x277c670: i64 = shl 0x27c5d70, Constant:i8<3>
try.c: 0x27c5d70: i64,ch = CopyFromReg 0x26fadf0, Register:i64 %vreg50
try.c: 0x2803b60: i64 = Register %vreg50
try.c: 0x27bcb90: i8 = Constant<3>
try.c: 0x2800e30: i64 = undef
try.c: 0x27aec80: v4i64,ch = CopyFromReg 0x26fadf0, Register:v4i64 %vreg13
try.c: 0x27abdf0: v4i64 = Register %vreg13
try.c: 0x27aded0: v16i32 = X86ISD::VBROADCAST 0x27c5fd0
try.c: 0x27c5fd0: i32,ch = load<LD4[ConstantPool]> 0x26fadf0, 0x2815c10, undef:i64
try.c: 0x2815c10: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0x27b1770: i64 = TargetConstantPool<i32 1> 0
try.c: 0x2800e30: i64 = undef
try.c: 0x2815fa0: v16i32 = BUILD_VECTOR Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>, Constant:i32<0>
try.c: 0x2815e70: i32 = Constant<0>
try.c: 0x2815e70: i32 = Constant<0>
try.c: 0x2815e70: i32 = Constant<0>
try.c: 0x2815e70: i32 = Constant<0>
try.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments sse4

Compiler output

Implementation: sse4
Security model: unknown
Compiler: gcc
stream.c: In file included from /usr/lib64/gcc/x86_64-suse-linux/7/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/lib64/gcc/x86_64-suse-linux/7/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: note: called from here
stream.c: #define XOR _mm_xor_si128
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: In file included from /usr/lib64/gcc/x86_64-suse-linux/7/include/smmintrin.h:32:0,
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: sse4
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
stream.c: In file included from /usr/lib64/gcc/x86_64-suse-linux/7/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/lib64/gcc/x86_64-suse-linux/7/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: note: called from here
stream.c: #define XOR _mm_xor_si128
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: In file included from /usr/lib64/gcc/x86_64-suse-linux/7/include/smmintrin.h:32:0,
stream.c: ...
stream.c: In file included from /usr/lib64/gcc/x86_64-suse-linux/7/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/lib64/gcc/x86_64-suse-linux/7/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: note: called from here
stream.c: #define XOR _mm_xor_si128
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: In file included from /usr/lib64/gcc/x86_64-suse-linux/7/include/smmintrin.h:32:0,
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