Implementation notes: amd64, oki, crypto_stream/simon128192ctr

Computer: oki
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20181123
Operation: crypto_stream
Primitive: simon128192ctr

Checksum failure

Implementation: avx2
Security model: unknown
Compiler: clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments
1f091783d9fce8d9ac313b042e20414465fdc1b084f4e0c31125690ead6502aa
Number of similar (compiler,implementation) pairs: 48, namely:
CompilerImplementations
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments avx2
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments avx2
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer avx2
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer avx2
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer avx2
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer avx2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv avx2
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments sse4
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments sse4
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments sse4
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments sse4
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer sse4
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer sse4
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer sse4
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer sse4
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer sse4
gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer sse4
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer sse4
gcc -m64 -march=core-avx2 -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 -O3 -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 -O3 -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-avx -O2 -fomit-frame-pointer sse4
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer sse4
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer sse4
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer sse4
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer sse4
gcc -m64 -march=corei7 -O3 -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=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 -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

Compiler output

Implementation: avx2
Security model: unknown
Compiler: cc
stream.c: In file included from Simon128192AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:24:46: note: in expansion of macro 'u256'
stream.c: int Encrypt(unsigned char *out, u64 nonce[], u256 rk[][8], u64 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:26:75: note: in expansion of macro 'u256'
stream.c: int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u256 rk[][8], u64 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:27:25: note: in expansion of macro 'u256'
stream.c: int ExpandKeyBS(u64 K[],u256 rk[][8]);
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:10:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:28:27: note: in expansion of macro 'u256'
stream.c: int ExpandKeyNBS(u64 K[], u256 rk[][8], u64 key[]);
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:128:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'Encrypt' that is compiled without support for 'sse4.2'
stream.c: SET1(X[0],nonce[1]); SET4(Y[0],nonce[0]);
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:128:24: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'Encrypt' that is compiled without support for 'sse4.2'
stream.c: SET1(X[0],nonce[1]); SET4(Y[0],nonce[0]);
stream.c: ^
stream.c: ./Intrinsics_AVX2_128block.h:26:22: note: expanded from macro 'SET4'
stream.c: #define SET4(X,c) (X=SET(c,c,c,c), X=ADD(X,_q))
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:128:24: error: always_inline function '_mm256_add_epi64' requires target feature 'sse4.2', but would be inlined into function 'Encrypt' that is compiled without support for 'sse4.2'
stream.c: ./Intrinsics_AVX2_128block.h:26:38: note: expanded from macro 'SET4'
stream.c: #define SET4(X,c) (X=SET(c,c,c,c), X=ADD(X,_q))
stream.c: ^
stream.c: ./Intrinsics_AVX2_128block.h:17:13: note: expanded from macro 'ADD'
stream.c: #define ADD _mm256_add_epi64
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: 0xf34ce0: v4i64 = X86ISD::VTRUNC 0xf34b10
try.c: 0xf34b10: v16i32 = vselect 0xf2d260, 0xec32c0, 0xf349e0
try.c: 0xf2d260: v4i1 = X86ISD::PCMPGTM 0xf1ffe0, 0xec78c0
try.c: 0xf1ffe0: v4i64 = X86ISD::VBROADCAST 0xec7c50
try.c: 0xec7c50: i64,ch = load<LD8[%uglygep72]> 0xe1bdd0, 0xee6bf0, undef:i64
try.c: 0xee6bf0: i64 = add 0xf20ec0, 0xebc850
try.c: 0xf20ec0: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0xf10890: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0xebc850: i64 = shl 0xf10040, Constant:i8<3>
try.c: 0xf10040: i64,ch = CopyFromReg 0xe1bdd0, Register:i64 %vreg50
try.c: 0xf21380: i64 = Register %vreg50
try.c: 0xe9c8f0: i8 = Constant<3>
try.c: 0xf1e650: i64 = undef
try.c: 0xec78c0: v4i64,ch = CopyFromReg 0xe1bdd0, Register:v4i64 %vreg13
try.c: 0xecdc90: v4i64 = Register %vreg13
try.c: 0xec32c0: v16i32 = X86ISD::VBROADCAST 0xf102a0
try.c: 0xf102a0: i32,ch = load<LD4[ConstantPool]> 0xe1bdd0, 0xf34650, undef:i64
try.c: 0xf34650: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0xecb7b0: i64 = TargetConstantPool<i32 1> 0
try.c: 0xf1e650: i64 = undef
try.c: 0xf349e0: 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: 0xf348b0: i32 = Constant<0>
try.c: 0xf348b0: i32 = Constant<0>
try.c: 0xf348b0: i32 = Constant<0>
try.c: 0xf348b0: 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:128:24: error: always_inline function '_mm256_add_epi64' 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]); SET4(Y[0],nonce[0]);
stream.c: ^
stream.c: ./Intrinsics_AVX2_128block.h:26:38: note: expanded from macro 'SET4'
stream.c: #define SET4(X,c) (X=SET(c,c,c,c), X=ADD(X,_q))
stream.c: ^
stream.c: ./Intrinsics_AVX2_128block.h:17:13: note: expanded from macro 'ADD'
stream.c: #define ADD _mm256_add_epi64
stream.c: ^
stream.c: stream.c:130:21: 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,4);
stream.c: ^
stream.c: ./Simon128192AVX2.h:47:24: note: expanded from macro 'Enc'
stream.c: #define Enc(X,Y,rk,n) (R2x##n(X,Y,rk,0,1), R2x##n(X,Y,rk,2,3), R2x##n(X,Y,rk,4,5), R2x##n(X,Y,rk,6,7), R2x##n(X,Y,rk,8,9), \
stream.c: ^
stream.c: <scratch space>:109:1: note: expanded from here
stream.c: R2x4
stream.c: ^
stream.c: ./Simon128192AVX2.h:31:28: note: expanded from macro 'R2x4'
stream.c: #define R2x4(X,Y,rk,r,s) (Sx4(X,Y,rk,r), Sx4(Y,X,rk,s))
stream.c: ^
stream.c: ./Simon128192AVX2.h:26:25: note: expanded from macro 'Sx4'
stream.c: #define Sx4(U,V,rk,s) (RD(U[0],V[0],rk[s][0]))
stream.c: ^
stream.c: ./Simon128192AVX2.h:24:22: note: expanded from macro 'RD'
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: 0x2758130: v4i64 = X86ISD::VTRUNC 0x2757f60
try.c: 0x2757f60: v16i32 = vselect 0x2754ba0, 0x26e2ad0, 0x2757e30
try.c: 0x2754ba0: v4i1 = X86ISD::PCMPGTM 0x2740a10, 0x26edde0
try.c: 0x2740a10: v4i64 = X86ISD::VBROADCAST 0x26ee170
try.c: 0x26ee170: i64,ch = load<LD8[%uglygep72]> 0x263add0, 0x271ff10, undef:i64
try.c: 0x271ff10: i64 = add 0x27418f0, 0x2702390
try.c: 0x27418f0: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0x26f7640: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0x2702390: i64 = shl 0x26f6df0, Constant:i8<3>
try.c: 0x26f6df0: i64,ch = CopyFromReg 0x263add0, Register:i64 %vreg50
try.c: 0x2741db0: i64 = Register %vreg50
try.c: 0x26d7500: i8 = Constant<3>
try.c: 0x273f080: i64 = undef
try.c: 0x26edde0: v4i64,ch = CopyFromReg 0x263add0, Register:v4i64 %vreg13
try.c: 0x26f0830: v4i64 = Register %vreg13
try.c: 0x26e2ad0: v16i32 = X86ISD::VBROADCAST 0x26f7050
try.c: 0x26f7050: i32,ch = load<LD4[ConstantPool]> 0x263add0, 0x2757aa0, undef:i64
try.c: 0x2757aa0: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0x26c2070: i64 = TargetConstantPool<i32 1> 0
try.c: 0x273f080: i64 = undef
try.c: 0x2757e30: 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: 0x2757d00: i32 = Constant<0>
try.c: 0x2757d00: i32 = Constant<0>
try.c: 0x2757d00: i32 = Constant<0>
try.c: 0x2757d00: 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 Simon128192AVX2.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/lib64/gcc/x86_64-suse-linux/7/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_128block.h:5,
stream.c: from Simon128192AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib64/gcc/x86_64-suse-linux/7/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 Simon128192AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:17:13: note: 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: 2, namely:
CompilerImplementations
gcc avx2
gcc -funroll-loops avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: gcc -O2 -fomit-frame-pointer
stream.c: In file included from Simon128192AVX2.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/lib64/gcc/x86_64-suse-linux/7/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_128block.h:5,
stream.c: from Simon128192AVX2.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Transpose':
stream.c: /usr/lib64/gcc/x86_64-suse-linux/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
stream.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128192AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:15:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c: stream.c:419:10: note: in expansion of macro 'XOR'
stream.c: T[6] = XOR(T[6], SL(W[3],1));
stream.c: ^~~
stream.c: In file included from /usr/lib64/gcc/x86_64-suse-linux/7/include/immintrin.h:43:0,
stream.c: ...
Number of similar (compiler,implementation) pairs: 84, namely:
CompilerImplementations
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 -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 Simon128192AVX2.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/lib64/gcc/x86_64-suse-linux/7/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_128block.h:5,
stream.c: from Simon128192AVX2.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Transpose':
stream.c: /usr/lib64/gcc/x86_64-suse-linux/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
stream.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128192AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:15:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c: stream.c:419:10: note: in expansion of macro 'XOR'
stream.c: T[6] = XOR(T[6], SL(W[3],1));
stream.c: ^~~
stream.c: In file included from /usr/lib64/gcc/x86_64-suse-linux/7/include/immintrin.h:43:0,
stream.c: ...
stream.c: In file included from Simon128192AVX2.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/lib64/gcc/x86_64-suse-linux/7/include/immintrin.h:43:0,
stream.c: from Intrinsics_AVX2_128block.h:5,
stream.c: from Simon128192AVX2.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Transpose':
stream.c: /usr/lib64/gcc/x86_64-suse-linux/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
stream.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128192AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:15:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c: stream.c:419:10: note: in expansion of macro 'XOR'
stream.c: T[6] = XOR(T[6], SL(W[3],1));
stream.c: ^~~
stream.c: In file included from /usr/lib64/gcc/x86_64-suse-linux/7/include/immintrin.h:43:0,
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_128block.h:5,
stream.c: from Simon128192AVX2.h:17,
stream.c: from stream.c:20:
stream.c: stream.c: In function 'Transpose':
stream.c: /usr/lib64/gcc/x86_64-suse-linux/7/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
stream.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
stream.c: ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128192AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:15:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c: stream.c:419:10: note: in expansion of macro 'XOR'
stream.c: T[6] = XOR(T[6], SL(W[3],1));
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_128block.h:5,
stream.c: from Simon128192AVX2.h:17,
stream.c: from stream.c:20:
stream.c: /usr/lib64/gcc/x86_64-suse-linux/7/include/avx2intrin.h:696:1: error: inlining failed in call to always_inline '_mm256_slli_epi64': target specific option mismatch
stream.c: _mm256_slli_epi64 (__m256i __A, int __B)
stream.c: ^~~~~~~~~~~~~~~~~
stream.c: In file included from Simon128192AVX2.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:15:13: note: called from here
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: avx2
Security model: unknown
Compiler: gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer
try.c: /usr/lib64/gcc/x86_64-suse-linux/7/../../../../x86_64-suse-linux/bin/ld: crypto_stream_simon128192ctr.a(stream.o): in function `Encrypt':
try.c: stream.c:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/lib64/gcc/x86_64-suse-linux/7/../../../../x86_64-suse-linux/bin/ld: stream.c:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/lib64/gcc/x86_64-suse-linux/7/../../../../x86_64-suse-linux/bin/ld: crypto_stream_simon128192ctr.a(stream.o): in function `Encrypt_Xor':
try.c: stream.c:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/lib64/gcc/x86_64-suse-linux/7/../../../../x86_64-suse-linux/bin/ld: stream.c:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/lib64/gcc/x86_64-suse-linux/7/../../../../x86_64-suse-linux/bin/ld: stream.c:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/lib64/gcc/x86_64-suse-linux/7/../../../../x86_64-suse-linux/bin/ld: crypto_stream_simon128192ctr.a(stream.o):stream.c:(.text+0x...): more undefined references to `Transpose' follow
try.c: collect2: error: ld returned 1 exit status
Number of similar (compiler,implementation) pairs: 3, namely:
CompilerImplementations
gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer avx2
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer
try.c: /usr/lib64/gcc/x86_64-suse-linux/7/../../../../x86_64-suse-linux/bin/ld: crypto_stream_simon128192ctr.a(stream.o): in function `Encrypt':
try.c: stream.c:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/lib64/gcc/x86_64-suse-linux/7/../../../../x86_64-suse-linux/bin/ld: stream.c:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/lib64/gcc/x86_64-suse-linux/7/../../../../x86_64-suse-linux/bin/ld: stream.c:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/lib64/gcc/x86_64-suse-linux/7/../../../../x86_64-suse-linux/bin/ld: stream.c:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/lib64/gcc/x86_64-suse-linux/7/../../../../x86_64-suse-linux/bin/ld: crypto_stream_simon128192ctr.a(stream.o): in function `Encrypt_Xor':
try.c: stream.c:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/lib64/gcc/x86_64-suse-linux/7/../../../../x86_64-suse-linux/bin/ld: crypto_stream_simon128192ctr.a(stream.o):stream.c:(.text+0x...): more undefined references to `Transpose' follow
try.c: collect2: error: ld returned 1 exit status
Number of similar (compiler,implementation) pairs: 3, namely:
CompilerImplementations
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer avx2
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv avx2

Compiler output

Implementation: sse4
Security model: unknown
Compiler: cc
stream.c: In file included from Intrinsics_SSE4_128block.h:5:0,
stream.c: from Simon128192SSE4.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 Simon128192SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_128block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:24:82: note: in expansion of macro 'u128'
stream.c: inline __attribute__((always_inline)) int Encrypt(unsigned char *out,u64 nonce[],u128 rk[][8],u64 key[],int numbytes);
stream.c: ^
stream.c: Intrinsics_SSE4_128block.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, u64 nonce[], u128 rk[][8], u64 key[], int numbytes);
stream.c: ^
stream.c: Intrinsics_SSE4_128block.h:10:14: error: unknown type name '__m128i'
stream.c: #define u128 __m128i
stream.c: ^
stream.c: stream.c:27:25: note: in expansion of macro 'u128'
stream.c: int ExpandKeyBS(u64 K[],u128 rk[][8]);
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:313:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'ExpandKeyBS' that is compiled without support for 'ssse3'
stream.c: EKBS(rk);
stream.c: ^
stream.c: ./Simon128192SSE4.h:65:19: note: expanded from macro 'EKBS'
stream.c: #define EKBS(rk) (RKBS(rk,3,_D), RKBS(rk,4,_D), RKBS(rk,5,_C), RKBS(rk,6,_D), RKBS(rk,7,_D), RKBS(rk,8,_C), \
stream.c: ^
stream.c: ./Simon128192SSE4.h:56:52: note: expanded from macro 'RKBS'
stream.c: #define RKBS(rk,r,_V) (rk[r][7]= _D ^ rk[r-3][7] ^ ROR8(rk[r-1][2] ^ rk[r-1][3]), \
stream.c: ^
stream.c: ./Intrinsics_SSE4_128block.h:39:19: note: expanded from macro 'ROR8'
stream.c: #define ROR8(X) (SHFL(X,R8))
stream.c: ^
stream.c: ./Intrinsics_SSE4_128block.h:35:14: note: expanded from macro 'SHFL'
stream.c: #define SHFL _mm_shuffle_epi8
stream.c: ^
stream.c: stream.c:313:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'ExpandKeyBS' that is compiled without support for 'ssse3'
stream.c: ./Simon128192SSE4.h:65:19: note: expanded from macro 'EKBS'
stream.c: #define EKBS(rk) (RKBS(rk,3,_D), RKBS(rk,4,_D), RKBS(rk,5,_C), RKBS(rk,6,_D), RKBS(rk,7,_D), RKBS(rk,8,_C), \
stream.c: ^
stream.c: ./Simon128192SSE4.h:57:38: note: expanded from macro 'RKBS'
stream.c: rk[r][6]= _D ^ rk[r-3][6] ^ ROR8(rk[r-1][1] ^ rk[r-1][2]), \
stream.c: ^
stream.c: ./Intrinsics_SSE4_128block.h:39:19: note: expanded from macro 'ROR8'
stream.c: #define ROR8(X) (SHFL(X,R8))
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: 0x1414fd0: v4i64 = X86ISD::VTRUNC 0x1414e00
try.c: 0x1414e00: v16i32 = vselect 0x1411a40, 0x1392af0, 0x1414cd0
try.c: 0x1411a40: v4i1 = X86ISD::PCMPGTM 0x13fccf0, 0x13938a0
try.c: 0x13fccf0: v4i64 = X86ISD::VBROADCAST 0x1393c30
try.c: 0x1393c30: i64,ch = load<LD8[%uglygep72]> 0x12f7db0, 0x13e61a0, undef:i64
try.c: 0x13e61a0: i64 = add 0x13fdbd0, 0x13908c0
try.c: 0x13fdbd0: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0x13bafd0: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0x13908c0: i64 = shl 0x13ba780, Constant:i8<3>
try.c: 0x13ba780: i64,ch = CopyFromReg 0x12f7db0, Register:i64 %vreg50
try.c: 0x13fe090: i64 = Register %vreg50
try.c: 0x1395ac0: i8 = Constant<3>
try.c: 0x13fb360: i64 = undef
try.c: 0x13938a0: v4i64,ch = CopyFromReg 0x12f7db0, Register:v4i64 %vreg13
try.c: 0x13bfc40: v4i64 = Register %vreg13
try.c: 0x1392af0: v16i32 = X86ISD::VBROADCAST 0x13ba9e0
try.c: 0x13ba9e0: i32,ch = load<LD4[ConstantPool]> 0x12f7db0, 0x1414940, undef:i64
try.c: 0x1414940: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0x13bd760: i64 = TargetConstantPool<i32 1> 0
try.c: 0x13fb360: i64 = undef
try.c: 0x1414cd0: 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: 0x1414ba0: i32 = Constant<0>
try.c: 0x1414ba0: i32 = Constant<0>
try.c: 0x1414ba0: i32 = Constant<0>
try.c: 0x1414ba0: 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: 0x242d2c0: v4i64 = X86ISD::VTRUNC 0x242d0f0
try.c: 0x242d0f0: v16i32 = vselect 0x241ce30, 0x23ae0e0, 0x242cfc0
try.c: 0x241ce30: v4i1 = X86ISD::PCMPGTM 0x2414ba0, 0x23aee90
try.c: 0x2414ba0: v4i64 = X86ISD::VBROADCAST 0x23af220
try.c: 0x23af220: i64,ch = load<LD8[%uglygep72]> 0x230edd0, 0x2403430, undef:i64
try.c: 0x2403430: i64 = add 0x2415a80, 0x23a7990
try.c: 0x2415a80: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0x23d6de0: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0x23a7990: i64 = shl 0x23d6590, Constant:i8<3>
try.c: 0x23d6590: i64,ch = CopyFromReg 0x230edd0, Register:i64 %vreg50
try.c: 0x2415f40: i64 = Register %vreg50
try.c: 0x23a8f90: i8 = Constant<3>
try.c: 0x2413210: i64 = undef
try.c: 0x23aee90: v4i64,ch = CopyFromReg 0x230edd0, Register:v4i64 %vreg13
try.c: 0x23d2f80: v4i64 = Register %vreg13
try.c: 0x23ae0e0: v16i32 = X86ISD::VBROADCAST 0x23d67f0
try.c: 0x23d67f0: i32,ch = load<LD4[ConstantPool]> 0x230edd0, 0x242cc30, undef:i64
try.c: 0x242cc30: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0x23c3570: i64 = TargetConstantPool<i32 1> 0
try.c: 0x2413210: i64 = undef
try.c: 0x242cfc0: 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: 0x242ce90: i32 = Constant<0>
try.c: 0x242ce90: i32 = Constant<0>
try.c: 0x242ce90: i32 = Constant<0>
try.c: 0x242ce90: 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_128block.h:5,
stream.c: from Simon128192SSE4.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 Simon128192SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_128block.h:15:13: note: called from here
stream.c: #define XOR _mm_xor_si128
stream.c: Simon128192SSE4.h:24:41: note: in expansion of macro 'XOR'
stream.c: #define RD(U,V,k) (V=XOR(V,ROL(U,2)), V=XOR(V,AND(ROL(U,1),ROL8(U))), V=XOR(V,k))
stream.c: ^~~
stream.c: Simon128192SSE4.h:26:25: note: in expansion of macro 'RD'
stream.c: #define Sx2(U,V,rk,s) (RD(U[0],V[0],rk[s][0]))
stream.c: ^~
stream.c: Simon128192SSE4.h:49:98: note: in expansion of macro 'Sx2'
stream.c: R2x##n(X,Y,rk,60,61), R2x##n(X,Y,rk,62,63), R2x##n(X,Y,rk,64,65), R2x##n(X,Y,rk,66,67), Sx##n(X,Y,rk,68))
stream.c: ^~
stream.c: stream.c:115:21: note: in expansion of macro 'Enc'
stream.c: if (numbytes==32) Enc(X,Y,rk,2);
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_128block.h:5,
stream.c: from Simon128192SSE4.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 Simon128192SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_128block.h:15:13: note: called from here
stream.c: #define XOR _mm_xor_si128
stream.c: Simon128192SSE4.h:24:41: note: in expansion of macro 'XOR'
stream.c: #define RD(U,V,k) (V=XOR(V,ROL(U,2)), V=XOR(V,AND(ROL(U,1),ROL8(U))), V=XOR(V,k))
stream.c: ^~~
stream.c: Simon128192SSE4.h:26:25: note: in expansion of macro 'RD'
stream.c: #define Sx2(U,V,rk,s) (RD(U[0],V[0],rk[s][0]))
stream.c: ^~
stream.c: Simon128192SSE4.h:49:98: note: in expansion of macro 'Sx2'
stream.c: R2x##n(X,Y,rk,60,61), R2x##n(X,Y,rk,62,63), R2x##n(X,Y,rk,64,65), R2x##n(X,Y,rk,66,67), Sx##n(X,Y,rk,68))
stream.c: ^~
stream.c: stream.c:115:21: note: in expansion of macro 'Enc'
stream.c: if (numbytes==32) Enc(X,Y,rk,2);
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_128block.h:5,
stream.c: from Simon128192SSE4.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 Simon128192SSE4.h:17:0,
stream.c: from stream.c:20:
stream.c: Intrinsics_SSE4_128block.h:15:13: note: called from here
stream.c: #define XOR _mm_xor_si128
stream.c: Simon128192SSE4.h:24:41: note: in expansion of macro 'XOR'
stream.c: #define RD(U,V,k) (V=XOR(V,ROL(U,2)), V=XOR(V,AND(ROL(U,1),ROL8(U))), V=XOR(V,k))
stream.c: ^~~
stream.c: Simon128192SSE4.h:26:25: note: in expansion of macro 'RD'
stream.c: #define Sx2(U,V,rk,s) (RD(U[0],V[0],rk[s][0]))
stream.c: ^~
stream.c: Simon128192SSE4.h:49:98: note: in expansion of macro 'Sx2'
stream.c: R2x##n(X,Y,rk,60,61), R2x##n(X,Y,rk,62,63), R2x##n(X,Y,rk,64,65), R2x##n(X,Y,rk,66,67), Sx##n(X,Y,rk,68))
stream.c: ^~
stream.c: stream.c:115:21: note: in expansion of macro 'Enc'
stream.c: if (numbytes==32) Enc(X,Y,rk,2);
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