Implementation notes: amd64, oki, crypto_stream/simon128128ctr

Computer: oki
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20181123
Operation: crypto_stream
Primitive: simon128128ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
4430? ? ?? ? ?avx2clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019011020181123
4466? ? ?? ? ?avx2clang_-O3_-fwrapv_-march=x86-64_-mcpu=core-avx2_-mavx2_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019011020181123
7002? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019011020181123
7030? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019011020181123
7070? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O2_-fomit-frame-pointer2019011020181123
7100? ? ?? ? ?avx2gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2019011020181123
7112? ? ?? ? ?avx2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019011020181123
7204? ? ?? ? ?avx2gcc_-m64_-march=core-avx2_-O_-fomit-frame-pointer2019011020181123
7376? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019011020181123
7398? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2019011020181123
8108? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2019011020181123
8110? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2019011020181123
8188? ? ?? ? ?sse4clang_-O3_-fwrapv_-march=x86-64_-mcpu=core-avx2_-mavx2_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019011020181123
8192? ? ?? ? ?sse4clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019011020181123
8194? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O3_-fomit-frame-pointer2019011020181123
8236? ? ?? ? ?sse4clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019011020181123
8252? ? ?? ? ?sse4clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019011020181123
8640? ? ?? ? ?sse4gcc_-m64_-march=core2_-O3_-fomit-frame-pointer2019011020181123
8652? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2019011020181123
8654? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2019011020181123
8686? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2019011020181123
11270? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O_-fomit-frame-pointer2019011020181123
11334? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2019011020181123
11352? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2019011020181123
11356? ? ?? ? ?sse4gcc_-m64_-march=core2_-O_-fomit-frame-pointer2019011020181123
12176? ? ?? ? ?sse4gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2019011020181123
12326? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O2_-fomit-frame-pointer2019011020181123
12356? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2019011020181123
12364? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2019011020181123
12420? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2019011020181123
12424? ? ?? ? ?sse4gcc_-m64_-march=core2_-O2_-fomit-frame-pointer2019011020181123
12424? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2019011020181123
12756? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019011020181123
12760? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2019011020181123
12854? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-O_-fomit-frame-pointer2019011020181123
12860? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2019011020181123
12860? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2019011020181123
12996? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019011020181123
13002? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019011020181123
13298? ? ?? ? ?sse4gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2019011020181123
13340? ? ?? ? ?sse4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019011020181123
13346? ? ?? ? ?sse4gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2019011020181123
13458? ? ?? ? ?sse4gcc_-m64_-march=core2_-Os_-fomit-frame-pointer2019011020181123
13458? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2019011020181123
13458? ? ?? ? ?sse4gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2019011020181123
14254? ? ?? ? ?sse4gcc_-m64_-march=core-avx2_-Os_-fomit-frame-pointer2019011020181123
14256? ? ?? ? ?sse4gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2019011020181123
14258? ? ?? ? ?sse4gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2019011020181123

Compiler output

Implementation: avx2
Security model: unknown
Compiler: cc
stream.c: In file included from Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:9:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:25:46: 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:9:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:27:75: 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:9:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:28:25: note: in expansion of macro 'u256'
stream.c: int ExpandKeyBS(u64 K[],u256 rk[][8]);
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:9:14: error: unknown type name '__m256i'
stream.c: #define u256 __m256i
stream.c: ^
stream.c: stream.c:29:27: 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:130:3: 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:24:22: 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:23:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi64x
stream.c: ^
stream.c: stream.c:130:24: 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:25:22: 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:23:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi64x
stream.c: ^
stream.c: stream.c:130:24: 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:25:38: 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:16:13: 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: 0x2058bd0: v4i64 = X86ISD::VTRUNC 0x2058a00
try.c: 0x2058a00: v16i32 = vselect 0x2055640, 0x2002020, 0x20588d0
try.c: 0x2055640: v4i1 = X86ISD::PCMPGTM 0x20410b0, 0x2002dd0
try.c: 0x20410b0: v4i64 = X86ISD::VBROADCAST 0x2003160
try.c: 0x2003160: i64,ch = load<LD8[%uglygep72]> 0x1f3cdb0, 0x1fe5180, undef:i64
try.c: 0x1fe5180: i64 = add 0x2041f90, 0x1fe1d10
try.c: 0x2041f90: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0x2022550: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0x1fe1d10: i64 = shl 0x2021d00, Constant:i8<3>
try.c: 0x2021d00: i64,ch = CopyFromReg 0x1f3cdb0, Register:i64 %vreg50
try.c: 0x2042450: i64 = Register %vreg50
try.c: 0x1fd7c60: i8 = Constant<3>
try.c: 0x203f720: i64 = undef
try.c: 0x2002dd0: v4i64,ch = CopyFromReg 0x1f3cdb0, Register:v4i64 %vreg13
try.c: 0x1fdd2b0: v4i64 = Register %vreg13
try.c: 0x2002020: v16i32 = X86ISD::VBROADCAST 0x2021f60
try.c: 0x2021f60: i32,ch = load<LD4[ConstantPool]> 0x1f3cdb0, 0x2058540, undef:i64
try.c: 0x2058540: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0x1fdadd0: i64 = TargetConstantPool<i32 1> 0
try.c: 0x203f720: i64 = undef
try.c: 0x20588d0: 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: 0x20587a0: i32 = Constant<0>
try.c: 0x20587a0: i32 = Constant<0>
try.c: 0x20587a0: i32 = Constant<0>
try.c: 0x20587a0: 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:130:24: 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:25:38: 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:16:13: note: expanded from macro 'ADD'
stream.c: #define ADD _mm256_add_epi64
stream.c: ^
stream.c: stream.c:132:21: 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: ./Simon128128AVX2.h:41:24: 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>:107:1: note: expanded from here
stream.c: R2x4
stream.c: ^
stream.c: ./Simon128128AVX2.h:30:28: note: expanded from macro 'R2x4'
stream.c: #define R2x4(X,Y,rk,r,s) (Sx4(X,Y,rk[r][0]), Sx4(Y,X,rk[s][0]))
stream.c: ^
stream.c: ./Simon128128AVX2.h:25:22: note: expanded from macro 'Sx4'
stream.c: #define Sx4(U,V,k) (RD(U[0],V[0],k))
stream.c: ^
stream.c: ./Simon128128AVX2.h:23:22: 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: 0x2081aa0: v4i64 = X86ISD::VTRUNC 0x20818d0
try.c: 0x20818d0: v16i32 = vselect 0x2071b40, 0x202b350, 0x20817a0
try.c: 0x2071b40: v4i1 = X86ISD::PCMPGTM 0x206a7d0, 0x2005620
try.c: 0x206a7d0: v4i64 = X86ISD::VBROADCAST 0x20059b0
try.c: 0x20059b0: i64,ch = load<LD8[%uglygep72]> 0x1f65dc0, 0x2024030, undef:i64
try.c: 0x2024030: i64 = add 0x206b6b0, 0x200aef0
try.c: 0x206b6b0: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0x2062320: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0x200aef0: i64 = shl 0x2061ad0, Constant:i8<3>
try.c: 0x2061ad0: i64,ch = CopyFromReg 0x1f65dc0, Register:i64 %vreg50
try.c: 0x206bb70: i64 = Register %vreg50
try.c: 0x1fe85c0: i8 = Constant<3>
try.c: 0x2068e40: i64 = undef
try.c: 0x2005620: v4i64,ch = CopyFromReg 0x1f65dc0, Register:v4i64 %vreg13
try.c: 0x2001830: v4i64 = Register %vreg13
try.c: 0x202b350: v16i32 = X86ISD::VBROADCAST 0x2061d30
try.c: 0x2061d30: i32,ch = load<LD4[ConstantPool]> 0x1f65dc0, 0x2081410, undef:i64
try.c: 0x2081410: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0x1fff350: i64 = TargetConstantPool<i32 1> 0
try.c: 0x2068e40: i64 = undef
try.c: 0x20817a0: 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: 0x2081670: i32 = Constant<0>
try.c: 0x2081670: i32 = Constant<0>
try.c: 0x2081670: i32 = Constant<0>
try.c: 0x2081670: 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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:24:21: 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:130:3: 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 Simon128128AVX2.h:17,
stream.c: from stream.c:21:
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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:16:13: note: called from here
stream.c: #define ADD _mm256_add_epi64
stream.c: ^
stream.c: Intrinsics_AVX2_128block.h:25:38: 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:130:24: 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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:24:21: 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:130:3: 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 Simon128128AVX2.h:17,
stream.c: from stream.c:21:
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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:14:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c: stream.c:414:10: 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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:24:21: 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:130:3: 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 Simon128128AVX2.h:17,
stream.c: from stream.c:21:
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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:14:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c: stream.c:414:10: 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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX2_128block.h:24:21: 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:130:3: 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 Simon128128AVX2.h:17,
stream.c: from stream.c:21:
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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:14:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c: stream.c:414:10: 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 Simon128128AVX2.h:17,
stream.c: from stream.c:21:
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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:14:13: note: called from here
stream.c: #define XOR _mm256_xor_si256
stream.c: stream.c:414:10: 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 Simon128128AVX2.h:17,
stream.c: from stream.c:21:
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 Simon128128AVX2.h:17:0,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:14:13: 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_simon128128ctr.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_simon128128ctr.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_simon128128ctr.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_simon128128ctr.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_simon128128ctr.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_simon128128ctr.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 Simon128128SSE4.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 Simon128128SSE4.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:23:82: 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:25:113: 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:26:25: 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:306:3: 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: ./Simon128128SSE4.h:62:19: note: expanded from macro 'EKBS'
stream.c: #define EKBS(rk) (RKBS(rk,2,_D), RKBS(rk,3,_C), RKBS(rk,4,_D), RKBS(rk,5,_C), RKBS(rk,6,_D), RKBS(rk,7,_D), RKBS(rk,8,_D), RKBS(rk,9,_D), \
stream.c: ^
stream.c: ./Simon128128SSE4.h:53:52: note: expanded from macro 'RKBS'
stream.c: #define RKBS(rk,r,_V) (rk[r][7]= _D ^ rk[r-2][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:306:3: 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: ./Simon128128SSE4.h:62:19: note: expanded from macro 'EKBS'
stream.c: #define EKBS(rk) (RKBS(rk,2,_D), RKBS(rk,3,_C), RKBS(rk,4,_D), RKBS(rk,5,_C), RKBS(rk,6,_D), RKBS(rk,7,_D), RKBS(rk,8,_D), RKBS(rk,9,_D), \
stream.c: ^
stream.c: ./Simon128128SSE4.h:54:38: note: expanded from macro 'RKBS'
stream.c: rk[r][6]= _D ^ rk[r-2][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: 0x10a46d0: v4i64 = X86ISD::VTRUNC 0x10a4500
try.c: 0x10a4500: v16i32 = vselect 0x107fb50, 0x1020070, 0x10a43d0
try.c: 0x107fb50: v4i1 = X86ISD::PCMPGTM 0x1087fc0, 0x1020e20
try.c: 0x1087fc0: v4i64 = X86ISD::VBROADCAST 0x10211b0
try.c: 0x10211b0: i64,ch = load<LD8[%uglygep72]> 0xf81dc0, 0x106e790, undef:i64
try.c: 0x106e790: i64 = add 0x1088ea0, 0x1021ec0
try.c: 0x1088ea0: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0x1017d20: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0x1021ec0: i64 = shl 0x10174d0, Constant:i8<3>
try.c: 0x10174d0: i64,ch = CopyFromReg 0xf81dc0, Register:i64 %vreg50
try.c: 0x1089360: i64 = Register %vreg50
try.c: 0x1004110: i8 = Constant<3>
try.c: 0x1086630: i64 = undef
try.c: 0x1020e20: v4i64,ch = CopyFromReg 0xf81dc0, Register:v4i64 %vreg13
try.c: 0x10344d0: v4i64 = Register %vreg13
try.c: 0x1020070: v16i32 = X86ISD::VBROADCAST 0x1017730
try.c: 0x1017730: i32,ch = load<LD4[ConstantPool]> 0xf81dc0, 0x10a4040, undef:i64
try.c: 0x10a4040: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0x101bf60: i64 = TargetConstantPool<i32 1> 0
try.c: 0x1086630: i64 = undef
try.c: 0x10a43d0: 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: 0x10a42a0: i32 = Constant<0>
try.c: 0x10a42a0: i32 = Constant<0>
try.c: 0x10a42a0: i32 = Constant<0>
try.c: 0x10a42a0: 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: 0x13ce8c0: v4i64 = X86ISD::VTRUNC 0x13ce6f0
try.c: 0x13ce6f0: v16i32 = vselect 0x13c0920, 0x1360bf0, 0x13ce5c0
try.c: 0x13c0920: v4i1 = X86ISD::PCMPGTM 0x13b71c0, 0x13619a0
try.c: 0x13b71c0: v4i64 = X86ISD::VBROADCAST 0x1361d30
try.c: 0x1361d30: i64,ch = load<LD8[%uglygep72]> 0x12b0df0, 0x1378b90, undef:i64
try.c: 0x1378b90: i64 = add 0x13b80a0, 0x13630e0
try.c: 0x13b80a0: i64 = X86ISD::Wrapper TargetGlobalAddress:i64<[64 x i64]* @cycles> 0
try.c: 0x136a6e0: i64 = TargetGlobalAddress<[64 x i64]* @cycles> 0
try.c: 0x13630e0: i64 = shl 0x1369e90, Constant:i8<3>
try.c: 0x1369e90: i64,ch = CopyFromReg 0x12b0df0, Register:i64 %vreg50
try.c: 0x13b8560: i64 = Register %vreg50
try.c: 0x1346790: i8 = Constant<3>
try.c: 0x13b5020: i64 = undef
try.c: 0x13619a0: v4i64,ch = CopyFromReg 0x12b0df0, Register:v4i64 %vreg13
try.c: 0x1375ce0: v4i64 = Register %vreg13
try.c: 0x1360bf0: v16i32 = X86ISD::VBROADCAST 0x136a0f0
try.c: 0x136a0f0: i32,ch = load<LD4[ConstantPool]> 0x12b0df0, 0x13ce230, undef:i64
try.c: 0x13ce230: i64 = X86ISD::Wrapper TargetConstantPool:i64<i32 1> 0
try.c: 0x134fb00: i64 = TargetConstantPool<i32 1> 0
try.c: 0x13b5020: i64 = undef
try.c: 0x13ce5c0: 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: 0x13ce490: i32 = Constant<0>
try.c: 0x13ce490: i32 = Constant<0>
try.c: 0x13ce490: i32 = Constant<0>
try.c: 0x13ce490: 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 Simon128128SSE4.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 Simon128128SSE4.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: Simon128128SSE4.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: Simon128128SSE4.h:26:22: note: in expansion of macro 'RD'
stream.c: #define Sx2(U,V,k) (RD(U[0],V[0],k))
stream.c: ^~
stream.c: Simon128128SSE4.h:31:47: note: in expansion of macro 'Sx2'
stream.c: #define R2x2(X,Y,rk,r,s) (Sx2(X,Y,rk[r][0]), Sx2(Y,X,rk[s][0]))
stream.c: ^~~
stream.c: Simon128128SSE4.h:47:76: note: in expansion of macro 'R2x2'
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))
stream.c: ^~~
stream.c: stream.c:113:21: note: in expansion of macro 'Enc'
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 Simon128128SSE4.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 Simon128128SSE4.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: Simon128128SSE4.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: Simon128128SSE4.h:26:22: note: in expansion of macro 'RD'
stream.c: #define Sx2(U,V,k) (RD(U[0],V[0],k))
stream.c: ^~
stream.c: Simon128128SSE4.h:31:47: note: in expansion of macro 'Sx2'
stream.c: #define R2x2(X,Y,rk,r,s) (Sx2(X,Y,rk[r][0]), Sx2(Y,X,rk[s][0]))
stream.c: ^~~
stream.c: Simon128128SSE4.h:47:76: note: in expansion of macro 'R2x2'
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))
stream.c: ^~~
stream.c: stream.c:113:21: note: in expansion of macro 'Enc'
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 Simon128128SSE4.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 Simon128128SSE4.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: Simon128128SSE4.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: Simon128128SSE4.h:26:22: note: in expansion of macro 'RD'
stream.c: #define Sx2(U,V,k) (RD(U[0],V[0],k))
stream.c: ^~
stream.c: Simon128128SSE4.h:31:47: note: in expansion of macro 'Sx2'
stream.c: #define R2x2(X,Y,rk,r,s) (Sx2(X,Y,rk[r][0]), Sx2(Y,X,rk[s][0]))
stream.c: ^~~
stream.c: Simon128128SSE4.h:47:76: note: in expansion of macro 'R2x2'
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))
stream.c: ^~~
stream.c: stream.c:113:21: note: in expansion of macro 'Enc'
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