Implementation notes: amd64, h6sandy, crypto_stream/simon128128ctr
Computer: h6sandy
Microarchitecture: amd64; Sandy Bridge (206a7)
Architecture: amd64
CPU ID: GenuineIntel-000206a7-bfebfbff
SUPERCOP version: 20240808
Operation: crypto_stream
Primitive: simon128128ctr
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
8071 | 113390 0 0 | 128757 804 1024 | T:sse4 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240718 | 20240716 |
8611 | 112160 0 0 | 128427 844 960 | T:sse4 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240718 | 20240716 |
8894 | 112208 0 0 | 126531 844 960 | T:sse4 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240718 | 20240716 |
13837 | 112240 0 0 | 124501 836 960 | T:sse4 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240718 | 20240716 |
14355 | 115927 0 0 | 128416 780 992 | T:sse4 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240718 | 20240716 |
14606 | 113198 0 0 | 127285 804 1024 | T:sse4 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240718 | 20240716 |
14762 | 115425 0 0 | 127995 844 960 | T:sse4 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240718 | 20240716 |
14831 | 118010 0 0 | 131708 796 1024 | T:sse4 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240718 | 20240716 |
Compiler output
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: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:132:21: error: always_inline function '_mm256_slli_epi64' 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>:223:1: 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: note: (skipping 1 expansions in backtrace; use -fmacro-backtrace-limit=0 to see all)
stream.c: ./Simon128128AVX2.h:23:28: note: expanded from macro 'RD'
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: ...
Number of similar (implementation,compiler) pairs: 4, namely:
Implementation | Compiler |
T:avx2 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:avx2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:avx2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:avx2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
stream.c: stream.c:130:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'avx', but would be inlined into function 'Encrypt' that is compiled without support for 'avx'
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:130:3: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
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:130:24: error: always_inline function '_mm256_set_epi64x' requires target feature 'avx', but would be inlined into function 'Encrypt' that is compiled without support for 'avx'
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: ...
Number of similar (implementation,compiler) pairs: 1, namely:
Implementation | Compiler |
T:avx2 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
stream.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
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/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:913:1: error: inlining failed in call to 'always_inline' '_mm256_xor_si256': target specific option mismatch
stream.c: 913 | _mm256_xor_si256 (__m256i __A, __m256i __B)
stream.c: | ^~~~~~~~~~~~~~~~
stream.c: In file included from Simon128128AVX2.h:17,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:15:13: note: called from here
stream.c: 15 | #define XOR _mm256_xor_si256
stream.c: stream.c:414:10: note: in expansion of macro 'XOR'
stream.c: 414 | T[6] = XOR(T[6], SL(W[3],1));
stream.c: | ^~~
stream.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
stream.c: from Intrinsics_AVX2_128block.h:5,
stream.c: from Simon128128AVX2.h:17,
stream.c: from stream.c:21:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:696:1: error: inlining failed in call to 'always_inline' '_mm256_slli_epi64': target specific option mismatch
stream.c: 696 | _mm256_slli_epi64 (__m256i __A, int __B)
stream.c: | ^~~~~~~~~~~~~~~~~
stream.c: In file included from Simon128128AVX2.h:17,
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX2_128block.h:15:13: note: called from here
stream.c: ...
Number of similar (implementation,compiler) pairs: 4, namely:
Implementation | Compiler |
T:avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
Compiler output
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 (implementation,compiler) pairs: 1, namely:
Implementation | Compiler |
T:sse4 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
stream.c: stream.c:324:58: warning: argument 1 of type '__m128i[8]' with mismatched bound [-Warray-parameter=]
stream.c: 324 | inline __attribute__((always_inline)) int Transpose(u128 T[8])
stream.c: stream.c:28:58: note: previously declared as '__m128i[]'
stream.c: 28 | inline __attribute__((always_inline)) int Transpose(u128 M[]);
Number of similar (implementation,compiler) pairs: 4, namely:
Implementation | Compiler |
T:sse4 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:sse4 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:sse4 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:sse4 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
Namespace violations
stream.o ExpandKeyBS T
stream.o ExpandKeyNBS T
Number of similar (implementation,compiler) pairs: 8, namely:
Implementation | Compiler |
T:sse4 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:sse4 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:sse4 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:sse4 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
T:sse4 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:sse4 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:sse4 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
T:sse4 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |