Implementation notes: amd64, hydra8, crypto_stream/simon64128ctr

Computer: hydra8
Microarchitecture: amd64; Ivy Bridge+AES (306a9)
Architecture: amd64
CPU ID: GenuineIntel-000306a9-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_stream
Primitive: simon64128ctr
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
598090779 0 0106149 804 1024T:sse4gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
621886316 0 0102592 860 960T:sse4clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
627085596 0 099928 860 960T:sse4clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
966390067 0 0104149 804 1024T:sse4gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
973185603 0 097882 852 960T:sse4clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
980189385 0 0101848 780 992T:sse4gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
993390775 0 0104468 796 1024T:sse4gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
1077889916 0 0102480 860 960T:sse4clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625

Compiler output


stream.c: stream.c:147:24: error: always_inline function '_mm256_add_epi32' requires target feature 'avx2', but would be inlined into function 'Encrypt' that is compiled without support for 'avx2'
stream.c:   SET1(X[0],nonce[1]); SET8(Y[0],nonce[0]);
stream.c:                        ^
stream.c: ./Intrinsics_AVX2_64block.h:25:46: note: expanded from macro 'SET8'
stream.c: #define SET8(X,c) (X=SET(c,c,c,c,c,c,c,c), X=ADD(X,_q))
stream.c:                                              ^
stream.c: ./Intrinsics_AVX2_64block.h:16:13: note: expanded from macro 'ADD'
stream.c: #define ADD _mm256_add_epi32
stream.c:             ^
stream.c: stream.c:149:21: error: always_inline function '_mm256_slli_epi32' requires target feature 'avx2', but would be inlined into function 'Encrypt' that is compiled without support for 'avx2'
stream.c:   if (numbytes==64) Enc(X,Y,rk,8);
stream.c:                     ^
stream.c: ./Simon64128AVX2.h:43:24: 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>:221:1: note: expanded from here
stream.c: R2x8
stream.c: ^
stream.c: ./Simon64128AVX2.h:30:28: note: expanded from macro 'R2x8'
stream.c: #define R2x8(X,Y,rk,r,s)  (Sx8(X,Y,rk[r][0]),  Sx8(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: ./Simon64128AVX2.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:
ImplementationCompiler
T:avx2clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:avx2clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:avx2clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:avx2clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


stream.c: stream.c:147:3: error: always_inline function '_mm256_set_epi32' 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]); SET8(Y[0],nonce[0]);
stream.c:   ^
stream.c: ./Intrinsics_AVX2_64block.h:24:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c:                      ^
stream.c: ./Intrinsics_AVX2_64block.h:23:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi32
stream.c:             ^
stream.c: stream.c:147:3: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
stream.c: ./Intrinsics_AVX2_64block.h:24:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c:                      ^
stream.c: ./Intrinsics_AVX2_64block.h:23:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi32
stream.c:             ^
stream.c: stream.c:147:24: error: always_inline function '_mm256_set_epi32' 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]); SET8(Y[0],nonce[0]);
stream.c:                        ^
stream.c: ./Intrinsics_AVX2_64block.h:25:22: note: expanded from macro 'SET8'
stream.c: #define SET8(X,c) (X=SET(c,c,c,c,c,c,c,c), X=ADD(X,_q))
stream.c:                      ^
stream.c: ./Intrinsics_AVX2_64block.h:23:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi32
stream.c:             ^
stream.c: ...

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
T:avx2clang -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_64block.h:5,
stream.c:                  from Simon64128AVX2.h:17,
stream.c:                  from stream.c:20:
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 Simon64128AVX2.h:17,
stream.c:                  from stream.c:20:
stream.c: Intrinsics_AVX2_64block.h:14:13: note: called from here
stream.c:    14 | #define XOR _mm256_xor_si256
stream.c: stream.c:460:10: note: in expansion of macro 'XOR'
stream.c:   460 |   M[6] = XOR(M[6], W[3]);
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_64block.h:5,
stream.c:                  from Simon64128AVX2.h:17,
stream.c:                  from stream.c:20:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:682:1: error: inlining failed in call to 'always_inline' '_mm256_slli_epi32': target specific option mismatch
stream.c:   682 | _mm256_slli_epi32 (__m256i __A, int __B)
stream.c:       | ^~~~~~~~~~~~~~~~~
stream.c: In file included from Simon64128AVX2.h:17,
stream.c:                  from stream.c:20:
stream.c: Intrinsics_AVX2_64block.h:17:13: note: called from here
stream.c: ...

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
T:avx2gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
T:avx2gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
T:avx2gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
T:avx2gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)

Compiler output


stream.c: stream.c:340:3: 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: ./Simon64128SSE4.h:64:19: note: expanded from macro 'EKBS'
stream.c: #define EKBS(rk) (RKBS(rk,4,_D),  RKBS(rk,5,_D),  RKBS(rk,6,_C),  RKBS(rk,7,_D),  RKBS(rk,8,_D),  RKBS(rk,9,_C),  RKBS(rk,10,_D), RKBS(rk,11,_D), \
stream.c:                   ^
stream.c: ./Simon64128SSE4.h:53:52: note: expanded from macro 'RKBS'
stream.c: #define RKBS(rk,r,_V) (rk[r][7]= _D ^ rk[r-4][7] ^ ROR8(rk[r-1][2])  ^ rk[r-3][7] ^ ROR8(rk[r-1][3])  ^ ROR8(rk[r-3][0]), \
stream.c:                                                    ^
stream.c: ./Intrinsics_SSE4_64block.h:39:19: note: expanded from macro 'ROR8'
stream.c: #define ROR8(X)  (SHFL(X,R8))
stream.c:                   ^
stream.c: ./Intrinsics_SSE4_64block.h:34:14: note: expanded from macro 'SHFL'
stream.c: #define SHFL _mm_shuffle_epi8
stream.c:              ^
stream.c: stream.c:340:3: 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: ./Simon64128SSE4.h:64:19: note: expanded from macro 'EKBS'
stream.c: #define EKBS(rk) (RKBS(rk,4,_D),  RKBS(rk,5,_D),  RKBS(rk,6,_C),  RKBS(rk,7,_D),  RKBS(rk,8,_D),  RKBS(rk,9,_C),  RKBS(rk,10,_D), RKBS(rk,11,_D), \
stream.c:                   ^
stream.c: ./Simon64128SSE4.h:53:85: note: expanded from macro 'RKBS'
stream.c: #define RKBS(rk,r,_V) (rk[r][7]= _D ^ rk[r-4][7] ^ ROR8(rk[r-1][2])  ^ rk[r-3][7] ^ ROR8(rk[r-1][3])  ^ ROR8(rk[r-3][0]), \
stream.c:                                                                                     ^
stream.c: ./Intrinsics_SSE4_64block.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:
ImplementationCompiler
T:sse4clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)