Implementation notes: amd64, hydra5, crypto_stream/speck128192ctr

Computer: hydra5
Microarchitecture: amd64; K10 32nm (300f10)
Architecture: amd64
CPU ID: AuthenticAMD-00300f10-178bfbff
SUPERCOP version: 20240625
Operation: crypto_stream
Primitive: speck128192ctr

Compiler output


stream.c: stream.c:292:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'avx', but would be inlined into function 'ExpandKey' that is compiled without support for 'avx'
stream.c:   EK(A,B,C,rk,key);
stream.c:   ^
stream.c: ./Speck128192AVX2.h:56:26: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,k,key) (RK(B,A,k,key,0),  RK(C,A,k,key,1),  RK(B,A,k,key,2),  RK(C,A,k,key,3),  RK(B,A,k,key,4),  RK(C,A,k,key,5),  RK(B,A,k,key,6), \
stream.c:                          ^
stream.c: ./Speck128192AVX2.h:54:28: note: expanded from macro 'RK'
stream.c: #define RK(X,Y,k,key,i)   (SET1(k[i],Y), key[i]=Y, X=RCS(X,8), X+=Y, X^=i, Y=LCS(Y,3), Y^=X)
stream.c:                            ^
stream.c: ./Intrinsics_AVX2_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:292:3: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
stream.c: ./Speck128192AVX2.h:56:26: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,k,key) (RK(B,A,k,key,0),  RK(C,A,k,key,1),  RK(B,A,k,key,2),  RK(C,A,k,key,3),  RK(B,A,k,key,4),  RK(C,A,k,key,5),  RK(B,A,k,key,6), \
stream.c:                          ^
stream.c: ./Speck128192AVX2.h:54:28: note: expanded from macro 'RK'
stream.c: #define RK(X,Y,k,key,i)   (SET1(k[i],Y), key[i]=Y, X=RCS(X,8), X+=Y, X^=i, Y=LCS(Y,3), Y^=X)
stream.c:                            ^
stream.c: ./Intrinsics_AVX2_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: ...

Number of similar (implementation,compiler) pairs: 5, 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)
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 Speck128192AVX2.h:17,
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:    25 | #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:   130 |   SET1(X[0],nonce[1]); SET4(Y[0],nonce[0]);
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 Speck128192AVX2.h:17,
stream.c:                  from stream.c:20:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:126:1: error: inlining failed in call to 'always_inline' '_mm256_add_epi64': target specific option mismatch
stream.c:   126 | _mm256_add_epi64 (__m256i __A, __m256i __B)
stream.c:       | ^~~~~~~~~~~~~~~~
stream.c: In file included from Speck128192AVX2.h:17,
stream.c:                  from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:17:13: note: called from here
stream.c:    17 | #define ADD _mm256_add_epi64
stream.c:       |             ^
stream.c: Intrinsics_AVX2_128block.h:26:38: note: in expansion of macro 'ADD'
stream.c:    26 | #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 (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:265:10: warning: unused variable 'j' [-Wunused-variable]
stream.c:   u64  i,j,x[2],y[2];
stream.c:          ^
stream.c: stream.c:265:8: warning: unused variable 'i' [-Wunused-variable]
stream.c:   u64  i,j,x[2],y[2];
stream.c:        ^
stream.c: stream.c:334:3: error: always_inline function '_mm512_set_epi64' requires target feature 'avx512f', but would be inlined into function 'ExpandKey' that is compiled without support for 'avx512f'
stream.c:   EK(A,B,C,rk,key);
stream.c:   ^
stream.c: ./Speck128192AVX512.h:62:26: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,k,key) (RK(B,A,k,key,0),  RK(C,A,k,key,1),  RK(B,A,k,key,2),  RK(C,A,k,key,3),  RK(B,A,k,key,4),  RK(C,A,k,key,5),  RK(B,A,k,key,6), \
stream.c:                          ^
stream.c: ./Speck128192AVX512.h:60:26: note: expanded from macro 'RK'
stream.c: #define RK(X,Y,k,key,i) (SET1(k[i],Y), key[i]=Y, X=RCS(X,8), X+=Y, X^=i, Y=LCS(Y,3), Y^=X)
stream.c:                          ^
stream.c: ./Intrinsics_AVX512_128block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c:                      ^
stream.c: ./Intrinsics_AVX512_128block.h:16:13: note: expanded from macro 'SET'
stream.c: #define SET _mm512_set_epi64
stream.c:             ^
stream.c: stream.c:334:3: error: AVX vector return of type '__m512i' (vector of 8 'long long' values) without 'avx512f' enabled changes the ABI
stream.c: ./Speck128192AVX512.h:62:26: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,k,key) (RK(B,A,k,key,0),  RK(C,A,k,key,1),  RK(B,A,k,key,2),  RK(C,A,k,key,3),  RK(B,A,k,key,4),  RK(C,A,k,key,5),  RK(B,A,k,key,6), \
stream.c:                          ^
stream.c: ...

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
T:avx512clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:avx512clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:avx512clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:avx512clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


stream.c: stream.c:265:8: warning: unused variable 'i' [-Wunused-variable]
stream.c:   u64  i,j,x[2],y[2];
stream.c:        ^
stream.c: stream.c:265:10: warning: unused variable 'j' [-Wunused-variable]
stream.c:   u64  i,j,x[2],y[2];
stream.c:          ^
stream.c: stream.c:334:3: error: always_inline function '_mm512_set_epi64' requires target feature 'avx512f', but would be inlined into function 'ExpandKey' that is compiled without support for 'avx512f'
stream.c:   EK(A,B,C,rk,key);
stream.c:   ^
stream.c: ./Speck128192AVX512.h:62:26: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,k,key) (RK(B,A,k,key,0),  RK(C,A,k,key,1),  RK(B,A,k,key,2),  RK(C,A,k,key,3),  RK(B,A,k,key,4),  RK(C,A,k,key,5),  RK(B,A,k,key,6), \
stream.c:                          ^
stream.c: ./Speck128192AVX512.h:60:26: note: expanded from macro 'RK'
stream.c: #define RK(X,Y,k,key,i) (SET1(k[i],Y), key[i]=Y, X=RCS(X,8), X+=Y, X^=i, Y=LCS(Y,3), Y^=X)
stream.c:                          ^
stream.c: ./Intrinsics_AVX512_128block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c:                      ^
stream.c: ./Intrinsics_AVX512_128block.h:16:13: note: expanded from macro 'SET'
stream.c: #define SET _mm512_set_epi64
stream.c:             ^
stream.c: stream.c:334:3: error: AVX vector return of type '__m512i' (vector of 8 'long long' values) without 'avx512f' enabled changes the ABI
stream.c: ./Speck128192AVX512.h:62:26: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,k,key) (RK(B,A,k,key,0),  RK(C,A,k,key,1),  RK(B,A,k,key,2),  RK(C,A,k,key,3),  RK(B,A,k,key,4),  RK(C,A,k,key,5),  RK(B,A,k,key,6), \
stream.c:                          ^
stream.c: ...

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
T:avx512clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


stream.c: stream.c: In function 'Encrypt_Xor':
stream.c: stream.c:265:10: warning: unused variable 'j' [-Wunused-variable]
stream.c:   265 |   u64  i,j,x[2],y[2];
stream.c:       |          ^
stream.c: stream.c:265:8: warning: unused variable 'i' [-Wunused-variable]
stream.c:   265 |   u64  i,j,x[2],y[2];
stream.c:       |        ^
stream.c: In file included from Speck128192AVX512.h:17,
stream.c:                  from stream.c:21:
stream.c: stream.c: In function 'Encrypt':
stream.c: Intrinsics_AVX512_128block.h:25:21: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
stream.c:    25 | #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c:       |                   ~~^~~~~~~~~~~~~~~~~~~~~~
stream.c: stream.c:137:5: note: in expansion of macro 'SET1'
stream.c:   137 |     SET1(X[0],nonce[1]); SET8(Y[0],nonce[0]);
stream.c:       |     ^~~~
stream.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:49,
stream.c:                  from Intrinsics_AVX512_128block.h:5,
stream.c:                  from Speck128192AVX512.h:17,
stream.c:                  from stream.c:21:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx512fintrin.h:6481:1: error: inlining failed in call to 'always_inline' '_mm512_storeu_si512': target specific option mismatch
stream.c:  6481 | _mm512_storeu_si512 (void *__P, __m512i __A)
stream.c:       | ^~~~~~~~~~~~~~~~~~~
stream.c: In file included from Speck128192AVX512.h:17,
stream.c:                  from stream.c:21:
stream.c: ...

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
T:avx512gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
T:avx512gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
T:avx512gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
T:avx512gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)

Compiler output


stream.c: stream.c:116:21: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'Encrypt' that is compiled without support for 'ssse3'
stream.c:   if (numbytes==32) Enc(X,Y,rk,2);
stream.c:                     ^
stream.c: ./Speck128192SSE4.h:42:23: note: expanded from macro 'Enc'
stream.c: #define Enc(X,Y,k,n) (Rx##n(X,Y,k[0]),  Rx##n(X,Y,k[1]),  Rx##n(X,Y,k[2]),  Rx##n(X,Y,k[3]),  Rx##n(X,Y,k[4]),  Rx##n(X,Y,k[5]),  Rx##n(X,Y,k[6]),  Rx##n(X,Y,k[7]), \
stream.c:                       ^
stream.c: <scratch space>:106:1: note: expanded from here
stream.c: Rx2
stream.c: ^
stream.c: ./Speck128192SSE4.h:25:21: note: expanded from macro 'Rx2'
stream.c: #define Rx2(X,Y,k) (R(X[0],Y[0],k))
stream.c:                     ^
stream.c: ./Speck128192SSE4.h:23:29: note: expanded from macro 'R'
stream.c: #define R(X,Y,k) (X=XOR(ADD(ROR8(X),Y),k), Y=XOR(ROL(Y,3),X))
stream.c:                             ^
stream.c: ./Intrinsics_SSE4_128block.h:41:19: note: expanded from macro 'ROR8'
stream.c: #define ROR8(X)  (SHFL(X,R8))
stream.c:                   ^
stream.c: ./Intrinsics_SSE4_128block.h:37:14: note: expanded from macro 'SHFL'
stream.c: #define SHFL _mm_shuffle_epi8
stream.c:              ^
stream.c: stream.c:116:21: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'Encrypt' that is compiled without support for 'ssse3'
stream.c: ./Speck128192SSE4.h:42:41: note: expanded from macro 'Enc'
stream.c: #define Enc(X,Y,k,n) (Rx##n(X,Y,k[0]),  Rx##n(X,Y,k[1]),  Rx##n(X,Y,k[2]),  Rx##n(X,Y,k[3]),  Rx##n(X,Y,k[4]),  Rx##n(X,Y,k[5]),  Rx##n(X,Y,k[6]),  Rx##n(X,Y,k[7]), \
stream.c:                                         ^
stream.c: ...

Number of similar (implementation,compiler) pairs: 5, namely:
ImplementationCompiler
T:sse4clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:sse4clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:sse4clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:sse4clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
T:sse4clang -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/smmintrin.h:32,
stream.c:                  from Intrinsics_SSE4_128block.h:5,
stream.c:                  from Speck128192SSE4.h:17,
stream.c:                  from stream.c:20:
stream.c: stream.c: In function 'Encrypt':
stream.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
stream.c:   136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
stream.c:       | ^~~~~~~~~~~~~~~~
stream.c: In file included from Speck128192SSE4.h:17,
stream.c:                  from stream.c:20:
stream.c: Intrinsics_SSE4_128block.h:15:13: note: called from here
stream.c:    15 | #define XOR _mm_xor_si128
stream.c: Speck128192SSE4.h:23:21: note: in expansion of macro 'XOR'
stream.c:    23 | #define R(X,Y,k) (X=XOR(ADD(ROR8(X),Y),k), Y=XOR(ROL(Y,3),X))
stream.c:       |                     ^~~
stream.c: Speck128192SSE4.h:25:21: note: in expansion of macro 'R'
stream.c:    25 | #define Rx2(X,Y,k) (R(X[0],Y[0],k))
stream.c:       |                     ^
stream.c: Speck128192SSE4.h:46:23: note: in expansion of macro 'Rx2'
stream.c:    46 |                       Rx##n(X,Y,k[32]))
stream.c:       |                       ^~
stream.c: stream.c:116:21: note: in expansion of macro 'Enc'
stream.c:   116 |   if (numbytes==32) Enc(X,Y,rk,2);
stream.c:       |                     ^~~
stream.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:32,
stream.c: ...

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
T:sse4gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
T:sse4gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
T:sse4gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
T:sse4gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)