Implementation notes: amd64, saber214, crypto_stream/simon128128ctr

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: ...

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: ...

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: ...

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: ...

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[]);