Implementation notes: amd64, panther, crypto_stream/speck64128ctr

Compiler output

stream.c: stream.c:332:3: error: always_inline function '_mm256_set_epi32' requires target feature 'avx', but would be inlined into function 'ExpandKey' that is compiled without support for 'avx'
stream.c:   EK(A,B,C,D,rk,key);
stream.c:   ^
stream.c: ./Speck64128AVX2.h:53:28: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,D,k,key) (RK(B,A,k,key,0),  RK(C,A,k,key,1),  RK(D,A,k,key,2),  RK(B,A,k,key,3),  RK(C,A,k,key,4),  RK(D,A,k,key,5),  RK(B,A,k,key,6), \
stream.c:                            ^
stream.c: ./Speck64128AVX2.h:51:28: 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_64block.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_AVX2_64block.h:24:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi32
stream.c:             ^
stream.c: stream.c:332:3: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
stream.c: ./Speck64128AVX2.h:53:28: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,D,k,key) (RK(B,A,k,key,0),  RK(C,A,k,key,1),  RK(D,A,k,key,2),  RK(B,A,k,key,3),  RK(C,A,k,key,4),  RK(D,A,k,key,5),  RK(B,A,k,key,6), \
stream.c:                            ^
stream.c: ./Speck64128AVX2.h:51:28: 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_64block.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: ...

Compiler output

stream.c: stream.c:348:3: error: always_inline function '_mm512_set_epi32' requires target feature 'avx512f', but would be inlined into function 'ExpandKey' that is compiled without support for 'avx512f'
stream.c:   EK(A,B,C,D,rk,key);
stream.c:   ^
stream.c: ./Speck64128AVX512.h:53:28: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,D,k,key) (RK(B,A,k,key,0),  RK(C,A,k,key,1),  RK(D,A,k,key,2),  RK(B,A,k,key,3),  RK(C,A,k,key,4),  RK(D,A,k,key,5),  RK(B,A,k,key,6), \
stream.c:                            ^
stream.c: ./Speck64128AVX512.h:51:26: 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_64block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c,c,c,c,c,c,c,c,c))
stream.c:                      ^
stream.c: ./Intrinsics_AVX512_64block.h:14:13: note: expanded from macro 'SET'
stream.c: #define SET _mm512_set_epi32
stream.c:             ^
stream.c: stream.c:348:3: error: AVX vector return of type '__m512i' (vector of 8 'long long' values) without 'avx512f' enabled changes the ABI
stream.c: ./Speck64128AVX512.h:53:28: note: expanded from macro 'EK'
stream.c: #define EK(A,B,C,D,k,key) (RK(B,A,k,key,0),  RK(C,A,k,key,1),  RK(D,A,k,key,2),  RK(B,A,k,key,3),  RK(C,A,k,key,4),  RK(D,A,k,key,5),  RK(B,A,k,key,6), \
stream.c:                            ^
stream.c: ./Speck64128AVX512.h:51:26: 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_64block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c,c,c,c,c,c,c,c,c))
stream.c:                      ^
stream.c: ...

Compiler output

stream.c: stream.c:134:21: 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,4);
stream.c:                     ^
stream.c: ./Speck64128SSE4.h:45:23: 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>:108:1: note: expanded from here
stream.c: Rx4
stream.c: ^
stream.c: ./Speck64128SSE4.h:25:22: note: expanded from macro 'Rx4'
stream.c: #define Rx4(X,Y,k)  (R(X[0],Y[0],k))
stream.c:                      ^
stream.c: ./Speck64128SSE4.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_64block.h:40:19: note: expanded from macro 'ROR8'
stream.c: #define ROR8(X)  (SHFL(X,R8))
stream.c:                   ^
stream.c: ./Intrinsics_SSE4_64block.h:35:14: note: expanded from macro 'SHFL'
stream.c: #define SHFL _mm_shuffle_epi8
stream.c:              ^
stream.c: stream.c:134:21: 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: ./Speck64128SSE4.h:45:41: 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: ...

Namespace violations

stream.o ExpandKey T