Implementation notes: amd64, scw1b63b1, crypto_stream/speck128128ctr

Computer: scw1b63b1
Architecture: amd64
CPU ID: GenuineIntel-000506f1-0f8bfbff
SUPERCOP version: 20191017
Operation: crypto_stream
Primitive: speck128128ctr

Compiler output

Implementation: avx2
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

stream.c: stream.c:288:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'xsave', but would be inlined into function 'ExpandKey' that is compiled without support for 'xsave'
stream.c: EK(A,B,rk,key);
stream.c: ^
stream.c: ./Speck128128AVX2.h:54:24: note: expanded from macro 'EK'
stream.c: #define EK(A,B,k,key) (RK(B,A,k,key,0), RK(B,A,k,key,1), RK(B,A,k,key,2), RK(B,A,k,key,3), RK(B,A,k,key,4), RK(B,A,k,key,5), RK(B,A,k,key,6), ^
stream.c: ./Speck128128AVX2.h:52:28: 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: ...
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: fatal error: too many errors emitted, stopping now [-ferror-limit=]
stream.c: 20 errors generated.

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

stream.c: stream.c:288:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'ExpandKey' that is compiled without support for 'sse4.2'
stream.c: EK(A,B,rk,key);
stream.c: ^
stream.c: ./Speck128128AVX2.h:54:24: note: expanded from macro 'EK'
stream.c: #define EK(A,B,k,key) (RK(B,A,k,key,0), RK(B,A,k,key,1), RK(B,A,k,key,2), RK(B,A,k,key,3), RK(B,A,k,key,4), RK(B,A,k,key,5), RK(B,A,k,key,6), ^
stream.c: ./Speck128128AVX2.h:52:28: 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: ...
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: fatal error: too many errors emitted, stopping now [-ferror-limit=]
stream.c: 20 errors generated.

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

stream.c: In file included from Speck128128AVX2.h:17:0,
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: #define SET1(X,c) (X=SET(c,c,c,c))
stream.c: ~~^~~~~~~~~~~~~~
stream.c: stream.c:128:3: note: in expansion of macro ‘SET1’
stream.c: 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/6/include/immintrin.h:43:0,
stream.c: ...
stream.c: from stream.c:20:
stream.c: Intrinsics_AVX2_128block.h:31:18: note: called from here
stream.c: #define ST(ip,X) _mm256_storeu_si256((__m256i *)(ip),X)
stream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: Intrinsics_AVX2_128block.h:32:25: note: in expansion of macro ‘ST’
stream.c: #define STORE(out,X,Y) (ST(out,LOW(Y,X)), ST(out+32,HIGH(Y,X)))
stream.c: ^~
stream.c: stream.c:149:22: note: in expansion of macro ‘STORE’
stream.c: if (numbytes>=256) STORE(out+192,X[3],Y[3]);
stream.c: ^~~~~

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2

Compiler output

Implementation: avx512
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

stream.c: stream.c:135:5: warning: implicit declaration of function '_mm512_set_epi64' is invalid in C99 [-Wimplicit-function-declaration]
stream.c: SET1(X[0],nonce[1]); SET8(Y[0],nonce[0]);
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:135:5: error: assigning to '__m512i' (vector of 8 'long long' values) from incompatible type 'int'
stream.c: ...
stream.c: Y[0]=XOR(ROL(Y[0],3),X[0]))
stream.c: ^~~~~~~~~~~
stream.c: ./Intrinsics_AVX512_128block.h:20:18: note: expanded from macro 'ROL'
stream.c: #define ROL(X,r) (_mm512_rol_epi64(X,r))
stream.c: ^~~~~~~~~~~~~~~~~~~~~~~
stream.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/avx512fintrin.h:406:26: note: passing argument to parameter '__a' here
stream.c: _mm512_xor_si512(__m512i __a, __m512i __b)
stream.c: ^
stream.c: fatal error: too many errors emitted, stopping now [-ferror-limit=]
stream.c: 3 warnings and 20 errors generated.

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx512
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx512
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx512
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx512
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx512

Compiler output

Implementation: avx512
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

stream.c: In file included from Speck128128AVX512.h:17:0,
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: #define SET1(X,c) (X=SET(c,c,c,c,c,c,c,c))
stream.c: ~~^~~~~~~~~~~~~~~~~~~~~~
stream.c: stream.c:135:5: note: in expansion of macro ‘SET1’
stream.c: 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/6/include/immintrin.h:45:0,
stream.c: ...
stream.c: from stream.c:21:
stream.c: Intrinsics_AVX512_128block.h:32:18: note: called from here
stream.c: #define ST(ip,X) _mm512_storeu_si512((void *)(ip),X)
stream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: Intrinsics_AVX512_128block.h:33:25: note: in expansion of macro ‘ST’
stream.c: #define STORE(out,X,Y) (ST(out,LOW(Y,X)), ST(out+64,HIGH(Y,X)))
stream.c: ^~
stream.c: stream.c:169:22: note: in expansion of macro ‘STORE’
stream.c: if (numbytes>=512) STORE(out+384,X[3],Y[3]);
stream.c: ^~~~~

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx512
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx512
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx512
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx512

Compiler output

Implementation: sse4
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

stream.c: stream.c:99:12: error: static declaration of 'Encrypt' follows non-static declaration
stream.c: static int Encrypt(unsigned char *out, u64 nonce[], u128 rk[], u64 key[], int numbytes)
stream.c: ^
stream.c: stream.c:23:5: note: previous declaration is here
stream.c: int Encrypt(unsigned char *out, u64 nonce[], u128 rk[], u64 key[], int numbytes);
stream.c: ^
stream.c: stream.c:212:12: error: static declaration of 'Encrypt_Xor' follows non-static declaration
stream.c: static int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[], u64 key[], int numbytes)
stream.c: ^
stream.c: stream.c:25:5: note: previous declaration is here
stream.c: int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[], u64 key[], int numbytes);
stream.c: ^
stream.c: stream.c:253:12: error: static declaration of 'ExpandKey' follows non-static declaration
stream.c: static int ExpandKey(u64 K[], u128 rk[], u64 key[])
stream.c: ^
stream.c: stream.c:26:5: note: previous declaration is here
stream.c: int ExpandKey(u64 K[], u128 rk[], u64 key[]);
stream.c: ^
stream.c: 3 errors generated.

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse4
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse4
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse4
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse4
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse4

Compiler output

Implementation: sse4
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

stream.c: stream.c:99:12: error: static declaration of ‘Encrypt’ follows non-static declaration
stream.c: static int Encrypt(unsigned char *out, u64 nonce[], u128 rk[], u64 key[], int numbytes)
stream.c: ^~~~~~~
stream.c: stream.c:23:5: note: previous declaration of ‘Encrypt’ was here
stream.c: int Encrypt(unsigned char *out, u64 nonce[], u128 rk[], u64 key[], int numbytes);
stream.c: ^~~~~~~
stream.c: stream.c:212:12: error: static declaration of ‘Encrypt_Xor’ follows non-static declaration
stream.c: static int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[], u64 key[], int numbytes)
stream.c: ^~~~~~~~~~~
stream.c: stream.c:25:5: note: previous declaration of ‘Encrypt_Xor’ was here
stream.c: int Encrypt_Xor(unsigned char *out, const unsigned char *in, u64 nonce[], u128 rk[], u64 key[], int numbytes);
stream.c: ^~~~~~~~~~~
stream.c: stream.c:253:12: error: static declaration of ‘ExpandKey’ follows non-static declaration
stream.c: static int ExpandKey(u64 K[], u128 rk[], u64 key[])
stream.c: ^~~~~~~~~
stream.c: stream.c:26:5: note: previous declaration of ‘ExpandKey’ was here
stream.c: int ExpandKey(u64 K[], u128 rk[], u64 key[]);
stream.c: ^~~~~~~~~

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	sse4
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	sse4
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	sse4
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	sse4