Implementation notes: x86, thoth, crypto_aead/morus1280256v1

Computer: thoth
Architecture: x86
CPU ID: AuthenticAMD-00000622-0183f9ff
SUPERCOP version: 20160806
Operation: crypto_aead
Primitive: morus1280256v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
76674	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160727	20160724
85931	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160727	20160724
86454	`ref64`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160727	20160724
88345	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160727	20160724
98177	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160727	20160724
101051	`ref64`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160727	20160724
101830	`ref64`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160727	20160724
103690	`ref64`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160727	20160724
105814	`ref64`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160727	20160724

Compiler output

Implementation: crypto_aead/morus1280256v1/avx2
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

morus1280256v1avx2.c: morus1280256v1avx2.c:67:13: error: always_inline function '_mm256_xor_si256' requires target feature 'sse3', but would be inlined into function 'morus_stateupdate' that is compiled without support for 'sse3'
morus1280256v1avx2.c: state[0] = XOR256(state[0], state[3]);
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: morus1280256v1avx2.c:22:27: note: expanded from macro 'XOR256'
morus1280256v1avx2.c: #define XOR256(x,y) _mm256_xor_si256((x),(y)) /*XOR256(x,y) = x ^ y, where x and y are two 256-bit word*/
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: morus1280256v1avx2.c:68:13: error: always_inline function '_mm256_xor_si256' requires target feature 'sse3', but would be inlined into function 'morus_stateupdate' that is compiled without support for 'sse3'
morus1280256v1avx2.c: state[0] = XOR256(state[0], AND256(state[1], state[2]));
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: morus1280256v1avx2.c:22:27: note: expanded from macro 'XOR256'
morus1280256v1avx2.c: #define XOR256(x,y) _mm256_xor_si256((x),(y)) /*XOR256(x,y) = x ^ y, where x and y are two 256-bit word*/
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: morus1280256v1avx2.c:68:30: error: always_inline function '_mm256_and_si256' requires target feature 'sse3', but would be inlined into function 'morus_stateupdate' that is compiled without support for 'sse3'
morus1280256v1avx2.c: state[0] = XOR256(state[0], AND256(state[1], state[2]));
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: morus1280256v1avx2.c:23:27: note: expanded from macro 'AND256'
morus1280256v1avx2.c: #define AND256(x,y) _mm256_and_si256((x),(y)) /*AND(x,y) = x & y, where x and y are two 256-bit word*/
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: morus1280256v1avx2.c:69:13: error: always_inline function '_mm256_or_si256' requires target feature 'sse3', but would be inlined into function 'morus_stateupdate' that is compiled without support for 'sse3'
morus1280256v1avx2.c: state[0] = ROTL256(state[0], n1);
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: morus1280256v1avx2.c:36:27: note: expanded from macro 'ROTL256'
morus1280256v1avx2.c: #define ROTL256(x,n) OR256( _mm256_slli_epi64((x), (n)), _mm256_srli_epi64((x),(64-n)) ) /*Rotate 4 64-bit unsigned integers in x to the left by n-bit positions*/
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: morus1280256v1avx2.c:25:27: note: expanded from macro 'OR256'
morus1280256v1avx2.c: ...

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

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx2

Compiler output

Implementation: crypto_aead/morus1280256v1/sse2
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

morus1280256v1sse2.c: morus1280256v1sse2.c:41:16: error: always_inline function '_mm_xor_si128' requires target feature 'sse2', but would be inlined into function 'morus_stateupdate' that is compiled without support for 'sse2'
morus1280256v1sse2.c: state[0][0] = XOR(state[0][0], state[3][0]); state[0][1] = XOR(state[0][1], state[3][1]);
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: morus1280256v1sse2.c:18:24: note: expanded from macro 'XOR'
morus1280256v1sse2.c: #define XOR(x,y) _mm_xor_si128((x),(y)) /*XOR(x,y) = x ^ y, where x and y are two 128-bit word*/
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: morus1280256v1sse2.c:41:62: error: always_inline function '_mm_xor_si128' requires target feature 'sse2', but would be inlined into function 'morus_stateupdate' that is compiled without support for 'sse2'
morus1280256v1sse2.c: state[0][0] = XOR(state[0][0], state[3][0]); state[0][1] = XOR(state[0][1], state[3][1]);
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: morus1280256v1sse2.c:18:24: note: expanded from macro 'XOR'
morus1280256v1sse2.c: #define XOR(x,y) _mm_xor_si128((x),(y)) /*XOR(x,y) = x ^ y, where x and y are two 128-bit word*/
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: morus1280256v1sse2.c:42:16: error: always_inline function '_mm_xor_si128' requires target feature 'sse2', but would be inlined into function 'morus_stateupdate' that is compiled without support for 'sse2'
morus1280256v1sse2.c: state[0][0] = XOR(state[0][0], AND(state[1][0], state[2][0])); state[0][1] = XOR(state[0][1], AND(state[1][1], state[2][1]));
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: morus1280256v1sse2.c:18:24: note: expanded from macro 'XOR'
morus1280256v1sse2.c: #define XOR(x,y) _mm_xor_si128((x),(y)) /*XOR(x,y) = x ^ y, where x and y are two 128-bit word*/
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: morus1280256v1sse2.c:42:33: error: always_inline function '_mm_and_si128' requires target feature 'sse2', but would be inlined into function 'morus_stateupdate' that is compiled without support for 'sse2'
morus1280256v1sse2.c: state[0][0] = XOR(state[0][0], AND(state[1][0], state[2][0])); state[0][1] = XOR(state[0][1], AND(state[1][1], state[2][1]));
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: morus1280256v1sse2.c:19:24: note: expanded from macro 'AND'
morus1280256v1sse2.c: #define AND(x,y) _mm_and_si128((x),(y)) /*AND(x,y) = x & y, where x and y are two 128-bit word*/
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: morus1280256v1sse2.c:42:81: error: always_inline function '_mm_xor_si128' requires target feature 'sse2', but would be inlined into function 'morus_stateupdate' that is compiled without support for 'sse2'
morus1280256v1sse2.c: ...

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

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	sse2

Compiler output

Implementation: crypto_aead/morus1280256v1/ref
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

try.c: crypto_aead_morus1280256v1.a(encrypt.o): In function `morus_initialization':
try.c: encrypt.c:(.text+0x...): undefined reference to `morus_stateupdate'
try.c: encrypt.c:(.text+0x...): undefined reference to `morus_stateupdate'
try.c: encrypt.c:(.text+0x...): undefined reference to `morus_stateupdate'
try.c: encrypt.c:(.text+0x...): undefined reference to `morus_stateupdate'
try.c: encrypt.c:(.text+0x...): undefined reference to `morus_stateupdate'
try.c: crypto_aead_morus1280256v1.a(encrypt.o):encrypt.c:(.text+0x...): more undefined references to `morus_stateupdate' follow
try.c: clang: error: linker command failed with exit code 1 (use -v to see invocation)

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

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ref

Compiler output

Implementation: crypto_aead/morus1280256v1/avx2
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

morus1280256v1avx2.c: morus1280256v1avx2.c: In function 'morus_stateupdate':
morus1280256v1avx2.c: morus1280256v1avx2.c:67:11: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
morus1280256v1avx2.c: state[0] = XOR256(state[0], state[3]);
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/immintrin.h:43:0,
morus1280256v1avx2.c: from morus1280256v1avx2.c:2:
morus1280256v1avx2.c: morus1280256v1avx2.c: In function 'morus_enc_aut_step':
morus1280256v1avx2.c: /usr/lib/gcc/i686-linux-gnu/5/include/avx2intrin.h:1068:1: error: inlining failed in call to always_inline '_mm256_permute4x64_epi64': target specific option mismatch
morus1280256v1avx2.c: _mm256_permute4x64_epi64 (__m256i __X, const int __M)
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: morus1280256v1avx2.c:38:27: error: called from here
morus1280256v1avx2.c: #define ROTL256_64(x) _mm256_permute4x64_epi64((x), _MM_SHUFFLE(2,1,0,3)) /*Rotate x by 64-bit positions to the left*/
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: morus1280256v1avx2.c:216:13: note: in expansion of macro 'ROTL256_64'
morus1280256v1avx2.c: state[2] = ROTL256_64(state[2]);
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/immintrin.h:43:0,
morus1280256v1avx2.c: from morus1280256v1avx2.c:2:
morus1280256v1avx2.c: /usr/lib/gcc/i686-linux-gnu/5/include/avx2intrin.h:574:1: error: inlining failed in call to always_inline '_mm256_or_si256': target specific option mismatch
morus1280256v1avx2.c: _mm256_or_si256 (__m256i __A, __m256i __B)
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: morus1280256v1avx2.c:25:27: error: called from here
morus1280256v1avx2.c: #define OR256(x,y) _mm256_or_si256((x),(y)) /*OR(x,y) = x | y, where x and y are two 256-bit word*/
morus1280256v1avx2.c: ^
morus1280256v1avx2.c: morus1280256v1avx2.c:36:27: note: in expansion of macro 'OR256'
morus1280256v1avx2.c: ...

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

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

Compiler output

Implementation: crypto_aead/morus1280256v1/sse2
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

morus1280256v1sse2.c: morus1280256v1sse2.c: In function 'morus_stateupdate':
morus1280256v1sse2.c: morus1280256v1sse2.c:41:14: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
morus1280256v1sse2.c: state[0][0] = XOR(state[0][0], state[3][0]); state[0][1] = XOR(state[0][1], state[3][1]);
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/xmmintrin.h:1249:0,
morus1280256v1sse2.c: from /usr/lib/gcc/i686-linux-gnu/5/include/immintrin.h:29,
morus1280256v1sse2.c: from morus1280256v1sse2.c:2:
morus1280256v1sse2.c: morus1280256v1sse2.c: In function 'morus_enc_aut_step':
morus1280256v1sse2.c: /usr/lib/gcc/i686-linux-gnu/5/include/emmintrin.h:708:1: error: inlining failed in call to always_inline '_mm_store_si128': target specific option mismatch
morus1280256v1sse2.c: _mm_store_si128 (__m128i *__P, __m128i __B)
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: morus1280256v1sse2.c:183:2: error: called from here
morus1280256v1sse2.c: _mm_store_si128( (__m128i*)(ciphertextblock+16), XOR(keystream[1], msgblk[1]) );
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/xmmintrin.h:1249:0,
morus1280256v1sse2.c: from /usr/lib/gcc/i686-linux-gnu/5/include/immintrin.h:29,
morus1280256v1sse2.c: from morus1280256v1sse2.c:2:
morus1280256v1sse2.c: /usr/lib/gcc/i686-linux-gnu/5/include/emmintrin.h:1286:1: error: inlining failed in call to always_inline '_mm_xor_si128': target specific option mismatch
morus1280256v1sse2.c: _mm_xor_si128 (__m128i __A, __m128i __B)
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: morus1280256v1sse2.c:183:2: error: called from here
morus1280256v1sse2.c: _mm_store_si128( (__m128i*)(ciphertextblock+16), XOR(keystream[1], msgblk[1]) );
morus1280256v1sse2.c: ^
morus1280256v1sse2.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/xmmintrin.h:1249:0,
morus1280256v1sse2.c: from /usr/lib/gcc/i686-linux-gnu/5/include/immintrin.h:29,
morus1280256v1sse2.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	sse2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	sse2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	sse2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	sse2