Implementation notes: x86, thoth, crypto_aead/morus640128v1

Computer: thoth
Architecture: x86
CPU ID: AuthenticAMD-00000622-0183f9ff
SUPERCOP version: 20160806
Operation: crypto_aead
Primitive: morus640128v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
39857	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160727	20160724
40270	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160727	20160724
43312	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160727	20160724
49496	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160727	20160724

Compiler output

Implementation: crypto_aead/morus640128v1/sse2
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

morus640128v1sse2.c: morus640128v1sse2.c:39:20: 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'
morus640128v1sse2.c: state[0] = XOR(state[0], state[3]);
morus640128v1sse2.c: ^
morus640128v1sse2.c: morus640128v1sse2.c:18:24: note: expanded from macro 'XOR'
morus640128v1sse2.c: #define XOR(x,y) _mm_xor_si128((x),(y)) /*XOR(x,y) = x ^ y, where x and y are two 128-bit word*/
morus640128v1sse2.c: ^
morus640128v1sse2.c: morus640128v1sse2.c:40:20: 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'
morus640128v1sse2.c: state[0] = XOR(state[0], AND(state[1], state[2]));
morus640128v1sse2.c: ^
morus640128v1sse2.c: morus640128v1sse2.c:18:24: note: expanded from macro 'XOR'
morus640128v1sse2.c: #define XOR(x,y) _mm_xor_si128((x),(y)) /*XOR(x,y) = x ^ y, where x and y are two 128-bit word*/
morus640128v1sse2.c: ^
morus640128v1sse2.c: morus640128v1sse2.c:40:34: 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'
morus640128v1sse2.c: state[0] = XOR(state[0], AND(state[1], state[2]));
morus640128v1sse2.c: ^
morus640128v1sse2.c: morus640128v1sse2.c:19:24: note: expanded from macro 'AND'
morus640128v1sse2.c: #define AND(x,y) _mm_and_si128((x),(y)) /*AND(x,y) = x & y, where x and y are two 128-bit word*/
morus640128v1sse2.c: ^
morus640128v1sse2.c: morus640128v1sse2.c:41:20: 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'
morus640128v1sse2.c: state[0] = ROTL(state[0], n1);
morus640128v1sse2.c: ^
morus640128v1sse2.c: morus640128v1sse2.c:25:24: note: expanded from macro 'ROTL'
morus640128v1sse2.c: #define ROTL(x,n) XOR(_mm_slli_epi32((x), (n)), _mm_srli_epi32((x),(32-n))) /*Rotate 4 32-bit unsigned integers in x to the left by n-bit positions*/
morus640128v1sse2.c: ^
morus640128v1sse2.c: morus640128v1sse2.c:18:24: note: expanded from macro 'XOR'
morus640128v1sse2.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/morus640128v1/ref
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

try.c: crypto_aead_morus640128v1.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_morus640128v1.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/morus640128v1/sse2
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

morus640128v1sse2.c: morus640128v1sse2.c: In function 'morus_stateupdate':
morus640128v1sse2.c: morus640128v1sse2.c:39:18: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
morus640128v1sse2.c: state[0] = XOR(state[0], state[3]);
morus640128v1sse2.c: ^
morus640128v1sse2.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/xmmintrin.h:1249:0,
morus640128v1sse2.c: from /usr/lib/gcc/i686-linux-gnu/5/include/immintrin.h:29,
morus640128v1sse2.c: from morus640128v1sse2.c:2:
morus640128v1sse2.c: /usr/lib/gcc/i686-linux-gnu/5/include/emmintrin.h:1415:1: error: inlining failed in call to always_inline '_mm_shuffle_epi32': target specific option mismatch
morus640128v1sse2.c: _mm_shuffle_epi32 (__m128i __A, const int __mask)
morus640128v1sse2.c: ^
morus640128v1sse2.c: morus640128v1sse2.c:28:24: error: called from here
morus640128v1sse2.c: #define ROTL32(x) _mm_shuffle_epi32((x),_MM_SHUFFLE(2,1,0,3)) /*Rotate x by 32-bit positions to the left*/
morus640128v1sse2.c: ^
morus640128v1sse2.c: morus640128v1sse2.c:66:20: note: in expansion of macro 'ROTL32'
morus640128v1sse2.c: state[2] = ROTL32(state[2]);
morus640128v1sse2.c: ^
morus640128v1sse2.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/xmmintrin.h:1249:0,
morus640128v1sse2.c: from /usr/lib/gcc/i686-linux-gnu/5/include/immintrin.h:29,
morus640128v1sse2.c: from morus640128v1sse2.c:2:
morus640128v1sse2.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
morus640128v1sse2.c: _mm_xor_si128 (__m128i __A, __m128i __B)
morus640128v1sse2.c: ^
morus640128v1sse2.c: morus640128v1sse2.c:18:24: error: called from here
morus640128v1sse2.c: #define XOR(x,y) _mm_xor_si128((x),(y)) /*XOR(x,y) = x ^ y, where x and y are two 128-bit word*/
morus640128v1sse2.c: ^
morus640128v1sse2.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