Implementation notes: x86, thoth, crypto_aead/kiasueq128v1

Computer: thoth
Architecture: x86
CPU ID: AuthenticAMD-00000622-0183f9ff
SUPERCOP version: 20160806
Operation: crypto_aead
Primitive: kiasueq128v1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
486351	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160727	20160724
557005	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160727	20160724
603567	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160727	20160724
640570	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160727	20160724
696758	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160727	20160724

Compiler output

Implementation: crypto_aead/kiasueq128v1/opt
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

kiasu.c: kiasu.c:117:34: error: always_inline function '_mm_set_epi8' requires target feature 'sse2', but would be inlined into function 'XLS' that is compiled without support for 'sse2'
kiasu.c: const __m128i STAGE_MASK = constant8( 0x0f ,0xff,0xff,0xff, 0xff,0xff,0xff,0xff, 0xff,0xff,0xff,0xff, 0xff,0xff,0xff,0xff );
kiasu.c: ^
kiasu.c: ./aes_ni.macros:13:76: note: expanded from macro 'constant8'
kiasu.c: #define constant8(b15,b14,b13,b12,b11,b10,b9,b8,b7,b6,b5,b4,b3,b2,b1,b0) _mm_set_epi8 ((b0),(b1),(b2),(b3),(b4),(b5),(b6),(b7),(b8),(b9),(b10),(b11),(b12),(b13),(b14),(b15))
kiasu.c: ^
kiasu.c: kiasu.c:118:34: error: always_inline function '_mm_set_epi8' requires target feature 'sse2', but would be inlined into function 'XLS' that is compiled without support for 'sse2'
kiasu.c: const __m128i BLOCK_MASK = constant8( 0xff ,0xff,0xff,0xff, 0xff,0xff,0xff,0xff, 0xf0,0x00,0xff,0xff, 0x00,0x00,0xff,0xf );
kiasu.c: ^
kiasu.c: ./aes_ni.macros:13:76: note: expanded from macro 'constant8'
kiasu.c: #define constant8(b15,b14,b13,b12,b11,b10,b9,b8,b7,b6,b5,b4,b3,b2,b1,b0) _mm_set_epi8 ((b0),(b1),(b2),(b3),(b4),(b5),(b6),(b7),(b8),(b9),(b10),(b11),(b12),(b13),(b14),(b15))
kiasu.c: ^
kiasu.c: kiasu.c:119:30: error: always_inline function '_mm_set_epi8' requires target feature 'sse2', but would be inlined into function 'XLS' that is compiled without support for 'sse2'
kiasu.c: const __m128i MSB_XLS1 = constant8( (0x8 kiasu.c: ^
kiasu.c: ./aes_ni.macros:13:76: note: expanded from macro 'constant8'
kiasu.c: #define constant8(b15,b14,b13,b12,b11,b10,b9,b8,b7,b6,b5,b4,b3,b2,b1,b0) _mm_set_epi8 ((b0),(b1),(b2),(b3),(b4),(b5),(b6),(b7),(b8),(b9),(b10),(b11),(b12),(b13),(b14),(b15))
kiasu.c: ^
kiasu.c: kiasu.c:120:30: error: always_inline function '_mm_set_epi8' requires target feature 'sse2', but would be inlined into function 'XLS' that is compiled without support for 'sse2'
kiasu.c: const __m128i MSB_XLS2 = constant8( (0x9 kiasu.c: ^
kiasu.c: ./aes_ni.macros:13:76: note: expanded from macro 'constant8'
kiasu.c: #define constant8(b15,b14,b13,b12,b11,b10,b9,b8,b7,b6,b5,b4,b3,b2,b1,b0) _mm_set_epi8 ((b0),(b1),(b2),(b3),(b4),(b5),(b6),(b7),(b8),(b9),(b10),(b11),(b12),(b13),(b14),(b15))
kiasu.c: ^
kiasu.c: kiasu.c:131:3: error: always_inline function '_mm_xor_si128' requires target feature 'sse2', but would be inlined into function 'XLS' that is compiled without support for 'sse2'
kiasu.c: ...

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

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

Compiler output

Implementation: crypto_aead/kiasueq128v1/bitslice
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

kiasu.c: kiasu.c:259:17: error: unknown type name 'block'
kiasu.c: void printBlock(block B) {
kiasu.c: ^
kiasu.c: kiasu.c:262:14: error: expected expression
kiasu.c: *(block *)tag=B;
kiasu.c: ^
kiasu.c: kiasu.c:262:7: error: use of undeclared identifier 'block'; did you mean 'lockf'?
kiasu.c: *(block *)tag=B;
kiasu.c: ^~~~~
kiasu.c: lockf
kiasu.c: /usr/include/unistd.h:1084:12: note: 'lockf' declared here
kiasu.c: extern int lockf (int __fd, int __cmd, __off_t __len) __wur;
kiasu.c: ^
kiasu.c: kiasu.c:324:15: error: unknown type name 'block'
kiasu.c: ALIGN(16) block ta[BPI]; /* 8 blocks for parallel processing */
kiasu.c: ^
kiasu.c: kiasu.c:326:21: error: unknown type name 'block'
kiasu.c: ALIGN(16) const block* adp; /* Pointer to the blocks to process */
kiasu.c: ^
kiasu.c: kiasu.c:338:17: error: expected expression
kiasu.c: adp=(block *)M1;
kiasu.c: ^
kiasu.c: kiasu.c:338:10: error: use of undeclared identifier 'block'; did you mean 'lockf'?
kiasu.c: adp=(block *)M1;
kiasu.c: ^~~~~
kiasu.c: ...

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

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

Compiler output

Implementation: crypto_aead/kiasueq128v1/opt
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

kiasu.c: kiasu.c: In function 'assist128':
kiasu.c: kiasu.c:35:1: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
kiasu.c: {
kiasu.c: ^
kiasu.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/xmmintrin.h:1249:0,
kiasu.c: from kiasu.c:26:
kiasu.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
kiasu.c: _mm_xor_si128 (__m128i __A, __m128i __B)
kiasu.c: ^
kiasu.c: kiasu.c:40:12: error: called from here
kiasu.c: return _mm_xor_si128 (a, _mm_shuffle_epi32 (b ,0xff));
kiasu.c: ^
kiasu.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/xmmintrin.h:1249:0,
kiasu.c: from kiasu.c:26:
kiasu.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
kiasu.c: _mm_shuffle_epi32 (__m128i __A, const int __mask)
kiasu.c: ^
kiasu.c: kiasu.c:40:12: error: called from here
kiasu.c: return _mm_xor_si128 (a, _mm_shuffle_epi32 (b ,0xff));
kiasu.c: ^
kiasu.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/xmmintrin.h:1249:0,
kiasu.c: from kiasu.c:26:
kiasu.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
kiasu.c: _mm_xor_si128 (__m128i __A, __m128i __B)
kiasu.c: ^
kiasu.c: ...

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

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

Compiler output

Implementation: crypto_aead/kiasueq128v1/bitslice
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

kiasu.c: kiasu.c:259:17: error: unknown type name 'block'
kiasu.c: void printBlock(block B) {
kiasu.c: ^
kiasu.c: kiasu.c: In function 'XLS':
kiasu.c: kiasu.c:324:15: error: unknown type name 'block'
kiasu.c: ALIGN(16) block ta[BPI]; /* 8 blocks for parallel processing */
kiasu.c: ^
kiasu.c: kiasu.c:326:21: error: unknown type name 'block'
kiasu.c: ALIGN(16) const block* adp; /* Pointer to the blocks to process */
kiasu.c: ^
kiasu.c: kiasu.c:338:10: error: 'block' undeclared (first use in this function)
kiasu.c: adp=(block *)M1;
kiasu.c: ^
kiasu.c: kiasu.c:338:10: note: each undeclared identifier is reported only once for each function it appears in
kiasu.c: kiasu.c:338:17: error: expected expression before ')' token
kiasu.c: adp=(block *)M1;
kiasu.c: ^
kiasu.c: kiasu.c:368:17: error: expected expression before ')' token
kiasu.c: adp=(block *)Xp1;
kiasu.c: ^
kiasu.c: kiasu.c:399:17: error: expected expression before ')' token
kiasu.c: adp=(block *)Yp1;
kiasu.c: ^
kiasu.c: kiasu.c: In function 'kiasu_aead_encrypt':
kiasu.c: kiasu.c:443:15: error: unknown type name 'block'
kiasu.c: ...

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

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