Implementation notes: amd64, par, crypto_hash/blake512

Computer: par
Architecture: amd64
CPU ID: GenuineIntel-000406c3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_hash
Primitive: blake512

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
22400	`bswap`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
22500	`bswap`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
22520	`bswap`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
22540	`regs`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
22640	`regs`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
22680	`regs`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
22680	`bswap`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
22800	`regs`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
22960	`bswap`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
23000	`bswap`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
23020	`regs`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
23060	`sphlib`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
23100	`sphlib`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
23160	`regs`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
23740	`sphlib`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
23740	`sphlib`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
24120	`sphlib`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
24300	`sphlib`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
28880	`sphlib-small`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
28960	`sphlib-small`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
33940	`ref`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
34040	`ref`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
43860	`sphlib-small`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
43860	`sse2`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
44000	`sphlib-small`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
44620	`sse2`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
45040	`sse2`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
45180	`sse2`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
45320	`sphlib-small`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
45600	`sse2`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
45640	`sphlib-small`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
45740	`sse2`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
46340	`ref`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
46360	`sse2s`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
46440	`ref`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
47200	`sse2s`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
47240	`ref`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
47800	`sse2s`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
47880	`sse2s`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
47920	`sse2s`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
48020	`sse2s`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
48860	`ref`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
49140	`sse41`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
49280	`sse41`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
49380	`sse41`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
49380	`vect128`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
49460	`vect128`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
49580	`vect128`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
49960	`sse41`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
50020	`sse41`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
50140	`sse41`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
50640	`vect128-inplace`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
50760	`vect128-inplace`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
50840	`vect128`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
50860	`vect128-inplace`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
50880	`vect128`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
50900	`vect128-inplace`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
51120	`vect128-inplace`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
51140	`vect128`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
51660	`ssse3`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
51740	`vect128-inplace`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
51940	`ssse3`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
52060	`ssse3`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
52640	`ssse3`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
52700	`ssse3`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
52900	`ssse3`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
89520	`sandy`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
89940	`sandy`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
91700	`sandy`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
91740	`sandy`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
91860	`sandy`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
91880	`sandy`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026

Test failure

Implementation: crypto_hash/blake512/avxicc
Compiler: gcc -funroll-loops -march=native -mcpu=native -O2

error 111

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
gcc -funroll-loops -march=native -mcpu=native -O2	avxicc
gcc -funroll-loops -march=native -mcpu=native -O3	avxicc
gcc -funroll-loops -march=native -mcpu=native -Os	avxicc
gcc -march=native -mcpu=native -O2	avxicc
gcc -march=native -mcpu=native -O3	avxicc
gcc -march=native -mcpu=native -Os	avxicc

Compiler output

Implementation: crypto_hash/blake512/sphlib
Compiler: gcc -funroll-loops -march=native -mcpu=native -O2

blake.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
hash.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
try.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
try.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
measure.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead

Number of similar (compiler,implementation) pairs: 12, namely:

Compiler	Implementations
gcc -funroll-loops -march=native -mcpu=native -O2	sphlib sphlib-small
gcc -funroll-loops -march=native -mcpu=native -O3	sphlib sphlib-small
gcc -funroll-loops -march=native -mcpu=native -Os	sphlib sphlib-small
gcc -march=native -mcpu=native -O2	sphlib sphlib-small
gcc -march=native -mcpu=native -O3	sphlib sphlib-small
gcc -march=native -mcpu=native -Os	sphlib sphlib-small

Compiler output

Implementation: crypto_hash/blake512/xop-2
Compiler: gcc -funroll-loops -march=native -mcpu=native -O2

hash.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
hash.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:54:0,
hash.c: from hash.c:5:
hash.c: hash.c: In function 'blake512_compress':
hash.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/xopintrin.h:212:1: error: inlining failed in call to always_inline '_mm_perm_epi8': target specific option mismatch
hash.c: _mm_perm_epi8(__m128i __A, __m128i __B, __m128i __C)
hash.c: ^~~~~~~~~~~~~
hash.c: In file included from hash.c:8:0:
hash.c: rounds.h:15:21: note: called from here
hash.c: #define BSWAP64(x) _mm_perm_epi8((x),(x),u8to64)
hash.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c:99:15: note: in expansion of macro 'BSWAP64'
hash.c: m.u128[7] = BSWAP64(m.u128[7]);
hash.c: ^~~~~~~
hash.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:54:0,
hash.c: from hash.c:5:
hash.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/xopintrin.h:212:1: error: inlining failed in call to always_inline '_mm_perm_epi8': target specific option mismatch
hash.c: _mm_perm_epi8(__m128i __A, __m128i __B, __m128i __C)
hash.c: ^~~~~~~~~~~~~
hash.c: In file included from hash.c:8:0:
hash.c: rounds.h:15:21: note: called from here
hash.c: #define BSWAP64(x) _mm_perm_epi8((x),(x),u8to64)
hash.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c:98:15: note: in expansion of macro 'BSWAP64'
hash.c: m.u128[6] = BSWAP64(m.u128[6]);
hash.c: ...

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
gcc -funroll-loops -march=native -mcpu=native -O2	xop-2
gcc -funroll-loops -march=native -mcpu=native -O3	xop-2
gcc -funroll-loops -march=native -mcpu=native -Os	xop-2
gcc -march=native -mcpu=native -O2	xop-2
gcc -march=native -mcpu=native -O3	xop-2
gcc -march=native -mcpu=native -Os	xop-2

Compiler output

Implementation: crypto_hash/blake512/xop
Compiler: gcc -funroll-loops -march=native -mcpu=native -O2

hash.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
hash.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:54:0,
hash.c: from hash.c:5:
hash.c: hash.c: In function 'blake512_compress':
hash.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/xopintrin.h:266:1: error: inlining failed in call to always_inline '_mm_roti_epi64': target specific option mismatch
hash.c: _mm_roti_epi64(__m128i __A, const int __B)
hash.c: ^~~~~~~~~~~~~~
hash.c: In file included from hash.c:8:0:
hash.c: rounds.h:825:9: note: called from here
hash.c: row2h = _mm_roti_epi64(row2h, -11); \
hash.c: ^
hash.c: rounds.h:867:3: note: in expansion of macro 'G2'
hash.c: G2(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h,b0,b1); \
hash.c: ^~
hash.c: hash.c:132:3: note: in expansion of macro 'ROUND'
hash.c: ROUND(15);
hash.c: ^~~~~
hash.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:54:0,
hash.c: from hash.c:5:
hash.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/xopintrin.h:266:1: error: inlining failed in call to always_inline '_mm_roti_epi64': target specific option mismatch
hash.c: _mm_roti_epi64(__m128i __A, const int __B)
hash.c: ^~~~~~~~~~~~~~
hash.c: In file included from hash.c:8:0:
hash.c: rounds.h:824:9: note: called from here
hash.c: row2l = _mm_roti_epi64(row2l, -11); \
hash.c: ...

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
gcc -funroll-loops -march=native -mcpu=native -O2	xop
gcc -funroll-loops -march=native -mcpu=native -O3	xop
gcc -funroll-loops -march=native -mcpu=native -Os	xop
gcc -march=native -mcpu=native -O2	xop
gcc -march=native -mcpu=native -O3	xop
gcc -march=native -mcpu=native -Os	xop

Compiler output

Implementation: crypto_hash/blake512/vect128
Compiler: gcc -funroll-loops -march=native -mcpu=native -O2

Number of similar (compiler,implementation) pairs: 12, namely:

Compiler	Implementations
gcc -funroll-loops -march=native -mcpu=native -O2	vect128 vect128-inplace
gcc -funroll-loops -march=native -mcpu=native -O3	vect128 vect128-inplace
gcc -funroll-loops -march=native -mcpu=native -Os	vect128 vect128-inplace
gcc -march=native -mcpu=native -O2	vect128 vect128-inplace
gcc -march=native -mcpu=native -O3	vect128 vect128-inplace
gcc -march=native -mcpu=native -Os	vect128 vect128-inplace

Compiler output

Implementation: crypto_hash/blake512/vect128-xop
Compiler: gcc -funroll-loops -march=native -mcpu=native -O2

hash.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
nist.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
vector.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
vector.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:54:0,
vector.c: from vector.h:29,
vector.c: from vector.c:7:
vector.c: vector.c: In function 'round512':
vector.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/xopintrin.h:266:1: error: inlining failed in call to always_inline '_mm_roti_epi64': target specific option mismatch
vector.c: _mm_roti_epi64(__m128i __A, const int __B)
vector.c: ^~~~~~~~~~~~~~
vector.c: vector.c:745:8: note: called from here
vector.c: B1 = v64_rotate(B1, 64-11); \
vector.c:
vector.c: vector.c:756:36: note: in expansion of macro 'ROUND'
vector.c: ROUND(12); ROUND(13); ROUND(14); ROUND(15);
vector.c: ^~~~~
vector.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/x86intrin.h:54:0,
vector.c: from vector.h:29,
vector.c: from vector.c:7:
vector.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/xopintrin.h:266:1: error: inlining failed in call to always_inline '_mm_roti_epi64': target specific option mismatch
vector.c: _mm_roti_epi64(__m128i __A, const int __B)
vector.c: ^~~~~~~~~~~~~~
vector.c: vector.c:744:8: note: called from here
vector.c: B0 = v64_rotate(B0, 64-11); \
vector.c:
vector.c: vector.c:756:36: note: in expansion of macro 'ROUND'
vector.c: ROUND(12); ROUND(13); ROUND(14); ROUND(15);
vector.c: ...

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
gcc -funroll-loops -march=native -mcpu=native -O2	vect128-xop
gcc -funroll-loops -march=native -mcpu=native -O3	vect128-xop
gcc -funroll-loops -march=native -mcpu=native -Os	vect128-xop
gcc -march=native -mcpu=native -O2	vect128-xop
gcc -march=native -mcpu=native -O3	vect128-xop
gcc -march=native -mcpu=native -Os	vect128-xop

Compiler output

Implementation: crypto_hash/blake512/bswap
Compiler: gcc -funroll-loops -march=native -mcpu=native -O2

hash.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
try.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
try.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
measure.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead

Number of similar (compiler,implementation) pairs: 48, namely:

Compiler	Implementations
gcc -funroll-loops -march=native -mcpu=native -O2	bswap ref regs sandy sse2 sse2s sse41 ssse3
gcc -funroll-loops -march=native -mcpu=native -O3	bswap ref regs sandy sse2 sse2s sse41 ssse3
gcc -funroll-loops -march=native -mcpu=native -Os	bswap ref regs sandy sse2 sse2s sse41 ssse3
gcc -march=native -mcpu=native -O2	bswap ref regs sandy sse2 sse2s sse41 ssse3
gcc -march=native -mcpu=native -O3	bswap ref regs sandy sse2 sse2s sse41 ssse3
gcc -march=native -mcpu=native -Os	bswap ref regs sandy sse2 sse2s sse41 ssse3

Compiler output

Implementation: crypto_hash/blake512/avxicc
Compiler: gcc -funroll-loops -march=native -mcpu=native -O2

hash.s: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
try.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
gcc -funroll-loops -march=native -mcpu=native -O2	avxicc
gcc -funroll-loops -march=native -mcpu=native -O3	avxicc
gcc -funroll-loops -march=native -mcpu=native -Os	avxicc
gcc -march=native -mcpu=native -O2	avxicc
gcc -march=native -mcpu=native -O3	avxicc
gcc -march=native -mcpu=native -Os	avxicc