Implementation notes: amd64, par, crypto_hash/cubehash512

Computer: par
Architecture: amd64
CPU ID: GenuineIntel-000406c3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_hash
Primitive: cubehash512

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
27160	`amd64-2`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
27160	`amd64-2`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
27160	`amd64-2`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
27160	`amd64-2`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
27180	`amd64-2`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
27180	`amd64-2`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
27900	`amd64`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
27900	`amd64`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
27900	`amd64`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
27900	`amd64`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
27900	`amd64`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
27900	`amd64`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
28660	`emmintrin4`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
28740	`emmintrin5`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
28860	`emmintrin4`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
29540	`emmintrin5`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
30240	`emmintrin4`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
30460	`emmintrin5`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
30500	`emmintrin4`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
31240	`emmintrin5`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
31620	`emmintrin5`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
32560	`emmintrin5`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
34520	`emmintrin4`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
34800	`emmintrin4`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
85900	`unrolled5`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
85940	`mmintrin`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
86600	`unrolled5`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
86700	`mmintrin`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
86760	`mmintrin`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
88080	`mmintrin`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
88340	`mmintrin`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
88460	`unrolled5`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
88480	`mmintrin`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
88560	`unrolled3`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
88940	`unrolled3`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
90640	`amd64-32`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
90660	`amd64-32`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
90680	`amd64-32`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
90680	`amd64-32`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
90720	`amd64-32`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
90940	`amd64-32`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
91660	`unrolled3`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
91980	`unrolled3`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
92100	`unrolled3`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
92240	`unrolled5`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
93220	`unrolled5`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
93380	`unrolled5`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
93460	`unrolled3`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
94360	`unrolled4`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
95160	`unrolled4`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
99260	`unrolled4`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
99780	`unrolled4`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
100120	`unrolled4`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
104920	`unrolled4`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
135920	`simple`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
142660	`simple`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
143040	`simple`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
144260	`unrolled2`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
145060	`unrolled2`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
147040	`unrolled2`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
147300	`unrolled2`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
156740	`unrolled`	`gcc -funroll-loops -march=native -mcpu=native -O2`	20161214	20161026
159140	`unrolled`	`gcc -funroll-loops -march=native -mcpu=native -O3`	20161214	20161026
159260	`unrolled`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
159600	`unrolled`	`gcc -march=native -mcpu=native -O3`	20161214	20161026
302920	`unrolled2`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
304040	`unrolled2`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
308820	`unrolled`	`gcc -march=native -mcpu=native -Os`	20161214	20161026
309340	`unrolled`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
818440	`simple`	`gcc -march=native -mcpu=native -O2`	20161214	20161026
1047740	`simple`	`gcc -funroll-loops -march=native -mcpu=native -Os`	20161214	20161026
1052460	`simple`	`gcc -march=native -mcpu=native -Os`	20161214	20161026

Test failure

Implementation: crypto_hash/cubehash512/amd64avx
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	amd64avx
gcc -funroll-loops -march=native -mcpu=native -O3	amd64avx
gcc -funroll-loops -march=native -mcpu=native -Os	amd64avx
gcc -march=native -mcpu=native -O2	amd64avx
gcc -march=native -mcpu=native -O3	amd64avx
gcc -march=native -mcpu=native -Os	amd64avx

Compiler output

Implementation: crypto_hash/cubehash512/amd64avx
Compiler: gcc -funroll-loops -march=native -mcpu=native -O2

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

Compiler	Implementations
gcc -funroll-loops -march=native -mcpu=native -O2	amd64avx
gcc -funroll-loops -march=native -mcpu=native -O3	amd64avx
gcc -funroll-loops -march=native -mcpu=native -Os	amd64avx
gcc -march=native -mcpu=native -O2	amd64avx
gcc -march=native -mcpu=native -O3	amd64avx
gcc -march=native -mcpu=native -Os	amd64avx

Compiler output

Implementation: crypto_hash/cubehash512/amd64
Compiler: gcc -funroll-loops -march=native -mcpu=native -O2

constants.S: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
hash.s: 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	amd64 amd64-2
gcc -funroll-loops -march=native -mcpu=native -O3	amd64 amd64-2
gcc -funroll-loops -march=native -mcpu=native -Os	amd64 amd64-2
gcc -march=native -mcpu=native -O2	amd64 amd64-2
gcc -march=native -mcpu=native -O3	amd64 amd64-2
gcc -march=native -mcpu=native -Os	amd64 amd64-2

Compiler output

Implementation: crypto_hash/cubehash512/emmintrin4
Compiler: gcc -funroll-loops -march=native -mcpu=native -O2

cubehash.c: gcc: warning: '-mcpu=' is deprecated; use '-mtune=' or '-march=' instead
nist.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: 24, namely:

Compiler	Implementations
gcc -funroll-loops -march=native -mcpu=native -O2	emmintrin4 simple unrolled unrolled2
gcc -funroll-loops -march=native -mcpu=native -O3	emmintrin4 simple unrolled unrolled2
gcc -funroll-loops -march=native -mcpu=native -Os	emmintrin4 simple unrolled unrolled2
gcc -march=native -mcpu=native -O2	emmintrin4 simple unrolled unrolled2
gcc -march=native -mcpu=native -O3	emmintrin4 simple unrolled unrolled2
gcc -march=native -mcpu=native -Os	emmintrin4 simple unrolled unrolled2

Compiler output

Implementation: crypto_hash/cubehash512/emmintrin5
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: 30, namely:

Compiler	Implementations
gcc -funroll-loops -march=native -mcpu=native -O2	emmintrin5 mmintrin unrolled3 unrolled4 unrolled5
gcc -funroll-loops -march=native -mcpu=native -O3	emmintrin5 mmintrin unrolled3 unrolled4 unrolled5
gcc -funroll-loops -march=native -mcpu=native -Os	emmintrin5 mmintrin unrolled3 unrolled4 unrolled5
gcc -march=native -mcpu=native -O2	emmintrin5 mmintrin unrolled3 unrolled4 unrolled5
gcc -march=native -mcpu=native -O3	emmintrin5 mmintrin unrolled3 unrolled4 unrolled5
gcc -march=native -mcpu=native -Os	emmintrin5 mmintrin unrolled3 unrolled4 unrolled5

Compiler output

Implementation: crypto_hash/cubehash512/amd64-32
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
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: 6, namely:

Compiler	Implementations
gcc -funroll-loops -march=native -mcpu=native -O2	amd64-32
gcc -funroll-loops -march=native -mcpu=native -O3	amd64-32
gcc -funroll-loops -march=native -mcpu=native -Os	amd64-32
gcc -march=native -mcpu=native -O2	amd64-32
gcc -march=native -mcpu=native -O3	amd64-32
gcc -march=native -mcpu=native -Os	amd64-32