Implementation notes: armeabi, a15, crypto_hash/groestl256

Computer: a15
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20161026
Operation: crypto_hash
Primitive: groestl256

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
68264	`neon-bitslice`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
68390	`neon-bitslice`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
68421	`neon-bitslice`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
68602	`neon-bitslice`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
68693	`neon-bitslice`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
68694	`neon-bitslice`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
72533	`neon-table`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
72751	`neon-table`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
72775	`neon-table`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
73271	`neon-table`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
74425	`neon-table`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
74464	`neon-table`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
79116	`arm11`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
79194	`arm11`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
80207	`arm11`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
82839	`arm11`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
83456	`arm11`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
84736	`arm11`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
105657	`arm32`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
106787	`arm32`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
108409	`arm32`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
130221	`32bit-2ktable`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
135389	`sphlib-adapted`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
135912	`sphlib-adapted`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
137450	`32bit-2ktable`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
138318	`sphlib`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
138516	`sphlib-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
139241	`sphlib`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
140653	`sphlib-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
146793	`opt32`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
147539	`opt32`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
148977	`opt32`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
148979	`opt32`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
149629	`opt32`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
157059	`sphlib-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
158468	`sphlib-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
158957	`sphlib-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
159179	`sphlib-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
163581	`sphlib-adapted`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
168508	`sphlib-adapted`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
171991	`sphlib-adapted`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
173573	`sphlib-adapted`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
186266	`32bit-2ktable`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
186912	`32bit-2ktable`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
187936	`32bit-2ktable`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
193504	`32bit-2ktable`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
193972	`sphlib`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
194626	`opt32`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
195256	`sphlib`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
198320	`sphlib`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
234766	`sphlib`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
236459	`32bit-bytesliced-c-fast`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
241526	`32bit-bytesliced-c-fast`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
274280	`32bit-bytesliced-c-fast`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
292534	`opt64`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
292679	`opt64`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
300290	`32bit-bytesliced-c-fast`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
333270	`8bit_c`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
337584	`32bit-bytesliced-c-fast`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
338614	`8bit_c`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
340039	`8bit_c`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
343778	`8bit_c`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
345562	`8bit_c`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
350189	`32bit-bytesliced-c-fast`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
350542	`32bit-bytesliced-c-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
350979	`8bit_c`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
352886	`32bit-bytesliced-c-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
355346	`32bit-bytesliced-c-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
597354	`32bit-bytesliced-c-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
606105	`opt64`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
630493	`32bit-bytesliced-c-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
631458	`32bit-bytesliced-c-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
737867	`opt64`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
751892	`opt64`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
752170	`opt64`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026

Checksum failure

Implementation: crypto_hash/groestl256/thumb-asm-fast
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

23aec871d1edec36a717bbdcebede1e50652efd23f7362f52b7aa9dc51c4e9dc

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	thumb-asm-fast

Checksum failure

Implementation: crypto_hash/groestl256/arm32
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

a4e9caceafa13f778217d0730d27684ca77f98b34bc9bd40c06808b5307af157

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	arm32

Checksum failure

Implementation: crypto_hash/groestl256/arm32
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3

f079b87636261cf3c9ea6c0c0fa5429569bc7bd103f8d0f0bb23bd4ba5d49053

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	arm32
gcc -mcpu=native -mfpu=neon-vfpv4 -O3	arm32

Test failure

Implementation: crypto_hash/groestl256/thumb-asm-small
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

error 142
sh: line 1: 29354 Alarm clock killafter 3600 ./try

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	thumb-asm-small

Test failure

Implementation: crypto_hash/groestl256/thumb-asm-fast
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3

error 111

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	thumb-asm-fast thumb-asm-small
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	thumb-asm-small
gcc -mcpu=native -mfpu=neon-vfpv4 -O2	thumb-asm-fast thumb-asm-small
gcc -mcpu=native -mfpu=neon-vfpv4 -O3	thumb-asm-fast thumb-asm-small
gcc -mcpu=native -mfpu=neon-vfpv4 -Os	thumb-asm-small

Test failure

Implementation: crypto_hash/groestl256/thumb-asm-fast
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os

error 142
sh: line 1: 29097 Alarm clock killafter 3600 ./try

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	thumb-asm-fast

Test failure

Implementation: crypto_hash/groestl256/thumb-asm-fast
Compiler: gcc -mcpu=native -mfpu=neon-vfpv4 -Os

error 142
sh: line 1: 28967 Alarm clock killafter 3600 ./try

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

Compiler	Implementations
gcc -mcpu=native -mfpu=neon-vfpv4 -Os	thumb-asm-fast

Compiler output

Implementation: crypto_hash/groestl256/vperm-intr
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

hash.c: In file included from hash.c:34:0:
hash.c: groestl-intr-vperm.h:13:23: fatal error: tmmintrin.h: No such file or directory
hash.c: #include gt;
hash.c: ^
hash.c: compilation terminated.

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	vperm-intr
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	vperm-intr
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	vperm-intr
gcc -mcpu=native -mfpu=neon-vfpv4 -O2	vperm-intr
gcc -mcpu=native -mfpu=neon-vfpv4 -O3	vperm-intr
gcc -mcpu=native -mfpu=neon-vfpv4 -Os	vperm-intr

Compiler output

Implementation: crypto_hash/groestl256/neon-bitslice
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

hash.c: hash.c: In function 'crypto_hash_groestl256_neon_bitslice':
hash.c: hash.c:40:12: warning: iteration 64 invokes undefined behavior [-Waggressive-loop-optimizations]
hash.c: ctx[i] = 0;
hash.c: ~~~~~~~^~~
hash.c: hash.c:39:3: note: within this loop
hash.c: for(i=0;i hash.c: ^~~

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	neon-bitslice
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	neon-bitslice
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	neon-bitslice
gcc -mcpu=native -mfpu=neon-vfpv4 -O2	neon-bitslice
gcc -mcpu=native -mfpu=neon-vfpv4 -O3	neon-bitslice
gcc -mcpu=native -mfpu=neon-vfpv4 -Os	neon-bitslice

Compiler output

Implementation: crypto_hash/groestl256/neon-vperm
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

hash.c: hash.c: In function 'crypto_hash_groestl256_neon_vperm':
hash.c: hash.c:38:12: warning: iteration 64 invokes undefined behavior [-Waggressive-loop-optimizations]
hash.c: ctx[i] = 0;
hash.c: ~~~~~~~^~~
hash.c: hash.c:37:3: note: within this loop
hash.c: for(i=0;i hash.c: ^~~
vperm-neon.S: vperm-neon.S: Assembler messages:
vperm-neon.S: vperm-neon.S:911: Error: expected symbol name
vperm-neon.S: vperm-neon.S:922: Error: expected symbol name

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	neon-vperm
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	neon-vperm
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	neon-vperm
gcc -mcpu=native -mfpu=neon-vfpv4 -O2	neon-vperm
gcc -mcpu=native -mfpu=neon-vfpv4 -O3	neon-vperm
gcc -mcpu=native -mfpu=neon-vfpv4 -Os	neon-vperm

Compiler output

Implementation: crypto_hash/groestl256/opt64
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

hash.c: hash.c:194:14: warning: 'inP' is static but declared in inline function 'F1024' which is not static
hash.c: static u64 inP[COLS1024] __attribute__((aligned(16)));
hash.c: ^~~
hash.c: hash.c:193:14: warning: 'outQ' is static but declared in inline function 'F1024' which is not static
hash.c: static u64 outQ[COLS1024] __attribute__((aligned(16)));
hash.c: ^~~~
hash.c: hash.c:192:14: warning: 'z' is static but declared in inline function 'F1024' which is not static
hash.c: static u64 z[COLS1024] __attribute__((aligned(16)));
hash.c: ^
hash.c: hash.c:191:14: warning: 'y' is static but declared in inline function 'F1024' which is not static
hash.c: static u64 y[COLS1024] __attribute__((aligned(16)));
hash.c: ^

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	opt64
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	opt64
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	opt64
gcc -mcpu=native -mfpu=neon-vfpv4 -O2	opt64
gcc -mcpu=native -mfpu=neon-vfpv4 -O3	opt64
gcc -mcpu=native -mfpu=neon-vfpv4 -Os	opt64