Implementation notes: armeabi, cubie2, crypto_hash/groestl256

Computer: cubie2
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20161026
Operation: crypto_hash
Primitive: groestl256

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
147731	`neon-table`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
147835	`neon-table`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
147853	`neon-table`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
148873	`neon-table`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
149626	`neon-table`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
149904	`neon-table`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
166794	`neon-bitslice`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
166878	`neon-bitslice`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
167007	`neon-bitslice`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
167328	`neon-bitslice`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
167392	`neon-bitslice`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
167447	`neon-bitslice`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
176889	`arm11`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
176898	`arm11`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
179089	`arm11`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
182109	`arm11`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
182385	`arm11`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
183626	`arm11`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
211124	`arm32`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
213349	`arm32`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
219483	`arm32`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
243684	`opt32`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
244230	`opt32`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
244788	`opt32`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
245637	`opt32`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
317387	`sphlib`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
329677	`sphlib`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
332779	`sphlib-adapted`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
332783	`sphlib-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
335650	`sphlib-adapted`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
363960	`32bit-2ktable`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
367662	`sphlib-adapted`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
367977	`32bit-2ktable`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
371357	`sphlib-adapted`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
372246	`32bit-2ktable`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
375075	`32bit-2ktable`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
376053	`sphlib-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
378606	`32bit-2ktable`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
378925	`sphlib-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
385881	`sphlib-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
386127	`sphlib-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
396245	`sphlib-adapted`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
397657	`sphlib-adapted`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
400246	`sphlib-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
434821	`sphlib`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
437602	`sphlib`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
438533	`32bit-2ktable`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
439042	`sphlib`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
444420	`sphlib`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
448228	`opt64`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
485520	`opt32`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
487164	`opt32`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
514529	`32bit-bytesliced-c-fast`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
523545	`opt64`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
569964	`32bit-bytesliced-c-fast`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
638873	`32bit-bytesliced-c-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
640195	`32bit-bytesliced-c-fast`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
653079	`8bit_c`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
661542	`8bit_c`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
671395	`8bit_c`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
677453	`8bit_c`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
688705	`32bit-bytesliced-c-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
692143	`32bit-bytesliced-c-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
727974	`32bit-bytesliced-c-fast`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
742589	`8bit_c`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
753408	`32bit-bytesliced-c-fast`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
785470	`opt64`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
796229	`8bit_c`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
826017	`32bit-bytesliced-c-fast`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
1002543	`opt64`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
1012701	`opt64`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
1035207	`opt64`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
1229419	`32bit-bytesliced-c-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
1258267	`32bit-bytesliced-c-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
1273890	`32bit-bytesliced-c-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026

Checksum failure

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

f079b87636261cf3c9ea6c0c0fa5429569bc7bd103f8d0f0bb23bd4ba5d49053

Number of similar (compiler,implementation) pairs: 3, namely:

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

error 142
sh: line 1: 9352 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-fast

Test failure

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

error 142
sh: line 1: 9647 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: 9390 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: 9267 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