Implementation notes: armeabi, c1, crypto_aead/pi64cipher128v2

Computer: c1
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: pi64cipher128v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
1143821	`goptv`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161211	20161026
1308785	`goptv`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161211	20161026
1322628	`goptv`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161211	20161026
1403393	`ref3`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161211	20161026
1423232	`ref3`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161211	20161026
1431761	`goptv`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161211	20161026
1467669	`goptv`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161211	20161026
1488452	`goptv`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161211	20161026
1672027	`ref3`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161211	20161026
1733699	`ref3`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161211	20161026
1856013	`ref3`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161211	20161026
1881242	`ref3`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161211	20161026
2533851	`ref2`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161211	20161026
2997823	`ref2`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161211	20161026
3043931	`ref2`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161211	20161026
3092033	`ref2`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161211	20161026
3121180	`ref2`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161211	20161026
3543539	`ref2`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161211	20161026

Test failure

Implementation: crypto_aead/pi64cipher128v2/ref
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os

error 111
crypto_aead_encrypt returns more than crypto_aead_ABYTES extra bytes

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	ref
gcc -mcpu=native -mfpu=neon-vfpv4 -O2	optimized_nonSSE
gcc -mcpu=native -mfpu=neon-vfpv4 -Os	optimized_nonSSE ref

Compiler output

Implementation: crypto_aead/pi64cipher128v2/optimized_nonSSE
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

encrypt.c: gcc: internal compiler error: Killed (program cc1)
encrypt.c: Please submit a full bug report,
encrypt.c: with preprocessed source if appropriate.
encrypt.c: See gt; for instructions.

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	optimized_nonSSE
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	optimized_nonSSE ref
gcc -mcpu=native -mfpu=neon-vfpv4 -O2	ref
gcc -mcpu=native -mfpu=neon-vfpv4 -O3	optimized_nonSSE ref