Implementation notes: armeabi, cubie2, crypto_core/aes256encrypt

Computer: cubie2
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20161026
Operation: crypto_core
Primitive: aes256encrypt

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
1410	`openssl`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
1410	`openssl`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
1410	`openssl`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
1422	`openssl`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
1431	`openssl`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
1434	`openssl`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
1626	`dolbeau/std-1ft`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
1626	`dolbeau/std-2ft`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
1635	`dolbeau/std-2ft`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
1649	`dolbeau/std-1ft`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
1650	`dolbeau/std-2ft`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
1662	`dolbeau/std-1ft`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
1662	`dolbeau/std-2ft`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
1662	`dolbeau/std-1ft`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
1695	`dolbeau/std-4ft`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
1716	`dolbeau/std-4ft`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
1719	`dolbeau/std-4ft`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
1740	`dolbeau/std-4ft`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
1956	`dolbeau/std-4ft`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
2061	`dolbeau/std-4ft`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
2133	`dolbeau/std-2ft`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
2172	`dolbeau/std-1ft`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
2313	`dolbeau/std-2ft`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
2358	`dolbeau/std-1ft`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
1128295	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
1152865	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
1346746	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
2708038	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
2834346	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
2856173	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026

Compiler output

Implementation: crypto_core/aes256encrypt/dolbeau/armv8crypto
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

core.c: In file included from core.c:9:0:
core.c: core.c: In function 'aes256_armv8_encrypt':
core.c: /usr/lib/gcc/armv7l-unknown-linux-gnueabihf/6.2.1/include/arm_neon.h:14724:1: error: inlining failed in call to always_inline 'vaeseq_u8': target specific option mismatch
core.c: vaeseq_u8 (uint8x16_t __data, uint8x16_t __key)
core.c: ^~~~~~~~~
core.c: core.c:122:8: note: called from here
core.c: temp = vaeseq_u8(temp, vld1q_u8((rkeys+208)));
core.c: ~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
core.c: In file included from core.c:9:0:
core.c: /usr/lib/gcc/armv7l-unknown-linux-gnueabihf/6.2.1/include/arm_neon.h:14724:1: error: inlining failed in call to always_inline 'vaeseq_u8': target specific option mismatch
core.c: vaeseq_u8 (uint8x16_t __data, uint8x16_t __key)
core.c: ^~~~~~~~~
core.c: core.c:122:8: note: called from here
core.c: temp = vaeseq_u8(temp, vld1q_u8((rkeys+208)));
core.c: ~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	dolbeau/armv8crypto
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	dolbeau/armv8crypto
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	dolbeau/armv8crypto
gcc -mcpu=native -mfpu=neon-vfpv4 -O2	dolbeau/armv8crypto
gcc -mcpu=native -mfpu=neon-vfpv4 -O3	dolbeau/armv8crypto
gcc -mcpu=native -mfpu=neon-vfpv4 -Os	dolbeau/armv8crypto