Implementation notes: armeabi, a15, crypto_aead/aes256gcmv1

Computer: a15
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: aes256gcmv1

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
115622	`openssl`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
116100	`openssl`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
116405	`openssl`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
116794	`openssl`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
116930	`openssl`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
117690	`openssl`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
2697567	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
2776958	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161215	20161026
16395081	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026
19850107	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
20560886	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161215	20161026
21724968	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161215	20161026

Compiler output

Implementation: crypto_aead/aes256gcmv1/cryptopp
Compiler: g++ -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

stream.cpp: stream.cpp:2:26: fatal error: cryptopp/aes.h: No such file or directory
stream.cpp: #include gt;
stream.cpp: ^
stream.cpp: compilation terminated.

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

Compiler	Implementations
g++ -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	cryptopp
g++ -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	cryptopp
g++ -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	cryptopp
g++ -mcpu=native -mfpu=neon-vfpv4 -O2	cryptopp
g++ -mcpu=native -mfpu=neon-vfpv4 -O3	cryptopp
g++ -mcpu=native -mfpu=neon-vfpv4 -Os	cryptopp

Compiler output

Implementation: crypto_aead/aes256gcmv1/dolbeau/armv8crypto
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

armv8crypto.c: armv8crypto.c: In function 'addmul':
armv8crypto.c: armv8crypto.c:328:19: warning: implicit declaration of function 'vrbitq_u8' [-Wimplicit-function-declaration]
armv8crypto.c: A = (poly8x16_t)vrbitq_u8((uint8x16_t)vreversebyteq_u128((uint32x4_t)A));
armv8crypto.c: ^~~~~~~~~
armv8crypto.c: armv8crypto.c:328:3: error: can't convert a value of type 'int' to vector type '__simd128_poly8_t' which has different size
armv8crypto.c: A = (poly8x16_t)vrbitq_u8((uint8x16_t)vreversebyteq_u128((uint32x4_t)A));
armv8crypto.c: ^
armv8crypto.c: armv8crypto.c:329:3: error: can't convert a value of type 'int' to vector type '__simd128_poly8_t' which has different size
armv8crypto.c: X = (poly8x16_t)vrbitq_u8((uint8x16_t)/* vreversebyteq_u128 */((uint32x4_t)X));
armv8crypto.c: ^
armv8crypto.c: armv8crypto.c:330:3: error: can't convert a value of type 'int' to vector type '__simd128_poly8_t' which has different size
armv8crypto.c: Y = (poly8x16_t)vrbitq_u8((uint8x16_t)vreversebyteq_u128((uint32x4_t)Y));
armv8crypto.c: ^
armv8crypto.c: armv8crypto.c:343:3: error: can't convert a value of type 'int' to vector type '__simd128_poly8_t' which has different size
armv8crypto.c: A = (poly8x16_t)vrbitq_u8((uint8x16_t)vreversebyteq_u128((uint32x4_t)A));
armv8crypto.c: ^
armv8crypto.c: armv8crypto.c: In function 'mulv':
armv8crypto.c: armv8crypto.c:400:3: error: can't convert a value of type 'int' to vector type '__simd128_uint32_t' which has different size
armv8crypto.c: return (uint32x4_t)vrbitq_u8((uint8x16_t)mulv_neon_nobr((uint32x4_t)vrbitq_u8((uint8x16_t)A),(uint32x4_t)vrbitq_u8((uint8x16_t)B)));
armv8crypto.c: ^~~~~~
armv8crypto.c: armv8crypto.c:400:3: error: can't convert a value of type 'int' to vector type '__simd128_uint32_t' which has different size

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