Implementation notes: armeabi, odroid, crypto_aead/hs1sivhiv2

Computer: odroid
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20160806
Operation: crypto_aead
Primitive: hs1sivhiv2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
78806	`faster`	`gcc -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv`	20160824	20160806
82187	`faster`	`gcc -mcpu=native -mfpu=neon -O2 -fomit-frame-pointer -fwrapv`	20160824	20160806
82630	`faster`	`gcc -mcpu=native -mfpu=neon -Os -fomit-frame-pointer -fwrapv`	20160824	20160806
88997	`faster`	`gcc -mcpu=native -mfpu=neon -O -fomit-frame-pointer -fwrapv`	20160824	20160806
138167	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160824	20160806
154084	`ref`	`gcc -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv`	20160824	20160806
163077	`ref`	`gcc -mcpu=native -mfpu=neon -O2 -fomit-frame-pointer -fwrapv`	20160824	20160806
183920	`ref`	`gcc -mcpu=native -mfpu=neon -Os -fomit-frame-pointer -fwrapv`	20160824	20160806
227886	`ref`	`gcc -mcpu=native -mfpu=neon -O -fomit-frame-pointer -fwrapv`	20160824	20160806

Test failure

Implementation: crypto_aead/hs1sivhiv2/faster
Compiler: clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

error 111
crypto_aead_decrypt with a=t overlap returns nonzero

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

Compiler	Implementations
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	faster

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/armv8crypto
Compiler: clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

encrypt.c: In file included from encrypt.c:192:
encrypt.c: ./c256.h:148:5: warning: implicit declaration of function 'vtrn1q_u32' is invalid in C99 [-Wimplicit-function-declaration]
encrypt.c: ONEQUAD_TRANSPOSE_NOXOR(0,1,2,3);
encrypt.c: ^
encrypt.c: ./c256.h:134:13: note: expanded from macro 'ONEQUAD_TRANSPOSE_NOXOR'
encrypt.c: t0l = vtrn1q_u32(x_##a,x_##b); \
encrypt.c: ^
encrypt.c: ./c256.h:148:5: error: assigning to 'uint32x4_t' (vector of 4 'uint32_t' values) from incompatible type 'int'
encrypt.c: ONEQUAD_TRANSPOSE_NOXOR(0,1,2,3);
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: ./c256.h:134:11: note: expanded from macro 'ONEQUAD_TRANSPOSE_NOXOR'
encrypt.c: t0l = vtrn1q_u32(x_##a,x_##b); \
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: ./c256.h:148:5: warning: implicit declaration of function 'vtrn2q_u32' is invalid in C99 [-Wimplicit-function-declaration]
encrypt.c: ./c256.h:135:13: note: expanded from macro 'ONEQUAD_TRANSPOSE_NOXOR'
encrypt.c: t0h = vtrn2q_u32(x_##a,x_##b); \
encrypt.c: ^
encrypt.c: ./c256.h:148:5: error: assigning to 'uint32x4_t' (vector of 4 'uint32_t' values) from incompatible type 'int'
encrypt.c: ONEQUAD_TRANSPOSE_NOXOR(0,1,2,3);
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: ./c256.h:135:11: note: expanded from macro 'ONEQUAD_TRANSPOSE_NOXOR'
encrypt.c: t0h = vtrn2q_u32(x_##a,x_##b); \
encrypt.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: ./c256.h:148:5: error: assigning to 'uint32x4_t' (vector of 4 'uint32_t' values) from incompatible type 'int'
encrypt.c: ONEQUAD_TRANSPOSE_NOXOR(0,1,2,3);
encrypt.c: ...

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

Compiler	Implementations
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	dolbeau/armv8crypto

Compiler output

Implementation: crypto_aead/hs1sivhiv2/faster
Compiler: clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

hs1.c: hs1.c:1033:30: warning: implicitly declaring library function 'malloc' with type 'void *(unsigned int)' [-Wimplicit-function-declaration]
hs1.c: unsigned char *tmp = malloc(abytes);
hs1.c: ^
hs1.c: hs1.c:1033:30: note: include the header gt; or explicitly provide a declaration for 'malloc'
hs1.c: hs1.c:1037:9: warning: implicit declaration of function 'free' is invalid in C99 [-Wimplicit-function-declaration]
hs1.c: free(tmp);
hs1.c: ^
hs1.c: 2 warnings generated.

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

Compiler	Implementations
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	faster

Compiler output

Implementation: crypto_aead/hs1sivhiv2/dolbeau/armv8crypto
Compiler: gcc -mcpu=native -mfpu=neon -O2 -fomit-frame-pointer -fwrapv

encrypt.c: In file included from encrypt.c:192:0:
encrypt.c: c256.h: In function 'chacha_noxor368':
encrypt.c: c256.h:134:13: warning: implicit declaration of function 'vtrn1q_u32' [-Wimplicit-function-declaration]
encrypt.c: t0l = vtrn1q_u32(x_##a,x_##b); \
encrypt.c: ^
encrypt.c: c256.h:148:5: note: in expansion of macro 'ONEQUAD_TRANSPOSE_NOXOR'
encrypt.c: ONEQUAD_TRANSPOSE_NOXOR(0,1,2,3);
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c256.h:134:11: error: incompatible types when assigning to type 'uint32x4_t' from type 'int'
encrypt.c: t0l = vtrn1q_u32(x_##a,x_##b); \
encrypt.c: ^
encrypt.c: c256.h:148:5: note: in expansion of macro 'ONEQUAD_TRANSPOSE_NOXOR'
encrypt.c: ONEQUAD_TRANSPOSE_NOXOR(0,1,2,3);
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c256.h:135:13: warning: implicit declaration of function 'vtrn2q_u32' [-Wimplicit-function-declaration]
encrypt.c: t0h = vtrn2q_u32(x_##a,x_##b); \
encrypt.c: ^
encrypt.c: c256.h:148:5: note: in expansion of macro 'ONEQUAD_TRANSPOSE_NOXOR'
encrypt.c: ONEQUAD_TRANSPOSE_NOXOR(0,1,2,3);
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: c256.h:135:11: error: incompatible types when assigning to type 'uint32x4_t' from type 'int'
encrypt.c: t0h = vtrn2q_u32(x_##a,x_##b); \
encrypt.c: ^
encrypt.c: c256.h:148:5: note: in expansion of macro 'ONEQUAD_TRANSPOSE_NOXOR'
encrypt.c: ONEQUAD_TRANSPOSE_NOXOR(0,1,2,3);
encrypt.c: ...

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

Compiler	Implementations
gcc -mcpu=native -mfpu=neon -O2 -fomit-frame-pointer -fwrapv	dolbeau/armv8crypto
gcc -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv	dolbeau/armv8crypto
gcc -mcpu=native -mfpu=neon -O -fomit-frame-pointer -fwrapv	dolbeau/armv8crypto
gcc -mcpu=native -mfpu=neon -Os -fomit-frame-pointer -fwrapv	dolbeau/armv8crypto

Compiler output

Implementation: crypto_aead/hs1sivhiv2/faster
Compiler: gcc -mcpu=native -mfpu=neon -O2 -fomit-frame-pointer -fwrapv

hs1.c: hs1.c: In function 'hs1siv_decrypt':
hs1.c: hs1.c:1033:30: warning: implicit declaration of function 'malloc' [-Wimplicit-function-declaration]
hs1.c: unsigned char *tmp = malloc(abytes);
hs1.c: ^~~~~~
hs1.c: hs1.c:1033:30: warning: incompatible implicit declaration of built-in function 'malloc'
hs1.c: hs1.c:1033:30: note: include 'gt;' or provide a declaration of 'malloc'
hs1.c: hs1.c:1037:9: warning: implicit declaration of function 'free' [-Wimplicit-function-declaration]
hs1.c: free(tmp);
hs1.c: ^~~~
hs1.c: hs1.c:1037:9: warning: incompatible implicit declaration of built-in function 'free'
hs1.c: hs1.c:1037:9: note: include 'gt;' or provide a declaration of 'free'

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

Compiler	Implementations
gcc -mcpu=native -mfpu=neon -O2 -fomit-frame-pointer -fwrapv	faster
gcc -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv	faster
gcc -mcpu=native -mfpu=neon -O -fomit-frame-pointer -fwrapv	faster
gcc -mcpu=native -mfpu=neon -Os -fomit-frame-pointer -fwrapv	faster