Implementation notes: armeabi, cubie2, crypto_hashblocks/sha256

Computer: cubie2
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20161026
Operation: crypto_hashblocks
Primitive: sha256

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
49488	`arm11`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
49488	`arm11`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
49491	`arm11`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
49503	`arm11`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
49504	`arm11`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
49542	`arm11`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
55909	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
55909	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
56172	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
56172	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
56484	`inplace`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
56502	`inplace`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
56615	`inplace`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
56616	`inplace`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
61329	`inplace`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
61428	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
62394	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
63279	`inplace`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026

Compiler output

Implementation: crypto_hashblocks/sha256/dolbeau/armv8crypto
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

blocks.c: In file included from blocks.c:37:0:
blocks.c: blocks.c: In function 'crypto_hashblocks_sha256_dolbeau_armv8crypto':
blocks.c: /usr/lib/gcc/armv7l-unknown-linux-gnueabihf/6.2.1/include/arm_neon.h:14799:1: error: inlining failed in call to always_inline 'vsha256h2q_u32': target specific option mismatch
blocks.c: vsha256h2q_u32 (uint32x4_t __hash_abcd, uint32x4_t __hash_efgh, uint32x4_t __wk)
blocks.c: ^~~~~~~~~~~~~~
blocks.c: blocks.c:118:6: note: called from here
blocks.c: s1 = vsha256h2q_u32(x1, x0, h1)
blocks.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: blocks.c:146:3: note: in expansion of macro 'DO16ROUNDS'
blocks.c: DO16ROUNDS(j0, j1, j2, j3, cc, cd, ce, cf);
blocks.c: ...
blocks.c: In file included from blocks.c:37:0:
blocks.c: /usr/lib/gcc/armv7l-unknown-linux-gnueabihf/6.2.1/include/arm_neon.h:14793:1: error: inlining failed in call to always_inline 'vsha256hq_u32': target specific option mismatch
blocks.c: vsha256hq_u32 (uint32x4_t __hash_abcd, uint32x4_t __hash_efgh, uint32x4_t __wk)
blocks.c: ^~~~~~~~~~~~~
blocks.c: blocks.c:117:6: note: called from here
blocks.c: s0 = vsha256hq_u32(x0, x1, h1); ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: blocks.c:146:3: note: in expansion of macro 'DO16ROUNDS'
blocks.c: DO16ROUNDS(j0, j1, j2, j3, cc, cd, ce, cf);
blocks.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

Compiler output

Implementation: crypto_hashblocks/sha256/dolbeau/amd64-sha
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

blocks.c: blocks.c:37:23: fatal error: immintrin.h: No such file or directory
blocks.c: #include gt;
blocks.c: ^
blocks.c: compilation terminated.

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	dolbeau/amd64-sha
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	dolbeau/amd64-sha
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	dolbeau/amd64-sha
gcc -mcpu=native -mfpu=neon-vfpv4 -O2	dolbeau/amd64-sha
gcc -mcpu=native -mfpu=neon-vfpv4 -O3	dolbeau/amd64-sha
gcc -mcpu=native -mfpu=neon-vfpv4 -Os	dolbeau/amd64-sha