Implementation notes: armeabi, tonido, crypto_hash/blake256

Computer: tonido
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20170718
Operation: crypto_hash
Primitive: blake256

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
134484	? ? ?	? ? ?	`regs`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-Os`	20170719	20170718
137148	? ? ?	? ? ?	`bswap`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-Os`	20170719	20170718
138816	? ? ?	? ? ?	`sphlib`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-Os`	20170719	20170718
139182	? ? ?	? ? ?	`regs`	`gcc_-march=native_-mtune=xscale_-Os`	20170719	20170718
140082	? ? ?	? ? ?	`bswap`	`gcc_-march=native_-mtune=xscale_-Os`	20170719	20170718
141750	? ? ?	? ? ?	`sphlib`	`gcc_-march=native_-mtune=xscale_-Os`	20170719	20170718
149136	? ? ?	? ? ?	`sphlib`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-O3`	20170719	20170718
150606	? ? ?	? ? ?	`sphlib`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-O2`	20170719	20170718
152808	? ? ?	? ? ?	`sphlib`	`gcc_-march=native_-mtune=xscale_-O2`	20170719	20170718
153258	? ? ?	? ? ?	`sphlib`	`gcc_-march=native_-mtune=xscale_-O3`	20170719	20170718
156420	? ? ?	? ? ?	`bswap`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-O2`	20170719	20170718
157428	? ? ?	? ? ?	`bswap`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-O3`	20170719	20170718
159558	? ? ?	? ? ?	`bswap`	`gcc_-march=native_-mtune=xscale_-O3`	20170719	20170718
159648	? ? ?	? ? ?	`bswap`	`gcc_-march=native_-mtune=xscale_-O2`	20170719	20170718
168420	? ? ?	? ? ?	`regs`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-O2`	20170719	20170718
172728	? ? ?	? ? ?	`regs`	`gcc_-march=native_-mtune=xscale_-O2`	20170719	20170718
173598	? ? ?	? ? ?	`regs`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-O3`	20170719	20170718
173928	? ? ?	? ? ?	`regs`	`gcc_-march=native_-mtune=xscale_-O3`	20170719	20170718
185844	? ? ?	? ? ?	`sphlib-small`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-Os`	20170719	20170718
191988	? ? ?	? ? ?	`sphlib-small`	`gcc_-march=native_-mtune=xscale_-Os`	20170719	20170718
192684	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-Os`	20170719	20170718
196950	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=xscale_-Os`	20170719	20170718
259776	? ? ?	? ? ?	`sphlib-small`	`gcc_-march=native_-mtune=xscale_-O2`	20170719	20170718
260964	? ? ?	? ? ?	`sphlib-small`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-O3`	20170719	20170718
261300	? ? ?	? ? ?	`sphlib-small`	`gcc_-march=native_-mtune=xscale_-O3`	20170719	20170718
261624	? ? ?	? ? ?	`sphlib-small`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-O2`	20170719	20170718
265248	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-O3`	20170719	20170718
266250	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=xscale_-O3`	20170719	20170718
266604	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=native_-mtune=xscale_-O2`	20170719	20170718
277800	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=xscale_-O2`	20170719	20170718

Test failure

Implementation: crypto_hash/blake256/vect128-neon
Compiler: gcc -funroll-loops -march=native -mtune=xscale -O2

error 111

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

Compiler	Implementations
gcc -funroll-loops -march=native -mtune=xscale -O2	vect128-neon
gcc -funroll-loops -march=native -mtune=xscale -O3	vect128-neon
gcc -funroll-loops -march=native -mtune=xscale -Os	vect128-neon
gcc -march=native -mtune=xscale -O2	vect128-neon
gcc -march=native -mtune=xscale -O3	vect128-neon
gcc -march=native -mtune=xscale -Os	vect128-neon

Compiler output

Implementation: crypto_hash/blake256/arm11
Compiler: gcc -funroll-loops -march=native -mtune=xscale -O2

compress.s: compress.s: Assembler messages:
compress.s: compress.s:962: Error: selected processor does not support `setend be' in ARM mode
compress.s: compress.s:975: Error: selected processor does not support `setend le' in ARM mode
compress.s: compress.s:988: Error: selected processor does not support `setend be' in ARM mode
compress.s: compress.s:1001: Error: selected processor does not support `setend le' in ARM mode
compress.s: compress.s:1014: Error: selected processor does not support `setend be' in ARM mode
compress.s: compress.s:1027: Error: selected processor does not support `setend le' in ARM mode
compress.s: compress.s:1040: Error: selected processor does not support `setend be' in ARM mode
compress.s: compress.s:1053: Error: selected processor does not support `setend le' in ARM mode

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

Compiler	Implementations
gcc -funroll-loops -march=native -mtune=xscale -O2	arm11
gcc -funroll-loops -march=native -mtune=xscale -O3	arm11
gcc -funroll-loops -march=native -mtune=xscale -Os	arm11
gcc -march=native -mtune=xscale -O2	arm11
gcc -march=native -mtune=xscale -O3	arm11
gcc -march=native -mtune=xscale -Os	arm11

Compiler output

Implementation: crypto_hash/blake256/arm_thumb2
Compiler: gcc -funroll-loops -march=native -mtune=xscale -O2

compress_stripped.s: compress_stripped.s: Assembler messages:
compress_stripped.s: compress_stripped.s:19: Error: cannot honor width suffix -- `str r8,[sp,#148]'
compress_stripped.s: compress_stripped.s:20: Error: cannot honor width suffix -- `str r9,[sp,#152]'
compress_stripped.s: compress_stripped.s:21: Error: cannot honor width suffix -- `str r10,[sp,#156]'
compress_stripped.s: compress_stripped.s:22: Error: cannot honor width suffix -- `str r11,[sp,#160]'
compress_stripped.s: compress_stripped.s:23: Error: cannot honor width suffix -- `str r14,[sp,#164]'
compress_stripped.s: compress_stripped.s:29: Error: cannot honor width suffix -- `ldr r8,[r3,#20]'
compress_stripped.s: compress_stripped.s:30: Error: cannot honor width suffix -- `ldr r9,[r3,#24]'
compress_stripped.s: compress_stripped.s:31: Error: cannot honor width suffix -- `ldr r10,[r3,#28]'
compress_stripped.s: compress_stripped.s:37: Error: cannot honor width suffix -- `str r8,[sp,#188]'
compress_stripped.s: ...
compress_stripped.s: compress_stripped.s:2253: Error: lo register required -- `add r1,r1,#64'
compress_stripped.s: compress_stripped.s:2254: Error: lo register required -- `subs r9,r9,#1'
compress_stripped.s: compress_stripped.s:2255: Error: cannot honor width suffix -- `str r9,[sp,#128]'
compress_stripped.s: compress_stripped.s:2261: Error: cannot honor width suffix -- `ldr r8,[sp,#148]'
compress_stripped.s: compress_stripped.s:2262: Error: cannot honor width suffix -- `ldr r9,[sp,#152]'
compress_stripped.s: compress_stripped.s:2263: Error: cannot honor width suffix -- `ldr r10,[sp,#156]'
compress_stripped.s: compress_stripped.s:2264: Error: cannot honor width suffix -- `ldr r11,[sp,#160]'
compress_stripped.s: compress_stripped.s:2265: Error: cannot honor width suffix -- `ldr r14,[sp,#164]'
compress_stripped.s: compress_stripped.s:13: Error: branch out of range
compress_stripped.s: compress_stripped.s:2256: Error: branch out of range

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

Compiler	Implementations
gcc -funroll-loops -march=native -mtune=xscale -O2	arm_thumb2
gcc -funroll-loops -march=native -mtune=xscale -O3	arm_thumb2
gcc -funroll-loops -march=native -mtune=xscale -Os	arm_thumb2
gcc -march=native -mtune=xscale -O2	arm_thumb2
gcc -march=native -mtune=xscale -O3	arm_thumb2
gcc -march=native -mtune=xscale -Os	arm_thumb2

Compiler output

Implementation: crypto_hash/blake256/vect128-mmxhack
Compiler: gcc -funroll-loops -march=native -mtune=xscale -O2

vector.c: In file included from vector.c:7:0:
vector.c: vector.h:968:2: error: #error "I don't know how to vectorize on this architecture."
vector.c: #error "I don't know how to vectorize on this architecture."
vector.c: ^~~~~
vector.c: vector.h:982:3: error: unknown type name 'v16'
vector.c: v16 v16;
vector.c: ^~~
vector.c: vector.h:987:3: error: unknown type name 'v8'
vector.c: v8 v8;
vector.c: ^~
vector.c: ...
vector.c: static const union cv8 v0 = CV(0);
vector.c: ^~
vector.c: In file included from vector.c:140:0:
vector.c: /usr/lib/gcc/armv5tel-unknown-linux-gnueabi/7.1.1/include/mmintrin.h:28:2: error: #error mmintrin.h included without enabling WMMX/WMMX2 instructions (e.g. -march=iwmmxt or -march=iwmmxt2)
vector.c: #error mmintrin.h included without enabling WMMX/WMMX2 instructions (e.g. -march=iwmmxt or -march=iwmmxt2)
vector.c: ^~~~~
vector.c: vector.c:141:10: fatal error: emmintrin.h: No such file or directory
vector.c: #include <emmintrin.h>
vector.c: ^~~~~~~~~~~~~
vector.c: compilation terminated.

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

Compiler	Implementations
gcc -funroll-loops -march=native -mtune=xscale -O2	vect128-mmxhack
gcc -funroll-loops -march=native -mtune=xscale -O3	vect128-mmxhack
gcc -funroll-loops -march=native -mtune=xscale -Os	vect128-mmxhack
gcc -march=native -mtune=xscale -O2	vect128-mmxhack
gcc -march=native -mtune=xscale -O3	vect128-mmxhack
gcc -march=native -mtune=xscale -Os	vect128-mmxhack

Compiler output

Implementation: crypto_hash/blake256/vect128
Compiler: gcc -funroll-loops -march=native -mtune=xscale -O2

vector.c: In file included from vector.c:7:0:
vector.c: vector.h:968:2: error: #error "I don't know how to vectorize on this architecture."
vector.c: #error "I don't know how to vectorize on this architecture."
vector.c: ^~~~~
vector.c: vector.h:982:3: error: unknown type name 'v16'
vector.c: v16 v16;
vector.c: ^~~
vector.c: vector.h:987:3: error: unknown type name 'v8'
vector.c: v8 v8;
vector.c: ^~
vector.c: ...
vector.c: vector.c:887:15: error: 'v32' undeclared (first use in this function); did you mean 'u32'?
vector.c: round256((v32*)S->buf, (v32*)S->h,
vector.c: ^~~
vector.c: u32
vector.c: vector.c:887:19: error: expected expression before ')' token
vector.c: round256((v32*)S->buf, (v32*)S->h,
vector.c: ^
vector.c: vector.c:902:19: error: expected expression before ')' token
vector.c: round256((v32*)data, (v32*)S->h,
vector.c: ^

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

Compiler	Implementations
gcc -funroll-loops -march=native -mtune=xscale -O2	vect128
gcc -funroll-loops -march=native -mtune=xscale -O3	vect128
gcc -funroll-loops -march=native -mtune=xscale -Os	vect128
gcc -march=native -mtune=xscale -O2	vect128
gcc -march=native -mtune=xscale -O3	vect128
gcc -march=native -mtune=xscale -Os	vect128