Implementation notes: armeabi, a15, crypto_hash/blake512

Computer: a15
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20161026
Operation: crypto_hash
Primitive: blake512

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
23068	`vect128-neon`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
23069	`vect128-neon`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
23070	`vect128-neon`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
23084	`vect128-neon`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
23093	`vect128-neon`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
23099	`vect128-neon`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
82458	`sphlib-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
82469	`sphlib`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
82902	`bswap`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
82978	`sphlib-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
83215	`sphlib`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
85811	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
86453	`sphlib`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
86541	`sphlib-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
86858	`sphlib-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
86916	`bswap`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
86942	`sphlib`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
87928	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
90886	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
91710	`regs`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
92578	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
93705	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
97837	`regs`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
98018	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
104412	`sphlib-small`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
104625	`sphlib`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
108153	`sphlib`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
108800	`sphlib-small`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161214	20161026
138612	`bswap`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
139888	`bswap`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
148850	`regs`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
150659	`regs`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
156981	`bswap`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
161090	`bswap`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026
176680	`regs`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161214	20161026
176981	`regs`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161214	20161026

Compiler output

Implementation: crypto_hash/blake512/vect128
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

vector.c: /tmp/ccm0ThJy.s: Assembler messages:
vector.c: /tmp/ccm0ThJy.s:296: Error: invalid instruction shape -- `vmov d20,s28'
vector.c: /tmp/ccm0ThJy.s:297: Error: invalid instruction shape -- `vmov d21,s2'
vector.c: /tmp/ccm0ThJy.s:311: Error: invalid instruction shape -- `vmov d9,s18'
vector.c: /tmp/ccm0ThJy.s:358: Error: invalid instruction shape -- `vmov d13,s6'
vector.c: /tmp/ccm0ThJy.s:383: Error: invalid instruction shape -- `vmov d9,s26'
vector.c: /tmp/ccm0ThJy.s:404: Error: invalid instruction shape -- `vmov d2,s10'
vector.c: /tmp/ccm0ThJy.s:465: Error: invalid instruction shape -- `vmov d7,s14'
vector.c: /tmp/ccm0ThJy.s:490: Error: invalid instruction shape -- `vmov d6,s22'
vector.c: /tmp/ccm0ThJy.s:491: Error: invalid instruction shape -- `vmov d7,s6'
vector.c: ...
vector.c: /tmp/ccm0ThJy.s:3244: Error: invalid instruction shape -- `vmov d1,s22'
vector.c: /tmp/ccm0ThJy.s:3269: Error: invalid instruction shape -- `vmov d10,s20'
vector.c: /tmp/ccm0ThJy.s:3270: Error: invalid instruction shape -- `vmov d11,s30'
vector.c: /tmp/ccm0ThJy.s:3319: Error: invalid instruction shape -- `vmov d4,s22'
vector.c: /tmp/ccm0ThJy.s:3350: Error: invalid instruction shape -- `vmov d10,s14'
vector.c: /tmp/ccm0ThJy.s:3390: Error: invalid instruction shape -- `vmov d5,s18'
vector.c: /tmp/ccm0ThJy.s:3485: Error: invalid instruction shape -- `vmov d23,s30'
vector.c: /tmp/ccm0ThJy.s:3495: Error: invalid instruction shape -- `vmov d24,s22'
vector.c: /tmp/ccm0ThJy.s:3519: Error: invalid instruction shape -- `vmov d30,s28'
vector.c: /tmp/ccm0ThJy.s:3520: Error: invalid instruction shape -- `vmov d31,s10'

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	vect128

Compiler output

Implementation: crypto_hash/blake512/vect128-inplace
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

vector.c: In file included from vector.c:588:0:
vector.c: vector.c: In function 'round512':
vector.c: perm512.h:6:10: warning: implicit declaration of function 'v64_interleavel' [-Wimplicit-function-declaration]
vector.c: m0 = v64_interleavel(mm0, mm1); ^
vector.c: vector.h:5:19: note: in expansion of macro 'PERM_512_0'
vector.c: #define CAT(x, y) x##y
vector.c: ^
vector.c: vector.h:6:19: note: in expansion of macro 'CAT'
vector.c: #define XCAT(x,y) CAT(x,y)
vector.c: ...
vector.c: ^~~
vector.c: perm512.h:1:17: note: in expansion of macro 'XCAT'
vector.c: #define PERM(i) XCAT(PERM_512_,i)
vector.c: ^~~~
vector.c: vector.c:670:5: note: in expansion of macro 'PERM'
vector.c: PERM(i); ^~~~
vector.c: vector.c:756:36: note: in expansion of macro 'ROUND'
vector.c: ROUND(12); ROUND(13); ROUND(14); ROUND(15);
vector.c: ^~~~~

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	vect128-inplace
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	vect128-inplace
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	vect128-inplace
gcc -mcpu=native -mfpu=neon-vfpv4 -O2	vect128-inplace
gcc -mcpu=native -mfpu=neon-vfpv4 -O3	vect128-inplace
gcc -mcpu=native -mfpu=neon-vfpv4 -Os	vect128-inplace

Compiler output

Implementation: crypto_hash/blake512/vect128
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3

vector.c: /tmp/cc1g9afT.s: Assembler messages:
vector.c: /tmp/cc1g9afT.s:296: Error: invalid instruction shape -- `vmov d20,s28'
vector.c: /tmp/cc1g9afT.s:297: Error: invalid instruction shape -- `vmov d21,s2'
vector.c: /tmp/cc1g9afT.s:311: Error: invalid instruction shape -- `vmov d9,s18'
vector.c: /tmp/cc1g9afT.s:358: Error: invalid instruction shape -- `vmov d13,s6'
vector.c: /tmp/cc1g9afT.s:383: Error: invalid instruction shape -- `vmov d9,s26'
vector.c: /tmp/cc1g9afT.s:404: Error: invalid instruction shape -- `vmov d2,s10'
vector.c: /tmp/cc1g9afT.s:465: Error: invalid instruction shape -- `vmov d7,s14'
vector.c: /tmp/cc1g9afT.s:490: Error: invalid instruction shape -- `vmov d6,s22'
vector.c: /tmp/cc1g9afT.s:491: Error: invalid instruction shape -- `vmov d7,s6'
vector.c: ...
vector.c: /tmp/cc1g9afT.s:3244: Error: invalid instruction shape -- `vmov d1,s22'
vector.c: /tmp/cc1g9afT.s:3269: Error: invalid instruction shape -- `vmov d10,s20'
vector.c: /tmp/cc1g9afT.s:3270: Error: invalid instruction shape -- `vmov d11,s30'
vector.c: /tmp/cc1g9afT.s:3319: Error: invalid instruction shape -- `vmov d4,s22'
vector.c: /tmp/cc1g9afT.s:3350: Error: invalid instruction shape -- `vmov d10,s14'
vector.c: /tmp/cc1g9afT.s:3390: Error: invalid instruction shape -- `vmov d5,s18'
vector.c: /tmp/cc1g9afT.s:3485: Error: invalid instruction shape -- `vmov d23,s30'
vector.c: /tmp/cc1g9afT.s:3495: Error: invalid instruction shape -- `vmov d24,s22'
vector.c: /tmp/cc1g9afT.s:3519: Error: invalid instruction shape -- `vmov d30,s28'
vector.c: /tmp/cc1g9afT.s:3520: Error: invalid instruction shape -- `vmov d31,s10'

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	vect128

Compiler output

Implementation: crypto_hash/blake512/vect128
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os

vector.c: /tmp/ccAjBWag.s: Assembler messages:
vector.c: /tmp/ccAjBWag.s:222: Error: invalid instruction shape -- `vmov d20,s4'
vector.c: /tmp/ccAjBWag.s:223: Error: invalid instruction shape -- `vmov d21,s6'
vector.c: /tmp/ccAjBWag.s:236: Error: invalid instruction shape -- `vmov d22,s2'
vector.c: /tmp/ccAjBWag.s:246: Error: invalid instruction shape -- `vmov d12,s8'
vector.c: /tmp/ccAjBWag.s:247: Error: invalid instruction shape -- `vmov d13,s10'
vector.c: /tmp/ccAjBWag.s:259: Error: invalid instruction shape -- `vmov d10,s12'
vector.c: /tmp/ccAjBWag.s:260: Error: invalid instruction shape -- `vmov d11,s14'
vector.c: /tmp/ccAjBWag.s:276: Error: invalid instruction shape -- `vmov d8,s16'
vector.c: /tmp/ccAjBWag.s:277: Error: invalid instruction shape -- `vmov d9,s18'
vector.c: ...
vector.c: /tmp/ccAjBWag.s:4386: Error: invalid instruction shape -- `vmov d24,s14'
vector.c: /tmp/ccAjBWag.s:4391: Error: invalid instruction shape -- `vmov d9,s10'
vector.c: /tmp/ccAjBWag.s:4394: Error: invalid instruction shape -- `vmov d6,s30'
vector.c: /tmp/ccAjBWag.s:4395: Error: invalid instruction shape -- `vmov d7,s26'
vector.c: /tmp/ccAjBWag.s:4403: Error: invalid instruction shape -- `vmov d10,s8'
vector.c: /tmp/ccAjBWag.s:4404: Error: invalid instruction shape -- `vmov d11,s28'
vector.c: /tmp/ccAjBWag.s:4412: Error: invalid instruction shape -- `vmov d15,s24'
vector.c: /tmp/ccAjBWag.s:4415: Error: invalid instruction shape -- `vmov d4,s10'
vector.c: /tmp/ccAjBWag.s:4416: Error: invalid instruction shape -- `vmov d5,s26'
vector.c: /tmp/ccAjBWag.s:4423: Error: invalid instruction shape -- `vmov d12,s24'

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	vect128

Compiler output

Implementation: crypto_hash/blake512/vect128
Compiler: gcc -mcpu=native -mfpu=neon-vfpv4 -O2

vector.c: /tmp/ccbuSBlt.s: Assembler messages:
vector.c: /tmp/ccbuSBlt.s:239: Error: invalid instruction shape -- `vmov d22,s22'
vector.c: /tmp/ccbuSBlt.s:250: Error: invalid instruction shape -- `vmov d20,s24'
vector.c: /tmp/ccbuSBlt.s:251: Error: invalid instruction shape -- `vmov d21,s26'
vector.c: /tmp/ccbuSBlt.s:263: Error: invalid instruction shape -- `vmov d2,s14'
vector.c: /tmp/ccbuSBlt.s:299: Error: invalid instruction shape -- `vmov d28,s28'
vector.c: /tmp/ccbuSBlt.s:303: Error: invalid instruction shape -- `vmov d16,s30'
vector.c: /tmp/ccbuSBlt.s:454: Error: invalid instruction shape -- `vmov d3,s6'
vector.c: /tmp/ccbuSBlt.s:472: Error: invalid instruction shape -- `vmov d28,s2'
vector.c: /tmp/ccbuSBlt.s:482: Error: invalid instruction shape -- `vmov d0,s2'
vector.c: ...
vector.c: /tmp/ccbuSBlt.s:3177: Error: invalid instruction shape -- `vmov d9,s22'
vector.c: /tmp/ccbuSBlt.s:3197: Error: invalid instruction shape -- `vmov d9,s22'
vector.c: /tmp/ccbuSBlt.s:3284: Error: invalid instruction shape -- `vmov d26,s22'
vector.c: /tmp/ccbuSBlt.s:3311: Error: invalid instruction shape -- `vmov d11,s14'
vector.c: /tmp/ccbuSBlt.s:3342: Error: invalid instruction shape -- `vmov d22,s14'
vector.c: /tmp/ccbuSBlt.s:3343: Error: invalid instruction shape -- `vmov d23,s22'
vector.c: /tmp/ccbuSBlt.s:3397: Error: invalid instruction shape -- `vmov d28,s26'
vector.c: /tmp/ccbuSBlt.s:3398: Error: invalid instruction shape -- `vmov d29,s22'
vector.c: /tmp/ccbuSBlt.s:3533: Error: invalid instruction shape -- `vmov d10,s22'
vector.c: /tmp/ccbuSBlt.s:3534: Error: invalid instruction shape -- `vmov d11,s18'

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

Compiler	Implementations
gcc -mcpu=native -mfpu=neon-vfpv4 -O2	vect128

Compiler output

Implementation: crypto_hash/blake512/vect128
Compiler: gcc -mcpu=native -mfpu=neon-vfpv4 -O3

vector.c: /tmp/ccOCVAhX.s: Assembler messages:
vector.c: /tmp/ccOCVAhX.s:297: Error: invalid instruction shape -- `vmov d20,s28'
vector.c: /tmp/ccOCVAhX.s:298: Error: invalid instruction shape -- `vmov d21,s2'
vector.c: /tmp/ccOCVAhX.s:346: Error: invalid instruction shape -- `vmov d17,s0'
vector.c: /tmp/ccOCVAhX.s:370: Error: invalid instruction shape -- `vmov d17,s6'
vector.c: /tmp/ccOCVAhX.s:445: Error: invalid instruction shape -- `vmov d9,s16'
vector.c: /tmp/ccOCVAhX.s:483: Error: invalid instruction shape -- `vmov d10,s14'
vector.c: /tmp/ccOCVAhX.s:484: Error: invalid instruction shape -- `vmov d11,s20'
vector.c: /tmp/ccOCVAhX.s:624: Error: invalid instruction shape -- `vmov d25,s18'
vector.c: /tmp/ccOCVAhX.s:686: Error: invalid instruction shape -- `vmov d26,s2'
vector.c: ...
vector.c: /tmp/ccOCVAhX.s:3264: Error: invalid instruction shape -- `vmov d11,s30'
vector.c: /tmp/ccOCVAhX.s:3279: Error: invalid instruction shape -- `vmov d6,s2'
vector.c: /tmp/ccOCVAhX.s:3303: Error: invalid instruction shape -- `vmov d5,s28'
vector.c: /tmp/ccOCVAhX.s:3324: Error: invalid instruction shape -- `vmov d10,s14'
vector.c: /tmp/ccOCVAhX.s:3370: Error: invalid instruction shape -- `vmov d5,s10'
vector.c: /tmp/ccOCVAhX.s:3381: Error: invalid instruction shape -- `vmov d26,s2'
vector.c: /tmp/ccOCVAhX.s:3462: Error: invalid instruction shape -- `vmov d23,s30'
vector.c: /tmp/ccOCVAhX.s:3472: Error: invalid instruction shape -- `vmov d24,s22'
vector.c: /tmp/ccOCVAhX.s:3490: Error: invalid instruction shape -- `vmov d6,s30'
vector.c: /tmp/ccOCVAhX.s:3491: Error: invalid instruction shape -- `vmov d7,s14'

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

Compiler	Implementations
gcc -mcpu=native -mfpu=neon-vfpv4 -O3	vect128

Compiler output

Implementation: crypto_hash/blake512/vect128
Compiler: gcc -mcpu=native -mfpu=neon-vfpv4 -Os

vector.c: /tmp/ccPxhJLh.s: Assembler messages:
vector.c: /tmp/ccPxhJLh.s:448: Error: invalid instruction shape -- `vmov d14,s16'
vector.c: /tmp/ccPxhJLh.s:449: Error: invalid instruction shape -- `vmov d15,s18'
vector.c: /tmp/ccPxhJLh.s:463: Error: invalid instruction shape -- `vmov d8,s16'
vector.c: /tmp/ccPxhJLh.s:464: Error: invalid instruction shape -- `vmov d9,s18'
vector.c: /tmp/ccPxhJLh.s:2724: Error: invalid instruction shape -- `vmov d14,s28'
vector.c: /tmp/ccPxhJLh.s:2725: Error: invalid instruction shape -- `vmov d15,s30'
vector.c: /tmp/ccPxhJLh.s:3008: Error: invalid instruction shape -- `vmov d14,s28'
vector.c: /tmp/ccPxhJLh.s:3009: Error: invalid instruction shape -- `vmov d15,s30'
vector.c: /tmp/ccPxhJLh.s:3466: Error: invalid instruction shape -- `vmov d0,s6'
vector.c: /tmp/ccPxhJLh.s:3467: Error: invalid instruction shape -- `vmov d1,s4'
vector.c: /tmp/ccPxhJLh.s:3475: Error: invalid instruction shape -- `vmov d2,s6'
vector.c: /tmp/ccPxhJLh.s:3476: Error: invalid instruction shape -- `vmov d3,s4'

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

Compiler	Implementations
gcc -mcpu=native -mfpu=neon-vfpv4 -Os	vect128