Implementation notes: armeabi, a15, crypto_scalarmult/curve25519

Computer: a15
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20161026
Operation: crypto_scalarmult
Primitive: curve25519

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
1250223	`neon2`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161217	20161026
1250224	`neon2`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161217	20161026
1250312	`neon2`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161217	20161026
1250320	`neon2`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161217	20161026
1250347	`neon2`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161217	20161026
1250347	`neon2`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161217	20161026
3214494	`ref10`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161217	20161026
3223319	`ref10`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161217	20161026
3259612	`ref10`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161217	20161026
3268160	`ref10`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161217	20161026
3440585	`ref10`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161217	20161026
3483703	`ref10`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161217	20161026
39822146	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3`	20161217	20161026
40561902	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2`	20161217	20161026
46457335	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O3`	20161217	20161026
49613619	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -O2`	20161217	20161026
53307097	`ref`	`gcc -mcpu=native -mfpu=neon-vfpv4 -Os`	20161217	20161026
53530293	`ref`	`gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os`	20161217	20161026

Compiler output

Implementation: crypto_scalarmult/curve25519/donna_c64
Compiler: gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2

smult.c: smult.c:34:1: error: unable to emulate 'TI'
smult.c: typedef unsigned uint128_t __attribute__((mode(TI)));
smult.c: ^~~~~~~
smult.c: smult.c: In function 'fscalar_product':
smult.c: smult.c:76:49: warning: right shift count >gt;= width of type [-Wshift-count-overflow]
smult.c: a = ((uint128_t) in[1]) * scalar + ((limb) (a >gt;>gt; 51));
smult.c: ^~
smult.c: smult.c:79:49: warning: right shift count >gt;= width of type [-Wshift-count-overflow]
smult.c: a = ((uint128_t) in[2]) * scalar + ((limb) (a >gt;>gt; 51));
smult.c: ^~
smult.c: ...
smult.c: ^~~~
smult.c: smult.c:70:1: warning: always_inline function might not be inlinable [-Wattributes]
smult.c: fscalar_product(felem output, const felem in, const limb scalar) {
smult.c: ^~~~~~~~~~~~~~~
smult.c: smult.c:56:1: warning: always_inline function might not be inlinable [-Wattributes]
smult.c: fdifference_backwards(felem out, const felem in) {
smult.c: ^~~~~~~~~~~~~~~~~~~~~
smult.c: smult.c:41:1: warning: always_inline function might not be inlinable [-Wattributes]
smult.c: fsum(limb *output, const limb *in) {
smult.c: ^~~~

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

Compiler	Implementations
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O2	donna_c64
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -O3	donna_c64
gcc -funroll-loops -mcpu=native -mfpu=neon-vfpv4 -Os	donna_c64
gcc -mcpu=native -mfpu=neon-vfpv4 -O2	donna_c64
gcc -mcpu=native -mfpu=neon-vfpv4 -O3	donna_c64
gcc -mcpu=native -mfpu=neon-vfpv4 -Os	donna_c64