a459ee44c0
Similar to my previous patch for setmem this one does the same for the cpymem expansion.
We count the number of ops emitted and compare it against the alternative of just calling
the library function when optimising for size.
For the code:
void
cpy_127 (char *out, char *in)
{
__builtin_memcpy (out, in, 127);
}
void
cpy_128 (char *out, char *in)
{
__builtin_memcpy (out, in, 128);
}
we now emit a call to memcpy (with an extra MOV-immediate instruction for the size) instead of:
cpy_127(char*, char*):
ldp q0, q1, [x1]
stp q0, q1, [x0]
ldp q0, q1, [x1, 32]
stp q0, q1, [x0, 32]
ldp q0, q1, [x1, 64]
stp q0, q1, [x0, 64]
ldr q0, [x1, 96]
str q0, [x0, 96]
ldr q0, [x1, 111]
str q0, [x0, 111]
ret
cpy_128(char*, char*):
ldp q0, q1, [x1]
stp q0, q1, [x0]
ldp q0, q1, [x1, 32]
stp q0, q1, [x0, 32]
ldp q0, q1, [x1, 64]
stp q0, q1, [x0, 64]
ldp q0, q1, [x1, 96]
stp q0, q1, [x0, 96]
ret
which is a clear code size win. Speed optimisation heuristics remain unchanged.
2021-09-29 Kyrylo Tkachov <kyrylo.tkachov@arm.com>
* config/aarch64/aarch64.c (aarch64_expand_cpymem): Count number of
emitted operations and adjust heuristic for code size.
2021-09-29 Kyrylo Tkachov <kyrylo.tkachov@arm.com>
* gcc.target/aarch64/cpymem-size.c: New test.
29 lines
390 B
C
29 lines
390 B
C
/* { dg-do compile } */
|
|
/* { dg-options "-Os" } */
|
|
|
|
#include <stdlib.h>
|
|
|
|
/*
|
|
** cpy_127:
|
|
** mov x2, 127
|
|
** b memcpy
|
|
*/
|
|
void
|
|
cpy_127 (char *out, char *in)
|
|
{
|
|
__builtin_memcpy (out, in, 127);
|
|
}
|
|
|
|
/*
|
|
** cpy_128:
|
|
** mov x2, 128
|
|
** b memcpy
|
|
*/
|
|
void
|
|
cpy_128 (char *out, char *in)
|
|
{
|
|
__builtin_memcpy (out, in, 128);
|
|
}
|
|
|
|
/* { dg-final { check-function-bodies "**" "" "" } } */
|
|
|