diff options
| author | Steve Ellcey <sellcey@caviumnetworks.com> | 2017-05-24 16:46:48 -0700 |
|---|---|---|
| committer | Steve Ellcey <sellcey@caviumnetworks.com> | 2017-05-24 16:46:48 -0700 |
| commit | 6a2c695266fab34cc057256d1b33d2268183f00e (patch) | |
| tree | 320796a70561a5459b120bc2f99b4398dcc4970f /sysdeps/aarch64/memcpy.S | |
| parent | 6edbe546d6ac243a5e3c2610853f2da53f0507b4 (diff) | |
| download | glibc-6a2c695266fab34cc057256d1b33d2268183f00e.zip glibc-6a2c695266fab34cc057256d1b33d2268183f00e.tar.gz glibc-6a2c695266fab34cc057256d1b33d2268183f00e.tar.bz2 | |
aarch64: Thunderx specific memcpy and memmove
* sysdeps/aarch64/memcpy.S (MEMMOVE, MEMCPY): New macros.
(memmove): Use MEMMOVE for name.
(memcpy): Use MEMCPY for name. Change internal labels
to external labels.
* sysdeps/aarch64/multiarch/Makefile: New file.
* sysdeps/aarch64/multiarch/ifunc-impl-list.c: Likewise.
* sysdeps/aarch64/multiarch/init-arch.h: Likewise.
* sysdeps/aarch64/multiarch/memcpy.c: Likewise.
* sysdeps/aarch64/multiarch/memcpy_generic.S: Likewise.
* sysdeps/aarch64/multiarch/memcpy_thunderx.S: Likewise.
* sysdeps/aarch64/multiarch/memmove.c: Likewise.
Diffstat (limited to 'sysdeps/aarch64/memcpy.S')
| -rw-r--r-- | sysdeps/aarch64/memcpy.S | 27 |
1 files changed, 17 insertions, 10 deletions
diff --git a/sysdeps/aarch64/memcpy.S b/sysdeps/aarch64/memcpy.S index 29af8b1..88a3b90 100644 --- a/sysdeps/aarch64/memcpy.S +++ b/sysdeps/aarch64/memcpy.S @@ -59,7 +59,14 @@ Overlapping large forward memmoves use a loop that copies backwards. */ -ENTRY_ALIGN (memmove, 6) +#ifndef MEMMOVE +# define MEMMOVE memmove +#endif +#ifndef MEMCPY +# define MEMCPY memcpy +#endif + +ENTRY_ALIGN (MEMMOVE, 6) DELOUSE (0) DELOUSE (1) @@ -71,9 +78,9 @@ ENTRY_ALIGN (memmove, 6) b.lo L(move_long) /* Common case falls through into memcpy. */ -END (memmove) -libc_hidden_builtin_def (memmove) -ENTRY (memcpy) +END (MEMMOVE) +libc_hidden_builtin_def (MEMMOVE) +ENTRY (MEMCPY) DELOUSE (0) DELOUSE (1) @@ -169,8 +176,8 @@ L(copy_long): ldp C_l, C_h, [src, 48] ldp D_l, D_h, [src, 64]! subs count, count, 128 + 16 /* Test and readjust count. */ - b.ls 2f -1: + b.ls L(last64) +L(loop64): stp A_l, A_h, [dst, 16] ldp A_l, A_h, [src, 16] stp B_l, B_h, [dst, 32] @@ -180,12 +187,12 @@ L(copy_long): stp D_l, D_h, [dst, 64]! ldp D_l, D_h, [src, 64]! subs count, count, 64 - b.hi 1b + b.hi L(loop64) /* Write the last full set of 64 bytes. The remainder is at most 64 bytes, so it is safe to always copy 64 bytes from the end even if there is just 1 byte left. */ -2: +L(last64): ldp E_l, E_h, [srcend, -64] stp A_l, A_h, [dst, 16] ldp A_l, A_h, [srcend, -48] @@ -256,5 +263,5 @@ L(move_long): stp C_l, C_h, [dstin] 3: ret -END (memcpy) -libc_hidden_builtin_def (memcpy) +END (MEMCPY) +libc_hidden_builtin_def (MEMCPY) |