[AArch64] Improve integer memcpy
Further optimize integer memcpy. Small cases now include copies up to 32 bytes. 64-128 byte copies are split into two cases to improve performance of 64-96 byte copies. Comments have been rewritten. (cherry picked from commit 700065132744e0dfa6d4d9142d63f6e3a1934726)
This commit is contained in:
Wilco Dijkstra
parent
c969e84e0c
commit
be3eaffd5a
|
|
@ -33,11 +33,11 @@
|
|||
#define A_l x6
|
||||
#define A_lw w6
|
||||
#define A_h x7
|
||||
#define A_hw w7
|
||||
#define B_l x8
|
||||
#define B_lw w8
|
||||
#define B_h x9
|
||||
#define C_l x10
|
||||
#define C_lw w10
|
||||
#define C_h x11
|
||||
#define D_l x12
|
||||
#define D_h x13
|
||||
|
|
@ -51,16 +51,6 @@
|
|||
#define H_h srcend
|
||||
#define tmp1 x14
|
||||
|
||||
/* Copies are split into 3 main cases: small copies of up to 32 bytes,
|
||||
medium copies of 33..128 bytes which are fully unrolled. Large copies
|
||||
of more than 128 bytes align the destination and use an unrolled loop
|
||||
processing 64 bytes per iteration.
|
||||
In order to share code with memmove, small and medium copies read all
|
||||
data before writing, allowing any kind of overlap. So small, medium
|
||||
and large backwards memmoves are handled by falling through into memcpy.
|
||||
Overlapping large forward memmoves use a loop that copies backwards.
|
||||
*/
|
||||
|
||||
#ifndef MEMMOVE
|
||||
# define MEMMOVE memmove
|
||||
#endif
|
||||
|
|
@ -68,35 +58,76 @@
|
|||
# define MEMCPY memcpy
|
||||
#endif
|
||||
|
||||
ENTRY_ALIGN (MEMMOVE, 6)
|
||||
/* This implementation supports both memcpy and memmove and shares most code.
|
||||
It uses unaligned accesses and branchless sequences to keep the code small,
|
||||
simple and improve performance.
|
||||
|
||||
Copies are split into 3 main cases: small copies of up to 32 bytes, medium
|
||||
copies of up to 128 bytes, and large copies. The overhead of the overlap
|
||||
check in memmove is negligible since it is only required for large copies.
|
||||
|
||||
Large copies use a software pipelined loop processing 64 bytes per
|
||||
iteration. The destination pointer is 16-byte aligned to minimize
|
||||
unaligned accesses. The loop tail is handled by always copying 64 bytes
|
||||
from the end.
|
||||
*/
|
||||
|
||||
ENTRY_ALIGN (MEMCPY, 6)
|
||||
DELOUSE (0)
|
||||
DELOUSE (1)
|
||||
DELOUSE (2)
|
||||
|
||||
sub tmp1, dstin, src
|
||||
cmp count, 128
|
||||
ccmp tmp1, count, 2, hi
|
||||
b.lo L(move_long)
|
||||
|
||||
/* Common case falls through into memcpy. */
|
||||
END (MEMMOVE)
|
||||
libc_hidden_builtin_def (MEMMOVE)
|
||||
ENTRY (MEMCPY)
|
||||
|
||||
DELOUSE (0)
|
||||
DELOUSE (1)
|
||||
DELOUSE (2)
|
||||
|
||||
prfm PLDL1KEEP, [src]
|
||||
add srcend, src, count
|
||||
add dstend, dstin, count
|
||||
cmp count, 32
|
||||
b.ls L(copy32)
|
||||
cmp count, 128
|
||||
b.hi L(copy_long)
|
||||
cmp count, 32
|
||||
b.hi L(copy32_128)
|
||||
|
||||
/* Small copies: 0..32 bytes. */
|
||||
cmp count, 16
|
||||
b.lo L(copy16)
|
||||
ldp A_l, A_h, [src]
|
||||
ldp D_l, D_h, [srcend, -16]
|
||||
stp A_l, A_h, [dstin]
|
||||
stp D_l, D_h, [dstend, -16]
|
||||
ret
|
||||
|
||||
/* Copy 8-15 bytes. */
|
||||
L(copy16):
|
||||
tbz count, 3, L(copy8)
|
||||
ldr A_l, [src]
|
||||
ldr A_h, [srcend, -8]
|
||||
str A_l, [dstin]
|
||||
str A_h, [dstend, -8]
|
||||
ret
|
||||
|
||||
.p2align 3
|
||||
/* Copy 4-7 bytes. */
|
||||
L(copy8):
|
||||
tbz count, 2, L(copy4)
|
||||
ldr A_lw, [src]
|
||||
ldr B_lw, [srcend, -4]
|
||||
str A_lw, [dstin]
|
||||
str B_lw, [dstend, -4]
|
||||
ret
|
||||
|
||||
/* Copy 0..3 bytes using a branchless sequence. */
|
||||
L(copy4):
|
||||
cbz count, L(copy0)
|
||||
lsr tmp1, count, 1
|
||||
ldrb A_lw, [src]
|
||||
ldrb C_lw, [srcend, -1]
|
||||
ldrb B_lw, [src, tmp1]
|
||||
strb A_lw, [dstin]
|
||||
strb B_lw, [dstin, tmp1]
|
||||
strb C_lw, [dstend, -1]
|
||||
L(copy0):
|
||||
ret
|
||||
|
||||
.p2align 4
|
||||
/* Medium copies: 33..128 bytes. */
|
||||
L(copy32_128):
|
||||
ldp A_l, A_h, [src]
|
||||
ldp B_l, B_h, [src, 16]
|
||||
ldp C_l, C_h, [srcend, -32]
|
||||
|
|
@ -110,76 +141,32 @@ ENTRY (MEMCPY)
|
|||
ret
|
||||
|
||||
.p2align 4
|
||||
/* Small copies: 0..32 bytes. */
|
||||
L(copy32):
|
||||
/* 16-32 bytes. */
|
||||
cmp count, 16
|
||||
b.lo 1f
|
||||
ldp A_l, A_h, [src]
|
||||
ldp B_l, B_h, [srcend, -16]
|
||||
stp A_l, A_h, [dstin]
|
||||
stp B_l, B_h, [dstend, -16]
|
||||
ret
|
||||
.p2align 4
|
||||
1:
|
||||
/* 8-15 bytes. */
|
||||
tbz count, 3, 1f
|
||||
ldr A_l, [src]
|
||||
ldr A_h, [srcend, -8]
|
||||
str A_l, [dstin]
|
||||
str A_h, [dstend, -8]
|
||||
ret
|
||||
.p2align 4
|
||||
1:
|
||||
/* 4-7 bytes. */
|
||||
tbz count, 2, 1f
|
||||
ldr A_lw, [src]
|
||||
ldr A_hw, [srcend, -4]
|
||||
str A_lw, [dstin]
|
||||
str A_hw, [dstend, -4]
|
||||
ret
|
||||
|
||||
/* Copy 0..3 bytes. Use a branchless sequence that copies the same
|
||||
byte 3 times if count==1, or the 2nd byte twice if count==2. */
|
||||
1:
|
||||
cbz count, 2f
|
||||
lsr tmp1, count, 1
|
||||
ldrb A_lw, [src]
|
||||
ldrb A_hw, [srcend, -1]
|
||||
ldrb B_lw, [src, tmp1]
|
||||
strb A_lw, [dstin]
|
||||
strb B_lw, [dstin, tmp1]
|
||||
strb A_hw, [dstend, -1]
|
||||
2: ret
|
||||
|
||||
.p2align 4
|
||||
/* Copy 65..128 bytes. Copy 64 bytes from the start and
|
||||
64 bytes from the end. */
|
||||
/* Copy 65..128 bytes. */
|
||||
L(copy128):
|
||||
ldp E_l, E_h, [src, 32]
|
||||
ldp F_l, F_h, [src, 48]
|
||||
cmp count, 96
|
||||
b.ls L(copy96)
|
||||
ldp G_l, G_h, [srcend, -64]
|
||||
ldp H_l, H_h, [srcend, -48]
|
||||
stp G_l, G_h, [dstend, -64]
|
||||
stp H_l, H_h, [dstend, -48]
|
||||
L(copy96):
|
||||
stp A_l, A_h, [dstin]
|
||||
stp B_l, B_h, [dstin, 16]
|
||||
stp E_l, E_h, [dstin, 32]
|
||||
stp F_l, F_h, [dstin, 48]
|
||||
stp G_l, G_h, [dstend, -64]
|
||||
stp H_l, H_h, [dstend, -48]
|
||||
stp C_l, C_h, [dstend, -32]
|
||||
stp D_l, D_h, [dstend, -16]
|
||||
ret
|
||||
|
||||
/* Align DST to 16 byte alignment so that we don't cross cache line
|
||||
boundaries on both loads and stores. There are at least 128 bytes
|
||||
to copy, so copy 16 bytes unaligned and then align. The loop
|
||||
copies 64 bytes per iteration and prefetches one iteration ahead. */
|
||||
|
||||
.p2align 4
|
||||
/* Copy more than 128 bytes. */
|
||||
L(copy_long):
|
||||
/* Copy 16 bytes and then align dst to 16-byte alignment. */
|
||||
ldp D_l, D_h, [src]
|
||||
and tmp1, dstin, 15
|
||||
bic dst, dstin, 15
|
||||
ldp D_l, D_h, [src]
|
||||
sub src, src, tmp1
|
||||
add count, count, tmp1 /* Count is now 16 too large. */
|
||||
ldp A_l, A_h, [src, 16]
|
||||
|
|
@ -188,7 +175,8 @@ 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 L(last64)
|
||||
b.ls L(copy64_from_end)
|
||||
|
||||
L(loop64):
|
||||
stp A_l, A_h, [dst, 16]
|
||||
ldp A_l, A_h, [src, 16]
|
||||
|
|
@ -201,10 +189,8 @@ L(loop64):
|
|||
subs count, count, 64
|
||||
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. */
|
||||
L(last64):
|
||||
/* Write the last iteration and copy 64 bytes from the end. */
|
||||
L(copy64_from_end):
|
||||
ldp E_l, E_h, [srcend, -64]
|
||||
stp A_l, A_h, [dst, 16]
|
||||
ldp A_l, A_h, [srcend, -48]
|
||||
|
|
@ -219,20 +205,42 @@ L(last64):
|
|||
stp C_l, C_h, [dstend, -16]
|
||||
ret
|
||||
|
||||
.p2align 4
|
||||
L(move_long):
|
||||
cbz tmp1, 3f
|
||||
END (MEMCPY)
|
||||
libc_hidden_builtin_def (MEMCPY)
|
||||
|
||||
ENTRY_ALIGN (MEMMOVE, 4)
|
||||
DELOUSE (0)
|
||||
DELOUSE (1)
|
||||
DELOUSE (2)
|
||||
|
||||
add srcend, src, count
|
||||
add dstend, dstin, count
|
||||
cmp count, 128
|
||||
b.hi L(move_long)
|
||||
cmp count, 32
|
||||
b.hi L(copy32_128)
|
||||
|
||||
/* Align dstend to 16 byte alignment so that we don't cross cache line
|
||||
boundaries on both loads and stores. There are at least 128 bytes
|
||||
to copy, so copy 16 bytes unaligned and then align. The loop
|
||||
copies 64 bytes per iteration and prefetches one iteration ahead. */
|
||||
|
||||
and tmp1, dstend, 15
|
||||
/* Small copies: 0..32 bytes. */
|
||||
cmp count, 16
|
||||
b.lo L(copy16)
|
||||
ldp A_l, A_h, [src]
|
||||
ldp D_l, D_h, [srcend, -16]
|
||||
stp A_l, A_h, [dstin]
|
||||
stp D_l, D_h, [dstend, -16]
|
||||
ret
|
||||
|
||||
.p2align 4
|
||||
L(move_long):
|
||||
/* Only use backward copy if there is an overlap. */
|
||||
sub tmp1, dstin, src
|
||||
cbz tmp1, L(copy0)
|
||||
cmp tmp1, count
|
||||
b.hs L(copy_long)
|
||||
|
||||
/* Large backwards copy for overlapping copies.
|
||||
Copy 16 bytes and then align dst to 16-byte alignment. */
|
||||
ldp D_l, D_h, [srcend, -16]
|
||||
and tmp1, dstend, 15
|
||||
sub srcend, srcend, tmp1
|
||||
sub count, count, tmp1
|
||||
ldp A_l, A_h, [srcend, -16]
|
||||
|
|
@ -242,10 +250,9 @@ L(move_long):
|
|||
ldp D_l, D_h, [srcend, -64]!
|
||||
sub dstend, dstend, tmp1
|
||||
subs count, count, 128
|
||||
b.ls 2f
|
||||
b.ls L(copy64_from_start)
|
||||
|
||||
nop
|
||||
1:
|
||||
L(loop64_backwards):
|
||||
stp A_l, A_h, [dstend, -16]
|
||||
ldp A_l, A_h, [srcend, -16]
|
||||
stp B_l, B_h, [dstend, -32]
|
||||
|
|
@ -255,12 +262,10 @@ L(move_long):
|
|||
stp D_l, D_h, [dstend, -64]!
|
||||
ldp D_l, D_h, [srcend, -64]!
|
||||
subs count, count, 64
|
||||
b.hi 1b
|
||||
b.hi L(loop64_backwards)
|
||||
|
||||
/* 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 start even if
|
||||
there is just 1 byte left. */
|
||||
2:
|
||||
/* Write the last iteration and copy 64 bytes from the start. */
|
||||
L(copy64_from_start):
|
||||
ldp G_l, G_h, [src, 48]
|
||||
stp A_l, A_h, [dstend, -16]
|
||||
ldp A_l, A_h, [src, 32]
|
||||
|
|
@ -273,7 +278,7 @@ L(move_long):
|
|||
stp A_l, A_h, [dstin, 32]
|
||||
stp B_l, B_h, [dstin, 16]
|
||||
stp C_l, C_h, [dstin]
|
||||
3: ret
|
||||
ret
|
||||
|
||||
END (MEMCPY)
|
||||
libc_hidden_builtin_def (MEMCPY)
|
||||
END (MEMMOVE)
|
||||
libc_hidden_builtin_def (MEMMOVE)
|
||||
|
|
|
|||
Loading…
Reference in New Issue