diff options
Diffstat (limited to 'sysdeps/powerpc/powerpc64/power7/memcpy.S')
| -rw-r--r-- | sysdeps/powerpc/powerpc64/power7/memcpy.S | 76 |
1 files changed, 40 insertions, 36 deletions
diff --git a/sysdeps/powerpc/powerpc64/power7/memcpy.S b/sysdeps/powerpc/powerpc64/power7/memcpy.S index 6bb5f13257..3d8629ca65 100644 --- a/sysdeps/powerpc/powerpc64/power7/memcpy.S +++ b/sysdeps/powerpc/powerpc64/power7/memcpy.S @@ -1,5 +1,5 @@ /* Optimized memcpy implementation for PowerPC64/POWER7. - Copyright (C) 2010-2016 Free Software Foundation, Inc. + Copyright (C) 2010-2018 Free Software Foundation, Inc. Contributed by Luis Machado <luisgpm@br.ibm.com>. This file is part of the GNU C Library. @@ -20,15 +20,19 @@ #include <sysdep.h> -/* __ptr_t [r3] memcpy (__ptr_t dst [r3], __ptr_t src [r4], size_t len [r5]); +/* void * [r3] memcpy (void *dst [r3], void *src [r4], size_t len [r5]); Returns 'dst'. */ +#ifndef MEMCPY +# define MEMCPY memcpy +#endif + #define dst 11 /* Use r11 so r3 kept unchanged. */ #define src 4 #define cnt 5 .machine power7 -EALIGN (memcpy, 5, 0) +ENTRY_TOCLESS (MEMCPY, 5) CALL_MCOUNT 3 cmpldi cr1,cnt,31 @@ -87,63 +91,63 @@ L(aligned_copy): srdi 12,cnt,7 cmpdi 12,0 beq L(aligned_tail) - lxvd2x 6,0,src - lxvd2x 7,src,6 + lvx 6,0,src + lvx 7,src,6 mtctr 12 b L(aligned_128loop) .align 4 L(aligned_128head): /* for the 2nd + iteration of this loop. */ - lxvd2x 6,0,src - lxvd2x 7,src,6 + lvx 6,0,src + lvx 7,src,6 L(aligned_128loop): - lxvd2x 8,src,7 - lxvd2x 9,src,8 - stxvd2x 6,0,dst + lvx 8,src,7 + lvx 9,src,8 + stvx 6,0,dst addi src,src,64 - stxvd2x 7,dst,6 - stxvd2x 8,dst,7 - stxvd2x 9,dst,8 - lxvd2x 6,0,src - lxvd2x 7,src,6 + stvx 7,dst,6 + stvx 8,dst,7 + stvx 9,dst,8 + lvx 6,0,src + lvx 7,src,6 addi dst,dst,64 - lxvd2x 8,src,7 - lxvd2x 9,src,8 + lvx 8,src,7 + lvx 9,src,8 addi src,src,64 - stxvd2x 6,0,dst - stxvd2x 7,dst,6 - stxvd2x 8,dst,7 - stxvd2x 9,dst,8 + stvx 6,0,dst + stvx 7,dst,6 + stvx 8,dst,7 + stvx 9,dst,8 addi dst,dst,64 bdnz L(aligned_128head) L(aligned_tail): mtocrf 0x01,cnt bf 25,32f - lxvd2x 6,0,src - lxvd2x 7,src,6 - lxvd2x 8,src,7 - lxvd2x 9,src,8 + lvx 6,0,src + lvx 7,src,6 + lvx 8,src,7 + lvx 9,src,8 addi src,src,64 - stxvd2x 6,0,dst - stxvd2x 7,dst,6 - stxvd2x 8,dst,7 - stxvd2x 9,dst,8 + stvx 6,0,dst + stvx 7,dst,6 + stvx 8,dst,7 + stvx 9,dst,8 addi dst,dst,64 32: bf 26,16f - lxvd2x 6,0,src - lxvd2x 7,src,6 + lvx 6,0,src + lvx 7,src,6 addi src,src,32 - stxvd2x 6,0,dst - stxvd2x 7,dst,6 + stvx 6,0,dst + stvx 7,dst,6 addi dst,dst,32 16: bf 27,8f - lxvd2x 6,0,src + lvx 6,0,src addi src,src,16 - stxvd2x 6,0,dst + stvx 6,0,dst addi dst,dst,16 8: bf 28,4f @@ -422,5 +426,5 @@ L(end_unaligned_loop): /* Return original DST pointer. */ blr -END_GEN_TB (memcpy,TB_TOCLESS) +END_GEN_TB (MEMCPY,TB_TOCLESS) libc_hidden_builtin_def (memcpy) |