diff options
Diffstat (limited to 'sysdeps/powerpc/powerpc64/power7/memmove.S')
| -rw-r--r-- | sysdeps/powerpc/powerpc64/power7/memmove.S | 139 |
1 files changed, 71 insertions, 68 deletions
diff --git a/sysdeps/powerpc/powerpc64/power7/memmove.S b/sysdeps/powerpc/powerpc64/power7/memmove.S index e263ba9608..b7f3dc28d1 100644 --- a/sysdeps/powerpc/powerpc64/power7/memmove.S +++ b/sysdeps/powerpc/powerpc64/power7/memmove.S @@ -1,5 +1,5 @@ /* Optimized memmove implementation for PowerPC64/POWER7. - Copyright (C) 2014-2016 Free Software Foundation, Inc. + Copyright (C) 2014-2018 Free Software Foundation, Inc. This file is part of the GNU C Library. The GNU C Library is free software; you can redistribute it and/or @@ -27,8 +27,11 @@ If source and destiny overlaps, a optimized backwards memcpy is used instead. */ +#ifndef MEMMOVE +# define MEMMOVE memmove +#endif .machine power7 -EALIGN (memmove, 5, 0) +ENTRY_TOCLESS (MEMMOVE, 5) CALL_MCOUNT 3 L(_memmove): @@ -89,63 +92,63 @@ L(aligned_copy): srdi 12,r5,7 cmpdi 12,0 beq L(aligned_tail) - lxvd2x 6,0,r4 - lxvd2x 7,r4,6 + lvx 6,0,r4 + lvx 7,r4,6 mtctr 12 b L(aligned_128loop) .align 4 L(aligned_128head): /* for the 2nd + iteration of this loop. */ - lxvd2x 6,0,r4 - lxvd2x 7,r4,6 + lvx 6,0,r4 + lvx 7,r4,6 L(aligned_128loop): - lxvd2x 8,r4,7 - lxvd2x 9,r4,8 - stxvd2x 6,0,r11 + lvx 8,r4,7 + lvx 9,r4,8 + stvx 6,0,r11 addi r4,r4,64 - stxvd2x 7,r11,6 - stxvd2x 8,r11,7 - stxvd2x 9,r11,8 - lxvd2x 6,0,r4 - lxvd2x 7,r4,6 + stvx 7,r11,6 + stvx 8,r11,7 + stvx 9,r11,8 + lvx 6,0,r4 + lvx 7,r4,6 addi r11,r11,64 - lxvd2x 8,r4,7 - lxvd2x 9,r4,8 + lvx 8,r4,7 + lvx 9,r4,8 addi r4,r4,64 - stxvd2x 6,0,r11 - stxvd2x 7,r11,6 - stxvd2x 8,r11,7 - stxvd2x 9,r11,8 + stvx 6,0,r11 + stvx 7,r11,6 + stvx 8,r11,7 + stvx 9,r11,8 addi r11,r11,64 bdnz L(aligned_128head) L(aligned_tail): mtocrf 0x01,r5 bf 25,32f - lxvd2x 6,0,r4 - lxvd2x 7,r4,6 - lxvd2x 8,r4,7 - lxvd2x 9,r4,8 + lvx 6,0,r4 + lvx 7,r4,6 + lvx 8,r4,7 + lvx 9,r4,8 addi r4,r4,64 - stxvd2x 6,0,r11 - stxvd2x 7,r11,6 - stxvd2x 8,r11,7 - stxvd2x 9,r11,8 + stvx 6,0,r11 + stvx 7,r11,6 + stvx 8,r11,7 + stvx 9,r11,8 addi r11,r11,64 32: bf 26,16f - lxvd2x 6,0,r4 - lxvd2x 7,r4,6 + lvx 6,0,r4 + lvx 7,r4,6 addi r4,r4,32 - stxvd2x 6,0,r11 - stxvd2x 7,r11,6 + stvx 6,0,r11 + stvx 7,r11,6 addi r11,r11,32 16: bf 27,8f - lxvd2x 6,0,r4 + lvx 6,0,r4 addi r4,r4,16 - stxvd2x 6,0,r11 + stvx 6,0,r11 addi r11,r11,16 8: bf 28,4f @@ -485,63 +488,63 @@ L(aligned_copy_bwd): srdi r12,r5,7 cmpdi r12,0 beq L(aligned_tail_bwd) - lxvd2x v6,r4,r6 - lxvd2x v7,r4,r7 + lvx v6,r4,r6 + lvx v7,r4,r7 mtctr 12 b L(aligned_128loop_bwd) .align 4 L(aligned_128head_bwd): /* for the 2nd + iteration of this loop. */ - lxvd2x v6,r4,r6 - lxvd2x v7,r4,r7 + lvx v6,r4,r6 + lvx v7,r4,r7 L(aligned_128loop_bwd): - lxvd2x v8,r4,r8 - lxvd2x v9,r4,r9 - stxvd2x v6,r11,r6 + lvx v8,r4,r8 + lvx v9,r4,r9 + stvx v6,r11,r6 subi r4,r4,64 - stxvd2x v7,r11,r7 - stxvd2x v8,r11,r8 - stxvd2x v9,r11,r9 - lxvd2x v6,r4,r6 - lxvd2x v7,r4,7 + stvx v7,r11,r7 + stvx v8,r11,r8 + stvx v9,r11,r9 + lvx v6,r4,r6 + lvx v7,r4,7 subi r11,r11,64 - lxvd2x v8,r4,r8 - lxvd2x v9,r4,r9 + lvx v8,r4,r8 + lvx v9,r4,r9 subi r4,r4,64 - stxvd2x v6,r11,r6 - stxvd2x v7,r11,r7 - stxvd2x v8,r11,r8 - stxvd2x v9,r11,r9 + stvx v6,r11,r6 + stvx v7,r11,r7 + stvx v8,r11,r8 + stvx v9,r11,r9 subi r11,r11,64 bdnz L(aligned_128head_bwd) L(aligned_tail_bwd): mtocrf 0x01,r5 bf 25,32f - lxvd2x v6,r4,r6 - lxvd2x v7,r4,r7 - lxvd2x v8,r4,r8 - lxvd2x v9,r4,r9 + lvx v6,r4,r6 + lvx v7,r4,r7 + lvx v8,r4,r8 + lvx v9,r4,r9 subi r4,r4,64 - stxvd2x v6,r11,r6 - stxvd2x v7,r11,r7 - stxvd2x v8,r11,r8 - stxvd2x v9,r11,r9 + stvx v6,r11,r6 + stvx v7,r11,r7 + stvx v8,r11,r8 + stvx v9,r11,r9 subi r11,r11,64 32: bf 26,16f - lxvd2x v6,r4,r6 - lxvd2x v7,r4,r7 + lvx v6,r4,r6 + lvx v7,r4,r7 subi r4,r4,32 - stxvd2x v6,r11,r6 - stxvd2x v7,r11,r7 + stvx v6,r11,r6 + stvx v7,r11,r7 subi r11,r11,32 16: bf 27,8f - lxvd2x v6,r4,r6 + lvx v6,r4,r6 subi r4,r4,16 - stxvd2x v6,r11,r6 + stvx v6,r11,r6 subi r11,r11,16 8: bf 28,4f @@ -816,14 +819,14 @@ L(end_unaligned_loop_bwd): stb r8,-7(r11) /* Return original DST pointer. */ blr -END_GEN_TB (memmove, TB_TOCLESS) +END_GEN_TB (MEMMOVE, TB_TOCLESS) libc_hidden_builtin_def (memmove) /* void bcopy(const void *src [r3], void *dest [r4], size_t n [r5]) Implemented in this file to avoid linker create a stub function call in the branch to '_memmove'. */ -ENTRY (__bcopy) +ENTRY_TOCLESS (__bcopy) mr r6,r3 mr r3,r4 mr r4,r6 |