/* Optimized memcpy implementation for PowerPC64/POWER7.
- Copyright (C) 2010-2017 Free Software Foundation, Inc.
+ Copyright (C) 2010-2019 Free Software Foundation, Inc.
Contributed by Luis Machado <luisgpm@br.ibm.com>.
This file is part of the GNU C Library.
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