source: trunk/libs/newlib/src/newlib/libc/machine/aarch64/memmove.S @ 444

/* Copyright (c) 2013, Linaro Limited
   All rights reserved.

   Redistribution and use in source and binary forms, with or without
   modification, are permitted provided that the following conditions are met:
       * Redistributions of source code must retain the above copyright
         notice, this list of conditions and the following disclaimer.
       * Redistributions in binary form must reproduce the above copyright
         notice, this list of conditions and the following disclaimer in the
         documentation and/or other materials provided with the distribution.
       * Neither the name of the Linaro nor the
         names of its contributors may be used to endorse or promote products
         derived from this software without specific prior written permission.

   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
   HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */

/*
 * Copyright (c) 2015 ARM Ltd
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. The name of the company may not be used to endorse or promote
 *    products derived from this software without specific prior written
 *    permission.
 *
 * THIS SOFTWARE IS PROVIDED BY ARM LTD ``AS IS'' AND ANY EXPRESS OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
 * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
 * IN NO EVENT SHALL ARM LTD BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
 * TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

/* Assumptions:
 *
 * ARMv8-a, AArch64, unaligned accesses
 */

#if (defined (__OPTIMIZE_SIZE__) || defined (PREFER_SIZE_OVER_SPEED))
/* See memmove-stub.c  */
#else

        .macro def_fn f p2align=0
        .text
        .p2align \p2align
        .global \f
        .type \f, %function
\f:
        .endm

/* Parameters and result.  */
#define dstin   x0
#define src     x1
#define count   x2
#define srcend  x3
#define dstend  x4
#define tmp1    x5
#define A_l     x6
#define A_h     x7
#define B_l     x8
#define B_h     x9
#define C_l     x10
#define C_h     x11
#define D_l     x12
#define D_h     x13
#define E_l     count
#define E_h     tmp1

/* All memmoves up to 96 bytes are done by memcpy as it supports overlaps.
   Larger backwards copies are also handled by memcpy. The only remaining
   case is forward large copies.  The destination is aligned, and an
   unrolled loop processes 64 bytes per iteration.
*/

def_fn memmove, 6
        sub     tmp1, dstin, src
        cmp     count, 96
        ccmp    tmp1, count, 2, hi
        b.hs    memcpy

        cbz     tmp1, 3f
        add     dstend, dstin, count
        add     srcend, src, count

        /* Align dstend to 16 byte alignment so that we don't cross cache line
           boundaries on both loads and stores.  There are at least 96 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
        ldp     D_l, D_h, [srcend, -16]
        sub     srcend, srcend, tmp1
        sub     count, count, tmp1
        ldp     A_l, A_h, [srcend, -16]
        stp     D_l, D_h, [dstend, -16]
        ldp     B_l, B_h, [srcend, -32]
        ldp     C_l, C_h, [srcend, -48]
        ldp     D_l, D_h, [srcend, -64]!
        sub     dstend, dstend, tmp1
        subs    count, count, 128
        b.ls    2f
        nop
1:
        stp     A_l, A_h, [dstend, -16]
        ldp     A_l, A_h, [srcend, -16]
        stp     B_l, B_h, [dstend, -32]
        ldp     B_l, B_h, [srcend, -32]
        stp     C_l, C_h, [dstend, -48]
        ldp     C_l, C_h, [srcend, -48]
        stp     D_l, D_h, [dstend, -64]!
        ldp     D_l, D_h, [srcend, -64]!
        subs    count, count, 64
        b.hi    1b

        /* 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:
        ldp     E_l, E_h, [src, 48]
        stp     A_l, A_h, [dstend, -16]
        ldp     A_l, A_h, [src, 32]
        stp     B_l, B_h, [dstend, -32]
        ldp     B_l, B_h, [src, 16]
        stp     C_l, C_h, [dstend, -48]
        ldp     C_l, C_h, [src]
        stp     D_l, D_h, [dstend, -64]
        stp     E_l, E_h, [dstin, 48]
        stp     A_l, A_h, [dstin, 32]
        stp     B_l, B_h, [dstin, 16]
        stp     C_l, C_h, [dstin]
3:      ret

        .size   memmove, . - memmove
#endif