1/*- 2 * Copyright (c) 2018 Instituto de Pesquisas Eldorado 3 * All rights reserved. 4 * 5 * Redistribution and use in source and binary forms, with or without 6 * modification, are permitted provided that the following conditions 7 * are met: 8 * 1. Redistributions of source code must retain the above copyright 9 * notice, this list of conditions and the following disclaimer. 10 * 2. Redistributions in binary form must reproduce the above copyright 11 * notice, this list of conditions and the following disclaimer in the 12 * documentation and/or other materials provided with the distribution. 13 * 3. Neither the name of the author nor the names of its contributors may 14 * be used to endorse or promote products derived from this software 15 * 16 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 17 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 18 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 19 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 20 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 21 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 22 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 23 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 24 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 25 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 26 * SUCH DAMAGE. 27 */ 28 29#define FN_NAME __memcpy_vsx 30#define BLOCK_BITS 6 31#define ALIGN_MASK 0xf 32 33/* 34 * r5: bytes to copy (multiple of BLOCK_BYTES) 35 * 36 */ 37#define FN_COPY_LOOP \ 38 /* Load CTR with number of blocks */ \ 39 srdi %r5, %r5, BLOCK_BITS ;\ 40 mtctr %r5 ;\ 41 /* Prepare indexes to load and store data */ \ 42 xor %r6, %r6, %r6 ;\ 43 li %r9, 16 ;\ 44 li %r10, 32 ;\ 45 li %r11, 48 ;\ 46.Lcopy_vsx_loop: \ 47 lxvd2x %vs6, %r6, %r4 ;\ 48 lxvd2x %vs7, %r9, %r4 ;\ 49 lxvd2x %vs8, %r10, %r4 ;\ 50 lxvd2x %vs9, %r11, %r4 ;\ 51 stxvd2x %vs6, %r6, %r3 ;\ 52 stxvd2x %vs7, %r9, %r3 ;\ 53 stxvd2x %vs8, %r10, %r3 ;\ 54 stxvd2x %vs9, %r11, %r3 ;\ 55 \ 56 addi %r3, %r3, BLOCK_BYTES ;\ 57 addi %r4, %r4, BLOCK_BYTES ;\ 58 bdnz .Lcopy_vsx_loop ;\ 59 \ 60 /* Check if there is remaining bytes */ \ 61 cmpd %r7, 0 ;\ 62 beq .Lexit ;\ 63 64#include "memcpy.S" 65