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#ifndef FN_NAME 30#define FN_NAME __bcopy_vsx 31#endif 32 33/* 34 * r3: dst 35 * r4: src 36 * r5: block increment 37 * r6: blocks to copy 38 * r7/r8/r9/r10: 16-byte offsets to copy 39 */ 40 41#define FN_PHASE2 \ 42 mtctr %r6 ;\ 43 .align 5 ;\ 44.Lphase2_loop: ;\ 45 lxvd2x %vs6, %r7, %r4 ;\ 46 lxvd2x %vs7, %r8, %r4 ;\ 47 lxvd2x %vs8, %r9, %r4 ;\ 48 lxvd2x %vs9, %r10, %r4 ;\ 49 stxvd2x %vs6, %r7, %r3 ;\ 50 stxvd2x %vs7, %r8, %r3 ;\ 51 stxvd2x %vs8, %r9, %r3 ;\ 52 stxvd2x %vs9, %r10, %r3 ;\ 53 /* phase 2 increment */ ;\ 54 add %r4, %r4, %r5 ;\ 55 add %r3, %r3, %r5 ;\ 56 \ 57 bdnz .Lphase2_loop ;\ 58 59#include "bcopy.S" 60