1/* $NetBSD: bcopy.S,v 1.1 2016/08/05 15:06:02 scole Exp $ */ 2 3/*- 4 * Copyright (c) 2000 Doug Rabson 5 * All rights reserved. 6 * 7 * Redistribution and use in source and binary forms, with or without 8 * modification, are permitted provided that the following conditions 9 * are met: 10 * 1. Redistributions of source code must retain the above copyright 11 * notice, this list of conditions and the following disclaimer. 12 * 2. Redistributions in binary form must reproduce the above copyright 13 * notice, this list of conditions and the following disclaimer in the 14 * documentation and/or other materials provided with the distribution. 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 * __FBSDID("$FreeBSD: releng/10.1/lib/libc/ia64/string/bcopy.S 125669 2004-02-10 20:45:28Z cperciva $"); 29 */ 30 31#include <machine/asm.h> 32 33/* 34 * void 35 * bcopy(const void *src, void *dst, size_t len); 36 */ 37 38/* 39 * Not the fastest bcopy in the world. 40 */ 41ENTRY(bcopy, 3) 42 43 cmp.le p6,p0=in2,r0 // bail if len <= 0 44(p6) br.ret.spnt.few rp 45 46 sub r14=in1,in0 ;; // check for overlap 47 cmp.ltu p6,p0=r14,in2 // dst-src < len 48(p6) br.cond.spnt.few 5f 49 50 extr.u r14=in0,0,3 // src & 7 51 extr.u r15=in1,0,3 ;; // dst & 7 52 cmp.eq p6,p0=r14,r15 // different alignment? 53(p6) br.cond.spnt.few 2f // branch if same alignment 54 551: ld1 r14=[in0],1 ;; // copy bytewise 56 st1 [in1]=r14,1 57 add in2=-1,in2 ;; // len-- 58 cmp.ne p6,p0=r0,in2 59(p6) br.cond.dptk.few 1b // loop 60 br.ret.sptk.few rp // done 61 622: cmp.eq p6,p0=r14,r0 // aligned? 63(p6) br.cond.sptk.few 4f 64 653: ld1 r14=[in0],1 ;; // copy bytewise 66 st1 [in1]=r14,1 67 extr.u r15=in0,0,3 // src & 7 68 add in2=-1,in2 ;; // len-- 69 cmp.eq p6,p0=r0,in2 // done? 70 cmp.eq p7,p0=r0,r15 ;; // aligned now? 71(p6) br.ret.spnt.few rp // return if done 72(p7) br.cond.spnt.few 4f // go to main copy 73 br.cond.sptk.few 3b // more bytes to copy 74 75 // At this point, in2 is non-zero 76 774: mov r14=8 ;; 78 cmp.ltu p6,p0=in2,r14 ;; // len < 8? 79(p6) br.cond.spnt.few 1b // byte copy the end 80 ld8 r15=[in0],8 ;; // copy word 81 st8 [in1]=r15,8 82 add in2=-8,in2 ;; // len -= 8 83 cmp.ne p6,p0=r0,in2 // done? 84(p6) br.cond.spnt.few 4b // again 85 86 br.ret.sptk.few rp // return 87 88 // Don't bother optimising overlap case 89 905: add in0=in0,in2 91 add in1=in1,in2 ;; 92 add in0=-1,in0 93 add in1=-1,in1 ;; 94 956: ld1 r14=[in0],-1 ;; 96 st1 [in1]=r14,-1 97 add in2=-1,in2 ;; 98 cmp.ne p6,p0=r0,in2 99(p6) br.cond.spnt.few 6b 100 101 br.ret.sptk.few rp 102END(bcopy) 103