1/* 2 * Copyright © 2013 Intel Corporation 3 * 4 * Permission is hereby granted, free of charge, to any person obtaining a 5 * copy of this software and associated documentation files (the "Software"), 6 * to deal in the Software without restriction, including without limitation 7 * the rights to use, copy, modify, merge, publish, distribute, sublicense, 8 * and/or sell copies of the Software, and to permit persons to whom the 9 * Software is furnished to do so, subject to the following conditions: 10 * 11 * The above copyright notice and this permission notice (including the next 12 * paragraph) shall be included in all copies or substantial portions of the 13 * Software. 14 * 15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS 21 * IN THE SOFTWARE. 22 * 23 * Authors: 24 * Eric Anholt <eric@anholt.net> 25 * Matt Turner <mattst88@gmail.com> 26 * 27 */ 28 29#include "main/macros.h" 30#include "util/streaming-load-memcpy.h" 31#include "x86/common_x86_asm.h" 32#ifdef USE_SSE41 33#include <smmintrin.h> 34#endif 35 36/* Copies memory from src to dst, using SSE 4.1's MOVNTDQA to get streaming 37 * read performance from uncached memory. 38 */ 39void 40util_streaming_load_memcpy(void *restrict dst, void *restrict src, size_t len) 41{ 42 char *restrict d = dst; 43 char *restrict s = src; 44 45#ifdef USE_SSE41 46 /* If dst and src are not co-aligned, or if SSE4.1 is not present, fallback to memcpy(). */ 47 if (((uintptr_t)d & 15) != ((uintptr_t)s & 15) || !cpu_has_sse4_1) { 48 memcpy(d, s, len); 49 return; 50 } 51 52 /* memcpy() the misaligned header. At the end of this if block, <d> and <s> 53 * are aligned to a 16-byte boundary or <len> == 0. 54 */ 55 if ((uintptr_t)d & 15) { 56 uintptr_t bytes_before_alignment_boundary = 16 - ((uintptr_t)d & 15); 57 assert(bytes_before_alignment_boundary < 16); 58 59 memcpy(d, s, MIN2(bytes_before_alignment_boundary, len)); 60 61 d = (char *)ALIGN((uintptr_t)d, 16); 62 s = (char *)ALIGN((uintptr_t)s, 16); 63 len -= MIN2(bytes_before_alignment_boundary, len); 64 } 65 66 if (len >= 64) 67 _mm_mfence(); 68 69 while (len >= 64) { 70 __m128i *dst_cacheline = (__m128i *)d; 71 __m128i *src_cacheline = (__m128i *)s; 72 73 __m128i temp1 = _mm_stream_load_si128(src_cacheline + 0); 74 __m128i temp2 = _mm_stream_load_si128(src_cacheline + 1); 75 __m128i temp3 = _mm_stream_load_si128(src_cacheline + 2); 76 __m128i temp4 = _mm_stream_load_si128(src_cacheline + 3); 77 78 _mm_store_si128(dst_cacheline + 0, temp1); 79 _mm_store_si128(dst_cacheline + 1, temp2); 80 _mm_store_si128(dst_cacheline + 2, temp3); 81 _mm_store_si128(dst_cacheline + 3, temp4); 82 83 d += 64; 84 s += 64; 85 len -= 64; 86 } 87#endif 88 /* memcpy() the tail. */ 89 if (len) { 90 memcpy(d, s, len); 91 } 92} 93