| 1 | /* |
| 2 | * Copyright (c) 2016, Intel Corporation |
| 3 | * |
| 4 | * Redistribution and use in source and binary forms, with or without |
| 5 | * modification, are permitted provided that the following conditions are met: |
| 6 | * |
| 7 | * * Redistributions of source code must retain the above copyright notice, |
| 8 | * this list of conditions and the following disclaimer. |
| 9 | * * Redistributions in binary form must reproduce the above copyright |
| 10 | * notice, this list of conditions and the following disclaimer in the |
| 11 | * documentation and/or other materials provided with the distribution. |
| 12 | * * Neither the name of Intel Corporation nor the names of its contributors |
| 13 | * may be used to endorse or promote products derived from this software |
| 14 | * without specific prior written permission. |
| 15 | * |
| 16 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" |
| 17 | * AND 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 COPYRIGHT OWNER OR CONTRIBUTORS BE |
| 20 | * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR |
| 21 | * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF |
| 22 | * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS |
| 23 | * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN |
| 24 | * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) |
| 25 | * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
| 26 | * POSSIBILITY OF SUCH DAMAGE. |
| 27 | */ |
| 28 | |
| 29 | #ifndef COPY_BYTES_H |
| 30 | #define COPY_BYTES_H |
| 31 | |
| 32 | #include "unaligned.h" |
| 33 | #include "simd_utils.h" |
| 34 | |
| 35 | static really_inline |
| 36 | void copy_upto_32_bytes(u8 *dst, const u8 *src, unsigned int len) { |
| 37 | switch (len) { |
| 38 | case 0: |
| 39 | break; |
| 40 | case 1: |
| 41 | *dst = *src; |
| 42 | break; |
| 43 | case 2: |
| 44 | unaligned_store_u16(dst, unaligned_load_u16(src)); |
| 45 | break; |
| 46 | case 3: |
| 47 | unaligned_store_u16(dst, unaligned_load_u16(src)); |
| 48 | dst[2] = src[2]; |
| 49 | break; |
| 50 | case 4: |
| 51 | unaligned_store_u32(dst, unaligned_load_u32(src)); |
| 52 | break; |
| 53 | case 5: |
| 54 | case 6: |
| 55 | case 7: |
| 56 | unaligned_store_u32(dst + len - 4, unaligned_load_u32(src + len - 4)); |
| 57 | unaligned_store_u32(dst, unaligned_load_u32(src)); |
| 58 | break; |
| 59 | case 8: |
| 60 | unaligned_store_u64a(dst, unaligned_load_u64a(src)); |
| 61 | break; |
| 62 | case 9: |
| 63 | case 10: |
| 64 | case 11: |
| 65 | case 12: |
| 66 | case 13: |
| 67 | case 14: |
| 68 | case 15: |
| 69 | unaligned_store_u64a(dst + len - 8, unaligned_load_u64a(src + len - 8)); |
| 70 | unaligned_store_u64a(dst, unaligned_load_u64a(src)); |
| 71 | break; |
| 72 | case 16: |
| 73 | storeu128(dst, loadu128(src)); |
| 74 | break; |
| 75 | case 32: |
| 76 | storeu256(dst, loadu256(src)); |
| 77 | break; |
| 78 | default: |
| 79 | assert(len < 32); |
| 80 | storeu128(dst + len - 16, loadu128(src + len - 16)); |
| 81 | storeu128(dst, loadu128(src)); |
| 82 | break; |
| 83 | } |
| 84 | } |
| 85 | |
| 86 | #endif |
| 87 | |