Showing the changes to codec/processing/src/arm64 (1 of 8 files). Show all
Unified · Split
| @@ -0,0 +1,88 @@ | |||
| 1 | /*! | ||
| 2 | * \copy | ||
| 3 | * Copyright (c) 2013, Cisco Systems | ||
| 4 | * All rights reserved. | ||
| 5 | * | ||
| 6 | * Redistribution and use in source and binary forms, with or without | ||
| 7 | * modification, are permitted provided that the following conditions | ||
| 8 | * are met: | ||
| 9 | * | ||
| 10 | * * Redistributions of source code must retain the above copyright | ||
| 11 | * notice, this list of conditions and the following disclaimer. | ||
| 12 | * | ||
| 13 | * * Redistributions in binary form must reproduce the above copyright | ||
| 14 | * notice, this list of conditions and the following disclaimer in | ||
| 15 | * the documentation and/or other materials provided with the | ||
| 16 | * distribution. | ||
| 17 | * | ||
| 18 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS | ||
| 19 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT | ||
| 20 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS | ||
| 21 | * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE | ||
| 22 | * COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, | ||
| 23 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, | ||
| 24 | * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; | ||
| 25 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER | ||
| 26 | * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT | ||
| 27 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN | ||
| 28 | * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE | ||
| 29 | * POSSIBILITY OF SUCH DAMAGE. | ||
| 30 | * | ||
| 31 | */ | ||
| 32 | |||
| 33 | #ifdef HAVE_NEON_AARCH64 | ||
| 34 | .text | ||
| 35 | #include "arm_arch64_common_macro.S" | ||
| 36 | WELS_ASM_AARCH64_FUNC_BEGIN SampleVariance16x16_AArch64_neon | ||
| 37 | ld1 {v1.16b}, [x0], x1 //save the ref data (16bytes) | ||
| 38 | ld1 {v0.16b}, [x2], x3 //save the src data (16bytes) | ||
| 39 | uabd v2.16b, v0.16b, v1.16b | ||
| 40 | umull v3.8h, v2.8b, v2.8b | ||
| 41 | umull2 v4.8h, v2.16b, v2.16b | ||
| 42 | uaddlp v4.4s, v4.8h | ||
| 43 | uadalp v4.4s, v3.8h //sqr | ||
| 44 | uaddlp v2.8h, v2.16b //sum | ||
| 45 | |||
| 46 | uaddlp v1.8h, v0.16b //sum_cur | ||
| 47 | |||
| 48 | umull v3.8h, v0.8b, v0.8b | ||
| 49 | umull2 v5.8h, v0.16b, v0.16b | ||
| 50 | uaddlp v3.4s, v3.8h | ||
| 51 | uadalp v3.4s, v5.8h //sqr_cur | ||
| 52 | .rept 15 | ||
| 53 | ld1 {v5.16b}, [x0], x1 //save the ref data (16bytes) | ||
| 54 | ld1 {v0.16b}, [x2], x3 //save the src data (16bytes) | ||
| 55 | |||
| 56 | uabd v6.16b, v0.16b, v5.16b | ||
| 57 | |||
| 58 | //v1 save sum_cur | ||
| 59 | uadalp v1.8h, v0.16b | ||
| 60 | |||
| 61 | //v4 save sqr | ||
| 62 | umull v5.8h, v6.8b, v6.8b | ||
| 63 | umull2 v7.8h, v6.16b, v6.16b | ||
| 64 | uadalp v4.4s, v5.8h //sqr | ||
| 65 | uadalp v4.4s, v7.8h //sqr | ||
| 66 | |||
| 67 | //v2 save sum | ||
| 68 | uadalp v2.8h, v6.16b | ||
| 69 | |||
| 70 | //v3 save sqr_cur | ||
| 71 | umull v5.8h, v0.8b, v0.8b | ||
| 72 | umull2 v7.8h, v0.16b, v0.16b | ||
| 73 | uadalp v3.4s, v5.8h //sqr_cur | ||
| 74 | uadalp v3.4s, v7.8h //sqr_cur | ||
| 75 | .endr | ||
| 76 | uaddlv s2, v2.8h //sum | ||
| 77 | uaddlv s1, v1.8h //sum_cur | ||
| 78 | ins v2.s[1], v1.s[0] // sum, sum_cur | ||
| 79 | shrn v2.4h, v2.4s, #8 // sum, sum_cur>>8 | ||
| 80 | mul v2.4h, v2.4h, v2.4h//// sum*sum, sum_cur*sum_cur | ||
| 81 | uaddlv d4, v4.4s //sqr | ||
| 82 | uaddlv d3, v3.4s //sqr_cur | ||
| 83 | ins v4.s[1], v3.s[0] // sqr, sqr_cur | ||
| 84 | shrn v4.4h, v4.4s, #8 // sqr, sqr_cur>>8 | ||
| 85 | sub v4.4h, v4.4h, v2.4h | ||
| 86 | st1 {v4.s}[0], [x4] | ||
| 87 | WELS_ASM_AARCH64_FUNC_END | ||
| 88 | #endif | ||