| 1 |
/* |
| 2 |
* All Video Processing kernels |
| 3 |
* Copyright © <2010>, Intel Corporation. |
| 4 |
* |
| 5 |
* Permission is hereby granted, free of charge, to any person obtaining a |
| 6 |
* copy of this software and associated documentation files (the |
| 7 |
* "Software"), to deal in the Software without restriction, including |
| 8 |
* without limitation the rights to use, copy, modify, merge, publish, |
| 9 |
* distribute, sub license, and/or sell copies of the Software, and to |
| 10 |
* permit persons to whom the Software is furnished to do so, subject to |
| 11 |
* the following conditions: |
| 12 |
* |
| 13 |
* The above copyright notice and this permission notice (including the |
| 14 |
* next paragraph) shall be included in all copies or substantial portions |
| 15 |
* of the Software. |
| 16 |
* |
| 17 |
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS |
| 18 |
* OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF |
| 19 |
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. |
| 20 |
* IN NO EVENT SHALL PRECISION INSIGHT AND/OR ITS SUPPLIERS BE LIABLE FOR |
| 21 |
* ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, |
| 22 |
* TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE |
| 23 |
* SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. |
| 24 |
* |
| 25 |
* This file was originally licensed under the following license |
| 26 |
* |
| 27 |
* Licensed under the Apache License, Version 2.0 (the "License"); |
| 28 |
* you may not use this file except in compliance with the License. |
| 29 |
* You may obtain a copy of the License at |
| 30 |
* |
| 31 |
* http://www.apache.org/licenses/LICENSE-2.0 |
| 32 |
* |
| 33 |
* Unless required by applicable law or agreed to in writing, software |
| 34 |
* distributed under the License is distributed on an "AS IS" BASIS, |
| 35 |
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 36 |
* See the License for the specific language governing permissions and |
| 37 |
* limitations under the License. |
| 38 |
* |
| 39 |
* Authors: |
| 40 |
* Halley Zhao <[email protected]> |
| 41 |
*/ |
| 42 |
|
| 43 |
// Module name: YUV_to_RGBX_Coef.asm |
| 44 |
//---------------------------------------------------------------- |
| 45 |
#define ubDEST_RGBX ubTOP_Y // I'd like use them for color conversion |
| 46 |
|
| 47 |
// is dst surface |R|G|B|X| layout? otherwise, it is |B|G|R|X| layout |
| 48 |
and.nz.f0.1 (1) dNULLREG r1.2:ud 0xFF000000:ud |
| 49 |
#ifdef FIX_POINT_CONVERSION |
| 50 |
// ###### set up transformation coefficient |
| 51 |
// R = clip(( 298 * C + 0 * D + 409 * E + 128) >> 8) |
| 52 |
// R = clip((0x012A * C + 0 * D + 0x0199 * E + 128) >> 8) |
| 53 |
(-f0.1) mov (1) REG2(r, nTEMP0, 0):ud 0x0000012A:ud |
| 54 |
(-f0.1) mov (1) REG2(r, nTEMP0, 1):ud 0x00000199:ud |
| 55 |
( f0.1) mov (1) REG2(r, nTEMP0, 4):ud 0x0000012A:ud |
| 56 |
( f0.1) mov (1) REG2(r, nTEMP0, 5):ud 0x00000199:ud |
| 57 |
|
| 58 |
// G = clip(( 298 * C - 100 * D - 208 * E + 128) >> 8) |
| 59 |
// G = clip(( 0x012A * C - 0x64 * D - 0xD0 * E + 128) >> 8) |
| 60 |
// G = clip(( 0x012A * C + 0xFF9C * D + 0xFF30 * E + 128) >> 8) |
| 61 |
mov (1) REG2(r, nTEMP0, 2):ud 0xFF9C012A:ud |
| 62 |
mov (1) REG2(r, nTEMP0, 3):ud 0x0000FF30:ud |
| 63 |
|
| 64 |
// B = clip(( 298 * C + 516 * D + 0 * E + 128) >> 8) |
| 65 |
// B = clip((0x012A* C + 0x0204 * D + 0 * E + 128) >> 8) |
| 66 |
(-f0.1) mov (1) REG2(r, nTEMP0, 4):ud 0x0204012A:ud |
| 67 |
(-f0.1) mov (1) REG2(r, nTEMP0, 5):ud 0x00000000:ud |
| 68 |
( f0.1) mov (1) REG2(r, nTEMP0, 0):ud 0x0204012A:ud |
| 69 |
( f0.1) mov (1) REG2(r, nTEMP0, 1):ud 0x00000000:ud |
| 70 |
|
| 71 |
// asr.sat (24) REG2(r,nTEMP0,0)<1> REG2(r,nTEMP0,0)<0;24,1> 1:w |
| 72 |
asr.sat (8) REG2(r,nTEMP0, 0)<1>:w REG2(r,nTEMP0, 0)<0;8,1>:w 1:w |
| 73 |
asr.sat (4) REG2(r,nTEMP0,8)<1>:w REG2(r,nTEMP0,8)<0;4,1>:w 1:w |
| 74 |
|
| 75 |
// C = Y' - 16 D = U - 128 E = V - 128 |
| 76 |
mov (1) REG2(r, nTEMP0, 6):ud 0x008080F0:ud |
| 77 |
|
| 78 |
#define wYUV_to_RGB_CH2_Coef_Fix REG2(r, nTEMP0, 0) |
| 79 |
#define wYUV_to_RGB_CH1_Coef_Fix REG2(r, nTEMP0, 4) |
| 80 |
#define wYUV_to_RGB_CH0_Coef_Fix REG2(r, nTEMP0, 8) |
| 81 |
#define bYUV_OFF REG2(r,nTEMP0,24) |
| 82 |
|
| 83 |
// debug use |
| 84 |
#define bYUV_to_RGB_CH2_Coef_Fix REG2(r, nTEMP0, 0) |
| 85 |
#define bYUV_to_RGB_CH1_Coef_Fix REG2(r, nTEMP0, 8) |
| 86 |
#define bYUV_to_RGB_CH0_Coef_Fix REG2(r, nTEMP0, 16) |
| 87 |
|
| 88 |
#else |
| 89 |
// R = Y + 1.13983*V |
| 90 |
// R = clip( Y + 1.402*(Cr-128)) // ITU-R |
| 91 |
(-f0.1) mov (1) REG2(r, nTEMP8, 3):f 0.000f // A coef |
| 92 |
(-f0.1) mov (1) REG2(r, nTEMP8, 2):f 1.402f // V coef |
| 93 |
(-f0.1) mov (1) REG2(r, nTEMP8, 1):f 0.0f // U coef |
| 94 |
(-f0.1) mov (1) REG2(r, nTEMP8, 0):f 1.0f // Y coef |
| 95 |
|
| 96 |
( f0.1) mov (1) REG2(r, nTEMP10, 3):f 0.000f // A coef |
| 97 |
( f0.1) mov (1) REG2(r, nTEMP10, 2):f 1.402f // V coef |
| 98 |
( f0.1) mov (1) REG2(r, nTEMP10, 1):f 0.0f // U coef |
| 99 |
( f0.1) mov (1) REG2(r, nTEMP10, 0):f 1.0f // Y coef |
| 100 |
|
| 101 |
// G = Y - 0.39465*U - 0.58060*V |
| 102 |
// G = clip( Y - 0.344*(Cb-128) - 0.714*(Cr-128)) |
| 103 |
mov (1) REG2(r, nTEMP8, 7):f 0.000f // A coef |
| 104 |
mov (1) REG2(r, nTEMP8, 6):f -0.714f // V coef |
| 105 |
mov (1) REG2(r, nTEMP8, 5):f -0.344f // U coef |
| 106 |
mov (1) REG2(r, nTEMP8, 4):f 1.0f // Y coef |
| 107 |
|
| 108 |
// B = Y + 2.03211*U |
| 109 |
// B = clip( Y + 1.772*(Cb-128)) |
| 110 |
(-f0.1) mov (1) REG2(r, nTEMP10, 3):f 0.000f // A coef |
| 111 |
(-f0.1) mov (1) REG2(r, nTEMP10, 2):f 0.0f // V coef |
| 112 |
(-f0.1) mov (1) REG2(r, nTEMP10, 1):f 1.772f // U coef |
| 113 |
(-f0.1) mov (1) REG2(r, nTEMP10, 0):f 1.0f // Y coef |
| 114 |
|
| 115 |
( f0.1) mov (1) REG2(r, nTEMP8, 3):f 0.000f // A coef |
| 116 |
( f0.1) mov (1) REG2(r, nTEMP8, 2):f 0.0f // V coef |
| 117 |
( f0.1) mov (1) REG2(r, nTEMP8, 1):f 1.772f // U coef |
| 118 |
( f0.1) mov (1) REG2(r, nTEMP8, 0):f 1.0f // Y coef |
| 119 |
|
| 120 |
mov (1) REG2(r, nTEMP10, 4):ud 0x008080F0:ud |
| 121 |
|
| 122 |
#define fYUV_to_RGB_CH2_Coef_Float REG2(r, nTEMP8, 0) |
| 123 |
#define fYUV_to_RGB_CH1_Coef_Float REG2(r, nTEMP8, 4) |
| 124 |
#define fYUV_to_RGB_CH0_Coef_Float REG2(r, nTEMP10, 0) |
| 125 |
#define bYUV_OFF REG2(r,nTEMP10,16) |
| 126 |
|
| 127 |
.declare fROW_YUVA Base=REG(r,nTEMP0) ElementSize=4 SrcRegion=REGION(8,8) Type=f // r nTEMP0 - r nTEMP7 |
| 128 |
|
| 129 |
#endif |