| 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 |
*/ |
| 40 |
|
| 41 |
// Module name: PA_Load_9x8.asm |
| 42 |
//---------------------------------------------------------------- |
| 43 |
// This module loads 16x8 Y, 9x8 U and 9x8 V planar data blocks for CSC module |
| 44 |
// and stores it in word-aligned format. |
| 45 |
//---------------------------------------------------------------- |
| 46 |
|
| 47 |
#define PA_LOAD_9x8 |
| 48 |
#include "PA_Load.inc" |
| 49 |
|
| 50 |
// Load 18x8 packed data block |
| 51 |
// Packed data block should be loaded as 36x8 pixel block |
| 52 |
add (2) rMSGSRC.0<1>:d wORIX<2;2,1>:w wSRC_H_ORI_OFFSET<2;2,1>:w // Source Block origin |
| 53 |
shl (1) rMSGSRC.0<1>:d acc0:w 1:w // H. block origin need to be doubled |
| 54 |
mov (1) rMSGSRC.2<1>:ud nDPR_BLOCK_SIZE_YUV_MAIN:ud // Block width and height (32x8) |
| 55 |
mov (8) mMSGHDRY<1>:ud rMSGSRC<8;8,1>:ud |
| 56 |
send (8) udSRC_YUV(0)<1> mMSGHDRY udDUMMY_NULL nDATAPORT_READ nDPMR_MSGDSC+nDPR_MSG_SIZE_YUV_MAIN+nBI_CURRENT_SRC_YUV:ud |
| 57 |
|
| 58 |
add (1) rMSGSRC.0<1>:d rMSGSRC.0:d 32:w //the last 4 pixels are read again for optimization |
| 59 |
mov (1) rMSGSRC.2<1>:ud nDPR_BLOCK_SIZE_YUV_ADDITION:ud // Block width and height (4x8) |
| 60 |
mov (8) mMSGHDRY<1>:ud rMSGSRC<8;8,1>:ud |
| 61 |
send (8) udSRC_YUV(8)<1> mMSGHDRY udDUMMY_NULL nDATAPORT_READ nDPMR_MSGDSC+nDPR_MSG_SIZE_YUV_ADDITION+nBI_CURRENT_SRC_YUV:ud |
| 62 |
|
| 63 |
// Unpack to "planar" YUV422 format in word-aligned bytes |
| 64 |
add (4) pCF_Y_OFFSET<1>:uw ubSRC_CF_OFFSET<4;4,1>:ub nSRC_YUV_REG*nGRFWIB:w // Initial Y,U,V offset in YUV422 block |
| 65 |
$for(0; <nY_NUM_OF_ROWS; 1) { |
| 66 |
mov (16) uwDEST_Y(0, %1*16)<1> r[pCF_Y_OFFSET, %1*nGRFWIB]REGION(16,2) |
| 67 |
mov (8) uwDEST_U(0, %1*16)<1> r[pCF_U_OFFSET, %1*nGRFWIB]REGION(8,4) |
| 68 |
mov (8) uwDEST_V(0, %1*16)<1> r[pCF_V_OFFSET, %1*nGRFWIB]REGION(8,4) |
| 69 |
} |
| 70 |
|
| 71 |
$for(0; <nUV_NUM_OF_ROWS; 1) { |
| 72 |
mov (1) uwDEST_U(0, %1*16+8)<1> r[pCF_U_OFFSET, %1*4+256]REGION(1,0) |
| 73 |
mov (1) uwDEST_V(0, %1*16+8)<1> r[pCF_V_OFFSET, %1*4+256]REGION(1,0) |
| 74 |
} |
| 75 |
//UV expansion done in PL9x8_PL16x8.asm module |
| 76 |
|
| 77 |
// End of PA_Load_9x8 |