Debian Codegraph @

src/shaders/post_processing/gen5_6/Common/RGBX_Load_16x8.asm

raw
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: RGBA_Load_16x8.asm (copied from AYUV_Load_16x8.asm)
42 //----------------------------------------------------------------
43
44
45 #include "RGBX_Load_16x8.inc"
46
47 // In order to load 64x8 RGBA data (16x8 pixels), we need to divide the data
48 // into two regions and load them separately.
49 //
50 // 32 byte 32 byte
51 //|----------------|----------------|
52 //| | |
53 //| A | B |8
54 //| | |
55 //| | |
56 //|----------------|----------------|
57
58 // Load the first 32x8 data block
59 // Packed data block should be loaded as 32x8 pixel block
60 add (2) rMSGSRC.0<1>:d wORIX<2;2,1>:w wSRC_H_ORI_OFFSET<2;2,1>:w // Source Block origin
61 shl (1) rMSGSRC.0<1>:d rMSGSRC.0<0;1,0>:w 2:w { NoDDClr } // H. block origin need to be four times larger
62 mov (1) rMSGSRC.2<1>:ud nDPR_BLOCK_SIZE_RGBA:ud { NoDDChk } // Block width and height (32x8)
63 mov (8) mMSGHDRY<1>:ud rMSGSRC<8;8,1>:ud
64 send (8) udSRC_RGBA(0)<1> mMSGHDRY udDUMMY_NULL nDATAPORT_READ nDPMR_MSGDSC+nDPR_MSG_SIZE_RGBA+nBI_CURRENT_SRC_YUV:ud
65
66 //Load the second 32x8 data block
67 // Offset the origin X - move to next 32 colomns
68 add (1) rMSGSRC.0<1>:d rMSGSRC.0<0;1,0>:d 32:w // Increase X origin by 8
69
70 // Size stays the same - 32x8
71 mov (8) mMSGHDRY<1>:ud rMSGSRC<8;8,1>:ud // Copy message description to message header
72 send (8) udSRC_RGBA(8)<1> mMSGHDRY udDUMMY_NULL nDATAPORT_READ nDPMR_MSGDSC+nDPR_MSG_SIZE_RGBA+nBI_CURRENT_SRC_YUV:ud
73
74 // Give AYUV region addresses to address register
75 // a0.0 is 0x38*32, a0.1 is 0x40*32. 0x40-0x38=8 (pixel)
76 mov (1) SRC_RGBA_OFFSET<1>:ud 0x00400038*32:ud //Address registers contain starting addresses of two halves
77
78 #if !defined(FIX_POINT_CONVERSION) && !defined(FLOAT_POINT_CONVERSION)
79 //Directly move the data to destination
80 $for(0; <nY_NUM_OF_ROWS; 1) {
81 // 8 means 8 elements, not 2=8/2 element per row.
82 mov (16) uwDEST_Y(%1)<1> r[SRC_RGBA_OFFSET,%1*32+3]<8,4>:ub // A/R
83 mov (16) uwDEST_U(%1)<1> r[SRC_RGBA_OFFSET,%1*32+2]<8,4>:ub // Y/G
84 mov (16) uwDEST_V(%1)<1> r[SRC_RGBA_OFFSET,%1*32+1]<8,4>:ub // U/B
85 }
86 #endif
87