Debian Codegraph @

src/shaders/post_processing/gen5_6/Common/RGB16x8_Save_RGB16.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: RGB16x8_Save_RGB16.asm
42 //
43 // Save packed RGB565 frame data block of size 16x8
44 //
45 // To save 16x8 block (32x8 byte layout for RGB565) we need 1 send instruction
46 // -----
47 // | 1 |
48 // -----
49
50 #include "RGB16x8_Save_RGB16.inc"
51
52 //convert 32 bit RGB to 16 bit RGB
53 // Truncate A8R8G8B8 to A6R5G6B5 within byte.
54 // That is keeping 5 MSB of R and B, and 6 MSB of G.
55
56 $for (0, 0; <nY_NUM_OF_ROWS; 1, 2) {
57 shr uwCSC_TEMP(%1,0)<1> ubDEST_ARGB(%2,0)<32;8,4> 3:w // B >> 3
58
59 shl (16) uwTEMP_RGB16(0)<1> uwDEST_ARGB(%2,1)<16;8,2> 8:w // R << 8
60 and (16) uwTEMP_RGB16(0)<1> uwTEMP_RGB16(0) 0xF800:uw
61 or (16) uwCSC_TEMP(%1,0)<1> uwCSC_TEMP(%1,0)<16;16,1> uwTEMP_RGB16(0)
62
63 shr (16) uwTEMP_RGB16(0)<1> uwDEST_ARGB(%2,0)<16;8,2> 5:w // G >> 5
64 and (16) uwTEMP_RGB16(0)<1> uwTEMP_RGB16(0) 0x07E0:uw
65 or (16) uwCSC_TEMP(%1,0)<1> uwCSC_TEMP(%1,0)<16;16,1> uwTEMP_RGB16(0)
66 }
67
68 mov (2) rMSGSRC.0<1>:d wORIX<2;2,1>:w // Block origin (1st quadrant)
69 shl (1) rMSGSRC.0<1>:d wORIX<0;1,0>:w 1:w // H. block origin need to be doubled for byte offset
70 mov (1) rMSGSRC.2<1>:ud nDPW_BLOCK_SIZE_RGB16:ud // Block width and height (32x8)
71 mov (8) mMSGHDR<1>:ud rMSGSRC<8;8,1>:ud
72
73 //Use the mask to determine which pixels shouldn't be over-written
74 and (1) acc0.0<1>:ud udBLOCK_MASK<0;1,0>:ud 0x00FFFFFF:ud
75 cmp.ge.f0.0(1) dNULLREG acc0.0<0;1,0>:ud 0x00FFFFFF:ud //Check if all pixels in the block need to be modified
76 (f0.0) jmpi WriteRGB16ToDataPort
77
78 //If mask is not all 1's, then load the entire 32x8 block
79 //so that only those bytes may be modified that need to be (using the mask)
80
81 // Load 32x8 packed RGB565 -----------------------------------------------------
82 send (8) udSRC_RGB16(0)<1> mMSGHDR udDUMMY_NULL nDATAPORT_READ nDPMR_MSGDSC+nDPR_MSG_SIZE_RGB16+nBI_DESTINATION_RGB:ud
83 mov (8) mMSGHDR<1>:ud rMSGSRC<8;8,1>:ud
84
85 //Merge the data
86 mov (1) f0.0:uw ubBLOCK_MASK_V:ub //Load the mask on flag reg
87 (f0.0) mov (8) rMASK_TEMP<1>:uw uwBLOCK_MASK_H:uw //use sel instruction - vK
88 (-f0.0) mov (8) rMASK_TEMP<1>:uw 0:uw
89
90 $for(0; <nY_NUM_OF_ROWS; 1) {
91 mov (1) f0.1:uw uwMASK_TEMP(0,%1)<0;1,0>
92 (-f0.1) mov (16) uwCSC_TEMP(%1)<1> uwSRC_RGB16(%1)
93 }
94
95 WriteRGB16ToDataPort:
96 // Move packed data to MRF and output
97 $for(0; <nY_NUM_OF_ROWS; 1) {
98 mov (8) mudMSGPAYLOAD(%1)<1> udCSC_TEMP(%1)
99 }
100 send (8) dNULLREG mMSGHDR udDUMMY_NULL nDATAPORT_WRITE nDPMW_MSGDSC+nDPW_MSG_SIZE_RGB16+nBI_DESTINATION_RGB:ud
101
102 // End of RGB16x8_Save_RGB16