Debian Codegraph @

src/shaders/post_processing/gen5_6/Common/NV12_Load_8x4.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: NV12_Load_8x4.asm
42 //----------------------------------------------------------------
43
44 #define NV12_LOAD_8x4
45 #include "PL2_Load.inc"
46
47 // Load 16x8 planar Y ----------------------------------------------------------
48 add (2) rMSGSRC.0<1>:d wORIX<2;2,1>:w wSRC_H_ORI_OFFSET<2;2,1>:w // Source Y Block origin
49 #if !defined(LOAD_UV_ONLY)
50 mov (1) rMSGSRC.2<1>:ud nDPR_BLOCK_SIZE_Y:ud // Y block width and height (16x8)
51 mov (8) mMSGHDRY<1>:ud rMSGSRC<8;8,1>:ud
52 send (8) udSRC_Y(0)<1> mMSGHDRY udDUMMY_NULL nDATAPORT_READ nDPMR_MSGDSC+nDPR_MSG_SIZE_Y+nBI_CURRENT_SRC_Y:ud
53 #endif
54
55 // Load 8x4 planar U and V -----------------------------------------------------
56 asr (1) rMSGSRC.1<1>:d rMSGSRC.1<0;1,0>:d 1:w // U/V block origin should be half of Y's
57 mov (1) rMSGSRC.2<1>:ud nDPR_BLOCK_SIZE_UV:ud // U/V block width and height (16x4)
58 mov (8) mMSGHDRU<1>:ud rMSGSRC<8;8,1>:ud
59 send (8) udSRC_U(0)<1> mMSGHDRU udDUMMY_NULL nDATAPORT_READ nDPMR_MSGDSC+nDPR_MSG_SIZE_UV+nBI_CURRENT_SRC_UV:ud
60
61 // Convert to word-aligned format ----------------------------------------------
62 #if defined(FIX_POINT_CONVERSION) || defined(FLOAT_POINT_CONVERSION)
63 // load NV12 and save it as packed AYUV to dst (64x8)
64
65 $for (nY_NUM_OF_ROWS-1; >-1; -1) {
66 // #### Y
67 mov (8) ubDEST_Y(0,%1*16*4)<4> ubSRC_Y(0,%1*16)<0;8,1>
68 mov (8) ubDEST_Y(0,(%1*16+8)*4)<4> ubSRC_Y(0,%1*16+8)<0;8,1>
69
70 // #### U/V
71 // error from compile: "Invalid horiz size 8", so I have to repeat UV first
72 // mov (4) ubDEST_Y(0,%1*16*4+1)<8> ubSRC_U(0,%1/2*16)<0;4,2>
73 // mov (4) ubDEST_Y(0,%1*16*4+1+32)<8> ubSRC_U(0,%1/2*16+8)<0;4,2>
74
75 // repeate U/V for each one
76 mov (8) REG2(r,nTEMP18,0)<2>:uw uwSRC_U(0,%1/2*8)<0;8,1>
77 mov (8) REG2(r,nTEMP18,1)<2>:uw uwSRC_U(0,%1/2*8)<0;8,1>
78
79 // mov U/V to ubDEST
80 mov (8) ubDEST_Y(0,%1*16*4+1)<4> REG2(r,nTEMP18,0)<0;8,2>:ub
81 mov (8) ubDEST_Y(0,%1*16*4+1+32)<4> REG2(r,nTEMP18,16)<0;8,2>:ub
82
83 mov (8) ubDEST_Y(0,%1*16*4+2)<4> REG2(r,nTEMP18,1)<0;8,2>:ub
84 mov (8) ubDEST_Y(0,%1*16*4+2+32)<4> REG2(r,nTEMP18,17)<0;8,2>:ub
85 }
86 #else
87 #if !defined(LOAD_UV_ONLY)
88 $for (nY_NUM_OF_ROWS-1; >-1; -1) {
89 mov (16) uwDEST_Y(0,%1*16)<1> ubSRC_Y(0,%1*16)
90 }
91 #endif
92 $for (nUV_NUM_OF_ROWS/2-1; >-1; -1) {
93 // why "mov (16)"? should it be 8?
94 mov (16) uwDEST_U(0,%1*16)<1> ubSRC_U(0,%1*32)<32;16,2>
95 mov (16) uwDEST_V(0,%1*16)<1> ubSRC_U(0,%1*32+1)<32;16,2>
96 }
97
98 #endif
99
100 // End of NV12_Load_8x4