Debian Codegraph @

src/shaders/h264/ildb/loadNV12_16x16T.asm

raw
1 /*
2 * Copyright © <2010>, Intel Corporation.
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the
6 * "Software"), to deal in the Software without restriction, including
7 * without limitation the rights to use, copy, modify, merge, publish,
8 * distribute, sub license, and/or sell copies of the Software, and to
9 * permit persons to whom the Software is furnished to do so, subject to
10 * the following conditions:
11 *
12 * The above copyright notice and this permission notice (including the
13 * next paragraph) shall be included in all copies or substantial portions
14 * of the Software.
15 *
16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
17 * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
18 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
19 * IN NO EVENT SHALL PRECISION INSIGHT AND/OR ITS SUPPLIERS BE LIABLE FOR
20 * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
21 * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
22 * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
23 *
24 * This file was originally licensed under the following license
25 *
26 * Licensed under the Apache License, Version 2.0 (the "License");
27 * you may not use this file except in compliance with the License.
28 * You may obtain a copy of the License at
29 *
30 * http://www.apache.org/licenses/LICENSE-2.0
31 *
32 * Unless required by applicable law or agreed to in writing, software
33 * distributed under the License is distributed on an "AS IS" BASIS,
34 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
35 * See the License for the specific language governing permissions and
36 * limitations under the License.
37 *
38 */
39 // Module name: loadNV12_16x16T.asm
40 //
41 // Load and transpose NV12 16x16 block
42 //
43 //----------------------------------------------------------------
44 // Symbols need to be defined before including this module
45 //
46 // Source region in :ud
47 // SRC_YD: SRC_YD Base=rxx ElementSize=4 SrcRegion=REGION(8,1) Type=ud // 8 GRFs
48 // SRC_UD: SRC_UD Base=rxx ElementSize=4 SrcRegion=REGION(8,1) Type=ud (U+V for NV12) // 4 GRFs
49 //
50 // Source region is :ub. The same region as :ud region
51 // SRC_YB: SRC_YB Base=rxx ElementSize=1 SrcRegion=REGION(16,1) Type=ub // 8 GRFs
52 // SRC_UB: SRC_UB Base=rxx ElementSize=1 SrcRegion=REGION(16,1) Type=ub // 2 GRFs
53 // SRC_VB: SRC_VB Base=rxx ElementSize=1 SrcRegion=REGION(16,1) Type=ub // 2 GRFs
54 //
55 // Binding table index:
56 // BI_SRC_Y: Binding table index of Y surface
57 // BI_SRC_UV: Binding table index of UV surface (NV12)
58 //
59 // Temp buffer:
60 // BUF_B: BUF_B Base=rxx ElementSize=1 SrcRegion=REGION(16,1) Type=ub
61 //
62 //----------------------------------------------------------------
63
64 #if defined(_DEBUG)
65 mov (1) EntrySignatureC:w 0xDDD1:w
66 #endif
67
68 // Read Y
69 mov (2) MSGSRC.0<1>:ud ORIX_CUR<2;2,1>:w // Block origin
70 mov (1) MSGSRC.2<1>:ud 0x000F000F:ud // Block width and height (16x16)
71 send (8) SRC_YD(0)<1> MSGHDRY MSGSRC<8;8,1>:ud DAPREAD RESP_LEN(8)+DWBRMSGDSC_RC+BI_SRC_Y // Read 8 GRFs
72
73 // Read U+V
74 asr (1) MSGSRC.1:ud MSGSRC.1:ud 1:w // NV12 U+V block origin y = half of Y comp
75 mov (1) MSGSRC.2<1>:ud 0x0007000F:ud // NV12 U+V block width and height (16x8)
76 send (8) SRC_UD(0)<1> MSGHDRU MSGSRC<8;8,1>:ud DAPREAD RESP_LEN(4)+DWBRMSGDSC_RC+BI_SRC_UV // Read 4 GRFs
77
78 #include "TransposeNV12_16x16.asm"
79
80 // #include "Transpose_Y_16x16.asm"
81 // #include "Transpose_NV12_UV_16x8.asm"
82
83 // End of loadNV12_16x16T