Debian Codegraph @

src/shaders/h264/ildb/load_Left_Y_4x16T_Mbaff.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: load_Y_4x16T.asm
40 //
41 // Load luma left MB 4x16 and transpose 4x16 to 16x4.
42 //
43 //----------------------------------------------------------------
44 // Symbols need to be defined before including this module
45 //
46 // Source region in :ud
47 // PREV_MB_YD: PREV_MB_YD Base=rxx ElementSize=4 SrcRegion=REGION(8,1) Type=ud // 2 GRFs
48 //
49 // Binding table index:
50 // BI_SRC_Y: Binding table index of Y surface
51 //
52 //----------------------------------------------------------------
53
54 #if defined(_DEBUG)
55 mov (1) EntrySignatureC:w 0xDDD0:w
56 #endif
57
58 // FieldModeCurrentMbFlag determines how to access left MB
59 and.z.f0.0 (1) null:w r[ECM_AddrReg, BitFlags]:ub FieldModeCurrentMbFlag:w
60
61 and.nz.f0.1 (1) NULLREGW BitFields:w BotFieldFlag:w // Get bottom field flag
62
63 // Read Y
64 mov (2) MSGSRC.0<1>:ud ORIX_LEFT<2;2,1>:w { NoDDClr } // Block origin
65 mov (1) MSGSRC.2<1>:ud 0x000F0003:ud { NoDDChk } // Block width and height (4x16)
66
67 // Set message descriptor, etc.
68
69 (f0.0) if (1) ELSE_Y_4x16T
70
71 // Frame picture
72 mov (1) MSGDSC RESP_LEN(2)+DWBRMSGDSC_RC+BI_DEST_Y:ud // Read 2 GRFs from DEST_Y
73
74 (f0.1) add (1) MSGSRC.1:d MSGSRC.1:d 16:w // Add vertical offset 16 for bot MB in MBAFF mode
75
76 ELSE_Y_4x16T:
77 else (1) ENDIF_Y_4x16T
78
79 // Field picture
80 (f0.1) mov (1) MSGDSC RESP_LEN(2)+DWBRMSGDSC_RC_BF+BI_DEST_Y:ud // Read 2 GRFs from DEST_Y bottom field
81 (-f0.1) mov (1) MSGDSC RESP_LEN(2)+DWBRMSGDSC_RC_TF+BI_DEST_Y:ud // Read 2 GRFs from DEST_Y top field
82
83 asr (1) MSGSRC.1:d MSGSRC.1:d 1:w // Reduce y by half in field access mode
84
85 endif
86 ENDIF_Y_4x16T:
87
88 // send (8) BUF_D(0)<1> MSGHDRY MSGSRC<8;8,1>:ud MSGDSC
89 send (8) LEFT_TEMP_D(0)<1> MSGHDRL MSGSRC<8;8,1>:ud DAPREAD MSGDSC
90
91
92 // Transpose 4x16 to 16x4
93
94 // Input received from dport:
95 // +-----------------------+-----------------------+-----------------------+-----------------------+
96 // |73 72 71 70 63 62 61 60 53 52 51 50 43 42 41 40 33 32 31 30 23 22 21 20 13 12 11 10 03 02 01 00|
97 // +-----------------------+-----------------------+-----------------------+-----------------------+
98 // |f3 f2 f1 f0 e3 e2 e1 e0 d3 d2 d1 d0 c3 c2 c1 c0 b3 b2 b1 b0 a3 a2 a1 a0 93 92 91 90 83 82 81 80|
99 // +-----------------------+-----------------------+-----------------------+-----------------------+
100
101 // Output of transpose: <1> <= <32;8,4>
102 // +-----------------------+-----------------------+-----------------------+-----------------------+
103 // |f1 e1 d1 c1 b1 a1 91 81 71 61 51 41 31 21 11 01 f0 e0 d0 c0 b0 a0 90 80 70 60 50 40 30 20 10 00|
104 // +-----------------------+-----------------------+-----------------------+-----------------------+
105 // |f3 e3 d3 c3 b3 a3 93 83 73 63 53 43 33 23 13 03 f2 e2 d2 c2 b2 a2 92 82 72 62 52 42 32 22 12 02|
106 // +-----------------------+-----------------------+-----------------------+-----------------------+
107 /*
108 // Transpose the data, also occupy 2 GRFs
109 mov (16) PREV_MB_YB(0)<1> BUF_B(0, 0)<32;8,4> { NoDDClr }
110 mov (16) PREV_MB_YB(0, 16)<1> BUF_B(0, 1)<32;8,4> { NoDDChk }
111 mov (16) PREV_MB_YB(1)<1> BUF_B(0, 2)<32;8,4> { NoDDClr }
112 mov (16) PREV_MB_YB(1, 16)<1> BUF_B(0, 3)<32;8,4> { NoDDChk }
113 */
114 // End of load_Y_4x16T