Debian Codegraph @

src/shaders/h264/mc/loadRef_C_10x5.asm

raw
1 /*
2 * Load reference 10x5 area for chroma NV12 4x4 MC
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 // Kernel name: LoadRef_C_10x5.asm
41 //
42 // Load reference 10x5 area for chroma NV12 4x4 MC
43
44
45 //#if !defined(__LOADREF_C_10x5__) // Make sure this is only included once
46 //#define __LOADREF_C_10x5__
47
48
49 #if 1
50
51 // Compute integer and fractional components of MV
52 asr (2) gMVX_INT<1>:w r[pMV,0]<2;2,1>:w 0x03:w {NoDDClr}
53 and (2) gMVX_FRACC<1>:w r[pMV,0]<2;2,1>:w 0x07:w {NoDDChk}
54
55 // Check whether MVY is integer
56 or.z.f0.0 (8) null:w gMVY_FRACC<0;1,0>:w 0:w
57
58 // Compute top-left corner position to be loaded
59 mov (2) gMSGSRC.0<1>:d gMVX_INT<2;2,1>:w
60 shl (1) gMSGSRC.0:d gMSGSRC.0:d 1:w
61
62 (f0.0) add (1) pMSGDSC:ud gMSGDSC_R:ud RESP_LEN(2)+nBI_LC_DIFF:ud
63 (-f0.0) add (1) pMSGDSC:ud gMSGDSC_R:ud RESP_LEN(3)+nBI_LC_DIFF:ud
64
65 // Read 16x5 pixels - TODO: Reading 12x5 instead of 16x5 took more time on CL. Why?
66 (f0.0) mov (1) gMSGSRC.2:ud 0x00030009:ud //{NoDDChk}
67 (-f0.0) mov (1) gMSGSRC.2:ud 0x00040009:ud //{NoDDChk}
68 send (8) gudREFC(0)<1> mMSGHDRC gMSGSRC<8;8,1>:ud DAPREAD pMSGDSC:ud
69
70 #else
71
72 add (1) pMSGDSC:ud gMSGDSC_R:ud RESP_LEN(3)+nBI_LC_DIFF:ud
73
74 // Compute integer and fractional components of MV
75 asr (2) gMVX_INT<1>:w r[pMV,0]<2;2,1>:w 0x03:w {NoDDClr}
76 and (2) gMVX_FRACC<1>:w r[pMV,0]<2;2,1>:w 0x07:w {NoDDChk}
77
78 // Compute top-left corner position to be loaded
79 mov (2) gMSGSRC.0<1>:d gMVX_INT<2;2,1>:w
80 shl (1) gMSGSRC.0:d gMSGSRC.0:d 1:w
81
82 // Read 16x5 pixels
83 mov (1) gMSGSRC.2:ud 0x00040009:ud {NoDDChk}
84 send (8) gudREFC(0)<1> mMSGHDRC gMSGSRC<8;8,1>:ud DAPREAD pMSGDSC:ud
85 #endif
86
87 //#endif // !defined(__LOADREF_C_10x5__)