Debian Codegraph @

src/shaders/h264/mc/interpolate_C_4x4.asm

raw
1 /*
2 * Interpolation kernel for chrominance 4x4 motion compensation
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: Interpolate_C_4x4_Func.asm
41 //
42 // Interpolation kernel for chrominance 4x4 motion compensation
43 //
44 // $Revision: 8 $
45 // $Date: 10/09/06 4:00p $
46 //
47
48
49 //#if !defined(__Interpolate_C_4x4_Func__) // Make sure this is only included once
50 //#define __Interpolate_C_4x4_Func__
51
52
53 INTERLABEL(Interpolate_C_4x4_Func):
54
55
56 // (8-xFrac) and (8-yFrac)
57 add (2) gW0<1>:w gMVX_FRACC<2;2,1>:w -0x08:w
58
59 // Compute the GRF address of the starting position of the reference area
60 mov (1) pREF0:w nOFFSET_REFC:w {NoDDClr}
61 mov (1) pREF1:uw nOFFSET_REFC+16:w {NoDDChk,NoDDClr}
62 mov (1) pRESULT:uw gpINTPC:uw {NoDDChk}
63
64 // gCOEFA = (8-xFrac)*(8-yFrac)
65 // gCOEFB = xFrac*(8-yFrac)
66 // gCOEFC = (8-xFrac)*yFrac
67 // gCOEFD = xFrac*yFrac
68 mul (1) gCOEFD:w gMVX_FRACC:w gMVY_FRACC:w {NoDDClr}
69 mul (1) gCOEFA:w -gW0:w -gW1:uw {NoDDClr,NoDDChk}
70 mul (1) gCOEFB:w gMVX_FRACC:w -gW1:uw {NoDDClr,NoDDChk}
71 mul (1) gCOEFC:w -gW0:w gMVY_FRACC:w {NoDDChk}
72
73 add (2) gW0<1>:uw pREF0<2;2,1>:uw 16:w
74
75 // (8-xFrac)*(8-yFrac)*A
76 // ---------------------
77 mul (16) acc0<1>:uw r[pREF0,0]<16;8,1>:ub gCOEFA:uw
78 mul (16) acc1<1>:uw r[pREF0,nGRFWIB]<16;8,1>:ub gCOEFA:uw
79
80 // xFrac*(8-yFrac)*B
81 // -------------------
82 mac (16) acc0<1>:uw r[pREF0,2]<16;8,1>:ub gCOEFB:uw
83 mac (16) acc1<1>:uw r[pREF0,nGRFWIB+2]<16;8,1>:ub gCOEFB:uw
84
85 // (8-xFrac)*yFrac*C
86 // -------------------
87 mov (2) pREF0<1>:uw gW0<2;2,1>:uw
88 mac (16) acc0<1>:uw r[pREF0,0]<8,1>:ub gCOEFC:uw
89 mac (16) acc1<1>:uw r[pREF0,nGRFWIB]<8,1>:ub gCOEFC:uw
90
91 // xFrac*yFrac*D
92 // -----------------
93 mac (16) r[pRESULT]<1>:uw r[pREF0,2]<8,1>:ub gCOEFD:uw
94 mac (16) r[pRESULT,GRFWIB]<1>:uw r[pREF0,nGRFWIB+2]<8,1>:ub gCOEFD:uw {SecHalf}
95
96
97 //#endif // !defined(__Interpolate_C_4x4_Func__)