1 /*
2 * Copyright (c) 2019, 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 "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice shall be included
12 * in all copies or substantial portions of the Software.
13 *
14 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
15 * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
16 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
17 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
18 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
19 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
20 * OTHER DEALINGS IN THE SOFTWARE.
21 */
22
23 #include "GammaC.h"
24
25 const uchar R[16] = {
26 0, 0, 0, 0,
27 0, 0, 0, 0,
28 0, 0, 0, 0,
29 0, 0, 0, 0
30 };
31
GammaC(CURBE_INPUT_OUTPUT,GLOBAL_BUFFER_INPUT_OUTPUT)32 _GENX_MAIN_ _CM_CALLABLE_ void GammaC(
33 CURBE_INPUT_OUTPUT,
34 GLOBAL_BUFFER_INPUT_OUTPUT)
35 {
36 /*
37 Buffer layout after shuffle
38 _________________________________________________
39 |_______Block0__________|_______Block1__________|
40 |_______Block2__________|_______Block3__________|
41 |_______Block4__________|_______Block5__________|
42 |_______Block6__________|_______Block7__________|
43
44 Write back buffer layout correlate to the block number#, each box stands for 1 GRF
45 _______________________________________________
46 |____R0_________R1_____|____R2_________R3_____|
47 |____G0_________G1_____|____G2_________G3_____|
48 |____B0_________B1_____|____B2_________B3_____|
49 |____A0_________A1_____|____A2_________A3_____|
50 |____R4_________R5_____|____R6_________R7_____|
51 |____G4_________G5_____|____G6_________G7_____|
52 |____B4_________B5_____|____B6_________B7_____|
53 |____A4_________A5_____|____A6_________A7_____|
54 */
55 matrix_ref<ushort, 16, 16> WriteBackBuffer = DataBuffer.select<4, 1, 64, 1>(Buffer_Index << 2, 0).format<ushort, 16, 16>();
56 matrix<uchar, 1, 256> GammaC_Lut_Linear = GammaC_Lut.format<uchar, 1, 256>();
57 vector<uchar, 16> row(R);
58 matrix<ushort, 2, 16> Temp;
59
60 #pragma unroll
61 for (uchar i = 0; i < 3; i++)
62 {
63 Temp = WriteBackBuffer.select<2, 1, 16, 1>(2 * i, 0);
64 vector<uchar, 16> LutCoordinate;
65 vector<uchar, 16> LutCoordinate1;
66
67 Temp = cm_add<ushort>(Temp, 0x80, SAT);
68
69 LutCoordinate = Temp.row(0).format<uchar>().select<16, 2>(1);
70 LutCoordinate1 = Temp.row(1).format<uchar>().select<16, 2>(1);
71
72 WriteBackBuffer.select<1, 1, 16, 1>(2 * i, 0) = GammaC_Lut_Linear.iselect(row, LutCoordinate);
73 WriteBackBuffer.select<1, 1, 16, 1>(2 * i + 1, 0) = GammaC_Lut_Linear.iselect(row, LutCoordinate1);
74
75 WriteBackBuffer.select<2, 1, 16, 1>(2 * i, 0) = cm_shl<ushort>(WriteBackBuffer.select<2, 1, 16, 1>(2 * i, 0), 8, SAT);
76 }
77
78 #pragma unroll
79 for (uchar i = 0; i < 3; i++)
80 {
81 Temp = WriteBackBuffer.select<2, 1, 16, 1>(2 * i + 8, 0);
82 vector<uchar, 16> LutCoordinate;
83 vector<uchar, 16> LutCoordinate1;
84
85 Temp = cm_add<ushort>(Temp, 0x80, SAT);
86
87 LutCoordinate = Temp.row(0).format<uchar>().select<16, 2>(1);
88 LutCoordinate1 = Temp.row(1).format<uchar>().select<16, 2>(1);
89
90 WriteBackBuffer.select<1, 1, 16, 1>(2 * i + 8, 0) = GammaC_Lut_Linear.iselect(row, LutCoordinate);
91 WriteBackBuffer.select<1, 1, 16, 1>(2 * i + 9, 0) = GammaC_Lut_Linear.iselect(row, LutCoordinate1);
92
93 WriteBackBuffer.select<2, 1, 16, 1>(2 * i + 8, 0) = cm_shl<ushort>(WriteBackBuffer.select<2, 1, 16, 1>(2 * i + 8, 0), 8, SAT);
94 }
95 }
96