Mercurial > libavcodec.hg
annotate bfin/idct_bfin.S @ 12471:d821f7c64fc9 libavcodec
Remove use of deprecated functions av_image_fill_pointers/linesizes in
libavcodec/utils.c, fix warnings.
author | stefano |
---|---|
date | Tue, 07 Sep 2010 21:24:03 +0000 |
parents | 8327c5b4df9b |
children |
rev | line source |
---|---|
4765
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
1 /* |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
2 * idct BlackFin |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
3 * |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
4 * Copyright (C) 2007 Marc Hoffman <marc.hoffman@analog.com> |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
5 * |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
6 * This file is part of FFmpeg. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
7 * |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
8 * FFmpeg is free software; you can redistribute it and/or |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
9 * modify it under the terms of the GNU Lesser General Public |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
10 * License as published by the Free Software Foundation; either |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
11 * version 2.1 of the License, or (at your option) any later version. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
12 * |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
13 * FFmpeg is distributed in the hope that it will be useful, |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
14 * but WITHOUT ANY WARRANTY; without even the implied warranty of |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
16 * Lesser General Public License for more details. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
17 * |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
18 * You should have received a copy of the GNU Lesser General Public |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
19 * License along with FFmpeg; if not, write to the Free Software |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
20 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
21 */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
22 /* |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
23 This blackfin DSP code implements an 8x8 inverse type II DCT. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
24 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
25 Prototype : void ff_bfin_idct(DCTELEM *in) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
26 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
27 Registers Used : A0, A1, R0-R7, I0-I3, B0, B2, B3, M0-M2, L0-L3, P0-P5, LC0. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
28 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
29 Performance : |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
30 Code Size : 498 Bytes. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
31 Cycle Count : 417 Cycles |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
32 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
33 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
34 ----------------------------------------------------------- |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
35 FFMPEG conformance testing results |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
36 ----------------------------------------------------------- |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
37 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
38 dct-test: modified with the following |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
39 dct_error("BFINidct", 1, ff_bfin_idct, idct, test); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
40 produces the following output |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
41 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
42 root:/u/ffmpeg/bhead/libavcodec> ./dct-test -i |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
43 ffmpeg DCT/IDCT test |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
44 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
45 8 15 -2 21 24 17 0 10 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
46 2 -10 -5 -5 -3 7 -14 -3 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
47 2 -13 -10 -19 18 -6 6 -2 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
48 9 4 16 -3 9 12 10 15 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
49 15 -9 -2 10 1 16 0 -15 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
50 -15 5 7 3 13 0 13 20 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
51 -6 -15 24 9 -18 1 9 -22 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
52 -8 25 23 2 -7 0 30 13 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
53 IDCT BFINidct: err_inf=1 err2=0.01002344 syserr=0.00150000 maxout=266 blockSumErr=64 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
54 IDCT BFINidct: 88.3 kdct/s |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
55 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
56 */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
57 |
11063 | 58 #include "config.h" |
4765
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
59 #include "config_bfin.h" |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
60 |
11063 | 61 #if defined(__FDPIC__) && CONFIG_SRAM |
4765
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
62 .section .l1.data.B,"aw",@progbits |
6362
78aa57eba353
FLAT objects cannot have multiple sections, so using the L1 attributes breaks
diego
parents:
5001
diff
changeset
|
63 #else |
78aa57eba353
FLAT objects cannot have multiple sections, so using the L1 attributes breaks
diego
parents:
5001
diff
changeset
|
64 .data |
78aa57eba353
FLAT objects cannot have multiple sections, so using the L1 attributes breaks
diego
parents:
5001
diff
changeset
|
65 #endif |
4765
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
66 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
67 .align 4; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
68 coefs: |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
69 .short 0x5a82; // C4 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
70 .short 0x5a82; // C4 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
71 .short 0x30FC; //cos(3pi/8) C6 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
72 .short 0x7642; //cos(pi/8) C2 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
73 .short 0x18F9; //cos(7pi/16) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
74 .short 0x7D8A; //cos(pi/16) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
75 .short 0x471D; //cos(5pi/16) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
76 .short 0x6A6E; //cos(3pi/16) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
77 .short 0x18F9; //cos(7pi/16) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
78 .short 0x7D8A; //cos(pi/16) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
79 |
11063 | 80 #if defined(__FDPIC__) && CONFIG_SRAM |
6362
78aa57eba353
FLAT objects cannot have multiple sections, so using the L1 attributes breaks
diego
parents:
5001
diff
changeset
|
81 .section .l1.data.A,"aw",@progbits |
78aa57eba353
FLAT objects cannot have multiple sections, so using the L1 attributes breaks
diego
parents:
5001
diff
changeset
|
82 #endif |
4765
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
83 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
84 vtmp: .space 256 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
85 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
86 #define TMP0 FP-8 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
87 #define TMP1 FP-12 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
88 #define TMP2 FP-16 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
89 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
90 |
6362
78aa57eba353
FLAT objects cannot have multiple sections, so using the L1 attributes breaks
diego
parents:
5001
diff
changeset
|
91 .text |
4765
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
92 DEFUN(idct,mL1, |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
93 (DCTELEM *block)): |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
94 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
95 /********************** Function Prologue *********************************/ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
96 link 16; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
97 [--SP] = (R7:4, P5:3); // Push the registers onto the stack. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
98 B0 = R0; // Pointer to Input matrix |
6362
78aa57eba353
FLAT objects cannot have multiple sections, so using the L1 attributes breaks
diego
parents:
5001
diff
changeset
|
99 RELOC(R1, P3, coefs); // Pointer to Coefficients |
78aa57eba353
FLAT objects cannot have multiple sections, so using the L1 attributes breaks
diego
parents:
5001
diff
changeset
|
100 RELOC(R2, P3, vtmp); // Pointer to Temporary matrix |
4765
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
101 B3 = R1; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
102 B2 = R2; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
103 L3 = 20; // L3 is used for making the coefficient array |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
104 // circular. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
105 // MUST BE RESTORED TO ZERO at function exit. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
106 M1 = 16 (X); // All these registers are initialized for |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
107 M3 = 8(X); // modifying address offsets. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
108 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
109 I0 = B0; // I0 points to Input Element (0, 0). |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
110 I2 = B0; // I2 points to Input Element (0, 0). |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
111 I2 += M3 || R0.H = W[I0]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
112 // Element 0 is read into R0.H |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
113 I1 = I2; // I1 points to input Element (0, 6). |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
114 I1 += 4 || R0.L = W[I2++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
115 // I2 points to input Element (0, 4). |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
116 // Element 4 is read into R0.L. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
117 P2 = 8 (X); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
118 P3 = 32 (X); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
119 P4 = -32 (X); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
120 P5 = 98 (X); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
121 R7 = 0x8000(Z); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
122 I3 = B3; // I3 points to Coefficients |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
123 P0 = B2; // P0 points to array Element (0, 0) of temp |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
124 P1 = B2; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
125 R7 = [I3++] || [TMP2]=R7; // Coefficient C4 is read into R7.H and R7.L. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
126 MNOP; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
127 NOP; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
128 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
129 /* |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
130 * A1 = Y0 * cos(pi/4) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
131 * A0 = Y0 * cos(pi/4) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
132 * A1 = A1 + Y4 * cos(pi/4) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
133 * A0 = A0 - Y4 * cos(pi/4) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
134 * load: |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
135 * R1=(Y2,Y6) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
136 * R7=(C2,C6) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
137 * res: |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
138 * R3=Y0, R2=Y4 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
139 */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
140 A1=R7.H*R0.H, A0=R7.H*R0.H (IS) || I0+= 4 || R1.L=W[I1++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
141 R3=(A1+=R7.H*R0.L), R2=(A0-=R7.H*R0.L) (IS) || R1.H=W[I0--] || R7=[I3++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
142 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
143 LSETUP (.0, .1) LC0 = P2; // perform 8 1d idcts |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
144 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
145 P2 = 112 (X); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
146 P1 = P1 + P2; // P1 points to element (7, 0) of temp buffer. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
147 P2 = -94(X); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
148 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
149 .0: |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
150 /* |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
151 * A1 = Y2 * cos(3pi/8) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
152 * A0 = Y2 * cos(pi/8) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
153 * A1 = A1 - Y6 * cos(pi/8) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
154 * A0 = A0 + Y6 * cos(3pi/8) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
155 * R5 = (Y1,Y7) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
156 * R7 = (C1,C7) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
157 * res: |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
158 * R1=Y2, R0=Y6 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
159 */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
160 A1=R7.L*R1.H, A0=R7.H*R1.H (IS) || I0+=4 || R5.H=W[I0]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
161 R1=(A1-=R7.H*R1.L), R0=(A0+=R7.L*R1.L) (IS) || R5.L=W[I1--] || R7=[I3++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
162 /* |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
163 * Y0 = Y0 + Y6. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
164 * Y4 = Y4 + Y2. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
165 * Y2 = Y4 - Y2. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
166 * Y6 = Y0 - Y6. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
167 * R3 is saved |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
168 * R6.l=Y3 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
169 * note: R3: Y0, R2: Y4, R1: Y2, R0: Y6 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
170 */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
171 R3=R3+R0, R0=R3-R0; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
172 R2=R2+R1, R1=R2-R1 || [TMP0]=R3 || R6.L=W[I0--]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
173 /* |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
174 * Compute the odd portion (1,3,5,7) even is done. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
175 * |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
176 * Y1 = C7 * Y1 - C1 * Y7 + C3 * Y5 - C5 * Y3. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
177 * Y7 = C1 * Y1 + C7 * Y7 + C5 * Y5 + C3 * Y3. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
178 * Y5 = C5 * Y1 + C3 * Y7 + C7 * Y5 - C1 * Y3. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
179 * Y3 = C3 * Y1 - C5 * Y7 - C1 * Y5 - C7 * Y3. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
180 */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
181 // R5=(Y1,Y7) R6=(Y5,Y3) // R7=(C1,C7) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
182 A1 =R7.L*R5.H, A0 =R7.H*R5.H (IS) || [TMP1]=R2 || R6.H=W[I2--]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
183 A1-=R7.H*R5.L, A0+=R7.L*R5.L (IS) || I0-=4 || R7=[I3++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
184 A1+=R7.H*R6.H, A0+=R7.L*R6.H (IS) || I0+=M1; // R7=(C3,C5) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
185 R3 =(A1-=R7.L*R6.L), R2 =(A0+=R7.H*R6.L) (IS); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
186 A1 =R7.L*R5.H, A0 =R7.H*R5.H (IS) || R4=[TMP0]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
187 A1+=R7.H*R5.L, A0-=R7.L*R5.L (IS) || I1+=M1 || R7=[I3++]; // R7=(C1,C7) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
188 A1+=R7.L*R6.H, A0-=R7.H*R6.H (IS); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
189 R7 =(A1-=R7.H*R6.L), R6 =(A0-=R7.L*R6.L) (IS) || I2+=M1; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
190 // R3=Y1, R2=Y7, R7=Y5, R6=Y3 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
191 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
192 /* Transpose write column. */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
193 R5.H=R4+R2 (RND12); // Y0=Y0+Y7 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
194 R5.L=R4-R2 (RND12) || R4 = [TMP1]; // Y7=Y7-Y0 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
195 R2.H=R1+R7 (RND12) || W[P0++P3]=R5.H; // Y2=Y2+Y5 st Y0 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
196 R2.L=R1-R7 (RND12) || W[P1++P4]=R5.L || R7=[I3++]; // Y5=Y2-Y5 st Y7 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
197 R5.H=R0-R3 (RND12) || W[P0++P3]=R2.H || R1.L=W[I1++]; // Y1=Y6-Y1 st Y2 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
198 R5.L=R0+R3 (RND12) || W[P1++P4]=R2.L || R0.H=W[I0++]; // Y6=Y6+Y1 st Y5 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
199 R3.H=R4-R6 (RND12) || W[P0++P3]=R5.H || R0.L=W[I2++]; // Y3=Y3-Y4 st Y1 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
200 R3.L=R4+R6 (RND12) || W[P1++P4]=R5.L || R1.H=W[I0++]; // Y4=Y3+Y4 st Y6 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
201 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
202 /* pipeline loop start, + drain Y3, Y4 */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
203 A1=R7.H*R0.H, A0=R7.H*R0.H (IS) || W[P0++P2]= R3.H || R1.H = W[I0--]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
204 .1: R3=(A1+=R7.H*R0.L), R2=(A0-=R7.H*R0.L) (IS) || W[P1++P5]= R3.L || R7 = [I3++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
205 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
206 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
207 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
208 I0 = B2; // I0 points to Input Element (0, 0) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
209 I2 = B2; // I2 points to Input Element (0, 0) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
210 I2 += M3 || R0.H = W[I0]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
211 // Y0 is read in R0.H |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
212 I1 = I2; // I1 points to input Element (0, 6) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
213 I1 += 4 || R0.L = W[I2++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
214 // I2 points to input Element (0, 4) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
215 // Y4 is read in R0.L |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
216 P2 = 8 (X); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
217 I3 = B3; // I3 points to Coefficients |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
218 P0 = B0; // P0 points to array Element (0, 0) for writing |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
219 // output |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
220 P1 = B0; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
221 R7 = [I3++]; // R7.H = C4 and R7.L = C4 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
222 NOP; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
223 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
224 /* |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
225 * A1 = Y0 * cos(pi/4) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
226 * A0 = Y0 * cos(pi/4) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
227 * A1 = A1 + Y4 * cos(pi/4) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
228 * A0 = A0 - Y4 * cos(pi/4) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
229 * load: |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
230 * R1=(Y2,Y6) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
231 * R7=(C2,C6) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
232 * res: |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
233 * R3=Y0, R2=Y4 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
234 */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
235 A1=R7.H*R0.H, A0=R7.H*R0.H (IS) || I0+=4 || R1.L=W[I1++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
236 R3=(A1+=R7.H*R0.L), R2=(A0-=R7.H*R0.L) (IS) || R1.H=W[I0--] || R7=[I3++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
237 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
238 LSETUP (.2, .3) LC0 = P2; // peform 8 1d idcts |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
239 P2 = 112 (X); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
240 P1 = P1 + P2; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
241 P2 = -94(X); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
242 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
243 .2: |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
244 /* |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
245 * A1 = Y2 * cos(3pi/8) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
246 * A0 = Y2 * cos(pi/8) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
247 * A1 = A1 - Y6 * cos(pi/8) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
248 * A0 = A0 + Y6 * cos(3pi/8) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
249 * R5 = (Y1,Y7) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
250 * R7 = (C1,C7) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
251 * res: |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
252 * R1=Y2, R0=Y6 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
253 */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
254 A1=R7.L*R1.H, A0=R7.H*R1.H (IS) || I0+=4 || R5.H=W[I0]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
255 R1=(A1-=R7.H*R1.L), R0=(A0+=R7.L*R1.L) (IS) || R5.L=W[I1--] || R7=[I3++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
256 /* |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
257 * Y0 = Y0 + Y6. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
258 * Y4 = Y4 + Y2. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
259 * Y2 = Y4 - Y2. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
260 * Y6 = Y0 - Y6. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
261 * R3 is saved |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
262 * R6.l=Y3 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
263 * note: R3: Y0, R2: Y4, R1: Y2, R0: Y6 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
264 */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
265 R3=R3+R0, R0=R3-R0; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
266 R2=R2+R1, R1=R2-R1 || [TMP0]=R3 || R6.L=W[I0--]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
267 /* |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
268 * Compute the odd portion (1,3,5,7) even is done. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
269 * |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
270 * Y1 = C7 * Y1 - C1 * Y7 + C3 * Y5 - C5 * Y3. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
271 * Y7 = C1 * Y1 + C7 * Y7 + C5 * Y5 + C3 * Y3. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
272 * Y5 = C5 * Y1 + C3 * Y7 + C7 * Y5 - C1 * Y3. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
273 * Y3 = C3 * Y1 - C5 * Y7 - C1 * Y5 - C7 * Y3. |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
274 */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
275 // R5=(Y1,Y7) R6=(Y5,Y3) // R7=(C1,C7) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
276 A1 =R7.L*R5.H, A0 =R7.H*R5.H (IS) || [TMP1]=R2 || R6.H=W[I2--]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
277 A1-=R7.H*R5.L, A0+=R7.L*R5.L (IS) || I0-=4 || R7=[I3++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
278 A1+=R7.H*R6.H, A0+=R7.L*R6.H (IS) || I0+=M1; // R7=(C3,C5) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
279 R3 =(A1-=R7.L*R6.L), R2 =(A0+=R7.H*R6.L) (IS); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
280 A1 =R7.L*R5.H, A0 =R7.H*R5.H (IS) || R4=[TMP0]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
281 A1+=R7.H*R5.L, A0-=R7.L*R5.L (IS) || I1+=M1 || R7=[I3++]; // R7=(C1,C7) |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
282 A1+=R7.L*R6.H, A0-=R7.H*R6.H (IS); |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
283 R7 =(A1-=R7.H*R6.L), R6 =(A0-=R7.L*R6.L) (IS) || I2+=M1; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
284 // R3=Y1, R2=Y7, R7=Y5, R6=Y3 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
285 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
286 /* Transpose write column. */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
287 R5.H=R4+R2 (RND20); // Y0=Y0+Y7 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
288 R5.L=R4-R2 (RND20) || R4 = [TMP1]; // Y7=Y7-Y0 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
289 R2.H=R1+R7 (RND20) || W[P0++P3]=R5.H; // Y2=Y2+Y5 st Y0 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
290 R2.L=R1-R7 (RND20) || W[P1++P4]=R5.L || R7=[I3++]; // Y5=Y2-Y5 st Y7 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
291 R5.H=R0-R3 (RND20) || W[P0++P3]=R2.H || R1.L=W[I1++]; // Y1=Y6-Y1 st Y2 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
292 R5.L=R0+R3 (RND20) || W[P1++P4]=R2.L || R0.H=W[I0++]; // Y6=Y6+Y1 st Y5 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
293 R3.H=R4-R6 (RND20) || W[P0++P3]=R5.H || R0.L=W[I2++]; // Y3=Y3-Y4 st Y1 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
294 R3.L=R4+R6 (RND20) || W[P1++P4]=R5.L || R1.H=W[I0++]; // Y4=Y3+Y4 st Y6 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
295 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
296 /* pipeline loop start, + drain Y3, Y4 */ |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
297 A1=R7.H*R0.H, A0=R7.H*R0.H (IS) || W[P0++P2]= R3.H || R1.H = W[I0--]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
298 .3: R3=(A1+=R7.H*R0.L), R2=(A0-=R7.H*R0.L) (IS) || W[P1++P5]= R3.L || R7 = [I3++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
299 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
300 L3 = 0; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
301 (R7:4,P5:3)=[SP++]; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
302 unlink; |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
303 RTS; |
5001 | 304 DEFUN_END(idct) |
4765
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
305 |
85298e8c55c4
bfin dsputils, basic pixel operations sads, diffs, motion compensation
diego
parents:
diff
changeset
|
306 |