| 1 |
/* |
| 2 |
* All Video Processing kernels |
| 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 |
|
| 41 |
///////////////////////////////////////////////////////////////////////////////// |
| 42 |
// Multiple_Loop.asm |
| 43 |
|
| 44 |
|
| 45 |
// This lable is for satisfying component kernel build. |
| 46 |
// DL will remove this label and reference the real one in Multiple_Loop_Head.asm. |
| 47 |
#if defined(COMPONENT) |
| 48 |
VIDEO_PROCESSING_LOOP: |
| 49 |
#endif |
| 50 |
|
| 51 |
|
| 52 |
//===== Possible build flags for component kernels |
| 53 |
// 1) INC_SCALING |
| 54 |
// 2) INC_BLENDING |
| 55 |
// 3) INC_BLENDING and INC_SCALING |
| 56 |
// 4) (no flags) |
| 57 |
|
| 58 |
|
| 59 |
#define MxN_MULTIPLE_BLOCKS |
| 60 |
|
| 61 |
//------------------------------------------------------------------------------ |
| 62 |
#if defined(MxN_MULTIPLE_BLOCKS) |
| 63 |
// Do Multiple Block Processing ------------------------------------------------ |
| 64 |
|
| 65 |
// The 1st block has been processed before entering the loop |
| 66 |
|
| 67 |
// Processed all blocks? |
| 68 |
add.z.f0.0 (1) wNUM_BLKS:w wNUM_BLKS:w -1:w |
| 69 |
|
| 70 |
// Reached multi-block width? |
| 71 |
add (1) wORIX:w wORIX:w 16:w |
| 72 |
cmp.l.f0.1 (1) null:w wORIX:w wFRAME_ENDX:w // acc0.0 has wORIX |
| 73 |
|
| 74 |
#if defined(INC_SCALING) |
| 75 |
// Update SRC_VID_H_ORI for scaling |
| 76 |
mul (1) REG(r,nTEMP0):f fVIDEO_STEP_X:f 16.0:f |
| 77 |
add (1) fSRC_VID_H_ORI:f REG(r,nTEMP0):f fSRC_VID_H_ORI:f |
| 78 |
#endif |
| 79 |
|
| 80 |
#if defined(INC_BLENDING) |
| 81 |
// Update SRC_ALPHA_H_ORI for blending |
| 82 |
mul (1) REG(r,nTEMP0):f fALPHA_STEP_X:f 16.0:f |
| 83 |
add (1) fSRC_ALPHA_H_ORI:f REG(r,nTEMP0):f fSRC_ALPHA_H_ORI:f |
| 84 |
#endif |
| 85 |
|
| 86 |
(f0.0)jmpi (1) END_VIDEO_PROCESSING // All blocks are done - Exit loop |
| 87 |
|
| 88 |
// blocks in the middle of the loop (neither the first nor the last one)? |
| 89 |
// it may be on the left edge (Mx1) or not (1xN) |
| 90 |
mov (1) uwBLOCK_MASK_H<1>:uw uwBLOCK_MASK_H_MIDDLE:uw |
| 91 |
|
| 92 |
// the last block? |
| 93 |
cmp.e.f0.0 (1) null:w wNUM_BLKS:w 1:w |
| 94 |
(f0.0) mov (1) uwBLOCK_MASK_H<1>:uw uwBLOCK_MASK_H_RIGHT:uw |
| 95 |
(f0.0) mov (1) ubBLOCK_MASK_V<1>:ub ubBLOCK_MASK_V_BOTTOM:ub |
| 96 |
|
| 97 |
(f0.1)jmpi (1) VIDEO_PROCESSING_LOOP // If not the end of row, goto the beginning of the loop |
| 98 |
|
| 99 |
//If end of row, restart Horizontal offset and calculate Vertical offsets next row. |
| 100 |
mov (1) wORIX:w wCOPY_ORIX:w |
| 101 |
add (1) wORIY:w wORIY:w 8:w |
| 102 |
|
| 103 |
#if defined(INC_SCALING) |
| 104 |
// Update SRC_VID_H_ORI and SRC_VID_V_ORI for scaling |
| 105 |
mov (1) fSRC_VID_H_ORI:f fFRAME_VID_ORIX:f // Reset normalised X origin to 0 for video and alpha |
| 106 |
mul (1) REG(r,nTEMP0):f fVIDEO_STEP_Y:f 8.0:f |
| 107 |
add (1) fSRC_VID_V_ORI:f REG(r,nTEMP0):f fSRC_VID_V_ORI:f |
| 108 |
#endif |
| 109 |
|
| 110 |
#if defined(INC_BLENDING) |
| 111 |
// Update SRC_ALPHA_H_ORI and SRC_ALPHA_V_ORI for blending |
| 112 |
mov (1) fSRC_ALPHA_H_ORI:f fFRAME_ALPHA_ORIX:f // Reset normalised X origin to 0 for video and alpha |
| 113 |
mul (1) REG(r,nTEMP0):f fALPHA_STEP_Y:f 8.0:f |
| 114 |
add (1) fSRC_ALPHA_V_ORI:f REG(r,nTEMP0):f fSRC_ALPHA_V_ORI:f |
| 115 |
#endif |
| 116 |
|
| 117 |
jmpi (1) VIDEO_PROCESSING_LOOP // Continue Loop |
| 118 |
|
| 119 |
END_VIDEO_PROCESSING: |
| 120 |
nop |
| 121 |
|
| 122 |
#endif |
| 123 |
END_THREAD // End of Thread |