| OLD | NEW |
| 1 ; | 1 ; |
| 2 ; jdmerss2.asm - merged upsampling/color conversion (SSE2) | 2 ; jdmerge.asm - merged upsampling/color conversion (64-bit SSE2) |
| 3 ; | 3 ; |
| 4 ; Copyright 2009 Pierre Ossman <ossman@cendio.se> for Cendio AB | 4 ; Copyright 2009 Pierre Ossman <ossman@cendio.se> for Cendio AB |
| 5 ; Copyright 2009 D. R. Commander | 5 ; Copyright 2009 D. R. Commander |
| 6 ; | 6 ; |
| 7 ; Based on | 7 ; Based on |
| 8 ; x86 SIMD extension for IJG JPEG library | 8 ; x86 SIMD extension for IJG JPEG library |
| 9 ; Copyright (C) 1999-2006, MIYASAKA Masaru. | 9 ; Copyright (C) 1999-2006, MIYASAKA Masaru. |
| 10 ; For conditions of distribution and use, see copyright notice in jsimdext.inc | 10 ; For conditions of distribution and use, see copyright notice in jsimdext.inc |
| 11 ; | 11 ; |
| 12 ; This file should be assembled with NASM (Netwide Assembler), | 12 ; This file should be assembled with NASM (Netwide Assembler), |
| 13 ; can *not* be assembled with Microsoft's MASM or any compatible | 13 ; can *not* be assembled with Microsoft's MASM or any compatible |
| 14 ; assembler (including Borland's Turbo Assembler). | 14 ; assembler (including Borland's Turbo Assembler). |
| 15 ; NASM is available from http://nasm.sourceforge.net/ or | 15 ; NASM is available from http://nasm.sourceforge.net/ or |
| 16 ; http://sourceforge.net/project/showfiles.php?group_id=6208 | 16 ; http://sourceforge.net/project/showfiles.php?group_id=6208 |
| 17 ; | 17 ; |
| 18 ; [TAB8] | 18 ; [TAB8] |
| 19 | 19 |
| 20 %include "jsimdext.inc" | 20 %include "jsimdext.inc" |
| 21 | 21 |
| 22 ; -------------------------------------------------------------------------- | 22 ; -------------------------------------------------------------------------- |
| 23 | 23 |
| 24 %define SCALEBITS» 16 | 24 %define SCALEBITS 16 |
| 25 | 25 |
| 26 F_0_344»equ» 22554» » » ; FIX(0.34414) | 26 F_0_344 equ 22554 ; FIX(0.34414) |
| 27 F_0_714»equ» 46802» » » ; FIX(0.71414) | 27 F_0_714 equ 46802 ; FIX(0.71414) |
| 28 F_1_402»equ» 91881» » » ; FIX(1.40200) | 28 F_1_402 equ 91881 ; FIX(1.40200) |
| 29 F_1_772»equ» 116130» » » ; FIX(1.77200) | 29 F_1_772 equ 116130 ; FIX(1.77200) |
| 30 F_0_402»equ» (F_1_402 - 65536)» ; FIX(1.40200) - FIX(1) | 30 F_0_402 equ (F_1_402 - 65536) ; FIX(1.40200) - FIX(1) |
| 31 F_0_285»equ» ( 65536 - F_0_714)» ; FIX(1) - FIX(0.71414) | 31 F_0_285 equ ( 65536 - F_0_714) ; FIX(1) - FIX(0.71414) |
| 32 F_0_228»equ» (131072 - F_1_772)» ; FIX(2) - FIX(1.77200) | 32 F_0_228 equ (131072 - F_1_772) ; FIX(2) - FIX(1.77200) |
| 33 | 33 |
| 34 ; -------------------------------------------------------------------------- | 34 ; -------------------------------------------------------------------------- |
| 35 » SECTION»SEG_CONST | 35 SECTION SEG_CONST |
| 36 | 36 |
| 37 » alignz» 16 | 37 alignz 16 |
| 38 » global» EXTN(jconst_merged_upsample_sse2) PRIVATE | 38 global EXTN(jconst_merged_upsample_sse2) |
| 39 | 39 |
| 40 EXTN(jconst_merged_upsample_sse2): | 40 EXTN(jconst_merged_upsample_sse2): |
| 41 | 41 |
| 42 PW_F0402» times 8 dw F_0_402 | 42 PW_F0402 times 8 dw F_0_402 |
| 43 PW_MF0228» times 8 dw -F_0_228 | 43 PW_MF0228 times 8 dw -F_0_228 |
| 44 PW_MF0344_F0285»times 4 dw -F_0_344, F_0_285 | 44 PW_MF0344_F0285 times 4 dw -F_0_344, F_0_285 |
| 45 PW_ONE» » times 8 dw 1 | 45 PW_ONE times 8 dw 1 |
| 46 PD_ONEHALF» times 4 dd 1 << (SCALEBITS-1) | 46 PD_ONEHALF times 4 dd 1 << (SCALEBITS-1) |
| 47 | 47 |
| 48 » alignz» 16 | 48 alignz 16 |
| 49 | 49 |
| 50 ; -------------------------------------------------------------------------- | 50 ; -------------------------------------------------------------------------- |
| 51 » SECTION»SEG_TEXT | 51 SECTION SEG_TEXT |
| 52 » BITS» 32 | 52 BITS 64 |
| 53 | 53 |
| 54 %include "jdmrgss2.asm" | 54 %include "jdmrgext-sse2-64.asm" |
| 55 | 55 |
| 56 %undef RGB_RED | 56 %undef RGB_RED |
| 57 %undef RGB_GREEN | 57 %undef RGB_GREEN |
| 58 %undef RGB_BLUE | 58 %undef RGB_BLUE |
| 59 %undef RGB_PIXELSIZE | 59 %undef RGB_PIXELSIZE |
| 60 %define RGB_RED EXT_RGB_RED | 60 %define RGB_RED EXT_RGB_RED |
| 61 %define RGB_GREEN EXT_RGB_GREEN | 61 %define RGB_GREEN EXT_RGB_GREEN |
| 62 %define RGB_BLUE EXT_RGB_BLUE | 62 %define RGB_BLUE EXT_RGB_BLUE |
| 63 %define RGB_PIXELSIZE EXT_RGB_PIXELSIZE | 63 %define RGB_PIXELSIZE EXT_RGB_PIXELSIZE |
| 64 %define jsimd_h2v1_merged_upsample_sse2 jsimd_h2v1_extrgb_merged_upsample_sse2 | 64 %define jsimd_h2v1_merged_upsample_sse2 jsimd_h2v1_extrgb_merged_upsample_sse2 |
| 65 %define jsimd_h2v2_merged_upsample_sse2 jsimd_h2v2_extrgb_merged_upsample_sse2 | 65 %define jsimd_h2v2_merged_upsample_sse2 jsimd_h2v2_extrgb_merged_upsample_sse2 |
| 66 %include "jdmrgss2.asm" | 66 %include "jdmrgext-sse2-64.asm" |
| 67 | 67 |
| 68 %undef RGB_RED | 68 %undef RGB_RED |
| 69 %undef RGB_GREEN | 69 %undef RGB_GREEN |
| 70 %undef RGB_BLUE | 70 %undef RGB_BLUE |
| 71 %undef RGB_PIXELSIZE | 71 %undef RGB_PIXELSIZE |
| 72 %define RGB_RED EXT_RGBX_RED | 72 %define RGB_RED EXT_RGBX_RED |
| 73 %define RGB_GREEN EXT_RGBX_GREEN | 73 %define RGB_GREEN EXT_RGBX_GREEN |
| 74 %define RGB_BLUE EXT_RGBX_BLUE | 74 %define RGB_BLUE EXT_RGBX_BLUE |
| 75 %define RGB_PIXELSIZE EXT_RGBX_PIXELSIZE | 75 %define RGB_PIXELSIZE EXT_RGBX_PIXELSIZE |
| 76 %define jsimd_h2v1_merged_upsample_sse2 jsimd_h2v1_extrgbx_merged_upsample_sse2 | 76 %define jsimd_h2v1_merged_upsample_sse2 jsimd_h2v1_extrgbx_merged_upsample_sse2 |
| 77 %define jsimd_h2v2_merged_upsample_sse2 jsimd_h2v2_extrgbx_merged_upsample_sse2 | 77 %define jsimd_h2v2_merged_upsample_sse2 jsimd_h2v2_extrgbx_merged_upsample_sse2 |
| 78 %include "jdmrgss2.asm" | 78 %include "jdmrgext-sse2-64.asm" |
| 79 | 79 |
| 80 %undef RGB_RED | 80 %undef RGB_RED |
| 81 %undef RGB_GREEN | 81 %undef RGB_GREEN |
| 82 %undef RGB_BLUE | 82 %undef RGB_BLUE |
| 83 %undef RGB_PIXELSIZE | 83 %undef RGB_PIXELSIZE |
| 84 %define RGB_RED EXT_BGR_RED | 84 %define RGB_RED EXT_BGR_RED |
| 85 %define RGB_GREEN EXT_BGR_GREEN | 85 %define RGB_GREEN EXT_BGR_GREEN |
| 86 %define RGB_BLUE EXT_BGR_BLUE | 86 %define RGB_BLUE EXT_BGR_BLUE |
| 87 %define RGB_PIXELSIZE EXT_BGR_PIXELSIZE | 87 %define RGB_PIXELSIZE EXT_BGR_PIXELSIZE |
| 88 %define jsimd_h2v1_merged_upsample_sse2 jsimd_h2v1_extbgr_merged_upsample_sse2 | 88 %define jsimd_h2v1_merged_upsample_sse2 jsimd_h2v1_extbgr_merged_upsample_sse2 |
| 89 %define jsimd_h2v2_merged_upsample_sse2 jsimd_h2v2_extbgr_merged_upsample_sse2 | 89 %define jsimd_h2v2_merged_upsample_sse2 jsimd_h2v2_extbgr_merged_upsample_sse2 |
| 90 %include "jdmrgss2.asm" | 90 %include "jdmrgext-sse2-64.asm" |
| 91 | 91 |
| 92 %undef RGB_RED | 92 %undef RGB_RED |
| 93 %undef RGB_GREEN | 93 %undef RGB_GREEN |
| 94 %undef RGB_BLUE | 94 %undef RGB_BLUE |
| 95 %undef RGB_PIXELSIZE | 95 %undef RGB_PIXELSIZE |
| 96 %define RGB_RED EXT_BGRX_RED | 96 %define RGB_RED EXT_BGRX_RED |
| 97 %define RGB_GREEN EXT_BGRX_GREEN | 97 %define RGB_GREEN EXT_BGRX_GREEN |
| 98 %define RGB_BLUE EXT_BGRX_BLUE | 98 %define RGB_BLUE EXT_BGRX_BLUE |
| 99 %define RGB_PIXELSIZE EXT_BGRX_PIXELSIZE | 99 %define RGB_PIXELSIZE EXT_BGRX_PIXELSIZE |
| 100 %define jsimd_h2v1_merged_upsample_sse2 jsimd_h2v1_extbgrx_merged_upsample_sse2 | 100 %define jsimd_h2v1_merged_upsample_sse2 jsimd_h2v1_extbgrx_merged_upsample_sse2 |
| 101 %define jsimd_h2v2_merged_upsample_sse2 jsimd_h2v2_extbgrx_merged_upsample_sse2 | 101 %define jsimd_h2v2_merged_upsample_sse2 jsimd_h2v2_extbgrx_merged_upsample_sse2 |
| 102 %include "jdmrgss2.asm" | 102 %include "jdmrgext-sse2-64.asm" |
| 103 | 103 |
| 104 %undef RGB_RED | 104 %undef RGB_RED |
| 105 %undef RGB_GREEN | 105 %undef RGB_GREEN |
| 106 %undef RGB_BLUE | 106 %undef RGB_BLUE |
| 107 %undef RGB_PIXELSIZE | 107 %undef RGB_PIXELSIZE |
| 108 %define RGB_RED EXT_XBGR_RED | 108 %define RGB_RED EXT_XBGR_RED |
| 109 %define RGB_GREEN EXT_XBGR_GREEN | 109 %define RGB_GREEN EXT_XBGR_GREEN |
| 110 %define RGB_BLUE EXT_XBGR_BLUE | 110 %define RGB_BLUE EXT_XBGR_BLUE |
| 111 %define RGB_PIXELSIZE EXT_XBGR_PIXELSIZE | 111 %define RGB_PIXELSIZE EXT_XBGR_PIXELSIZE |
| 112 %define jsimd_h2v1_merged_upsample_sse2 jsimd_h2v1_extxbgr_merged_upsample_sse2 | 112 %define jsimd_h2v1_merged_upsample_sse2 jsimd_h2v1_extxbgr_merged_upsample_sse2 |
| 113 %define jsimd_h2v2_merged_upsample_sse2 jsimd_h2v2_extxbgr_merged_upsample_sse2 | 113 %define jsimd_h2v2_merged_upsample_sse2 jsimd_h2v2_extxbgr_merged_upsample_sse2 |
| 114 %include "jdmrgss2.asm" | 114 %include "jdmrgext-sse2-64.asm" |
| 115 | 115 |
| 116 %undef RGB_RED | 116 %undef RGB_RED |
| 117 %undef RGB_GREEN | 117 %undef RGB_GREEN |
| 118 %undef RGB_BLUE | 118 %undef RGB_BLUE |
| 119 %undef RGB_PIXELSIZE | 119 %undef RGB_PIXELSIZE |
| 120 %define RGB_RED EXT_XRGB_RED | 120 %define RGB_RED EXT_XRGB_RED |
| 121 %define RGB_GREEN EXT_XRGB_GREEN | 121 %define RGB_GREEN EXT_XRGB_GREEN |
| 122 %define RGB_BLUE EXT_XRGB_BLUE | 122 %define RGB_BLUE EXT_XRGB_BLUE |
| 123 %define RGB_PIXELSIZE EXT_XRGB_PIXELSIZE | 123 %define RGB_PIXELSIZE EXT_XRGB_PIXELSIZE |
| 124 %define jsimd_h2v1_merged_upsample_sse2 jsimd_h2v1_extxrgb_merged_upsample_sse2 | 124 %define jsimd_h2v1_merged_upsample_sse2 jsimd_h2v1_extxrgb_merged_upsample_sse2 |
| 125 %define jsimd_h2v2_merged_upsample_sse2 jsimd_h2v2_extxrgb_merged_upsample_sse2 | 125 %define jsimd_h2v2_merged_upsample_sse2 jsimd_h2v2_extxrgb_merged_upsample_sse2 |
| 126 %include "jdmrgss2.asm" | 126 %include "jdmrgext-sse2-64.asm" |
| OLD | NEW |