Fork of DMemWin by
png/pnggccrd.c@2:0e2ef1edf01b, 2016-06-02 (annotated)
- Committer:
- destinyXfate
- Date:
- Thu Jun 02 04:52:54 2016 +0000
- Revision:
- 2:0e2ef1edf01b
;
Who changed what in which revision?
User | Revision | Line number | New contents of line |
---|---|---|---|
destinyXfate | 2:0e2ef1edf01b | 1 | |
destinyXfate | 2:0e2ef1edf01b | 2 | /* pnggccrd.c - mixed C/assembler version of utilities to read a PNG file |
destinyXfate | 2:0e2ef1edf01b | 3 | * |
destinyXfate | 2:0e2ef1edf01b | 4 | * For Intel x86 CPU (Pentium-MMX or later) and GNU C compiler. |
destinyXfate | 2:0e2ef1edf01b | 5 | * |
destinyXfate | 2:0e2ef1edf01b | 6 | * See http://www.intel.com/drg/pentiumII/appnotes/916/916.htm |
destinyXfate | 2:0e2ef1edf01b | 7 | * and http://www.intel.com/drg/pentiumII/appnotes/923/923.htm |
destinyXfate | 2:0e2ef1edf01b | 8 | * for Intel's performance analysis of the MMX vs. non-MMX code. |
destinyXfate | 2:0e2ef1edf01b | 9 | * |
destinyXfate | 2:0e2ef1edf01b | 10 | * Last changed in libpng 1.2.15 January 5, 2007 |
destinyXfate | 2:0e2ef1edf01b | 11 | * For conditions of distribution and use, see copyright notice in png.h |
destinyXfate | 2:0e2ef1edf01b | 12 | * Copyright (c) 1998-2007 Glenn Randers-Pehrson |
destinyXfate | 2:0e2ef1edf01b | 13 | * Copyright (c) 1998, Intel Corporation |
destinyXfate | 2:0e2ef1edf01b | 14 | * |
destinyXfate | 2:0e2ef1edf01b | 15 | * Based on MSVC code contributed by Nirav Chhatrapati, Intel Corp., 1998. |
destinyXfate | 2:0e2ef1edf01b | 16 | * Interface to libpng contributed by Gilles Vollant, 1999. |
destinyXfate | 2:0e2ef1edf01b | 17 | * GNU C port by Greg Roelofs, 1999-2001. |
destinyXfate | 2:0e2ef1edf01b | 18 | * |
destinyXfate | 2:0e2ef1edf01b | 19 | * Lines 2350-4300 converted in place with intel2gas 1.3.1: |
destinyXfate | 2:0e2ef1edf01b | 20 | * |
destinyXfate | 2:0e2ef1edf01b | 21 | * intel2gas -mdI pnggccrd.c.partially-msvc -o pnggccrd.c |
destinyXfate | 2:0e2ef1edf01b | 22 | * |
destinyXfate | 2:0e2ef1edf01b | 23 | * and then cleaned up by hand. See http://hermes.terminal.at/intel2gas/ . |
destinyXfate | 2:0e2ef1edf01b | 24 | * |
destinyXfate | 2:0e2ef1edf01b | 25 | * NOTE: A sufficiently recent version of GNU as (or as.exe under DOS/Windows) |
destinyXfate | 2:0e2ef1edf01b | 26 | * is required to assemble the newer MMX instructions such as movq. |
destinyXfate | 2:0e2ef1edf01b | 27 | * For djgpp, see |
destinyXfate | 2:0e2ef1edf01b | 28 | * |
destinyXfate | 2:0e2ef1edf01b | 29 | * ftp://ftp.simtel.net/pub/simtelnet/gnu/djgpp/v2gnu/bnu281b.zip |
destinyXfate | 2:0e2ef1edf01b | 30 | * |
destinyXfate | 2:0e2ef1edf01b | 31 | * (or a later version in the same directory). For Linux, check your |
destinyXfate | 2:0e2ef1edf01b | 32 | * distribution's web site(s) or try these links: |
destinyXfate | 2:0e2ef1edf01b | 33 | * |
destinyXfate | 2:0e2ef1edf01b | 34 | * http://rufus.w3.org/linux/RPM/binutils.html |
destinyXfate | 2:0e2ef1edf01b | 35 | * http://www.debian.org/Packages/stable/devel/binutils.html |
destinyXfate | 2:0e2ef1edf01b | 36 | * ftp://ftp.slackware.com/pub/linux/slackware/slackware/slakware/d1/ |
destinyXfate | 2:0e2ef1edf01b | 37 | * binutils.tgz |
destinyXfate | 2:0e2ef1edf01b | 38 | * |
destinyXfate | 2:0e2ef1edf01b | 39 | * For other platforms, see the main GNU site: |
destinyXfate | 2:0e2ef1edf01b | 40 | * |
destinyXfate | 2:0e2ef1edf01b | 41 | * ftp://ftp.gnu.org/pub/gnu/binutils/ |
destinyXfate | 2:0e2ef1edf01b | 42 | * |
destinyXfate | 2:0e2ef1edf01b | 43 | * Version 2.5.2l.15 is definitely too old... |
destinyXfate | 2:0e2ef1edf01b | 44 | */ |
destinyXfate | 2:0e2ef1edf01b | 45 | |
destinyXfate | 2:0e2ef1edf01b | 46 | /* |
destinyXfate | 2:0e2ef1edf01b | 47 | * TEMPORARY PORTING NOTES AND CHANGELOG (mostly by Greg Roelofs) |
destinyXfate | 2:0e2ef1edf01b | 48 | * ===================================== |
destinyXfate | 2:0e2ef1edf01b | 49 | * |
destinyXfate | 2:0e2ef1edf01b | 50 | * 19991006: |
destinyXfate | 2:0e2ef1edf01b | 51 | * - fixed sign error in post-MMX cleanup code (16- & 32-bit cases) |
destinyXfate | 2:0e2ef1edf01b | 52 | * |
destinyXfate | 2:0e2ef1edf01b | 53 | * 19991007: |
destinyXfate | 2:0e2ef1edf01b | 54 | * - additional optimizations (possible or definite): |
destinyXfate | 2:0e2ef1edf01b | 55 | * x [DONE] write MMX code for 64-bit case (pixel_bytes == 8) [not tested] |
destinyXfate | 2:0e2ef1edf01b | 56 | * - write MMX code for 48-bit case (pixel_bytes == 6) |
destinyXfate | 2:0e2ef1edf01b | 57 | * - figure out what's up with 24-bit case (pixel_bytes == 3): |
destinyXfate | 2:0e2ef1edf01b | 58 | * why subtract 8 from width_mmx in the pass 4/5 case? |
destinyXfate | 2:0e2ef1edf01b | 59 | * (only width_mmx case) (near line 1606) |
destinyXfate | 2:0e2ef1edf01b | 60 | * x [DONE] replace pixel_bytes within each block with the true |
destinyXfate | 2:0e2ef1edf01b | 61 | * constant value (or are compilers smart enough to do that?) |
destinyXfate | 2:0e2ef1edf01b | 62 | * - rewrite all MMX interlacing code so it's aligned with |
destinyXfate | 2:0e2ef1edf01b | 63 | * the *beginning* of the row buffer, not the end. This |
destinyXfate | 2:0e2ef1edf01b | 64 | * would not only allow one to eliminate half of the memory |
destinyXfate | 2:0e2ef1edf01b | 65 | * writes for odd passes (that is, pass == odd), it may also |
destinyXfate | 2:0e2ef1edf01b | 66 | * eliminate some unaligned-data-access exceptions (assuming |
destinyXfate | 2:0e2ef1edf01b | 67 | * there's a penalty for not aligning 64-bit accesses on |
destinyXfate | 2:0e2ef1edf01b | 68 | * 64-bit boundaries). The only catch is that the "leftover" |
destinyXfate | 2:0e2ef1edf01b | 69 | * pixel(s) at the end of the row would have to be saved, |
destinyXfate | 2:0e2ef1edf01b | 70 | * but there are enough unused MMX registers in every case, |
destinyXfate | 2:0e2ef1edf01b | 71 | * so this is not a problem. A further benefit is that the |
destinyXfate | 2:0e2ef1edf01b | 72 | * post-MMX cleanup code (C code) in at least some of the |
destinyXfate | 2:0e2ef1edf01b | 73 | * cases could be done within the assembler block. |
destinyXfate | 2:0e2ef1edf01b | 74 | * x [DONE] the "v3 v2 v1 v0 v7 v6 v5 v4" comments are confusing, |
destinyXfate | 2:0e2ef1edf01b | 75 | * inconsistent, and don't match the MMX Programmer's Reference |
destinyXfate | 2:0e2ef1edf01b | 76 | * Manual conventions anyway. They should be changed to |
destinyXfate | 2:0e2ef1edf01b | 77 | * "b7 b6 b5 b4 b3 b2 b1 b0," where b0 indicates the byte that |
destinyXfate | 2:0e2ef1edf01b | 78 | * was lowest in memory (e.g., corresponding to a left pixel) |
destinyXfate | 2:0e2ef1edf01b | 79 | * and b7 is the byte that was highest (e.g., a right pixel). |
destinyXfate | 2:0e2ef1edf01b | 80 | * |
destinyXfate | 2:0e2ef1edf01b | 81 | * 19991016: |
destinyXfate | 2:0e2ef1edf01b | 82 | * - Brennan's Guide notwithstanding, gcc under Linux does *not* |
destinyXfate | 2:0e2ef1edf01b | 83 | * want globals prefixed by underscores when referencing them-- |
destinyXfate | 2:0e2ef1edf01b | 84 | * i.e., if the variable is const4, then refer to it as const4, |
destinyXfate | 2:0e2ef1edf01b | 85 | * not _const4. This seems to be a djgpp-specific requirement. |
destinyXfate | 2:0e2ef1edf01b | 86 | * Also, such variables apparently *must* be declared outside |
destinyXfate | 2:0e2ef1edf01b | 87 | * of functions; neither static nor automatic variables work if |
destinyXfate | 2:0e2ef1edf01b | 88 | * defined within the scope of a single function, but both |
destinyXfate | 2:0e2ef1edf01b | 89 | * static and truly global (multi-module) variables work fine. |
destinyXfate | 2:0e2ef1edf01b | 90 | * |
destinyXfate | 2:0e2ef1edf01b | 91 | * 19991023: |
destinyXfate | 2:0e2ef1edf01b | 92 | * - fixed png_combine_row() non-MMX replication bug (odd passes only?) |
destinyXfate | 2:0e2ef1edf01b | 93 | * - switched from string-concatenation-with-macros to cleaner method of |
destinyXfate | 2:0e2ef1edf01b | 94 | * renaming global variables for djgpp--i.e., always use prefixes in |
destinyXfate | 2:0e2ef1edf01b | 95 | * inlined assembler code (== strings) and conditionally rename the |
destinyXfate | 2:0e2ef1edf01b | 96 | * variables, not the other way around. Hence _const4, _mask8_0, etc. |
destinyXfate | 2:0e2ef1edf01b | 97 | * |
destinyXfate | 2:0e2ef1edf01b | 98 | * 19991024: |
destinyXfate | 2:0e2ef1edf01b | 99 | * - fixed mmxsupport()/png_do_read_interlace() first-row bug |
destinyXfate | 2:0e2ef1edf01b | 100 | * This one was severely weird: even though mmxsupport() doesn't touch |
destinyXfate | 2:0e2ef1edf01b | 101 | * ebx (where "row" pointer was stored), it nevertheless managed to zero |
destinyXfate | 2:0e2ef1edf01b | 102 | * the register (even in static/non-fPIC code--see below), which in turn |
destinyXfate | 2:0e2ef1edf01b | 103 | * caused png_do_read_interlace() to return prematurely on the first row of |
destinyXfate | 2:0e2ef1edf01b | 104 | * interlaced images (i.e., without expanding the interlaced pixels). |
destinyXfate | 2:0e2ef1edf01b | 105 | * Inspection of the generated assembly code didn't turn up any clues, |
destinyXfate | 2:0e2ef1edf01b | 106 | * although it did point at a minor optimization (i.e., get rid of |
destinyXfate | 2:0e2ef1edf01b | 107 | * mmx_supported_local variable and just use eax). Possibly the CPUID |
destinyXfate | 2:0e2ef1edf01b | 108 | * instruction is more destructive than it looks? (Not yet checked.) |
destinyXfate | 2:0e2ef1edf01b | 109 | * - "info gcc" was next to useless, so compared fPIC and non-fPIC assembly |
destinyXfate | 2:0e2ef1edf01b | 110 | * listings... Apparently register spillage has to do with ebx, since |
destinyXfate | 2:0e2ef1edf01b | 111 | * it's used to index the global offset table. Commenting it out of the |
destinyXfate | 2:0e2ef1edf01b | 112 | * input-reg lists in png_combine_row() eliminated compiler barfage, so |
destinyXfate | 2:0e2ef1edf01b | 113 | * ifdef'd with __PIC__ macro: if defined, use a global for unmask |
destinyXfate | 2:0e2ef1edf01b | 114 | * |
destinyXfate | 2:0e2ef1edf01b | 115 | * 19991107: |
destinyXfate | 2:0e2ef1edf01b | 116 | * - verified CPUID clobberage: 12-char string constant ("GenuineIntel", |
destinyXfate | 2:0e2ef1edf01b | 117 | * "AuthenticAMD", etc.) placed in ebx:ecx:edx. Still need to polish. |
destinyXfate | 2:0e2ef1edf01b | 118 | * |
destinyXfate | 2:0e2ef1edf01b | 119 | * 19991120: |
destinyXfate | 2:0e2ef1edf01b | 120 | * - made "diff" variable (now "_dif") global to simplify conversion of |
destinyXfate | 2:0e2ef1edf01b | 121 | * filtering routines (running out of regs, sigh). "diff" is still used |
destinyXfate | 2:0e2ef1edf01b | 122 | * in interlacing routines, however. |
destinyXfate | 2:0e2ef1edf01b | 123 | * - fixed up both versions of mmxsupport() (ORIG_THAT_USED_TO_CLOBBER_EBX |
destinyXfate | 2:0e2ef1edf01b | 124 | * macro determines which is used); original not yet tested. |
destinyXfate | 2:0e2ef1edf01b | 125 | * |
destinyXfate | 2:0e2ef1edf01b | 126 | * 20000213: |
destinyXfate | 2:0e2ef1edf01b | 127 | * - when compiling with gcc, be sure to use -fomit-frame-pointer |
destinyXfate | 2:0e2ef1edf01b | 128 | * |
destinyXfate | 2:0e2ef1edf01b | 129 | * 20000319: |
destinyXfate | 2:0e2ef1edf01b | 130 | * - fixed a register-name typo in png_do_read_interlace(), default (MMX) case, |
destinyXfate | 2:0e2ef1edf01b | 131 | * pass == 4 or 5, that caused visible corruption of interlaced images |
destinyXfate | 2:0e2ef1edf01b | 132 | * |
destinyXfate | 2:0e2ef1edf01b | 133 | * 20000623: |
destinyXfate | 2:0e2ef1edf01b | 134 | * - Various problems were reported with gcc 2.95.2 in the Cygwin environment, |
destinyXfate | 2:0e2ef1edf01b | 135 | * many of the form "forbidden register 0 (ax) was spilled for class AREG." |
destinyXfate | 2:0e2ef1edf01b | 136 | * This is explained at http://gcc.gnu.org/fom_serv/cache/23.html, and |
destinyXfate | 2:0e2ef1edf01b | 137 | * Chuck Wilson supplied a patch involving dummy output registers. See |
destinyXfate | 2:0e2ef1edf01b | 138 | * http://sourceforge.net/bugs/?func=detailbug&bug_id=108741&group_id=5624 |
destinyXfate | 2:0e2ef1edf01b | 139 | * for the original (anonymous) SourceForge bug report. |
destinyXfate | 2:0e2ef1edf01b | 140 | * |
destinyXfate | 2:0e2ef1edf01b | 141 | * 20000706: |
destinyXfate | 2:0e2ef1edf01b | 142 | * - Chuck Wilson passed along these remaining gcc 2.95.2 errors: |
destinyXfate | 2:0e2ef1edf01b | 143 | * pnggccrd.c: In function `png_combine_row': |
destinyXfate | 2:0e2ef1edf01b | 144 | * pnggccrd.c:525: more than 10 operands in `asm' |
destinyXfate | 2:0e2ef1edf01b | 145 | * pnggccrd.c:669: more than 10 operands in `asm' |
destinyXfate | 2:0e2ef1edf01b | 146 | * pnggccrd.c:828: more than 10 operands in `asm' |
destinyXfate | 2:0e2ef1edf01b | 147 | * pnggccrd.c:994: more than 10 operands in `asm' |
destinyXfate | 2:0e2ef1edf01b | 148 | * pnggccrd.c:1177: more than 10 operands in `asm' |
destinyXfate | 2:0e2ef1edf01b | 149 | * They are all the same problem and can be worked around by using the |
destinyXfate | 2:0e2ef1edf01b | 150 | * global _unmask variable unconditionally, not just in the -fPIC case. |
destinyXfate | 2:0e2ef1edf01b | 151 | * Reportedly earlier versions of gcc also have the problem with more than |
destinyXfate | 2:0e2ef1edf01b | 152 | * 10 operands; they just don't report it. Much strangeness ensues, etc. |
destinyXfate | 2:0e2ef1edf01b | 153 | * |
destinyXfate | 2:0e2ef1edf01b | 154 | * 20000729: |
destinyXfate | 2:0e2ef1edf01b | 155 | * - enabled png_read_filter_row_mmx_up() (shortest remaining unconverted |
destinyXfate | 2:0e2ef1edf01b | 156 | * MMX routine); began converting png_read_filter_row_mmx_sub() |
destinyXfate | 2:0e2ef1edf01b | 157 | * - to finish remaining sections: |
destinyXfate | 2:0e2ef1edf01b | 158 | * - clean up indentation and comments |
destinyXfate | 2:0e2ef1edf01b | 159 | * - preload local variables |
destinyXfate | 2:0e2ef1edf01b | 160 | * - add output and input regs (order of former determines numerical |
destinyXfate | 2:0e2ef1edf01b | 161 | * mapping of latter) |
destinyXfate | 2:0e2ef1edf01b | 162 | * - avoid all usage of ebx (including bx, bh, bl) register [20000823] |
destinyXfate | 2:0e2ef1edf01b | 163 | * - remove "$" from addressing of Shift and Mask variables [20000823] |
destinyXfate | 2:0e2ef1edf01b | 164 | * |
destinyXfate | 2:0e2ef1edf01b | 165 | * 20000731: |
destinyXfate | 2:0e2ef1edf01b | 166 | * - global union vars causing segfaults in png_read_filter_row_mmx_sub()? |
destinyXfate | 2:0e2ef1edf01b | 167 | * |
destinyXfate | 2:0e2ef1edf01b | 168 | * 20000822: |
destinyXfate | 2:0e2ef1edf01b | 169 | * - ARGH, stupid png_read_filter_row_mmx_sub() segfault only happens with |
destinyXfate | 2:0e2ef1edf01b | 170 | * shared-library (-fPIC) version! Code works just fine as part of static |
destinyXfate | 2:0e2ef1edf01b | 171 | * library. Damn damn damn damn damn, should have tested that sooner. |
destinyXfate | 2:0e2ef1edf01b | 172 | * ebx is getting clobbered again (explicitly this time); need to save it |
destinyXfate | 2:0e2ef1edf01b | 173 | * on stack or rewrite asm code to avoid using it altogether. Blargh! |
destinyXfate | 2:0e2ef1edf01b | 174 | * |
destinyXfate | 2:0e2ef1edf01b | 175 | * 20000823: |
destinyXfate | 2:0e2ef1edf01b | 176 | * - first section was trickiest; all remaining sections have ebx -> edx now. |
destinyXfate | 2:0e2ef1edf01b | 177 | * (-fPIC works again.) Also added missing underscores to various Shift* |
destinyXfate | 2:0e2ef1edf01b | 178 | * and *Mask* globals and got rid of leading "$" signs. |
destinyXfate | 2:0e2ef1edf01b | 179 | * |
destinyXfate | 2:0e2ef1edf01b | 180 | * 20000826: |
destinyXfate | 2:0e2ef1edf01b | 181 | * - added visual separators to help navigate microscopic printed copies |
destinyXfate | 2:0e2ef1edf01b | 182 | * (http://pobox.com/~newt/code/gpr-latest.zip, mode 10); started working |
destinyXfate | 2:0e2ef1edf01b | 183 | * on png_read_filter_row_mmx_avg() |
destinyXfate | 2:0e2ef1edf01b | 184 | * |
destinyXfate | 2:0e2ef1edf01b | 185 | * 20000828: |
destinyXfate | 2:0e2ef1edf01b | 186 | * - finished png_read_filter_row_mmx_avg(): only Paeth left! (930 lines...) |
destinyXfate | 2:0e2ef1edf01b | 187 | * What the hell, did png_read_filter_row_mmx_paeth(), too. Comments not |
destinyXfate | 2:0e2ef1edf01b | 188 | * cleaned up/shortened in either routine, but functionality is complete |
destinyXfate | 2:0e2ef1edf01b | 189 | * and seems to be working fine. |
destinyXfate | 2:0e2ef1edf01b | 190 | * |
destinyXfate | 2:0e2ef1edf01b | 191 | * 20000829: |
destinyXfate | 2:0e2ef1edf01b | 192 | * - ahhh, figured out last(?) bit of gcc/gas asm-fu: if register is listed |
destinyXfate | 2:0e2ef1edf01b | 193 | * as an input reg (with dummy output variables, etc.), then it *cannot* |
destinyXfate | 2:0e2ef1edf01b | 194 | * also appear in the clobber list or gcc 2.95.2 will barf. The solution |
destinyXfate | 2:0e2ef1edf01b | 195 | * is simple enough... |
destinyXfate | 2:0e2ef1edf01b | 196 | * |
destinyXfate | 2:0e2ef1edf01b | 197 | * 20000914: |
destinyXfate | 2:0e2ef1edf01b | 198 | * - bug in png_read_filter_row_mmx_avg(): 16-bit grayscale not handled |
destinyXfate | 2:0e2ef1edf01b | 199 | * correctly (but 48-bit RGB just fine) |
destinyXfate | 2:0e2ef1edf01b | 200 | * |
destinyXfate | 2:0e2ef1edf01b | 201 | * 20000916: |
destinyXfate | 2:0e2ef1edf01b | 202 | * - fixed bug in png_read_filter_row_mmx_avg(), bpp == 2 case; three errors: |
destinyXfate | 2:0e2ef1edf01b | 203 | * - "_ShiftBpp.use = 24;" should have been "_ShiftBpp.use = 16;" |
destinyXfate | 2:0e2ef1edf01b | 204 | * - "_ShiftRem.use = 40;" should have been "_ShiftRem.use = 48;" |
destinyXfate | 2:0e2ef1edf01b | 205 | * - "psllq _ShiftRem, %%mm2" should have been "psrlq _ShiftRem, %%mm2" |
destinyXfate | 2:0e2ef1edf01b | 206 | * |
destinyXfate | 2:0e2ef1edf01b | 207 | * 20010101: |
destinyXfate | 2:0e2ef1edf01b | 208 | * - added new png_init_mmx_flags() function (here only because it needs to |
destinyXfate | 2:0e2ef1edf01b | 209 | * call mmxsupport(), which should probably become global png_mmxsupport()); |
destinyXfate | 2:0e2ef1edf01b | 210 | * modified other MMX routines to run conditionally (png_ptr->asm_flags) |
destinyXfate | 2:0e2ef1edf01b | 211 | * |
destinyXfate | 2:0e2ef1edf01b | 212 | * 20010103: |
destinyXfate | 2:0e2ef1edf01b | 213 | * - renamed mmxsupport() to png_mmx_support(), with auto-set of mmx_supported, |
destinyXfate | 2:0e2ef1edf01b | 214 | * and made it public; moved png_init_mmx_flags() to png.c as internal func |
destinyXfate | 2:0e2ef1edf01b | 215 | * |
destinyXfate | 2:0e2ef1edf01b | 216 | * 20010104: |
destinyXfate | 2:0e2ef1edf01b | 217 | * - removed dependency on png_read_filter_row_c() (C code already duplicated |
destinyXfate | 2:0e2ef1edf01b | 218 | * within MMX version of png_read_filter_row()) so no longer necessary to |
destinyXfate | 2:0e2ef1edf01b | 219 | * compile it into pngrutil.o |
destinyXfate | 2:0e2ef1edf01b | 220 | * |
destinyXfate | 2:0e2ef1edf01b | 221 | * 20010310: |
destinyXfate | 2:0e2ef1edf01b | 222 | * - fixed buffer-overrun bug in png_combine_row() C code (non-MMX) |
destinyXfate | 2:0e2ef1edf01b | 223 | * |
destinyXfate | 2:0e2ef1edf01b | 224 | * 20020304: |
destinyXfate | 2:0e2ef1edf01b | 225 | * - eliminated incorrect use of width_mmx in pixel_bytes == 8 case |
destinyXfate | 2:0e2ef1edf01b | 226 | * |
destinyXfate | 2:0e2ef1edf01b | 227 | * 20040724: |
destinyXfate | 2:0e2ef1edf01b | 228 | * - more tinkering with clobber list at lines 4529 and 5033, to get |
destinyXfate | 2:0e2ef1edf01b | 229 | * it to compile on gcc-3.4. |
destinyXfate | 2:0e2ef1edf01b | 230 | * |
destinyXfate | 2:0e2ef1edf01b | 231 | * STILL TO DO: |
destinyXfate | 2:0e2ef1edf01b | 232 | * - test png_do_read_interlace() 64-bit case (pixel_bytes == 8) |
destinyXfate | 2:0e2ef1edf01b | 233 | * - write MMX code for 48-bit case (pixel_bytes == 6) |
destinyXfate | 2:0e2ef1edf01b | 234 | * - figure out what's up with 24-bit case (pixel_bytes == 3): |
destinyXfate | 2:0e2ef1edf01b | 235 | * why subtract 8 from width_mmx in the pass 4/5 case? |
destinyXfate | 2:0e2ef1edf01b | 236 | * (only width_mmx case) (near line 1606) |
destinyXfate | 2:0e2ef1edf01b | 237 | * - rewrite all MMX interlacing code so it's aligned with beginning |
destinyXfate | 2:0e2ef1edf01b | 238 | * of the row buffer, not the end (see 19991007 for details) |
destinyXfate | 2:0e2ef1edf01b | 239 | * x pick one version of mmxsupport() and get rid of the other |
destinyXfate | 2:0e2ef1edf01b | 240 | * - add error messages to any remaining bogus default cases |
destinyXfate | 2:0e2ef1edf01b | 241 | * - enable pixel_depth == 8 cases in png_read_filter_row()? (test speed) |
destinyXfate | 2:0e2ef1edf01b | 242 | * x add support for runtime enable/disable/query of various MMX routines |
destinyXfate | 2:0e2ef1edf01b | 243 | */ |
destinyXfate | 2:0e2ef1edf01b | 244 | |
destinyXfate | 2:0e2ef1edf01b | 245 | #define PNG_INTERNAL |
destinyXfate | 2:0e2ef1edf01b | 246 | #include "png.h" |
destinyXfate | 2:0e2ef1edf01b | 247 | |
destinyXfate | 2:0e2ef1edf01b | 248 | #if defined(PNG_ASSEMBLER_CODE_SUPPORTED) && defined(PNG_USE_PNGGCCRD) |
destinyXfate | 2:0e2ef1edf01b | 249 | |
destinyXfate | 2:0e2ef1edf01b | 250 | int PNGAPI png_mmx_support(void); |
destinyXfate | 2:0e2ef1edf01b | 251 | |
destinyXfate | 2:0e2ef1edf01b | 252 | #ifdef PNG_USE_LOCAL_ARRAYS |
destinyXfate | 2:0e2ef1edf01b | 253 | static const int FARDATA png_pass_start[7] = {0, 4, 0, 2, 0, 1, 0}; |
destinyXfate | 2:0e2ef1edf01b | 254 | static const int FARDATA png_pass_inc[7] = {8, 8, 4, 4, 2, 2, 1}; |
destinyXfate | 2:0e2ef1edf01b | 255 | static const int FARDATA png_pass_width[7] = {8, 4, 4, 2, 2, 1, 1}; |
destinyXfate | 2:0e2ef1edf01b | 256 | #endif |
destinyXfate | 2:0e2ef1edf01b | 257 | |
destinyXfate | 2:0e2ef1edf01b | 258 | #if defined(PNG_MMX_CODE_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 259 | /* djgpp, Win32, Cygwin, and OS2 add their own underscores to global variables, |
destinyXfate | 2:0e2ef1edf01b | 260 | * so define them without: */ |
destinyXfate | 2:0e2ef1edf01b | 261 | #if defined(__DJGPP__) || defined(WIN32) || defined(__CYGWIN__) || \ |
destinyXfate | 2:0e2ef1edf01b | 262 | defined(__OS2__) |
destinyXfate | 2:0e2ef1edf01b | 263 | # define _mmx_supported mmx_supported |
destinyXfate | 2:0e2ef1edf01b | 264 | # define _const4 const4 |
destinyXfate | 2:0e2ef1edf01b | 265 | # define _const6 const6 |
destinyXfate | 2:0e2ef1edf01b | 266 | # define _mask8_0 mask8_0 |
destinyXfate | 2:0e2ef1edf01b | 267 | # define _mask16_1 mask16_1 |
destinyXfate | 2:0e2ef1edf01b | 268 | # define _mask16_0 mask16_0 |
destinyXfate | 2:0e2ef1edf01b | 269 | # define _mask24_2 mask24_2 |
destinyXfate | 2:0e2ef1edf01b | 270 | # define _mask24_1 mask24_1 |
destinyXfate | 2:0e2ef1edf01b | 271 | # define _mask24_0 mask24_0 |
destinyXfate | 2:0e2ef1edf01b | 272 | # define _mask32_3 mask32_3 |
destinyXfate | 2:0e2ef1edf01b | 273 | # define _mask32_2 mask32_2 |
destinyXfate | 2:0e2ef1edf01b | 274 | # define _mask32_1 mask32_1 |
destinyXfate | 2:0e2ef1edf01b | 275 | # define _mask32_0 mask32_0 |
destinyXfate | 2:0e2ef1edf01b | 276 | # define _mask48_5 mask48_5 |
destinyXfate | 2:0e2ef1edf01b | 277 | # define _mask48_4 mask48_4 |
destinyXfate | 2:0e2ef1edf01b | 278 | # define _mask48_3 mask48_3 |
destinyXfate | 2:0e2ef1edf01b | 279 | # define _mask48_2 mask48_2 |
destinyXfate | 2:0e2ef1edf01b | 280 | # define _mask48_1 mask48_1 |
destinyXfate | 2:0e2ef1edf01b | 281 | # define _mask48_0 mask48_0 |
destinyXfate | 2:0e2ef1edf01b | 282 | # define _LBCarryMask LBCarryMask |
destinyXfate | 2:0e2ef1edf01b | 283 | # define _HBClearMask HBClearMask |
destinyXfate | 2:0e2ef1edf01b | 284 | # define _ActiveMask ActiveMask |
destinyXfate | 2:0e2ef1edf01b | 285 | # define _ActiveMask2 ActiveMask2 |
destinyXfate | 2:0e2ef1edf01b | 286 | # define _ActiveMaskEnd ActiveMaskEnd |
destinyXfate | 2:0e2ef1edf01b | 287 | # define _ShiftBpp ShiftBpp |
destinyXfate | 2:0e2ef1edf01b | 288 | # define _ShiftRem ShiftRem |
destinyXfate | 2:0e2ef1edf01b | 289 | #ifdef PNG_THREAD_UNSAFE_OK |
destinyXfate | 2:0e2ef1edf01b | 290 | # define _unmask unmask |
destinyXfate | 2:0e2ef1edf01b | 291 | # define _FullLength FullLength |
destinyXfate | 2:0e2ef1edf01b | 292 | # define _MMXLength MMXLength |
destinyXfate | 2:0e2ef1edf01b | 293 | # define _dif dif |
destinyXfate | 2:0e2ef1edf01b | 294 | # define _patemp patemp |
destinyXfate | 2:0e2ef1edf01b | 295 | # define _pbtemp pbtemp |
destinyXfate | 2:0e2ef1edf01b | 296 | # define _pctemp pctemp |
destinyXfate | 2:0e2ef1edf01b | 297 | #endif |
destinyXfate | 2:0e2ef1edf01b | 298 | #endif |
destinyXfate | 2:0e2ef1edf01b | 299 | |
destinyXfate | 2:0e2ef1edf01b | 300 | |
destinyXfate | 2:0e2ef1edf01b | 301 | /* These constants are used in the inlined MMX assembly code. |
destinyXfate | 2:0e2ef1edf01b | 302 | Ignore gcc's "At top level: defined but not used" warnings. */ |
destinyXfate | 2:0e2ef1edf01b | 303 | |
destinyXfate | 2:0e2ef1edf01b | 304 | /* GRR 20000706: originally _unmask was needed only when compiling with -fPIC, |
destinyXfate | 2:0e2ef1edf01b | 305 | * since that case uses the %ebx register for indexing the Global Offset Table |
destinyXfate | 2:0e2ef1edf01b | 306 | * and there were no other registers available. But gcc 2.95 and later emit |
destinyXfate | 2:0e2ef1edf01b | 307 | * "more than 10 operands in `asm'" errors when %ebx is used to preload unmask |
destinyXfate | 2:0e2ef1edf01b | 308 | * in the non-PIC case, so we'll just use the global unconditionally now. |
destinyXfate | 2:0e2ef1edf01b | 309 | */ |
destinyXfate | 2:0e2ef1edf01b | 310 | #ifdef PNG_THREAD_UNSAFE_OK |
destinyXfate | 2:0e2ef1edf01b | 311 | static int _unmask; |
destinyXfate | 2:0e2ef1edf01b | 312 | #endif |
destinyXfate | 2:0e2ef1edf01b | 313 | |
destinyXfate | 2:0e2ef1edf01b | 314 | static unsigned long long _mask8_0 = 0x0102040810204080LL; |
destinyXfate | 2:0e2ef1edf01b | 315 | |
destinyXfate | 2:0e2ef1edf01b | 316 | static unsigned long long _mask16_1 = 0x0101020204040808LL; |
destinyXfate | 2:0e2ef1edf01b | 317 | static unsigned long long _mask16_0 = 0x1010202040408080LL; |
destinyXfate | 2:0e2ef1edf01b | 318 | |
destinyXfate | 2:0e2ef1edf01b | 319 | static unsigned long long _mask24_2 = 0x0101010202020404LL; |
destinyXfate | 2:0e2ef1edf01b | 320 | static unsigned long long _mask24_1 = 0x0408080810101020LL; |
destinyXfate | 2:0e2ef1edf01b | 321 | static unsigned long long _mask24_0 = 0x2020404040808080LL; |
destinyXfate | 2:0e2ef1edf01b | 322 | |
destinyXfate | 2:0e2ef1edf01b | 323 | static unsigned long long _mask32_3 = 0x0101010102020202LL; |
destinyXfate | 2:0e2ef1edf01b | 324 | static unsigned long long _mask32_2 = 0x0404040408080808LL; |
destinyXfate | 2:0e2ef1edf01b | 325 | static unsigned long long _mask32_1 = 0x1010101020202020LL; |
destinyXfate | 2:0e2ef1edf01b | 326 | static unsigned long long _mask32_0 = 0x4040404080808080LL; |
destinyXfate | 2:0e2ef1edf01b | 327 | |
destinyXfate | 2:0e2ef1edf01b | 328 | static unsigned long long _mask48_5 = 0x0101010101010202LL; |
destinyXfate | 2:0e2ef1edf01b | 329 | static unsigned long long _mask48_4 = 0x0202020204040404LL; |
destinyXfate | 2:0e2ef1edf01b | 330 | static unsigned long long _mask48_3 = 0x0404080808080808LL; |
destinyXfate | 2:0e2ef1edf01b | 331 | static unsigned long long _mask48_2 = 0x1010101010102020LL; |
destinyXfate | 2:0e2ef1edf01b | 332 | static unsigned long long _mask48_1 = 0x2020202040404040LL; |
destinyXfate | 2:0e2ef1edf01b | 333 | static unsigned long long _mask48_0 = 0x4040808080808080LL; |
destinyXfate | 2:0e2ef1edf01b | 334 | |
destinyXfate | 2:0e2ef1edf01b | 335 | static unsigned long long _const4 = 0x0000000000FFFFFFLL; |
destinyXfate | 2:0e2ef1edf01b | 336 | //static unsigned long long _const5 = 0x000000FFFFFF0000LL; // NOT USED |
destinyXfate | 2:0e2ef1edf01b | 337 | static unsigned long long _const6 = 0x00000000000000FFLL; |
destinyXfate | 2:0e2ef1edf01b | 338 | |
destinyXfate | 2:0e2ef1edf01b | 339 | // These are used in the row-filter routines and should/would be local |
destinyXfate | 2:0e2ef1edf01b | 340 | // variables if not for gcc addressing limitations. |
destinyXfate | 2:0e2ef1edf01b | 341 | // WARNING: Their presence probably defeats the thread safety of libpng. |
destinyXfate | 2:0e2ef1edf01b | 342 | |
destinyXfate | 2:0e2ef1edf01b | 343 | #ifdef PNG_THREAD_UNSAFE_OK |
destinyXfate | 2:0e2ef1edf01b | 344 | static png_uint_32 _FullLength; |
destinyXfate | 2:0e2ef1edf01b | 345 | static png_uint_32 _MMXLength; |
destinyXfate | 2:0e2ef1edf01b | 346 | static int _dif; |
destinyXfate | 2:0e2ef1edf01b | 347 | static int _patemp; // temp variables for Paeth routine |
destinyXfate | 2:0e2ef1edf01b | 348 | static int _pbtemp; |
destinyXfate | 2:0e2ef1edf01b | 349 | static int _pctemp; |
destinyXfate | 2:0e2ef1edf01b | 350 | #endif |
destinyXfate | 2:0e2ef1edf01b | 351 | |
destinyXfate | 2:0e2ef1edf01b | 352 | void /* PRIVATE */ |
destinyXfate | 2:0e2ef1edf01b | 353 | png_squelch_warnings(void) |
destinyXfate | 2:0e2ef1edf01b | 354 | { |
destinyXfate | 2:0e2ef1edf01b | 355 | #ifdef PNG_THREAD_UNSAFE_OK |
destinyXfate | 2:0e2ef1edf01b | 356 | _dif = _dif; |
destinyXfate | 2:0e2ef1edf01b | 357 | _patemp = _patemp; |
destinyXfate | 2:0e2ef1edf01b | 358 | _pbtemp = _pbtemp; |
destinyXfate | 2:0e2ef1edf01b | 359 | _pctemp = _pctemp; |
destinyXfate | 2:0e2ef1edf01b | 360 | _MMXLength = _MMXLength; |
destinyXfate | 2:0e2ef1edf01b | 361 | #endif |
destinyXfate | 2:0e2ef1edf01b | 362 | _const4 = _const4; |
destinyXfate | 2:0e2ef1edf01b | 363 | _const6 = _const6; |
destinyXfate | 2:0e2ef1edf01b | 364 | _mask8_0 = _mask8_0; |
destinyXfate | 2:0e2ef1edf01b | 365 | _mask16_1 = _mask16_1; |
destinyXfate | 2:0e2ef1edf01b | 366 | _mask16_0 = _mask16_0; |
destinyXfate | 2:0e2ef1edf01b | 367 | _mask24_2 = _mask24_2; |
destinyXfate | 2:0e2ef1edf01b | 368 | _mask24_1 = _mask24_1; |
destinyXfate | 2:0e2ef1edf01b | 369 | _mask24_0 = _mask24_0; |
destinyXfate | 2:0e2ef1edf01b | 370 | _mask32_3 = _mask32_3; |
destinyXfate | 2:0e2ef1edf01b | 371 | _mask32_2 = _mask32_2; |
destinyXfate | 2:0e2ef1edf01b | 372 | _mask32_1 = _mask32_1; |
destinyXfate | 2:0e2ef1edf01b | 373 | _mask32_0 = _mask32_0; |
destinyXfate | 2:0e2ef1edf01b | 374 | _mask48_5 = _mask48_5; |
destinyXfate | 2:0e2ef1edf01b | 375 | _mask48_4 = _mask48_4; |
destinyXfate | 2:0e2ef1edf01b | 376 | _mask48_3 = _mask48_3; |
destinyXfate | 2:0e2ef1edf01b | 377 | _mask48_2 = _mask48_2; |
destinyXfate | 2:0e2ef1edf01b | 378 | _mask48_1 = _mask48_1; |
destinyXfate | 2:0e2ef1edf01b | 379 | _mask48_0 = _mask48_0; |
destinyXfate | 2:0e2ef1edf01b | 380 | } |
destinyXfate | 2:0e2ef1edf01b | 381 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 382 | |
destinyXfate | 2:0e2ef1edf01b | 383 | |
destinyXfate | 2:0e2ef1edf01b | 384 | static int _mmx_supported = 2; |
destinyXfate | 2:0e2ef1edf01b | 385 | |
destinyXfate | 2:0e2ef1edf01b | 386 | /*===========================================================================*/ |
destinyXfate | 2:0e2ef1edf01b | 387 | /* */ |
destinyXfate | 2:0e2ef1edf01b | 388 | /* P N G _ C O M B I N E _ R O W */ |
destinyXfate | 2:0e2ef1edf01b | 389 | /* */ |
destinyXfate | 2:0e2ef1edf01b | 390 | /*===========================================================================*/ |
destinyXfate | 2:0e2ef1edf01b | 391 | |
destinyXfate | 2:0e2ef1edf01b | 392 | #if defined(PNG_HAVE_MMX_COMBINE_ROW) |
destinyXfate | 2:0e2ef1edf01b | 393 | |
destinyXfate | 2:0e2ef1edf01b | 394 | #define BPP2 2 |
destinyXfate | 2:0e2ef1edf01b | 395 | #define BPP3 3 /* bytes per pixel (a.k.a. pixel_bytes) */ |
destinyXfate | 2:0e2ef1edf01b | 396 | #define BPP4 4 |
destinyXfate | 2:0e2ef1edf01b | 397 | #define BPP6 6 /* (defined only to help avoid cut-and-paste errors) */ |
destinyXfate | 2:0e2ef1edf01b | 398 | #define BPP8 8 |
destinyXfate | 2:0e2ef1edf01b | 399 | |
destinyXfate | 2:0e2ef1edf01b | 400 | /* Combines the row recently read in with the previous row. |
destinyXfate | 2:0e2ef1edf01b | 401 | This routine takes care of alpha and transparency if requested. |
destinyXfate | 2:0e2ef1edf01b | 402 | This routine also handles the two methods of progressive display |
destinyXfate | 2:0e2ef1edf01b | 403 | of interlaced images, depending on the mask value. |
destinyXfate | 2:0e2ef1edf01b | 404 | The mask value describes which pixels are to be combined with |
destinyXfate | 2:0e2ef1edf01b | 405 | the row. The pattern always repeats every 8 pixels, so just 8 |
destinyXfate | 2:0e2ef1edf01b | 406 | bits are needed. A one indicates the pixel is to be combined; a |
destinyXfate | 2:0e2ef1edf01b | 407 | zero indicates the pixel is to be skipped. This is in addition |
destinyXfate | 2:0e2ef1edf01b | 408 | to any alpha or transparency value associated with the pixel. |
destinyXfate | 2:0e2ef1edf01b | 409 | If you want all pixels to be combined, pass 0xff (255) in mask. */ |
destinyXfate | 2:0e2ef1edf01b | 410 | |
destinyXfate | 2:0e2ef1edf01b | 411 | /* Use this routine for the x86 platform - it uses a faster MMX routine |
destinyXfate | 2:0e2ef1edf01b | 412 | if the machine supports MMX. */ |
destinyXfate | 2:0e2ef1edf01b | 413 | |
destinyXfate | 2:0e2ef1edf01b | 414 | void /* PRIVATE */ |
destinyXfate | 2:0e2ef1edf01b | 415 | png_combine_row(png_structp png_ptr, png_bytep row, int mask) |
destinyXfate | 2:0e2ef1edf01b | 416 | { |
destinyXfate | 2:0e2ef1edf01b | 417 | png_debug(1, "in png_combine_row (pnggccrd.c)\n"); |
destinyXfate | 2:0e2ef1edf01b | 418 | |
destinyXfate | 2:0e2ef1edf01b | 419 | #if defined(PNG_MMX_CODE_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 420 | if (_mmx_supported == 2) { |
destinyXfate | 2:0e2ef1edf01b | 421 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 422 | /* this should have happened in png_init_mmx_flags() already */ |
destinyXfate | 2:0e2ef1edf01b | 423 | png_warning(png_ptr, "asm_flags may not have been initialized"); |
destinyXfate | 2:0e2ef1edf01b | 424 | #endif |
destinyXfate | 2:0e2ef1edf01b | 425 | png_mmx_support(); |
destinyXfate | 2:0e2ef1edf01b | 426 | } |
destinyXfate | 2:0e2ef1edf01b | 427 | #endif |
destinyXfate | 2:0e2ef1edf01b | 428 | |
destinyXfate | 2:0e2ef1edf01b | 429 | if (mask == 0xff) |
destinyXfate | 2:0e2ef1edf01b | 430 | { |
destinyXfate | 2:0e2ef1edf01b | 431 | png_debug(2,"mask == 0xff: doing single png_memcpy()\n"); |
destinyXfate | 2:0e2ef1edf01b | 432 | png_memcpy(row, png_ptr->row_buf + 1, |
destinyXfate | 2:0e2ef1edf01b | 433 | (png_size_t)PNG_ROWBYTES(png_ptr->row_info.pixel_depth,png_ptr->width)); |
destinyXfate | 2:0e2ef1edf01b | 434 | } |
destinyXfate | 2:0e2ef1edf01b | 435 | else /* (png_combine_row() is never called with mask == 0) */ |
destinyXfate | 2:0e2ef1edf01b | 436 | { |
destinyXfate | 2:0e2ef1edf01b | 437 | switch (png_ptr->row_info.pixel_depth) |
destinyXfate | 2:0e2ef1edf01b | 438 | { |
destinyXfate | 2:0e2ef1edf01b | 439 | case 1: /* png_ptr->row_info.pixel_depth */ |
destinyXfate | 2:0e2ef1edf01b | 440 | { |
destinyXfate | 2:0e2ef1edf01b | 441 | png_bytep sp; |
destinyXfate | 2:0e2ef1edf01b | 442 | png_bytep dp; |
destinyXfate | 2:0e2ef1edf01b | 443 | int s_inc, s_start, s_end; |
destinyXfate | 2:0e2ef1edf01b | 444 | int m; |
destinyXfate | 2:0e2ef1edf01b | 445 | int shift; |
destinyXfate | 2:0e2ef1edf01b | 446 | png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 447 | |
destinyXfate | 2:0e2ef1edf01b | 448 | sp = png_ptr->row_buf + 1; |
destinyXfate | 2:0e2ef1edf01b | 449 | dp = row; |
destinyXfate | 2:0e2ef1edf01b | 450 | m = 0x80; |
destinyXfate | 2:0e2ef1edf01b | 451 | #if defined(PNG_READ_PACKSWAP_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 452 | if (png_ptr->transformations & PNG_PACKSWAP) |
destinyXfate | 2:0e2ef1edf01b | 453 | { |
destinyXfate | 2:0e2ef1edf01b | 454 | s_start = 0; |
destinyXfate | 2:0e2ef1edf01b | 455 | s_end = 7; |
destinyXfate | 2:0e2ef1edf01b | 456 | s_inc = 1; |
destinyXfate | 2:0e2ef1edf01b | 457 | } |
destinyXfate | 2:0e2ef1edf01b | 458 | else |
destinyXfate | 2:0e2ef1edf01b | 459 | #endif |
destinyXfate | 2:0e2ef1edf01b | 460 | { |
destinyXfate | 2:0e2ef1edf01b | 461 | s_start = 7; |
destinyXfate | 2:0e2ef1edf01b | 462 | s_end = 0; |
destinyXfate | 2:0e2ef1edf01b | 463 | s_inc = -1; |
destinyXfate | 2:0e2ef1edf01b | 464 | } |
destinyXfate | 2:0e2ef1edf01b | 465 | |
destinyXfate | 2:0e2ef1edf01b | 466 | shift = s_start; |
destinyXfate | 2:0e2ef1edf01b | 467 | |
destinyXfate | 2:0e2ef1edf01b | 468 | for (i = 0; i < png_ptr->width; i++) |
destinyXfate | 2:0e2ef1edf01b | 469 | { |
destinyXfate | 2:0e2ef1edf01b | 470 | if (m & mask) |
destinyXfate | 2:0e2ef1edf01b | 471 | { |
destinyXfate | 2:0e2ef1edf01b | 472 | int value; |
destinyXfate | 2:0e2ef1edf01b | 473 | |
destinyXfate | 2:0e2ef1edf01b | 474 | value = (*sp >> shift) & 0x1; |
destinyXfate | 2:0e2ef1edf01b | 475 | *dp &= (png_byte)((0x7f7f >> (7 - shift)) & 0xff); |
destinyXfate | 2:0e2ef1edf01b | 476 | *dp |= (png_byte)(value << shift); |
destinyXfate | 2:0e2ef1edf01b | 477 | } |
destinyXfate | 2:0e2ef1edf01b | 478 | |
destinyXfate | 2:0e2ef1edf01b | 479 | if (shift == s_end) |
destinyXfate | 2:0e2ef1edf01b | 480 | { |
destinyXfate | 2:0e2ef1edf01b | 481 | shift = s_start; |
destinyXfate | 2:0e2ef1edf01b | 482 | sp++; |
destinyXfate | 2:0e2ef1edf01b | 483 | dp++; |
destinyXfate | 2:0e2ef1edf01b | 484 | } |
destinyXfate | 2:0e2ef1edf01b | 485 | else |
destinyXfate | 2:0e2ef1edf01b | 486 | shift += s_inc; |
destinyXfate | 2:0e2ef1edf01b | 487 | |
destinyXfate | 2:0e2ef1edf01b | 488 | if (m == 1) |
destinyXfate | 2:0e2ef1edf01b | 489 | m = 0x80; |
destinyXfate | 2:0e2ef1edf01b | 490 | else |
destinyXfate | 2:0e2ef1edf01b | 491 | m >>= 1; |
destinyXfate | 2:0e2ef1edf01b | 492 | } |
destinyXfate | 2:0e2ef1edf01b | 493 | break; |
destinyXfate | 2:0e2ef1edf01b | 494 | } |
destinyXfate | 2:0e2ef1edf01b | 495 | |
destinyXfate | 2:0e2ef1edf01b | 496 | case 2: /* png_ptr->row_info.pixel_depth */ |
destinyXfate | 2:0e2ef1edf01b | 497 | { |
destinyXfate | 2:0e2ef1edf01b | 498 | png_bytep sp; |
destinyXfate | 2:0e2ef1edf01b | 499 | png_bytep dp; |
destinyXfate | 2:0e2ef1edf01b | 500 | int s_start, s_end, s_inc; |
destinyXfate | 2:0e2ef1edf01b | 501 | int m; |
destinyXfate | 2:0e2ef1edf01b | 502 | int shift; |
destinyXfate | 2:0e2ef1edf01b | 503 | png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 504 | int value; |
destinyXfate | 2:0e2ef1edf01b | 505 | |
destinyXfate | 2:0e2ef1edf01b | 506 | sp = png_ptr->row_buf + 1; |
destinyXfate | 2:0e2ef1edf01b | 507 | dp = row; |
destinyXfate | 2:0e2ef1edf01b | 508 | m = 0x80; |
destinyXfate | 2:0e2ef1edf01b | 509 | #if defined(PNG_READ_PACKSWAP_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 510 | if (png_ptr->transformations & PNG_PACKSWAP) |
destinyXfate | 2:0e2ef1edf01b | 511 | { |
destinyXfate | 2:0e2ef1edf01b | 512 | s_start = 0; |
destinyXfate | 2:0e2ef1edf01b | 513 | s_end = 6; |
destinyXfate | 2:0e2ef1edf01b | 514 | s_inc = 2; |
destinyXfate | 2:0e2ef1edf01b | 515 | } |
destinyXfate | 2:0e2ef1edf01b | 516 | else |
destinyXfate | 2:0e2ef1edf01b | 517 | #endif |
destinyXfate | 2:0e2ef1edf01b | 518 | { |
destinyXfate | 2:0e2ef1edf01b | 519 | s_start = 6; |
destinyXfate | 2:0e2ef1edf01b | 520 | s_end = 0; |
destinyXfate | 2:0e2ef1edf01b | 521 | s_inc = -2; |
destinyXfate | 2:0e2ef1edf01b | 522 | } |
destinyXfate | 2:0e2ef1edf01b | 523 | |
destinyXfate | 2:0e2ef1edf01b | 524 | shift = s_start; |
destinyXfate | 2:0e2ef1edf01b | 525 | |
destinyXfate | 2:0e2ef1edf01b | 526 | for (i = 0; i < png_ptr->width; i++) |
destinyXfate | 2:0e2ef1edf01b | 527 | { |
destinyXfate | 2:0e2ef1edf01b | 528 | if (m & mask) |
destinyXfate | 2:0e2ef1edf01b | 529 | { |
destinyXfate | 2:0e2ef1edf01b | 530 | value = (*sp >> shift) & 0x3; |
destinyXfate | 2:0e2ef1edf01b | 531 | *dp &= (png_byte)((0x3f3f >> (6 - shift)) & 0xff); |
destinyXfate | 2:0e2ef1edf01b | 532 | *dp |= (png_byte)(value << shift); |
destinyXfate | 2:0e2ef1edf01b | 533 | } |
destinyXfate | 2:0e2ef1edf01b | 534 | |
destinyXfate | 2:0e2ef1edf01b | 535 | if (shift == s_end) |
destinyXfate | 2:0e2ef1edf01b | 536 | { |
destinyXfate | 2:0e2ef1edf01b | 537 | shift = s_start; |
destinyXfate | 2:0e2ef1edf01b | 538 | sp++; |
destinyXfate | 2:0e2ef1edf01b | 539 | dp++; |
destinyXfate | 2:0e2ef1edf01b | 540 | } |
destinyXfate | 2:0e2ef1edf01b | 541 | else |
destinyXfate | 2:0e2ef1edf01b | 542 | shift += s_inc; |
destinyXfate | 2:0e2ef1edf01b | 543 | if (m == 1) |
destinyXfate | 2:0e2ef1edf01b | 544 | m = 0x80; |
destinyXfate | 2:0e2ef1edf01b | 545 | else |
destinyXfate | 2:0e2ef1edf01b | 546 | m >>= 1; |
destinyXfate | 2:0e2ef1edf01b | 547 | } |
destinyXfate | 2:0e2ef1edf01b | 548 | break; |
destinyXfate | 2:0e2ef1edf01b | 549 | } |
destinyXfate | 2:0e2ef1edf01b | 550 | |
destinyXfate | 2:0e2ef1edf01b | 551 | case 4: /* png_ptr->row_info.pixel_depth */ |
destinyXfate | 2:0e2ef1edf01b | 552 | { |
destinyXfate | 2:0e2ef1edf01b | 553 | png_bytep sp; |
destinyXfate | 2:0e2ef1edf01b | 554 | png_bytep dp; |
destinyXfate | 2:0e2ef1edf01b | 555 | int s_start, s_end, s_inc; |
destinyXfate | 2:0e2ef1edf01b | 556 | int m; |
destinyXfate | 2:0e2ef1edf01b | 557 | int shift; |
destinyXfate | 2:0e2ef1edf01b | 558 | png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 559 | int value; |
destinyXfate | 2:0e2ef1edf01b | 560 | |
destinyXfate | 2:0e2ef1edf01b | 561 | sp = png_ptr->row_buf + 1; |
destinyXfate | 2:0e2ef1edf01b | 562 | dp = row; |
destinyXfate | 2:0e2ef1edf01b | 563 | m = 0x80; |
destinyXfate | 2:0e2ef1edf01b | 564 | #if defined(PNG_READ_PACKSWAP_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 565 | if (png_ptr->transformations & PNG_PACKSWAP) |
destinyXfate | 2:0e2ef1edf01b | 566 | { |
destinyXfate | 2:0e2ef1edf01b | 567 | s_start = 0; |
destinyXfate | 2:0e2ef1edf01b | 568 | s_end = 4; |
destinyXfate | 2:0e2ef1edf01b | 569 | s_inc = 4; |
destinyXfate | 2:0e2ef1edf01b | 570 | } |
destinyXfate | 2:0e2ef1edf01b | 571 | else |
destinyXfate | 2:0e2ef1edf01b | 572 | #endif |
destinyXfate | 2:0e2ef1edf01b | 573 | { |
destinyXfate | 2:0e2ef1edf01b | 574 | s_start = 4; |
destinyXfate | 2:0e2ef1edf01b | 575 | s_end = 0; |
destinyXfate | 2:0e2ef1edf01b | 576 | s_inc = -4; |
destinyXfate | 2:0e2ef1edf01b | 577 | } |
destinyXfate | 2:0e2ef1edf01b | 578 | shift = s_start; |
destinyXfate | 2:0e2ef1edf01b | 579 | |
destinyXfate | 2:0e2ef1edf01b | 580 | for (i = 0; i < png_ptr->width; i++) |
destinyXfate | 2:0e2ef1edf01b | 581 | { |
destinyXfate | 2:0e2ef1edf01b | 582 | if (m & mask) |
destinyXfate | 2:0e2ef1edf01b | 583 | { |
destinyXfate | 2:0e2ef1edf01b | 584 | value = (*sp >> shift) & 0xf; |
destinyXfate | 2:0e2ef1edf01b | 585 | *dp &= (png_byte)((0xf0f >> (4 - shift)) & 0xff); |
destinyXfate | 2:0e2ef1edf01b | 586 | *dp |= (png_byte)(value << shift); |
destinyXfate | 2:0e2ef1edf01b | 587 | } |
destinyXfate | 2:0e2ef1edf01b | 588 | |
destinyXfate | 2:0e2ef1edf01b | 589 | if (shift == s_end) |
destinyXfate | 2:0e2ef1edf01b | 590 | { |
destinyXfate | 2:0e2ef1edf01b | 591 | shift = s_start; |
destinyXfate | 2:0e2ef1edf01b | 592 | sp++; |
destinyXfate | 2:0e2ef1edf01b | 593 | dp++; |
destinyXfate | 2:0e2ef1edf01b | 594 | } |
destinyXfate | 2:0e2ef1edf01b | 595 | else |
destinyXfate | 2:0e2ef1edf01b | 596 | shift += s_inc; |
destinyXfate | 2:0e2ef1edf01b | 597 | if (m == 1) |
destinyXfate | 2:0e2ef1edf01b | 598 | m = 0x80; |
destinyXfate | 2:0e2ef1edf01b | 599 | else |
destinyXfate | 2:0e2ef1edf01b | 600 | m >>= 1; |
destinyXfate | 2:0e2ef1edf01b | 601 | } |
destinyXfate | 2:0e2ef1edf01b | 602 | break; |
destinyXfate | 2:0e2ef1edf01b | 603 | } |
destinyXfate | 2:0e2ef1edf01b | 604 | |
destinyXfate | 2:0e2ef1edf01b | 605 | case 8: /* png_ptr->row_info.pixel_depth */ |
destinyXfate | 2:0e2ef1edf01b | 606 | { |
destinyXfate | 2:0e2ef1edf01b | 607 | png_bytep srcptr; |
destinyXfate | 2:0e2ef1edf01b | 608 | png_bytep dstptr; |
destinyXfate | 2:0e2ef1edf01b | 609 | |
destinyXfate | 2:0e2ef1edf01b | 610 | #if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK) |
destinyXfate | 2:0e2ef1edf01b | 611 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 612 | if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW) |
destinyXfate | 2:0e2ef1edf01b | 613 | /* && _mmx_supported */ ) |
destinyXfate | 2:0e2ef1edf01b | 614 | #else |
destinyXfate | 2:0e2ef1edf01b | 615 | if (_mmx_supported) |
destinyXfate | 2:0e2ef1edf01b | 616 | #endif |
destinyXfate | 2:0e2ef1edf01b | 617 | { |
destinyXfate | 2:0e2ef1edf01b | 618 | png_uint_32 len; |
destinyXfate | 2:0e2ef1edf01b | 619 | int diff; |
destinyXfate | 2:0e2ef1edf01b | 620 | int dummy_value_a; // fix 'forbidden register spilled' error |
destinyXfate | 2:0e2ef1edf01b | 621 | int dummy_value_d; |
destinyXfate | 2:0e2ef1edf01b | 622 | int dummy_value_c; |
destinyXfate | 2:0e2ef1edf01b | 623 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 624 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 625 | _unmask = ~mask; // global variable for -fPIC version |
destinyXfate | 2:0e2ef1edf01b | 626 | srcptr = png_ptr->row_buf + 1; |
destinyXfate | 2:0e2ef1edf01b | 627 | dstptr = row; |
destinyXfate | 2:0e2ef1edf01b | 628 | len = png_ptr->width &~7; // reduce to multiple of 8 |
destinyXfate | 2:0e2ef1edf01b | 629 | diff = (int) (png_ptr->width & 7); // amount lost |
destinyXfate | 2:0e2ef1edf01b | 630 | |
destinyXfate | 2:0e2ef1edf01b | 631 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 632 | "movd _unmask, %%mm7 \n\t" // load bit pattern |
destinyXfate | 2:0e2ef1edf01b | 633 | "psubb %%mm6, %%mm6 \n\t" // zero mm6 |
destinyXfate | 2:0e2ef1edf01b | 634 | "punpcklbw %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 635 | "punpcklwd %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 636 | "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks |
destinyXfate | 2:0e2ef1edf01b | 637 | |
destinyXfate | 2:0e2ef1edf01b | 638 | "movq _mask8_0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 639 | "pand %%mm7, %%mm0 \n\t" // nonzero if keep byte |
destinyXfate | 2:0e2ef1edf01b | 640 | "pcmpeqb %%mm6, %%mm0 \n\t" // zeros->1s, v versa |
destinyXfate | 2:0e2ef1edf01b | 641 | |
destinyXfate | 2:0e2ef1edf01b | 642 | // preload "movl len, %%ecx \n\t" // load length of line |
destinyXfate | 2:0e2ef1edf01b | 643 | // preload "movl srcptr, %%esi \n\t" // load source |
destinyXfate | 2:0e2ef1edf01b | 644 | // preload "movl dstptr, %%edi \n\t" // load dest |
destinyXfate | 2:0e2ef1edf01b | 645 | |
destinyXfate | 2:0e2ef1edf01b | 646 | "cmpl $0, %%ecx \n\t" // len == 0 ? |
destinyXfate | 2:0e2ef1edf01b | 647 | "je mainloop8end \n\t" |
destinyXfate | 2:0e2ef1edf01b | 648 | |
destinyXfate | 2:0e2ef1edf01b | 649 | "mainloop8: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 650 | "movq (%%esi), %%mm4 \n\t" // *srcptr |
destinyXfate | 2:0e2ef1edf01b | 651 | "pand %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 652 | "movq %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 653 | "pandn (%%edi), %%mm6 \n\t" // *dstptr |
destinyXfate | 2:0e2ef1edf01b | 654 | "por %%mm6, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 655 | "movq %%mm4, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 656 | "addl $8, %%esi \n\t" // inc by 8 bytes processed |
destinyXfate | 2:0e2ef1edf01b | 657 | "addl $8, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 658 | "subl $8, %%ecx \n\t" // dec by 8 pixels processed |
destinyXfate | 2:0e2ef1edf01b | 659 | "ja mainloop8 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 660 | |
destinyXfate | 2:0e2ef1edf01b | 661 | "mainloop8end: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 662 | // preload "movl diff, %%ecx \n\t" // (diff is in eax) |
destinyXfate | 2:0e2ef1edf01b | 663 | "movl %%eax, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 664 | "cmpl $0, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 665 | "jz end8 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 666 | // preload "movl mask, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 667 | "sall $24, %%edx \n\t" // make low byte, high byte |
destinyXfate | 2:0e2ef1edf01b | 668 | |
destinyXfate | 2:0e2ef1edf01b | 669 | "secondloop8: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 670 | "sall %%edx \n\t" // move high bit to CF |
destinyXfate | 2:0e2ef1edf01b | 671 | "jnc skip8 \n\t" // if CF = 0 |
destinyXfate | 2:0e2ef1edf01b | 672 | "movb (%%esi), %%al \n\t" |
destinyXfate | 2:0e2ef1edf01b | 673 | "movb %%al, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 674 | |
destinyXfate | 2:0e2ef1edf01b | 675 | "skip8: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 676 | "incl %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 677 | "incl %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 678 | "decl %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 679 | "jnz secondloop8 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 680 | |
destinyXfate | 2:0e2ef1edf01b | 681 | "end8: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 682 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 683 | |
destinyXfate | 2:0e2ef1edf01b | 684 | : "=a" (dummy_value_a), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 685 | "=d" (dummy_value_d), |
destinyXfate | 2:0e2ef1edf01b | 686 | "=c" (dummy_value_c), |
destinyXfate | 2:0e2ef1edf01b | 687 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 688 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 689 | |
destinyXfate | 2:0e2ef1edf01b | 690 | : "3" (srcptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 691 | "4" (dstptr), // edi |
destinyXfate | 2:0e2ef1edf01b | 692 | "0" (diff), // eax |
destinyXfate | 2:0e2ef1edf01b | 693 | // was (unmask) "b" RESERVED // ebx // Global Offset Table idx |
destinyXfate | 2:0e2ef1edf01b | 694 | "2" (len), // ecx |
destinyXfate | 2:0e2ef1edf01b | 695 | "1" (mask) // edx |
destinyXfate | 2:0e2ef1edf01b | 696 | |
destinyXfate | 2:0e2ef1edf01b | 697 | #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 698 | : "%mm0", "%mm4", "%mm6", "%mm7" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 699 | #endif |
destinyXfate | 2:0e2ef1edf01b | 700 | ); |
destinyXfate | 2:0e2ef1edf01b | 701 | } |
destinyXfate | 2:0e2ef1edf01b | 702 | else /* mmx _not supported - Use modified C routine */ |
destinyXfate | 2:0e2ef1edf01b | 703 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 704 | { |
destinyXfate | 2:0e2ef1edf01b | 705 | register png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 706 | png_uint_32 initial_val = png_pass_start[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 707 | /* png.c: png_pass_start[] = {0, 4, 0, 2, 0, 1, 0}; */ |
destinyXfate | 2:0e2ef1edf01b | 708 | register int stride = png_pass_inc[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 709 | /* png.c: png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */ |
destinyXfate | 2:0e2ef1edf01b | 710 | register int rep_bytes = png_pass_width[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 711 | /* png.c: png_pass_width[] = {8, 4, 4, 2, 2, 1, 1}; */ |
destinyXfate | 2:0e2ef1edf01b | 712 | png_uint_32 len = png_ptr->width &~7; /* reduce to mult. of 8 */ |
destinyXfate | 2:0e2ef1edf01b | 713 | int diff = (int) (png_ptr->width & 7); /* amount lost */ |
destinyXfate | 2:0e2ef1edf01b | 714 | register png_uint_32 final_val = len; /* GRR bugfix */ |
destinyXfate | 2:0e2ef1edf01b | 715 | |
destinyXfate | 2:0e2ef1edf01b | 716 | srcptr = png_ptr->row_buf + 1 + initial_val; |
destinyXfate | 2:0e2ef1edf01b | 717 | dstptr = row + initial_val; |
destinyXfate | 2:0e2ef1edf01b | 718 | |
destinyXfate | 2:0e2ef1edf01b | 719 | for (i = initial_val; i < final_val; i += stride) |
destinyXfate | 2:0e2ef1edf01b | 720 | { |
destinyXfate | 2:0e2ef1edf01b | 721 | png_memcpy(dstptr, srcptr, rep_bytes); |
destinyXfate | 2:0e2ef1edf01b | 722 | srcptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 723 | dstptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 724 | } |
destinyXfate | 2:0e2ef1edf01b | 725 | if (diff) /* number of leftover pixels: 3 for pngtest */ |
destinyXfate | 2:0e2ef1edf01b | 726 | { |
destinyXfate | 2:0e2ef1edf01b | 727 | final_val+=diff /* *BPP1 */ ; |
destinyXfate | 2:0e2ef1edf01b | 728 | for (; i < final_val; i += stride) |
destinyXfate | 2:0e2ef1edf01b | 729 | { |
destinyXfate | 2:0e2ef1edf01b | 730 | if (rep_bytes > (int)(final_val-i)) |
destinyXfate | 2:0e2ef1edf01b | 731 | rep_bytes = (int)(final_val-i); |
destinyXfate | 2:0e2ef1edf01b | 732 | png_memcpy(dstptr, srcptr, rep_bytes); |
destinyXfate | 2:0e2ef1edf01b | 733 | srcptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 734 | dstptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 735 | } |
destinyXfate | 2:0e2ef1edf01b | 736 | } |
destinyXfate | 2:0e2ef1edf01b | 737 | |
destinyXfate | 2:0e2ef1edf01b | 738 | } /* end of else (_mmx_supported) */ |
destinyXfate | 2:0e2ef1edf01b | 739 | |
destinyXfate | 2:0e2ef1edf01b | 740 | break; |
destinyXfate | 2:0e2ef1edf01b | 741 | } /* end 8 bpp */ |
destinyXfate | 2:0e2ef1edf01b | 742 | |
destinyXfate | 2:0e2ef1edf01b | 743 | case 16: /* png_ptr->row_info.pixel_depth */ |
destinyXfate | 2:0e2ef1edf01b | 744 | { |
destinyXfate | 2:0e2ef1edf01b | 745 | png_bytep srcptr; |
destinyXfate | 2:0e2ef1edf01b | 746 | png_bytep dstptr; |
destinyXfate | 2:0e2ef1edf01b | 747 | |
destinyXfate | 2:0e2ef1edf01b | 748 | #if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK) |
destinyXfate | 2:0e2ef1edf01b | 749 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 750 | if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW) |
destinyXfate | 2:0e2ef1edf01b | 751 | /* && _mmx_supported */ ) |
destinyXfate | 2:0e2ef1edf01b | 752 | #else |
destinyXfate | 2:0e2ef1edf01b | 753 | if (_mmx_supported) |
destinyXfate | 2:0e2ef1edf01b | 754 | #endif |
destinyXfate | 2:0e2ef1edf01b | 755 | { |
destinyXfate | 2:0e2ef1edf01b | 756 | png_uint_32 len; |
destinyXfate | 2:0e2ef1edf01b | 757 | int diff; |
destinyXfate | 2:0e2ef1edf01b | 758 | int dummy_value_a; // fix 'forbidden register spilled' error |
destinyXfate | 2:0e2ef1edf01b | 759 | int dummy_value_d; |
destinyXfate | 2:0e2ef1edf01b | 760 | int dummy_value_c; |
destinyXfate | 2:0e2ef1edf01b | 761 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 762 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 763 | _unmask = ~mask; // global variable for -fPIC version |
destinyXfate | 2:0e2ef1edf01b | 764 | srcptr = png_ptr->row_buf + 1; |
destinyXfate | 2:0e2ef1edf01b | 765 | dstptr = row; |
destinyXfate | 2:0e2ef1edf01b | 766 | len = png_ptr->width &~7; // reduce to multiple of 8 |
destinyXfate | 2:0e2ef1edf01b | 767 | diff = (int) (png_ptr->width & 7); // amount lost // |
destinyXfate | 2:0e2ef1edf01b | 768 | |
destinyXfate | 2:0e2ef1edf01b | 769 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 770 | "movd _unmask, %%mm7 \n\t" // load bit pattern |
destinyXfate | 2:0e2ef1edf01b | 771 | "psubb %%mm6, %%mm6 \n\t" // zero mm6 |
destinyXfate | 2:0e2ef1edf01b | 772 | "punpcklbw %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 773 | "punpcklwd %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 774 | "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks |
destinyXfate | 2:0e2ef1edf01b | 775 | |
destinyXfate | 2:0e2ef1edf01b | 776 | "movq _mask16_0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 777 | "movq _mask16_1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 778 | |
destinyXfate | 2:0e2ef1edf01b | 779 | "pand %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 780 | "pand %%mm7, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 781 | |
destinyXfate | 2:0e2ef1edf01b | 782 | "pcmpeqb %%mm6, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 783 | "pcmpeqb %%mm6, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 784 | |
destinyXfate | 2:0e2ef1edf01b | 785 | // preload "movl len, %%ecx \n\t" // load length of line |
destinyXfate | 2:0e2ef1edf01b | 786 | // preload "movl srcptr, %%esi \n\t" // load source |
destinyXfate | 2:0e2ef1edf01b | 787 | // preload "movl dstptr, %%edi \n\t" // load dest |
destinyXfate | 2:0e2ef1edf01b | 788 | |
destinyXfate | 2:0e2ef1edf01b | 789 | "cmpl $0, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 790 | "jz mainloop16end \n\t" |
destinyXfate | 2:0e2ef1edf01b | 791 | |
destinyXfate | 2:0e2ef1edf01b | 792 | "mainloop16: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 793 | "movq (%%esi), %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 794 | "pand %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 795 | "movq %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 796 | "movq (%%edi), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 797 | "pandn %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 798 | "por %%mm6, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 799 | "movq %%mm4, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 800 | |
destinyXfate | 2:0e2ef1edf01b | 801 | "movq 8(%%esi), %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 802 | "pand %%mm1, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 803 | "movq %%mm1, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 804 | "movq 8(%%edi), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 805 | "pandn %%mm6, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 806 | "por %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 807 | "movq %%mm5, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 808 | |
destinyXfate | 2:0e2ef1edf01b | 809 | "addl $16, %%esi \n\t" // inc by 16 bytes processed |
destinyXfate | 2:0e2ef1edf01b | 810 | "addl $16, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 811 | "subl $8, %%ecx \n\t" // dec by 8 pixels processed |
destinyXfate | 2:0e2ef1edf01b | 812 | "ja mainloop16 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 813 | |
destinyXfate | 2:0e2ef1edf01b | 814 | "mainloop16end: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 815 | // preload "movl diff, %%ecx \n\t" // (diff is in eax) |
destinyXfate | 2:0e2ef1edf01b | 816 | "movl %%eax, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 817 | "cmpl $0, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 818 | "jz end16 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 819 | // preload "movl mask, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 820 | "sall $24, %%edx \n\t" // make low byte, high byte |
destinyXfate | 2:0e2ef1edf01b | 821 | |
destinyXfate | 2:0e2ef1edf01b | 822 | "secondloop16: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 823 | "sall %%edx \n\t" // move high bit to CF |
destinyXfate | 2:0e2ef1edf01b | 824 | "jnc skip16 \n\t" // if CF = 0 |
destinyXfate | 2:0e2ef1edf01b | 825 | "movw (%%esi), %%ax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 826 | "movw %%ax, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 827 | |
destinyXfate | 2:0e2ef1edf01b | 828 | "skip16: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 829 | "addl $2, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 830 | "addl $2, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 831 | "decl %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 832 | "jnz secondloop16 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 833 | |
destinyXfate | 2:0e2ef1edf01b | 834 | "end16: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 835 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 836 | |
destinyXfate | 2:0e2ef1edf01b | 837 | : "=a" (dummy_value_a), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 838 | "=c" (dummy_value_c), |
destinyXfate | 2:0e2ef1edf01b | 839 | "=d" (dummy_value_d), |
destinyXfate | 2:0e2ef1edf01b | 840 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 841 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 842 | |
destinyXfate | 2:0e2ef1edf01b | 843 | : "0" (diff), // eax // input regs |
destinyXfate | 2:0e2ef1edf01b | 844 | // was (unmask) " " RESERVED // ebx // Global Offset Table idx |
destinyXfate | 2:0e2ef1edf01b | 845 | "1" (len), // ecx |
destinyXfate | 2:0e2ef1edf01b | 846 | "2" (mask), // edx |
destinyXfate | 2:0e2ef1edf01b | 847 | "3" (srcptr), // esi |
destinyXfate | 2:0e2ef1edf01b | 848 | "4" (dstptr) // edi |
destinyXfate | 2:0e2ef1edf01b | 849 | |
destinyXfate | 2:0e2ef1edf01b | 850 | #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 851 | : "%mm0", "%mm1", "%mm4" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 852 | , "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 853 | #endif |
destinyXfate | 2:0e2ef1edf01b | 854 | ); |
destinyXfate | 2:0e2ef1edf01b | 855 | } |
destinyXfate | 2:0e2ef1edf01b | 856 | else /* mmx _not supported - Use modified C routine */ |
destinyXfate | 2:0e2ef1edf01b | 857 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 858 | { |
destinyXfate | 2:0e2ef1edf01b | 859 | register png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 860 | png_uint_32 initial_val = BPP2 * png_pass_start[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 861 | /* png.c: png_pass_start[] = {0, 4, 0, 2, 0, 1, 0}; */ |
destinyXfate | 2:0e2ef1edf01b | 862 | register int stride = BPP2 * png_pass_inc[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 863 | /* png.c: png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */ |
destinyXfate | 2:0e2ef1edf01b | 864 | register int rep_bytes = BPP2 * png_pass_width[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 865 | /* png.c: png_pass_width[] = {8, 4, 4, 2, 2, 1, 1}; */ |
destinyXfate | 2:0e2ef1edf01b | 866 | png_uint_32 len = png_ptr->width &~7; /* reduce to mult. of 8 */ |
destinyXfate | 2:0e2ef1edf01b | 867 | int diff = (int) (png_ptr->width & 7); /* amount lost */ |
destinyXfate | 2:0e2ef1edf01b | 868 | register png_uint_32 final_val = BPP2 * len; /* GRR bugfix */ |
destinyXfate | 2:0e2ef1edf01b | 869 | |
destinyXfate | 2:0e2ef1edf01b | 870 | srcptr = png_ptr->row_buf + 1 + initial_val; |
destinyXfate | 2:0e2ef1edf01b | 871 | dstptr = row + initial_val; |
destinyXfate | 2:0e2ef1edf01b | 872 | |
destinyXfate | 2:0e2ef1edf01b | 873 | for (i = initial_val; i < final_val; i += stride) |
destinyXfate | 2:0e2ef1edf01b | 874 | { |
destinyXfate | 2:0e2ef1edf01b | 875 | png_memcpy(dstptr, srcptr, rep_bytes); |
destinyXfate | 2:0e2ef1edf01b | 876 | srcptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 877 | dstptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 878 | } |
destinyXfate | 2:0e2ef1edf01b | 879 | if (diff) /* number of leftover pixels: 3 for pngtest */ |
destinyXfate | 2:0e2ef1edf01b | 880 | { |
destinyXfate | 2:0e2ef1edf01b | 881 | final_val+=diff*BPP2; |
destinyXfate | 2:0e2ef1edf01b | 882 | for (; i < final_val; i += stride) |
destinyXfate | 2:0e2ef1edf01b | 883 | { |
destinyXfate | 2:0e2ef1edf01b | 884 | if (rep_bytes > (int)(final_val-i)) |
destinyXfate | 2:0e2ef1edf01b | 885 | rep_bytes = (int)(final_val-i); |
destinyXfate | 2:0e2ef1edf01b | 886 | png_memcpy(dstptr, srcptr, rep_bytes); |
destinyXfate | 2:0e2ef1edf01b | 887 | srcptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 888 | dstptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 889 | } |
destinyXfate | 2:0e2ef1edf01b | 890 | } |
destinyXfate | 2:0e2ef1edf01b | 891 | } /* end of else (_mmx_supported) */ |
destinyXfate | 2:0e2ef1edf01b | 892 | |
destinyXfate | 2:0e2ef1edf01b | 893 | break; |
destinyXfate | 2:0e2ef1edf01b | 894 | } /* end 16 bpp */ |
destinyXfate | 2:0e2ef1edf01b | 895 | |
destinyXfate | 2:0e2ef1edf01b | 896 | case 24: /* png_ptr->row_info.pixel_depth */ |
destinyXfate | 2:0e2ef1edf01b | 897 | { |
destinyXfate | 2:0e2ef1edf01b | 898 | png_bytep srcptr; |
destinyXfate | 2:0e2ef1edf01b | 899 | png_bytep dstptr; |
destinyXfate | 2:0e2ef1edf01b | 900 | |
destinyXfate | 2:0e2ef1edf01b | 901 | #if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK) |
destinyXfate | 2:0e2ef1edf01b | 902 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 903 | if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW) |
destinyXfate | 2:0e2ef1edf01b | 904 | /* && _mmx_supported */ ) |
destinyXfate | 2:0e2ef1edf01b | 905 | #else |
destinyXfate | 2:0e2ef1edf01b | 906 | if (_mmx_supported) |
destinyXfate | 2:0e2ef1edf01b | 907 | #endif |
destinyXfate | 2:0e2ef1edf01b | 908 | { |
destinyXfate | 2:0e2ef1edf01b | 909 | png_uint_32 len; |
destinyXfate | 2:0e2ef1edf01b | 910 | int diff; |
destinyXfate | 2:0e2ef1edf01b | 911 | int dummy_value_a; // fix 'forbidden register spilled' error |
destinyXfate | 2:0e2ef1edf01b | 912 | int dummy_value_d; |
destinyXfate | 2:0e2ef1edf01b | 913 | int dummy_value_c; |
destinyXfate | 2:0e2ef1edf01b | 914 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 915 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 916 | _unmask = ~mask; // global variable for -fPIC version |
destinyXfate | 2:0e2ef1edf01b | 917 | srcptr = png_ptr->row_buf + 1; |
destinyXfate | 2:0e2ef1edf01b | 918 | dstptr = row; |
destinyXfate | 2:0e2ef1edf01b | 919 | len = png_ptr->width &~7; // reduce to multiple of 8 |
destinyXfate | 2:0e2ef1edf01b | 920 | diff = (int) (png_ptr->width & 7); // amount lost // |
destinyXfate | 2:0e2ef1edf01b | 921 | |
destinyXfate | 2:0e2ef1edf01b | 922 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 923 | "movd _unmask, %%mm7 \n\t" // load bit pattern |
destinyXfate | 2:0e2ef1edf01b | 924 | "psubb %%mm6, %%mm6 \n\t" // zero mm6 |
destinyXfate | 2:0e2ef1edf01b | 925 | "punpcklbw %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 926 | "punpcklwd %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 927 | "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks |
destinyXfate | 2:0e2ef1edf01b | 928 | |
destinyXfate | 2:0e2ef1edf01b | 929 | "movq _mask24_0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 930 | "movq _mask24_1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 931 | "movq _mask24_2, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 932 | |
destinyXfate | 2:0e2ef1edf01b | 933 | "pand %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 934 | "pand %%mm7, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 935 | "pand %%mm7, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 936 | |
destinyXfate | 2:0e2ef1edf01b | 937 | "pcmpeqb %%mm6, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 938 | "pcmpeqb %%mm6, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 939 | "pcmpeqb %%mm6, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 940 | |
destinyXfate | 2:0e2ef1edf01b | 941 | // preload "movl len, %%ecx \n\t" // load length of line |
destinyXfate | 2:0e2ef1edf01b | 942 | // preload "movl srcptr, %%esi \n\t" // load source |
destinyXfate | 2:0e2ef1edf01b | 943 | // preload "movl dstptr, %%edi \n\t" // load dest |
destinyXfate | 2:0e2ef1edf01b | 944 | |
destinyXfate | 2:0e2ef1edf01b | 945 | "cmpl $0, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 946 | "jz mainloop24end \n\t" |
destinyXfate | 2:0e2ef1edf01b | 947 | |
destinyXfate | 2:0e2ef1edf01b | 948 | "mainloop24: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 949 | "movq (%%esi), %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 950 | "pand %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 951 | "movq %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 952 | "movq (%%edi), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 953 | "pandn %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 954 | "por %%mm6, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 955 | "movq %%mm4, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 956 | |
destinyXfate | 2:0e2ef1edf01b | 957 | "movq 8(%%esi), %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 958 | "pand %%mm1, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 959 | "movq %%mm1, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 960 | "movq 8(%%edi), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 961 | "pandn %%mm6, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 962 | "por %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 963 | "movq %%mm5, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 964 | |
destinyXfate | 2:0e2ef1edf01b | 965 | "movq 16(%%esi), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 966 | "pand %%mm2, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 967 | "movq %%mm2, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 968 | "movq 16(%%edi), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 969 | "pandn %%mm7, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 970 | "por %%mm4, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 971 | "movq %%mm6, 16(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 972 | |
destinyXfate | 2:0e2ef1edf01b | 973 | "addl $24, %%esi \n\t" // inc by 24 bytes processed |
destinyXfate | 2:0e2ef1edf01b | 974 | "addl $24, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 975 | "subl $8, %%ecx \n\t" // dec by 8 pixels processed |
destinyXfate | 2:0e2ef1edf01b | 976 | |
destinyXfate | 2:0e2ef1edf01b | 977 | "ja mainloop24 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 978 | |
destinyXfate | 2:0e2ef1edf01b | 979 | "mainloop24end: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 980 | // preload "movl diff, %%ecx \n\t" // (diff is in eax) |
destinyXfate | 2:0e2ef1edf01b | 981 | "movl %%eax, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 982 | "cmpl $0, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 983 | "jz end24 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 984 | // preload "movl mask, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 985 | "sall $24, %%edx \n\t" // make low byte, high byte |
destinyXfate | 2:0e2ef1edf01b | 986 | |
destinyXfate | 2:0e2ef1edf01b | 987 | "secondloop24: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 988 | "sall %%edx \n\t" // move high bit to CF |
destinyXfate | 2:0e2ef1edf01b | 989 | "jnc skip24 \n\t" // if CF = 0 |
destinyXfate | 2:0e2ef1edf01b | 990 | "movw (%%esi), %%ax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 991 | "movw %%ax, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 992 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 993 | "movb 2(%%esi), %%al \n\t" |
destinyXfate | 2:0e2ef1edf01b | 994 | "movb %%al, 2(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 995 | |
destinyXfate | 2:0e2ef1edf01b | 996 | "skip24: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 997 | "addl $3, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 998 | "addl $3, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 999 | "decl %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1000 | "jnz secondloop24 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1001 | |
destinyXfate | 2:0e2ef1edf01b | 1002 | "end24: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1003 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 1004 | |
destinyXfate | 2:0e2ef1edf01b | 1005 | : "=a" (dummy_value_a), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 1006 | "=d" (dummy_value_d), |
destinyXfate | 2:0e2ef1edf01b | 1007 | "=c" (dummy_value_c), |
destinyXfate | 2:0e2ef1edf01b | 1008 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 1009 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 1010 | |
destinyXfate | 2:0e2ef1edf01b | 1011 | : "3" (srcptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 1012 | "4" (dstptr), // edi |
destinyXfate | 2:0e2ef1edf01b | 1013 | "0" (diff), // eax |
destinyXfate | 2:0e2ef1edf01b | 1014 | // was (unmask) "b" RESERVED // ebx // Global Offset Table idx |
destinyXfate | 2:0e2ef1edf01b | 1015 | "2" (len), // ecx |
destinyXfate | 2:0e2ef1edf01b | 1016 | "1" (mask) // edx |
destinyXfate | 2:0e2ef1edf01b | 1017 | |
destinyXfate | 2:0e2ef1edf01b | 1018 | #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 1019 | : "%mm0", "%mm1", "%mm2" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 1020 | , "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 1021 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1022 | ); |
destinyXfate | 2:0e2ef1edf01b | 1023 | } |
destinyXfate | 2:0e2ef1edf01b | 1024 | else /* mmx _not supported - Use modified C routine */ |
destinyXfate | 2:0e2ef1edf01b | 1025 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 1026 | { |
destinyXfate | 2:0e2ef1edf01b | 1027 | register png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 1028 | png_uint_32 initial_val = BPP3 * png_pass_start[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 1029 | /* png.c: png_pass_start[] = {0, 4, 0, 2, 0, 1, 0}; */ |
destinyXfate | 2:0e2ef1edf01b | 1030 | register int stride = BPP3 * png_pass_inc[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 1031 | /* png.c: png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */ |
destinyXfate | 2:0e2ef1edf01b | 1032 | register int rep_bytes = BPP3 * png_pass_width[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 1033 | /* png.c: png_pass_width[] = {8, 4, 4, 2, 2, 1, 1}; */ |
destinyXfate | 2:0e2ef1edf01b | 1034 | png_uint_32 len = png_ptr->width &~7; /* reduce to mult. of 8 */ |
destinyXfate | 2:0e2ef1edf01b | 1035 | int diff = (int) (png_ptr->width & 7); /* amount lost */ |
destinyXfate | 2:0e2ef1edf01b | 1036 | register png_uint_32 final_val = BPP3 * len; /* GRR bugfix */ |
destinyXfate | 2:0e2ef1edf01b | 1037 | |
destinyXfate | 2:0e2ef1edf01b | 1038 | srcptr = png_ptr->row_buf + 1 + initial_val; |
destinyXfate | 2:0e2ef1edf01b | 1039 | dstptr = row + initial_val; |
destinyXfate | 2:0e2ef1edf01b | 1040 | |
destinyXfate | 2:0e2ef1edf01b | 1041 | for (i = initial_val; i < final_val; i += stride) |
destinyXfate | 2:0e2ef1edf01b | 1042 | { |
destinyXfate | 2:0e2ef1edf01b | 1043 | png_memcpy(dstptr, srcptr, rep_bytes); |
destinyXfate | 2:0e2ef1edf01b | 1044 | srcptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1045 | dstptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1046 | } |
destinyXfate | 2:0e2ef1edf01b | 1047 | if (diff) /* number of leftover pixels: 3 for pngtest */ |
destinyXfate | 2:0e2ef1edf01b | 1048 | { |
destinyXfate | 2:0e2ef1edf01b | 1049 | final_val+=diff*BPP3; |
destinyXfate | 2:0e2ef1edf01b | 1050 | for (; i < final_val; i += stride) |
destinyXfate | 2:0e2ef1edf01b | 1051 | { |
destinyXfate | 2:0e2ef1edf01b | 1052 | if (rep_bytes > (int)(final_val-i)) |
destinyXfate | 2:0e2ef1edf01b | 1053 | rep_bytes = (int)(final_val-i); |
destinyXfate | 2:0e2ef1edf01b | 1054 | png_memcpy(dstptr, srcptr, rep_bytes); |
destinyXfate | 2:0e2ef1edf01b | 1055 | srcptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1056 | dstptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1057 | } |
destinyXfate | 2:0e2ef1edf01b | 1058 | } |
destinyXfate | 2:0e2ef1edf01b | 1059 | } /* end of else (_mmx_supported) */ |
destinyXfate | 2:0e2ef1edf01b | 1060 | |
destinyXfate | 2:0e2ef1edf01b | 1061 | break; |
destinyXfate | 2:0e2ef1edf01b | 1062 | } /* end 24 bpp */ |
destinyXfate | 2:0e2ef1edf01b | 1063 | |
destinyXfate | 2:0e2ef1edf01b | 1064 | case 32: /* png_ptr->row_info.pixel_depth */ |
destinyXfate | 2:0e2ef1edf01b | 1065 | { |
destinyXfate | 2:0e2ef1edf01b | 1066 | png_bytep srcptr; |
destinyXfate | 2:0e2ef1edf01b | 1067 | png_bytep dstptr; |
destinyXfate | 2:0e2ef1edf01b | 1068 | |
destinyXfate | 2:0e2ef1edf01b | 1069 | #if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK) |
destinyXfate | 2:0e2ef1edf01b | 1070 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 1071 | if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW) |
destinyXfate | 2:0e2ef1edf01b | 1072 | /* && _mmx_supported */ ) |
destinyXfate | 2:0e2ef1edf01b | 1073 | #else |
destinyXfate | 2:0e2ef1edf01b | 1074 | if (_mmx_supported) |
destinyXfate | 2:0e2ef1edf01b | 1075 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1076 | { |
destinyXfate | 2:0e2ef1edf01b | 1077 | png_uint_32 len; |
destinyXfate | 2:0e2ef1edf01b | 1078 | int diff; |
destinyXfate | 2:0e2ef1edf01b | 1079 | int dummy_value_a; // fix 'forbidden register spilled' error |
destinyXfate | 2:0e2ef1edf01b | 1080 | int dummy_value_d; |
destinyXfate | 2:0e2ef1edf01b | 1081 | int dummy_value_c; |
destinyXfate | 2:0e2ef1edf01b | 1082 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 1083 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 1084 | _unmask = ~mask; // global variable for -fPIC version |
destinyXfate | 2:0e2ef1edf01b | 1085 | srcptr = png_ptr->row_buf + 1; |
destinyXfate | 2:0e2ef1edf01b | 1086 | dstptr = row; |
destinyXfate | 2:0e2ef1edf01b | 1087 | len = png_ptr->width &~7; // reduce to multiple of 8 |
destinyXfate | 2:0e2ef1edf01b | 1088 | diff = (int) (png_ptr->width & 7); // amount lost // |
destinyXfate | 2:0e2ef1edf01b | 1089 | |
destinyXfate | 2:0e2ef1edf01b | 1090 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 1091 | "movd _unmask, %%mm7 \n\t" // load bit pattern |
destinyXfate | 2:0e2ef1edf01b | 1092 | "psubb %%mm6, %%mm6 \n\t" // zero mm6 |
destinyXfate | 2:0e2ef1edf01b | 1093 | "punpcklbw %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1094 | "punpcklwd %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1095 | "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks |
destinyXfate | 2:0e2ef1edf01b | 1096 | |
destinyXfate | 2:0e2ef1edf01b | 1097 | "movq _mask32_0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1098 | "movq _mask32_1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1099 | "movq _mask32_2, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1100 | "movq _mask32_3, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1101 | |
destinyXfate | 2:0e2ef1edf01b | 1102 | "pand %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1103 | "pand %%mm7, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1104 | "pand %%mm7, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1105 | "pand %%mm7, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1106 | |
destinyXfate | 2:0e2ef1edf01b | 1107 | "pcmpeqb %%mm6, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1108 | "pcmpeqb %%mm6, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1109 | "pcmpeqb %%mm6, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1110 | "pcmpeqb %%mm6, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1111 | |
destinyXfate | 2:0e2ef1edf01b | 1112 | // preload "movl len, %%ecx \n\t" // load length of line |
destinyXfate | 2:0e2ef1edf01b | 1113 | // preload "movl srcptr, %%esi \n\t" // load source |
destinyXfate | 2:0e2ef1edf01b | 1114 | // preload "movl dstptr, %%edi \n\t" // load dest |
destinyXfate | 2:0e2ef1edf01b | 1115 | |
destinyXfate | 2:0e2ef1edf01b | 1116 | "cmpl $0, %%ecx \n\t" // lcr |
destinyXfate | 2:0e2ef1edf01b | 1117 | "jz mainloop32end \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1118 | |
destinyXfate | 2:0e2ef1edf01b | 1119 | "mainloop32: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1120 | "movq (%%esi), %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1121 | "pand %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1122 | "movq %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1123 | "movq (%%edi), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1124 | "pandn %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1125 | "por %%mm6, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1126 | "movq %%mm4, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1127 | |
destinyXfate | 2:0e2ef1edf01b | 1128 | "movq 8(%%esi), %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1129 | "pand %%mm1, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1130 | "movq %%mm1, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1131 | "movq 8(%%edi), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1132 | "pandn %%mm6, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1133 | "por %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1134 | "movq %%mm5, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1135 | |
destinyXfate | 2:0e2ef1edf01b | 1136 | "movq 16(%%esi), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1137 | "pand %%mm2, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1138 | "movq %%mm2, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1139 | "movq 16(%%edi), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1140 | "pandn %%mm7, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1141 | "por %%mm4, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1142 | "movq %%mm6, 16(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1143 | |
destinyXfate | 2:0e2ef1edf01b | 1144 | "movq 24(%%esi), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1145 | "pand %%mm3, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1146 | "movq %%mm3, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1147 | "movq 24(%%edi), %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1148 | "pandn %%mm4, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1149 | "por %%mm5, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1150 | "movq %%mm7, 24(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1151 | |
destinyXfate | 2:0e2ef1edf01b | 1152 | "addl $32, %%esi \n\t" // inc by 32 bytes processed |
destinyXfate | 2:0e2ef1edf01b | 1153 | "addl $32, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1154 | "subl $8, %%ecx \n\t" // dec by 8 pixels processed |
destinyXfate | 2:0e2ef1edf01b | 1155 | "ja mainloop32 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1156 | |
destinyXfate | 2:0e2ef1edf01b | 1157 | "mainloop32end: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1158 | // preload "movl diff, %%ecx \n\t" // (diff is in eax) |
destinyXfate | 2:0e2ef1edf01b | 1159 | "movl %%eax, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1160 | "cmpl $0, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1161 | "jz end32 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1162 | // preload "movl mask, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1163 | "sall $24, %%edx \n\t" // low byte => high byte |
destinyXfate | 2:0e2ef1edf01b | 1164 | |
destinyXfate | 2:0e2ef1edf01b | 1165 | "secondloop32: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1166 | "sall %%edx \n\t" // move high bit to CF |
destinyXfate | 2:0e2ef1edf01b | 1167 | "jnc skip32 \n\t" // if CF = 0 |
destinyXfate | 2:0e2ef1edf01b | 1168 | "movl (%%esi), %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1169 | "movl %%eax, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1170 | |
destinyXfate | 2:0e2ef1edf01b | 1171 | "skip32: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1172 | "addl $4, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1173 | "addl $4, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1174 | "decl %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1175 | "jnz secondloop32 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1176 | |
destinyXfate | 2:0e2ef1edf01b | 1177 | "end32: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1178 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 1179 | |
destinyXfate | 2:0e2ef1edf01b | 1180 | : "=a" (dummy_value_a), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 1181 | "=d" (dummy_value_d), |
destinyXfate | 2:0e2ef1edf01b | 1182 | "=c" (dummy_value_c), |
destinyXfate | 2:0e2ef1edf01b | 1183 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 1184 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 1185 | |
destinyXfate | 2:0e2ef1edf01b | 1186 | : "3" (srcptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 1187 | "4" (dstptr), // edi |
destinyXfate | 2:0e2ef1edf01b | 1188 | "0" (diff), // eax |
destinyXfate | 2:0e2ef1edf01b | 1189 | // was (unmask) "b" RESERVED // ebx // Global Offset Table idx |
destinyXfate | 2:0e2ef1edf01b | 1190 | "2" (len), // ecx |
destinyXfate | 2:0e2ef1edf01b | 1191 | "1" (mask) // edx |
destinyXfate | 2:0e2ef1edf01b | 1192 | |
destinyXfate | 2:0e2ef1edf01b | 1193 | #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 1194 | : "%mm0", "%mm1", "%mm2", "%mm3" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 1195 | , "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 1196 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1197 | ); |
destinyXfate | 2:0e2ef1edf01b | 1198 | } |
destinyXfate | 2:0e2ef1edf01b | 1199 | else /* mmx _not supported - Use modified C routine */ |
destinyXfate | 2:0e2ef1edf01b | 1200 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 1201 | { |
destinyXfate | 2:0e2ef1edf01b | 1202 | register png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 1203 | png_uint_32 initial_val = BPP4 * png_pass_start[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 1204 | /* png.c: png_pass_start[] = {0, 4, 0, 2, 0, 1, 0}; */ |
destinyXfate | 2:0e2ef1edf01b | 1205 | register int stride = BPP4 * png_pass_inc[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 1206 | /* png.c: png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */ |
destinyXfate | 2:0e2ef1edf01b | 1207 | register int rep_bytes = BPP4 * png_pass_width[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 1208 | /* png.c: png_pass_width[] = {8, 4, 4, 2, 2, 1, 1}; */ |
destinyXfate | 2:0e2ef1edf01b | 1209 | png_uint_32 len = png_ptr->width &~7; /* reduce to mult. of 8 */ |
destinyXfate | 2:0e2ef1edf01b | 1210 | int diff = (int) (png_ptr->width & 7); /* amount lost */ |
destinyXfate | 2:0e2ef1edf01b | 1211 | register png_uint_32 final_val = BPP4 * len; /* GRR bugfix */ |
destinyXfate | 2:0e2ef1edf01b | 1212 | |
destinyXfate | 2:0e2ef1edf01b | 1213 | srcptr = png_ptr->row_buf + 1 + initial_val; |
destinyXfate | 2:0e2ef1edf01b | 1214 | dstptr = row + initial_val; |
destinyXfate | 2:0e2ef1edf01b | 1215 | |
destinyXfate | 2:0e2ef1edf01b | 1216 | for (i = initial_val; i < final_val; i += stride) |
destinyXfate | 2:0e2ef1edf01b | 1217 | { |
destinyXfate | 2:0e2ef1edf01b | 1218 | png_memcpy(dstptr, srcptr, rep_bytes); |
destinyXfate | 2:0e2ef1edf01b | 1219 | srcptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1220 | dstptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1221 | } |
destinyXfate | 2:0e2ef1edf01b | 1222 | if (diff) /* number of leftover pixels: 3 for pngtest */ |
destinyXfate | 2:0e2ef1edf01b | 1223 | { |
destinyXfate | 2:0e2ef1edf01b | 1224 | final_val+=diff*BPP4; |
destinyXfate | 2:0e2ef1edf01b | 1225 | for (; i < final_val; i += stride) |
destinyXfate | 2:0e2ef1edf01b | 1226 | { |
destinyXfate | 2:0e2ef1edf01b | 1227 | if (rep_bytes > (int)(final_val-i)) |
destinyXfate | 2:0e2ef1edf01b | 1228 | rep_bytes = (int)(final_val-i); |
destinyXfate | 2:0e2ef1edf01b | 1229 | png_memcpy(dstptr, srcptr, rep_bytes); |
destinyXfate | 2:0e2ef1edf01b | 1230 | srcptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1231 | dstptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1232 | } |
destinyXfate | 2:0e2ef1edf01b | 1233 | } |
destinyXfate | 2:0e2ef1edf01b | 1234 | } /* end of else (_mmx_supported) */ |
destinyXfate | 2:0e2ef1edf01b | 1235 | |
destinyXfate | 2:0e2ef1edf01b | 1236 | break; |
destinyXfate | 2:0e2ef1edf01b | 1237 | } /* end 32 bpp */ |
destinyXfate | 2:0e2ef1edf01b | 1238 | |
destinyXfate | 2:0e2ef1edf01b | 1239 | case 48: /* png_ptr->row_info.pixel_depth */ |
destinyXfate | 2:0e2ef1edf01b | 1240 | { |
destinyXfate | 2:0e2ef1edf01b | 1241 | png_bytep srcptr; |
destinyXfate | 2:0e2ef1edf01b | 1242 | png_bytep dstptr; |
destinyXfate | 2:0e2ef1edf01b | 1243 | |
destinyXfate | 2:0e2ef1edf01b | 1244 | #if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK) |
destinyXfate | 2:0e2ef1edf01b | 1245 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 1246 | if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW) |
destinyXfate | 2:0e2ef1edf01b | 1247 | /* && _mmx_supported */ ) |
destinyXfate | 2:0e2ef1edf01b | 1248 | #else |
destinyXfate | 2:0e2ef1edf01b | 1249 | if (_mmx_supported) |
destinyXfate | 2:0e2ef1edf01b | 1250 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1251 | { |
destinyXfate | 2:0e2ef1edf01b | 1252 | png_uint_32 len; |
destinyXfate | 2:0e2ef1edf01b | 1253 | int diff; |
destinyXfate | 2:0e2ef1edf01b | 1254 | int dummy_value_a; // fix 'forbidden register spilled' error |
destinyXfate | 2:0e2ef1edf01b | 1255 | int dummy_value_d; |
destinyXfate | 2:0e2ef1edf01b | 1256 | int dummy_value_c; |
destinyXfate | 2:0e2ef1edf01b | 1257 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 1258 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 1259 | _unmask = ~mask; // global variable for -fPIC version |
destinyXfate | 2:0e2ef1edf01b | 1260 | srcptr = png_ptr->row_buf + 1; |
destinyXfate | 2:0e2ef1edf01b | 1261 | dstptr = row; |
destinyXfate | 2:0e2ef1edf01b | 1262 | len = png_ptr->width &~7; // reduce to multiple of 8 |
destinyXfate | 2:0e2ef1edf01b | 1263 | diff = (int) (png_ptr->width & 7); // amount lost // |
destinyXfate | 2:0e2ef1edf01b | 1264 | |
destinyXfate | 2:0e2ef1edf01b | 1265 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 1266 | "movd _unmask, %%mm7 \n\t" // load bit pattern |
destinyXfate | 2:0e2ef1edf01b | 1267 | "psubb %%mm6, %%mm6 \n\t" // zero mm6 |
destinyXfate | 2:0e2ef1edf01b | 1268 | "punpcklbw %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1269 | "punpcklwd %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1270 | "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks |
destinyXfate | 2:0e2ef1edf01b | 1271 | |
destinyXfate | 2:0e2ef1edf01b | 1272 | "movq _mask48_0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1273 | "movq _mask48_1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1274 | "movq _mask48_2, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1275 | "movq _mask48_3, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1276 | "movq _mask48_4, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1277 | "movq _mask48_5, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1278 | |
destinyXfate | 2:0e2ef1edf01b | 1279 | "pand %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1280 | "pand %%mm7, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1281 | "pand %%mm7, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1282 | "pand %%mm7, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1283 | "pand %%mm7, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1284 | "pand %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1285 | |
destinyXfate | 2:0e2ef1edf01b | 1286 | "pcmpeqb %%mm6, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1287 | "pcmpeqb %%mm6, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1288 | "pcmpeqb %%mm6, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1289 | "pcmpeqb %%mm6, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1290 | "pcmpeqb %%mm6, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1291 | "pcmpeqb %%mm6, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1292 | |
destinyXfate | 2:0e2ef1edf01b | 1293 | // preload "movl len, %%ecx \n\t" // load length of line |
destinyXfate | 2:0e2ef1edf01b | 1294 | // preload "movl srcptr, %%esi \n\t" // load source |
destinyXfate | 2:0e2ef1edf01b | 1295 | // preload "movl dstptr, %%edi \n\t" // load dest |
destinyXfate | 2:0e2ef1edf01b | 1296 | |
destinyXfate | 2:0e2ef1edf01b | 1297 | "cmpl $0, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1298 | "jz mainloop48end \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1299 | |
destinyXfate | 2:0e2ef1edf01b | 1300 | "mainloop48: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1301 | "movq (%%esi), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1302 | "pand %%mm0, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1303 | "movq %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1304 | "pandn (%%edi), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1305 | "por %%mm6, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1306 | "movq %%mm7, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1307 | |
destinyXfate | 2:0e2ef1edf01b | 1308 | "movq 8(%%esi), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1309 | "pand %%mm1, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1310 | "movq %%mm1, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1311 | "pandn 8(%%edi), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1312 | "por %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1313 | "movq %%mm6, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1314 | |
destinyXfate | 2:0e2ef1edf01b | 1315 | "movq 16(%%esi), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1316 | "pand %%mm2, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1317 | "movq %%mm2, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1318 | "pandn 16(%%edi), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1319 | "por %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1320 | "movq %%mm6, 16(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1321 | |
destinyXfate | 2:0e2ef1edf01b | 1322 | "movq 24(%%esi), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1323 | "pand %%mm3, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1324 | "movq %%mm3, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1325 | "pandn 24(%%edi), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1326 | "por %%mm6, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1327 | "movq %%mm7, 24(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1328 | |
destinyXfate | 2:0e2ef1edf01b | 1329 | "movq 32(%%esi), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1330 | "pand %%mm4, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1331 | "movq %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1332 | "pandn 32(%%edi), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1333 | "por %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1334 | "movq %%mm6, 32(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1335 | |
destinyXfate | 2:0e2ef1edf01b | 1336 | "movq 40(%%esi), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1337 | "pand %%mm5, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1338 | "movq %%mm5, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1339 | "pandn 40(%%edi), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1340 | "por %%mm6, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1341 | "movq %%mm7, 40(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1342 | |
destinyXfate | 2:0e2ef1edf01b | 1343 | "addl $48, %%esi \n\t" // inc by 48 bytes processed |
destinyXfate | 2:0e2ef1edf01b | 1344 | "addl $48, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1345 | "subl $8, %%ecx \n\t" // dec by 8 pixels processed |
destinyXfate | 2:0e2ef1edf01b | 1346 | |
destinyXfate | 2:0e2ef1edf01b | 1347 | "ja mainloop48 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1348 | |
destinyXfate | 2:0e2ef1edf01b | 1349 | "mainloop48end: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1350 | // preload "movl diff, %%ecx \n\t" // (diff is in eax) |
destinyXfate | 2:0e2ef1edf01b | 1351 | "movl %%eax, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1352 | "cmpl $0, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1353 | "jz end48 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1354 | // preload "movl mask, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1355 | "sall $24, %%edx \n\t" // make low byte, high byte |
destinyXfate | 2:0e2ef1edf01b | 1356 | |
destinyXfate | 2:0e2ef1edf01b | 1357 | "secondloop48: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1358 | "sall %%edx \n\t" // move high bit to CF |
destinyXfate | 2:0e2ef1edf01b | 1359 | "jnc skip48 \n\t" // if CF = 0 |
destinyXfate | 2:0e2ef1edf01b | 1360 | "movl (%%esi), %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1361 | "movl %%eax, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1362 | |
destinyXfate | 2:0e2ef1edf01b | 1363 | "skip48: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1364 | "addl $4, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1365 | "addl $4, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1366 | "decl %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1367 | "jnz secondloop48 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1368 | |
destinyXfate | 2:0e2ef1edf01b | 1369 | "end48: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1370 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 1371 | |
destinyXfate | 2:0e2ef1edf01b | 1372 | : "=a" (dummy_value_a), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 1373 | "=d" (dummy_value_d), |
destinyXfate | 2:0e2ef1edf01b | 1374 | "=c" (dummy_value_c), |
destinyXfate | 2:0e2ef1edf01b | 1375 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 1376 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 1377 | |
destinyXfate | 2:0e2ef1edf01b | 1378 | : "3" (srcptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 1379 | "4" (dstptr), // edi |
destinyXfate | 2:0e2ef1edf01b | 1380 | "0" (diff), // eax |
destinyXfate | 2:0e2ef1edf01b | 1381 | // was (unmask) "b" RESERVED // ebx // Global Offset Table idx |
destinyXfate | 2:0e2ef1edf01b | 1382 | "2" (len), // ecx |
destinyXfate | 2:0e2ef1edf01b | 1383 | "1" (mask) // edx |
destinyXfate | 2:0e2ef1edf01b | 1384 | |
destinyXfate | 2:0e2ef1edf01b | 1385 | #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 1386 | : "%mm0", "%mm1", "%mm2", "%mm3" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 1387 | , "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 1388 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1389 | ); |
destinyXfate | 2:0e2ef1edf01b | 1390 | } |
destinyXfate | 2:0e2ef1edf01b | 1391 | else /* mmx _not supported - Use modified C routine */ |
destinyXfate | 2:0e2ef1edf01b | 1392 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 1393 | { |
destinyXfate | 2:0e2ef1edf01b | 1394 | register png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 1395 | png_uint_32 initial_val = BPP6 * png_pass_start[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 1396 | /* png.c: png_pass_start[] = {0, 4, 0, 2, 0, 1, 0}; */ |
destinyXfate | 2:0e2ef1edf01b | 1397 | register int stride = BPP6 * png_pass_inc[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 1398 | /* png.c: png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */ |
destinyXfate | 2:0e2ef1edf01b | 1399 | register int rep_bytes = BPP6 * png_pass_width[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 1400 | /* png.c: png_pass_width[] = {8, 4, 4, 2, 2, 1, 1}; */ |
destinyXfate | 2:0e2ef1edf01b | 1401 | png_uint_32 len = png_ptr->width &~7; /* reduce to mult. of 8 */ |
destinyXfate | 2:0e2ef1edf01b | 1402 | int diff = (int) (png_ptr->width & 7); /* amount lost */ |
destinyXfate | 2:0e2ef1edf01b | 1403 | register png_uint_32 final_val = BPP6 * len; /* GRR bugfix */ |
destinyXfate | 2:0e2ef1edf01b | 1404 | |
destinyXfate | 2:0e2ef1edf01b | 1405 | srcptr = png_ptr->row_buf + 1 + initial_val; |
destinyXfate | 2:0e2ef1edf01b | 1406 | dstptr = row + initial_val; |
destinyXfate | 2:0e2ef1edf01b | 1407 | |
destinyXfate | 2:0e2ef1edf01b | 1408 | for (i = initial_val; i < final_val; i += stride) |
destinyXfate | 2:0e2ef1edf01b | 1409 | { |
destinyXfate | 2:0e2ef1edf01b | 1410 | png_memcpy(dstptr, srcptr, rep_bytes); |
destinyXfate | 2:0e2ef1edf01b | 1411 | srcptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1412 | dstptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1413 | } |
destinyXfate | 2:0e2ef1edf01b | 1414 | if (diff) /* number of leftover pixels: 3 for pngtest */ |
destinyXfate | 2:0e2ef1edf01b | 1415 | { |
destinyXfate | 2:0e2ef1edf01b | 1416 | final_val+=diff*BPP6; |
destinyXfate | 2:0e2ef1edf01b | 1417 | for (; i < final_val; i += stride) |
destinyXfate | 2:0e2ef1edf01b | 1418 | { |
destinyXfate | 2:0e2ef1edf01b | 1419 | if (rep_bytes > (int)(final_val-i)) |
destinyXfate | 2:0e2ef1edf01b | 1420 | rep_bytes = (int)(final_val-i); |
destinyXfate | 2:0e2ef1edf01b | 1421 | png_memcpy(dstptr, srcptr, rep_bytes); |
destinyXfate | 2:0e2ef1edf01b | 1422 | srcptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1423 | dstptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1424 | } |
destinyXfate | 2:0e2ef1edf01b | 1425 | } |
destinyXfate | 2:0e2ef1edf01b | 1426 | } /* end of else (_mmx_supported) */ |
destinyXfate | 2:0e2ef1edf01b | 1427 | |
destinyXfate | 2:0e2ef1edf01b | 1428 | break; |
destinyXfate | 2:0e2ef1edf01b | 1429 | } /* end 48 bpp */ |
destinyXfate | 2:0e2ef1edf01b | 1430 | |
destinyXfate | 2:0e2ef1edf01b | 1431 | case 64: /* png_ptr->row_info.pixel_depth */ |
destinyXfate | 2:0e2ef1edf01b | 1432 | { |
destinyXfate | 2:0e2ef1edf01b | 1433 | png_bytep srcptr; |
destinyXfate | 2:0e2ef1edf01b | 1434 | png_bytep dstptr; |
destinyXfate | 2:0e2ef1edf01b | 1435 | register png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 1436 | png_uint_32 initial_val = BPP8 * png_pass_start[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 1437 | /* png.c: png_pass_start[] = {0, 4, 0, 2, 0, 1, 0}; */ |
destinyXfate | 2:0e2ef1edf01b | 1438 | register int stride = BPP8 * png_pass_inc[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 1439 | /* png.c: png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */ |
destinyXfate | 2:0e2ef1edf01b | 1440 | register int rep_bytes = BPP8 * png_pass_width[png_ptr->pass]; |
destinyXfate | 2:0e2ef1edf01b | 1441 | /* png.c: png_pass_width[] = {8, 4, 4, 2, 2, 1, 1}; */ |
destinyXfate | 2:0e2ef1edf01b | 1442 | png_uint_32 len = png_ptr->width &~7; /* reduce to mult. of 8 */ |
destinyXfate | 2:0e2ef1edf01b | 1443 | int diff = (int) (png_ptr->width & 7); /* amount lost */ |
destinyXfate | 2:0e2ef1edf01b | 1444 | register png_uint_32 final_val = BPP8 * len; /* GRR bugfix */ |
destinyXfate | 2:0e2ef1edf01b | 1445 | |
destinyXfate | 2:0e2ef1edf01b | 1446 | srcptr = png_ptr->row_buf + 1 + initial_val; |
destinyXfate | 2:0e2ef1edf01b | 1447 | dstptr = row + initial_val; |
destinyXfate | 2:0e2ef1edf01b | 1448 | |
destinyXfate | 2:0e2ef1edf01b | 1449 | for (i = initial_val; i < final_val; i += stride) |
destinyXfate | 2:0e2ef1edf01b | 1450 | { |
destinyXfate | 2:0e2ef1edf01b | 1451 | png_memcpy(dstptr, srcptr, rep_bytes); |
destinyXfate | 2:0e2ef1edf01b | 1452 | srcptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1453 | dstptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1454 | } |
destinyXfate | 2:0e2ef1edf01b | 1455 | if (diff) /* number of leftover pixels: 3 for pngtest */ |
destinyXfate | 2:0e2ef1edf01b | 1456 | { |
destinyXfate | 2:0e2ef1edf01b | 1457 | final_val+=diff*BPP8; |
destinyXfate | 2:0e2ef1edf01b | 1458 | for (; i < final_val; i += stride) |
destinyXfate | 2:0e2ef1edf01b | 1459 | { |
destinyXfate | 2:0e2ef1edf01b | 1460 | if (rep_bytes > (int)(final_val-i)) |
destinyXfate | 2:0e2ef1edf01b | 1461 | rep_bytes = (int)(final_val-i); |
destinyXfate | 2:0e2ef1edf01b | 1462 | png_memcpy(dstptr, srcptr, rep_bytes); |
destinyXfate | 2:0e2ef1edf01b | 1463 | srcptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1464 | dstptr += stride; |
destinyXfate | 2:0e2ef1edf01b | 1465 | } |
destinyXfate | 2:0e2ef1edf01b | 1466 | } |
destinyXfate | 2:0e2ef1edf01b | 1467 | |
destinyXfate | 2:0e2ef1edf01b | 1468 | break; |
destinyXfate | 2:0e2ef1edf01b | 1469 | } /* end 64 bpp */ |
destinyXfate | 2:0e2ef1edf01b | 1470 | |
destinyXfate | 2:0e2ef1edf01b | 1471 | default: /* png_ptr->row_info.pixel_depth != 1,2,4,8,16,24,32,48,64 */ |
destinyXfate | 2:0e2ef1edf01b | 1472 | { |
destinyXfate | 2:0e2ef1edf01b | 1473 | /* this should never happen */ |
destinyXfate | 2:0e2ef1edf01b | 1474 | png_warning(png_ptr, "Invalid row_info.pixel_depth in pnggccrd"); |
destinyXfate | 2:0e2ef1edf01b | 1475 | break; |
destinyXfate | 2:0e2ef1edf01b | 1476 | } |
destinyXfate | 2:0e2ef1edf01b | 1477 | } /* end switch (png_ptr->row_info.pixel_depth) */ |
destinyXfate | 2:0e2ef1edf01b | 1478 | |
destinyXfate | 2:0e2ef1edf01b | 1479 | } /* end if (non-trivial mask) */ |
destinyXfate | 2:0e2ef1edf01b | 1480 | |
destinyXfate | 2:0e2ef1edf01b | 1481 | } /* end png_combine_row() */ |
destinyXfate | 2:0e2ef1edf01b | 1482 | |
destinyXfate | 2:0e2ef1edf01b | 1483 | #endif /* PNG_HAVE_MMX_COMBINE_ROW */ |
destinyXfate | 2:0e2ef1edf01b | 1484 | |
destinyXfate | 2:0e2ef1edf01b | 1485 | |
destinyXfate | 2:0e2ef1edf01b | 1486 | |
destinyXfate | 2:0e2ef1edf01b | 1487 | |
destinyXfate | 2:0e2ef1edf01b | 1488 | /*===========================================================================*/ |
destinyXfate | 2:0e2ef1edf01b | 1489 | /* */ |
destinyXfate | 2:0e2ef1edf01b | 1490 | /* P N G _ D O _ R E A D _ I N T E R L A C E */ |
destinyXfate | 2:0e2ef1edf01b | 1491 | /* */ |
destinyXfate | 2:0e2ef1edf01b | 1492 | /*===========================================================================*/ |
destinyXfate | 2:0e2ef1edf01b | 1493 | |
destinyXfate | 2:0e2ef1edf01b | 1494 | #if defined(PNG_READ_INTERLACING_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 1495 | #if defined(PNG_HAVE_MMX_READ_INTERLACE) |
destinyXfate | 2:0e2ef1edf01b | 1496 | |
destinyXfate | 2:0e2ef1edf01b | 1497 | /* png_do_read_interlace() is called after any 16-bit to 8-bit conversion |
destinyXfate | 2:0e2ef1edf01b | 1498 | * has taken place. [GRR: what other steps come before and/or after?] |
destinyXfate | 2:0e2ef1edf01b | 1499 | */ |
destinyXfate | 2:0e2ef1edf01b | 1500 | |
destinyXfate | 2:0e2ef1edf01b | 1501 | void /* PRIVATE */ |
destinyXfate | 2:0e2ef1edf01b | 1502 | png_do_read_interlace(png_structp png_ptr) |
destinyXfate | 2:0e2ef1edf01b | 1503 | { |
destinyXfate | 2:0e2ef1edf01b | 1504 | png_row_infop row_info = &(png_ptr->row_info); |
destinyXfate | 2:0e2ef1edf01b | 1505 | png_bytep row = png_ptr->row_buf + 1; |
destinyXfate | 2:0e2ef1edf01b | 1506 | int pass = png_ptr->pass; |
destinyXfate | 2:0e2ef1edf01b | 1507 | #if defined(PNG_READ_PACKSWAP_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 1508 | png_uint_32 transformations = png_ptr->transformations; |
destinyXfate | 2:0e2ef1edf01b | 1509 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1510 | |
destinyXfate | 2:0e2ef1edf01b | 1511 | png_debug(1, "in png_do_read_interlace (pnggccrd.c)\n"); |
destinyXfate | 2:0e2ef1edf01b | 1512 | |
destinyXfate | 2:0e2ef1edf01b | 1513 | #if defined(PNG_MMX_CODE_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 1514 | if (_mmx_supported == 2) { |
destinyXfate | 2:0e2ef1edf01b | 1515 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 1516 | /* this should have happened in png_init_mmx_flags() already */ |
destinyXfate | 2:0e2ef1edf01b | 1517 | png_warning(png_ptr, "asm_flags may not have been initialized"); |
destinyXfate | 2:0e2ef1edf01b | 1518 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1519 | png_mmx_support(); |
destinyXfate | 2:0e2ef1edf01b | 1520 | } |
destinyXfate | 2:0e2ef1edf01b | 1521 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1522 | |
destinyXfate | 2:0e2ef1edf01b | 1523 | if (row != NULL && row_info != NULL) |
destinyXfate | 2:0e2ef1edf01b | 1524 | { |
destinyXfate | 2:0e2ef1edf01b | 1525 | png_uint_32 final_width; |
destinyXfate | 2:0e2ef1edf01b | 1526 | |
destinyXfate | 2:0e2ef1edf01b | 1527 | final_width = row_info->width * png_pass_inc[pass]; |
destinyXfate | 2:0e2ef1edf01b | 1528 | |
destinyXfate | 2:0e2ef1edf01b | 1529 | switch (row_info->pixel_depth) |
destinyXfate | 2:0e2ef1edf01b | 1530 | { |
destinyXfate | 2:0e2ef1edf01b | 1531 | case 1: |
destinyXfate | 2:0e2ef1edf01b | 1532 | { |
destinyXfate | 2:0e2ef1edf01b | 1533 | png_bytep sp, dp; |
destinyXfate | 2:0e2ef1edf01b | 1534 | int sshift, dshift; |
destinyXfate | 2:0e2ef1edf01b | 1535 | int s_start, s_end, s_inc; |
destinyXfate | 2:0e2ef1edf01b | 1536 | png_byte v; |
destinyXfate | 2:0e2ef1edf01b | 1537 | png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 1538 | int j; |
destinyXfate | 2:0e2ef1edf01b | 1539 | |
destinyXfate | 2:0e2ef1edf01b | 1540 | sp = row + (png_size_t)((row_info->width - 1) >> 3); |
destinyXfate | 2:0e2ef1edf01b | 1541 | dp = row + (png_size_t)((final_width - 1) >> 3); |
destinyXfate | 2:0e2ef1edf01b | 1542 | #if defined(PNG_READ_PACKSWAP_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 1543 | if (transformations & PNG_PACKSWAP) |
destinyXfate | 2:0e2ef1edf01b | 1544 | { |
destinyXfate | 2:0e2ef1edf01b | 1545 | sshift = (int)((row_info->width + 7) & 7); |
destinyXfate | 2:0e2ef1edf01b | 1546 | dshift = (int)((final_width + 7) & 7); |
destinyXfate | 2:0e2ef1edf01b | 1547 | s_start = 7; |
destinyXfate | 2:0e2ef1edf01b | 1548 | s_end = 0; |
destinyXfate | 2:0e2ef1edf01b | 1549 | s_inc = -1; |
destinyXfate | 2:0e2ef1edf01b | 1550 | } |
destinyXfate | 2:0e2ef1edf01b | 1551 | else |
destinyXfate | 2:0e2ef1edf01b | 1552 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1553 | { |
destinyXfate | 2:0e2ef1edf01b | 1554 | sshift = 7 - (int)((row_info->width + 7) & 7); |
destinyXfate | 2:0e2ef1edf01b | 1555 | dshift = 7 - (int)((final_width + 7) & 7); |
destinyXfate | 2:0e2ef1edf01b | 1556 | s_start = 0; |
destinyXfate | 2:0e2ef1edf01b | 1557 | s_end = 7; |
destinyXfate | 2:0e2ef1edf01b | 1558 | s_inc = 1; |
destinyXfate | 2:0e2ef1edf01b | 1559 | } |
destinyXfate | 2:0e2ef1edf01b | 1560 | |
destinyXfate | 2:0e2ef1edf01b | 1561 | for (i = row_info->width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 1562 | { |
destinyXfate | 2:0e2ef1edf01b | 1563 | v = (png_byte)((*sp >> sshift) & 0x1); |
destinyXfate | 2:0e2ef1edf01b | 1564 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 1565 | { |
destinyXfate | 2:0e2ef1edf01b | 1566 | *dp &= (png_byte)((0x7f7f >> (7 - dshift)) & 0xff); |
destinyXfate | 2:0e2ef1edf01b | 1567 | *dp |= (png_byte)(v << dshift); |
destinyXfate | 2:0e2ef1edf01b | 1568 | if (dshift == s_end) |
destinyXfate | 2:0e2ef1edf01b | 1569 | { |
destinyXfate | 2:0e2ef1edf01b | 1570 | dshift = s_start; |
destinyXfate | 2:0e2ef1edf01b | 1571 | dp--; |
destinyXfate | 2:0e2ef1edf01b | 1572 | } |
destinyXfate | 2:0e2ef1edf01b | 1573 | else |
destinyXfate | 2:0e2ef1edf01b | 1574 | dshift += s_inc; |
destinyXfate | 2:0e2ef1edf01b | 1575 | } |
destinyXfate | 2:0e2ef1edf01b | 1576 | if (sshift == s_end) |
destinyXfate | 2:0e2ef1edf01b | 1577 | { |
destinyXfate | 2:0e2ef1edf01b | 1578 | sshift = s_start; |
destinyXfate | 2:0e2ef1edf01b | 1579 | sp--; |
destinyXfate | 2:0e2ef1edf01b | 1580 | } |
destinyXfate | 2:0e2ef1edf01b | 1581 | else |
destinyXfate | 2:0e2ef1edf01b | 1582 | sshift += s_inc; |
destinyXfate | 2:0e2ef1edf01b | 1583 | } |
destinyXfate | 2:0e2ef1edf01b | 1584 | break; |
destinyXfate | 2:0e2ef1edf01b | 1585 | } |
destinyXfate | 2:0e2ef1edf01b | 1586 | |
destinyXfate | 2:0e2ef1edf01b | 1587 | case 2: |
destinyXfate | 2:0e2ef1edf01b | 1588 | { |
destinyXfate | 2:0e2ef1edf01b | 1589 | png_bytep sp, dp; |
destinyXfate | 2:0e2ef1edf01b | 1590 | int sshift, dshift; |
destinyXfate | 2:0e2ef1edf01b | 1591 | int s_start, s_end, s_inc; |
destinyXfate | 2:0e2ef1edf01b | 1592 | png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 1593 | |
destinyXfate | 2:0e2ef1edf01b | 1594 | sp = row + (png_size_t)((row_info->width - 1) >> 2); |
destinyXfate | 2:0e2ef1edf01b | 1595 | dp = row + (png_size_t)((final_width - 1) >> 2); |
destinyXfate | 2:0e2ef1edf01b | 1596 | #if defined(PNG_READ_PACKSWAP_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 1597 | if (transformations & PNG_PACKSWAP) |
destinyXfate | 2:0e2ef1edf01b | 1598 | { |
destinyXfate | 2:0e2ef1edf01b | 1599 | sshift = (png_size_t)(((row_info->width + 3) & 3) << 1); |
destinyXfate | 2:0e2ef1edf01b | 1600 | dshift = (png_size_t)(((final_width + 3) & 3) << 1); |
destinyXfate | 2:0e2ef1edf01b | 1601 | s_start = 6; |
destinyXfate | 2:0e2ef1edf01b | 1602 | s_end = 0; |
destinyXfate | 2:0e2ef1edf01b | 1603 | s_inc = -2; |
destinyXfate | 2:0e2ef1edf01b | 1604 | } |
destinyXfate | 2:0e2ef1edf01b | 1605 | else |
destinyXfate | 2:0e2ef1edf01b | 1606 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1607 | { |
destinyXfate | 2:0e2ef1edf01b | 1608 | sshift = (png_size_t)((3 - ((row_info->width + 3) & 3)) << 1); |
destinyXfate | 2:0e2ef1edf01b | 1609 | dshift = (png_size_t)((3 - ((final_width + 3) & 3)) << 1); |
destinyXfate | 2:0e2ef1edf01b | 1610 | s_start = 0; |
destinyXfate | 2:0e2ef1edf01b | 1611 | s_end = 6; |
destinyXfate | 2:0e2ef1edf01b | 1612 | s_inc = 2; |
destinyXfate | 2:0e2ef1edf01b | 1613 | } |
destinyXfate | 2:0e2ef1edf01b | 1614 | |
destinyXfate | 2:0e2ef1edf01b | 1615 | for (i = row_info->width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 1616 | { |
destinyXfate | 2:0e2ef1edf01b | 1617 | png_byte v; |
destinyXfate | 2:0e2ef1edf01b | 1618 | int j; |
destinyXfate | 2:0e2ef1edf01b | 1619 | |
destinyXfate | 2:0e2ef1edf01b | 1620 | v = (png_byte)((*sp >> sshift) & 0x3); |
destinyXfate | 2:0e2ef1edf01b | 1621 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 1622 | { |
destinyXfate | 2:0e2ef1edf01b | 1623 | *dp &= (png_byte)((0x3f3f >> (6 - dshift)) & 0xff); |
destinyXfate | 2:0e2ef1edf01b | 1624 | *dp |= (png_byte)(v << dshift); |
destinyXfate | 2:0e2ef1edf01b | 1625 | if (dshift == s_end) |
destinyXfate | 2:0e2ef1edf01b | 1626 | { |
destinyXfate | 2:0e2ef1edf01b | 1627 | dshift = s_start; |
destinyXfate | 2:0e2ef1edf01b | 1628 | dp--; |
destinyXfate | 2:0e2ef1edf01b | 1629 | } |
destinyXfate | 2:0e2ef1edf01b | 1630 | else |
destinyXfate | 2:0e2ef1edf01b | 1631 | dshift += s_inc; |
destinyXfate | 2:0e2ef1edf01b | 1632 | } |
destinyXfate | 2:0e2ef1edf01b | 1633 | if (sshift == s_end) |
destinyXfate | 2:0e2ef1edf01b | 1634 | { |
destinyXfate | 2:0e2ef1edf01b | 1635 | sshift = s_start; |
destinyXfate | 2:0e2ef1edf01b | 1636 | sp--; |
destinyXfate | 2:0e2ef1edf01b | 1637 | } |
destinyXfate | 2:0e2ef1edf01b | 1638 | else |
destinyXfate | 2:0e2ef1edf01b | 1639 | sshift += s_inc; |
destinyXfate | 2:0e2ef1edf01b | 1640 | } |
destinyXfate | 2:0e2ef1edf01b | 1641 | break; |
destinyXfate | 2:0e2ef1edf01b | 1642 | } |
destinyXfate | 2:0e2ef1edf01b | 1643 | |
destinyXfate | 2:0e2ef1edf01b | 1644 | case 4: |
destinyXfate | 2:0e2ef1edf01b | 1645 | { |
destinyXfate | 2:0e2ef1edf01b | 1646 | png_bytep sp, dp; |
destinyXfate | 2:0e2ef1edf01b | 1647 | int sshift, dshift; |
destinyXfate | 2:0e2ef1edf01b | 1648 | int s_start, s_end, s_inc; |
destinyXfate | 2:0e2ef1edf01b | 1649 | png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 1650 | |
destinyXfate | 2:0e2ef1edf01b | 1651 | sp = row + (png_size_t)((row_info->width - 1) >> 1); |
destinyXfate | 2:0e2ef1edf01b | 1652 | dp = row + (png_size_t)((final_width - 1) >> 1); |
destinyXfate | 2:0e2ef1edf01b | 1653 | #if defined(PNG_READ_PACKSWAP_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 1654 | if (transformations & PNG_PACKSWAP) |
destinyXfate | 2:0e2ef1edf01b | 1655 | { |
destinyXfate | 2:0e2ef1edf01b | 1656 | sshift = (png_size_t)(((row_info->width + 1) & 1) << 2); |
destinyXfate | 2:0e2ef1edf01b | 1657 | dshift = (png_size_t)(((final_width + 1) & 1) << 2); |
destinyXfate | 2:0e2ef1edf01b | 1658 | s_start = 4; |
destinyXfate | 2:0e2ef1edf01b | 1659 | s_end = 0; |
destinyXfate | 2:0e2ef1edf01b | 1660 | s_inc = -4; |
destinyXfate | 2:0e2ef1edf01b | 1661 | } |
destinyXfate | 2:0e2ef1edf01b | 1662 | else |
destinyXfate | 2:0e2ef1edf01b | 1663 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1664 | { |
destinyXfate | 2:0e2ef1edf01b | 1665 | sshift = (png_size_t)((1 - ((row_info->width + 1) & 1)) << 2); |
destinyXfate | 2:0e2ef1edf01b | 1666 | dshift = (png_size_t)((1 - ((final_width + 1) & 1)) << 2); |
destinyXfate | 2:0e2ef1edf01b | 1667 | s_start = 0; |
destinyXfate | 2:0e2ef1edf01b | 1668 | s_end = 4; |
destinyXfate | 2:0e2ef1edf01b | 1669 | s_inc = 4; |
destinyXfate | 2:0e2ef1edf01b | 1670 | } |
destinyXfate | 2:0e2ef1edf01b | 1671 | |
destinyXfate | 2:0e2ef1edf01b | 1672 | for (i = row_info->width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 1673 | { |
destinyXfate | 2:0e2ef1edf01b | 1674 | png_byte v; |
destinyXfate | 2:0e2ef1edf01b | 1675 | int j; |
destinyXfate | 2:0e2ef1edf01b | 1676 | |
destinyXfate | 2:0e2ef1edf01b | 1677 | v = (png_byte)((*sp >> sshift) & 0xf); |
destinyXfate | 2:0e2ef1edf01b | 1678 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 1679 | { |
destinyXfate | 2:0e2ef1edf01b | 1680 | *dp &= (png_byte)((0xf0f >> (4 - dshift)) & 0xff); |
destinyXfate | 2:0e2ef1edf01b | 1681 | *dp |= (png_byte)(v << dshift); |
destinyXfate | 2:0e2ef1edf01b | 1682 | if (dshift == s_end) |
destinyXfate | 2:0e2ef1edf01b | 1683 | { |
destinyXfate | 2:0e2ef1edf01b | 1684 | dshift = s_start; |
destinyXfate | 2:0e2ef1edf01b | 1685 | dp--; |
destinyXfate | 2:0e2ef1edf01b | 1686 | } |
destinyXfate | 2:0e2ef1edf01b | 1687 | else |
destinyXfate | 2:0e2ef1edf01b | 1688 | dshift += s_inc; |
destinyXfate | 2:0e2ef1edf01b | 1689 | } |
destinyXfate | 2:0e2ef1edf01b | 1690 | if (sshift == s_end) |
destinyXfate | 2:0e2ef1edf01b | 1691 | { |
destinyXfate | 2:0e2ef1edf01b | 1692 | sshift = s_start; |
destinyXfate | 2:0e2ef1edf01b | 1693 | sp--; |
destinyXfate | 2:0e2ef1edf01b | 1694 | } |
destinyXfate | 2:0e2ef1edf01b | 1695 | else |
destinyXfate | 2:0e2ef1edf01b | 1696 | sshift += s_inc; |
destinyXfate | 2:0e2ef1edf01b | 1697 | } |
destinyXfate | 2:0e2ef1edf01b | 1698 | break; |
destinyXfate | 2:0e2ef1edf01b | 1699 | } |
destinyXfate | 2:0e2ef1edf01b | 1700 | |
destinyXfate | 2:0e2ef1edf01b | 1701 | /*====================================================================*/ |
destinyXfate | 2:0e2ef1edf01b | 1702 | |
destinyXfate | 2:0e2ef1edf01b | 1703 | default: /* 8-bit or larger (this is where the routine is modified) */ |
destinyXfate | 2:0e2ef1edf01b | 1704 | { |
destinyXfate | 2:0e2ef1edf01b | 1705 | #if 0 |
destinyXfate | 2:0e2ef1edf01b | 1706 | // static unsigned long long _const4 = 0x0000000000FFFFFFLL; no good |
destinyXfate | 2:0e2ef1edf01b | 1707 | // static unsigned long long const4 = 0x0000000000FFFFFFLL; no good |
destinyXfate | 2:0e2ef1edf01b | 1708 | // unsigned long long _const4 = 0x0000000000FFFFFFLL; no good |
destinyXfate | 2:0e2ef1edf01b | 1709 | // unsigned long long const4 = 0x0000000000FFFFFFLL; no good |
destinyXfate | 2:0e2ef1edf01b | 1710 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1711 | png_bytep sptr, dp; |
destinyXfate | 2:0e2ef1edf01b | 1712 | png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 1713 | png_size_t pixel_bytes; |
destinyXfate | 2:0e2ef1edf01b | 1714 | int width = (int)row_info->width; |
destinyXfate | 2:0e2ef1edf01b | 1715 | |
destinyXfate | 2:0e2ef1edf01b | 1716 | pixel_bytes = (row_info->pixel_depth >> 3); |
destinyXfate | 2:0e2ef1edf01b | 1717 | |
destinyXfate | 2:0e2ef1edf01b | 1718 | /* point sptr at the last pixel in the pre-expanded row: */ |
destinyXfate | 2:0e2ef1edf01b | 1719 | sptr = row + (width - 1) * pixel_bytes; |
destinyXfate | 2:0e2ef1edf01b | 1720 | |
destinyXfate | 2:0e2ef1edf01b | 1721 | /* point dp at the last pixel position in the expanded row: */ |
destinyXfate | 2:0e2ef1edf01b | 1722 | dp = row + (final_width - 1) * pixel_bytes; |
destinyXfate | 2:0e2ef1edf01b | 1723 | |
destinyXfate | 2:0e2ef1edf01b | 1724 | /* New code by Nirav Chhatrapati - Intel Corporation */ |
destinyXfate | 2:0e2ef1edf01b | 1725 | |
destinyXfate | 2:0e2ef1edf01b | 1726 | #if defined(PNG_MMX_CODE_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 1727 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 1728 | if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_INTERLACE) |
destinyXfate | 2:0e2ef1edf01b | 1729 | /* && _mmx_supported */ ) |
destinyXfate | 2:0e2ef1edf01b | 1730 | #else |
destinyXfate | 2:0e2ef1edf01b | 1731 | if (_mmx_supported) |
destinyXfate | 2:0e2ef1edf01b | 1732 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1733 | { |
destinyXfate | 2:0e2ef1edf01b | 1734 | //-------------------------------------------------------------- |
destinyXfate | 2:0e2ef1edf01b | 1735 | if (pixel_bytes == 3) |
destinyXfate | 2:0e2ef1edf01b | 1736 | { |
destinyXfate | 2:0e2ef1edf01b | 1737 | if (((pass == 0) || (pass == 1)) && width) |
destinyXfate | 2:0e2ef1edf01b | 1738 | { |
destinyXfate | 2:0e2ef1edf01b | 1739 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 1740 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 1741 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 1742 | int dummy_value_a; |
destinyXfate | 2:0e2ef1edf01b | 1743 | |
destinyXfate | 2:0e2ef1edf01b | 1744 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 1745 | "subl $21, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1746 | // (png_pass_inc[pass] - 1)*pixel_bytes |
destinyXfate | 2:0e2ef1edf01b | 1747 | |
destinyXfate | 2:0e2ef1edf01b | 1748 | ".loop3_pass0: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1749 | "movd (%%esi), %%mm0 \n\t" // x x x x x 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1750 | "pand (%3), %%mm0 \n\t" // z z z z z 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1751 | "movq %%mm0, %%mm1 \n\t" // z z z z z 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1752 | "psllq $16, %%mm0 \n\t" // z z z 2 1 0 z z |
destinyXfate | 2:0e2ef1edf01b | 1753 | "movq %%mm0, %%mm2 \n\t" // z z z 2 1 0 z z |
destinyXfate | 2:0e2ef1edf01b | 1754 | "psllq $24, %%mm0 \n\t" // 2 1 0 z z z z z |
destinyXfate | 2:0e2ef1edf01b | 1755 | "psrlq $8, %%mm1 \n\t" // z z z z z z 2 1 |
destinyXfate | 2:0e2ef1edf01b | 1756 | "por %%mm2, %%mm0 \n\t" // 2 1 0 2 1 0 z z |
destinyXfate | 2:0e2ef1edf01b | 1757 | "por %%mm1, %%mm0 \n\t" // 2 1 0 2 1 0 2 1 |
destinyXfate | 2:0e2ef1edf01b | 1758 | "movq %%mm0, %%mm3 \n\t" // 2 1 0 2 1 0 2 1 |
destinyXfate | 2:0e2ef1edf01b | 1759 | "psllq $16, %%mm0 \n\t" // 0 2 1 0 2 1 z z |
destinyXfate | 2:0e2ef1edf01b | 1760 | "movq %%mm3, %%mm4 \n\t" // 2 1 0 2 1 0 2 1 |
destinyXfate | 2:0e2ef1edf01b | 1761 | "punpckhdq %%mm0, %%mm3 \n\t" // 0 2 1 0 2 1 0 2 |
destinyXfate | 2:0e2ef1edf01b | 1762 | "movq %%mm4, 16(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1763 | "psrlq $32, %%mm0 \n\t" // z z z z 0 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1764 | "movq %%mm3, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1765 | "punpckldq %%mm4, %%mm0 \n\t" // 1 0 2 1 0 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1766 | "subl $3, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1767 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1768 | "subl $24, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1769 | "decl %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1770 | "jnz .loop3_pass0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1771 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 1772 | |
destinyXfate | 2:0e2ef1edf01b | 1773 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 1774 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 1775 | "=D" (dummy_value_D), |
destinyXfate | 2:0e2ef1edf01b | 1776 | "=a" (dummy_value_a) |
destinyXfate | 2:0e2ef1edf01b | 1777 | |
destinyXfate | 2:0e2ef1edf01b | 1778 | |
destinyXfate | 2:0e2ef1edf01b | 1779 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 1780 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 1781 | "0" (width), // ecx |
destinyXfate | 2:0e2ef1edf01b | 1782 | "3" (&_const4) // %1(?) (0x0000000000FFFFFFLL) |
destinyXfate | 2:0e2ef1edf01b | 1783 | |
destinyXfate | 2:0e2ef1edf01b | 1784 | #if 0 /* %mm0, ..., %mm4 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 1785 | : "%mm0", "%mm1", "%mm2" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 1786 | , "%mm3", "%mm4" |
destinyXfate | 2:0e2ef1edf01b | 1787 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1788 | ); |
destinyXfate | 2:0e2ef1edf01b | 1789 | } |
destinyXfate | 2:0e2ef1edf01b | 1790 | else if (((pass == 2) || (pass == 3)) && width) |
destinyXfate | 2:0e2ef1edf01b | 1791 | { |
destinyXfate | 2:0e2ef1edf01b | 1792 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 1793 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 1794 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 1795 | int dummy_value_a; |
destinyXfate | 2:0e2ef1edf01b | 1796 | |
destinyXfate | 2:0e2ef1edf01b | 1797 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 1798 | "subl $9, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1799 | // (png_pass_inc[pass] - 1)*pixel_bytes |
destinyXfate | 2:0e2ef1edf01b | 1800 | |
destinyXfate | 2:0e2ef1edf01b | 1801 | ".loop3_pass2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1802 | "movd (%%esi), %%mm0 \n\t" // x x x x x 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1803 | "pand (%3), %%mm0 \n\t" // z z z z z 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1804 | "movq %%mm0, %%mm1 \n\t" // z z z z z 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1805 | "psllq $16, %%mm0 \n\t" // z z z 2 1 0 z z |
destinyXfate | 2:0e2ef1edf01b | 1806 | "movq %%mm0, %%mm2 \n\t" // z z z 2 1 0 z z |
destinyXfate | 2:0e2ef1edf01b | 1807 | "psllq $24, %%mm0 \n\t" // 2 1 0 z z z z z |
destinyXfate | 2:0e2ef1edf01b | 1808 | "psrlq $8, %%mm1 \n\t" // z z z z z z 2 1 |
destinyXfate | 2:0e2ef1edf01b | 1809 | "por %%mm2, %%mm0 \n\t" // 2 1 0 2 1 0 z z |
destinyXfate | 2:0e2ef1edf01b | 1810 | "por %%mm1, %%mm0 \n\t" // 2 1 0 2 1 0 2 1 |
destinyXfate | 2:0e2ef1edf01b | 1811 | "movq %%mm0, 4(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1812 | "psrlq $16, %%mm0 \n\t" // z z 2 1 0 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1813 | "subl $3, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1814 | "movd %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1815 | "subl $12, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1816 | "decl %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1817 | "jnz .loop3_pass2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1818 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 1819 | |
destinyXfate | 2:0e2ef1edf01b | 1820 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 1821 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 1822 | "=D" (dummy_value_D), |
destinyXfate | 2:0e2ef1edf01b | 1823 | "=a" (dummy_value_a) |
destinyXfate | 2:0e2ef1edf01b | 1824 | |
destinyXfate | 2:0e2ef1edf01b | 1825 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 1826 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 1827 | "0" (width), // ecx |
destinyXfate | 2:0e2ef1edf01b | 1828 | "3" (&_const4) // (0x0000000000FFFFFFLL) |
destinyXfate | 2:0e2ef1edf01b | 1829 | |
destinyXfate | 2:0e2ef1edf01b | 1830 | #if 0 /* %mm0, ..., %mm2 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 1831 | : "%mm0", "%mm1", "%mm2" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 1832 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1833 | ); |
destinyXfate | 2:0e2ef1edf01b | 1834 | } |
destinyXfate | 2:0e2ef1edf01b | 1835 | else if (width) /* && ((pass == 4) || (pass == 5)) */ |
destinyXfate | 2:0e2ef1edf01b | 1836 | { |
destinyXfate | 2:0e2ef1edf01b | 1837 | int width_mmx = ((width >> 1) << 1) - 8; // GRR: huh? |
destinyXfate | 2:0e2ef1edf01b | 1838 | if (width_mmx < 0) |
destinyXfate | 2:0e2ef1edf01b | 1839 | width_mmx = 0; |
destinyXfate | 2:0e2ef1edf01b | 1840 | width -= width_mmx; // 8 or 9 pix, 24 or 27 bytes |
destinyXfate | 2:0e2ef1edf01b | 1841 | if (width_mmx) |
destinyXfate | 2:0e2ef1edf01b | 1842 | { |
destinyXfate | 2:0e2ef1edf01b | 1843 | // png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; |
destinyXfate | 2:0e2ef1edf01b | 1844 | // sptr points at last pixel in pre-expanded row |
destinyXfate | 2:0e2ef1edf01b | 1845 | // dp points at last pixel position in expanded row |
destinyXfate | 2:0e2ef1edf01b | 1846 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 1847 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 1848 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 1849 | int dummy_value_a; |
destinyXfate | 2:0e2ef1edf01b | 1850 | int dummy_value_d; |
destinyXfate | 2:0e2ef1edf01b | 1851 | |
destinyXfate | 2:0e2ef1edf01b | 1852 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 1853 | "subl $3, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1854 | "subl $9, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1855 | // (png_pass_inc[pass] + 1)*pixel_bytes |
destinyXfate | 2:0e2ef1edf01b | 1856 | |
destinyXfate | 2:0e2ef1edf01b | 1857 | ".loop3_pass4: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1858 | "movq (%%esi), %%mm0 \n\t" // x x 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1859 | "movq %%mm0, %%mm1 \n\t" // x x 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1860 | "movq %%mm0, %%mm2 \n\t" // x x 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1861 | "psllq $24, %%mm0 \n\t" // 4 3 2 1 0 z z z |
destinyXfate | 2:0e2ef1edf01b | 1862 | "pand (%3), %%mm1 \n\t" // z z z z z 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1863 | "psrlq $24, %%mm2 \n\t" // z z z x x 5 4 3 |
destinyXfate | 2:0e2ef1edf01b | 1864 | "por %%mm1, %%mm0 \n\t" // 4 3 2 1 0 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1865 | "movq %%mm2, %%mm3 \n\t" // z z z x x 5 4 3 |
destinyXfate | 2:0e2ef1edf01b | 1866 | "psllq $8, %%mm2 \n\t" // z z x x 5 4 3 z |
destinyXfate | 2:0e2ef1edf01b | 1867 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1868 | "psrlq $16, %%mm3 \n\t" // z z z z z x x 5 |
destinyXfate | 2:0e2ef1edf01b | 1869 | "pand (%4), %%mm3 \n\t" // z z z z z z z 5 |
destinyXfate | 2:0e2ef1edf01b | 1870 | "por %%mm3, %%mm2 \n\t" // z z x x 5 4 3 5 |
destinyXfate | 2:0e2ef1edf01b | 1871 | "subl $6, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1872 | "movd %%mm2, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1873 | "subl $12, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1874 | "subl $2, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1875 | "jnz .loop3_pass4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1876 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 1877 | |
destinyXfate | 2:0e2ef1edf01b | 1878 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 1879 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 1880 | "=D" (dummy_value_D), |
destinyXfate | 2:0e2ef1edf01b | 1881 | "=a" (dummy_value_a), |
destinyXfate | 2:0e2ef1edf01b | 1882 | "=d" (dummy_value_d) |
destinyXfate | 2:0e2ef1edf01b | 1883 | |
destinyXfate | 2:0e2ef1edf01b | 1884 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 1885 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 1886 | "0" (width_mmx), // ecx |
destinyXfate | 2:0e2ef1edf01b | 1887 | "3" (&_const4), // 0x0000000000FFFFFFLL |
destinyXfate | 2:0e2ef1edf01b | 1888 | "4" (&_const6) // 0x00000000000000FFLL |
destinyXfate | 2:0e2ef1edf01b | 1889 | |
destinyXfate | 2:0e2ef1edf01b | 1890 | #if 0 /* %mm0, ..., %mm3 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 1891 | : "%mm0", "%mm1" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 1892 | , "%mm2", "%mm3" |
destinyXfate | 2:0e2ef1edf01b | 1893 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1894 | ); |
destinyXfate | 2:0e2ef1edf01b | 1895 | } |
destinyXfate | 2:0e2ef1edf01b | 1896 | |
destinyXfate | 2:0e2ef1edf01b | 1897 | sptr -= width_mmx*3; |
destinyXfate | 2:0e2ef1edf01b | 1898 | dp -= width_mmx*6; |
destinyXfate | 2:0e2ef1edf01b | 1899 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 1900 | { |
destinyXfate | 2:0e2ef1edf01b | 1901 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 1902 | int j; |
destinyXfate | 2:0e2ef1edf01b | 1903 | |
destinyXfate | 2:0e2ef1edf01b | 1904 | png_memcpy(v, sptr, 3); |
destinyXfate | 2:0e2ef1edf01b | 1905 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 1906 | { |
destinyXfate | 2:0e2ef1edf01b | 1907 | png_memcpy(dp, v, 3); |
destinyXfate | 2:0e2ef1edf01b | 1908 | dp -= 3; |
destinyXfate | 2:0e2ef1edf01b | 1909 | } |
destinyXfate | 2:0e2ef1edf01b | 1910 | sptr -= 3; |
destinyXfate | 2:0e2ef1edf01b | 1911 | } |
destinyXfate | 2:0e2ef1edf01b | 1912 | } |
destinyXfate | 2:0e2ef1edf01b | 1913 | } /* end of pixel_bytes == 3 */ |
destinyXfate | 2:0e2ef1edf01b | 1914 | |
destinyXfate | 2:0e2ef1edf01b | 1915 | //-------------------------------------------------------------- |
destinyXfate | 2:0e2ef1edf01b | 1916 | else if (pixel_bytes == 1) |
destinyXfate | 2:0e2ef1edf01b | 1917 | { |
destinyXfate | 2:0e2ef1edf01b | 1918 | if (((pass == 0) || (pass == 1)) && width) |
destinyXfate | 2:0e2ef1edf01b | 1919 | { |
destinyXfate | 2:0e2ef1edf01b | 1920 | int width_mmx = ((width >> 2) << 2); |
destinyXfate | 2:0e2ef1edf01b | 1921 | width -= width_mmx; // 0-3 pixels => 0-3 bytes |
destinyXfate | 2:0e2ef1edf01b | 1922 | if (width_mmx) |
destinyXfate | 2:0e2ef1edf01b | 1923 | { |
destinyXfate | 2:0e2ef1edf01b | 1924 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 1925 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 1926 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 1927 | |
destinyXfate | 2:0e2ef1edf01b | 1928 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 1929 | "subl $3, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1930 | "subl $31, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1931 | |
destinyXfate | 2:0e2ef1edf01b | 1932 | ".loop1_pass0: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1933 | "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1934 | "movq %%mm0, %%mm1 \n\t" // x x x x 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 1935 | "punpcklbw %%mm0, %%mm0 \n\t" // 3 3 2 2 1 1 0 0 |
destinyXfate | 2:0e2ef1edf01b | 1936 | "movq %%mm0, %%mm2 \n\t" // 3 3 2 2 1 1 0 0 |
destinyXfate | 2:0e2ef1edf01b | 1937 | "punpcklwd %%mm0, %%mm0 \n\t" // 1 1 1 1 0 0 0 0 |
destinyXfate | 2:0e2ef1edf01b | 1938 | "movq %%mm0, %%mm3 \n\t" // 1 1 1 1 0 0 0 0 |
destinyXfate | 2:0e2ef1edf01b | 1939 | "punpckldq %%mm0, %%mm0 \n\t" // 0 0 0 0 0 0 0 0 |
destinyXfate | 2:0e2ef1edf01b | 1940 | "punpckhdq %%mm3, %%mm3 \n\t" // 1 1 1 1 1 1 1 1 |
destinyXfate | 2:0e2ef1edf01b | 1941 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1942 | "punpckhwd %%mm2, %%mm2 \n\t" // 3 3 3 3 2 2 2 2 |
destinyXfate | 2:0e2ef1edf01b | 1943 | "movq %%mm3, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1944 | "movq %%mm2, %%mm4 \n\t" // 3 3 3 3 2 2 2 2 |
destinyXfate | 2:0e2ef1edf01b | 1945 | "punpckldq %%mm2, %%mm2 \n\t" // 2 2 2 2 2 2 2 2 |
destinyXfate | 2:0e2ef1edf01b | 1946 | "punpckhdq %%mm4, %%mm4 \n\t" // 3 3 3 3 3 3 3 3 |
destinyXfate | 2:0e2ef1edf01b | 1947 | "movq %%mm2, 16(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1948 | "subl $4, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1949 | "movq %%mm4, 24(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1950 | "subl $32, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1951 | "subl $4, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1952 | "jnz .loop1_pass0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 1953 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 1954 | |
destinyXfate | 2:0e2ef1edf01b | 1955 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 1956 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 1957 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 1958 | |
destinyXfate | 2:0e2ef1edf01b | 1959 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 1960 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 1961 | "0" (width_mmx) // ecx |
destinyXfate | 2:0e2ef1edf01b | 1962 | |
destinyXfate | 2:0e2ef1edf01b | 1963 | #if 0 /* %mm0, ..., %mm4 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 1964 | : "%mm0", "%mm1", "%mm2" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 1965 | , "%mm3", "%mm4" |
destinyXfate | 2:0e2ef1edf01b | 1966 | #endif |
destinyXfate | 2:0e2ef1edf01b | 1967 | ); |
destinyXfate | 2:0e2ef1edf01b | 1968 | } |
destinyXfate | 2:0e2ef1edf01b | 1969 | |
destinyXfate | 2:0e2ef1edf01b | 1970 | sptr -= width_mmx; |
destinyXfate | 2:0e2ef1edf01b | 1971 | dp -= width_mmx*8; |
destinyXfate | 2:0e2ef1edf01b | 1972 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 1973 | { |
destinyXfate | 2:0e2ef1edf01b | 1974 | int j; |
destinyXfate | 2:0e2ef1edf01b | 1975 | |
destinyXfate | 2:0e2ef1edf01b | 1976 | /* I simplified this part in version 1.0.4e |
destinyXfate | 2:0e2ef1edf01b | 1977 | * here and in several other instances where |
destinyXfate | 2:0e2ef1edf01b | 1978 | * pixel_bytes == 1 -- GR-P |
destinyXfate | 2:0e2ef1edf01b | 1979 | * |
destinyXfate | 2:0e2ef1edf01b | 1980 | * Original code: |
destinyXfate | 2:0e2ef1edf01b | 1981 | * |
destinyXfate | 2:0e2ef1edf01b | 1982 | * png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 1983 | * png_memcpy(v, sptr, pixel_bytes); |
destinyXfate | 2:0e2ef1edf01b | 1984 | * for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 1985 | * { |
destinyXfate | 2:0e2ef1edf01b | 1986 | * png_memcpy(dp, v, pixel_bytes); |
destinyXfate | 2:0e2ef1edf01b | 1987 | * dp -= pixel_bytes; |
destinyXfate | 2:0e2ef1edf01b | 1988 | * } |
destinyXfate | 2:0e2ef1edf01b | 1989 | * sptr -= pixel_bytes; |
destinyXfate | 2:0e2ef1edf01b | 1990 | * |
destinyXfate | 2:0e2ef1edf01b | 1991 | * Replacement code is in the next three lines: |
destinyXfate | 2:0e2ef1edf01b | 1992 | */ |
destinyXfate | 2:0e2ef1edf01b | 1993 | |
destinyXfate | 2:0e2ef1edf01b | 1994 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 1995 | { |
destinyXfate | 2:0e2ef1edf01b | 1996 | *dp-- = *sptr; |
destinyXfate | 2:0e2ef1edf01b | 1997 | } |
destinyXfate | 2:0e2ef1edf01b | 1998 | --sptr; |
destinyXfate | 2:0e2ef1edf01b | 1999 | } |
destinyXfate | 2:0e2ef1edf01b | 2000 | } |
destinyXfate | 2:0e2ef1edf01b | 2001 | else if (((pass == 2) || (pass == 3)) && width) |
destinyXfate | 2:0e2ef1edf01b | 2002 | { |
destinyXfate | 2:0e2ef1edf01b | 2003 | int width_mmx = ((width >> 2) << 2); |
destinyXfate | 2:0e2ef1edf01b | 2004 | width -= width_mmx; // 0-3 pixels => 0-3 bytes |
destinyXfate | 2:0e2ef1edf01b | 2005 | if (width_mmx) |
destinyXfate | 2:0e2ef1edf01b | 2006 | { |
destinyXfate | 2:0e2ef1edf01b | 2007 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 2008 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 2009 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 2010 | |
destinyXfate | 2:0e2ef1edf01b | 2011 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2012 | "subl $3, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2013 | "subl $15, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2014 | |
destinyXfate | 2:0e2ef1edf01b | 2015 | ".loop1_pass2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2016 | "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2017 | "punpcklbw %%mm0, %%mm0 \n\t" // 3 3 2 2 1 1 0 0 |
destinyXfate | 2:0e2ef1edf01b | 2018 | "movq %%mm0, %%mm1 \n\t" // 3 3 2 2 1 1 0 0 |
destinyXfate | 2:0e2ef1edf01b | 2019 | "punpcklwd %%mm0, %%mm0 \n\t" // 1 1 1 1 0 0 0 0 |
destinyXfate | 2:0e2ef1edf01b | 2020 | "punpckhwd %%mm1, %%mm1 \n\t" // 3 3 3 3 2 2 2 2 |
destinyXfate | 2:0e2ef1edf01b | 2021 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2022 | "subl $4, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2023 | "movq %%mm1, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2024 | "subl $16, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2025 | "subl $4, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2026 | "jnz .loop1_pass2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2027 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 2028 | |
destinyXfate | 2:0e2ef1edf01b | 2029 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 2030 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 2031 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2032 | |
destinyXfate | 2:0e2ef1edf01b | 2033 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 2034 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 2035 | "0" (width_mmx) // ecx |
destinyXfate | 2:0e2ef1edf01b | 2036 | |
destinyXfate | 2:0e2ef1edf01b | 2037 | #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 2038 | : "%mm0", "%mm1" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2039 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2040 | ); |
destinyXfate | 2:0e2ef1edf01b | 2041 | } |
destinyXfate | 2:0e2ef1edf01b | 2042 | |
destinyXfate | 2:0e2ef1edf01b | 2043 | sptr -= width_mmx; |
destinyXfate | 2:0e2ef1edf01b | 2044 | dp -= width_mmx*4; |
destinyXfate | 2:0e2ef1edf01b | 2045 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2046 | { |
destinyXfate | 2:0e2ef1edf01b | 2047 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2048 | |
destinyXfate | 2:0e2ef1edf01b | 2049 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2050 | { |
destinyXfate | 2:0e2ef1edf01b | 2051 | *dp-- = *sptr; |
destinyXfate | 2:0e2ef1edf01b | 2052 | } |
destinyXfate | 2:0e2ef1edf01b | 2053 | --sptr; |
destinyXfate | 2:0e2ef1edf01b | 2054 | } |
destinyXfate | 2:0e2ef1edf01b | 2055 | } |
destinyXfate | 2:0e2ef1edf01b | 2056 | else if (width) /* && ((pass == 4) || (pass == 5)) */ |
destinyXfate | 2:0e2ef1edf01b | 2057 | { |
destinyXfate | 2:0e2ef1edf01b | 2058 | int width_mmx = ((width >> 3) << 3); |
destinyXfate | 2:0e2ef1edf01b | 2059 | width -= width_mmx; // 0-3 pixels => 0-3 bytes |
destinyXfate | 2:0e2ef1edf01b | 2060 | if (width_mmx) |
destinyXfate | 2:0e2ef1edf01b | 2061 | { |
destinyXfate | 2:0e2ef1edf01b | 2062 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 2063 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 2064 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 2065 | |
destinyXfate | 2:0e2ef1edf01b | 2066 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2067 | "subl $7, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2068 | "subl $15, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2069 | |
destinyXfate | 2:0e2ef1edf01b | 2070 | ".loop1_pass4: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2071 | "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2072 | "movq %%mm0, %%mm1 \n\t" // 7 6 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2073 | "punpcklbw %%mm0, %%mm0 \n\t" // 3 3 2 2 1 1 0 0 |
destinyXfate | 2:0e2ef1edf01b | 2074 | "punpckhbw %%mm1, %%mm1 \n\t" // 7 7 6 6 5 5 4 4 |
destinyXfate | 2:0e2ef1edf01b | 2075 | "movq %%mm1, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2076 | "subl $8, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2077 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2078 | "subl $16, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2079 | "subl $8, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2080 | "jnz .loop1_pass4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2081 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 2082 | |
destinyXfate | 2:0e2ef1edf01b | 2083 | : "=c" (dummy_value_c), // output regs (none) |
destinyXfate | 2:0e2ef1edf01b | 2084 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 2085 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2086 | |
destinyXfate | 2:0e2ef1edf01b | 2087 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 2088 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 2089 | "0" (width_mmx) // ecx |
destinyXfate | 2:0e2ef1edf01b | 2090 | |
destinyXfate | 2:0e2ef1edf01b | 2091 | #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 2092 | : "%mm0", "%mm1" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2093 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2094 | ); |
destinyXfate | 2:0e2ef1edf01b | 2095 | } |
destinyXfate | 2:0e2ef1edf01b | 2096 | |
destinyXfate | 2:0e2ef1edf01b | 2097 | sptr -= width_mmx; |
destinyXfate | 2:0e2ef1edf01b | 2098 | dp -= width_mmx*2; |
destinyXfate | 2:0e2ef1edf01b | 2099 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2100 | { |
destinyXfate | 2:0e2ef1edf01b | 2101 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2102 | |
destinyXfate | 2:0e2ef1edf01b | 2103 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2104 | { |
destinyXfate | 2:0e2ef1edf01b | 2105 | *dp-- = *sptr; |
destinyXfate | 2:0e2ef1edf01b | 2106 | } |
destinyXfate | 2:0e2ef1edf01b | 2107 | --sptr; |
destinyXfate | 2:0e2ef1edf01b | 2108 | } |
destinyXfate | 2:0e2ef1edf01b | 2109 | } |
destinyXfate | 2:0e2ef1edf01b | 2110 | } /* end of pixel_bytes == 1 */ |
destinyXfate | 2:0e2ef1edf01b | 2111 | |
destinyXfate | 2:0e2ef1edf01b | 2112 | //-------------------------------------------------------------- |
destinyXfate | 2:0e2ef1edf01b | 2113 | else if (pixel_bytes == 2) |
destinyXfate | 2:0e2ef1edf01b | 2114 | { |
destinyXfate | 2:0e2ef1edf01b | 2115 | if (((pass == 0) || (pass == 1)) && width) |
destinyXfate | 2:0e2ef1edf01b | 2116 | { |
destinyXfate | 2:0e2ef1edf01b | 2117 | int width_mmx = ((width >> 1) << 1); |
destinyXfate | 2:0e2ef1edf01b | 2118 | width -= width_mmx; // 0,1 pixels => 0,2 bytes |
destinyXfate | 2:0e2ef1edf01b | 2119 | if (width_mmx) |
destinyXfate | 2:0e2ef1edf01b | 2120 | { |
destinyXfate | 2:0e2ef1edf01b | 2121 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 2122 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 2123 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 2124 | |
destinyXfate | 2:0e2ef1edf01b | 2125 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2126 | "subl $2, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2127 | "subl $30, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2128 | |
destinyXfate | 2:0e2ef1edf01b | 2129 | ".loop2_pass0: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2130 | "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2131 | "punpcklwd %%mm0, %%mm0 \n\t" // 3 2 3 2 1 0 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2132 | "movq %%mm0, %%mm1 \n\t" // 3 2 3 2 1 0 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2133 | "punpckldq %%mm0, %%mm0 \n\t" // 1 0 1 0 1 0 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2134 | "punpckhdq %%mm1, %%mm1 \n\t" // 3 2 3 2 3 2 3 2 |
destinyXfate | 2:0e2ef1edf01b | 2135 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2136 | "movq %%mm0, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2137 | "movq %%mm1, 16(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2138 | "subl $4, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2139 | "movq %%mm1, 24(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2140 | "subl $32, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2141 | "subl $2, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2142 | "jnz .loop2_pass0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2143 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 2144 | |
destinyXfate | 2:0e2ef1edf01b | 2145 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 2146 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 2147 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2148 | |
destinyXfate | 2:0e2ef1edf01b | 2149 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 2150 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 2151 | "0" (width_mmx) // ecx |
destinyXfate | 2:0e2ef1edf01b | 2152 | |
destinyXfate | 2:0e2ef1edf01b | 2153 | #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 2154 | : "%mm0", "%mm1" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2155 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2156 | ); |
destinyXfate | 2:0e2ef1edf01b | 2157 | } |
destinyXfate | 2:0e2ef1edf01b | 2158 | |
destinyXfate | 2:0e2ef1edf01b | 2159 | sptr -= (width_mmx*2 - 2); // sign fixed |
destinyXfate | 2:0e2ef1edf01b | 2160 | dp -= (width_mmx*16 - 2); // sign fixed |
destinyXfate | 2:0e2ef1edf01b | 2161 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2162 | { |
destinyXfate | 2:0e2ef1edf01b | 2163 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2164 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2165 | sptr -= 2; |
destinyXfate | 2:0e2ef1edf01b | 2166 | png_memcpy(v, sptr, 2); |
destinyXfate | 2:0e2ef1edf01b | 2167 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2168 | { |
destinyXfate | 2:0e2ef1edf01b | 2169 | dp -= 2; |
destinyXfate | 2:0e2ef1edf01b | 2170 | png_memcpy(dp, v, 2); |
destinyXfate | 2:0e2ef1edf01b | 2171 | } |
destinyXfate | 2:0e2ef1edf01b | 2172 | } |
destinyXfate | 2:0e2ef1edf01b | 2173 | } |
destinyXfate | 2:0e2ef1edf01b | 2174 | else if (((pass == 2) || (pass == 3)) && width) |
destinyXfate | 2:0e2ef1edf01b | 2175 | { |
destinyXfate | 2:0e2ef1edf01b | 2176 | int width_mmx = ((width >> 1) << 1) ; |
destinyXfate | 2:0e2ef1edf01b | 2177 | width -= width_mmx; // 0,1 pixels => 0,2 bytes |
destinyXfate | 2:0e2ef1edf01b | 2178 | if (width_mmx) |
destinyXfate | 2:0e2ef1edf01b | 2179 | { |
destinyXfate | 2:0e2ef1edf01b | 2180 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 2181 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 2182 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 2183 | |
destinyXfate | 2:0e2ef1edf01b | 2184 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2185 | "subl $2, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2186 | "subl $14, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2187 | |
destinyXfate | 2:0e2ef1edf01b | 2188 | ".loop2_pass2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2189 | "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2190 | "punpcklwd %%mm0, %%mm0 \n\t" // 3 2 3 2 1 0 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2191 | "movq %%mm0, %%mm1 \n\t" // 3 2 3 2 1 0 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2192 | "punpckldq %%mm0, %%mm0 \n\t" // 1 0 1 0 1 0 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2193 | "punpckhdq %%mm1, %%mm1 \n\t" // 3 2 3 2 3 2 3 2 |
destinyXfate | 2:0e2ef1edf01b | 2194 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2195 | "subl $4, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2196 | "movq %%mm1, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2197 | "subl $16, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2198 | "subl $2, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2199 | "jnz .loop2_pass2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2200 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 2201 | |
destinyXfate | 2:0e2ef1edf01b | 2202 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 2203 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 2204 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2205 | |
destinyXfate | 2:0e2ef1edf01b | 2206 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 2207 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 2208 | "0" (width_mmx) // ecx |
destinyXfate | 2:0e2ef1edf01b | 2209 | |
destinyXfate | 2:0e2ef1edf01b | 2210 | #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 2211 | : "%mm0", "%mm1" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2212 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2213 | ); |
destinyXfate | 2:0e2ef1edf01b | 2214 | } |
destinyXfate | 2:0e2ef1edf01b | 2215 | |
destinyXfate | 2:0e2ef1edf01b | 2216 | sptr -= (width_mmx*2 - 2); // sign fixed |
destinyXfate | 2:0e2ef1edf01b | 2217 | dp -= (width_mmx*8 - 2); // sign fixed |
destinyXfate | 2:0e2ef1edf01b | 2218 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2219 | { |
destinyXfate | 2:0e2ef1edf01b | 2220 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2221 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2222 | sptr -= 2; |
destinyXfate | 2:0e2ef1edf01b | 2223 | png_memcpy(v, sptr, 2); |
destinyXfate | 2:0e2ef1edf01b | 2224 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2225 | { |
destinyXfate | 2:0e2ef1edf01b | 2226 | dp -= 2; |
destinyXfate | 2:0e2ef1edf01b | 2227 | png_memcpy(dp, v, 2); |
destinyXfate | 2:0e2ef1edf01b | 2228 | } |
destinyXfate | 2:0e2ef1edf01b | 2229 | } |
destinyXfate | 2:0e2ef1edf01b | 2230 | } |
destinyXfate | 2:0e2ef1edf01b | 2231 | else if (width) // pass == 4 or 5 |
destinyXfate | 2:0e2ef1edf01b | 2232 | { |
destinyXfate | 2:0e2ef1edf01b | 2233 | int width_mmx = ((width >> 1) << 1) ; |
destinyXfate | 2:0e2ef1edf01b | 2234 | width -= width_mmx; // 0,1 pixels => 0,2 bytes |
destinyXfate | 2:0e2ef1edf01b | 2235 | if (width_mmx) |
destinyXfate | 2:0e2ef1edf01b | 2236 | { |
destinyXfate | 2:0e2ef1edf01b | 2237 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 2238 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 2239 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 2240 | |
destinyXfate | 2:0e2ef1edf01b | 2241 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2242 | "subl $2, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2243 | "subl $6, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2244 | |
destinyXfate | 2:0e2ef1edf01b | 2245 | ".loop2_pass4: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2246 | "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2247 | "punpcklwd %%mm0, %%mm0 \n\t" // 3 2 3 2 1 0 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2248 | "subl $4, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2249 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2250 | "subl $8, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2251 | "subl $2, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2252 | "jnz .loop2_pass4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2253 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 2254 | |
destinyXfate | 2:0e2ef1edf01b | 2255 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 2256 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 2257 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2258 | |
destinyXfate | 2:0e2ef1edf01b | 2259 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 2260 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 2261 | "0" (width_mmx) // ecx |
destinyXfate | 2:0e2ef1edf01b | 2262 | |
destinyXfate | 2:0e2ef1edf01b | 2263 | #if 0 /* %mm0 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 2264 | : "%mm0" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2265 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2266 | ); |
destinyXfate | 2:0e2ef1edf01b | 2267 | } |
destinyXfate | 2:0e2ef1edf01b | 2268 | |
destinyXfate | 2:0e2ef1edf01b | 2269 | sptr -= (width_mmx*2 - 2); // sign fixed |
destinyXfate | 2:0e2ef1edf01b | 2270 | dp -= (width_mmx*4 - 2); // sign fixed |
destinyXfate | 2:0e2ef1edf01b | 2271 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2272 | { |
destinyXfate | 2:0e2ef1edf01b | 2273 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2274 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2275 | sptr -= 2; |
destinyXfate | 2:0e2ef1edf01b | 2276 | png_memcpy(v, sptr, 2); |
destinyXfate | 2:0e2ef1edf01b | 2277 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2278 | { |
destinyXfate | 2:0e2ef1edf01b | 2279 | dp -= 2; |
destinyXfate | 2:0e2ef1edf01b | 2280 | png_memcpy(dp, v, 2); |
destinyXfate | 2:0e2ef1edf01b | 2281 | } |
destinyXfate | 2:0e2ef1edf01b | 2282 | } |
destinyXfate | 2:0e2ef1edf01b | 2283 | } |
destinyXfate | 2:0e2ef1edf01b | 2284 | } /* end of pixel_bytes == 2 */ |
destinyXfate | 2:0e2ef1edf01b | 2285 | |
destinyXfate | 2:0e2ef1edf01b | 2286 | //-------------------------------------------------------------- |
destinyXfate | 2:0e2ef1edf01b | 2287 | else if (pixel_bytes == 4) |
destinyXfate | 2:0e2ef1edf01b | 2288 | { |
destinyXfate | 2:0e2ef1edf01b | 2289 | if (((pass == 0) || (pass == 1)) && width) |
destinyXfate | 2:0e2ef1edf01b | 2290 | { |
destinyXfate | 2:0e2ef1edf01b | 2291 | int width_mmx = ((width >> 1) << 1); |
destinyXfate | 2:0e2ef1edf01b | 2292 | width -= width_mmx; // 0,1 pixels => 0,4 bytes |
destinyXfate | 2:0e2ef1edf01b | 2293 | if (width_mmx) |
destinyXfate | 2:0e2ef1edf01b | 2294 | { |
destinyXfate | 2:0e2ef1edf01b | 2295 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 2296 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 2297 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 2298 | |
destinyXfate | 2:0e2ef1edf01b | 2299 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2300 | "subl $4, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2301 | "subl $60, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2302 | |
destinyXfate | 2:0e2ef1edf01b | 2303 | ".loop4_pass0: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2304 | "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2305 | "movq %%mm0, %%mm1 \n\t" // 7 6 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2306 | "punpckldq %%mm0, %%mm0 \n\t" // 3 2 1 0 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2307 | "punpckhdq %%mm1, %%mm1 \n\t" // 7 6 5 4 7 6 5 4 |
destinyXfate | 2:0e2ef1edf01b | 2308 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2309 | "movq %%mm0, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2310 | "movq %%mm0, 16(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2311 | "movq %%mm0, 24(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2312 | "movq %%mm1, 32(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2313 | "movq %%mm1, 40(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2314 | "movq %%mm1, 48(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2315 | "subl $8, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2316 | "movq %%mm1, 56(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2317 | "subl $64, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2318 | "subl $2, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2319 | "jnz .loop4_pass0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2320 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 2321 | |
destinyXfate | 2:0e2ef1edf01b | 2322 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 2323 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 2324 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2325 | |
destinyXfate | 2:0e2ef1edf01b | 2326 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 2327 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 2328 | "0" (width_mmx) // ecx |
destinyXfate | 2:0e2ef1edf01b | 2329 | |
destinyXfate | 2:0e2ef1edf01b | 2330 | #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 2331 | : "%mm0", "%mm1" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2332 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2333 | ); |
destinyXfate | 2:0e2ef1edf01b | 2334 | } |
destinyXfate | 2:0e2ef1edf01b | 2335 | |
destinyXfate | 2:0e2ef1edf01b | 2336 | sptr -= (width_mmx*4 - 4); // sign fixed |
destinyXfate | 2:0e2ef1edf01b | 2337 | dp -= (width_mmx*32 - 4); // sign fixed |
destinyXfate | 2:0e2ef1edf01b | 2338 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2339 | { |
destinyXfate | 2:0e2ef1edf01b | 2340 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2341 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2342 | sptr -= 4; |
destinyXfate | 2:0e2ef1edf01b | 2343 | png_memcpy(v, sptr, 4); |
destinyXfate | 2:0e2ef1edf01b | 2344 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2345 | { |
destinyXfate | 2:0e2ef1edf01b | 2346 | dp -= 4; |
destinyXfate | 2:0e2ef1edf01b | 2347 | png_memcpy(dp, v, 4); |
destinyXfate | 2:0e2ef1edf01b | 2348 | } |
destinyXfate | 2:0e2ef1edf01b | 2349 | } |
destinyXfate | 2:0e2ef1edf01b | 2350 | } |
destinyXfate | 2:0e2ef1edf01b | 2351 | else if (((pass == 2) || (pass == 3)) && width) |
destinyXfate | 2:0e2ef1edf01b | 2352 | { |
destinyXfate | 2:0e2ef1edf01b | 2353 | int width_mmx = ((width >> 1) << 1); |
destinyXfate | 2:0e2ef1edf01b | 2354 | width -= width_mmx; // 0,1 pixels => 0,4 bytes |
destinyXfate | 2:0e2ef1edf01b | 2355 | if (width_mmx) |
destinyXfate | 2:0e2ef1edf01b | 2356 | { |
destinyXfate | 2:0e2ef1edf01b | 2357 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 2358 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 2359 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 2360 | |
destinyXfate | 2:0e2ef1edf01b | 2361 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2362 | "subl $4, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2363 | "subl $28, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2364 | |
destinyXfate | 2:0e2ef1edf01b | 2365 | ".loop4_pass2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2366 | "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2367 | "movq %%mm0, %%mm1 \n\t" // 7 6 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2368 | "punpckldq %%mm0, %%mm0 \n\t" // 3 2 1 0 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2369 | "punpckhdq %%mm1, %%mm1 \n\t" // 7 6 5 4 7 6 5 4 |
destinyXfate | 2:0e2ef1edf01b | 2370 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2371 | "movq %%mm0, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2372 | "movq %%mm1, 16(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2373 | "movq %%mm1, 24(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2374 | "subl $8, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2375 | "subl $32, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2376 | "subl $2, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2377 | "jnz .loop4_pass2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2378 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 2379 | |
destinyXfate | 2:0e2ef1edf01b | 2380 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 2381 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 2382 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2383 | |
destinyXfate | 2:0e2ef1edf01b | 2384 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 2385 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 2386 | "0" (width_mmx) // ecx |
destinyXfate | 2:0e2ef1edf01b | 2387 | |
destinyXfate | 2:0e2ef1edf01b | 2388 | #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 2389 | : "%mm0", "%mm1" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2390 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2391 | ); |
destinyXfate | 2:0e2ef1edf01b | 2392 | } |
destinyXfate | 2:0e2ef1edf01b | 2393 | |
destinyXfate | 2:0e2ef1edf01b | 2394 | sptr -= (width_mmx*4 - 4); // sign fixed |
destinyXfate | 2:0e2ef1edf01b | 2395 | dp -= (width_mmx*16 - 4); // sign fixed |
destinyXfate | 2:0e2ef1edf01b | 2396 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2397 | { |
destinyXfate | 2:0e2ef1edf01b | 2398 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2399 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2400 | sptr -= 4; |
destinyXfate | 2:0e2ef1edf01b | 2401 | png_memcpy(v, sptr, 4); |
destinyXfate | 2:0e2ef1edf01b | 2402 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2403 | { |
destinyXfate | 2:0e2ef1edf01b | 2404 | dp -= 4; |
destinyXfate | 2:0e2ef1edf01b | 2405 | png_memcpy(dp, v, 4); |
destinyXfate | 2:0e2ef1edf01b | 2406 | } |
destinyXfate | 2:0e2ef1edf01b | 2407 | } |
destinyXfate | 2:0e2ef1edf01b | 2408 | } |
destinyXfate | 2:0e2ef1edf01b | 2409 | else if (width) // pass == 4 or 5 |
destinyXfate | 2:0e2ef1edf01b | 2410 | { |
destinyXfate | 2:0e2ef1edf01b | 2411 | int width_mmx = ((width >> 1) << 1) ; |
destinyXfate | 2:0e2ef1edf01b | 2412 | width -= width_mmx; // 0,1 pixels => 0,4 bytes |
destinyXfate | 2:0e2ef1edf01b | 2413 | if (width_mmx) |
destinyXfate | 2:0e2ef1edf01b | 2414 | { |
destinyXfate | 2:0e2ef1edf01b | 2415 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 2416 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 2417 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 2418 | |
destinyXfate | 2:0e2ef1edf01b | 2419 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2420 | "subl $4, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2421 | "subl $12, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2422 | |
destinyXfate | 2:0e2ef1edf01b | 2423 | ".loop4_pass4: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2424 | "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2425 | "movq %%mm0, %%mm1 \n\t" // 7 6 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2426 | "punpckldq %%mm0, %%mm0 \n\t" // 3 2 1 0 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2427 | "punpckhdq %%mm1, %%mm1 \n\t" // 7 6 5 4 7 6 5 4 |
destinyXfate | 2:0e2ef1edf01b | 2428 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2429 | "subl $8, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2430 | "movq %%mm1, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2431 | "subl $16, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2432 | "subl $2, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2433 | "jnz .loop4_pass4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2434 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 2435 | |
destinyXfate | 2:0e2ef1edf01b | 2436 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 2437 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 2438 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2439 | |
destinyXfate | 2:0e2ef1edf01b | 2440 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 2441 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 2442 | "0" (width_mmx) // ecx |
destinyXfate | 2:0e2ef1edf01b | 2443 | |
destinyXfate | 2:0e2ef1edf01b | 2444 | #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 2445 | : "%mm0", "%mm1" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2446 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2447 | ); |
destinyXfate | 2:0e2ef1edf01b | 2448 | } |
destinyXfate | 2:0e2ef1edf01b | 2449 | |
destinyXfate | 2:0e2ef1edf01b | 2450 | sptr -= (width_mmx*4 - 4); // sign fixed |
destinyXfate | 2:0e2ef1edf01b | 2451 | dp -= (width_mmx*8 - 4); // sign fixed |
destinyXfate | 2:0e2ef1edf01b | 2452 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2453 | { |
destinyXfate | 2:0e2ef1edf01b | 2454 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2455 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2456 | sptr -= 4; |
destinyXfate | 2:0e2ef1edf01b | 2457 | png_memcpy(v, sptr, 4); |
destinyXfate | 2:0e2ef1edf01b | 2458 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2459 | { |
destinyXfate | 2:0e2ef1edf01b | 2460 | dp -= 4; |
destinyXfate | 2:0e2ef1edf01b | 2461 | png_memcpy(dp, v, 4); |
destinyXfate | 2:0e2ef1edf01b | 2462 | } |
destinyXfate | 2:0e2ef1edf01b | 2463 | } |
destinyXfate | 2:0e2ef1edf01b | 2464 | } |
destinyXfate | 2:0e2ef1edf01b | 2465 | } /* end of pixel_bytes == 4 */ |
destinyXfate | 2:0e2ef1edf01b | 2466 | |
destinyXfate | 2:0e2ef1edf01b | 2467 | //-------------------------------------------------------------- |
destinyXfate | 2:0e2ef1edf01b | 2468 | else if (pixel_bytes == 8) |
destinyXfate | 2:0e2ef1edf01b | 2469 | { |
destinyXfate | 2:0e2ef1edf01b | 2470 | // GRR TEST: should work, but needs testing (special 64-bit version of rpng2?) |
destinyXfate | 2:0e2ef1edf01b | 2471 | // GRR NOTE: no need to combine passes here! |
destinyXfate | 2:0e2ef1edf01b | 2472 | if (((pass == 0) || (pass == 1)) && width) |
destinyXfate | 2:0e2ef1edf01b | 2473 | { |
destinyXfate | 2:0e2ef1edf01b | 2474 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 2475 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 2476 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 2477 | |
destinyXfate | 2:0e2ef1edf01b | 2478 | // source is 8-byte RRGGBBAA |
destinyXfate | 2:0e2ef1edf01b | 2479 | // dest is 64-byte RRGGBBAA RRGGBBAA RRGGBBAA RRGGBBAA ... |
destinyXfate | 2:0e2ef1edf01b | 2480 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2481 | "subl $56, %%edi \n\t" // start of last block |
destinyXfate | 2:0e2ef1edf01b | 2482 | |
destinyXfate | 2:0e2ef1edf01b | 2483 | ".loop8_pass0: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2484 | "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2485 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2486 | "movq %%mm0, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2487 | "movq %%mm0, 16(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2488 | "movq %%mm0, 24(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2489 | "movq %%mm0, 32(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2490 | "movq %%mm0, 40(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2491 | "movq %%mm0, 48(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2492 | "subl $8, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2493 | "movq %%mm0, 56(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2494 | "subl $64, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2495 | "decl %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2496 | "jnz .loop8_pass0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2497 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 2498 | |
destinyXfate | 2:0e2ef1edf01b | 2499 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 2500 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 2501 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2502 | |
destinyXfate | 2:0e2ef1edf01b | 2503 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 2504 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 2505 | "0" (width) // ecx |
destinyXfate | 2:0e2ef1edf01b | 2506 | |
destinyXfate | 2:0e2ef1edf01b | 2507 | #if 0 /* %mm0 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 2508 | : "%mm0" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2509 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2510 | ); |
destinyXfate | 2:0e2ef1edf01b | 2511 | } |
destinyXfate | 2:0e2ef1edf01b | 2512 | else if (((pass == 2) || (pass == 3)) && width) |
destinyXfate | 2:0e2ef1edf01b | 2513 | { |
destinyXfate | 2:0e2ef1edf01b | 2514 | // source is 8-byte RRGGBBAA |
destinyXfate | 2:0e2ef1edf01b | 2515 | // dest is 32-byte RRGGBBAA RRGGBBAA RRGGBBAA RRGGBBAA |
destinyXfate | 2:0e2ef1edf01b | 2516 | // (recall that expansion is _in place_: sptr and dp |
destinyXfate | 2:0e2ef1edf01b | 2517 | // both point at locations within same row buffer) |
destinyXfate | 2:0e2ef1edf01b | 2518 | { |
destinyXfate | 2:0e2ef1edf01b | 2519 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 2520 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 2521 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 2522 | |
destinyXfate | 2:0e2ef1edf01b | 2523 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2524 | "subl $24, %%edi \n\t" // start of last block |
destinyXfate | 2:0e2ef1edf01b | 2525 | |
destinyXfate | 2:0e2ef1edf01b | 2526 | ".loop8_pass2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2527 | "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2528 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2529 | "movq %%mm0, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2530 | "movq %%mm0, 16(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2531 | "subl $8, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2532 | "movq %%mm0, 24(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2533 | "subl $32, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2534 | "decl %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2535 | "jnz .loop8_pass2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2536 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 2537 | |
destinyXfate | 2:0e2ef1edf01b | 2538 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 2539 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 2540 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2541 | |
destinyXfate | 2:0e2ef1edf01b | 2542 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 2543 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 2544 | "0" (width) // ecx |
destinyXfate | 2:0e2ef1edf01b | 2545 | |
destinyXfate | 2:0e2ef1edf01b | 2546 | #if 0 /* %mm0 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 2547 | : "%mm0" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2548 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2549 | ); |
destinyXfate | 2:0e2ef1edf01b | 2550 | } |
destinyXfate | 2:0e2ef1edf01b | 2551 | } |
destinyXfate | 2:0e2ef1edf01b | 2552 | else if (width) // pass == 4 or 5 |
destinyXfate | 2:0e2ef1edf01b | 2553 | { |
destinyXfate | 2:0e2ef1edf01b | 2554 | // source is 8-byte RRGGBBAA |
destinyXfate | 2:0e2ef1edf01b | 2555 | // dest is 16-byte RRGGBBAA RRGGBBAA |
destinyXfate | 2:0e2ef1edf01b | 2556 | { |
destinyXfate | 2:0e2ef1edf01b | 2557 | int dummy_value_c; // fix 'forbidden register spilled' |
destinyXfate | 2:0e2ef1edf01b | 2558 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 2559 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 2560 | |
destinyXfate | 2:0e2ef1edf01b | 2561 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2562 | "subl $8, %%edi \n\t" // start of last block |
destinyXfate | 2:0e2ef1edf01b | 2563 | |
destinyXfate | 2:0e2ef1edf01b | 2564 | ".loop8_pass4: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2565 | "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 |
destinyXfate | 2:0e2ef1edf01b | 2566 | "movq %%mm0, (%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2567 | "subl $8, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2568 | "movq %%mm0, 8(%%edi) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2569 | "subl $16, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2570 | "decl %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2571 | "jnz .loop8_pass4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2572 | "EMMS \n\t" // DONE |
destinyXfate | 2:0e2ef1edf01b | 2573 | |
destinyXfate | 2:0e2ef1edf01b | 2574 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 2575 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 2576 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2577 | |
destinyXfate | 2:0e2ef1edf01b | 2578 | : "1" (sptr), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 2579 | "2" (dp), // edi |
destinyXfate | 2:0e2ef1edf01b | 2580 | "0" (width) // ecx |
destinyXfate | 2:0e2ef1edf01b | 2581 | |
destinyXfate | 2:0e2ef1edf01b | 2582 | #if 0 /* %mm0 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 2583 | : "%mm0" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2584 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2585 | ); |
destinyXfate | 2:0e2ef1edf01b | 2586 | } |
destinyXfate | 2:0e2ef1edf01b | 2587 | } |
destinyXfate | 2:0e2ef1edf01b | 2588 | |
destinyXfate | 2:0e2ef1edf01b | 2589 | } /* end of pixel_bytes == 8 */ |
destinyXfate | 2:0e2ef1edf01b | 2590 | |
destinyXfate | 2:0e2ef1edf01b | 2591 | //-------------------------------------------------------------- |
destinyXfate | 2:0e2ef1edf01b | 2592 | else if (pixel_bytes == 6) |
destinyXfate | 2:0e2ef1edf01b | 2593 | { |
destinyXfate | 2:0e2ef1edf01b | 2594 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2595 | { |
destinyXfate | 2:0e2ef1edf01b | 2596 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2597 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2598 | png_memcpy(v, sptr, 6); |
destinyXfate | 2:0e2ef1edf01b | 2599 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2600 | { |
destinyXfate | 2:0e2ef1edf01b | 2601 | png_memcpy(dp, v, 6); |
destinyXfate | 2:0e2ef1edf01b | 2602 | dp -= 6; |
destinyXfate | 2:0e2ef1edf01b | 2603 | } |
destinyXfate | 2:0e2ef1edf01b | 2604 | sptr -= 6; |
destinyXfate | 2:0e2ef1edf01b | 2605 | } |
destinyXfate | 2:0e2ef1edf01b | 2606 | } /* end of pixel_bytes == 6 */ |
destinyXfate | 2:0e2ef1edf01b | 2607 | |
destinyXfate | 2:0e2ef1edf01b | 2608 | //-------------------------------------------------------------- |
destinyXfate | 2:0e2ef1edf01b | 2609 | else |
destinyXfate | 2:0e2ef1edf01b | 2610 | { |
destinyXfate | 2:0e2ef1edf01b | 2611 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2612 | { |
destinyXfate | 2:0e2ef1edf01b | 2613 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2614 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2615 | png_memcpy(v, sptr, pixel_bytes); |
destinyXfate | 2:0e2ef1edf01b | 2616 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2617 | { |
destinyXfate | 2:0e2ef1edf01b | 2618 | png_memcpy(dp, v, pixel_bytes); |
destinyXfate | 2:0e2ef1edf01b | 2619 | dp -= pixel_bytes; |
destinyXfate | 2:0e2ef1edf01b | 2620 | } |
destinyXfate | 2:0e2ef1edf01b | 2621 | sptr-= pixel_bytes; |
destinyXfate | 2:0e2ef1edf01b | 2622 | } |
destinyXfate | 2:0e2ef1edf01b | 2623 | } |
destinyXfate | 2:0e2ef1edf01b | 2624 | } // end of _mmx_supported ======================================== |
destinyXfate | 2:0e2ef1edf01b | 2625 | |
destinyXfate | 2:0e2ef1edf01b | 2626 | else /* MMX not supported: use modified C code - takes advantage |
destinyXfate | 2:0e2ef1edf01b | 2627 | * of inlining of png_memcpy for a constant */ |
destinyXfate | 2:0e2ef1edf01b | 2628 | /* GRR 19991007: does it? or should pixel_bytes in each |
destinyXfate | 2:0e2ef1edf01b | 2629 | * block be replaced with immediate value (e.g., 1)? */ |
destinyXfate | 2:0e2ef1edf01b | 2630 | /* GRR 19991017: replaced with constants in each case */ |
destinyXfate | 2:0e2ef1edf01b | 2631 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 2632 | { |
destinyXfate | 2:0e2ef1edf01b | 2633 | if (pixel_bytes == 1) |
destinyXfate | 2:0e2ef1edf01b | 2634 | { |
destinyXfate | 2:0e2ef1edf01b | 2635 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2636 | { |
destinyXfate | 2:0e2ef1edf01b | 2637 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2638 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2639 | { |
destinyXfate | 2:0e2ef1edf01b | 2640 | *dp-- = *sptr; |
destinyXfate | 2:0e2ef1edf01b | 2641 | } |
destinyXfate | 2:0e2ef1edf01b | 2642 | --sptr; |
destinyXfate | 2:0e2ef1edf01b | 2643 | } |
destinyXfate | 2:0e2ef1edf01b | 2644 | } |
destinyXfate | 2:0e2ef1edf01b | 2645 | else if (pixel_bytes == 3) |
destinyXfate | 2:0e2ef1edf01b | 2646 | { |
destinyXfate | 2:0e2ef1edf01b | 2647 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2648 | { |
destinyXfate | 2:0e2ef1edf01b | 2649 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2650 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2651 | png_memcpy(v, sptr, 3); |
destinyXfate | 2:0e2ef1edf01b | 2652 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2653 | { |
destinyXfate | 2:0e2ef1edf01b | 2654 | png_memcpy(dp, v, 3); |
destinyXfate | 2:0e2ef1edf01b | 2655 | dp -= 3; |
destinyXfate | 2:0e2ef1edf01b | 2656 | } |
destinyXfate | 2:0e2ef1edf01b | 2657 | sptr -= 3; |
destinyXfate | 2:0e2ef1edf01b | 2658 | } |
destinyXfate | 2:0e2ef1edf01b | 2659 | } |
destinyXfate | 2:0e2ef1edf01b | 2660 | else if (pixel_bytes == 2) |
destinyXfate | 2:0e2ef1edf01b | 2661 | { |
destinyXfate | 2:0e2ef1edf01b | 2662 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2663 | { |
destinyXfate | 2:0e2ef1edf01b | 2664 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2665 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2666 | png_memcpy(v, sptr, 2); |
destinyXfate | 2:0e2ef1edf01b | 2667 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2668 | { |
destinyXfate | 2:0e2ef1edf01b | 2669 | png_memcpy(dp, v, 2); |
destinyXfate | 2:0e2ef1edf01b | 2670 | dp -= 2; |
destinyXfate | 2:0e2ef1edf01b | 2671 | } |
destinyXfate | 2:0e2ef1edf01b | 2672 | sptr -= 2; |
destinyXfate | 2:0e2ef1edf01b | 2673 | } |
destinyXfate | 2:0e2ef1edf01b | 2674 | } |
destinyXfate | 2:0e2ef1edf01b | 2675 | else if (pixel_bytes == 4) |
destinyXfate | 2:0e2ef1edf01b | 2676 | { |
destinyXfate | 2:0e2ef1edf01b | 2677 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2678 | { |
destinyXfate | 2:0e2ef1edf01b | 2679 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2680 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2681 | png_memcpy(v, sptr, 4); |
destinyXfate | 2:0e2ef1edf01b | 2682 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2683 | { |
destinyXfate | 2:0e2ef1edf01b | 2684 | #ifdef PNG_DEBUG |
destinyXfate | 2:0e2ef1edf01b | 2685 | if (dp < row || dp+3 > row+png_ptr->row_buf_size) |
destinyXfate | 2:0e2ef1edf01b | 2686 | { |
destinyXfate | 2:0e2ef1edf01b | 2687 | printf("dp out of bounds: row=%d, dp=%d, rp=%d\n", |
destinyXfate | 2:0e2ef1edf01b | 2688 | row, dp, row+png_ptr->row_buf_size); |
destinyXfate | 2:0e2ef1edf01b | 2689 | printf("row_buf=%d\n",png_ptr->row_buf_size); |
destinyXfate | 2:0e2ef1edf01b | 2690 | } |
destinyXfate | 2:0e2ef1edf01b | 2691 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2692 | png_memcpy(dp, v, 4); |
destinyXfate | 2:0e2ef1edf01b | 2693 | dp -= 4; |
destinyXfate | 2:0e2ef1edf01b | 2694 | } |
destinyXfate | 2:0e2ef1edf01b | 2695 | sptr -= 4; |
destinyXfate | 2:0e2ef1edf01b | 2696 | } |
destinyXfate | 2:0e2ef1edf01b | 2697 | } |
destinyXfate | 2:0e2ef1edf01b | 2698 | else if (pixel_bytes == 6) |
destinyXfate | 2:0e2ef1edf01b | 2699 | { |
destinyXfate | 2:0e2ef1edf01b | 2700 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2701 | { |
destinyXfate | 2:0e2ef1edf01b | 2702 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2703 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2704 | png_memcpy(v, sptr, 6); |
destinyXfate | 2:0e2ef1edf01b | 2705 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2706 | { |
destinyXfate | 2:0e2ef1edf01b | 2707 | png_memcpy(dp, v, 6); |
destinyXfate | 2:0e2ef1edf01b | 2708 | dp -= 6; |
destinyXfate | 2:0e2ef1edf01b | 2709 | } |
destinyXfate | 2:0e2ef1edf01b | 2710 | sptr -= 6; |
destinyXfate | 2:0e2ef1edf01b | 2711 | } |
destinyXfate | 2:0e2ef1edf01b | 2712 | } |
destinyXfate | 2:0e2ef1edf01b | 2713 | else if (pixel_bytes == 8) |
destinyXfate | 2:0e2ef1edf01b | 2714 | { |
destinyXfate | 2:0e2ef1edf01b | 2715 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2716 | { |
destinyXfate | 2:0e2ef1edf01b | 2717 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2718 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2719 | png_memcpy(v, sptr, 8); |
destinyXfate | 2:0e2ef1edf01b | 2720 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2721 | { |
destinyXfate | 2:0e2ef1edf01b | 2722 | png_memcpy(dp, v, 8); |
destinyXfate | 2:0e2ef1edf01b | 2723 | dp -= 8; |
destinyXfate | 2:0e2ef1edf01b | 2724 | } |
destinyXfate | 2:0e2ef1edf01b | 2725 | sptr -= 8; |
destinyXfate | 2:0e2ef1edf01b | 2726 | } |
destinyXfate | 2:0e2ef1edf01b | 2727 | } |
destinyXfate | 2:0e2ef1edf01b | 2728 | else /* GRR: should never be reached */ |
destinyXfate | 2:0e2ef1edf01b | 2729 | { |
destinyXfate | 2:0e2ef1edf01b | 2730 | for (i = width; i; i--) |
destinyXfate | 2:0e2ef1edf01b | 2731 | { |
destinyXfate | 2:0e2ef1edf01b | 2732 | png_byte v[8]; |
destinyXfate | 2:0e2ef1edf01b | 2733 | int j; |
destinyXfate | 2:0e2ef1edf01b | 2734 | png_memcpy(v, sptr, pixel_bytes); |
destinyXfate | 2:0e2ef1edf01b | 2735 | for (j = 0; j < png_pass_inc[pass]; j++) |
destinyXfate | 2:0e2ef1edf01b | 2736 | { |
destinyXfate | 2:0e2ef1edf01b | 2737 | png_memcpy(dp, v, pixel_bytes); |
destinyXfate | 2:0e2ef1edf01b | 2738 | dp -= pixel_bytes; |
destinyXfate | 2:0e2ef1edf01b | 2739 | } |
destinyXfate | 2:0e2ef1edf01b | 2740 | sptr -= pixel_bytes; |
destinyXfate | 2:0e2ef1edf01b | 2741 | } |
destinyXfate | 2:0e2ef1edf01b | 2742 | } |
destinyXfate | 2:0e2ef1edf01b | 2743 | |
destinyXfate | 2:0e2ef1edf01b | 2744 | } /* end if (MMX not supported) */ |
destinyXfate | 2:0e2ef1edf01b | 2745 | break; |
destinyXfate | 2:0e2ef1edf01b | 2746 | } |
destinyXfate | 2:0e2ef1edf01b | 2747 | } /* end switch (row_info->pixel_depth) */ |
destinyXfate | 2:0e2ef1edf01b | 2748 | |
destinyXfate | 2:0e2ef1edf01b | 2749 | row_info->width = final_width; |
destinyXfate | 2:0e2ef1edf01b | 2750 | |
destinyXfate | 2:0e2ef1edf01b | 2751 | row_info->rowbytes = PNG_ROWBYTES(row_info->pixel_depth,final_width); |
destinyXfate | 2:0e2ef1edf01b | 2752 | } |
destinyXfate | 2:0e2ef1edf01b | 2753 | |
destinyXfate | 2:0e2ef1edf01b | 2754 | } /* end png_do_read_interlace() */ |
destinyXfate | 2:0e2ef1edf01b | 2755 | |
destinyXfate | 2:0e2ef1edf01b | 2756 | #endif /* PNG_HAVE_MMX_READ_INTERLACE */ |
destinyXfate | 2:0e2ef1edf01b | 2757 | #endif /* PNG_READ_INTERLACING_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 2758 | |
destinyXfate | 2:0e2ef1edf01b | 2759 | |
destinyXfate | 2:0e2ef1edf01b | 2760 | |
destinyXfate | 2:0e2ef1edf01b | 2761 | #if defined(PNG_HAVE_MMX_READ_FILTER_ROW) |
destinyXfate | 2:0e2ef1edf01b | 2762 | #if defined(PNG_MMX_CODE_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 2763 | |
destinyXfate | 2:0e2ef1edf01b | 2764 | // These variables are utilized in the functions below. They are declared |
destinyXfate | 2:0e2ef1edf01b | 2765 | // globally here to ensure alignment on 8-byte boundaries. |
destinyXfate | 2:0e2ef1edf01b | 2766 | |
destinyXfate | 2:0e2ef1edf01b | 2767 | union uAll { |
destinyXfate | 2:0e2ef1edf01b | 2768 | long long use; |
destinyXfate | 2:0e2ef1edf01b | 2769 | double align; |
destinyXfate | 2:0e2ef1edf01b | 2770 | } _LBCarryMask = {0x0101010101010101LL}, |
destinyXfate | 2:0e2ef1edf01b | 2771 | _HBClearMask = {0x7f7f7f7f7f7f7f7fLL}, |
destinyXfate | 2:0e2ef1edf01b | 2772 | _ActiveMask, _ActiveMask2, _ActiveMaskEnd, _ShiftBpp, _ShiftRem; |
destinyXfate | 2:0e2ef1edf01b | 2773 | |
destinyXfate | 2:0e2ef1edf01b | 2774 | #ifdef PNG_THREAD_UNSAFE_OK |
destinyXfate | 2:0e2ef1edf01b | 2775 | //===========================================================================// |
destinyXfate | 2:0e2ef1edf01b | 2776 | // // |
destinyXfate | 2:0e2ef1edf01b | 2777 | // P N G _ R E A D _ F I L T E R _ R O W _ M M X _ A V G // |
destinyXfate | 2:0e2ef1edf01b | 2778 | // // |
destinyXfate | 2:0e2ef1edf01b | 2779 | //===========================================================================// |
destinyXfate | 2:0e2ef1edf01b | 2780 | |
destinyXfate | 2:0e2ef1edf01b | 2781 | // Optimized code for PNG Average filter decoder |
destinyXfate | 2:0e2ef1edf01b | 2782 | |
destinyXfate | 2:0e2ef1edf01b | 2783 | static void /* PRIVATE */ |
destinyXfate | 2:0e2ef1edf01b | 2784 | png_read_filter_row_mmx_avg(png_row_infop row_info, png_bytep row, |
destinyXfate | 2:0e2ef1edf01b | 2785 | png_bytep prev_row) |
destinyXfate | 2:0e2ef1edf01b | 2786 | { |
destinyXfate | 2:0e2ef1edf01b | 2787 | int bpp; |
destinyXfate | 2:0e2ef1edf01b | 2788 | int dummy_value_c; // fix 'forbidden register 2 (cx) was spilled' error |
destinyXfate | 2:0e2ef1edf01b | 2789 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 2790 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 2791 | |
destinyXfate | 2:0e2ef1edf01b | 2792 | bpp = (row_info->pixel_depth + 7) >> 3; // get # bytes per pixel |
destinyXfate | 2:0e2ef1edf01b | 2793 | _FullLength = row_info->rowbytes; // # of bytes to filter |
destinyXfate | 2:0e2ef1edf01b | 2794 | |
destinyXfate | 2:0e2ef1edf01b | 2795 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2796 | // initialize address pointers and offset |
destinyXfate | 2:0e2ef1edf01b | 2797 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 2798 | "pushl %%ebx \n\t" // save index to Global Offset Table |
destinyXfate | 2:0e2ef1edf01b | 2799 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2800 | //pre "movl row, %%edi \n\t" // edi: Avg(x) |
destinyXfate | 2:0e2ef1edf01b | 2801 | "xorl %%ebx, %%ebx \n\t" // ebx: x |
destinyXfate | 2:0e2ef1edf01b | 2802 | "movl %%edi, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2803 | //pre "movl prev_row, %%esi \n\t" // esi: Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 2804 | //pre "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx) |
destinyXfate | 2:0e2ef1edf01b | 2805 | "subl %%ecx, %%edx \n\t" // edx: Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 2806 | |
destinyXfate | 2:0e2ef1edf01b | 2807 | "xorl %%eax,%%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2808 | |
destinyXfate | 2:0e2ef1edf01b | 2809 | // Compute the Raw value for the first bpp bytes |
destinyXfate | 2:0e2ef1edf01b | 2810 | // Raw(x) = Avg(x) + (Prior(x)/2) |
destinyXfate | 2:0e2ef1edf01b | 2811 | "avg_rlp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2812 | "movb (%%esi,%%ebx,),%%al \n\t" // load al with Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 2813 | "incl %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2814 | "shrb %%al \n\t" // divide by 2 |
destinyXfate | 2:0e2ef1edf01b | 2815 | "addb -1(%%edi,%%ebx,),%%al \n\t" // add Avg(x); -1 to offset inc ebx |
destinyXfate | 2:0e2ef1edf01b | 2816 | //pre "cmpl bpp, %%ebx \n\t" // (bpp is preloaded into ecx) |
destinyXfate | 2:0e2ef1edf01b | 2817 | "cmpl %%ecx, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2818 | "movb %%al,-1(%%edi,%%ebx,) \n\t" // write Raw(x); -1 to offset inc ebx |
destinyXfate | 2:0e2ef1edf01b | 2819 | "jb avg_rlp \n\t" // mov does not affect flags |
destinyXfate | 2:0e2ef1edf01b | 2820 | |
destinyXfate | 2:0e2ef1edf01b | 2821 | // get # of bytes to alignment |
destinyXfate | 2:0e2ef1edf01b | 2822 | "movl %%edi, _dif \n\t" // take start of row |
destinyXfate | 2:0e2ef1edf01b | 2823 | "addl %%ebx, _dif \n\t" // add bpp |
destinyXfate | 2:0e2ef1edf01b | 2824 | "addl $0xf, _dif \n\t" // add 7+8 to incr past alignment bdry |
destinyXfate | 2:0e2ef1edf01b | 2825 | "andl $0xfffffff8, _dif \n\t" // mask to alignment boundary |
destinyXfate | 2:0e2ef1edf01b | 2826 | "subl %%edi, _dif \n\t" // subtract from start => value ebx at |
destinyXfate | 2:0e2ef1edf01b | 2827 | "jz avg_go \n\t" // alignment |
destinyXfate | 2:0e2ef1edf01b | 2828 | |
destinyXfate | 2:0e2ef1edf01b | 2829 | // fix alignment |
destinyXfate | 2:0e2ef1edf01b | 2830 | // Compute the Raw value for the bytes up to the alignment boundary |
destinyXfate | 2:0e2ef1edf01b | 2831 | // Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2) |
destinyXfate | 2:0e2ef1edf01b | 2832 | "xorl %%ecx, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2833 | |
destinyXfate | 2:0e2ef1edf01b | 2834 | "avg_lp1: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2835 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2836 | "movb (%%esi,%%ebx,), %%cl \n\t" // load cl with Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 2837 | "movb (%%edx,%%ebx,), %%al \n\t" // load al with Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 2838 | "addw %%cx, %%ax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2839 | "incl %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2840 | "shrw %%ax \n\t" // divide by 2 |
destinyXfate | 2:0e2ef1edf01b | 2841 | "addb -1(%%edi,%%ebx,), %%al \n\t" // add Avg(x); -1 to offset inc ebx |
destinyXfate | 2:0e2ef1edf01b | 2842 | "cmpl _dif, %%ebx \n\t" // check if at alignment boundary |
destinyXfate | 2:0e2ef1edf01b | 2843 | "movb %%al, -1(%%edi,%%ebx,) \n\t" // write Raw(x); -1 to offset inc ebx |
destinyXfate | 2:0e2ef1edf01b | 2844 | "jb avg_lp1 \n\t" // repeat until at alignment boundary |
destinyXfate | 2:0e2ef1edf01b | 2845 | |
destinyXfate | 2:0e2ef1edf01b | 2846 | "avg_go: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2847 | "movl _FullLength, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2848 | "movl %%eax, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2849 | "subl %%ebx, %%eax \n\t" // subtract alignment fix |
destinyXfate | 2:0e2ef1edf01b | 2850 | "andl $0x00000007, %%eax \n\t" // calc bytes over mult of 8 |
destinyXfate | 2:0e2ef1edf01b | 2851 | "subl %%eax, %%ecx \n\t" // drop over bytes from original length |
destinyXfate | 2:0e2ef1edf01b | 2852 | "movl %%ecx, _MMXLength \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2853 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 2854 | "popl %%ebx \n\t" // restore index to Global Offset Table |
destinyXfate | 2:0e2ef1edf01b | 2855 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2856 | |
destinyXfate | 2:0e2ef1edf01b | 2857 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 2858 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 2859 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2860 | |
destinyXfate | 2:0e2ef1edf01b | 2861 | : "0" (bpp), // ecx // input regs |
destinyXfate | 2:0e2ef1edf01b | 2862 | "1" (prev_row), // esi |
destinyXfate | 2:0e2ef1edf01b | 2863 | "2" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 2864 | |
destinyXfate | 2:0e2ef1edf01b | 2865 | : "%eax", "%edx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2866 | #ifndef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 2867 | , "%ebx" |
destinyXfate | 2:0e2ef1edf01b | 2868 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2869 | // GRR: INCLUDE "memory" as clobbered? (_dif, _MMXLength) |
destinyXfate | 2:0e2ef1edf01b | 2870 | // (seems to work fine without...) |
destinyXfate | 2:0e2ef1edf01b | 2871 | ); |
destinyXfate | 2:0e2ef1edf01b | 2872 | |
destinyXfate | 2:0e2ef1edf01b | 2873 | // now do the math for the rest of the row |
destinyXfate | 2:0e2ef1edf01b | 2874 | switch (bpp) |
destinyXfate | 2:0e2ef1edf01b | 2875 | { |
destinyXfate | 2:0e2ef1edf01b | 2876 | case 3: |
destinyXfate | 2:0e2ef1edf01b | 2877 | { |
destinyXfate | 2:0e2ef1edf01b | 2878 | _ActiveMask.use = 0x0000000000ffffffLL; |
destinyXfate | 2:0e2ef1edf01b | 2879 | _ShiftBpp.use = 24; // == 3 * 8 |
destinyXfate | 2:0e2ef1edf01b | 2880 | _ShiftRem.use = 40; // == 64 - 24 |
destinyXfate | 2:0e2ef1edf01b | 2881 | |
destinyXfate | 2:0e2ef1edf01b | 2882 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 2883 | // re-init address pointers and offset |
destinyXfate | 2:0e2ef1edf01b | 2884 | "movq _ActiveMask, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2885 | "movl _dif, %%ecx \n\t" // ecx: x = offset to |
destinyXfate | 2:0e2ef1edf01b | 2886 | "movq _LBCarryMask, %%mm5 \n\t" // alignment boundary |
destinyXfate | 2:0e2ef1edf01b | 2887 | // preload "movl row, %%edi \n\t" // edi: Avg(x) |
destinyXfate | 2:0e2ef1edf01b | 2888 | "movq _HBClearMask, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2889 | // preload "movl prev_row, %%esi \n\t" // esi: Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 2890 | |
destinyXfate | 2:0e2ef1edf01b | 2891 | // prime the pump: load the first Raw(x-bpp) data set |
destinyXfate | 2:0e2ef1edf01b | 2892 | "movq -8(%%edi,%%ecx,), %%mm2 \n\t" // load previous aligned 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 2893 | // (correct pos. in loop below) |
destinyXfate | 2:0e2ef1edf01b | 2894 | "avg_3lp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2895 | "movq (%%edi,%%ecx,), %%mm0 \n\t" // load mm0 with Avg(x) |
destinyXfate | 2:0e2ef1edf01b | 2896 | "movq %%mm5, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2897 | "psrlq _ShiftRem, %%mm2 \n\t" // correct position Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 2898 | // data |
destinyXfate | 2:0e2ef1edf01b | 2899 | "movq (%%esi,%%ecx,), %%mm1 \n\t" // load mm1 with Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 2900 | "movq %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2901 | "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte |
destinyXfate | 2:0e2ef1edf01b | 2902 | "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 2903 | "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 2904 | // byte |
destinyXfate | 2:0e2ef1edf01b | 2905 | "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg for |
destinyXfate | 2:0e2ef1edf01b | 2906 | // each byte |
destinyXfate | 2:0e2ef1edf01b | 2907 | // add 1st active group (Raw(x-bpp)/2) to average with LBCarry |
destinyXfate | 2:0e2ef1edf01b | 2908 | "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting |
destinyXfate | 2:0e2ef1edf01b | 2909 | // LBCarrys |
destinyXfate | 2:0e2ef1edf01b | 2910 | "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte |
destinyXfate | 2:0e2ef1edf01b | 2911 | // where both |
destinyXfate | 2:0e2ef1edf01b | 2912 | // lsb's were == 1 (only valid for active group) |
destinyXfate | 2:0e2ef1edf01b | 2913 | "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 2914 | "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 2915 | // byte |
destinyXfate | 2:0e2ef1edf01b | 2916 | "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) |
destinyXfate | 2:0e2ef1edf01b | 2917 | // for each byte |
destinyXfate | 2:0e2ef1edf01b | 2918 | "pand %%mm6, %%mm2 \n\t" // leave only Active Group 1 |
destinyXfate | 2:0e2ef1edf01b | 2919 | // bytes to add to Avg |
destinyXfate | 2:0e2ef1edf01b | 2920 | "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to |
destinyXfate | 2:0e2ef1edf01b | 2921 | // Avg for each Active |
destinyXfate | 2:0e2ef1edf01b | 2922 | // byte |
destinyXfate | 2:0e2ef1edf01b | 2923 | // add 2nd active group (Raw(x-bpp)/2) to average with _LBCarry |
destinyXfate | 2:0e2ef1edf01b | 2924 | "psllq _ShiftBpp, %%mm6 \n\t" // shift the mm6 mask to cover |
destinyXfate | 2:0e2ef1edf01b | 2925 | // bytes 3-5 |
destinyXfate | 2:0e2ef1edf01b | 2926 | "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 |
destinyXfate | 2:0e2ef1edf01b | 2927 | "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 2928 | "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting |
destinyXfate | 2:0e2ef1edf01b | 2929 | // LBCarrys |
destinyXfate | 2:0e2ef1edf01b | 2930 | "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte |
destinyXfate | 2:0e2ef1edf01b | 2931 | // where both |
destinyXfate | 2:0e2ef1edf01b | 2932 | // lsb's were == 1 (only valid for active group) |
destinyXfate | 2:0e2ef1edf01b | 2933 | "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 2934 | "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 2935 | // byte |
destinyXfate | 2:0e2ef1edf01b | 2936 | "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) |
destinyXfate | 2:0e2ef1edf01b | 2937 | // for each byte |
destinyXfate | 2:0e2ef1edf01b | 2938 | "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2 |
destinyXfate | 2:0e2ef1edf01b | 2939 | // bytes to add to Avg |
destinyXfate | 2:0e2ef1edf01b | 2940 | "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to |
destinyXfate | 2:0e2ef1edf01b | 2941 | // Avg for each Active |
destinyXfate | 2:0e2ef1edf01b | 2942 | // byte |
destinyXfate | 2:0e2ef1edf01b | 2943 | |
destinyXfate | 2:0e2ef1edf01b | 2944 | // add 3rd active group (Raw(x-bpp)/2) to average with _LBCarry |
destinyXfate | 2:0e2ef1edf01b | 2945 | "psllq _ShiftBpp, %%mm6 \n\t" // shift mm6 mask to cover last |
destinyXfate | 2:0e2ef1edf01b | 2946 | // two |
destinyXfate | 2:0e2ef1edf01b | 2947 | // bytes |
destinyXfate | 2:0e2ef1edf01b | 2948 | "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 |
destinyXfate | 2:0e2ef1edf01b | 2949 | "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 2950 | // Data only needs to be shifted once here to |
destinyXfate | 2:0e2ef1edf01b | 2951 | // get the correct x-bpp offset. |
destinyXfate | 2:0e2ef1edf01b | 2952 | "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting |
destinyXfate | 2:0e2ef1edf01b | 2953 | // LBCarrys |
destinyXfate | 2:0e2ef1edf01b | 2954 | "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte |
destinyXfate | 2:0e2ef1edf01b | 2955 | // where both |
destinyXfate | 2:0e2ef1edf01b | 2956 | // lsb's were == 1 (only valid for active group) |
destinyXfate | 2:0e2ef1edf01b | 2957 | "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 2958 | "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 2959 | // byte |
destinyXfate | 2:0e2ef1edf01b | 2960 | "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) |
destinyXfate | 2:0e2ef1edf01b | 2961 | // for each byte |
destinyXfate | 2:0e2ef1edf01b | 2962 | "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2 |
destinyXfate | 2:0e2ef1edf01b | 2963 | // bytes to add to Avg |
destinyXfate | 2:0e2ef1edf01b | 2964 | "addl $8, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2965 | "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to |
destinyXfate | 2:0e2ef1edf01b | 2966 | // Avg for each Active |
destinyXfate | 2:0e2ef1edf01b | 2967 | // byte |
destinyXfate | 2:0e2ef1edf01b | 2968 | // now ready to write back to memory |
destinyXfate | 2:0e2ef1edf01b | 2969 | "movq %%mm0, -8(%%edi,%%ecx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2970 | // move updated Raw(x) to use as Raw(x-bpp) for next loop |
destinyXfate | 2:0e2ef1edf01b | 2971 | "cmpl _MMXLength, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2972 | "movq %%mm0, %%mm2 \n\t" // mov updated Raw(x) to mm2 |
destinyXfate | 2:0e2ef1edf01b | 2973 | "jb avg_3lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 2974 | |
destinyXfate | 2:0e2ef1edf01b | 2975 | : "=S" (dummy_value_S), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 2976 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 2977 | |
destinyXfate | 2:0e2ef1edf01b | 2978 | : "0" (prev_row), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 2979 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 2980 | |
destinyXfate | 2:0e2ef1edf01b | 2981 | : "%ecx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 2982 | #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 2983 | , "%mm0", "%mm1", "%mm2", "%mm3" |
destinyXfate | 2:0e2ef1edf01b | 2984 | , "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 2985 | #endif |
destinyXfate | 2:0e2ef1edf01b | 2986 | ); |
destinyXfate | 2:0e2ef1edf01b | 2987 | } |
destinyXfate | 2:0e2ef1edf01b | 2988 | break; // end 3 bpp |
destinyXfate | 2:0e2ef1edf01b | 2989 | |
destinyXfate | 2:0e2ef1edf01b | 2990 | case 6: |
destinyXfate | 2:0e2ef1edf01b | 2991 | case 4: |
destinyXfate | 2:0e2ef1edf01b | 2992 | //case 7: // who wrote this? PNG doesn't support 5 or 7 bytes/pixel |
destinyXfate | 2:0e2ef1edf01b | 2993 | //case 5: // GRR BOGUS |
destinyXfate | 2:0e2ef1edf01b | 2994 | { |
destinyXfate | 2:0e2ef1edf01b | 2995 | _ActiveMask.use = 0xffffffffffffffffLL; // use shift below to clear |
destinyXfate | 2:0e2ef1edf01b | 2996 | // appropriate inactive bytes |
destinyXfate | 2:0e2ef1edf01b | 2997 | _ShiftBpp.use = bpp << 3; |
destinyXfate | 2:0e2ef1edf01b | 2998 | _ShiftRem.use = 64 - _ShiftBpp.use; |
destinyXfate | 2:0e2ef1edf01b | 2999 | |
destinyXfate | 2:0e2ef1edf01b | 3000 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 3001 | "movq _HBClearMask, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3002 | |
destinyXfate | 2:0e2ef1edf01b | 3003 | // re-init address pointers and offset |
destinyXfate | 2:0e2ef1edf01b | 3004 | "movl _dif, %%ecx \n\t" // ecx: x = offset to |
destinyXfate | 2:0e2ef1edf01b | 3005 | // alignment boundary |
destinyXfate | 2:0e2ef1edf01b | 3006 | |
destinyXfate | 2:0e2ef1edf01b | 3007 | // load _ActiveMask and clear all bytes except for 1st active group |
destinyXfate | 2:0e2ef1edf01b | 3008 | "movq _ActiveMask, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3009 | // preload "movl row, %%edi \n\t" // edi: Avg(x) |
destinyXfate | 2:0e2ef1edf01b | 3010 | "psrlq _ShiftRem, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3011 | // preload "movl prev_row, %%esi \n\t" // esi: Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3012 | "movq %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3013 | "movq _LBCarryMask, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3014 | "psllq _ShiftBpp, %%mm6 \n\t" // create mask for 2nd active |
destinyXfate | 2:0e2ef1edf01b | 3015 | // group |
destinyXfate | 2:0e2ef1edf01b | 3016 | |
destinyXfate | 2:0e2ef1edf01b | 3017 | // prime the pump: load the first Raw(x-bpp) data set |
destinyXfate | 2:0e2ef1edf01b | 3018 | "movq -8(%%edi,%%ecx,), %%mm2 \n\t" // load previous aligned 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 3019 | // (we correct pos. in loop below) |
destinyXfate | 2:0e2ef1edf01b | 3020 | "avg_4lp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3021 | "movq (%%edi,%%ecx,), %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3022 | "psrlq _ShiftRem, %%mm2 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 3023 | "movq (%%esi,%%ecx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3024 | // add (Prev_row/2) to average |
destinyXfate | 2:0e2ef1edf01b | 3025 | "movq %%mm5, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3026 | "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte |
destinyXfate | 2:0e2ef1edf01b | 3027 | "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 3028 | "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 3029 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3030 | "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg for |
destinyXfate | 2:0e2ef1edf01b | 3031 | // each byte |
destinyXfate | 2:0e2ef1edf01b | 3032 | // add 1st active group (Raw(x-bpp)/2) to average with _LBCarry |
destinyXfate | 2:0e2ef1edf01b | 3033 | "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting |
destinyXfate | 2:0e2ef1edf01b | 3034 | // LBCarrys |
destinyXfate | 2:0e2ef1edf01b | 3035 | "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte |
destinyXfate | 2:0e2ef1edf01b | 3036 | // where both |
destinyXfate | 2:0e2ef1edf01b | 3037 | // lsb's were == 1 (only valid for active group) |
destinyXfate | 2:0e2ef1edf01b | 3038 | "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 3039 | "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 3040 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3041 | "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) |
destinyXfate | 2:0e2ef1edf01b | 3042 | // for each byte |
destinyXfate | 2:0e2ef1edf01b | 3043 | "pand %%mm7, %%mm2 \n\t" // leave only Active Group 1 |
destinyXfate | 2:0e2ef1edf01b | 3044 | // bytes to add to Avg |
destinyXfate | 2:0e2ef1edf01b | 3045 | "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to Avg |
destinyXfate | 2:0e2ef1edf01b | 3046 | // for each Active |
destinyXfate | 2:0e2ef1edf01b | 3047 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3048 | // add 2nd active group (Raw(x-bpp)/2) to average with _LBCarry |
destinyXfate | 2:0e2ef1edf01b | 3049 | "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 |
destinyXfate | 2:0e2ef1edf01b | 3050 | "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 3051 | "addl $8, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3052 | "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting |
destinyXfate | 2:0e2ef1edf01b | 3053 | // LBCarrys |
destinyXfate | 2:0e2ef1edf01b | 3054 | "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte |
destinyXfate | 2:0e2ef1edf01b | 3055 | // where both |
destinyXfate | 2:0e2ef1edf01b | 3056 | // lsb's were == 1 (only valid for active group) |
destinyXfate | 2:0e2ef1edf01b | 3057 | "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 3058 | "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 3059 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3060 | "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) |
destinyXfate | 2:0e2ef1edf01b | 3061 | // for each byte |
destinyXfate | 2:0e2ef1edf01b | 3062 | "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2 |
destinyXfate | 2:0e2ef1edf01b | 3063 | // bytes to add to Avg |
destinyXfate | 2:0e2ef1edf01b | 3064 | "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to |
destinyXfate | 2:0e2ef1edf01b | 3065 | // Avg for each Active |
destinyXfate | 2:0e2ef1edf01b | 3066 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3067 | "cmpl _MMXLength, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3068 | // now ready to write back to memory |
destinyXfate | 2:0e2ef1edf01b | 3069 | "movq %%mm0, -8(%%edi,%%ecx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3070 | // prep Raw(x-bpp) for next loop |
destinyXfate | 2:0e2ef1edf01b | 3071 | "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 |
destinyXfate | 2:0e2ef1edf01b | 3072 | "jb avg_4lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3073 | |
destinyXfate | 2:0e2ef1edf01b | 3074 | : "=S" (dummy_value_S), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 3075 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 3076 | |
destinyXfate | 2:0e2ef1edf01b | 3077 | : "0" (prev_row), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 3078 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 3079 | |
destinyXfate | 2:0e2ef1edf01b | 3080 | : "%ecx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 3081 | #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 3082 | , "%mm0", "%mm1", "%mm2", "%mm3" |
destinyXfate | 2:0e2ef1edf01b | 3083 | , "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 3084 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3085 | ); |
destinyXfate | 2:0e2ef1edf01b | 3086 | } |
destinyXfate | 2:0e2ef1edf01b | 3087 | break; // end 4,6 bpp |
destinyXfate | 2:0e2ef1edf01b | 3088 | |
destinyXfate | 2:0e2ef1edf01b | 3089 | case 2: |
destinyXfate | 2:0e2ef1edf01b | 3090 | { |
destinyXfate | 2:0e2ef1edf01b | 3091 | _ActiveMask.use = 0x000000000000ffffLL; |
destinyXfate | 2:0e2ef1edf01b | 3092 | _ShiftBpp.use = 16; // == 2 * 8 |
destinyXfate | 2:0e2ef1edf01b | 3093 | _ShiftRem.use = 48; // == 64 - 16 |
destinyXfate | 2:0e2ef1edf01b | 3094 | |
destinyXfate | 2:0e2ef1edf01b | 3095 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 3096 | // load _ActiveMask |
destinyXfate | 2:0e2ef1edf01b | 3097 | "movq _ActiveMask, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3098 | // re-init address pointers and offset |
destinyXfate | 2:0e2ef1edf01b | 3099 | "movl _dif, %%ecx \n\t" // ecx: x = offset to alignment |
destinyXfate | 2:0e2ef1edf01b | 3100 | // boundary |
destinyXfate | 2:0e2ef1edf01b | 3101 | "movq _LBCarryMask, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3102 | // preload "movl row, %%edi \n\t" // edi: Avg(x) |
destinyXfate | 2:0e2ef1edf01b | 3103 | "movq _HBClearMask, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3104 | // preload "movl prev_row, %%esi \n\t" // esi: Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3105 | |
destinyXfate | 2:0e2ef1edf01b | 3106 | // prime the pump: load the first Raw(x-bpp) data set |
destinyXfate | 2:0e2ef1edf01b | 3107 | "movq -8(%%edi,%%ecx,), %%mm2 \n\t" // load previous aligned 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 3108 | // (we correct pos. in loop below) |
destinyXfate | 2:0e2ef1edf01b | 3109 | "avg_2lp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3110 | "movq (%%edi,%%ecx,), %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3111 | "psrlq _ShiftRem, %%mm2 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 3112 | "movq (%%esi,%%ecx,), %%mm1 \n\t" // (GRR BUGFIX: was psllq) |
destinyXfate | 2:0e2ef1edf01b | 3113 | // add (Prev_row/2) to average |
destinyXfate | 2:0e2ef1edf01b | 3114 | "movq %%mm5, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3115 | "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte |
destinyXfate | 2:0e2ef1edf01b | 3116 | "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 3117 | "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 3118 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3119 | "movq %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3120 | "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg for |
destinyXfate | 2:0e2ef1edf01b | 3121 | // each byte |
destinyXfate | 2:0e2ef1edf01b | 3122 | |
destinyXfate | 2:0e2ef1edf01b | 3123 | // add 1st active group (Raw(x-bpp)/2) to average with _LBCarry |
destinyXfate | 2:0e2ef1edf01b | 3124 | "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting |
destinyXfate | 2:0e2ef1edf01b | 3125 | // LBCarrys |
destinyXfate | 2:0e2ef1edf01b | 3126 | "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte |
destinyXfate | 2:0e2ef1edf01b | 3127 | // where both |
destinyXfate | 2:0e2ef1edf01b | 3128 | // lsb's were == 1 (only valid |
destinyXfate | 2:0e2ef1edf01b | 3129 | // for active group) |
destinyXfate | 2:0e2ef1edf01b | 3130 | "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 3131 | "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 3132 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3133 | "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) |
destinyXfate | 2:0e2ef1edf01b | 3134 | // for each byte |
destinyXfate | 2:0e2ef1edf01b | 3135 | "pand %%mm6, %%mm2 \n\t" // leave only Active Group 1 |
destinyXfate | 2:0e2ef1edf01b | 3136 | // bytes to add to Avg |
destinyXfate | 2:0e2ef1edf01b | 3137 | "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to Avg |
destinyXfate | 2:0e2ef1edf01b | 3138 | // for each Active byte |
destinyXfate | 2:0e2ef1edf01b | 3139 | |
destinyXfate | 2:0e2ef1edf01b | 3140 | // add 2nd active group (Raw(x-bpp)/2) to average with _LBCarry |
destinyXfate | 2:0e2ef1edf01b | 3141 | "psllq _ShiftBpp, %%mm6 \n\t" // shift the mm6 mask to cover |
destinyXfate | 2:0e2ef1edf01b | 3142 | // bytes 2 & 3 |
destinyXfate | 2:0e2ef1edf01b | 3143 | "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 |
destinyXfate | 2:0e2ef1edf01b | 3144 | "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 3145 | "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting |
destinyXfate | 2:0e2ef1edf01b | 3146 | // LBCarrys |
destinyXfate | 2:0e2ef1edf01b | 3147 | "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte |
destinyXfate | 2:0e2ef1edf01b | 3148 | // where both |
destinyXfate | 2:0e2ef1edf01b | 3149 | // lsb's were == 1 (only valid |
destinyXfate | 2:0e2ef1edf01b | 3150 | // for active group) |
destinyXfate | 2:0e2ef1edf01b | 3151 | "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 3152 | "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 3153 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3154 | "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) |
destinyXfate | 2:0e2ef1edf01b | 3155 | // for each byte |
destinyXfate | 2:0e2ef1edf01b | 3156 | "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2 |
destinyXfate | 2:0e2ef1edf01b | 3157 | // bytes to add to Avg |
destinyXfate | 2:0e2ef1edf01b | 3158 | "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to |
destinyXfate | 2:0e2ef1edf01b | 3159 | // Avg for each Active byte |
destinyXfate | 2:0e2ef1edf01b | 3160 | |
destinyXfate | 2:0e2ef1edf01b | 3161 | // add 3rd active group (Raw(x-bpp)/2) to average with _LBCarry |
destinyXfate | 2:0e2ef1edf01b | 3162 | "psllq _ShiftBpp, %%mm6 \n\t" // shift the mm6 mask to cover |
destinyXfate | 2:0e2ef1edf01b | 3163 | // bytes 4 & 5 |
destinyXfate | 2:0e2ef1edf01b | 3164 | "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 |
destinyXfate | 2:0e2ef1edf01b | 3165 | "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 3166 | "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting |
destinyXfate | 2:0e2ef1edf01b | 3167 | // LBCarrys |
destinyXfate | 2:0e2ef1edf01b | 3168 | "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte |
destinyXfate | 2:0e2ef1edf01b | 3169 | // where both lsb's were == 1 |
destinyXfate | 2:0e2ef1edf01b | 3170 | // (only valid for active group) |
destinyXfate | 2:0e2ef1edf01b | 3171 | "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 3172 | "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 3173 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3174 | "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) |
destinyXfate | 2:0e2ef1edf01b | 3175 | // for each byte |
destinyXfate | 2:0e2ef1edf01b | 3176 | "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2 |
destinyXfate | 2:0e2ef1edf01b | 3177 | // bytes to add to Avg |
destinyXfate | 2:0e2ef1edf01b | 3178 | "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to |
destinyXfate | 2:0e2ef1edf01b | 3179 | // Avg for each Active byte |
destinyXfate | 2:0e2ef1edf01b | 3180 | |
destinyXfate | 2:0e2ef1edf01b | 3181 | // add 4th active group (Raw(x-bpp)/2) to average with _LBCarry |
destinyXfate | 2:0e2ef1edf01b | 3182 | "psllq _ShiftBpp, %%mm6 \n\t" // shift the mm6 mask to cover |
destinyXfate | 2:0e2ef1edf01b | 3183 | // bytes 6 & 7 |
destinyXfate | 2:0e2ef1edf01b | 3184 | "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 |
destinyXfate | 2:0e2ef1edf01b | 3185 | "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 3186 | "addl $8, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3187 | "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting |
destinyXfate | 2:0e2ef1edf01b | 3188 | // LBCarrys |
destinyXfate | 2:0e2ef1edf01b | 3189 | "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte |
destinyXfate | 2:0e2ef1edf01b | 3190 | // where both |
destinyXfate | 2:0e2ef1edf01b | 3191 | // lsb's were == 1 (only valid |
destinyXfate | 2:0e2ef1edf01b | 3192 | // for active group) |
destinyXfate | 2:0e2ef1edf01b | 3193 | "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 3194 | "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 3195 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3196 | "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) |
destinyXfate | 2:0e2ef1edf01b | 3197 | // for each byte |
destinyXfate | 2:0e2ef1edf01b | 3198 | "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2 |
destinyXfate | 2:0e2ef1edf01b | 3199 | // bytes to add to Avg |
destinyXfate | 2:0e2ef1edf01b | 3200 | "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to |
destinyXfate | 2:0e2ef1edf01b | 3201 | // Avg for each Active byte |
destinyXfate | 2:0e2ef1edf01b | 3202 | |
destinyXfate | 2:0e2ef1edf01b | 3203 | "cmpl _MMXLength, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3204 | // now ready to write back to memory |
destinyXfate | 2:0e2ef1edf01b | 3205 | "movq %%mm0, -8(%%edi,%%ecx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3206 | // prep Raw(x-bpp) for next loop |
destinyXfate | 2:0e2ef1edf01b | 3207 | "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 |
destinyXfate | 2:0e2ef1edf01b | 3208 | "jb avg_2lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3209 | |
destinyXfate | 2:0e2ef1edf01b | 3210 | : "=S" (dummy_value_S), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 3211 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 3212 | |
destinyXfate | 2:0e2ef1edf01b | 3213 | : "0" (prev_row), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 3214 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 3215 | |
destinyXfate | 2:0e2ef1edf01b | 3216 | : "%ecx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 3217 | #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 3218 | , "%mm0", "%mm1", "%mm2", "%mm3" |
destinyXfate | 2:0e2ef1edf01b | 3219 | , "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 3220 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3221 | ); |
destinyXfate | 2:0e2ef1edf01b | 3222 | } |
destinyXfate | 2:0e2ef1edf01b | 3223 | break; // end 2 bpp |
destinyXfate | 2:0e2ef1edf01b | 3224 | |
destinyXfate | 2:0e2ef1edf01b | 3225 | case 1: |
destinyXfate | 2:0e2ef1edf01b | 3226 | { |
destinyXfate | 2:0e2ef1edf01b | 3227 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 3228 | // re-init address pointers and offset |
destinyXfate | 2:0e2ef1edf01b | 3229 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 3230 | "pushl %%ebx \n\t" // save Global Offset Table index |
destinyXfate | 2:0e2ef1edf01b | 3231 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3232 | "movl _dif, %%ebx \n\t" // ebx: x = offset to alignment |
destinyXfate | 2:0e2ef1edf01b | 3233 | // boundary |
destinyXfate | 2:0e2ef1edf01b | 3234 | // preload "movl row, %%edi \n\t" // edi: Avg(x) |
destinyXfate | 2:0e2ef1edf01b | 3235 | "cmpl _FullLength, %%ebx \n\t" // test if offset at end of array |
destinyXfate | 2:0e2ef1edf01b | 3236 | "jnb avg_1end \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3237 | // do Paeth decode for remaining bytes |
destinyXfate | 2:0e2ef1edf01b | 3238 | // preload "movl prev_row, %%esi \n\t" // esi: Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3239 | "movl %%edi, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3240 | // preload "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx) |
destinyXfate | 2:0e2ef1edf01b | 3241 | "subl %%ecx, %%edx \n\t" // edx: Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3242 | "xorl %%ecx, %%ecx \n\t" // zero ecx before using cl & cx |
destinyXfate | 2:0e2ef1edf01b | 3243 | // in loop below |
destinyXfate | 2:0e2ef1edf01b | 3244 | "avg_1lp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3245 | // Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2) |
destinyXfate | 2:0e2ef1edf01b | 3246 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3247 | "movb (%%esi,%%ebx,), %%cl \n\t" // load cl with Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3248 | "movb (%%edx,%%ebx,), %%al \n\t" // load al with Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3249 | "addw %%cx, %%ax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3250 | "incl %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3251 | "shrw %%ax \n\t" // divide by 2 |
destinyXfate | 2:0e2ef1edf01b | 3252 | "addb -1(%%edi,%%ebx,), %%al \n\t" // add Avg(x); -1 to offset |
destinyXfate | 2:0e2ef1edf01b | 3253 | // inc ebx |
destinyXfate | 2:0e2ef1edf01b | 3254 | "cmpl _FullLength, %%ebx \n\t" // check if at end of array |
destinyXfate | 2:0e2ef1edf01b | 3255 | "movb %%al, -1(%%edi,%%ebx,) \n\t" // write back Raw(x); |
destinyXfate | 2:0e2ef1edf01b | 3256 | // mov does not affect flags; -1 to offset inc ebx |
destinyXfate | 2:0e2ef1edf01b | 3257 | "jb avg_1lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3258 | |
destinyXfate | 2:0e2ef1edf01b | 3259 | "avg_1end: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3260 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 3261 | "popl %%ebx \n\t" // Global Offset Table index |
destinyXfate | 2:0e2ef1edf01b | 3262 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3263 | |
destinyXfate | 2:0e2ef1edf01b | 3264 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 3265 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 3266 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 3267 | |
destinyXfate | 2:0e2ef1edf01b | 3268 | : "0" (bpp), // ecx // input regs |
destinyXfate | 2:0e2ef1edf01b | 3269 | "1" (prev_row), // esi |
destinyXfate | 2:0e2ef1edf01b | 3270 | "2" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 3271 | |
destinyXfate | 2:0e2ef1edf01b | 3272 | : "%eax", "%edx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 3273 | #ifndef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 3274 | , "%ebx" |
destinyXfate | 2:0e2ef1edf01b | 3275 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3276 | ); |
destinyXfate | 2:0e2ef1edf01b | 3277 | } |
destinyXfate | 2:0e2ef1edf01b | 3278 | return; // end 1 bpp |
destinyXfate | 2:0e2ef1edf01b | 3279 | |
destinyXfate | 2:0e2ef1edf01b | 3280 | case 8: |
destinyXfate | 2:0e2ef1edf01b | 3281 | { |
destinyXfate | 2:0e2ef1edf01b | 3282 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 3283 | // re-init address pointers and offset |
destinyXfate | 2:0e2ef1edf01b | 3284 | "movl _dif, %%ecx \n\t" // ecx: x == offset to alignment |
destinyXfate | 2:0e2ef1edf01b | 3285 | "movq _LBCarryMask, %%mm5 \n\t" // boundary |
destinyXfate | 2:0e2ef1edf01b | 3286 | // preload "movl row, %%edi \n\t" // edi: Avg(x) |
destinyXfate | 2:0e2ef1edf01b | 3287 | "movq _HBClearMask, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3288 | // preload "movl prev_row, %%esi \n\t" // esi: Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3289 | |
destinyXfate | 2:0e2ef1edf01b | 3290 | // prime the pump: load the first Raw(x-bpp) data set |
destinyXfate | 2:0e2ef1edf01b | 3291 | "movq -8(%%edi,%%ecx,), %%mm2 \n\t" // load previous aligned 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 3292 | // (NO NEED to correct pos. in loop below) |
destinyXfate | 2:0e2ef1edf01b | 3293 | |
destinyXfate | 2:0e2ef1edf01b | 3294 | "avg_8lp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3295 | "movq (%%edi,%%ecx,), %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3296 | "movq %%mm5, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3297 | "movq (%%esi,%%ecx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3298 | "addl $8, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3299 | "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte |
destinyXfate | 2:0e2ef1edf01b | 3300 | "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 3301 | "pand %%mm2, %%mm3 \n\t" // get LBCarrys for each byte |
destinyXfate | 2:0e2ef1edf01b | 3302 | // where both lsb's were == 1 |
destinyXfate | 2:0e2ef1edf01b | 3303 | "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 3304 | "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7, each byte |
destinyXfate | 2:0e2ef1edf01b | 3305 | "paddb %%mm3, %%mm0 \n\t" // add LBCarrys to Avg, each byte |
destinyXfate | 2:0e2ef1edf01b | 3306 | "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7, each byte |
destinyXfate | 2:0e2ef1edf01b | 3307 | "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg, each |
destinyXfate | 2:0e2ef1edf01b | 3308 | "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) to Avg for each |
destinyXfate | 2:0e2ef1edf01b | 3309 | "cmpl _MMXLength, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3310 | "movq %%mm0, -8(%%edi,%%ecx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3311 | "movq %%mm0, %%mm2 \n\t" // reuse as Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3312 | "jb avg_8lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3313 | |
destinyXfate | 2:0e2ef1edf01b | 3314 | : "=S" (dummy_value_S), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 3315 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 3316 | |
destinyXfate | 2:0e2ef1edf01b | 3317 | : "0" (prev_row), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 3318 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 3319 | |
destinyXfate | 2:0e2ef1edf01b | 3320 | : "%ecx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 3321 | #if 0 /* %mm0, ..., %mm5 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 3322 | , "%mm0", "%mm1", "%mm2" |
destinyXfate | 2:0e2ef1edf01b | 3323 | , "%mm3", "%mm4", "%mm5" |
destinyXfate | 2:0e2ef1edf01b | 3324 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3325 | ); |
destinyXfate | 2:0e2ef1edf01b | 3326 | } |
destinyXfate | 2:0e2ef1edf01b | 3327 | break; // end 8 bpp |
destinyXfate | 2:0e2ef1edf01b | 3328 | |
destinyXfate | 2:0e2ef1edf01b | 3329 | default: // bpp greater than 8 (!= 1,2,3,4,[5],6,[7],8) |
destinyXfate | 2:0e2ef1edf01b | 3330 | { |
destinyXfate | 2:0e2ef1edf01b | 3331 | |
destinyXfate | 2:0e2ef1edf01b | 3332 | #ifdef PNG_DEBUG |
destinyXfate | 2:0e2ef1edf01b | 3333 | // GRR: PRINT ERROR HERE: SHOULD NEVER BE REACHED |
destinyXfate | 2:0e2ef1edf01b | 3334 | png_debug(1, |
destinyXfate | 2:0e2ef1edf01b | 3335 | "Internal logic error in pnggccrd (png_read_filter_row_mmx_avg())\n"); |
destinyXfate | 2:0e2ef1edf01b | 3336 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3337 | |
destinyXfate | 2:0e2ef1edf01b | 3338 | #if 0 |
destinyXfate | 2:0e2ef1edf01b | 3339 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 3340 | "movq _LBCarryMask, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3341 | // re-init address pointers and offset |
destinyXfate | 2:0e2ef1edf01b | 3342 | "movl _dif, %%ebx \n\t" // ebx: x = offset to |
destinyXfate | 2:0e2ef1edf01b | 3343 | // alignment boundary |
destinyXfate | 2:0e2ef1edf01b | 3344 | "movl row, %%edi \n\t" // edi: Avg(x) |
destinyXfate | 2:0e2ef1edf01b | 3345 | "movq _HBClearMask, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3346 | "movl %%edi, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3347 | "movl prev_row, %%esi \n\t" // esi: Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3348 | "subl bpp, %%edx \n\t" // edx: Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3349 | "avg_Alp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3350 | "movq (%%edi,%%ebx,), %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3351 | "movq %%mm5, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3352 | "movq (%%esi,%%ebx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3353 | "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte |
destinyXfate | 2:0e2ef1edf01b | 3354 | "movq (%%edx,%%ebx,), %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3355 | "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 3356 | "pand %%mm2, %%mm3 \n\t" // get LBCarrys for each byte |
destinyXfate | 2:0e2ef1edf01b | 3357 | // where both lsb's were == 1 |
destinyXfate | 2:0e2ef1edf01b | 3358 | "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 |
destinyXfate | 2:0e2ef1edf01b | 3359 | "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 3360 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3361 | "paddb %%mm3, %%mm0 \n\t" // add LBCarrys to Avg for each |
destinyXfate | 2:0e2ef1edf01b | 3362 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3363 | "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each |
destinyXfate | 2:0e2ef1edf01b | 3364 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3365 | "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg for |
destinyXfate | 2:0e2ef1edf01b | 3366 | // each byte |
destinyXfate | 2:0e2ef1edf01b | 3367 | "addl $8, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3368 | "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) to Avg for each |
destinyXfate | 2:0e2ef1edf01b | 3369 | // byte |
destinyXfate | 2:0e2ef1edf01b | 3370 | "cmpl _MMXLength, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3371 | "movq %%mm0, -8(%%edi,%%ebx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3372 | "jb avg_Alp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3373 | |
destinyXfate | 2:0e2ef1edf01b | 3374 | : // FIXASM: output regs/vars go here, e.g.: "=m" (memory_var) |
destinyXfate | 2:0e2ef1edf01b | 3375 | |
destinyXfate | 2:0e2ef1edf01b | 3376 | : // FIXASM: input regs, e.g.: "c" (count), "S" (src), "D" (dest) |
destinyXfate | 2:0e2ef1edf01b | 3377 | |
destinyXfate | 2:0e2ef1edf01b | 3378 | : "%ebx", "%edx", "%edi", "%esi" // CHECKASM: clobber list |
destinyXfate | 2:0e2ef1edf01b | 3379 | ); |
destinyXfate | 2:0e2ef1edf01b | 3380 | #endif /* 0 - NEVER REACHED */ |
destinyXfate | 2:0e2ef1edf01b | 3381 | } |
destinyXfate | 2:0e2ef1edf01b | 3382 | break; |
destinyXfate | 2:0e2ef1edf01b | 3383 | |
destinyXfate | 2:0e2ef1edf01b | 3384 | } // end switch (bpp) |
destinyXfate | 2:0e2ef1edf01b | 3385 | |
destinyXfate | 2:0e2ef1edf01b | 3386 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 3387 | // MMX acceleration complete; now do clean-up |
destinyXfate | 2:0e2ef1edf01b | 3388 | // check if any remaining bytes left to decode |
destinyXfate | 2:0e2ef1edf01b | 3389 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 3390 | "pushl %%ebx \n\t" // save index to Global Offset Table |
destinyXfate | 2:0e2ef1edf01b | 3391 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3392 | "movl _MMXLength, %%ebx \n\t" // ebx: x == offset bytes after MMX |
destinyXfate | 2:0e2ef1edf01b | 3393 | //pre "movl row, %%edi \n\t" // edi: Avg(x) |
destinyXfate | 2:0e2ef1edf01b | 3394 | "cmpl _FullLength, %%ebx \n\t" // test if offset at end of array |
destinyXfate | 2:0e2ef1edf01b | 3395 | "jnb avg_end \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3396 | |
destinyXfate | 2:0e2ef1edf01b | 3397 | // do Avg decode for remaining bytes |
destinyXfate | 2:0e2ef1edf01b | 3398 | //pre "movl prev_row, %%esi \n\t" // esi: Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3399 | "movl %%edi, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3400 | //pre "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx) |
destinyXfate | 2:0e2ef1edf01b | 3401 | "subl %%ecx, %%edx \n\t" // edx: Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3402 | "xorl %%ecx, %%ecx \n\t" // zero ecx before using cl & cx below |
destinyXfate | 2:0e2ef1edf01b | 3403 | |
destinyXfate | 2:0e2ef1edf01b | 3404 | "avg_lp2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3405 | // Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2) |
destinyXfate | 2:0e2ef1edf01b | 3406 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3407 | "movb (%%esi,%%ebx,), %%cl \n\t" // load cl with Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3408 | "movb (%%edx,%%ebx,), %%al \n\t" // load al with Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3409 | "addw %%cx, %%ax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3410 | "incl %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3411 | "shrw %%ax \n\t" // divide by 2 |
destinyXfate | 2:0e2ef1edf01b | 3412 | "addb -1(%%edi,%%ebx,), %%al \n\t" // add Avg(x); -1 to offset inc ebx |
destinyXfate | 2:0e2ef1edf01b | 3413 | "cmpl _FullLength, %%ebx \n\t" // check if at end of array |
destinyXfate | 2:0e2ef1edf01b | 3414 | "movb %%al, -1(%%edi,%%ebx,) \n\t" // write back Raw(x) [mov does not |
destinyXfate | 2:0e2ef1edf01b | 3415 | "jb avg_lp2 \n\t" // affect flags; -1 to offset inc ebx] |
destinyXfate | 2:0e2ef1edf01b | 3416 | |
destinyXfate | 2:0e2ef1edf01b | 3417 | "avg_end: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3418 | "EMMS \n\t" // end MMX; prep for poss. FP instrs. |
destinyXfate | 2:0e2ef1edf01b | 3419 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 3420 | "popl %%ebx \n\t" // restore index to Global Offset Table |
destinyXfate | 2:0e2ef1edf01b | 3421 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3422 | |
destinyXfate | 2:0e2ef1edf01b | 3423 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 3424 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 3425 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 3426 | |
destinyXfate | 2:0e2ef1edf01b | 3427 | : "0" (bpp), // ecx // input regs |
destinyXfate | 2:0e2ef1edf01b | 3428 | "1" (prev_row), // esi |
destinyXfate | 2:0e2ef1edf01b | 3429 | "2" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 3430 | |
destinyXfate | 2:0e2ef1edf01b | 3431 | : "%eax", "%edx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 3432 | #ifndef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 3433 | , "%ebx" |
destinyXfate | 2:0e2ef1edf01b | 3434 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3435 | ); |
destinyXfate | 2:0e2ef1edf01b | 3436 | |
destinyXfate | 2:0e2ef1edf01b | 3437 | } /* end png_read_filter_row_mmx_avg() */ |
destinyXfate | 2:0e2ef1edf01b | 3438 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3439 | |
destinyXfate | 2:0e2ef1edf01b | 3440 | |
destinyXfate | 2:0e2ef1edf01b | 3441 | |
destinyXfate | 2:0e2ef1edf01b | 3442 | #ifdef PNG_THREAD_UNSAFE_OK |
destinyXfate | 2:0e2ef1edf01b | 3443 | //===========================================================================// |
destinyXfate | 2:0e2ef1edf01b | 3444 | // // |
destinyXfate | 2:0e2ef1edf01b | 3445 | // P N G _ R E A D _ F I L T E R _ R O W _ M M X _ P A E T H // |
destinyXfate | 2:0e2ef1edf01b | 3446 | // // |
destinyXfate | 2:0e2ef1edf01b | 3447 | //===========================================================================// |
destinyXfate | 2:0e2ef1edf01b | 3448 | |
destinyXfate | 2:0e2ef1edf01b | 3449 | // Optimized code for PNG Paeth filter decoder |
destinyXfate | 2:0e2ef1edf01b | 3450 | |
destinyXfate | 2:0e2ef1edf01b | 3451 | static void /* PRIVATE */ |
destinyXfate | 2:0e2ef1edf01b | 3452 | png_read_filter_row_mmx_paeth(png_row_infop row_info, png_bytep row, |
destinyXfate | 2:0e2ef1edf01b | 3453 | png_bytep prev_row) |
destinyXfate | 2:0e2ef1edf01b | 3454 | { |
destinyXfate | 2:0e2ef1edf01b | 3455 | int bpp; |
destinyXfate | 2:0e2ef1edf01b | 3456 | int dummy_value_c; // fix 'forbidden register 2 (cx) was spilled' error |
destinyXfate | 2:0e2ef1edf01b | 3457 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 3458 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 3459 | |
destinyXfate | 2:0e2ef1edf01b | 3460 | bpp = (row_info->pixel_depth + 7) >> 3; // Get # bytes per pixel |
destinyXfate | 2:0e2ef1edf01b | 3461 | _FullLength = row_info->rowbytes; // # of bytes to filter |
destinyXfate | 2:0e2ef1edf01b | 3462 | |
destinyXfate | 2:0e2ef1edf01b | 3463 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 3464 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 3465 | "pushl %%ebx \n\t" // save index to Global Offset Table |
destinyXfate | 2:0e2ef1edf01b | 3466 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3467 | "xorl %%ebx, %%ebx \n\t" // ebx: x offset |
destinyXfate | 2:0e2ef1edf01b | 3468 | //pre "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3469 | "xorl %%edx, %%edx \n\t" // edx: x-bpp offset |
destinyXfate | 2:0e2ef1edf01b | 3470 | //pre "movl prev_row, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3471 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3472 | |
destinyXfate | 2:0e2ef1edf01b | 3473 | // Compute the Raw value for the first bpp bytes |
destinyXfate | 2:0e2ef1edf01b | 3474 | // Note: the formula works out to be always |
destinyXfate | 2:0e2ef1edf01b | 3475 | // Paeth(x) = Raw(x) + Prior(x) where x < bpp |
destinyXfate | 2:0e2ef1edf01b | 3476 | "paeth_rlp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3477 | "movb (%%edi,%%ebx,), %%al \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3478 | "addb (%%esi,%%ebx,), %%al \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3479 | "incl %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3480 | //pre "cmpl bpp, %%ebx \n\t" (bpp is preloaded into ecx) |
destinyXfate | 2:0e2ef1edf01b | 3481 | "cmpl %%ecx, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3482 | "movb %%al, -1(%%edi,%%ebx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3483 | "jb paeth_rlp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3484 | // get # of bytes to alignment |
destinyXfate | 2:0e2ef1edf01b | 3485 | "movl %%edi, _dif \n\t" // take start of row |
destinyXfate | 2:0e2ef1edf01b | 3486 | "addl %%ebx, _dif \n\t" // add bpp |
destinyXfate | 2:0e2ef1edf01b | 3487 | "xorl %%ecx, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3488 | "addl $0xf, _dif \n\t" // add 7 + 8 to incr past alignment |
destinyXfate | 2:0e2ef1edf01b | 3489 | // boundary |
destinyXfate | 2:0e2ef1edf01b | 3490 | "andl $0xfffffff8, _dif \n\t" // mask to alignment boundary |
destinyXfate | 2:0e2ef1edf01b | 3491 | "subl %%edi, _dif \n\t" // subtract from start ==> value ebx |
destinyXfate | 2:0e2ef1edf01b | 3492 | // at alignment |
destinyXfate | 2:0e2ef1edf01b | 3493 | "jz paeth_go \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3494 | // fix alignment |
destinyXfate | 2:0e2ef1edf01b | 3495 | |
destinyXfate | 2:0e2ef1edf01b | 3496 | "paeth_lp1: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3497 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3498 | // pav = p - a = (a + b - c) - a = b - c |
destinyXfate | 2:0e2ef1edf01b | 3499 | "movb (%%esi,%%ebx,), %%al \n\t" // load Prior(x) into al |
destinyXfate | 2:0e2ef1edf01b | 3500 | "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl |
destinyXfate | 2:0e2ef1edf01b | 3501 | "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3502 | "movl %%eax, _patemp \n\t" // Save pav for later use |
destinyXfate | 2:0e2ef1edf01b | 3503 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3504 | // pbv = p - b = (a + b - c) - b = a - c |
destinyXfate | 2:0e2ef1edf01b | 3505 | "movb (%%edi,%%edx,), %%al \n\t" // load Raw(x-bpp) into al |
destinyXfate | 2:0e2ef1edf01b | 3506 | "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3507 | "movl %%eax, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3508 | // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 3509 | "addl _patemp, %%eax \n\t" // pcv = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 3510 | // pc = abs(pcv) |
destinyXfate | 2:0e2ef1edf01b | 3511 | "testl $0x80000000, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3512 | "jz paeth_pca \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3513 | "negl %%eax \n\t" // reverse sign of neg values |
destinyXfate | 2:0e2ef1edf01b | 3514 | |
destinyXfate | 2:0e2ef1edf01b | 3515 | "paeth_pca: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3516 | "movl %%eax, _pctemp \n\t" // save pc for later use |
destinyXfate | 2:0e2ef1edf01b | 3517 | // pb = abs(pbv) |
destinyXfate | 2:0e2ef1edf01b | 3518 | "testl $0x80000000, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3519 | "jz paeth_pba \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3520 | "negl %%ecx \n\t" // reverse sign of neg values |
destinyXfate | 2:0e2ef1edf01b | 3521 | |
destinyXfate | 2:0e2ef1edf01b | 3522 | "paeth_pba: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3523 | "movl %%ecx, _pbtemp \n\t" // save pb for later use |
destinyXfate | 2:0e2ef1edf01b | 3524 | // pa = abs(pav) |
destinyXfate | 2:0e2ef1edf01b | 3525 | "movl _patemp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3526 | "testl $0x80000000, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3527 | "jz paeth_paa \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3528 | "negl %%eax \n\t" // reverse sign of neg values |
destinyXfate | 2:0e2ef1edf01b | 3529 | |
destinyXfate | 2:0e2ef1edf01b | 3530 | "paeth_paa: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3531 | "movl %%eax, _patemp \n\t" // save pa for later use |
destinyXfate | 2:0e2ef1edf01b | 3532 | // test if pa <= pb |
destinyXfate | 2:0e2ef1edf01b | 3533 | "cmpl %%ecx, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3534 | "jna paeth_abb \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3535 | // pa > pb; now test if pb <= pc |
destinyXfate | 2:0e2ef1edf01b | 3536 | "cmpl _pctemp, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3537 | "jna paeth_bbc \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3538 | // pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3539 | "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl |
destinyXfate | 2:0e2ef1edf01b | 3540 | "jmp paeth_paeth \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3541 | |
destinyXfate | 2:0e2ef1edf01b | 3542 | "paeth_bbc: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3543 | // pb <= pc; Raw(x) = Paeth(x) + Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3544 | "movb (%%esi,%%ebx,), %%cl \n\t" // load Prior(x) into cl |
destinyXfate | 2:0e2ef1edf01b | 3545 | "jmp paeth_paeth \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3546 | |
destinyXfate | 2:0e2ef1edf01b | 3547 | "paeth_abb: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3548 | // pa <= pb; now test if pa <= pc |
destinyXfate | 2:0e2ef1edf01b | 3549 | "cmpl _pctemp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3550 | "jna paeth_abc \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3551 | // pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3552 | "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl |
destinyXfate | 2:0e2ef1edf01b | 3553 | "jmp paeth_paeth \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3554 | |
destinyXfate | 2:0e2ef1edf01b | 3555 | "paeth_abc: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3556 | // pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3557 | "movb (%%edi,%%edx,), %%cl \n\t" // load Raw(x-bpp) into cl |
destinyXfate | 2:0e2ef1edf01b | 3558 | |
destinyXfate | 2:0e2ef1edf01b | 3559 | "paeth_paeth: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3560 | "incl %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3561 | "incl %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3562 | // Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256 |
destinyXfate | 2:0e2ef1edf01b | 3563 | "addb %%cl, -1(%%edi,%%ebx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3564 | "cmpl _dif, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3565 | "jb paeth_lp1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3566 | |
destinyXfate | 2:0e2ef1edf01b | 3567 | "paeth_go: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3568 | "movl _FullLength, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3569 | "movl %%ecx, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3570 | "subl %%ebx, %%eax \n\t" // subtract alignment fix |
destinyXfate | 2:0e2ef1edf01b | 3571 | "andl $0x00000007, %%eax \n\t" // calc bytes over mult of 8 |
destinyXfate | 2:0e2ef1edf01b | 3572 | "subl %%eax, %%ecx \n\t" // drop over bytes from original length |
destinyXfate | 2:0e2ef1edf01b | 3573 | "movl %%ecx, _MMXLength \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3574 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 3575 | "popl %%ebx \n\t" // restore index to Global Offset Table |
destinyXfate | 2:0e2ef1edf01b | 3576 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3577 | |
destinyXfate | 2:0e2ef1edf01b | 3578 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 3579 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 3580 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 3581 | |
destinyXfate | 2:0e2ef1edf01b | 3582 | : "0" (bpp), // ecx // input regs |
destinyXfate | 2:0e2ef1edf01b | 3583 | "1" (prev_row), // esi |
destinyXfate | 2:0e2ef1edf01b | 3584 | "2" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 3585 | |
destinyXfate | 2:0e2ef1edf01b | 3586 | : "%eax", "%edx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 3587 | #ifndef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 3588 | , "%ebx" |
destinyXfate | 2:0e2ef1edf01b | 3589 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3590 | ); |
destinyXfate | 2:0e2ef1edf01b | 3591 | |
destinyXfate | 2:0e2ef1edf01b | 3592 | // now do the math for the rest of the row |
destinyXfate | 2:0e2ef1edf01b | 3593 | switch (bpp) |
destinyXfate | 2:0e2ef1edf01b | 3594 | { |
destinyXfate | 2:0e2ef1edf01b | 3595 | case 3: |
destinyXfate | 2:0e2ef1edf01b | 3596 | { |
destinyXfate | 2:0e2ef1edf01b | 3597 | _ActiveMask.use = 0x0000000000ffffffLL; |
destinyXfate | 2:0e2ef1edf01b | 3598 | _ActiveMaskEnd.use = 0xffff000000000000LL; |
destinyXfate | 2:0e2ef1edf01b | 3599 | _ShiftBpp.use = 24; // == bpp(3) * 8 |
destinyXfate | 2:0e2ef1edf01b | 3600 | _ShiftRem.use = 40; // == 64 - 24 |
destinyXfate | 2:0e2ef1edf01b | 3601 | |
destinyXfate | 2:0e2ef1edf01b | 3602 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 3603 | "movl _dif, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3604 | // preload "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3605 | // preload "movl prev_row, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3606 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3607 | // prime the pump: load the first Raw(x-bpp) data set |
destinyXfate | 2:0e2ef1edf01b | 3608 | "movq -8(%%edi,%%ecx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3609 | "paeth_3lp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3610 | "psrlq _ShiftRem, %%mm1 \n\t" // shift last 3 bytes to 1st |
destinyXfate | 2:0e2ef1edf01b | 3611 | // 3 bytes |
destinyXfate | 2:0e2ef1edf01b | 3612 | "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3613 | "punpcklbw %%mm0, %%mm1 \n\t" // unpack High bytes of a |
destinyXfate | 2:0e2ef1edf01b | 3614 | "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // prep c=Prior(x-bpp) bytes |
destinyXfate | 2:0e2ef1edf01b | 3615 | "punpcklbw %%mm0, %%mm2 \n\t" // unpack High bytes of b |
destinyXfate | 2:0e2ef1edf01b | 3616 | "psrlq _ShiftRem, %%mm3 \n\t" // shift last 3 bytes to 1st |
destinyXfate | 2:0e2ef1edf01b | 3617 | // 3 bytes |
destinyXfate | 2:0e2ef1edf01b | 3618 | // pav = p - a = (a + b - c) - a = b - c |
destinyXfate | 2:0e2ef1edf01b | 3619 | "movq %%mm2, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3620 | "punpcklbw %%mm0, %%mm3 \n\t" // unpack High bytes of c |
destinyXfate | 2:0e2ef1edf01b | 3621 | // pbv = p - b = (a + b - c) - b = a - c |
destinyXfate | 2:0e2ef1edf01b | 3622 | "movq %%mm1, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3623 | "psubw %%mm3, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3624 | "pxor %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3625 | // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 3626 | "movq %%mm4, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3627 | "psubw %%mm3, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3628 | |
destinyXfate | 2:0e2ef1edf01b | 3629 | // pa = abs(p-a) = abs(pav) |
destinyXfate | 2:0e2ef1edf01b | 3630 | // pb = abs(p-b) = abs(pbv) |
destinyXfate | 2:0e2ef1edf01b | 3631 | // pc = abs(p-c) = abs(pcv) |
destinyXfate | 2:0e2ef1edf01b | 3632 | "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3633 | "paddw %%mm5, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3634 | "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 3635 | "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3636 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3637 | "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 |
destinyXfate | 2:0e2ef1edf01b | 3638 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3639 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3640 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3641 | "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3642 | "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 3643 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3644 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3645 | // test pa <= pb |
destinyXfate | 2:0e2ef1edf01b | 3646 | "movq %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3647 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3648 | "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? |
destinyXfate | 2:0e2ef1edf01b | 3649 | "movq %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3650 | // use mm7 mask to merge pa & pb |
destinyXfate | 2:0e2ef1edf01b | 3651 | "pand %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3652 | // use mm0 mask copy to merge a & b |
destinyXfate | 2:0e2ef1edf01b | 3653 | "pand %%mm0, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3654 | "pandn %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3655 | "pandn %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3656 | "paddw %%mm5, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3657 | "paddw %%mm2, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3658 | // test ((pa <= pb)? pa:pb) <= pc |
destinyXfate | 2:0e2ef1edf01b | 3659 | "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? |
destinyXfate | 2:0e2ef1edf01b | 3660 | "pxor %%mm1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3661 | "pand %%mm7, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3662 | "pandn %%mm0, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3663 | "paddw %%mm3, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3664 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3665 | "packuswb %%mm1, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3666 | "movq (%%esi,%%ecx,), %%mm3 \n\t" // load c=Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3667 | "pand _ActiveMask, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3668 | "movq %%mm3, %%mm2 \n\t" // load b=Prior(x) step 1 |
destinyXfate | 2:0e2ef1edf01b | 3669 | "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor with Raw(x) |
destinyXfate | 2:0e2ef1edf01b | 3670 | "punpcklbw %%mm0, %%mm3 \n\t" // unpack High bytes of c |
destinyXfate | 2:0e2ef1edf01b | 3671 | "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value |
destinyXfate | 2:0e2ef1edf01b | 3672 | "movq %%mm7, %%mm1 \n\t" // now mm1 will be used as |
destinyXfate | 2:0e2ef1edf01b | 3673 | // Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3674 | // now do Paeth for 2nd set of bytes (3-5) |
destinyXfate | 2:0e2ef1edf01b | 3675 | "psrlq _ShiftBpp, %%mm2 \n\t" // load b=Prior(x) step 2 |
destinyXfate | 2:0e2ef1edf01b | 3676 | "punpcklbw %%mm0, %%mm1 \n\t" // unpack High bytes of a |
destinyXfate | 2:0e2ef1edf01b | 3677 | "pxor %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3678 | "punpcklbw %%mm0, %%mm2 \n\t" // unpack High bytes of b |
destinyXfate | 2:0e2ef1edf01b | 3679 | // pbv = p - b = (a + b - c) - b = a - c |
destinyXfate | 2:0e2ef1edf01b | 3680 | "movq %%mm1, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3681 | // pav = p - a = (a + b - c) - a = b - c |
destinyXfate | 2:0e2ef1edf01b | 3682 | "movq %%mm2, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3683 | "psubw %%mm3, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3684 | "psubw %%mm3, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3685 | // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = |
destinyXfate | 2:0e2ef1edf01b | 3686 | // pav + pbv = pbv + pav |
destinyXfate | 2:0e2ef1edf01b | 3687 | "movq %%mm5, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3688 | "paddw %%mm4, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3689 | |
destinyXfate | 2:0e2ef1edf01b | 3690 | // pa = abs(p-a) = abs(pav) |
destinyXfate | 2:0e2ef1edf01b | 3691 | // pb = abs(p-b) = abs(pbv) |
destinyXfate | 2:0e2ef1edf01b | 3692 | // pc = abs(p-c) = abs(pcv) |
destinyXfate | 2:0e2ef1edf01b | 3693 | "pcmpgtw %%mm5, %%mm0 \n\t" // create mask pbv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3694 | "pcmpgtw %%mm4, %%mm7 \n\t" // create mask pav bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3695 | "pand %%mm5, %%mm0 \n\t" // only pbv bytes < 0 in mm0 |
destinyXfate | 2:0e2ef1edf01b | 3696 | "pand %%mm4, %%mm7 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 3697 | "psubw %%mm0, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3698 | "psubw %%mm7, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3699 | "psubw %%mm0, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3700 | "psubw %%mm7, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3701 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3702 | "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3703 | "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 3704 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3705 | // test pa <= pb |
destinyXfate | 2:0e2ef1edf01b | 3706 | "movq %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3707 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3708 | "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? |
destinyXfate | 2:0e2ef1edf01b | 3709 | "movq %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3710 | // use mm7 mask to merge pa & pb |
destinyXfate | 2:0e2ef1edf01b | 3711 | "pand %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3712 | // use mm0 mask copy to merge a & b |
destinyXfate | 2:0e2ef1edf01b | 3713 | "pand %%mm0, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3714 | "pandn %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3715 | "pandn %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3716 | "paddw %%mm5, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3717 | "paddw %%mm2, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3718 | // test ((pa <= pb)? pa:pb) <= pc |
destinyXfate | 2:0e2ef1edf01b | 3719 | "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? |
destinyXfate | 2:0e2ef1edf01b | 3720 | "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3721 | "pand %%mm7, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3722 | "pandn %%mm0, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3723 | "pxor %%mm1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3724 | "paddw %%mm3, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3725 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3726 | "packuswb %%mm1, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3727 | "movq %%mm2, %%mm3 \n\t" // load c=Prior(x-bpp) step 1 |
destinyXfate | 2:0e2ef1edf01b | 3728 | "pand _ActiveMask, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3729 | "punpckhbw %%mm0, %%mm2 \n\t" // unpack High bytes of b |
destinyXfate | 2:0e2ef1edf01b | 3730 | "psllq _ShiftBpp, %%mm7 \n\t" // shift bytes to 2nd group of |
destinyXfate | 2:0e2ef1edf01b | 3731 | // 3 bytes |
destinyXfate | 2:0e2ef1edf01b | 3732 | // pav = p - a = (a + b - c) - a = b - c |
destinyXfate | 2:0e2ef1edf01b | 3733 | "movq %%mm2, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3734 | "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor with Raw(x) |
destinyXfate | 2:0e2ef1edf01b | 3735 | "psllq _ShiftBpp, %%mm3 \n\t" // load c=Prior(x-bpp) step 2 |
destinyXfate | 2:0e2ef1edf01b | 3736 | "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value |
destinyXfate | 2:0e2ef1edf01b | 3737 | "movq %%mm7, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3738 | "punpckhbw %%mm0, %%mm3 \n\t" // unpack High bytes of c |
destinyXfate | 2:0e2ef1edf01b | 3739 | "psllq _ShiftBpp, %%mm1 \n\t" // shift bytes |
destinyXfate | 2:0e2ef1edf01b | 3740 | // now mm1 will be used as Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3741 | // now do Paeth for 3rd, and final, set of bytes (6-7) |
destinyXfate | 2:0e2ef1edf01b | 3742 | "pxor %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3743 | "punpckhbw %%mm0, %%mm1 \n\t" // unpack High bytes of a |
destinyXfate | 2:0e2ef1edf01b | 3744 | "psubw %%mm3, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3745 | // pbv = p - b = (a + b - c) - b = a - c |
destinyXfate | 2:0e2ef1edf01b | 3746 | "movq %%mm1, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3747 | // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 3748 | "movq %%mm4, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3749 | "psubw %%mm3, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3750 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3751 | "paddw %%mm5, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3752 | |
destinyXfate | 2:0e2ef1edf01b | 3753 | // pa = abs(p-a) = abs(pav) |
destinyXfate | 2:0e2ef1edf01b | 3754 | // pb = abs(p-b) = abs(pbv) |
destinyXfate | 2:0e2ef1edf01b | 3755 | // pc = abs(p-c) = abs(pcv) |
destinyXfate | 2:0e2ef1edf01b | 3756 | "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3757 | "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3758 | "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 3759 | "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 |
destinyXfate | 2:0e2ef1edf01b | 3760 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3761 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3762 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3763 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3764 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3765 | "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3766 | "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 3767 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3768 | // test pa <= pb |
destinyXfate | 2:0e2ef1edf01b | 3769 | "movq %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3770 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3771 | "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? |
destinyXfate | 2:0e2ef1edf01b | 3772 | "movq %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3773 | // use mm0 mask copy to merge a & b |
destinyXfate | 2:0e2ef1edf01b | 3774 | "pand %%mm0, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3775 | // use mm7 mask to merge pa & pb |
destinyXfate | 2:0e2ef1edf01b | 3776 | "pand %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3777 | "pandn %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3778 | "pandn %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3779 | "paddw %%mm2, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3780 | "paddw %%mm5, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3781 | // test ((pa <= pb)? pa:pb) <= pc |
destinyXfate | 2:0e2ef1edf01b | 3782 | "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? |
destinyXfate | 2:0e2ef1edf01b | 3783 | "pand %%mm7, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3784 | "pandn %%mm0, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3785 | "paddw %%mm3, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3786 | "pxor %%mm1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3787 | "packuswb %%mm7, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3788 | // step ecx to next set of 8 bytes and repeat loop til done |
destinyXfate | 2:0e2ef1edf01b | 3789 | "addl $8, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3790 | "pand _ActiveMaskEnd, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3791 | "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" // add Paeth predictor with |
destinyXfate | 2:0e2ef1edf01b | 3792 | // Raw(x) |
destinyXfate | 2:0e2ef1edf01b | 3793 | |
destinyXfate | 2:0e2ef1edf01b | 3794 | "cmpl _MMXLength, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3795 | "pxor %%mm0, %%mm0 \n\t" // pxor does not affect flags |
destinyXfate | 2:0e2ef1edf01b | 3796 | "movq %%mm1, -8(%%edi,%%ecx,) \n\t" // write back updated value |
destinyXfate | 2:0e2ef1edf01b | 3797 | // mm1 will be used as Raw(x-bpp) next loop |
destinyXfate | 2:0e2ef1edf01b | 3798 | // mm3 ready to be used as Prior(x-bpp) next loop |
destinyXfate | 2:0e2ef1edf01b | 3799 | "jb paeth_3lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3800 | |
destinyXfate | 2:0e2ef1edf01b | 3801 | : "=S" (dummy_value_S), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 3802 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 3803 | |
destinyXfate | 2:0e2ef1edf01b | 3804 | : "0" (prev_row), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 3805 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 3806 | |
destinyXfate | 2:0e2ef1edf01b | 3807 | : "%ecx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 3808 | #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 3809 | , "%mm0", "%mm1", "%mm2", "%mm3" |
destinyXfate | 2:0e2ef1edf01b | 3810 | , "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 3811 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3812 | ); |
destinyXfate | 2:0e2ef1edf01b | 3813 | } |
destinyXfate | 2:0e2ef1edf01b | 3814 | break; // end 3 bpp |
destinyXfate | 2:0e2ef1edf01b | 3815 | |
destinyXfate | 2:0e2ef1edf01b | 3816 | case 6: |
destinyXfate | 2:0e2ef1edf01b | 3817 | //case 7: // GRR BOGUS |
destinyXfate | 2:0e2ef1edf01b | 3818 | //case 5: // GRR BOGUS |
destinyXfate | 2:0e2ef1edf01b | 3819 | { |
destinyXfate | 2:0e2ef1edf01b | 3820 | _ActiveMask.use = 0x00000000ffffffffLL; |
destinyXfate | 2:0e2ef1edf01b | 3821 | _ActiveMask2.use = 0xffffffff00000000LL; |
destinyXfate | 2:0e2ef1edf01b | 3822 | _ShiftBpp.use = bpp << 3; // == bpp * 8 |
destinyXfate | 2:0e2ef1edf01b | 3823 | _ShiftRem.use = 64 - _ShiftBpp.use; |
destinyXfate | 2:0e2ef1edf01b | 3824 | |
destinyXfate | 2:0e2ef1edf01b | 3825 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 3826 | "movl _dif, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3827 | // preload "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3828 | // preload "movl prev_row, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3829 | // prime the pump: load the first Raw(x-bpp) data set |
destinyXfate | 2:0e2ef1edf01b | 3830 | "movq -8(%%edi,%%ecx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3831 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3832 | |
destinyXfate | 2:0e2ef1edf01b | 3833 | "paeth_6lp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3834 | // must shift to position Raw(x-bpp) data |
destinyXfate | 2:0e2ef1edf01b | 3835 | "psrlq _ShiftRem, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3836 | // do first set of 4 bytes |
destinyXfate | 2:0e2ef1edf01b | 3837 | "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // read c=Prior(x-bpp) bytes |
destinyXfate | 2:0e2ef1edf01b | 3838 | "punpcklbw %%mm0, %%mm1 \n\t" // unpack Low bytes of a |
destinyXfate | 2:0e2ef1edf01b | 3839 | "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3840 | "punpcklbw %%mm0, %%mm2 \n\t" // unpack Low bytes of b |
destinyXfate | 2:0e2ef1edf01b | 3841 | // must shift to position Prior(x-bpp) data |
destinyXfate | 2:0e2ef1edf01b | 3842 | "psrlq _ShiftRem, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3843 | // pav = p - a = (a + b - c) - a = b - c |
destinyXfate | 2:0e2ef1edf01b | 3844 | "movq %%mm2, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3845 | "punpcklbw %%mm0, %%mm3 \n\t" // unpack Low bytes of c |
destinyXfate | 2:0e2ef1edf01b | 3846 | // pbv = p - b = (a + b - c) - b = a - c |
destinyXfate | 2:0e2ef1edf01b | 3847 | "movq %%mm1, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3848 | "psubw %%mm3, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3849 | "pxor %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3850 | // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 3851 | "movq %%mm4, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3852 | "psubw %%mm3, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3853 | // pa = abs(p-a) = abs(pav) |
destinyXfate | 2:0e2ef1edf01b | 3854 | // pb = abs(p-b) = abs(pbv) |
destinyXfate | 2:0e2ef1edf01b | 3855 | // pc = abs(p-c) = abs(pcv) |
destinyXfate | 2:0e2ef1edf01b | 3856 | "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3857 | "paddw %%mm5, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3858 | "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 3859 | "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3860 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3861 | "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 |
destinyXfate | 2:0e2ef1edf01b | 3862 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3863 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3864 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3865 | "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3866 | "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 3867 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3868 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3869 | // test pa <= pb |
destinyXfate | 2:0e2ef1edf01b | 3870 | "movq %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3871 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3872 | "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? |
destinyXfate | 2:0e2ef1edf01b | 3873 | "movq %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3874 | // use mm7 mask to merge pa & pb |
destinyXfate | 2:0e2ef1edf01b | 3875 | "pand %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3876 | // use mm0 mask copy to merge a & b |
destinyXfate | 2:0e2ef1edf01b | 3877 | "pand %%mm0, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3878 | "pandn %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3879 | "pandn %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3880 | "paddw %%mm5, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3881 | "paddw %%mm2, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3882 | // test ((pa <= pb)? pa:pb) <= pc |
destinyXfate | 2:0e2ef1edf01b | 3883 | "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? |
destinyXfate | 2:0e2ef1edf01b | 3884 | "pxor %%mm1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3885 | "pand %%mm7, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3886 | "pandn %%mm0, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3887 | "paddw %%mm3, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3888 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3889 | "packuswb %%mm1, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3890 | "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // load c=Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 3891 | "pand _ActiveMask, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3892 | "psrlq _ShiftRem, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3893 | "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) step 1 |
destinyXfate | 2:0e2ef1edf01b | 3894 | "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor and Raw(x) |
destinyXfate | 2:0e2ef1edf01b | 3895 | "movq %%mm2, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3896 | "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value |
destinyXfate | 2:0e2ef1edf01b | 3897 | "movq -8(%%edi,%%ecx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3898 | "psllq _ShiftBpp, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3899 | "movq %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3900 | "psrlq _ShiftRem, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3901 | "por %%mm6, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3902 | "psllq _ShiftBpp, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3903 | "punpckhbw %%mm0, %%mm3 \n\t" // unpack High bytes of c |
destinyXfate | 2:0e2ef1edf01b | 3904 | "por %%mm5, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3905 | // do second set of 4 bytes |
destinyXfate | 2:0e2ef1edf01b | 3906 | "punpckhbw %%mm0, %%mm2 \n\t" // unpack High bytes of b |
destinyXfate | 2:0e2ef1edf01b | 3907 | "punpckhbw %%mm0, %%mm1 \n\t" // unpack High bytes of a |
destinyXfate | 2:0e2ef1edf01b | 3908 | // pav = p - a = (a + b - c) - a = b - c |
destinyXfate | 2:0e2ef1edf01b | 3909 | "movq %%mm2, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3910 | // pbv = p - b = (a + b - c) - b = a - c |
destinyXfate | 2:0e2ef1edf01b | 3911 | "movq %%mm1, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3912 | "psubw %%mm3, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3913 | "pxor %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3914 | // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 3915 | "movq %%mm4, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3916 | "psubw %%mm3, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3917 | // pa = abs(p-a) = abs(pav) |
destinyXfate | 2:0e2ef1edf01b | 3918 | // pb = abs(p-b) = abs(pbv) |
destinyXfate | 2:0e2ef1edf01b | 3919 | // pc = abs(p-c) = abs(pcv) |
destinyXfate | 2:0e2ef1edf01b | 3920 | "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3921 | "paddw %%mm5, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3922 | "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 3923 | "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3924 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3925 | "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 |
destinyXfate | 2:0e2ef1edf01b | 3926 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3927 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3928 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3929 | "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 3930 | "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 3931 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3932 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3933 | // test pa <= pb |
destinyXfate | 2:0e2ef1edf01b | 3934 | "movq %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3935 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3936 | "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? |
destinyXfate | 2:0e2ef1edf01b | 3937 | "movq %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3938 | // use mm7 mask to merge pa & pb |
destinyXfate | 2:0e2ef1edf01b | 3939 | "pand %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3940 | // use mm0 mask copy to merge a & b |
destinyXfate | 2:0e2ef1edf01b | 3941 | "pand %%mm0, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3942 | "pandn %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3943 | "pandn %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3944 | "paddw %%mm5, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3945 | "paddw %%mm2, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3946 | // test ((pa <= pb)? pa:pb) <= pc |
destinyXfate | 2:0e2ef1edf01b | 3947 | "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? |
destinyXfate | 2:0e2ef1edf01b | 3948 | "pxor %%mm1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3949 | "pand %%mm7, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3950 | "pandn %%mm0, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3951 | "pxor %%mm1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3952 | "paddw %%mm3, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3953 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3954 | // step ecx to next set of 8 bytes and repeat loop til done |
destinyXfate | 2:0e2ef1edf01b | 3955 | "addl $8, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3956 | "packuswb %%mm7, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3957 | "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" // add Paeth predictor with Raw(x) |
destinyXfate | 2:0e2ef1edf01b | 3958 | "cmpl _MMXLength, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3959 | "movq %%mm1, -8(%%edi,%%ecx,) \n\t" // write back updated value |
destinyXfate | 2:0e2ef1edf01b | 3960 | // mm1 will be used as Raw(x-bpp) next loop |
destinyXfate | 2:0e2ef1edf01b | 3961 | "jb paeth_6lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3962 | |
destinyXfate | 2:0e2ef1edf01b | 3963 | : "=S" (dummy_value_S), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 3964 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 3965 | |
destinyXfate | 2:0e2ef1edf01b | 3966 | : "0" (prev_row), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 3967 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 3968 | |
destinyXfate | 2:0e2ef1edf01b | 3969 | : "%ecx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 3970 | #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 3971 | , "%mm0", "%mm1", "%mm2", "%mm3" |
destinyXfate | 2:0e2ef1edf01b | 3972 | , "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 3973 | #endif |
destinyXfate | 2:0e2ef1edf01b | 3974 | ); |
destinyXfate | 2:0e2ef1edf01b | 3975 | } |
destinyXfate | 2:0e2ef1edf01b | 3976 | break; // end 6 bpp |
destinyXfate | 2:0e2ef1edf01b | 3977 | |
destinyXfate | 2:0e2ef1edf01b | 3978 | case 4: |
destinyXfate | 2:0e2ef1edf01b | 3979 | { |
destinyXfate | 2:0e2ef1edf01b | 3980 | _ActiveMask.use = 0x00000000ffffffffLL; |
destinyXfate | 2:0e2ef1edf01b | 3981 | |
destinyXfate | 2:0e2ef1edf01b | 3982 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 3983 | "movl _dif, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3984 | // preload "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3985 | // preload "movl prev_row, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3986 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3987 | // prime the pump: load the first Raw(x-bpp) data set |
destinyXfate | 2:0e2ef1edf01b | 3988 | "movq -8(%%edi,%%ecx,), %%mm1 \n\t" // only time should need to read |
destinyXfate | 2:0e2ef1edf01b | 3989 | // a=Raw(x-bpp) bytes |
destinyXfate | 2:0e2ef1edf01b | 3990 | "paeth_4lp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3991 | // do first set of 4 bytes |
destinyXfate | 2:0e2ef1edf01b | 3992 | "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // read c=Prior(x-bpp) bytes |
destinyXfate | 2:0e2ef1edf01b | 3993 | "punpckhbw %%mm0, %%mm1 \n\t" // unpack Low bytes of a |
destinyXfate | 2:0e2ef1edf01b | 3994 | "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 3995 | "punpcklbw %%mm0, %%mm2 \n\t" // unpack High bytes of b |
destinyXfate | 2:0e2ef1edf01b | 3996 | // pav = p - a = (a + b - c) - a = b - c |
destinyXfate | 2:0e2ef1edf01b | 3997 | "movq %%mm2, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 3998 | "punpckhbw %%mm0, %%mm3 \n\t" // unpack High bytes of c |
destinyXfate | 2:0e2ef1edf01b | 3999 | // pbv = p - b = (a + b - c) - b = a - c |
destinyXfate | 2:0e2ef1edf01b | 4000 | "movq %%mm1, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4001 | "psubw %%mm3, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4002 | "pxor %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4003 | // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 4004 | "movq %%mm4, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4005 | "psubw %%mm3, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4006 | // pa = abs(p-a) = abs(pav) |
destinyXfate | 2:0e2ef1edf01b | 4007 | // pb = abs(p-b) = abs(pbv) |
destinyXfate | 2:0e2ef1edf01b | 4008 | // pc = abs(p-c) = abs(pcv) |
destinyXfate | 2:0e2ef1edf01b | 4009 | "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 4010 | "paddw %%mm5, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4011 | "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 4012 | "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 4013 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4014 | "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 |
destinyXfate | 2:0e2ef1edf01b | 4015 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4016 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4017 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4018 | "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 4019 | "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 4020 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4021 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4022 | // test pa <= pb |
destinyXfate | 2:0e2ef1edf01b | 4023 | "movq %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4024 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4025 | "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? |
destinyXfate | 2:0e2ef1edf01b | 4026 | "movq %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4027 | // use mm7 mask to merge pa & pb |
destinyXfate | 2:0e2ef1edf01b | 4028 | "pand %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4029 | // use mm0 mask copy to merge a & b |
destinyXfate | 2:0e2ef1edf01b | 4030 | "pand %%mm0, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4031 | "pandn %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4032 | "pandn %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4033 | "paddw %%mm5, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4034 | "paddw %%mm2, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4035 | // test ((pa <= pb)? pa:pb) <= pc |
destinyXfate | 2:0e2ef1edf01b | 4036 | "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? |
destinyXfate | 2:0e2ef1edf01b | 4037 | "pxor %%mm1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4038 | "pand %%mm7, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4039 | "pandn %%mm0, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4040 | "paddw %%mm3, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4041 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4042 | "packuswb %%mm1, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4043 | "movq (%%esi,%%ecx,), %%mm3 \n\t" // load c=Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4044 | "pand _ActiveMask, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4045 | "movq %%mm3, %%mm2 \n\t" // load b=Prior(x) step 1 |
destinyXfate | 2:0e2ef1edf01b | 4046 | "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor with Raw(x) |
destinyXfate | 2:0e2ef1edf01b | 4047 | "punpcklbw %%mm0, %%mm3 \n\t" // unpack High bytes of c |
destinyXfate | 2:0e2ef1edf01b | 4048 | "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value |
destinyXfate | 2:0e2ef1edf01b | 4049 | "movq %%mm7, %%mm1 \n\t" // now mm1 will be used as Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4050 | // do second set of 4 bytes |
destinyXfate | 2:0e2ef1edf01b | 4051 | "punpckhbw %%mm0, %%mm2 \n\t" // unpack Low bytes of b |
destinyXfate | 2:0e2ef1edf01b | 4052 | "punpcklbw %%mm0, %%mm1 \n\t" // unpack Low bytes of a |
destinyXfate | 2:0e2ef1edf01b | 4053 | // pav = p - a = (a + b - c) - a = b - c |
destinyXfate | 2:0e2ef1edf01b | 4054 | "movq %%mm2, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4055 | // pbv = p - b = (a + b - c) - b = a - c |
destinyXfate | 2:0e2ef1edf01b | 4056 | "movq %%mm1, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4057 | "psubw %%mm3, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4058 | "pxor %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4059 | // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 4060 | "movq %%mm4, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4061 | "psubw %%mm3, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4062 | // pa = abs(p-a) = abs(pav) |
destinyXfate | 2:0e2ef1edf01b | 4063 | // pb = abs(p-b) = abs(pbv) |
destinyXfate | 2:0e2ef1edf01b | 4064 | // pc = abs(p-c) = abs(pcv) |
destinyXfate | 2:0e2ef1edf01b | 4065 | "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 4066 | "paddw %%mm5, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4067 | "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 4068 | "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 4069 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4070 | "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 |
destinyXfate | 2:0e2ef1edf01b | 4071 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4072 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4073 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4074 | "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 4075 | "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 4076 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4077 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4078 | // test pa <= pb |
destinyXfate | 2:0e2ef1edf01b | 4079 | "movq %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4080 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4081 | "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? |
destinyXfate | 2:0e2ef1edf01b | 4082 | "movq %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4083 | // use mm7 mask to merge pa & pb |
destinyXfate | 2:0e2ef1edf01b | 4084 | "pand %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4085 | // use mm0 mask copy to merge a & b |
destinyXfate | 2:0e2ef1edf01b | 4086 | "pand %%mm0, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4087 | "pandn %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4088 | "pandn %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4089 | "paddw %%mm5, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4090 | "paddw %%mm2, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4091 | // test ((pa <= pb)? pa:pb) <= pc |
destinyXfate | 2:0e2ef1edf01b | 4092 | "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? |
destinyXfate | 2:0e2ef1edf01b | 4093 | "pxor %%mm1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4094 | "pand %%mm7, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4095 | "pandn %%mm0, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4096 | "pxor %%mm1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4097 | "paddw %%mm3, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4098 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4099 | // step ecx to next set of 8 bytes and repeat loop til done |
destinyXfate | 2:0e2ef1edf01b | 4100 | "addl $8, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4101 | "packuswb %%mm7, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4102 | "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" // add predictor with Raw(x) |
destinyXfate | 2:0e2ef1edf01b | 4103 | "cmpl _MMXLength, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4104 | "movq %%mm1, -8(%%edi,%%ecx,) \n\t" // write back updated value |
destinyXfate | 2:0e2ef1edf01b | 4105 | // mm1 will be used as Raw(x-bpp) next loop |
destinyXfate | 2:0e2ef1edf01b | 4106 | "jb paeth_4lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4107 | |
destinyXfate | 2:0e2ef1edf01b | 4108 | : "=S" (dummy_value_S), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 4109 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 4110 | |
destinyXfate | 2:0e2ef1edf01b | 4111 | : "0" (prev_row), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 4112 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 4113 | |
destinyXfate | 2:0e2ef1edf01b | 4114 | : "%ecx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 4115 | #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 4116 | , "%mm0", "%mm1", "%mm2", "%mm3" |
destinyXfate | 2:0e2ef1edf01b | 4117 | , "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 4118 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4119 | ); |
destinyXfate | 2:0e2ef1edf01b | 4120 | } |
destinyXfate | 2:0e2ef1edf01b | 4121 | break; // end 4 bpp |
destinyXfate | 2:0e2ef1edf01b | 4122 | |
destinyXfate | 2:0e2ef1edf01b | 4123 | case 8: // bpp == 8 |
destinyXfate | 2:0e2ef1edf01b | 4124 | { |
destinyXfate | 2:0e2ef1edf01b | 4125 | _ActiveMask.use = 0x00000000ffffffffLL; |
destinyXfate | 2:0e2ef1edf01b | 4126 | |
destinyXfate | 2:0e2ef1edf01b | 4127 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 4128 | "movl _dif, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4129 | // preload "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4130 | // preload "movl prev_row, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4131 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4132 | // prime the pump: load the first Raw(x-bpp) data set |
destinyXfate | 2:0e2ef1edf01b | 4133 | "movq -8(%%edi,%%ecx,), %%mm1 \n\t" // only time should need to read |
destinyXfate | 2:0e2ef1edf01b | 4134 | // a=Raw(x-bpp) bytes |
destinyXfate | 2:0e2ef1edf01b | 4135 | "paeth_8lp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4136 | // do first set of 4 bytes |
destinyXfate | 2:0e2ef1edf01b | 4137 | "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // read c=Prior(x-bpp) bytes |
destinyXfate | 2:0e2ef1edf01b | 4138 | "punpcklbw %%mm0, %%mm1 \n\t" // unpack Low bytes of a |
destinyXfate | 2:0e2ef1edf01b | 4139 | "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 4140 | "punpcklbw %%mm0, %%mm2 \n\t" // unpack Low bytes of b |
destinyXfate | 2:0e2ef1edf01b | 4141 | // pav = p - a = (a + b - c) - a = b - c |
destinyXfate | 2:0e2ef1edf01b | 4142 | "movq %%mm2, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4143 | "punpcklbw %%mm0, %%mm3 \n\t" // unpack Low bytes of c |
destinyXfate | 2:0e2ef1edf01b | 4144 | // pbv = p - b = (a + b - c) - b = a - c |
destinyXfate | 2:0e2ef1edf01b | 4145 | "movq %%mm1, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4146 | "psubw %%mm3, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4147 | "pxor %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4148 | // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 4149 | "movq %%mm4, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4150 | "psubw %%mm3, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4151 | // pa = abs(p-a) = abs(pav) |
destinyXfate | 2:0e2ef1edf01b | 4152 | // pb = abs(p-b) = abs(pbv) |
destinyXfate | 2:0e2ef1edf01b | 4153 | // pc = abs(p-c) = abs(pcv) |
destinyXfate | 2:0e2ef1edf01b | 4154 | "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 4155 | "paddw %%mm5, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4156 | "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 4157 | "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 4158 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4159 | "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 |
destinyXfate | 2:0e2ef1edf01b | 4160 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4161 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4162 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4163 | "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 4164 | "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 4165 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4166 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4167 | // test pa <= pb |
destinyXfate | 2:0e2ef1edf01b | 4168 | "movq %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4169 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4170 | "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? |
destinyXfate | 2:0e2ef1edf01b | 4171 | "movq %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4172 | // use mm7 mask to merge pa & pb |
destinyXfate | 2:0e2ef1edf01b | 4173 | "pand %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4174 | // use mm0 mask copy to merge a & b |
destinyXfate | 2:0e2ef1edf01b | 4175 | "pand %%mm0, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4176 | "pandn %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4177 | "pandn %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4178 | "paddw %%mm5, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4179 | "paddw %%mm2, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4180 | // test ((pa <= pb)? pa:pb) <= pc |
destinyXfate | 2:0e2ef1edf01b | 4181 | "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? |
destinyXfate | 2:0e2ef1edf01b | 4182 | "pxor %%mm1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4183 | "pand %%mm7, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4184 | "pandn %%mm0, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4185 | "paddw %%mm3, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4186 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4187 | "packuswb %%mm1, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4188 | "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // read c=Prior(x-bpp) bytes |
destinyXfate | 2:0e2ef1edf01b | 4189 | "pand _ActiveMask, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4190 | "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 4191 | "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor with Raw(x) |
destinyXfate | 2:0e2ef1edf01b | 4192 | "punpckhbw %%mm0, %%mm3 \n\t" // unpack High bytes of c |
destinyXfate | 2:0e2ef1edf01b | 4193 | "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value |
destinyXfate | 2:0e2ef1edf01b | 4194 | "movq -8(%%edi,%%ecx,), %%mm1 \n\t" // read a=Raw(x-bpp) bytes |
destinyXfate | 2:0e2ef1edf01b | 4195 | |
destinyXfate | 2:0e2ef1edf01b | 4196 | // do second set of 4 bytes |
destinyXfate | 2:0e2ef1edf01b | 4197 | "punpckhbw %%mm0, %%mm2 \n\t" // unpack High bytes of b |
destinyXfate | 2:0e2ef1edf01b | 4198 | "punpckhbw %%mm0, %%mm1 \n\t" // unpack High bytes of a |
destinyXfate | 2:0e2ef1edf01b | 4199 | // pav = p - a = (a + b - c) - a = b - c |
destinyXfate | 2:0e2ef1edf01b | 4200 | "movq %%mm2, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4201 | // pbv = p - b = (a + b - c) - b = a - c |
destinyXfate | 2:0e2ef1edf01b | 4202 | "movq %%mm1, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4203 | "psubw %%mm3, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4204 | "pxor %%mm7, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4205 | // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 4206 | "movq %%mm4, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4207 | "psubw %%mm3, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4208 | // pa = abs(p-a) = abs(pav) |
destinyXfate | 2:0e2ef1edf01b | 4209 | // pb = abs(p-b) = abs(pbv) |
destinyXfate | 2:0e2ef1edf01b | 4210 | // pc = abs(p-c) = abs(pcv) |
destinyXfate | 2:0e2ef1edf01b | 4211 | "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 4212 | "paddw %%mm5, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4213 | "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 4214 | "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 4215 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4216 | "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 |
destinyXfate | 2:0e2ef1edf01b | 4217 | "psubw %%mm0, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4218 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4219 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4220 | "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 |
destinyXfate | 2:0e2ef1edf01b | 4221 | "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 |
destinyXfate | 2:0e2ef1edf01b | 4222 | "psubw %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4223 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4224 | // test pa <= pb |
destinyXfate | 2:0e2ef1edf01b | 4225 | "movq %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4226 | "psubw %%mm0, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4227 | "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? |
destinyXfate | 2:0e2ef1edf01b | 4228 | "movq %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4229 | // use mm7 mask to merge pa & pb |
destinyXfate | 2:0e2ef1edf01b | 4230 | "pand %%mm7, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4231 | // use mm0 mask copy to merge a & b |
destinyXfate | 2:0e2ef1edf01b | 4232 | "pand %%mm0, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4233 | "pandn %%mm4, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4234 | "pandn %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4235 | "paddw %%mm5, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4236 | "paddw %%mm2, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4237 | // test ((pa <= pb)? pa:pb) <= pc |
destinyXfate | 2:0e2ef1edf01b | 4238 | "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? |
destinyXfate | 2:0e2ef1edf01b | 4239 | "pxor %%mm1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4240 | "pand %%mm7, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4241 | "pandn %%mm0, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4242 | "pxor %%mm1, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4243 | "paddw %%mm3, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4244 | "pxor %%mm0, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4245 | // step ecx to next set of 8 bytes and repeat loop til done |
destinyXfate | 2:0e2ef1edf01b | 4246 | "addl $8, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4247 | "packuswb %%mm7, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4248 | "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" // add Paeth predictor with Raw(x) |
destinyXfate | 2:0e2ef1edf01b | 4249 | "cmpl _MMXLength, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4250 | "movq %%mm1, -8(%%edi,%%ecx,) \n\t" // write back updated value |
destinyXfate | 2:0e2ef1edf01b | 4251 | // mm1 will be used as Raw(x-bpp) next loop |
destinyXfate | 2:0e2ef1edf01b | 4252 | "jb paeth_8lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4253 | |
destinyXfate | 2:0e2ef1edf01b | 4254 | : "=S" (dummy_value_S), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 4255 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 4256 | |
destinyXfate | 2:0e2ef1edf01b | 4257 | : "0" (prev_row), // esi // input regs |
destinyXfate | 2:0e2ef1edf01b | 4258 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 4259 | |
destinyXfate | 2:0e2ef1edf01b | 4260 | : "%ecx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 4261 | #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 4262 | , "%mm0", "%mm1", "%mm2", "%mm3" |
destinyXfate | 2:0e2ef1edf01b | 4263 | , "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 4264 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4265 | ); |
destinyXfate | 2:0e2ef1edf01b | 4266 | } |
destinyXfate | 2:0e2ef1edf01b | 4267 | break; // end 8 bpp |
destinyXfate | 2:0e2ef1edf01b | 4268 | |
destinyXfate | 2:0e2ef1edf01b | 4269 | case 1: // bpp = 1 |
destinyXfate | 2:0e2ef1edf01b | 4270 | case 2: // bpp = 2 |
destinyXfate | 2:0e2ef1edf01b | 4271 | default: // bpp > 8 |
destinyXfate | 2:0e2ef1edf01b | 4272 | { |
destinyXfate | 2:0e2ef1edf01b | 4273 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 4274 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 4275 | "pushl %%ebx \n\t" // save Global Offset Table index |
destinyXfate | 2:0e2ef1edf01b | 4276 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4277 | "movl _dif, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4278 | "cmpl _FullLength, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4279 | "jnb paeth_dend \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4280 | |
destinyXfate | 2:0e2ef1edf01b | 4281 | // preload "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4282 | // preload "movl prev_row, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4283 | // do Paeth decode for remaining bytes |
destinyXfate | 2:0e2ef1edf01b | 4284 | "movl %%ebx, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4285 | // preload "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx) |
destinyXfate | 2:0e2ef1edf01b | 4286 | "subl %%ecx, %%edx \n\t" // edx = ebx - bpp |
destinyXfate | 2:0e2ef1edf01b | 4287 | "xorl %%ecx, %%ecx \n\t" // zero ecx before using cl & cx |
destinyXfate | 2:0e2ef1edf01b | 4288 | |
destinyXfate | 2:0e2ef1edf01b | 4289 | "paeth_dlp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4290 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4291 | // pav = p - a = (a + b - c) - a = b - c |
destinyXfate | 2:0e2ef1edf01b | 4292 | "movb (%%esi,%%ebx,), %%al \n\t" // load Prior(x) into al |
destinyXfate | 2:0e2ef1edf01b | 4293 | "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl |
destinyXfate | 2:0e2ef1edf01b | 4294 | "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4295 | "movl %%eax, _patemp \n\t" // Save pav for later use |
destinyXfate | 2:0e2ef1edf01b | 4296 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4297 | // pbv = p - b = (a + b - c) - b = a - c |
destinyXfate | 2:0e2ef1edf01b | 4298 | "movb (%%edi,%%edx,), %%al \n\t" // load Raw(x-bpp) into al |
destinyXfate | 2:0e2ef1edf01b | 4299 | "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4300 | "movl %%eax, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4301 | // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 4302 | "addl _patemp, %%eax \n\t" // pcv = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 4303 | // pc = abs(pcv) |
destinyXfate | 2:0e2ef1edf01b | 4304 | "testl $0x80000000, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4305 | "jz paeth_dpca \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4306 | "negl %%eax \n\t" // reverse sign of neg values |
destinyXfate | 2:0e2ef1edf01b | 4307 | |
destinyXfate | 2:0e2ef1edf01b | 4308 | "paeth_dpca: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4309 | "movl %%eax, _pctemp \n\t" // save pc for later use |
destinyXfate | 2:0e2ef1edf01b | 4310 | // pb = abs(pbv) |
destinyXfate | 2:0e2ef1edf01b | 4311 | "testl $0x80000000, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4312 | "jz paeth_dpba \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4313 | "negl %%ecx \n\t" // reverse sign of neg values |
destinyXfate | 2:0e2ef1edf01b | 4314 | |
destinyXfate | 2:0e2ef1edf01b | 4315 | "paeth_dpba: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4316 | "movl %%ecx, _pbtemp \n\t" // save pb for later use |
destinyXfate | 2:0e2ef1edf01b | 4317 | // pa = abs(pav) |
destinyXfate | 2:0e2ef1edf01b | 4318 | "movl _patemp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4319 | "testl $0x80000000, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4320 | "jz paeth_dpaa \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4321 | "negl %%eax \n\t" // reverse sign of neg values |
destinyXfate | 2:0e2ef1edf01b | 4322 | |
destinyXfate | 2:0e2ef1edf01b | 4323 | "paeth_dpaa: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4324 | "movl %%eax, _patemp \n\t" // save pa for later use |
destinyXfate | 2:0e2ef1edf01b | 4325 | // test if pa <= pb |
destinyXfate | 2:0e2ef1edf01b | 4326 | "cmpl %%ecx, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4327 | "jna paeth_dabb \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4328 | // pa > pb; now test if pb <= pc |
destinyXfate | 2:0e2ef1edf01b | 4329 | "cmpl _pctemp, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4330 | "jna paeth_dbbc \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4331 | // pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4332 | "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl |
destinyXfate | 2:0e2ef1edf01b | 4333 | "jmp paeth_dpaeth \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4334 | |
destinyXfate | 2:0e2ef1edf01b | 4335 | "paeth_dbbc: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4336 | // pb <= pc; Raw(x) = Paeth(x) + Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 4337 | "movb (%%esi,%%ebx,), %%cl \n\t" // load Prior(x) into cl |
destinyXfate | 2:0e2ef1edf01b | 4338 | "jmp paeth_dpaeth \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4339 | |
destinyXfate | 2:0e2ef1edf01b | 4340 | "paeth_dabb: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4341 | // pa <= pb; now test if pa <= pc |
destinyXfate | 2:0e2ef1edf01b | 4342 | "cmpl _pctemp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4343 | "jna paeth_dabc \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4344 | // pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4345 | "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl |
destinyXfate | 2:0e2ef1edf01b | 4346 | "jmp paeth_dpaeth \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4347 | |
destinyXfate | 2:0e2ef1edf01b | 4348 | "paeth_dabc: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4349 | // pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4350 | "movb (%%edi,%%edx,), %%cl \n\t" // load Raw(x-bpp) into cl |
destinyXfate | 2:0e2ef1edf01b | 4351 | |
destinyXfate | 2:0e2ef1edf01b | 4352 | "paeth_dpaeth: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4353 | "incl %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4354 | "incl %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4355 | // Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256 |
destinyXfate | 2:0e2ef1edf01b | 4356 | "addb %%cl, -1(%%edi,%%ebx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4357 | "cmpl _FullLength, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4358 | "jb paeth_dlp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4359 | |
destinyXfate | 2:0e2ef1edf01b | 4360 | "paeth_dend: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4361 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 4362 | "popl %%ebx \n\t" // index to Global Offset Table |
destinyXfate | 2:0e2ef1edf01b | 4363 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4364 | |
destinyXfate | 2:0e2ef1edf01b | 4365 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 4366 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 4367 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 4368 | |
destinyXfate | 2:0e2ef1edf01b | 4369 | : "0" (bpp), // ecx // input regs |
destinyXfate | 2:0e2ef1edf01b | 4370 | "1" (prev_row), // esi |
destinyXfate | 2:0e2ef1edf01b | 4371 | "2" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 4372 | |
destinyXfate | 2:0e2ef1edf01b | 4373 | : "%eax", "%edx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 4374 | #ifndef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 4375 | , "%ebx" |
destinyXfate | 2:0e2ef1edf01b | 4376 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4377 | ); |
destinyXfate | 2:0e2ef1edf01b | 4378 | } |
destinyXfate | 2:0e2ef1edf01b | 4379 | return; // No need to go further with this one |
destinyXfate | 2:0e2ef1edf01b | 4380 | |
destinyXfate | 2:0e2ef1edf01b | 4381 | } // end switch (bpp) |
destinyXfate | 2:0e2ef1edf01b | 4382 | |
destinyXfate | 2:0e2ef1edf01b | 4383 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 4384 | // MMX acceleration complete; now do clean-up |
destinyXfate | 2:0e2ef1edf01b | 4385 | // check if any remaining bytes left to decode |
destinyXfate | 2:0e2ef1edf01b | 4386 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 4387 | "pushl %%ebx \n\t" // save index to Global Offset Table |
destinyXfate | 2:0e2ef1edf01b | 4388 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4389 | "movl _MMXLength, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4390 | "cmpl _FullLength, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4391 | "jnb paeth_end \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4392 | //pre "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4393 | //pre "movl prev_row, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4394 | // do Paeth decode for remaining bytes |
destinyXfate | 2:0e2ef1edf01b | 4395 | "movl %%ebx, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4396 | //pre "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx) |
destinyXfate | 2:0e2ef1edf01b | 4397 | "subl %%ecx, %%edx \n\t" // edx = ebx - bpp |
destinyXfate | 2:0e2ef1edf01b | 4398 | "xorl %%ecx, %%ecx \n\t" // zero ecx before using cl & cx below |
destinyXfate | 2:0e2ef1edf01b | 4399 | |
destinyXfate | 2:0e2ef1edf01b | 4400 | "paeth_lp2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4401 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4402 | // pav = p - a = (a + b - c) - a = b - c |
destinyXfate | 2:0e2ef1edf01b | 4403 | "movb (%%esi,%%ebx,), %%al \n\t" // load Prior(x) into al |
destinyXfate | 2:0e2ef1edf01b | 4404 | "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl |
destinyXfate | 2:0e2ef1edf01b | 4405 | "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4406 | "movl %%eax, _patemp \n\t" // Save pav for later use |
destinyXfate | 2:0e2ef1edf01b | 4407 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4408 | // pbv = p - b = (a + b - c) - b = a - c |
destinyXfate | 2:0e2ef1edf01b | 4409 | "movb (%%edi,%%edx,), %%al \n\t" // load Raw(x-bpp) into al |
destinyXfate | 2:0e2ef1edf01b | 4410 | "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4411 | "movl %%eax, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4412 | // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 4413 | "addl _patemp, %%eax \n\t" // pcv = pav + pbv |
destinyXfate | 2:0e2ef1edf01b | 4414 | // pc = abs(pcv) |
destinyXfate | 2:0e2ef1edf01b | 4415 | "testl $0x80000000, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4416 | "jz paeth_pca2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4417 | "negl %%eax \n\t" // reverse sign of neg values |
destinyXfate | 2:0e2ef1edf01b | 4418 | |
destinyXfate | 2:0e2ef1edf01b | 4419 | "paeth_pca2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4420 | "movl %%eax, _pctemp \n\t" // save pc for later use |
destinyXfate | 2:0e2ef1edf01b | 4421 | // pb = abs(pbv) |
destinyXfate | 2:0e2ef1edf01b | 4422 | "testl $0x80000000, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4423 | "jz paeth_pba2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4424 | "negl %%ecx \n\t" // reverse sign of neg values |
destinyXfate | 2:0e2ef1edf01b | 4425 | |
destinyXfate | 2:0e2ef1edf01b | 4426 | "paeth_pba2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4427 | "movl %%ecx, _pbtemp \n\t" // save pb for later use |
destinyXfate | 2:0e2ef1edf01b | 4428 | // pa = abs(pav) |
destinyXfate | 2:0e2ef1edf01b | 4429 | "movl _patemp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4430 | "testl $0x80000000, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4431 | "jz paeth_paa2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4432 | "negl %%eax \n\t" // reverse sign of neg values |
destinyXfate | 2:0e2ef1edf01b | 4433 | |
destinyXfate | 2:0e2ef1edf01b | 4434 | "paeth_paa2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4435 | "movl %%eax, _patemp \n\t" // save pa for later use |
destinyXfate | 2:0e2ef1edf01b | 4436 | // test if pa <= pb |
destinyXfate | 2:0e2ef1edf01b | 4437 | "cmpl %%ecx, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4438 | "jna paeth_abb2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4439 | // pa > pb; now test if pb <= pc |
destinyXfate | 2:0e2ef1edf01b | 4440 | "cmpl _pctemp, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4441 | "jna paeth_bbc2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4442 | // pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4443 | "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl |
destinyXfate | 2:0e2ef1edf01b | 4444 | "jmp paeth_paeth2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4445 | |
destinyXfate | 2:0e2ef1edf01b | 4446 | "paeth_bbc2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4447 | // pb <= pc; Raw(x) = Paeth(x) + Prior(x) |
destinyXfate | 2:0e2ef1edf01b | 4448 | "movb (%%esi,%%ebx,), %%cl \n\t" // load Prior(x) into cl |
destinyXfate | 2:0e2ef1edf01b | 4449 | "jmp paeth_paeth2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4450 | |
destinyXfate | 2:0e2ef1edf01b | 4451 | "paeth_abb2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4452 | // pa <= pb; now test if pa <= pc |
destinyXfate | 2:0e2ef1edf01b | 4453 | "cmpl _pctemp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4454 | "jna paeth_abc2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4455 | // pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4456 | "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl |
destinyXfate | 2:0e2ef1edf01b | 4457 | "jmp paeth_paeth2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4458 | |
destinyXfate | 2:0e2ef1edf01b | 4459 | "paeth_abc2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4460 | // pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4461 | "movb (%%edi,%%edx,), %%cl \n\t" // load Raw(x-bpp) into cl |
destinyXfate | 2:0e2ef1edf01b | 4462 | |
destinyXfate | 2:0e2ef1edf01b | 4463 | "paeth_paeth2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4464 | "incl %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4465 | "incl %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4466 | // Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256 |
destinyXfate | 2:0e2ef1edf01b | 4467 | "addb %%cl, -1(%%edi,%%ebx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4468 | "cmpl _FullLength, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4469 | "jb paeth_lp2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4470 | |
destinyXfate | 2:0e2ef1edf01b | 4471 | "paeth_end: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4472 | "EMMS \n\t" // end MMX; prep for poss. FP instrs. |
destinyXfate | 2:0e2ef1edf01b | 4473 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 4474 | "popl %%ebx \n\t" // restore index to Global Offset Table |
destinyXfate | 2:0e2ef1edf01b | 4475 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4476 | |
destinyXfate | 2:0e2ef1edf01b | 4477 | : "=c" (dummy_value_c), // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 4478 | "=S" (dummy_value_S), |
destinyXfate | 2:0e2ef1edf01b | 4479 | "=D" (dummy_value_D) |
destinyXfate | 2:0e2ef1edf01b | 4480 | |
destinyXfate | 2:0e2ef1edf01b | 4481 | : "0" (bpp), // ecx // input regs |
destinyXfate | 2:0e2ef1edf01b | 4482 | "1" (prev_row), // esi |
destinyXfate | 2:0e2ef1edf01b | 4483 | "2" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 4484 | |
destinyXfate | 2:0e2ef1edf01b | 4485 | : "%eax", "%edx" // clobber list (no input regs!) |
destinyXfate | 2:0e2ef1edf01b | 4486 | #ifndef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 4487 | , "%ebx" |
destinyXfate | 2:0e2ef1edf01b | 4488 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4489 | ); |
destinyXfate | 2:0e2ef1edf01b | 4490 | |
destinyXfate | 2:0e2ef1edf01b | 4491 | } /* end png_read_filter_row_mmx_paeth() */ |
destinyXfate | 2:0e2ef1edf01b | 4492 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4493 | |
destinyXfate | 2:0e2ef1edf01b | 4494 | |
destinyXfate | 2:0e2ef1edf01b | 4495 | |
destinyXfate | 2:0e2ef1edf01b | 4496 | |
destinyXfate | 2:0e2ef1edf01b | 4497 | #ifdef PNG_THREAD_UNSAFE_OK |
destinyXfate | 2:0e2ef1edf01b | 4498 | //===========================================================================// |
destinyXfate | 2:0e2ef1edf01b | 4499 | // // |
destinyXfate | 2:0e2ef1edf01b | 4500 | // P N G _ R E A D _ F I L T E R _ R O W _ M M X _ S U B // |
destinyXfate | 2:0e2ef1edf01b | 4501 | // // |
destinyXfate | 2:0e2ef1edf01b | 4502 | //===========================================================================// |
destinyXfate | 2:0e2ef1edf01b | 4503 | |
destinyXfate | 2:0e2ef1edf01b | 4504 | // Optimized code for PNG Sub filter decoder |
destinyXfate | 2:0e2ef1edf01b | 4505 | |
destinyXfate | 2:0e2ef1edf01b | 4506 | static void /* PRIVATE */ |
destinyXfate | 2:0e2ef1edf01b | 4507 | png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) |
destinyXfate | 2:0e2ef1edf01b | 4508 | { |
destinyXfate | 2:0e2ef1edf01b | 4509 | int bpp; |
destinyXfate | 2:0e2ef1edf01b | 4510 | int dummy_value_a; |
destinyXfate | 2:0e2ef1edf01b | 4511 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 4512 | |
destinyXfate | 2:0e2ef1edf01b | 4513 | bpp = (row_info->pixel_depth + 7) >> 3; // calc number of bytes per pixel |
destinyXfate | 2:0e2ef1edf01b | 4514 | _FullLength = row_info->rowbytes - bpp; // number of bytes to filter |
destinyXfate | 2:0e2ef1edf01b | 4515 | |
destinyXfate | 2:0e2ef1edf01b | 4516 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 4517 | //pre "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4518 | "movl %%edi, %%esi \n\t" // lp = row |
destinyXfate | 2:0e2ef1edf01b | 4519 | //pre "movl bpp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4520 | "addl %%eax, %%edi \n\t" // rp = row + bpp |
destinyXfate | 2:0e2ef1edf01b | 4521 | //irr "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4522 | // get # of bytes to alignment |
destinyXfate | 2:0e2ef1edf01b | 4523 | "movl %%edi, _dif \n\t" // take start of row |
destinyXfate | 2:0e2ef1edf01b | 4524 | "addl $0xf, _dif \n\t" // add 7 + 8 to incr past |
destinyXfate | 2:0e2ef1edf01b | 4525 | // alignment boundary |
destinyXfate | 2:0e2ef1edf01b | 4526 | "xorl %%ecx, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4527 | "andl $0xfffffff8, _dif \n\t" // mask to alignment boundary |
destinyXfate | 2:0e2ef1edf01b | 4528 | "subl %%edi, _dif \n\t" // subtract from start ==> value |
destinyXfate | 2:0e2ef1edf01b | 4529 | "jz sub_go \n\t" // ecx at alignment |
destinyXfate | 2:0e2ef1edf01b | 4530 | |
destinyXfate | 2:0e2ef1edf01b | 4531 | "sub_lp1: \n\t" // fix alignment |
destinyXfate | 2:0e2ef1edf01b | 4532 | "movb (%%esi,%%ecx,), %%al \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4533 | "addb %%al, (%%edi,%%ecx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4534 | "incl %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4535 | "cmpl _dif, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4536 | "jb sub_lp1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4537 | |
destinyXfate | 2:0e2ef1edf01b | 4538 | "sub_go: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4539 | "movl _FullLength, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4540 | "movl %%eax, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4541 | "subl %%ecx, %%edx \n\t" // subtract alignment fix |
destinyXfate | 2:0e2ef1edf01b | 4542 | "andl $0x00000007, %%edx \n\t" // calc bytes over mult of 8 |
destinyXfate | 2:0e2ef1edf01b | 4543 | "subl %%edx, %%eax \n\t" // drop over bytes from length |
destinyXfate | 2:0e2ef1edf01b | 4544 | "movl %%eax, _MMXLength \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4545 | |
destinyXfate | 2:0e2ef1edf01b | 4546 | : "=a" (dummy_value_a), // 0 // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 4547 | "=D" (dummy_value_D) // 1 |
destinyXfate | 2:0e2ef1edf01b | 4548 | |
destinyXfate | 2:0e2ef1edf01b | 4549 | : "0" (bpp), // eax // input regs |
destinyXfate | 2:0e2ef1edf01b | 4550 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 4551 | |
destinyXfate | 2:0e2ef1edf01b | 4552 | : "%esi", "%ecx", "%edx" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 4553 | |
destinyXfate | 2:0e2ef1edf01b | 4554 | #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 4555 | , "%mm0", "%mm1", "%mm2", "%mm3" |
destinyXfate | 2:0e2ef1edf01b | 4556 | , "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 4557 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4558 | ); |
destinyXfate | 2:0e2ef1edf01b | 4559 | |
destinyXfate | 2:0e2ef1edf01b | 4560 | // now do the math for the rest of the row |
destinyXfate | 2:0e2ef1edf01b | 4561 | switch (bpp) |
destinyXfate | 2:0e2ef1edf01b | 4562 | { |
destinyXfate | 2:0e2ef1edf01b | 4563 | case 3: |
destinyXfate | 2:0e2ef1edf01b | 4564 | { |
destinyXfate | 2:0e2ef1edf01b | 4565 | _ActiveMask.use = 0x0000ffffff000000LL; |
destinyXfate | 2:0e2ef1edf01b | 4566 | _ShiftBpp.use = 24; // == 3 * 8 |
destinyXfate | 2:0e2ef1edf01b | 4567 | _ShiftRem.use = 40; // == 64 - 24 |
destinyXfate | 2:0e2ef1edf01b | 4568 | |
destinyXfate | 2:0e2ef1edf01b | 4569 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 4570 | // preload "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4571 | "movq _ActiveMask, %%mm7 \n\t" // load _ActiveMask for 2nd |
destinyXfate | 2:0e2ef1edf01b | 4572 | // active byte group |
destinyXfate | 2:0e2ef1edf01b | 4573 | "movl %%edi, %%esi \n\t" // lp = row |
destinyXfate | 2:0e2ef1edf01b | 4574 | // preload "movl bpp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4575 | "addl %%eax, %%edi \n\t" // rp = row + bpp |
destinyXfate | 2:0e2ef1edf01b | 4576 | "movq %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4577 | "movl _dif, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4578 | "psllq _ShiftBpp, %%mm6 \n\t" // move mask in mm6 to cover |
destinyXfate | 2:0e2ef1edf01b | 4579 | // 3rd active byte group |
destinyXfate | 2:0e2ef1edf01b | 4580 | // prime the pump: load the first Raw(x-bpp) data set |
destinyXfate | 2:0e2ef1edf01b | 4581 | "movq -8(%%edi,%%edx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4582 | |
destinyXfate | 2:0e2ef1edf01b | 4583 | "sub_3lp: \n\t" // shift data for adding first |
destinyXfate | 2:0e2ef1edf01b | 4584 | "psrlq _ShiftRem, %%mm1 \n\t" // bpp bytes (no need for mask; |
destinyXfate | 2:0e2ef1edf01b | 4585 | // shift clears inactive bytes) |
destinyXfate | 2:0e2ef1edf01b | 4586 | // add 1st active group |
destinyXfate | 2:0e2ef1edf01b | 4587 | "movq (%%edi,%%edx,), %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4588 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4589 | |
destinyXfate | 2:0e2ef1edf01b | 4590 | // add 2nd active group |
destinyXfate | 2:0e2ef1edf01b | 4591 | "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1 |
destinyXfate | 2:0e2ef1edf01b | 4592 | "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 4593 | "pand %%mm7, %%mm1 \n\t" // mask to use 2nd active group |
destinyXfate | 2:0e2ef1edf01b | 4594 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4595 | |
destinyXfate | 2:0e2ef1edf01b | 4596 | // add 3rd active group |
destinyXfate | 2:0e2ef1edf01b | 4597 | "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1 |
destinyXfate | 2:0e2ef1edf01b | 4598 | "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 4599 | "pand %%mm6, %%mm1 \n\t" // mask to use 3rd active group |
destinyXfate | 2:0e2ef1edf01b | 4600 | "addl $8, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4601 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4602 | |
destinyXfate | 2:0e2ef1edf01b | 4603 | "cmpl _MMXLength, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4604 | "movq %%mm0, -8(%%edi,%%edx,) \n\t" // write updated Raws to array |
destinyXfate | 2:0e2ef1edf01b | 4605 | "movq %%mm0, %%mm1 \n\t" // prep 1st add at top of loop |
destinyXfate | 2:0e2ef1edf01b | 4606 | "jb sub_3lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4607 | |
destinyXfate | 2:0e2ef1edf01b | 4608 | : "=a" (dummy_value_a), // 0 // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 4609 | "=D" (dummy_value_D) // 1 |
destinyXfate | 2:0e2ef1edf01b | 4610 | |
destinyXfate | 2:0e2ef1edf01b | 4611 | : "0" (bpp), // eax // input regs |
destinyXfate | 2:0e2ef1edf01b | 4612 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 4613 | |
destinyXfate | 2:0e2ef1edf01b | 4614 | : "%edx", "%esi" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 4615 | #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 4616 | , "%mm0", "%mm1", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 4617 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4618 | ); |
destinyXfate | 2:0e2ef1edf01b | 4619 | } |
destinyXfate | 2:0e2ef1edf01b | 4620 | break; |
destinyXfate | 2:0e2ef1edf01b | 4621 | |
destinyXfate | 2:0e2ef1edf01b | 4622 | case 1: |
destinyXfate | 2:0e2ef1edf01b | 4623 | { |
destinyXfate | 2:0e2ef1edf01b | 4624 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 4625 | "movl _dif, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4626 | // preload "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4627 | "cmpl _FullLength, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4628 | "jnb sub_1end \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4629 | "movl %%edi, %%esi \n\t" // lp = row |
destinyXfate | 2:0e2ef1edf01b | 4630 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4631 | // preload "movl bpp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4632 | "addl %%eax, %%edi \n\t" // rp = row + bpp |
destinyXfate | 2:0e2ef1edf01b | 4633 | |
destinyXfate | 2:0e2ef1edf01b | 4634 | "sub_1lp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4635 | "movb (%%esi,%%edx,), %%al \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4636 | "addb %%al, (%%edi,%%edx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4637 | "incl %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4638 | "cmpl _FullLength, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4639 | "jb sub_1lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4640 | |
destinyXfate | 2:0e2ef1edf01b | 4641 | "sub_1end: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4642 | |
destinyXfate | 2:0e2ef1edf01b | 4643 | : "=a" (dummy_value_a), // 0 // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 4644 | "=D" (dummy_value_D) // 1 |
destinyXfate | 2:0e2ef1edf01b | 4645 | |
destinyXfate | 2:0e2ef1edf01b | 4646 | : "0" (bpp), // eax // input regs |
destinyXfate | 2:0e2ef1edf01b | 4647 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 4648 | |
destinyXfate | 2:0e2ef1edf01b | 4649 | : "%edx", "%esi" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 4650 | ); |
destinyXfate | 2:0e2ef1edf01b | 4651 | } |
destinyXfate | 2:0e2ef1edf01b | 4652 | return; |
destinyXfate | 2:0e2ef1edf01b | 4653 | |
destinyXfate | 2:0e2ef1edf01b | 4654 | case 6: |
destinyXfate | 2:0e2ef1edf01b | 4655 | case 4: |
destinyXfate | 2:0e2ef1edf01b | 4656 | //case 7: // GRR BOGUS |
destinyXfate | 2:0e2ef1edf01b | 4657 | //case 5: // GRR BOGUS |
destinyXfate | 2:0e2ef1edf01b | 4658 | { |
destinyXfate | 2:0e2ef1edf01b | 4659 | _ShiftBpp.use = bpp << 3; |
destinyXfate | 2:0e2ef1edf01b | 4660 | _ShiftRem.use = 64 - _ShiftBpp.use; |
destinyXfate | 2:0e2ef1edf01b | 4661 | |
destinyXfate | 2:0e2ef1edf01b | 4662 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 4663 | // preload "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4664 | "movl _dif, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4665 | "movl %%edi, %%esi \n\t" // lp = row |
destinyXfate | 2:0e2ef1edf01b | 4666 | // preload "movl bpp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4667 | "addl %%eax, %%edi \n\t" // rp = row + bpp |
destinyXfate | 2:0e2ef1edf01b | 4668 | |
destinyXfate | 2:0e2ef1edf01b | 4669 | // prime the pump: load the first Raw(x-bpp) data set |
destinyXfate | 2:0e2ef1edf01b | 4670 | "movq -8(%%edi,%%edx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4671 | |
destinyXfate | 2:0e2ef1edf01b | 4672 | "sub_4lp: \n\t" // shift data for adding first |
destinyXfate | 2:0e2ef1edf01b | 4673 | "psrlq _ShiftRem, %%mm1 \n\t" // bpp bytes (no need for mask; |
destinyXfate | 2:0e2ef1edf01b | 4674 | // shift clears inactive bytes) |
destinyXfate | 2:0e2ef1edf01b | 4675 | "movq (%%edi,%%edx,), %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4676 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4677 | |
destinyXfate | 2:0e2ef1edf01b | 4678 | // add 2nd active group |
destinyXfate | 2:0e2ef1edf01b | 4679 | "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1 |
destinyXfate | 2:0e2ef1edf01b | 4680 | "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 4681 | "addl $8, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4682 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4683 | |
destinyXfate | 2:0e2ef1edf01b | 4684 | "cmpl _MMXLength, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4685 | "movq %%mm0, -8(%%edi,%%edx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4686 | "movq %%mm0, %%mm1 \n\t" // prep 1st add at top of loop |
destinyXfate | 2:0e2ef1edf01b | 4687 | "jb sub_4lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4688 | |
destinyXfate | 2:0e2ef1edf01b | 4689 | : "=a" (dummy_value_a), // 0 // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 4690 | "=D" (dummy_value_D) // 1 |
destinyXfate | 2:0e2ef1edf01b | 4691 | |
destinyXfate | 2:0e2ef1edf01b | 4692 | : "0" (bpp), // eax // input regs |
destinyXfate | 2:0e2ef1edf01b | 4693 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 4694 | |
destinyXfate | 2:0e2ef1edf01b | 4695 | : "%edx", "%esi" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 4696 | #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 4697 | , "%mm0", "%mm1" |
destinyXfate | 2:0e2ef1edf01b | 4698 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4699 | ); |
destinyXfate | 2:0e2ef1edf01b | 4700 | } |
destinyXfate | 2:0e2ef1edf01b | 4701 | break; |
destinyXfate | 2:0e2ef1edf01b | 4702 | |
destinyXfate | 2:0e2ef1edf01b | 4703 | case 2: |
destinyXfate | 2:0e2ef1edf01b | 4704 | { |
destinyXfate | 2:0e2ef1edf01b | 4705 | _ActiveMask.use = 0x00000000ffff0000LL; |
destinyXfate | 2:0e2ef1edf01b | 4706 | _ShiftBpp.use = 16; // == 2 * 8 |
destinyXfate | 2:0e2ef1edf01b | 4707 | _ShiftRem.use = 48; // == 64 - 16 |
destinyXfate | 2:0e2ef1edf01b | 4708 | |
destinyXfate | 2:0e2ef1edf01b | 4709 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 4710 | "movq _ActiveMask, %%mm7 \n\t" // load _ActiveMask for 2nd |
destinyXfate | 2:0e2ef1edf01b | 4711 | // active byte group |
destinyXfate | 2:0e2ef1edf01b | 4712 | "movl _dif, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4713 | "movq %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4714 | // preload "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4715 | "psllq _ShiftBpp, %%mm6 \n\t" // move mask in mm6 to cover |
destinyXfate | 2:0e2ef1edf01b | 4716 | // 3rd active byte group |
destinyXfate | 2:0e2ef1edf01b | 4717 | "movl %%edi, %%esi \n\t" // lp = row |
destinyXfate | 2:0e2ef1edf01b | 4718 | "movq %%mm6, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4719 | // preload "movl bpp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4720 | "addl %%eax, %%edi \n\t" // rp = row + bpp |
destinyXfate | 2:0e2ef1edf01b | 4721 | "psllq _ShiftBpp, %%mm5 \n\t" // move mask in mm5 to cover |
destinyXfate | 2:0e2ef1edf01b | 4722 | // 4th active byte group |
destinyXfate | 2:0e2ef1edf01b | 4723 | // prime the pump: load the first Raw(x-bpp) data set |
destinyXfate | 2:0e2ef1edf01b | 4724 | "movq -8(%%edi,%%edx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4725 | |
destinyXfate | 2:0e2ef1edf01b | 4726 | "sub_2lp: \n\t" // shift data for adding first |
destinyXfate | 2:0e2ef1edf01b | 4727 | "psrlq _ShiftRem, %%mm1 \n\t" // bpp bytes (no need for mask; |
destinyXfate | 2:0e2ef1edf01b | 4728 | // shift clears inactive bytes) |
destinyXfate | 2:0e2ef1edf01b | 4729 | // add 1st active group |
destinyXfate | 2:0e2ef1edf01b | 4730 | "movq (%%edi,%%edx,), %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4731 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4732 | |
destinyXfate | 2:0e2ef1edf01b | 4733 | // add 2nd active group |
destinyXfate | 2:0e2ef1edf01b | 4734 | "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1 |
destinyXfate | 2:0e2ef1edf01b | 4735 | "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 4736 | "pand %%mm7, %%mm1 \n\t" // mask to use 2nd active group |
destinyXfate | 2:0e2ef1edf01b | 4737 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4738 | |
destinyXfate | 2:0e2ef1edf01b | 4739 | // add 3rd active group |
destinyXfate | 2:0e2ef1edf01b | 4740 | "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1 |
destinyXfate | 2:0e2ef1edf01b | 4741 | "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 4742 | "pand %%mm6, %%mm1 \n\t" // mask to use 3rd active group |
destinyXfate | 2:0e2ef1edf01b | 4743 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4744 | |
destinyXfate | 2:0e2ef1edf01b | 4745 | // add 4th active group |
destinyXfate | 2:0e2ef1edf01b | 4746 | "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1 |
destinyXfate | 2:0e2ef1edf01b | 4747 | "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly |
destinyXfate | 2:0e2ef1edf01b | 4748 | "pand %%mm5, %%mm1 \n\t" // mask to use 4th active group |
destinyXfate | 2:0e2ef1edf01b | 4749 | "addl $8, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4750 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4751 | "cmpl _MMXLength, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4752 | "movq %%mm0, -8(%%edi,%%edx,) \n\t" // write updated Raws to array |
destinyXfate | 2:0e2ef1edf01b | 4753 | "movq %%mm0, %%mm1 \n\t" // prep 1st add at top of loop |
destinyXfate | 2:0e2ef1edf01b | 4754 | "jb sub_2lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4755 | |
destinyXfate | 2:0e2ef1edf01b | 4756 | : "=a" (dummy_value_a), // 0 // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 4757 | "=D" (dummy_value_D) // 1 |
destinyXfate | 2:0e2ef1edf01b | 4758 | |
destinyXfate | 2:0e2ef1edf01b | 4759 | : "0" (bpp), // eax // input regs |
destinyXfate | 2:0e2ef1edf01b | 4760 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 4761 | |
destinyXfate | 2:0e2ef1edf01b | 4762 | : "%edx", "%esi" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 4763 | #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 4764 | , "%mm0", "%mm1", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 4765 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4766 | ); |
destinyXfate | 2:0e2ef1edf01b | 4767 | } |
destinyXfate | 2:0e2ef1edf01b | 4768 | break; |
destinyXfate | 2:0e2ef1edf01b | 4769 | |
destinyXfate | 2:0e2ef1edf01b | 4770 | case 8: |
destinyXfate | 2:0e2ef1edf01b | 4771 | { |
destinyXfate | 2:0e2ef1edf01b | 4772 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 4773 | // preload "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4774 | "movl _dif, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4775 | "movl %%edi, %%esi \n\t" // lp = row |
destinyXfate | 2:0e2ef1edf01b | 4776 | // preload "movl bpp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4777 | "addl %%eax, %%edi \n\t" // rp = row + bpp |
destinyXfate | 2:0e2ef1edf01b | 4778 | "movl _MMXLength, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4779 | |
destinyXfate | 2:0e2ef1edf01b | 4780 | // prime the pump: load the first Raw(x-bpp) data set |
destinyXfate | 2:0e2ef1edf01b | 4781 | "movq -8(%%edi,%%edx,), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4782 | "andl $0x0000003f, %%ecx \n\t" // calc bytes over mult of 64 |
destinyXfate | 2:0e2ef1edf01b | 4783 | |
destinyXfate | 2:0e2ef1edf01b | 4784 | "sub_8lp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4785 | "movq (%%edi,%%edx,), %%mm0 \n\t" // load Sub(x) for 1st 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4786 | "paddb %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4787 | "movq 8(%%edi,%%edx,), %%mm1 \n\t" // load Sub(x) for 2nd 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4788 | "movq %%mm0, (%%edi,%%edx,) \n\t" // write Raw(x) for 1st 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4789 | |
destinyXfate | 2:0e2ef1edf01b | 4790 | // Now mm0 will be used as Raw(x-bpp) for the 2nd group of 8 bytes. |
destinyXfate | 2:0e2ef1edf01b | 4791 | // This will be repeated for each group of 8 bytes with the 8th |
destinyXfate | 2:0e2ef1edf01b | 4792 | // group being used as the Raw(x-bpp) for the 1st group of the |
destinyXfate | 2:0e2ef1edf01b | 4793 | // next loop. |
destinyXfate | 2:0e2ef1edf01b | 4794 | |
destinyXfate | 2:0e2ef1edf01b | 4795 | "paddb %%mm0, %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4796 | "movq 16(%%edi,%%edx,), %%mm2 \n\t" // load Sub(x) for 3rd 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4797 | "movq %%mm1, 8(%%edi,%%edx,) \n\t" // write Raw(x) for 2nd 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4798 | "paddb %%mm1, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4799 | "movq 24(%%edi,%%edx,), %%mm3 \n\t" // load Sub(x) for 4th 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4800 | "movq %%mm2, 16(%%edi,%%edx,) \n\t" // write Raw(x) for 3rd 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4801 | "paddb %%mm2, %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4802 | "movq 32(%%edi,%%edx,), %%mm4 \n\t" // load Sub(x) for 5th 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4803 | "movq %%mm3, 24(%%edi,%%edx,) \n\t" // write Raw(x) for 4th 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4804 | "paddb %%mm3, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4805 | "movq 40(%%edi,%%edx,), %%mm5 \n\t" // load Sub(x) for 6th 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4806 | "movq %%mm4, 32(%%edi,%%edx,) \n\t" // write Raw(x) for 5th 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4807 | "paddb %%mm4, %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4808 | "movq 48(%%edi,%%edx,), %%mm6 \n\t" // load Sub(x) for 7th 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4809 | "movq %%mm5, 40(%%edi,%%edx,) \n\t" // write Raw(x) for 6th 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4810 | "paddb %%mm5, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4811 | "movq 56(%%edi,%%edx,), %%mm7 \n\t" // load Sub(x) for 8th 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4812 | "movq %%mm6, 48(%%edi,%%edx,) \n\t" // write Raw(x) for 7th 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4813 | "addl $64, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4814 | "paddb %%mm6, %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4815 | "cmpl %%ecx, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4816 | "movq %%mm7, -8(%%edi,%%edx,) \n\t" // write Raw(x) for 8th 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 4817 | "jb sub_8lp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4818 | |
destinyXfate | 2:0e2ef1edf01b | 4819 | "cmpl _MMXLength, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4820 | "jnb sub_8lt8 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4821 | |
destinyXfate | 2:0e2ef1edf01b | 4822 | "sub_8lpA: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4823 | "movq (%%edi,%%edx,), %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4824 | "addl $8, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4825 | "paddb %%mm7, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4826 | "cmpl _MMXLength, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4827 | "movq %%mm0, -8(%%edi,%%edx,) \n\t" // -8 to offset early addl edx |
destinyXfate | 2:0e2ef1edf01b | 4828 | "movq %%mm0, %%mm7 \n\t" // move calculated Raw(x) data |
destinyXfate | 2:0e2ef1edf01b | 4829 | // to mm1 to be new Raw(x-bpp) |
destinyXfate | 2:0e2ef1edf01b | 4830 | // for next loop |
destinyXfate | 2:0e2ef1edf01b | 4831 | "jb sub_8lpA \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4832 | |
destinyXfate | 2:0e2ef1edf01b | 4833 | "sub_8lt8: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4834 | |
destinyXfate | 2:0e2ef1edf01b | 4835 | : "=a" (dummy_value_a), // 0 // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 4836 | "=D" (dummy_value_D) // 1 |
destinyXfate | 2:0e2ef1edf01b | 4837 | |
destinyXfate | 2:0e2ef1edf01b | 4838 | : "0" (bpp), // eax // input regs |
destinyXfate | 2:0e2ef1edf01b | 4839 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 4840 | |
destinyXfate | 2:0e2ef1edf01b | 4841 | : "%ecx", "%edx", "%esi" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 4842 | #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 4843 | , "%mm0", "%mm1", "%mm2", "%mm3", "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 4844 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4845 | ); |
destinyXfate | 2:0e2ef1edf01b | 4846 | } |
destinyXfate | 2:0e2ef1edf01b | 4847 | break; |
destinyXfate | 2:0e2ef1edf01b | 4848 | |
destinyXfate | 2:0e2ef1edf01b | 4849 | default: // bpp greater than 8 bytes GRR BOGUS |
destinyXfate | 2:0e2ef1edf01b | 4850 | { |
destinyXfate | 2:0e2ef1edf01b | 4851 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 4852 | "movl _dif, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4853 | // preload "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4854 | "movl %%edi, %%esi \n\t" // lp = row |
destinyXfate | 2:0e2ef1edf01b | 4855 | // preload "movl bpp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4856 | "addl %%eax, %%edi \n\t" // rp = row + bpp |
destinyXfate | 2:0e2ef1edf01b | 4857 | |
destinyXfate | 2:0e2ef1edf01b | 4858 | "sub_Alp: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4859 | "movq (%%edi,%%edx,), %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4860 | "movq (%%esi,%%edx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4861 | "addl $8, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4862 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4863 | "cmpl _MMXLength, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4864 | "movq %%mm0, -8(%%edi,%%edx,) \n\t" // mov does not affect flags; |
destinyXfate | 2:0e2ef1edf01b | 4865 | // -8 to offset addl edx |
destinyXfate | 2:0e2ef1edf01b | 4866 | "jb sub_Alp \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4867 | |
destinyXfate | 2:0e2ef1edf01b | 4868 | : "=a" (dummy_value_a), // 0 // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 4869 | "=D" (dummy_value_D) // 1 |
destinyXfate | 2:0e2ef1edf01b | 4870 | |
destinyXfate | 2:0e2ef1edf01b | 4871 | : "0" (bpp), // eax // input regs |
destinyXfate | 2:0e2ef1edf01b | 4872 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 4873 | |
destinyXfate | 2:0e2ef1edf01b | 4874 | : "%edx", "%esi" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 4875 | #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 4876 | , "%mm0", "%mm1" |
destinyXfate | 2:0e2ef1edf01b | 4877 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4878 | ); |
destinyXfate | 2:0e2ef1edf01b | 4879 | } |
destinyXfate | 2:0e2ef1edf01b | 4880 | break; |
destinyXfate | 2:0e2ef1edf01b | 4881 | |
destinyXfate | 2:0e2ef1edf01b | 4882 | } // end switch (bpp) |
destinyXfate | 2:0e2ef1edf01b | 4883 | |
destinyXfate | 2:0e2ef1edf01b | 4884 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 4885 | "movl _MMXLength, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4886 | //pre "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4887 | "cmpl _FullLength, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4888 | "jnb sub_end \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4889 | |
destinyXfate | 2:0e2ef1edf01b | 4890 | "movl %%edi, %%esi \n\t" // lp = row |
destinyXfate | 2:0e2ef1edf01b | 4891 | //pre "movl bpp, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4892 | "addl %%eax, %%edi \n\t" // rp = row + bpp |
destinyXfate | 2:0e2ef1edf01b | 4893 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4894 | |
destinyXfate | 2:0e2ef1edf01b | 4895 | "sub_lp2: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4896 | "movb (%%esi,%%edx,), %%al \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4897 | "addb %%al, (%%edi,%%edx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4898 | "incl %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4899 | "cmpl _FullLength, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4900 | "jb sub_lp2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4901 | |
destinyXfate | 2:0e2ef1edf01b | 4902 | "sub_end: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4903 | "EMMS \n\t" // end MMX instructions |
destinyXfate | 2:0e2ef1edf01b | 4904 | |
destinyXfate | 2:0e2ef1edf01b | 4905 | : "=a" (dummy_value_a), // 0 // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 4906 | "=D" (dummy_value_D) // 1 |
destinyXfate | 2:0e2ef1edf01b | 4907 | |
destinyXfate | 2:0e2ef1edf01b | 4908 | : "0" (bpp), // eax // input regs |
destinyXfate | 2:0e2ef1edf01b | 4909 | "1" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 4910 | |
destinyXfate | 2:0e2ef1edf01b | 4911 | : "%edx", "%esi" // clobber list |
destinyXfate | 2:0e2ef1edf01b | 4912 | ); |
destinyXfate | 2:0e2ef1edf01b | 4913 | |
destinyXfate | 2:0e2ef1edf01b | 4914 | } // end of png_read_filter_row_mmx_sub() |
destinyXfate | 2:0e2ef1edf01b | 4915 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4916 | |
destinyXfate | 2:0e2ef1edf01b | 4917 | |
destinyXfate | 2:0e2ef1edf01b | 4918 | |
destinyXfate | 2:0e2ef1edf01b | 4919 | |
destinyXfate | 2:0e2ef1edf01b | 4920 | //===========================================================================// |
destinyXfate | 2:0e2ef1edf01b | 4921 | // // |
destinyXfate | 2:0e2ef1edf01b | 4922 | // P N G _ R E A D _ F I L T E R _ R O W _ M M X _ U P // |
destinyXfate | 2:0e2ef1edf01b | 4923 | // // |
destinyXfate | 2:0e2ef1edf01b | 4924 | //===========================================================================// |
destinyXfate | 2:0e2ef1edf01b | 4925 | |
destinyXfate | 2:0e2ef1edf01b | 4926 | // Optimized code for PNG Up filter decoder |
destinyXfate | 2:0e2ef1edf01b | 4927 | |
destinyXfate | 2:0e2ef1edf01b | 4928 | static void /* PRIVATE */ |
destinyXfate | 2:0e2ef1edf01b | 4929 | png_read_filter_row_mmx_up(png_row_infop row_info, png_bytep row, |
destinyXfate | 2:0e2ef1edf01b | 4930 | png_bytep prev_row) |
destinyXfate | 2:0e2ef1edf01b | 4931 | { |
destinyXfate | 2:0e2ef1edf01b | 4932 | png_uint_32 len; |
destinyXfate | 2:0e2ef1edf01b | 4933 | int dummy_value_d; // fix 'forbidden register 3 (dx) was spilled' error |
destinyXfate | 2:0e2ef1edf01b | 4934 | int dummy_value_S; |
destinyXfate | 2:0e2ef1edf01b | 4935 | int dummy_value_D; |
destinyXfate | 2:0e2ef1edf01b | 4936 | |
destinyXfate | 2:0e2ef1edf01b | 4937 | len = row_info->rowbytes; // number of bytes to filter |
destinyXfate | 2:0e2ef1edf01b | 4938 | |
destinyXfate | 2:0e2ef1edf01b | 4939 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 4940 | //pre "movl row, %%edi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4941 | // get # of bytes to alignment |
destinyXfate | 2:0e2ef1edf01b | 4942 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 4943 | "pushl %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4944 | #endif |
destinyXfate | 2:0e2ef1edf01b | 4945 | "movl %%edi, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4946 | "xorl %%ebx, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4947 | "addl $0x7, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4948 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4949 | "andl $0xfffffff8, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4950 | //pre "movl prev_row, %%esi \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4951 | "subl %%edi, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4952 | "jz up_go \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4953 | |
destinyXfate | 2:0e2ef1edf01b | 4954 | "up_lp1: \n\t" // fix alignment |
destinyXfate | 2:0e2ef1edf01b | 4955 | "movb (%%edi,%%ebx,), %%al \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4956 | "addb (%%esi,%%ebx,), %%al \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4957 | "incl %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4958 | "cmpl %%ecx, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4959 | "movb %%al, -1(%%edi,%%ebx,) \n\t" // mov does not affect flags; -1 to |
destinyXfate | 2:0e2ef1edf01b | 4960 | "jb up_lp1 \n\t" // offset incl ebx |
destinyXfate | 2:0e2ef1edf01b | 4961 | |
destinyXfate | 2:0e2ef1edf01b | 4962 | "up_go: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4963 | //pre "movl len, %%edx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4964 | "movl %%edx, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4965 | "subl %%ebx, %%edx \n\t" // subtract alignment fix |
destinyXfate | 2:0e2ef1edf01b | 4966 | "andl $0x0000003f, %%edx \n\t" // calc bytes over mult of 64 |
destinyXfate | 2:0e2ef1edf01b | 4967 | "subl %%edx, %%ecx \n\t" // drop over bytes from length |
destinyXfate | 2:0e2ef1edf01b | 4968 | |
destinyXfate | 2:0e2ef1edf01b | 4969 | // unrolled loop - use all MMX registers and interleave to reduce |
destinyXfate | 2:0e2ef1edf01b | 4970 | // number of branch instructions (loops) and reduce partial stalls |
destinyXfate | 2:0e2ef1edf01b | 4971 | "up_loop: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4972 | "movq (%%esi,%%ebx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4973 | "movq (%%edi,%%ebx,), %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4974 | "movq 8(%%esi,%%ebx,), %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4975 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4976 | "movq 8(%%edi,%%ebx,), %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4977 | "movq %%mm0, (%%edi,%%ebx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4978 | "paddb %%mm3, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4979 | "movq 16(%%esi,%%ebx,), %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4980 | "movq %%mm2, 8(%%edi,%%ebx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4981 | "movq 16(%%edi,%%ebx,), %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4982 | "movq 24(%%esi,%%ebx,), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4983 | "paddb %%mm5, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4984 | "movq 24(%%edi,%%ebx,), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4985 | "movq %%mm4, 16(%%edi,%%ebx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4986 | "paddb %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4987 | "movq 32(%%esi,%%ebx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4988 | "movq %%mm6, 24(%%edi,%%ebx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4989 | "movq 32(%%edi,%%ebx,), %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4990 | "movq 40(%%esi,%%ebx,), %%mm3 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4991 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4992 | "movq 40(%%edi,%%ebx,), %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4993 | "movq %%mm0, 32(%%edi,%%ebx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4994 | "paddb %%mm3, %%mm2 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4995 | "movq 48(%%esi,%%ebx,), %%mm5 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4996 | "movq %%mm2, 40(%%edi,%%ebx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4997 | "movq 48(%%edi,%%ebx,), %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4998 | "movq 56(%%esi,%%ebx,), %%mm7 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 4999 | "paddb %%mm5, %%mm4 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5000 | "movq 56(%%edi,%%ebx,), %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5001 | "movq %%mm4, 48(%%edi,%%ebx,) \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5002 | "addl $64, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5003 | "paddb %%mm7, %%mm6 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5004 | "cmpl %%ecx, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5005 | "movq %%mm6, -8(%%edi,%%ebx,) \n\t" // (+56)movq does not affect flags; |
destinyXfate | 2:0e2ef1edf01b | 5006 | "jb up_loop \n\t" // -8 to offset addl ebx |
destinyXfate | 2:0e2ef1edf01b | 5007 | |
destinyXfate | 2:0e2ef1edf01b | 5008 | "cmpl $0, %%edx \n\t" // test for bytes over mult of 64 |
destinyXfate | 2:0e2ef1edf01b | 5009 | "jz up_end \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5010 | |
destinyXfate | 2:0e2ef1edf01b | 5011 | "cmpl $8, %%edx \n\t" // test for less than 8 bytes |
destinyXfate | 2:0e2ef1edf01b | 5012 | "jb up_lt8 \n\t" // [added by lcreeve at netins.net] |
destinyXfate | 2:0e2ef1edf01b | 5013 | |
destinyXfate | 2:0e2ef1edf01b | 5014 | "addl %%edx, %%ecx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5015 | "andl $0x00000007, %%edx \n\t" // calc bytes over mult of 8 |
destinyXfate | 2:0e2ef1edf01b | 5016 | "subl %%edx, %%ecx \n\t" // drop over bytes from length |
destinyXfate | 2:0e2ef1edf01b | 5017 | "jz up_lt8 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5018 | |
destinyXfate | 2:0e2ef1edf01b | 5019 | "up_lpA: \n\t" // use MMX regs to update 8 bytes sim. |
destinyXfate | 2:0e2ef1edf01b | 5020 | "movq (%%esi,%%ebx,), %%mm1 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5021 | "movq (%%edi,%%ebx,), %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5022 | "addl $8, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5023 | "paddb %%mm1, %%mm0 \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5024 | "cmpl %%ecx, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5025 | "movq %%mm0, -8(%%edi,%%ebx,) \n\t" // movq does not affect flags; -8 to |
destinyXfate | 2:0e2ef1edf01b | 5026 | "jb up_lpA \n\t" // offset add ebx |
destinyXfate | 2:0e2ef1edf01b | 5027 | "cmpl $0, %%edx \n\t" // test for bytes over mult of 8 |
destinyXfate | 2:0e2ef1edf01b | 5028 | "jz up_end \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5029 | |
destinyXfate | 2:0e2ef1edf01b | 5030 | "up_lt8: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5031 | "xorl %%eax, %%eax \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5032 | "addl %%edx, %%ecx \n\t" // move over byte count into counter |
destinyXfate | 2:0e2ef1edf01b | 5033 | |
destinyXfate | 2:0e2ef1edf01b | 5034 | "up_lp2: \n\t" // use x86 regs for remaining bytes |
destinyXfate | 2:0e2ef1edf01b | 5035 | "movb (%%edi,%%ebx,), %%al \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5036 | "addb (%%esi,%%ebx,), %%al \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5037 | "incl %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5038 | "cmpl %%ecx, %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5039 | "movb %%al, -1(%%edi,%%ebx,) \n\t" // mov does not affect flags; -1 to |
destinyXfate | 2:0e2ef1edf01b | 5040 | "jb up_lp2 \n\t" // offset inc ebx |
destinyXfate | 2:0e2ef1edf01b | 5041 | |
destinyXfate | 2:0e2ef1edf01b | 5042 | "up_end: \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5043 | "EMMS \n\t" // conversion of filtered row complete |
destinyXfate | 2:0e2ef1edf01b | 5044 | #ifdef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 5045 | "popl %%ebx \n\t" |
destinyXfate | 2:0e2ef1edf01b | 5046 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5047 | |
destinyXfate | 2:0e2ef1edf01b | 5048 | : "=d" (dummy_value_d), // 0 // output regs (dummy) |
destinyXfate | 2:0e2ef1edf01b | 5049 | "=S" (dummy_value_S), // 1 |
destinyXfate | 2:0e2ef1edf01b | 5050 | "=D" (dummy_value_D) // 2 |
destinyXfate | 2:0e2ef1edf01b | 5051 | |
destinyXfate | 2:0e2ef1edf01b | 5052 | : "0" (len), // edx // input regs |
destinyXfate | 2:0e2ef1edf01b | 5053 | "1" (prev_row), // esi |
destinyXfate | 2:0e2ef1edf01b | 5054 | "2" (row) // edi |
destinyXfate | 2:0e2ef1edf01b | 5055 | |
destinyXfate | 2:0e2ef1edf01b | 5056 | : "%eax", "%ecx" // clobber list (no input regs!) |
destinyXfate | 2:0e2ef1edf01b | 5057 | #ifndef __PIC__ |
destinyXfate | 2:0e2ef1edf01b | 5058 | , "%ebx" |
destinyXfate | 2:0e2ef1edf01b | 5059 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5060 | |
destinyXfate | 2:0e2ef1edf01b | 5061 | #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ |
destinyXfate | 2:0e2ef1edf01b | 5062 | , "%mm0", "%mm1", "%mm2", "%mm3" |
destinyXfate | 2:0e2ef1edf01b | 5063 | , "%mm4", "%mm5", "%mm6", "%mm7" |
destinyXfate | 2:0e2ef1edf01b | 5064 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5065 | ); |
destinyXfate | 2:0e2ef1edf01b | 5066 | |
destinyXfate | 2:0e2ef1edf01b | 5067 | } // end of png_read_filter_row_mmx_up() |
destinyXfate | 2:0e2ef1edf01b | 5068 | |
destinyXfate | 2:0e2ef1edf01b | 5069 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 5070 | |
destinyXfate | 2:0e2ef1edf01b | 5071 | |
destinyXfate | 2:0e2ef1edf01b | 5072 | |
destinyXfate | 2:0e2ef1edf01b | 5073 | |
destinyXfate | 2:0e2ef1edf01b | 5074 | /*===========================================================================*/ |
destinyXfate | 2:0e2ef1edf01b | 5075 | /* */ |
destinyXfate | 2:0e2ef1edf01b | 5076 | /* P N G _ R E A D _ F I L T E R _ R O W */ |
destinyXfate | 2:0e2ef1edf01b | 5077 | /* */ |
destinyXfate | 2:0e2ef1edf01b | 5078 | /*===========================================================================*/ |
destinyXfate | 2:0e2ef1edf01b | 5079 | |
destinyXfate | 2:0e2ef1edf01b | 5080 | |
destinyXfate | 2:0e2ef1edf01b | 5081 | /* Optimized png_read_filter_row routines */ |
destinyXfate | 2:0e2ef1edf01b | 5082 | |
destinyXfate | 2:0e2ef1edf01b | 5083 | void /* PRIVATE */ |
destinyXfate | 2:0e2ef1edf01b | 5084 | png_read_filter_row(png_structp png_ptr, png_row_infop row_info, png_bytep |
destinyXfate | 2:0e2ef1edf01b | 5085 | row, png_bytep prev_row, int filter) |
destinyXfate | 2:0e2ef1edf01b | 5086 | { |
destinyXfate | 2:0e2ef1edf01b | 5087 | #ifdef PNG_DEBUG |
destinyXfate | 2:0e2ef1edf01b | 5088 | char filnm[10]; |
destinyXfate | 2:0e2ef1edf01b | 5089 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5090 | |
destinyXfate | 2:0e2ef1edf01b | 5091 | #if defined(PNG_MMX_CODE_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 5092 | /* GRR: these are superseded by png_ptr->asm_flags: */ |
destinyXfate | 2:0e2ef1edf01b | 5093 | #define UseMMX_sub 1 // GRR: converted 20000730 |
destinyXfate | 2:0e2ef1edf01b | 5094 | #define UseMMX_up 1 // GRR: converted 20000729 |
destinyXfate | 2:0e2ef1edf01b | 5095 | #define UseMMX_avg 1 // GRR: converted 20000828 (+ 16-bit bugfix 20000916) |
destinyXfate | 2:0e2ef1edf01b | 5096 | #define UseMMX_paeth 1 // GRR: converted 20000828 |
destinyXfate | 2:0e2ef1edf01b | 5097 | |
destinyXfate | 2:0e2ef1edf01b | 5098 | if (_mmx_supported == 2) { |
destinyXfate | 2:0e2ef1edf01b | 5099 | /* this should have happened in png_init_mmx_flags() already */ |
destinyXfate | 2:0e2ef1edf01b | 5100 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 5101 | png_warning(png_ptr, "asm_flags may not have been initialized"); |
destinyXfate | 2:0e2ef1edf01b | 5102 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5103 | png_mmx_support(); |
destinyXfate | 2:0e2ef1edf01b | 5104 | } |
destinyXfate | 2:0e2ef1edf01b | 5105 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 5106 | |
destinyXfate | 2:0e2ef1edf01b | 5107 | #ifdef PNG_DEBUG |
destinyXfate | 2:0e2ef1edf01b | 5108 | png_debug(1, "in png_read_filter_row (pnggccrd.c)\n"); |
destinyXfate | 2:0e2ef1edf01b | 5109 | switch (filter) |
destinyXfate | 2:0e2ef1edf01b | 5110 | { |
destinyXfate | 2:0e2ef1edf01b | 5111 | case 0: sprintf(filnm, "none"); |
destinyXfate | 2:0e2ef1edf01b | 5112 | break; |
destinyXfate | 2:0e2ef1edf01b | 5113 | case 1: sprintf(filnm, "sub-%s", |
destinyXfate | 2:0e2ef1edf01b | 5114 | #if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK) |
destinyXfate | 2:0e2ef1edf01b | 5115 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 5116 | (png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_SUB)? "MMX" : |
destinyXfate | 2:0e2ef1edf01b | 5117 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5118 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5119 | "x86"); |
destinyXfate | 2:0e2ef1edf01b | 5120 | break; |
destinyXfate | 2:0e2ef1edf01b | 5121 | case 2: sprintf(filnm, "up-%s", |
destinyXfate | 2:0e2ef1edf01b | 5122 | #ifdef PNG_MMX_CODE_SUPPORTED |
destinyXfate | 2:0e2ef1edf01b | 5123 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 5124 | (png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_UP)? "MMX" : |
destinyXfate | 2:0e2ef1edf01b | 5125 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5126 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5127 | "x86"); |
destinyXfate | 2:0e2ef1edf01b | 5128 | break; |
destinyXfate | 2:0e2ef1edf01b | 5129 | case 3: sprintf(filnm, "avg-%s", |
destinyXfate | 2:0e2ef1edf01b | 5130 | #if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK) |
destinyXfate | 2:0e2ef1edf01b | 5131 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 5132 | (png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_AVG)? "MMX" : |
destinyXfate | 2:0e2ef1edf01b | 5133 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5134 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5135 | "x86"); |
destinyXfate | 2:0e2ef1edf01b | 5136 | break; |
destinyXfate | 2:0e2ef1edf01b | 5137 | case 4: sprintf(filnm, "Paeth-%s", |
destinyXfate | 2:0e2ef1edf01b | 5138 | #if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK) |
destinyXfate | 2:0e2ef1edf01b | 5139 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 5140 | (png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_PAETH)? "MMX": |
destinyXfate | 2:0e2ef1edf01b | 5141 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5142 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5143 | "x86"); |
destinyXfate | 2:0e2ef1edf01b | 5144 | break; |
destinyXfate | 2:0e2ef1edf01b | 5145 | default: sprintf(filnm, "unknw"); |
destinyXfate | 2:0e2ef1edf01b | 5146 | break; |
destinyXfate | 2:0e2ef1edf01b | 5147 | } |
destinyXfate | 2:0e2ef1edf01b | 5148 | png_debug2(0, "row_number=%5ld, %5s, ", png_ptr->row_number, filnm); |
destinyXfate | 2:0e2ef1edf01b | 5149 | png_debug1(0, "row=0x%08lx, ", (unsigned long)row); |
destinyXfate | 2:0e2ef1edf01b | 5150 | png_debug2(0, "pixdepth=%2d, bytes=%d, ", (int)row_info->pixel_depth, |
destinyXfate | 2:0e2ef1edf01b | 5151 | (int)((row_info->pixel_depth + 7) >> 3)); |
destinyXfate | 2:0e2ef1edf01b | 5152 | png_debug1(0,"rowbytes=%8ld\n", row_info->rowbytes); |
destinyXfate | 2:0e2ef1edf01b | 5153 | #endif /* PNG_DEBUG */ |
destinyXfate | 2:0e2ef1edf01b | 5154 | |
destinyXfate | 2:0e2ef1edf01b | 5155 | switch (filter) |
destinyXfate | 2:0e2ef1edf01b | 5156 | { |
destinyXfate | 2:0e2ef1edf01b | 5157 | case PNG_FILTER_VALUE_NONE: |
destinyXfate | 2:0e2ef1edf01b | 5158 | break; |
destinyXfate | 2:0e2ef1edf01b | 5159 | |
destinyXfate | 2:0e2ef1edf01b | 5160 | case PNG_FILTER_VALUE_SUB: |
destinyXfate | 2:0e2ef1edf01b | 5161 | #if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK) |
destinyXfate | 2:0e2ef1edf01b | 5162 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 5163 | if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_SUB) && |
destinyXfate | 2:0e2ef1edf01b | 5164 | (row_info->pixel_depth >= png_ptr->mmx_bitdepth_threshold) && |
destinyXfate | 2:0e2ef1edf01b | 5165 | (row_info->rowbytes >= png_ptr->mmx_rowbytes_threshold)) |
destinyXfate | 2:0e2ef1edf01b | 5166 | #else |
destinyXfate | 2:0e2ef1edf01b | 5167 | if (_mmx_supported) |
destinyXfate | 2:0e2ef1edf01b | 5168 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5169 | { |
destinyXfate | 2:0e2ef1edf01b | 5170 | png_read_filter_row_mmx_sub(row_info, row); |
destinyXfate | 2:0e2ef1edf01b | 5171 | } |
destinyXfate | 2:0e2ef1edf01b | 5172 | else |
destinyXfate | 2:0e2ef1edf01b | 5173 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 5174 | { |
destinyXfate | 2:0e2ef1edf01b | 5175 | png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 5176 | png_uint_32 istop = row_info->rowbytes; |
destinyXfate | 2:0e2ef1edf01b | 5177 | png_uint_32 bpp = (row_info->pixel_depth + 7) >> 3; |
destinyXfate | 2:0e2ef1edf01b | 5178 | png_bytep rp = row + bpp; |
destinyXfate | 2:0e2ef1edf01b | 5179 | png_bytep lp = row; |
destinyXfate | 2:0e2ef1edf01b | 5180 | |
destinyXfate | 2:0e2ef1edf01b | 5181 | for (i = bpp; i < istop; i++) |
destinyXfate | 2:0e2ef1edf01b | 5182 | { |
destinyXfate | 2:0e2ef1edf01b | 5183 | *rp = (png_byte)(((int)(*rp) + (int)(*lp++)) & 0xff); |
destinyXfate | 2:0e2ef1edf01b | 5184 | rp++; |
destinyXfate | 2:0e2ef1edf01b | 5185 | } |
destinyXfate | 2:0e2ef1edf01b | 5186 | } /* end !UseMMX_sub */ |
destinyXfate | 2:0e2ef1edf01b | 5187 | break; |
destinyXfate | 2:0e2ef1edf01b | 5188 | |
destinyXfate | 2:0e2ef1edf01b | 5189 | case PNG_FILTER_VALUE_UP: |
destinyXfate | 2:0e2ef1edf01b | 5190 | #if defined(PNG_MMX_CODE_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 5191 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 5192 | if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_UP) && |
destinyXfate | 2:0e2ef1edf01b | 5193 | (row_info->pixel_depth >= png_ptr->mmx_bitdepth_threshold) && |
destinyXfate | 2:0e2ef1edf01b | 5194 | (row_info->rowbytes >= png_ptr->mmx_rowbytes_threshold)) |
destinyXfate | 2:0e2ef1edf01b | 5195 | #else |
destinyXfate | 2:0e2ef1edf01b | 5196 | if (_mmx_supported) |
destinyXfate | 2:0e2ef1edf01b | 5197 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5198 | { |
destinyXfate | 2:0e2ef1edf01b | 5199 | png_read_filter_row_mmx_up(row_info, row, prev_row); |
destinyXfate | 2:0e2ef1edf01b | 5200 | } |
destinyXfate | 2:0e2ef1edf01b | 5201 | else |
destinyXfate | 2:0e2ef1edf01b | 5202 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 5203 | { |
destinyXfate | 2:0e2ef1edf01b | 5204 | png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 5205 | png_uint_32 istop = row_info->rowbytes; |
destinyXfate | 2:0e2ef1edf01b | 5206 | png_bytep rp = row; |
destinyXfate | 2:0e2ef1edf01b | 5207 | png_bytep pp = prev_row; |
destinyXfate | 2:0e2ef1edf01b | 5208 | |
destinyXfate | 2:0e2ef1edf01b | 5209 | for (i = 0; i < istop; ++i) |
destinyXfate | 2:0e2ef1edf01b | 5210 | { |
destinyXfate | 2:0e2ef1edf01b | 5211 | *rp = (png_byte)(((int)(*rp) + (int)(*pp++)) & 0xff); |
destinyXfate | 2:0e2ef1edf01b | 5212 | rp++; |
destinyXfate | 2:0e2ef1edf01b | 5213 | } |
destinyXfate | 2:0e2ef1edf01b | 5214 | } /* end !UseMMX_up */ |
destinyXfate | 2:0e2ef1edf01b | 5215 | break; |
destinyXfate | 2:0e2ef1edf01b | 5216 | |
destinyXfate | 2:0e2ef1edf01b | 5217 | case PNG_FILTER_VALUE_AVG: |
destinyXfate | 2:0e2ef1edf01b | 5218 | #if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK) |
destinyXfate | 2:0e2ef1edf01b | 5219 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 5220 | if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_AVG) && |
destinyXfate | 2:0e2ef1edf01b | 5221 | (row_info->pixel_depth >= png_ptr->mmx_bitdepth_threshold) && |
destinyXfate | 2:0e2ef1edf01b | 5222 | (row_info->rowbytes >= png_ptr->mmx_rowbytes_threshold)) |
destinyXfate | 2:0e2ef1edf01b | 5223 | #else |
destinyXfate | 2:0e2ef1edf01b | 5224 | if (_mmx_supported) |
destinyXfate | 2:0e2ef1edf01b | 5225 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5226 | { |
destinyXfate | 2:0e2ef1edf01b | 5227 | png_read_filter_row_mmx_avg(row_info, row, prev_row); |
destinyXfate | 2:0e2ef1edf01b | 5228 | } |
destinyXfate | 2:0e2ef1edf01b | 5229 | else |
destinyXfate | 2:0e2ef1edf01b | 5230 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 5231 | { |
destinyXfate | 2:0e2ef1edf01b | 5232 | png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 5233 | png_bytep rp = row; |
destinyXfate | 2:0e2ef1edf01b | 5234 | png_bytep pp = prev_row; |
destinyXfate | 2:0e2ef1edf01b | 5235 | png_bytep lp = row; |
destinyXfate | 2:0e2ef1edf01b | 5236 | png_uint_32 bpp = (row_info->pixel_depth + 7) >> 3; |
destinyXfate | 2:0e2ef1edf01b | 5237 | png_uint_32 istop = row_info->rowbytes - bpp; |
destinyXfate | 2:0e2ef1edf01b | 5238 | |
destinyXfate | 2:0e2ef1edf01b | 5239 | for (i = 0; i < bpp; i++) |
destinyXfate | 2:0e2ef1edf01b | 5240 | { |
destinyXfate | 2:0e2ef1edf01b | 5241 | *rp = (png_byte)(((int)(*rp) + |
destinyXfate | 2:0e2ef1edf01b | 5242 | ((int)(*pp++) >> 1)) & 0xff); |
destinyXfate | 2:0e2ef1edf01b | 5243 | rp++; |
destinyXfate | 2:0e2ef1edf01b | 5244 | } |
destinyXfate | 2:0e2ef1edf01b | 5245 | |
destinyXfate | 2:0e2ef1edf01b | 5246 | for (i = 0; i < istop; i++) |
destinyXfate | 2:0e2ef1edf01b | 5247 | { |
destinyXfate | 2:0e2ef1edf01b | 5248 | *rp = (png_byte)(((int)(*rp) + |
destinyXfate | 2:0e2ef1edf01b | 5249 | ((int)(*pp++ + *lp++) >> 1)) & 0xff); |
destinyXfate | 2:0e2ef1edf01b | 5250 | rp++; |
destinyXfate | 2:0e2ef1edf01b | 5251 | } |
destinyXfate | 2:0e2ef1edf01b | 5252 | } /* end !UseMMX_avg */ |
destinyXfate | 2:0e2ef1edf01b | 5253 | break; |
destinyXfate | 2:0e2ef1edf01b | 5254 | |
destinyXfate | 2:0e2ef1edf01b | 5255 | case PNG_FILTER_VALUE_PAETH: |
destinyXfate | 2:0e2ef1edf01b | 5256 | #if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK) |
destinyXfate | 2:0e2ef1edf01b | 5257 | #if !defined(PNG_1_0_X) |
destinyXfate | 2:0e2ef1edf01b | 5258 | if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_PAETH) && |
destinyXfate | 2:0e2ef1edf01b | 5259 | (row_info->pixel_depth >= png_ptr->mmx_bitdepth_threshold) && |
destinyXfate | 2:0e2ef1edf01b | 5260 | (row_info->rowbytes >= png_ptr->mmx_rowbytes_threshold)) |
destinyXfate | 2:0e2ef1edf01b | 5261 | #else |
destinyXfate | 2:0e2ef1edf01b | 5262 | if (_mmx_supported) |
destinyXfate | 2:0e2ef1edf01b | 5263 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5264 | { |
destinyXfate | 2:0e2ef1edf01b | 5265 | png_read_filter_row_mmx_paeth(row_info, row, prev_row); |
destinyXfate | 2:0e2ef1edf01b | 5266 | } |
destinyXfate | 2:0e2ef1edf01b | 5267 | else |
destinyXfate | 2:0e2ef1edf01b | 5268 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 5269 | { |
destinyXfate | 2:0e2ef1edf01b | 5270 | png_uint_32 i; |
destinyXfate | 2:0e2ef1edf01b | 5271 | png_bytep rp = row; |
destinyXfate | 2:0e2ef1edf01b | 5272 | png_bytep pp = prev_row; |
destinyXfate | 2:0e2ef1edf01b | 5273 | png_bytep lp = row; |
destinyXfate | 2:0e2ef1edf01b | 5274 | png_bytep cp = prev_row; |
destinyXfate | 2:0e2ef1edf01b | 5275 | png_uint_32 bpp = (row_info->pixel_depth + 7) >> 3; |
destinyXfate | 2:0e2ef1edf01b | 5276 | png_uint_32 istop = row_info->rowbytes - bpp; |
destinyXfate | 2:0e2ef1edf01b | 5277 | |
destinyXfate | 2:0e2ef1edf01b | 5278 | for (i = 0; i < bpp; i++) |
destinyXfate | 2:0e2ef1edf01b | 5279 | { |
destinyXfate | 2:0e2ef1edf01b | 5280 | *rp = (png_byte)(((int)(*rp) + (int)(*pp++)) & 0xff); |
destinyXfate | 2:0e2ef1edf01b | 5281 | rp++; |
destinyXfate | 2:0e2ef1edf01b | 5282 | } |
destinyXfate | 2:0e2ef1edf01b | 5283 | |
destinyXfate | 2:0e2ef1edf01b | 5284 | for (i = 0; i < istop; i++) /* use leftover rp,pp */ |
destinyXfate | 2:0e2ef1edf01b | 5285 | { |
destinyXfate | 2:0e2ef1edf01b | 5286 | int a, b, c, pa, pb, pc, p; |
destinyXfate | 2:0e2ef1edf01b | 5287 | |
destinyXfate | 2:0e2ef1edf01b | 5288 | a = *lp++; |
destinyXfate | 2:0e2ef1edf01b | 5289 | b = *pp++; |
destinyXfate | 2:0e2ef1edf01b | 5290 | c = *cp++; |
destinyXfate | 2:0e2ef1edf01b | 5291 | |
destinyXfate | 2:0e2ef1edf01b | 5292 | p = b - c; |
destinyXfate | 2:0e2ef1edf01b | 5293 | pc = a - c; |
destinyXfate | 2:0e2ef1edf01b | 5294 | |
destinyXfate | 2:0e2ef1edf01b | 5295 | #ifdef PNG_USE_ABS |
destinyXfate | 2:0e2ef1edf01b | 5296 | pa = abs(p); |
destinyXfate | 2:0e2ef1edf01b | 5297 | pb = abs(pc); |
destinyXfate | 2:0e2ef1edf01b | 5298 | pc = abs(p + pc); |
destinyXfate | 2:0e2ef1edf01b | 5299 | #else |
destinyXfate | 2:0e2ef1edf01b | 5300 | pa = p < 0 ? -p : p; |
destinyXfate | 2:0e2ef1edf01b | 5301 | pb = pc < 0 ? -pc : pc; |
destinyXfate | 2:0e2ef1edf01b | 5302 | pc = (p + pc) < 0 ? -(p + pc) : p + pc; |
destinyXfate | 2:0e2ef1edf01b | 5303 | #endif |
destinyXfate | 2:0e2ef1edf01b | 5304 | |
destinyXfate | 2:0e2ef1edf01b | 5305 | /* |
destinyXfate | 2:0e2ef1edf01b | 5306 | if (pa <= pb && pa <= pc) |
destinyXfate | 2:0e2ef1edf01b | 5307 | p = a; |
destinyXfate | 2:0e2ef1edf01b | 5308 | else if (pb <= pc) |
destinyXfate | 2:0e2ef1edf01b | 5309 | p = b; |
destinyXfate | 2:0e2ef1edf01b | 5310 | else |
destinyXfate | 2:0e2ef1edf01b | 5311 | p = c; |
destinyXfate | 2:0e2ef1edf01b | 5312 | */ |
destinyXfate | 2:0e2ef1edf01b | 5313 | |
destinyXfate | 2:0e2ef1edf01b | 5314 | p = (pa <= pb && pa <= pc) ? a : (pb <= pc) ? b : c; |
destinyXfate | 2:0e2ef1edf01b | 5315 | |
destinyXfate | 2:0e2ef1edf01b | 5316 | *rp = (png_byte)(((int)(*rp) + p) & 0xff); |
destinyXfate | 2:0e2ef1edf01b | 5317 | rp++; |
destinyXfate | 2:0e2ef1edf01b | 5318 | } |
destinyXfate | 2:0e2ef1edf01b | 5319 | } /* end !UseMMX_paeth */ |
destinyXfate | 2:0e2ef1edf01b | 5320 | break; |
destinyXfate | 2:0e2ef1edf01b | 5321 | |
destinyXfate | 2:0e2ef1edf01b | 5322 | default: |
destinyXfate | 2:0e2ef1edf01b | 5323 | png_warning(png_ptr, "Ignoring bad row-filter type"); |
destinyXfate | 2:0e2ef1edf01b | 5324 | *row=0; |
destinyXfate | 2:0e2ef1edf01b | 5325 | break; |
destinyXfate | 2:0e2ef1edf01b | 5326 | } |
destinyXfate | 2:0e2ef1edf01b | 5327 | } |
destinyXfate | 2:0e2ef1edf01b | 5328 | |
destinyXfate | 2:0e2ef1edf01b | 5329 | #endif /* PNG_HAVE_MMX_READ_FILTER_ROW */ |
destinyXfate | 2:0e2ef1edf01b | 5330 | |
destinyXfate | 2:0e2ef1edf01b | 5331 | |
destinyXfate | 2:0e2ef1edf01b | 5332 | /*===========================================================================*/ |
destinyXfate | 2:0e2ef1edf01b | 5333 | /* */ |
destinyXfate | 2:0e2ef1edf01b | 5334 | /* P N G _ M M X _ S U P P O R T */ |
destinyXfate | 2:0e2ef1edf01b | 5335 | /* */ |
destinyXfate | 2:0e2ef1edf01b | 5336 | /*===========================================================================*/ |
destinyXfate | 2:0e2ef1edf01b | 5337 | |
destinyXfate | 2:0e2ef1edf01b | 5338 | /* GRR NOTES: (1) the following code assumes 386 or better (pushfl/popfl) |
destinyXfate | 2:0e2ef1edf01b | 5339 | * (2) all instructions compile with gcc 2.7.2.3 and later |
destinyXfate | 2:0e2ef1edf01b | 5340 | * (3) the function is moved down here to prevent gcc from |
destinyXfate | 2:0e2ef1edf01b | 5341 | * inlining it in multiple places and then barfing be- |
destinyXfate | 2:0e2ef1edf01b | 5342 | * cause the ".NOT_SUPPORTED" label is multiply defined |
destinyXfate | 2:0e2ef1edf01b | 5343 | * [is there a way to signal that a *single* function should |
destinyXfate | 2:0e2ef1edf01b | 5344 | * not be inlined? is there a way to modify the label for |
destinyXfate | 2:0e2ef1edf01b | 5345 | * each inlined instance, e.g., by appending _1, _2, etc.? |
destinyXfate | 2:0e2ef1edf01b | 5346 | * maybe if don't use leading "." in label name? (nope...sigh)] |
destinyXfate | 2:0e2ef1edf01b | 5347 | */ |
destinyXfate | 2:0e2ef1edf01b | 5348 | |
destinyXfate | 2:0e2ef1edf01b | 5349 | int PNGAPI |
destinyXfate | 2:0e2ef1edf01b | 5350 | png_mmx_support(void) |
destinyXfate | 2:0e2ef1edf01b | 5351 | { |
destinyXfate | 2:0e2ef1edf01b | 5352 | #if defined(PNG_MMX_CODE_SUPPORTED) |
destinyXfate | 2:0e2ef1edf01b | 5353 | int result; |
destinyXfate | 2:0e2ef1edf01b | 5354 | __asm__ __volatile__ ( |
destinyXfate | 2:0e2ef1edf01b | 5355 | "pushl %%ebx \n\t" // ebx gets clobbered by CPUID instruction |
destinyXfate | 2:0e2ef1edf01b | 5356 | "pushl %%ecx \n\t" // so does ecx... |
destinyXfate | 2:0e2ef1edf01b | 5357 | "pushl %%edx \n\t" // ...and edx (but ecx & edx safe on Linux) |
destinyXfate | 2:0e2ef1edf01b | 5358 | // ".byte 0x66 \n\t" // convert 16-bit pushf to 32-bit pushfd |
destinyXfate | 2:0e2ef1edf01b | 5359 | // "pushf \n\t" // 16-bit pushf |
destinyXfate | 2:0e2ef1edf01b | 5360 | "pushfl \n\t" // save Eflag to stack |
destinyXfate | 2:0e2ef1edf01b | 5361 | "popl %%eax \n\t" // get Eflag from stack into eax |
destinyXfate | 2:0e2ef1edf01b | 5362 | "movl %%eax, %%ecx \n\t" // make another copy of Eflag in ecx |
destinyXfate | 2:0e2ef1edf01b | 5363 | "xorl $0x200000, %%eax \n\t" // toggle ID bit in Eflag (i.e., bit 21) |
destinyXfate | 2:0e2ef1edf01b | 5364 | "pushl %%eax \n\t" // save modified Eflag back to stack |
destinyXfate | 2:0e2ef1edf01b | 5365 | // ".byte 0x66 \n\t" // convert 16-bit popf to 32-bit popfd |
destinyXfate | 2:0e2ef1edf01b | 5366 | // "popf \n\t" // 16-bit popf |
destinyXfate | 2:0e2ef1edf01b | 5367 | "popfl \n\t" // restore modified value to Eflag reg |
destinyXfate | 2:0e2ef1edf01b | 5368 | "pushfl \n\t" // save Eflag to stack |
destinyXfate | 2:0e2ef1edf01b | 5369 | "popl %%eax \n\t" // get Eflag from stack |
destinyXfate | 2:0e2ef1edf01b | 5370 | "pushl %%ecx \n\t" // save original Eflag to stack |
destinyXfate | 2:0e2ef1edf01b | 5371 | "popfl \n\t" // restore original Eflag |
destinyXfate | 2:0e2ef1edf01b | 5372 | "xorl %%ecx, %%eax \n\t" // compare new Eflag with original Eflag |
destinyXfate | 2:0e2ef1edf01b | 5373 | "jz 0f \n\t" // if same, CPUID instr. is not supported |
destinyXfate | 2:0e2ef1edf01b | 5374 | |
destinyXfate | 2:0e2ef1edf01b | 5375 | "xorl %%eax, %%eax \n\t" // set eax to zero |
destinyXfate | 2:0e2ef1edf01b | 5376 | // ".byte 0x0f, 0xa2 \n\t" // CPUID instruction (two-byte opcode) |
destinyXfate | 2:0e2ef1edf01b | 5377 | "cpuid \n\t" // get the CPU identification info |
destinyXfate | 2:0e2ef1edf01b | 5378 | "cmpl $1, %%eax \n\t" // make sure eax return non-zero value |
destinyXfate | 2:0e2ef1edf01b | 5379 | "jl 0f \n\t" // if eax is zero, MMX is not supported |
destinyXfate | 2:0e2ef1edf01b | 5380 | |
destinyXfate | 2:0e2ef1edf01b | 5381 | "xorl %%eax, %%eax \n\t" // set eax to zero and... |
destinyXfate | 2:0e2ef1edf01b | 5382 | "incl %%eax \n\t" // ...increment eax to 1. This pair is |
destinyXfate | 2:0e2ef1edf01b | 5383 | // faster than the instruction "mov eax, 1" |
destinyXfate | 2:0e2ef1edf01b | 5384 | "cpuid \n\t" // get the CPU identification info again |
destinyXfate | 2:0e2ef1edf01b | 5385 | "andl $0x800000, %%edx \n\t" // mask out all bits but MMX bit (23) |
destinyXfate | 2:0e2ef1edf01b | 5386 | "cmpl $0, %%edx \n\t" // 0 = MMX not supported |
destinyXfate | 2:0e2ef1edf01b | 5387 | "jz 0f \n\t" // non-zero = yes, MMX IS supported |
destinyXfate | 2:0e2ef1edf01b | 5388 | |
destinyXfate | 2:0e2ef1edf01b | 5389 | "movl $1, %%eax \n\t" // set return value to 1 |
destinyXfate | 2:0e2ef1edf01b | 5390 | "jmp 1f \n\t" // DONE: have MMX support |
destinyXfate | 2:0e2ef1edf01b | 5391 | |
destinyXfate | 2:0e2ef1edf01b | 5392 | "0: \n\t" // .NOT_SUPPORTED: target label for jump instructions |
destinyXfate | 2:0e2ef1edf01b | 5393 | "movl $0, %%eax \n\t" // set return value to 0 |
destinyXfate | 2:0e2ef1edf01b | 5394 | "1: \n\t" // .RETURN: target label for jump instructions |
destinyXfate | 2:0e2ef1edf01b | 5395 | "popl %%edx \n\t" // restore edx |
destinyXfate | 2:0e2ef1edf01b | 5396 | "popl %%ecx \n\t" // restore ecx |
destinyXfate | 2:0e2ef1edf01b | 5397 | "popl %%ebx \n\t" // restore ebx |
destinyXfate | 2:0e2ef1edf01b | 5398 | |
destinyXfate | 2:0e2ef1edf01b | 5399 | // "ret \n\t" // DONE: no MMX support |
destinyXfate | 2:0e2ef1edf01b | 5400 | // (fall through to standard C "ret") |
destinyXfate | 2:0e2ef1edf01b | 5401 | |
destinyXfate | 2:0e2ef1edf01b | 5402 | : "=a" (result) // output list |
destinyXfate | 2:0e2ef1edf01b | 5403 | |
destinyXfate | 2:0e2ef1edf01b | 5404 | : // any variables used on input (none) |
destinyXfate | 2:0e2ef1edf01b | 5405 | |
destinyXfate | 2:0e2ef1edf01b | 5406 | // no clobber list |
destinyXfate | 2:0e2ef1edf01b | 5407 | // , "%ebx", "%ecx", "%edx" // GRR: we handle these manually |
destinyXfate | 2:0e2ef1edf01b | 5408 | // , "memory" // if write to a variable gcc thought was in a reg |
destinyXfate | 2:0e2ef1edf01b | 5409 | // , "cc" // "condition codes" (flag bits) |
destinyXfate | 2:0e2ef1edf01b | 5410 | ); |
destinyXfate | 2:0e2ef1edf01b | 5411 | _mmx_supported = result; |
destinyXfate | 2:0e2ef1edf01b | 5412 | #else |
destinyXfate | 2:0e2ef1edf01b | 5413 | _mmx_supported = 0; |
destinyXfate | 2:0e2ef1edf01b | 5414 | #endif /* PNG_MMX_CODE_SUPPORTED */ |
destinyXfate | 2:0e2ef1edf01b | 5415 | |
destinyXfate | 2:0e2ef1edf01b | 5416 | return _mmx_supported; |
destinyXfate | 2:0e2ef1edf01b | 5417 | } |
destinyXfate | 2:0e2ef1edf01b | 5418 | |
destinyXfate | 2:0e2ef1edf01b | 5419 | |
destinyXfate | 2:0e2ef1edf01b | 5420 | #endif /* PNG_USE_PNGGCCRD */ |
destinyXfate | 2:0e2ef1edf01b | 5421 |