| 1 | /* |
| 2 | SDL - Simple DirectMedia Layer |
| 3 | Copyright (C) 1997-2009 Sam Lantinga |
| 4 | |
| 5 | This library is free software; you can redistribute it and/or |
| 6 | modify it under the terms of the GNU Lesser General Public |
| 7 | License as published by the Free Software Foundation; either |
| 8 | version 2.1 of the License, or (at your option) any later version. |
| 9 | |
| 10 | This library is distributed in the hope that it will be useful, |
| 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 13 | Lesser General Public License for more details. |
| 14 | |
| 15 | You should have received a copy of the GNU Lesser General Public |
| 16 | License along with this library; if not, write to the Free Software |
| 17 | Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA |
| 18 | |
| 19 | Sam Lantinga |
| 20 | slouken@libsdl.org |
| 21 | */ |
| 22 | #include "SDL_config.h" |
| 23 | |
| 24 | /* |
| 25 | MMX assembler version of SDL_MixAudio for signed little endian 16 bit samples and signed 8 bit samples |
| 26 | Copyright 2002 Stephane Marchesin (stephane.marchesin@wanadoo.fr) |
| 27 | This code is licensed under the LGPL (see COPYING for details) |
| 28 | |
| 29 | Assumes buffer size in bytes is a multiple of 16 |
| 30 | Assumes SDL_MIX_MAXVOLUME = 128 |
| 31 | */ |
| 32 | |
| 33 | |
| 34 | /*********************************************** |
| 35 | * Mixing for 16 bit signed buffers |
| 36 | ***********************************************/ |
| 37 | |
| 38 | #if defined(SDL_BUGGY_MMX_MIXERS) /* buggy, so we're disabling them. --ryan. */ |
| 39 | #if defined(__GNUC__) && defined(__i386__) && defined(SDL_ASSEMBLY_ROUTINES) |
| 40 | void SDL_MixAudio_MMX_S16(char* dst,char* src,unsigned int size,int volume) |
| 41 | { |
| 42 | __asm__ __volatile__ ( |
| 43 | |
| 44 | " movl %3,%%eax\n" /* eax = volume */ |
| 45 | |
| 46 | " movl %2,%%edx\n" /* edx = size */ |
| 47 | |
| 48 | " shrl $4,%%edx\n" /* process 16 bytes per iteration = 8 samples */ |
| 49 | |
| 50 | " jz .endS16\n" |
| 51 | |
| 52 | " pxor %%mm0,%%mm0\n" |
| 53 | |
| 54 | " movd %%eax,%%mm0\n" |
| 55 | " movq %%mm0,%%mm1\n" |
| 56 | " psllq $16,%%mm0\n" |
| 57 | " por %%mm1,%%mm0\n" |
| 58 | " psllq $16,%%mm0\n" |
| 59 | " por %%mm1,%%mm0\n" |
| 60 | " psllq $16,%%mm0\n" |
| 61 | " por %%mm1,%%mm0\n" /* mm0 = vol|vol|vol|vol */ |
| 62 | |
| 63 | ".align 8\n" |
| 64 | " .mixloopS16:\n" |
| 65 | |
| 66 | " movq (%1),%%mm1\n" /* mm1 = a|b|c|d */ |
| 67 | |
| 68 | " movq %%mm1,%%mm2\n" /* mm2 = a|b|c|d */ |
| 69 | |
| 70 | " movq 8(%1),%%mm4\n" /* mm4 = e|f|g|h */ |
| 71 | |
| 72 |