Mercurial > sdl-ios-xcode

view src/audio/SDL_mixer_m68k.c @ 1542:a8bf1aa21020

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Fixed bug #15 SDL_blit_A.mmx-speed.patch.txt -- Speed improvements and a bugfix for the current GCC inline mmx asm code: - Changed some ops and removed some resulting useless ones. - Added some instruction parallelism (some gain) The resulting speed on my Xeon improved upto 35% depending on the function (measured in fps). - Fixed a bug where BlitRGBtoRGBSurfaceAlphaMMX() was setting the alpha component on the destination surfaces (to opaque-alpha) even when the surface had none. SDL_blit_A.mmx-msvc.patch.txt -- MSVC mmx intrinsics version of the same GCC asm code. MSVC compiler tries to parallelize the code and to avoid register stalls, but does not always do a very good job. Per-surface blending MSVC functions run quite a bit faster than their pure-asm counterparts (upto 55% faster for 16bit ones), but the per-pixel blending runs somewhat slower than asm. - BlitRGBtoRGBSurfaceAlphaMMX and BlitRGBtoRGBPixelAlphaMMX (and all variants) can now also handle formats other than (A)RGB8888. Formats like RGBA8888 and some quite exotic ones are allowed -- like RAGB8888, or actually anything having channels aligned on 8bit boundary and full 8bit alpha (for per-pixel alpha blending). The performance cost of this change is virtually 0 for per-surface alpha blending (no extra ops inside the loop) and a single non-MMX op inside the loop for per-pixel blending. In testing, the per-pixel alpha blending takes a ~2% performance hit, but it still runs much faster than the current code in CVS. If necessary, a separate function with this functionality can be made. This code requires Processor Pack for VC6.
author Sam Lantinga <slouken@libsdl.org>
date Wed, 15 Mar 2006 15:39:29 +0000
parents d910939febfa
children 782fd950bd46 c121d94672cb a1b03ba2fcd0
line wrap: on
line source

/*
    SDL - Simple DirectMedia Layer
    Copyright (C) 1997-2004 Sam Lantinga

    This library is free software; you can redistribute it and/or
    modify it under the terms of the GNU Library General Public
    License as published by the Free Software Foundation; either
    version 2 of the License, or (at your option) any later version.

    This library is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
    Library General Public License for more details.

    You should have received a copy of the GNU Library General Public
    License along with this library; if not, write to the Free
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA

    Sam Lantinga
    slouken@libsdl.org
*/
#include "SDL_config.h"

/*
	m68k assembly mix routines

	Patrice Mandin
*/

#if defined(__M68000__) && defined(__GNUC__)
void SDL_MixAudio_m68k_U8(char* dst, char* src, long len, long volume, char* mix8)
{
    __asm__ __volatile__ (

	"tstl	%2\n"
"	beqs	stoploop_u8\n"
"mixloop_u8:\n"

	/* Mix a sample */

"	moveq	#0,%%d0\n"
"	moveq	#0,%%d1\n"

"	moveb	%1@+,%%d0\n"	/* d0 = *src++ */
"	sub	#128,%%d0\n"	/* d0 -= 128 */
"	muls	%3,%%d0\n"	/* d0 *= volume (0<=volume<=128) */
"	moveb	%0@,%%d1\n"	/* d1 = *dst */
"	asr	#7,%%d0\n"	/* d0 /= 128 (SDL_MIX_MAXVOLUME) */
"	add	#128,%%d0\n"	/* d0 += 128 */

"	add	%%d1,%%d0\n"

"	moveb	%4@(%%d0:w),%0@+\n"

	/* Loop till done */

"	subql	#1,%2\n"
"	bhis	mixloop_u8\n"
"stoploop_u8:\n"

	 : /* no return value */
	 : /* input */
	 	"a"(dst), "a"(src), "d"(len), "d"(volume), "a"(mix8)	
	 : /* clobbered registers */
	 	"d0", "d1", "cc", "memory" 
	 );
}

void SDL_MixAudio_m68k_S8(char* dst, char* src, long len, long volume)
{
    __asm__ __volatile__ (

	"tstl	%2\n"
"	beqs	stoploop_s8\n"
"	moveq	#-128,%%d2\n"
"	moveq	#127,%%d3\n"
"mixloop_s8:\n"

	/* Mix a sample */

"	moveq	#0,%%d0\n"
"	moveq	#0,%%d1\n"

"	moveb	%1@+,%%d0\n"	/* d0 = *src++ */
"	muls	%3,%%d0\n"	/* d0 *= volume (0<=volume<=128) */
"	moveb	%0@,%%d1\n"	/* d1 = *dst */
"	asr	#7,%%d0\n"	/* d0 /= 128 (SDL_MIX_MAXVOLUME) */

"	add	%%d1,%%d0\n"

"	cmp	%%d2,%%d0\n"
"	bges	lower_limit_s8\n"
"	move	%%d2,%%d0\n"
"lower_limit_s8:\n"

"	cmp	%%d3,%%d0\n"
"	bles	upper_limit_s8\n"
"	move	%%d3,%%d0\n"
"upper_limit_s8:\n"
"	moveb	%%d0,%0@+\n"

	/* Loop till done */

"	subql	#1,%2\n"
"	bhis	mixloop_s8\n"
"stoploop_s8:\n"

	 : /* no return value */
	 : /* input */
	 	"a"(dst), "a"(src), "d"(len), "d"(volume)	
	 : /* clobbered registers */
	 	"d0", "d1", "d2", "d3", "cc", "memory" 
	 );
}

void SDL_MixAudio_m68k_S16MSB(short* dst, short* src, long len, long volume)
{
    __asm__ __volatile__ (

	"tstl	%2\n"
"	beqs	stoploop_s16msb\n"
"	movel	#-32768,%%d2\n"
"	movel	#32767,%%d3\n"
"	lsrl	#1,%2\n"
"mixloop_s16msb:\n"

	/* Mix a sample */

"	move	%1@+,%%d0\n"	/* d0 = *src++ */
"	muls	%3,%%d0\n"	/* d0 *= volume (0<=volume<=128) */
"	move	%0@,%%d1\n"	/* d1 = *dst */
"	extl	%%d1\n"		/* extend d1 to 32 bits */
"	asrl	#7,%%d0\n"	/* d0 /= 128 (SDL_MIX_MAXVOLUME) */

"	addl	%%d1,%%d0\n"

"	cmpl	%%d2,%%d0\n"
"	bges	lower_limit_s16msb\n"
"	move	%%d2,%%d0\n"
"lower_limit_s16msb:\n"

"	cmpl	%%d3,%%d0\n"
"	bles	upper_limit_s16msb\n"
"	move	%%d3,%%d0\n"
"upper_limit_s16msb:\n"
"	move	%%d0,%0@+\n"

	/* Loop till done */

"	subql	#1,%2\n"
"	bhis	mixloop_s16msb\n"
"stoploop_s16msb:\n"

	 : /* no return value */
	 : /* input */
	 	"a"(dst), "a"(src), "d"(len), "d"(volume)	
	 : /* clobbered registers */
	 	"d0", "d1", "d2", "d3", "cc", "memory" 
	 );
}

void SDL_MixAudio_m68k_S16LSB(short* dst, short* src, long len, long volume)
{
    __asm__ __volatile__ (

	"tstl	%2\n"
"	beqs	stoploop_s16lsb\n"
"	movel	#-32768,%%d2\n"
"	movel	#32767,%%d3\n"
"	lsrl	#1,%2\n"
"mixloop_s16lsb:\n"

	/* Mix a sample */

"	move	%1@+,%%d0\n"	/* d0 = *src++ */
"	rorw	#8,%%d0\n"
"	muls	%3,%%d0\n"	/* d0 *= volume (0<=volume<=128) */
"	move	%0@,%%d1\n"	/* d1 = *dst */
"	rorw	#8,%%d1\n"
"	extl	%%d1\n"		/* extend d1 to 32 bits */
"	asrl	#7,%%d0\n"	/* d0 /= 128 (SDL_MIX_MAXVOLUME) */

"	addl	%%d1,%%d0\n"

"	cmpl	%%d2,%%d0\n"
"	bges	lower_limit_s16lsb\n"
"	move	%%d2,%%d0\n"
"lower_limit_s16lsb:\n"

"	cmpl	%%d3,%%d0\n"
"	bles	upper_limit_s16lsb\n"
"	move	%%d3,%%d0\n"
"upper_limit_s16lsb:\n"
"	rorw	#8,%%d0\n"
"	move	%%d0,%0@+\n"

	/* Loop till done */

"	subql	#1,%2\n"
"	bhis	mixloop_s16lsb\n"
"stoploop_s16lsb:\n"

	 : /* no return value */
	 : /* input */
	 	"a"(dst), "a"(src), "d"(len), "d"(volume)	
	 : /* clobbered registers */
	 	"d0", "d1", "d2", "d3", "cc", "memory" 
	 );
}
#endif