Mercurial > sdl-ios-xcode
view src/video/SDL_memops.h @ 689:5bb080d35049
Date: Tue, 19 Aug 2003 17:57:00 +0200
From: Stephane Marchesin
Subject: Re: [SDL] [patch] MMX alpha blit patches with MMX detection
I think everything is correct now. I've done as much testing as I could,
but some real-world testing wouldn't hurt, I think.
The patch is here : http://icps.u-strasbg.fr/~marchesin/sdl_mmxblit.patch
If you do byte-by-byte comparison of the output between C and MMX
functions, you'll notice that the results for 555 and 565 RGB alpha
blits aren't exactly the same. This is because MMX functions for 555 and
565 RGB have an higher accuracy. If you want the exact same behaviour
that's possible by masking the three lower alpha bits in the MMX
functions. Just ask !
I removed one MMX function because after I fixed it to match its C
equivalent, it revealed to be slower than the C version on a PIII
(although a bit faster on an Athlon XP).
I've also added MMX and PIII replacements for SDL_memcpy. Those provide
some speed up in testvidinfo -benchmark (at least for me, under linux &
X11).
author | Sam Lantinga <slouken@libsdl.org> |
---|---|
date | Fri, 22 Aug 2003 05:51:19 +0000 |
parents | f6ffac90895c |
children | b8d311d90021 |
line wrap: on
line source
/* SDL - Simple DirectMedia Layer Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002 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 */ #ifdef SAVE_RCSID static char rcsid = "@(#) $Id$"; #endif #ifndef _SDL_memops_h #define _SDL_memops_h /* System dependent optimized memory manipulation routines: */ #include <string.h> #if defined(__GNUC__) && defined(i386) /* Thanks to Brennan "Bas" Underwood, for the inspiration. :) */ #define SDL_memcpy(dst, src, len) \ do { \ int u0, u1, u2; \ __asm__ __volatile__ ( \ "cld\n\t" \ "rep ; movsl\n\t" \ "testb $2,%b4\n\t" \ "je 1f\n\t" \ "movsw\n" \ "1:\ttestb $1,%b4\n\t" \ "je 2f\n\t" \ "movsb\n" \ "2:" \ : "=&c" (u0), "=&D" (u1), "=&S" (u2) \ : "0" ((unsigned)(len)/4), "q" (len), "1" (dst),"2" (src) \ : "memory" ); \ } while(0) #define SDL_memcpy4(dst, src, len) \ do { \ int ecx, edi, esi; \ __asm__ __volatile__ ( \ "cld\n\t" \ "rep ; movsl" \ : "=&c" (ecx), "=&D" (edi), "=&S" (esi) \ : "0" ((unsigned)(len)), "1" (dst), "2" (src) \ : "memory" ); \ } while(0) #define SDL_revcpy(dst, src, len) \ do { \ int u0, u1, u2; \ char *dstp = (char *)(dst); \ char *srcp = (char *)(src); \ int n = (len); \ if ( n >= 4 ) { \ __asm__ __volatile__ ( \ "std\n\t" \ "rep ; movsl\n\t" \ : "=&c" (u0), "=&D" (u1), "=&S" (u2) \ : "0" (n >> 2), \ "1" (dstp+(n-4)), "2" (srcp+(n-4)) \ : "memory" ); \ } \ switch (n & 3) { \ case 3: dstp[2] = srcp[2]; \ case 2: dstp[1] = srcp[1]; \ case 1: dstp[0] = srcp[0]; \ break; \ default: \ break; \ } \ } while(0) #define SDL_memmove(dst, src, len) \ do { \ if ( (dst) < (src) ) { \ SDL_memcpy((dst), (src), (len)); \ } else { \ SDL_revcpy((dst), (src), (len)); \ } \ } while(0) #define SDL_memset4(dst, val, len) \ do { \ int u0, u1, u2; \ __asm__ __volatile__ ( \ "cld\n\t" \ "rep ; stosl\n\t" \ : "=&D" (u0), "=&a" (u1), "=&c" (u2) \ : "0" (dst), "1" (val), "2" ((Uint32)(len)) \ : "memory" ); \ } while(0) #endif /* GNU C and x86 */ /* If there are no optimized versions, define the normal versions */ #ifndef SDL_memcpy #define SDL_memcpy(dst, src, len) memcpy(dst, src, len) #endif #ifndef SDL_memcpy4 #define SDL_memcpy4(dst, src, len) memcpy(dst, src, (len) << 2) #endif #ifndef SDL_revcpy #define SDL_revcpy(dst, src, len) memmove(dst, src, len) #endif #ifndef SDL_memset4 #define SDL_memset4(dst, val, len) \ do { \ unsigned _count = (len); \ unsigned _n = (_count + 3) / 4; \ Uint32 *_p = (Uint32 *)(dst); \ Uint32 _val = (val); \ switch (_count % 4) { \ case 0: do { *_p++ = _val; \ case 3: *_p++ = _val; \ case 2: *_p++ = _val; \ case 1: *_p++ = _val; \ } while ( --_n ); \ } \ } while(0) #endif #endif /* _SDL_memops_h */